Sensors

Research

Jump to: Review

12 pages, 2014 KiB

Open AccessArticle

Fault Restoration of Six-Axis Force/Torque Sensor Based on Optimized Back Propagation Networks

by Xuhao Li, Lifu Gao, Xiaohui Li, Huibin Cao and Yuxiang Sun

Sensors 2022, 22(17), 6691; https://doi.org/10.3390/s22176691 - 4 Sep 2022

Cited by 2 | Viewed by 2064

Abstract

Six-axis force/torque sensors are widely installed in manipulators to help researchers achieve closed-loop control. When manipulators work in comic space and deep sea, the adverse ambient environment will cause various degrees of damage to F/T sensors. If the disability of one or two [...] Read more.

Six-axis force/torque sensors are widely installed in manipulators to help researchers achieve closed-loop control. When manipulators work in comic space and deep sea, the adverse ambient environment will cause various degrees of damage to F/T sensors. If the disability of one or two dimensions is restored by self-restoration methods, the robustness and practicality of F/T sensors can be considerably enhanced. The coupling effect is an important characteristic of multi-axis F/T sensors, which implies that all dimensions of F/T sensors will influence each other. We can use this phenomenon to speculate the broken dimension by other regular dimensions. Back propagation neural network (BPNN) is a classical feedforward neural network, which consists of several layers and adopts the back-propagation algorithm to train networks. Hyperparameters of BPNN cannot be updated by training, but they impact the network performance directly. Hence, the particle swarm optimization (PSO) algorithm is adopted to tune the hyperparameters of BPNN. In this work, each dimension of a six-axis F/T sensor is regarded as an element in the input vector, and the relationships among six dimensions can be obtained using optimized BPNN. The average MSE of restoring one dimension and two dimensions over the testing data is

1.1693 \times 10^{- 5}

and

3.4205 \times 10^{- 5}

, respectively. Furthermore, the average quote error of one restored dimension and two restored dimensions are

8.800 {\times 10}^{- 3}

and

8.200 {\times 10}^{- 3}

, respectively. The analysis of experimental results illustrates that the proposed fault restoration method based on PSO-BPNN is viable and practical. The F/T sensor restored using the proposed method can reach the original measurement precision. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Graphical abstract

20 pages, 11947 KiB

Open AccessArticle

Infrared Thermography Smart Sensor for the Condition Monitoring of Gearbox and Bearings Faults in Induction Motors

by Alvaro Ivan Alvarado-Hernandez, Israel Zamudio-Ramirez, Arturo Yosimar Jaen-Cuellar, Roque Alfredo Osornio-Rios, Vicente Donderis-Quiles and Jose Alfonso Antonino-Daviu

Sensors 2022, 22(16), 6075; https://doi.org/10.3390/s22166075 - 14 Aug 2022

Cited by 10 | Viewed by 3079

Abstract

The monitoring of machine conditions is very important from the viewpoints of productivity, economic benefits, and maintenance. Several techniques have been proposed in which sensors are the key to providing relevant information to verify the system. Recently, the smart sensor concept is common, [...] Read more.

The monitoring of machine conditions is very important from the viewpoints of productivity, economic benefits, and maintenance. Several techniques have been proposed in which sensors are the key to providing relevant information to verify the system. Recently, the smart sensor concept is common, in which the sensors are integrated with a data processing unit executing dedicated algorithms used to generate meaningful information about the system in situ. Additionally, infrared thermography has gained relevance in monitoring processes, since the new infrared cameras have more resolution, smaller dimensions, reliability, functionality, and lower costs. These units were firstly used as secondary elements in the condition monitoring of machines, but thanks to modern techniques for data processing, the infrared sensors can be used to give a first, or even a direct, diagnosis in a nonintrusive way in industrial applications. Therefore, in this manuscript, the structure and development of an infrared-thermography-based smart sensor for diagnosing faults in the elements associated with induction motors, such as rolling bearings and the gearbox, is described. The smart sensor structure includes five main parts: an infrared primary sensor, a preprocessing module, an image processing module, classification of faults, and a user interface. The infrared primary sensor considers a low-cost micro thermal camera for acquiring the thermal images. The processing modules and the classification module implement the data processing algorithms into digital development boards, enabling smart system characteristics. Finally, the interface module allows the final users to require the smart sensor to perform processing actions and data visualization, with the additional feature that the diagnosis report can be provided by the system. The smart sensor is validated in a real experimental test bench, demonstrating its capabilities in different case studies. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

18 pages, 2480 KiB

Open AccessArticle

Semi-ProtoPNet Deep Neural Network for the Classification of Defective Power Grid Distribution Structures

by Stefano Frizzo Stefenon, Gurmail Singh, Kin-Choong Yow and Alessandro Cimatti

Sensors 2022, 22(13), 4859; https://doi.org/10.3390/s22134859 - 27 Jun 2022

Cited by 36 | Viewed by 3192

Abstract

Power distribution grids are typically installed outdoors and are exposed to environmental conditions. When contamination accumulates in the structures of the network, there may be shutdowns caused by electrical arcs. To improve the reliability of the network, visual inspections of the electrical power [...] Read more.

Power distribution grids are typically installed outdoors and are exposed to environmental conditions. When contamination accumulates in the structures of the network, there may be shutdowns caused by electrical arcs. To improve the reliability of the network, visual inspections of the electrical power system can be carried out; these inspections can be automated using computer vision techniques based on deep neural networks. Based on this need, this paper proposes the Semi-ProtoPNet deep learning model to classify defective structures in the power distribution networks. The Semi-ProtoPNet deep neural network does not perform convex optimization of its last dense layer to maintain the impact of the negative reasoning process on image classification. The negative reasoning process rejects the incorrect classes of an input image; for this reason, it is possible to carry out an analysis with a low number of images that have different backgrounds, which is one of the challenges of this type of analysis. Semi-ProtoPNet achieves an accuracy of 97.22%, being superior to VGG-13, VGG-16, VGG-19, ResNet-34, ResNet-50, ResNet-152, DenseNet-121, DenseNet-161, DenseNet-201, and also models of the same class such as ProtoPNet, NP-ProtoPNet, Gen-ProtoPNet, and Ps-ProtoPNet. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

13 pages, 1716 KiB

Open AccessArticle

Adaptive Contrastive Learning with Label Consistency for Source Data Free Unsupervised Domain Adaptation

by Xuejun Zhao, Rafal Stanislawski, Paolo Gardoni, Maciej Sulowicz, Adam Glowacz, Grzegorz Krolczyk and Zhixiong Li

Sensors 2022, 22(11), 4238; https://doi.org/10.3390/s22114238 - 2 Jun 2022

Cited by 5 | Viewed by 2983

Abstract

Unsupervised domain adaptation, which aims to alleviate the domain shift between source domain and target domain, has attracted extensive research interest; however, this is unlikely in practical application scenarios, which may be due to privacy issues and intellectual rights. In this paper, we [...] Read more.

