Machines

17 pages, 24201 KiB

Open AccessArticle

An Echo State Network-Based Light Framework for Online Anomaly Detection: An Approach to Using AI at the Edge

by Andrea Bonci, Renat Kermenov, Lorenzo Longarini, Sauro Longhi, Geremia Pompei, Mariorosario Prist and Carlo Verdini

Machines 2024, 12(10), 743; https://doi.org/10.3390/machines12100743 - 21 Oct 2024

Viewed by 601

Abstract

Production efficiency is used to determine the best conditions for manufacturing goods at the lowest possible unit cost. When achieved, production efficiency leads to increased revenues for the manufacturer, enhanced employee safety, and a satisfied customer base. Production efficiency not only measures the [...] Read more.

Production efficiency is used to determine the best conditions for manufacturing goods at the lowest possible unit cost. When achieved, production efficiency leads to increased revenues for the manufacturer, enhanced employee safety, and a satisfied customer base. Production efficiency not only measures the amount of resources that are needed for production but also considers the productivity levels and the state of the production lines. In this context, online anomaly detection (AD) is an important tool for maintaining the reliability of the production ecosystem. With advancements in artificial intelligence and the growing significance of identifying and mitigating anomalies across different fields, approaches based on artificial neural networks facilitate the recognition of intricate types of anomalies by taking into account both temporal and contextual attributes. In this paper, a lightweight framework based on the Echo State Network (ESN) model running at the edge is introduced for online AD. Compared to other AD methods, such as Long Short-Term Memory (LSTM), it achieves superior precision, accuracy, and recall metrics while reducing training time, CO₂ emissions, and the need for high computational resources. The preliminary evaluation of the proposed solution was conducted using a low-resource computing device at the edge of the real production machine through an Industrial Internet of Things (IIoT) smart meter module. The machine used to test the proposed solution was provided by the Italian company SIFIM Srl, which manufactures filter mats for industrial kitchens. Experimental results demonstrate the feasibility of developing an AD method that achieves high accuracy, with the ESN-based framework reaching

85 %

compared to

80.88 %

for the LSTM-based model. Furthermore, this method requires minimal hardware resources, with a training time of

9.5

s compared to

2.100

s for the other model. Full article

(This article belongs to the Special Issue Recent Advances in Robotics, Factory Automation and Intelligent Networked Systems)

► Show Figures

Figure 1

16 pages, 2383 KiB

Open AccessArticle

Efficient Nonlinear Model Predictive Path Tracking Control for Autonomous Vehicle: Investigating the Effects of Vehicle Dynamics Stiffness

by Guozhu Zhu and Weirong Hong

Machines 2024, 12(10), 742; https://doi.org/10.3390/machines12100742 - 21 Oct 2024

Viewed by 599

Abstract

Motion control is one of the three core modules of autonomous driving, and nonlinear model predictive control (NMPC) has recently attracted widespread attention in the field of motion control. Vehicle dynamics equations, as a widely used model, have a significant impact on the [...] Read more.

Motion control is one of the three core modules of autonomous driving, and nonlinear model predictive control (NMPC) has recently attracted widespread attention in the field of motion control. Vehicle dynamics equations, as a widely used model, have a significant impact on the solution efficiency of NMPC due to their stiffness. This paper first theoretically analyzes the limitations on the discretized time step caused by the stiffness of the vehicle dynamics model equations when using existing common numerical methods to solve NMPC, thereby revealing the reasons for the low computational efficiency of NMPC. Then, an A-stable controller based on the finite element orthogonal collocation method is proposed, which greatly expands the stable domain range of the numerical solution process of NMPC, thus achieving the purpose of relaxing the discretized time step restrictions and improving the real-time performance of NMPC. Finally, through CarSim 8.0/Simulink 2021a co-simulation, it is verified that the vehicle dynamics model equations are with great stiffness when the vehicle speed is low, and the proposed controller can enhance the real-time performance of NMPC. As the vehicle speed increases, the stiffness of the vehicle dynamics model equation decreases. In addition to the superior capability in addressing the integration stability issues arising from the stiffness nature of the vehicle dynamics equations, the proposed NMPC controller also demonstrates higher accuracy across a broad range of vehicle speeds. Full article

(This article belongs to the Section Vehicle Engineering)

► Show Figures

Figure 1

16 pages, 9334 KiB

Open AccessArticle

Study on the Effect of Cracks in Diaphragm Couplings on the Dynamic Characteristics of Shaft System

by Meijun Liao, Lan Zhang, Su Nong, Chao Zhang, Rupeng