Unsupervised domain adaptation, which aims to alleviate the domain shift between source domain and target domain, has attracted extensive research interest; however, this is unlikely in practical application scenarios, which may be due to privacy issues and intellectual rights. In this paper, we discuss a more challenging and practical source-free unsupervised domain adaptation, which needs to adapt the source domain model to the target domain without the aid of source domain data. We propose label consistent contrastive learning (LCCL), an adaptive contrastive learning framework for source-free unsupervised domain adaptation, which encourages target domain samples to learn class-level discriminative features. Considering that the data in the source domain are unavailable, we introduce the memory bank to store the samples with the same pseudo label output and the samples obtained by clustering, and the trusted historical samples are involved in contrastive learning. In addition, we demonstrate that LCCL is a general framework that can be applied to unsupervised domain adaptation. Extensive experiments on digit recognition and image classification benchmark datasets demonstrate the effectiveness of the proposed method. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

32 pages, 4052 KiB

Open AccessArticle

Fuzzy-Logic-Based Recommendation System for Processing in Condition Monitoring

by Jakub Gorski, Mateusz Heesch, Michal Dziendzikowski and Ziemowit Dworakowski

Sensors 2022, 22(10), 3695; https://doi.org/10.3390/s22103695 - 12 May 2022

Cited by 6 | Viewed by 2265

Abstract

The development of a machine’s condition monitoring system is often a challenging task. This process requires the collection of a sufficiently large dataset on signals from machine operation, context information related to the operation conditions, and the diagnosis experience. The two referred problems [...] Read more.

The development of a machine’s condition monitoring system is often a challenging task. This process requires the collection of a sufficiently large dataset on signals from machine operation, context information related to the operation conditions, and the diagnosis experience. The two referred problems are today relatively easy to solve. The hardest to describe is the diagnosis experience because it is based on imprecise and non-numerical information. However, it is essential to process acquired data to develop a robust monitoring system. This article presents a framework for a system dedicated to recommending processing algorithms for condition monitoring. It includes a database and fuzzy-logic-based modules composed within the system. Based on the contextual knowledge provided by the user, the procedure suggests processing algorithms. This paper presents the evaluation of the proposed agent on two different parallel gearboxes. The results of the system are processing algorithms with assigned model types. The obtained results show that the algorithms recommended by the system achieve a higher accuracy than those selected arbitrarily. The results obtained allow for an average of 5 to 14.5% higher accuracy. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

19 pages, 6161 KiB

Open AccessArticle

A New Fusion Fault Diagnosis Method for Fiber Optic Gyroscopes

by Wanpeng Zhang, Dailin Zhang, Peng Zhang and Lei Han

Sensors 2022, 22(8), 2877; https://doi.org/10.3390/s22082877 - 8 Apr 2022

Cited by 4 | Viewed by 2479

Abstract

The fiber optic gyroscope (FOG) is a high precision inertial navigation device, and it is necessary to ensure its reliability for effective use. However, the extracted fault features are easily distorted due to the interference of vibrations when the FOG is in operation. [...] Read more.

The fiber optic gyroscope (FOG) is a high precision inertial navigation device, and it is necessary to ensure its reliability for effective use. However, the extracted fault features are easily distorted due to the interference of vibrations when the FOG is in operation. In order to minimize the influence of vibrations to the greatest extent, a fusion diagnosis method was proposed in this paper. It extracted features from fault data with Fast Fourier Transform (FFT) and wavelet packet decomposition (WPD), and built a strong diagnostic classifier with a sparse auto encoder (SAE) and a neural network (NN). Then, a fusion neural network model was established based on the diagnostic output probabilities of the two primary classifiers, which improved the diagnostic accuracy and the anti-vibration capability. Then, five fault types of the FOG under random vibration conditions were established. Fault data sets were collected and generated for experimental comparison with other methods. The results showed that the proposed fusion fault diagnosis method could perform effective and robust fault diagnosis for the FOG under vibration conditions with a high diagnostic accuracy. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

16 pages, 1618 KiB

Open AccessArticle

Resilient Consensus Control Design for DC Microgrids against False Data Injection Attacks Using a Distributed Bank of Sliding Mode Observers

by Yousof Barzegari, Jafar Zarei, Roozbeh Razavi-Far, Mehrdad Saif and Vasile Palade

Sensors 2022, 22(7), 2644; https://doi.org/10.3390/s22072644 - 30 Mar 2022

Cited by 15 | Viewed by 2500

Abstract

This paper investigates the problem of false data injection attack (FDIA) detection in microgrids. The grid under study is a DC microgrid with distributed boost converters, where the false data are injected into the voltage data so as to investigate the effect of [...] Read more.

This paper investigates the problem of false data injection attack (FDIA) detection in microgrids. The grid under study is a DC microgrid with distributed boost converters, where the false data are injected into the voltage data so as to investigate the effect of attacks. The proposed algorithm uses a bank of sliding mode observers that estimates the states of the neighbor agents. Each agent estimates the neighboring states and, according to the estimation and communication data, the detection mechanism reveals the presence of FDIA. The proposed control scheme provides resiliency to the system by replacing the conventional consensus rule with attack-resilient ones. In order to evaluate the efficiency of the proposed method, a real-time simulation with eight agents has been performed. Moreover, a verification experimental test with three boost converters has been utilized to confirm the simulation results. It is shown that the proposed algorithm is able to detect FDI attacks and it protects the consensus deviation against FDI attacks. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

23 pages, 5070 KiB

Open AccessArticle

Data-Driven Fault Diagnosis Techniques: Non-Linear Directional Residual vs. Machine-Learning-Based Methods

by Nicholas Cartocci, Marcello R. Napolitano, Francesco Crocetti, Gabriele Costante, Paolo Valigi and Mario L. Fravolini

Sensors 2022, 22(7), 2635; https://doi.org/10.3390/s22072635 - 29 Mar 2022

Cited by 8 | Viewed by 2890

Abstract

Linear dependence of variables is a commonly used assumption in most diagnostic systems for which many robust methodologies have been developed over the years. In case the system nonlinearities are relevant, fault diagnosis methods, relying on the assumption of linearity, might potentially provide [...] Read more.

Linear dependence of variables is a commonly used assumption in most diagnostic systems for which many robust methodologies have been developed over the years. In case the system nonlinearities are relevant, fault diagnosis methods, relying on the assumption of linearity, might potentially provide unsatisfactory results in terms of false alarms and missed detections. In recent years, many authors have proposed machine learning (ML) techniques to improve fault diagnosis performance to mitigate this problem. Although very powerful, these techniques require faulty data samples that are representative of any fault scenario. Additionally, ML techniques suffer from issues related to overfitting and unpredictable performance in regions which are not fully explored in the training phase. This paper proposes a non-linear additive model to characterize the non-linear redundancy relationships among the system signals. Using the multivariate adaptive regression splines (MARS) algorithm, these relationships are identified directly from the data. Next, the non-linear redundancy relationships are linearized to derive a local time-dependent fault signature matrix. The faulty sensor can then be isolated by measuring the angular distance between the column vectors of the fault signature matrix and the primary residual vector. A quantitative analysis of fault isolation and fault estimation performance is performed by exploiting real data from multiple flights of a semi-autonomous aircraft, thus allowing a detailed quantitative comparison with state-of-the-art machine-learning-based fault diagnosis algorithms. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

18 pages, 5160 KiB

Open AccessArticle

Navigating an Automated Driving Vehicle via the Early Fusion of Multi-Modality

by Malik Haris and Adam Glowacz

Sensors 2022, 22(4), 1425; https://doi.org/10.3390/s22041425 - 13 Feb 2022

Cited by 17 | Viewed by 3863

Abstract

The ability of artificial intelligence to drive toward an intended destination is a key component of an autonomous vehicle. Different paradigms are now being employed to address artificial intelligence advancement. On the one hand, modular pipelines break down the driving model into submodels, [...] Read more.

The ability of artificial intelligence to drive toward an intended destination is a key component of an autonomous vehicle. Different paradigms are now being employed to address artificial intelligence advancement. On the one hand, modular pipelines break down the driving model into submodels, such as perception, maneuver planning and control. On the other hand, we used the end-to-end driving method to assign raw sensor data directly to vehicle control signals. The latter is less well-studied but is becoming more popular since it is easier to use. This article focuses on end-to-end autonomous driving, using RGB pictures as the primary sensor input data. The autonomous vehicle is equipped with a camera and active sensors, such as LiDAR and Radar, for safe navigation. Active sensors (e.g., LiDAR) provide more accurate depth information than passive sensors. As a result, this paper examines whether combining the RGB from the camera and active depth information from LiDAR has better results in end-to-end artificial driving than using only a single modality. This paper focuses on the early fusion of multi-modality and demonstrates how it outperforms a single modality using the CARLA simulator. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

20 pages, 2738 KiB

Open AccessArticle

Attention-Based Deep Recurrent Neural Network to Forecast the Temperature Behavior of an Electric Arc Furnace Side-Wall

by Diego F. Godoy-Rojas, Jersson X. Leon-Medina, Bernardo Rueda, Whilmar Vargas, Juan Romero, Cesar Pedraza, Francesc Pozo and Diego A. Tibaduiza

Sensors 2022, 22(4), 1418; https://doi.org/10.3390/s22041418 - 12 Feb 2022

Cited by 11 | Viewed by 3235

Abstract

Structural health monitoring (SHM) in an electric arc furnace is performed in several ways. It depends on the kind of element or variable to monitor. For instance, the lining of these furnaces is made of refractory materials that can be worn out over [...] Read more.

Structural health monitoring (SHM) in an electric arc furnace is performed in several ways. It depends on the kind of element or variable to monitor. For instance, the lining of these furnaces is made of refractory materials that can be worn out over time. Therefore, monitoring the temperatures on the walls and the cooling elements of the furnace is essential for correct structural monitoring. In this work, a multivariate time series temperature prediction was performed through a deep learning approach. To take advantage of data from the last 5 years while not neglecting the initial parts of the sequence in the oldest years, an attention mechanism was used to model time series forecasting using deep learning. The attention mechanism was built on the foundation of the encoder–decoder approach in neural networks. Thus, with the use of an attention mechanism, the long-term dependency of the temperature predictions in a furnace was improved. A warm-up period in the training process of the neural network was implemented. The results of the attention-based mechanism were compared with the use of recurrent neural network architectures to deal with time series data, such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The results of the Average Root Mean Square Error (ARMSE) obtained with the attention-based mechanism were the lowest. Finally, a variable importance study was performed to identify the best variables to train the model. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

23 pages, 6142 KiB

Open AccessArticle

Beam Damage Assessment Using Natural Frequency Shift and Machine Learning

by Nicoleta Gillich, Cristian Tufisi, Christian Sacarea, Catalin V. Rusu, Gilbert-Rainer Gillich, Zeno-Iosif Praisach and Mario Ardeljan

Sensors 2022, 22(3), 1118; https://doi.org/10.3390/s22031118 - 1 Feb 2022

Cited by 33 | Viewed by 4230

Abstract

Damage detection based on modal parameter changes has become popular in the last few decades. Nowadays, there are robust and reliable mathematical relations available to predict natural frequency changes if damage parameters are known. Using these relations, it is possible to create databases [...] Read more.

Damage detection based on modal parameter changes has become popular in the last few decades. Nowadays, there are robust and reliable mathematical relations available to predict natural frequency changes if damage parameters are known. Using these relations, it is possible to create databases containing a large variety of damage scenarios. Damage can be thus assessed by applying an inverse method. The problem is the complexity of the database, especially for structures with more cracks. In this paper, we propose two machine learning methods, namely the random forest (RF), and the artificial neural network (ANN), as search tools. The databases we developed contain damage scenarios for a prismatic cantilever beam with one crack and ideal and non-ideal boundary conditions. The crack assessment was made in two steps. First, a coarse damage location was found from the networks trained for scenarios comprising the whole beam. Afterwards, the assessment was made involving a particular network trained for the segment of the beam on which the crack was previously found. Using the two machine learning methods, we succeeded in estimating the crack location and severity with high accuracy for both simulation and laboratory experiments. Regarding the location of the crack, which was the main goal of the practitioners, the errors were less than 0.6%. Based on these achievements, we concluded that the damage assessment we propose, in conjunction with the machine learning methods, is robust and reliable. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

23 pages, 4913 KiB

Open AccessArticle

Intelligent Fault Diagnosis Framework for Modular Multilevel Converters in HVDC Transmission

by Hosameldin O. A. Ahmed, Yuexiao Yu, Qinghua Wang, Mohamed Darwish and Asoke K. Nandi

Sensors 2022, 22(1), 362; https://doi.org/10.3390/s22010362 - 4 Jan 2022

Cited by 8 | Viewed by 3001

Abstract

Open circuit failure mode in insulated-gate bipolar transistors (IGBT) is one of the most common faults in modular multilevel converters (MMCs). Several techniques for MMC fault diagnosis based on threshold parameters have been proposed, but very few studies have considered artificial intelligence (AI) [...] Read more.

Open circuit failure mode in insulated-gate bipolar transistors (IGBT) is one of the most common faults in modular multilevel converters (MMCs). Several techniques for MMC fault diagnosis based on threshold parameters have been proposed, but very few studies have considered artificial intelligence (AI) techniques. Using thresholds has the difficulty of selecting suitable threshold values for different operating conditions. In addition, very little attention has been paid to the importance of developing fast and accurate techniques for the real-life application of open-circuit failures of IGBT fault diagnosis. To achieve high classification accuracy and reduced computation time, a fault diagnosis framework with a combination of the AC-side three-phase current, and the upper and lower bridges’ currents of the MMCs to automatically classify health conditions of MMCs is proposed. In this framework, the principal component analysis (PCA) is used for feature extraction. Then, two classification algorithms—multiclass support vector machine (SVM) based on error-correcting output codes (ECOC) and multinomial logistic regression (MLR)—are used for classification. The effectiveness of the proposed framework is validated by a two-terminal simulation model of the MMC-high-voltage direct current (HVDC) transmission power system using PSCAD/EMTDC software. The simulation results demonstrate that the proposed framework is highly effective in diagnosing the health conditions of MMCs compared to recently published results. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

17 pages, 11672 KiB

Open AccessArticle

Utilizing SVD and VMD for Denoising Non-Stationary Signals of Roller Bearings

by Qinghua Wang, Lijuan Wang, Hongtao Yu, Dong Wang and Asoke K. Nandi

Sensors 2022, 22(1), 195; https://doi.org/10.3390/s22010195 - 28 Dec 2021

Cited by 30 | Viewed by 3254

Abstract

In view of the fact that vibration signals of rolling bearings are much contaminated by noise in the early failure period, this paper presents a new denoising SVD-VMD method by combining singular value decomposition (SVD) and variational mode decomposition (VMD). SVD is used [...] Read more.

In view of the fact that vibration signals of rolling bearings are much contaminated by noise in the early failure period, this paper presents a new denoising SVD-VMD method by combining singular value decomposition (SVD) and variational mode decomposition (VMD). SVD is used to determine the structure of the underlying model, which is referred to as signal and noise subspaces, and VMD is used to decompose the original signal into several band-limited modes. Then the effective components are selected from these modes to reconstruct the denoised signal according to the difference spectrum (DS) of singular values and kurtosis values. Simulated signals and experimental signals of roller bearing faults have been analyzed using this proposed method and compared with SVD-DS. The results demonstrate that the proposed method can effectively retain the useful signals and denoise the bearing signals in extremely noisy backgrounds. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

21 pages, 8706 KiB

Open AccessArticle

Fuzzy Logic in Aircraft Onboard Systems Reliability Evaluation—A New Approach

by Andrzej Żyluk, Konrad Kuźma, Norbert Grzesik, Mariusz Zieja and Justyna Tomaszewska

Sensors 2021, 21(23), 7913; https://doi.org/10.3390/s21237913 - 27 Nov 2021

Cited by 21 | Viewed by 3227

Abstract

This paper is a continuation of research into the possibility of using fuzzy logic to assess the reliability of a selected airborne system. The research objectives include an analysis of statistical data, a reliability analysis in the classical approach, a reliability analysis in [...] Read more.

This paper is a continuation of research into the possibility of using fuzzy logic to assess the reliability of a selected airborne system. The research objectives include an analysis of statistical data, a reliability analysis in the classical approach, a reliability analysis in the fuzzy set theory approach, and a comparison of the obtained results. The system selected for the investigation was the aircraft gun system. In the first step, after analysing the statistical (operational) data, reliability was assessed using a classical probabilistic model in which, on the basis of the Weibull distribution fitted to the operational data, the basic reliability characteristics were determined, including the reliability function for the selected aircraft system. The second reliability analysis, in a fuzzy set theory approach, was conducted using a Mamdani Type Fuzzy Logic Controller developed in the Matlab software with the Fuzzy Logic Toolbox package. The controller was designed on the basis of expert knowledge obtained by a survey. Based on the input signals in the form of equipment operation time (number of flying hours), number of shots performed (shots), and the state of equipment corrosion (corrosion), the controller determines the reliability of air armament. The final step was to compare the results obtained from two methods: classical probabilistic model and fuzzy logic. The authors have proved that the reliability model using fuzzy logic can be used to assess the reliability of aircraft airborne systems. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

16 pages, 103608 KiB

Open AccessArticle

Thermographic Fault Diagnosis of Ventilation in BLDC Motors

by Adam Glowacz

Sensors 2021, 21(21), 7245; https://doi.org/10.3390/s21217245 - 30 Oct 2021

Cited by 82 | Viewed by 3508

Abstract

Thermographic fault diagnosis of ventilation in BLDC (brushless DC) motors is described. The following states of BLDC motors were analyzed: a healthy BLDC motor running at 1450 rpm, a healthy BLDC motor at 2100 rpm, blocked ventilation of the BLDC motor at 1450 [...] Read more.

Thermographic fault diagnosis of ventilation in BLDC (brushless DC) motors is described. The following states of BLDC motors were analyzed: a healthy BLDC motor running at 1450 rpm, a healthy BLDC motor at 2100 rpm, blocked ventilation of the BLDC motor at 1450 rpm, blocked ventilation of the BLDC motor at 2100 rpm, healthy clipper, and blocked ventilation of the clipper. A feature extraction method called the Common Part of Arithmetic Mean of Thermographic Images (CPoAMoTI) was proposed. Test thermal images were analyzed successfully. The developed method, CPoAMoTI is useful for industry and society. Electric cars, trains, fans, clippers, computers, cordless power tools can be diagnosed using the developed method. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

18 pages, 6632 KiB

Open AccessArticle

CNN-LSTM-Based Prognostics of Bidirectional Converters for Electric Vehicles’ Machine

by Gabriel Rojas-Dueñas, Jordi-Roger Riba and Manuel Moreno-Eguilaz

Sensors 2021, 21(21), 7079; https://doi.org/10.3390/s21217079 - 26 Oct 2021

Cited by 11 | Viewed by 2385

Abstract

This paper proposes an approach to estimate the state of health of DC-DC converters that feed the electrical system of an electric vehicle. They have an important role in providing a smooth and rectified DC voltage to the electric machine. Thus, it is [...] Read more.

This paper proposes an approach to estimate the state of health of DC-DC converters that feed the electrical system of an electric vehicle. They have an important role in providing a smooth and rectified DC voltage to the electric machine. Thus, it is important to diagnose the actual status and predict the future performance of the converter and specifically of the electrolytic capacitors, in order to avoid malfunctioning and failures, since it is known they have the highest failure rates among power converter components. To this end, accelerated aging tests of the electrolytic capacitors are performed by applying an electrical overstress. The gathered data are used to train a CNN-LSTM model that is capable of predicting the future values of the capacitance and the equivalent series resistance (ESR) of the electrolytic capacitor. This model can be used to estimate the remaining useful life of the device, thus, increasing the reliability of the system and ensuring an adequate operating condition of the electric motor. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

20 pages, 5576 KiB

Open AccessArticle

Analysis of Graphomotor Tests with Machine Learning Algorithms for an Early and Universal Pre-Diagnosis of Dysgraphia

by Louis Devillaine, Raphaël Lambert, Jérôme Boutet, Saifeddine Aloui, Vincent Brault, Caroline Jolly and Etienne Labyt

Sensors 2021, 21(21), 7026; https://doi.org/10.3390/s21217026 - 23 Oct 2021

Cited by 18 | Viewed by 4027

Abstract

Five to ten percent of school-aged children display dysgraphia, a neuro-motor disorder that causes difficulties in handwriting, which becomes a handicap in the daily life of these children. Yet, the diagnosis of dysgraphia remains tedious, subjective and dependent to the language besides stepping [...] Read more.

Five to ten percent of school-aged children display dysgraphia, a neuro-motor disorder that causes difficulties in handwriting, which becomes a handicap in the daily life of these children. Yet, the diagnosis of dysgraphia remains tedious, subjective and dependent to the language besides stepping in late in the schooling. We propose a pre-diagnosis tool for dysgraphia using drawings called graphomotor tests. These tests are recorded using graphical tablets. We evaluate several machine-learning models and compare them to build this tool. A database comprising 305 children from the region of Grenoble, including 43 children with dysgraphia, has been established and diagnosed by specialists using the BHK test, which is the gold standard for the diagnosis of dysgraphia in France. We performed tests of classification by extracting, correcting and selecting features from the raw data collected with the tablets and achieved a maximum accuracy of 73% with cross-validation for three models. These promising results highlight the relevance of graphomotor tests to diagnose dysgraphia earlier and more broadly. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

29 pages, 15314 KiB

Open AccessArticle

Big Machinery Data Preprocessing Methodology for Data-Driven Models in Prognostics and Health Management

by Sergio Cofre-Martel, Enrique Lopez Droguett and Mohammad Modarres

Sensors 2021, 21(20), 6841; https://doi.org/10.3390/s21206841 - 14 Oct 2021

Cited by 29 | Viewed by 4893

Abstract

Sensor monitoring networks and advances in big data analytics have guided the reliability engineering landscape to a new era of big machinery data. Low-cost sensors, along with the evolution of the internet of things and industry 4.0, have resulted in rich databases that [...] Read more.

Sensor monitoring networks and advances in big data analytics have guided the reliability engineering landscape to a new era of big machinery data. Low-cost sensors, along with the evolution of the internet of things and industry 4.0, have resulted in rich databases that can be analyzed through prognostics and health management (PHM) frameworks. Several data-driven models (DDMs) have been proposed and applied for diagnostics and prognostics purposes in complex systems. However, many of these models are developed using simulated or experimental data sets, and there is still a knowledge gap for applications in real operating systems. Furthermore, little attention has been given to the required data preprocessing steps compared to the training processes of these DDMs. Up to date, research works do not follow a formal and consistent data preprocessing guideline for PHM applications. This paper presents a comprehensive step-by-step pipeline for the preprocessing of monitoring data from complex systems aimed for DDMs. The importance of expert knowledge is discussed in the context of data selection and label generation. Two case studies are presented for validation, with the end goal of creating clean data sets with healthy and unhealthy labels that are then used to train machinery health state classifiers. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

26 pages, 5826 KiB

Open AccessArticle

Remaining Useful Life Prediction from 3D Scan Data with Genetically Optimized Convolutional Neural Networks

by Giovanni Diraco, Pietro Siciliano and Alessandro Leone

Sensors 2021, 21(20), 6772; https://doi.org/10.3390/s21206772 - 12 Oct 2021

Cited by 8 | Viewed by 2665

Abstract

In the current industrial landscape, increasingly pervaded by technological innovations, the adoption of optimized strategies for asset management is becoming a critical key success factor. Among the various strategies available, the “Prognostics and Health Management” strategy is able to support maintenance management decisions [...] Read more.

In the current industrial landscape, increasingly pervaded by technological innovations, the adoption of optimized strategies for asset management is becoming a critical key success factor. Among the various strategies available, the “Prognostics and Health Management” strategy is able to support maintenance management decisions more accurately, through continuous monitoring of equipment health and “Remaining Useful Life” forecasting. In the present study, convolutional neural network-based deep neural network techniques are investigated for the remaining useful life prediction of a punch tool, whose degradation is caused by working surface deformations during the machining process. Surface deformation is determined using a 3D scanning sensor capable of returning point clouds with micrometric accuracy during the operation of the punching machine, avoiding both downtime and human intervention. The 3D point clouds thus obtained are transformed into bidimensional image-type maps, i.e., maps of depths and normal vectors, to fully exploit the potential of convolutional neural networks for extracting features. Such maps are then processed by comparing 15 genetically optimized architectures with the transfer learning of 19 pretrained models, using a classic machine learning approach, i.e., support vector regression, as a benchmark. The achieved results clearly show that, in this specific case, optimized architectures provide performance far superior (MAPE = 0.058) to that of transfer learning, which, instead, remains at a lower or slightly higher level (MAPE = 0.416) than support vector regression (MAPE = 0.857). Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

25 pages, 2691 KiB

Open AccessArticle

On the Importance of Characterizing Virtual PMUs for Hardware-in-the-Loop and Digital Twin Applications

by Alessandro Mingotti, Federica Costa, Diego Cavaliere, Lorenzo Peretto and Roberto Tinarelli

Sensors 2021, 21(18), 6133; https://doi.org/10.3390/s21186133 - 13 Sep 2021

Cited by 8 | Viewed by 3232

Abstract

In recent years, the introduction of real-time simulators (RTS) has changed the way of researching the power network. In particular, researchers and system operators (SOs) are now capable of simulating the complete network and of making it interact with the real world thanks [...] Read more.

In recent years, the introduction of real-time simulators (RTS) has changed the way of researching the power network. In particular, researchers and system operators (SOs) are now capable of simulating the complete network and of making it interact with the real world thanks to the hardware-in-the-loop (HIL) and digital twin (DT) concepts. Such tools create infinite scenarios in which the network can be tested and virtually monitored to, for example, predict and avoid faults or energy shortages. Furthermore, the real-time monitoring of the network allows estimating the status of the electrical assets and consequently undertake their predictive maintenance. The success of the HIL and DT application relies on the fact that the simulated network elements (cables, generation, accessories, converters, etc.) are correctly modeled and characterized. This is particularly true if the RTS acquisition capabilities are used to enable the HIL and the DT. To this purpose, this work aims at emphasizing the role of a preliminary characterization of the virtual elements inside the RTS system, experimentally verifying how the overall performance is significantly affected by them. To this purpose, a virtual phasor measurement unit (PMU) is tested and characterized to understand its uncertainty contribution. To achieve that, firstly, the characterization of a virtual PMU calibrator is described. Afterward, the virtual PMU calibration is performed, and the results clearly highlight its key role in the overall uncertainty. It is then possible to conclude that the characterization of the virtual elements, or models, inside RTS systems (omitted most of the time) is fundamental to avoid wrong results. The same concepts can be extended to all those fields that exploit HIL and DT capabilities. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

21 pages, 24561 KiB

Open AccessArticle

Evaluation of Wear of Disc Brake Friction Linings and the Variability of the Friction Coefficient on the Basis of Vibroacoustic Signals

by Wojciech Sawczuk, Dariusz Ulbrich, Jakub Kowalczyk and Agnieszka Merkisz-Guranowska

Sensors 2021, 21(17), 5927; https://doi.org/10.3390/s21175927 - 3 Sep 2021

Cited by 17 | Viewed by 3295

Abstract

The article presents the results of friction and vibroacoustic tests of a railway disc brake carried out on a brake stand. The vibration signal generated by the friction linings provides information on their wear and offers evaluation of the braking process, i.e., changes [...] Read more.

The article presents the results of friction and vibroacoustic tests of a railway disc brake carried out on a brake stand. The vibration signal generated by the friction linings provides information on their wear and offers evaluation of the braking process, i.e., changes in the average friction coefficient. The algorithm presents simple regression linear and non-linear models for the thickness of the friction linings and the average coefficient of friction based on the effective value of vibration acceleration. The vibration acceleration signals were analyzed in the amplitude and frequency domains. In both cases, satisfactory values of the dynamics of changes above 6 dB were obtained. In the case of spectral analysis using a mid-band filter, more accurate models of the friction lining thickness and the average coefficient of friction were obtained. However, the spectral analysis does not allow the estimation of the lining thickness and the friction coefficient at low braking speeds, i.e., 50 and 80 km/h. The analysis of amplitudes leads to the determination of models in the entire braking speed range from 50 to 200 km/h, despite the lower accuracy compared to the model, based on the spectral analysis. The vibroacoustic literature presents methods of diagnosis of the wear of various machine elements such as bearings or friction linings, based on amplitude or frequency analysis of vibrations. These signal analysis methods have their limitations with regard to their scope of use and the accuracy of diagnosis. There are no cases of simultaneous use of different methods of analysis. This article presents the simultaneous application of the amplitude and frequency methods in the analysis of vibroacoustic signals generated by brake linings. Moreover, algorithms for assessing the wear of friction linings and the average coefficient of friction were presented. The algorithm enables determination of the time at which the friction linings should be replaced with new ones. The final algorithm analyzes the vibration acceleration signals using both amplitude analysis for low braking speeds, as well as spectral analysis for medium and high braking speeds. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

30 pages, 19628 KiB

Open AccessArticle

Towards Interpretable Deep Learning: A Feature Selection Framework for Prognostics and Health Management Using Deep Neural Networks

by Joaquín Figueroa Barraza, Enrique López Droguett and Marcelo Ramos Martins

Sensors 2021, 21(17), 5888; https://doi.org/10.3390/s21175888 - 1 Sep 2021

Cited by 33 | Viewed by 6210

Abstract

In the last five years, the inclusion of Deep Learning algorithms in prognostics and health management (PHM) has led to a performance increase in diagnostics, prognostics, and anomaly detection. However, the lack of interpretability of these models results in resistance towards their deployment. [...] Read more.

In the last five years, the inclusion of Deep Learning algorithms in prognostics and health management (PHM) has led to a performance increase in diagnostics, prognostics, and anomaly detection. However, the lack of interpretability of these models results in resistance towards their deployment. Deep Learning-based models fall within the accuracy/interpretability tradeoff, which means that their complexity leads to high performance levels but lacks interpretability. This work aims at addressing this tradeoff by proposing a technique for feature selection embedded in deep neural networks that uses a feature selection (FS) layer trained with the rest of the network to evaluate the input features’ importance. The importance values are used to determine which will be considered for deployment of a PHM model. For comparison with other techniques, this paper introduces a new metric called ranking quality score (RQS), that measures how performance evolves while following the corresponding ranking. The proposed framework is exemplified with three case studies involving health state diagnostics and prognostics and remaining useful life prediction. Results show that the proposed technique achieves higher RQS than the compared techniques, while maintaining the same performance level when compared to the same model but without an FS layer. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

27 pages, 4996 KiB

Open AccessArticle

Diagnosis Methodology Based on Deep Feature Learning for Fault Identification in Metallic, Hybrid and Ceramic Bearings

by Juan Jose Saucedo-Dorantes, Francisco Arellano-Espitia, Miguel Delgado-Prieto and Roque Alfredo Osornio-Rios

Sensors 2021, 21(17), 5832; https://doi.org/10.3390/s21175832 - 30 Aug 2021

Cited by 32 | Viewed by 3547

Abstract

Scientific and technological advances in the field of rotatory electrical machinery are leading to an increased efficiency in those processes and systems in which they are involved. In addition, the consideration of advanced materials, such as hybrid or ceramic bearings, are of high [...] Read more.

Scientific and technological advances in the field of rotatory electrical machinery are leading to an increased efficiency in those processes and systems in which they are involved. In addition, the consideration of advanced materials, such as hybrid or ceramic bearings, are of high interest towards high-performance rotary electromechanical actuators. Therefore, most of the diagnosis approaches for bearing fault detection are highly dependent of the bearing technology, commonly focused on the metallic bearings. Although the mechanical principles remain as the basis to analyze the characteristic patterns and effects related to the fault appearance, the quantitative response of the vibration pattern considering different bearing technology varies. In this regard, in this work a novel data-driven diagnosis methodology is proposed based on deep feature learning applied to the diagnosis and identification of bearing faults for different bearing technologies, such as metallic, hybrid and ceramic bearings, in electromechanical systems. The proposed methodology consists of three main stages: first, a deep learning-based model, supported by stacked autoencoder structures, is designed with the ability of self-adapting to the extraction of characteristic fault-related features from different signals that are processed in different domains. Second, in a feature fusion stage, information from different domains is integrated to increase the posterior discrimination capabilities during the condition assessment. Third, the bearing assessment is achieved by a simple softmax layer to compute the final classification results. The achieved results show that the proposed diagnosis methodology based on deep feature learning can be effectively applied to the diagnosis and identification of bearing faults for different bearing technologies, such as metallic, hybrid and ceramic bearings, in electromechanical systems. The proposed methodology is validated in front of two different electromechanical systems and the obtained results validate the adaptability and performance of the proposed approach to be considered as a part of the condition-monitoring strategies where different bearing technologies are involved. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

17 pages, 3786 KiB

Open AccessArticle

Deep-Learning-Based Approach to Anomaly Detection Techniques for Large Acoustic Data in Machine Operation

by Hyojung Ahn and Inchoon Yeo

Sensors 2021, 21(16), 5446; https://doi.org/10.3390/s21165446 - 12 Aug 2021

Cited by 9 | Viewed by 4827

Abstract

As the workforce shrinks, the demand for automatic, labor-saving, anomaly detection technology that can perform maintenance on advanced equipment such as vehicles has been increasing. In a vehicular environment, noise in the cabin, which directly affects users, is considered an important factor in [...] Read more.

As the workforce shrinks, the demand for automatic, labor-saving, anomaly detection technology that can perform maintenance on advanced equipment such as vehicles has been increasing. In a vehicular environment, noise in the cabin, which directly affects users, is considered an important factor in lowering the emotional satisfaction of the driver and/or passengers in the vehicles. In this study, we provide an efficient method that can collect acoustic data, measured using a large number of microphones, in order to detect abnormal operations inside the machine via deep learning in a quick and highly accurate manner. Unlike most current approaches based on Long Short-Term Memory (LSTM) or autoencoders, we propose an anomaly detection (AD) algorithm that can overcome the limitations of noisy measurement and detection system anomalies via noise signals measured inside the mechanical system. These features are utilized to train a variety of anomaly detection models for demonstration in noisy environments with five different errors in machine operation, achieving an accuracy of approximately 90% or more. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

14 pages, 851 KiB

Open AccessArticle

Generative Adversarial Network-Based Scheme for Diagnosing Faults in Cyber-Physical Power Systems

by Hossein Hassani, Roozbeh Razavi-Far, Mehrdad Saif and Vasile Palade

Sensors 2021, 21(15), 5173; https://doi.org/10.3390/s21155173 - 30 Jul 2021

Cited by 9 | Viewed by 2931

Abstract

This paper presents a novel diagnostic framework for distributed power systems that is based on using generative adversarial networks for generating artificial knockoffs in the power grid. The proposed framework makes use of the raw data measurements including voltage, frequency, and phase-angle that [...] Read more.

This paper presents a novel diagnostic framework for distributed power systems that is based on using generative adversarial networks for generating artificial knockoffs in the power grid. The proposed framework makes use of the raw data measurements including voltage, frequency, and phase-angle that are collected from each bus in the cyber-physical power systems. The collected measurements are firstly fed into a feature selection module, where multiple state-of-the-art techniques have been used to extract the most informative features from the initial set of available features. The selected features are inputs to a knockoff generation module, where the generative adversarial networks are employed to generate the corresponding knockoffs of the selected features. The generated knockoffs are then fed into a classification module, in which two different classification models are used for the sake of fault diagnosis. Multiple experiments have been designed to investigate the effect of noise, fault resistance value, and sampling rate on the performance of the proposed framework. The effectiveness of the proposed framework is validated through a comprehensive study on the IEEE 118-bus system. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

24 pages, 4927 KiB

Open AccessArticle

Crack Size Identification for Bearings Using an Adaptive Digital Twin

by Farzin Piltan and Jong-Myon Kim

Sensors 2021, 21(15), 5009; https://doi.org/10.3390/s21155009 - 23 Jul 2021

Cited by 18 | Viewed by 3271

Abstract

In this research, the aim is to investigate an adaptive digital twin algorithm for fault diagnosis and crack size identification in bearings. The main contribution of this research is to design an adaptive digital twin (ADT). The design of the ADT technique is [...] Read more.

In this research, the aim is to investigate an adaptive digital twin algorithm for fault diagnosis and crack size identification in bearings. The main contribution of this research is to design an adaptive digital twin (ADT). The design of the ADT technique is based on two principles: normal signal modeling and estimation of signals. A combination of mathematical and data-driven techniques will be used to model the normal vibration signal. Therefore, in the first step, the normal vibration signal is modeled to increase the reliability of the modeling algorithm in the ADT. Then, to help challenge the complexity and uncertainty, the data-driven method will solve the problems of the mathematically based algorithm. Thus, first, Gaussian process regression is selected, and then, in two steps, we improve its resistance and accuracy by a Laguerre filter and fuzzy logic algorithm. After modeling the vibration signal, the second step is to design the data estimation for ADT. These signals are estimated by an adaptive observer. Therefore, a proportional-integral observer is then combined with the proposed technique for signal modeling. Then, in two stages, its robustness and reliability are strengthened using the Lyapunov-based algorithm and adaptive technique, respectively. After designing the ADT, the residual signals that are the difference between original and estimated signals are obtained. After that, the residual signals are resampled, and the root means square (RMS) signals are extracted from the residual signals. A support vector machine (SVM) is recommended for fault classification and crack size identification. The strength of the proposed technique is tested using the Case Western Reserve University Bearing Dataset (CWRUBD) under diverse torque loads, various motor speeds, and different crack sizes. In terms of fault diagnosis, the average detection accuracy in the proposed scheme is 95.75%. In terms of crack size identification for the roller, inner, and outer faults, the proposed scheme has average detection accuracies of 97.33%, 98.33%, and 98.33%, respectively. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

16 pages, 3332 KiB

Open AccessCommunication

A Novel Feature Extraction and Fault Detection Technique for the Intelligent Fault Identification of Water Pump Bearings

by Muhammad Irfan, Abdullah Saeed Alwadie, Adam Glowacz, Muhammad Awais, Saifur Rahman, Mohammad Kamal Asif Khan, Mohammad Jalalah, Omar Alshorman and Wahyu Caesarendra

Sensors 2021, 21(12), 4225; https://doi.org/10.3390/s21124225 - 20 Jun 2021

Cited by 16 | Viewed by 3770

Abstract

The reliable and cost-effective condition monitoring of the bearings installed in water pumps is a real challenge in the industry. This paper presents a novel strong feature selection and extraction algorithm (SFSEA) to extract fault-related features from the instantaneous power spectrum (IPS). The [...] Read more.

The reliable and cost-effective condition monitoring of the bearings installed in water pumps is a real challenge in the industry. This paper presents a novel strong feature selection and extraction algorithm (SFSEA) to extract fault-related features from the instantaneous power spectrum (IPS). The three features extracted from the IPS using the SFSEA are fed to an extreme gradient boosting (XBG) classifier to reliably detect and classify the minor bearing faults. The experiments performed on a lab-scale test setup demonstrated classification accuracy up to 100%, which is better than the previously reported fault classification accuracies and indicates the effectiveness of the proposed method. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

18 pages, 5927 KiB

Open AccessArticle

Ventilation Diagnosis of Angle Grinder Using Thermal Imaging

by Adam Glowacz

Sensors 2021, 21(8), 2853; https://doi.org/10.3390/s21082853 - 18 Apr 2021

Cited by 147 | Viewed by 5933

Abstract

The paper presents an analysis and classification method to evaluate the working condition of angle grinders by means of infrared (IR) thermography and IR image processing. An innovative method called BCAoMID-F (Binarized Common Areas of Maximum Image Differences—Fusion) is proposed in this paper. [...] Read more.

The paper presents an analysis and classification method to evaluate the working condition of angle grinders by means of infrared (IR) thermography and IR image processing. An innovative method called BCAoMID-F (Binarized Common Areas of Maximum Image Differences—Fusion) is proposed in this paper. This method is used to extract features of thermal images of three angle grinders. The computed features are 1-element or 256-element vectors. Feature vectors are the sum of pixels of matrix V or PCA of matrix V or histogram of matrix V. Three different cases of thermal images were considered: healthy angle grinder, angle grinder with 1 blocked air inlet, angle grinder with 2 blocked air inlets. The classification of feature vectors was carried out using two classifiers: Support Vector Machine and Nearest Neighbor. Total recognition efficiency for 3 classes (TR_AG) was in the range of 98.5–100%. The presented technique is efficient for fault diagnosis of electrical devices and electric power tools. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

19 pages, 9195 KiB

Open AccessArticle

Signal Identification of Gear Vibration in Engine-Gearbox Systems Based on Auto-Regression and Optimized Resonance-Based Signal Sparse Decomposition

by Yuanyuan Huang, Shuiguang Tong, Zheming Tong and Feiyun Cong

Sensors 2021, 21(5), 1868; https://doi.org/10.3390/s21051868 - 7 Mar 2021

Cited by 10 | Viewed by 3383

Abstract

As an essential part of the transmission system, gearboxes are considered as a major source of vibration. Signal identification of gear vibration is necessary for online monitoring of the mechanical systems. However, in engine-gearbox systems, the ignition impact of the engine is strong, [...] Read more.

As an essential part of the transmission system, gearboxes are considered as a major source of vibration. Signal identification of gear vibration is necessary for online monitoring of the mechanical systems. However, in engine-gearbox systems, the ignition impact of the engine is strong, so that the gear vibration is generally submerged. To overcome this issue, the resonance-based signal sparse decomposition (RSSD) method is used in this paper based on different oscillatory behaviors of the gear meshing impact and the engine ignition impact. To improve the accuracy of RSSD under interferences, the meshing frequency energy ratio (MF–ER) index is introduced into RSSD to adaptively choose the decomposition parameters. Before applying the RSSD method, the auto-regression (AR) model is used as a pre-whitening step to eliminate the normal gear meshing vibration, which improves the decomposition performance of RSSD. The effectiveness of the proposed AR-ORSSD (AR-based optimized RSSD) algorithm is tested using both simulated signals and measured vibration signals from an engine-gearbox system in a forklift. Comparisons were made with the RSSD algorithm based on a genetic algorithm. Experimental results indicate that the AR-ORSSD algorithm is superior at identifying gear vibration signals especially when under strong interferences. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

18 pages, 4117 KiB

Open AccessArticle

Wavelet-Prototypical Network Based on Fusion of Time and Frequency Domain for Fault Diagnosis

by Yu Wang, Lei Chen, Yang Liu and Lipeng Gao

Sensors 2021, 21(4), 1483; https://doi.org/10.3390/s21041483 - 20 Feb 2021

Cited by 30 | Viewed by 3325

Abstract

Neural networks for fault diagnosis need enough samples for training, but in practical applications, there are often insufficient samples. In order to solve this problem, we propose a wavelet-prototypical network based on fusion of time and frequency domain (WPNF). The time domain and [...] Read more.

Neural networks for fault diagnosis need enough samples for training, but in practical applications, there are often insufficient samples. In order to solve this problem, we propose a wavelet-prototypical network based on fusion of time and frequency domain (WPNF). The time domain and frequency domain information of the vibration signal can be sent to the model simultaneously to expand the characteristics of the data, a parallel two-channel convolutional structure is proposed to process the information of the signal. After that, a wavelet layer is designed to further extract features. Finally, a prototypical layer is applied to train this network. Experimental results show that the proposed method can accurately identify new classes that have never been used during the training phase when the number of samples in each class is very small, and it is far better than other traditional machine learning models in few-shot scenarios. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

16 pages, 6065 KiB

Open AccessCommunication

Heat Rate Prediction of Combined Cycle Power Plant Using an Artificial Neural Network (ANN) Method

by Yondha Dwika Arferiandi, Wahyu Caesarendra and Herry Nugraha

Sensors 2021, 21(4), 1022; https://doi.org/10.3390/s21041022 - 3 Feb 2021

Cited by 9 | Viewed by 4621

Abstract

Heat rate of a combined cycle power plant (CCPP) is a parameter that is typically used to assess how efficient a power plant is. In this paper, the CCPP heat rate was predicted using an artificial neural network (ANN) method to support maintenance [...] Read more.

Heat rate of a combined cycle power plant (CCPP) is a parameter that is typically used to assess how efficient a power plant is. In this paper, the CCPP heat rate was predicted using an artificial neural network (ANN) method to support maintenance people in monitoring the efficiency of the CCPP. The ANN method used fuel gas heat input (P1), CO₂ percentage (P2), and power output (P3) as input parameters. Approximately 4322 actual operation data are generated from the digital control system (DCS) in a year. These data were used for ANN training and prediction. Seven parameter variations were developed to find the best parameter variation to predict heat rate. The model with one input parameter predicted heat rate with regression R² values of 0.925, 0.005, and 0.995 for P1, P2, and P3. Combining two parameters as inputs increased accuracy with regression R² values of 0.970, 0.994, and 0.984 for P1 + P2, P1 + P3, and P2 + P3, respectively. The ANN model that utilized three parameters as input data had the best prediction heat rate data with a regression R² value of 0.995. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

20 pages, 52583 KiB

Open AccessArticle

An Experimental Study on Condition Diagnosis for Thrust Bearings in Oscillating Water Column Type Wave Power Systems

by Tae-Wook Kim, Jaewon Oh, Cheonhong Min, Se-Yun Hwang, Min-Seok Kim and Jang-Hyun Lee

Sensors 2021, 21(2), 457; https://doi.org/10.3390/s21020457 - 11 Jan 2021

Cited by 7 | Viewed by 2941

Abstract

In order to utilize wave energy, various wave power systems are being actively researched and developed and interest in them is increasing. To maximize the operational efficiency, it is very important to monitor and maintain the fault of components of the system. In [...] Read more.

In order to utilize wave energy, various wave power systems are being actively researched and developed and interest in them is increasing. To maximize the operational efficiency, it is very important to monitor and maintain the fault of components of the system. In recent years, interest in the management cost, high reliability and facility utilization of such systems has increased. In this regard, fault diagnosis technology including fault factor analysis and fault reproduction is drawing attention as an important main technology. Therefore, in this study, to reproduce and monitor the faults of a wave power system, firstly, the failure mode of the system was analyzed using FMEA analysis. Secondly, according to the derived failure mode and effect, the thrust bearing was selected as a target for fault reproduction and a test equipment bench was constructed. Finally, with the vibration data obtained by conducting the tests, the vibration spectrum was analyzed to extract the features of the data for each operating status; the data was classified by applying the three machine learning algorithms: naïve Bayes (NB), k-nearest neighbor (k-NN), and multi-layer perceptron (MLP). The criteria for determining the fault were derived. It is estimated that a more efficient fault diagnosis is possible by using the standard and fault monitoring method of this study. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

26 pages, 7068 KiB

Open AccessArticle

Frequency-Domain Fusing Convolutional Neural Network: A Unified Architecture Improving Effect of Domain Adaptation for Fault Diagnosis

by Xudong Li, Jianhua Zheng, Mingtao Li, Wenzhen Ma and Yang Hu

Sensors 2021, 21(2), 450; https://doi.org/10.3390/s21020450 - 10 Jan 2021

Cited by 21 | Viewed by 4388

Abstract

In recent years, transfer learning has been widely applied in fault diagnosis for solving the problem of inconsistent distribution of the original training dataset and the online-collecting testing dataset. In particular, the domain adaptation method can solve the problem of the unlabeled testing [...] Read more.

In recent years, transfer learning has been widely applied in fault diagnosis for solving the problem of inconsistent distribution of the original training dataset and the online-collecting testing dataset. In particular, the domain adaptation method can solve the problem of the unlabeled testing dataset in transfer learning. Moreover, Convolutional Neural Network (CNN) is the most widely used network among existing domain adaptation approaches due to its powerful feature extraction capability. However, network designing is too empirical, and there is no network designing principle from the frequency domain. In this paper, we propose a unified convolutional neural network architecture from a frequency domain perspective for a domain adaptation named Frequency-domain Fusing Convolutional Neural Network (FFCNN). The method of FFCNN contains two parts, frequency-domain fusing layer and feature extractor. The frequency-domain fusing layer uses convolution operations to filter signals at different frequency bands and combines them into new input signals. These signals are input to the feature extractor to extract features and make domain adaptation. We apply FFCNN for three domain adaptation methods, and the diagnosis accuracy is improved compared to the typical CNN. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

Review

Jump to: Research

20 pages, 498 KiB

Open AccessReview

Detection of Mechanical Failures in Industrial Machines Using Overlapping Acoustic Anomalies: A Systematic Literature Review

by Ahmad Qurthobi, Rytis Maskeliūnas and Robertas Damaševičius

Sensors 2022, 22(10), 3888; https://doi.org/10.3390/s22103888 - 20 May 2022

Cited by 15 | Viewed by 4822

Abstract

One of the most important strategies for preventative factory maintenance is anomaly detection without the need for dedicated sensors for each industrial unit. The implementation of sound-data-based anomaly detection is an unduly complicated process since factory-collected sound data are frequently corrupted and affected [...] Read more.

One of the most important strategies for preventative factory maintenance is anomaly detection without the need for dedicated sensors for each industrial unit. The implementation of sound-data-based anomaly detection is an unduly complicated process since factory-collected sound data are frequently corrupted and affected by ordinary production noises. The use of acoustic methods to detect the irregularities in systems has a long history. Unfortunately, limited reference to the implementation of the acoustic approach could be found in the failure detection of industrial machines. This paper presents a systematic review of acoustic approaches in mechanical failure detection in terms of recent implementations and structural extensions. The 52 articles are selected from IEEEXplore, Science Direct and Springer Link databases following the PRISMA methodology for performing systematic literature reviews. The study identifies the research gaps while considering the potential in responding to the challenges of the mechanical failure detection of industrial machines. The results of this study reveal that the use of acoustic emission is still dominant in the research community. In addition, based on the 52 selected articles, research that discusses failure detection in noisy conditions is still very limited and shows that it will still be a challenge in the future. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

52 pages, 13341 KiB

Open AccessEditor’s ChoiceReview

Non-Destructive Techniques for the Condition and Structural Health Monitoring of Wind Turbines: A Literature Review of the Last 20 Years

by Marco Civera and Cecilia Surace

Sensors 2022, 22(4), 1627; https://doi.org/10.3390/s22041627 - 18 Feb 2022

Cited by 89 | Viewed by 13481

Abstract

A complete surveillance strategy for wind turbines requires both the condition monitoring (CM) of their mechanical components and the structural health monitoring (SHM) of their load-bearing structural elements (foundations, tower, and blades). Therefore, it spans both the civil and mechanical engineering fields. Several [...] Read more.

A complete surveillance strategy for wind turbines requires both the condition monitoring (CM) of their mechanical components and the structural health monitoring (SHM) of their load-bearing structural elements (foundations, tower, and blades). Therefore, it spans both the civil and mechanical engineering fields. Several traditional and advanced non-destructive techniques (NDTs) have been proposed for both areas of application throughout the last years. These include visual inspection (VI), acoustic emissions (AEs), ultrasonic testing (UT), infrared thermography (IRT), radiographic testing (RT), electromagnetic testing (ET), oil monitoring, and many other methods. These NDTs can be performed by human personnel, robots, or unmanned aerial vehicles (UAVs); they can also be applied both for isolated wind turbines or systematically for whole onshore or offshore wind farms. These non-destructive approaches have been extensively reviewed here; more than 300 scientific articles, technical reports, and other documents are included in this review, encompassing all the main aspects of these survey strategies. Particular attention was dedicated to the latest developments in the last two decades (2000–2021). Highly influential research works, which received major attention from the scientific community, are highlighted and commented upon. Furthermore, for each strategy, a selection of relevant applications is reported by way of example, including newer and less developed strategies as well. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

25 pages, 4834 KiB

Open AccessReview

Challenges and Opportunities of System-Level Prognostics

by Seokgoo Kim, Joo-Ho Choi and Nam H. Kim

Sensors 2021, 21(22), 7655; https://doi.org/10.3390/s21227655 - 18 Nov 2021

Cited by 23 | Viewed by 4641

Abstract

Prognostics and health management (PHM) has become an essential function for safe system operation and scheduling economic maintenance. To date, there has been much research and publications on component-level prognostics. In practice, however, most industrial systems consist of multiple components that are interlinked. [...] Read more.

Prognostics and health management (PHM) has become an essential function for safe system operation and scheduling economic maintenance. To date, there has been much research and publications on component-level prognostics. In practice, however, most industrial systems consist of multiple components that are interlinked. This paper aims to provide a review of approaches for system-level prognostics. To achieve this goal, the approaches are grouped into four categories: health index-based, component RUL-based, influenced component-based, and multiple failure mode-based prognostics. Issues of each approach are presented in terms of the target systems and employed algorithms. Two examples of PHM datasets are used to demonstrate how the system-level prognostics should be conducted. Challenges for practical system-level prognostics are also addressed. Full article

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence for Fault Diagnostics and Prognostics

Share This Special Issue

Special Issue Editors

Special Issue Information

Benefits of Publishing in a Special Issue

Published Papers (36 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI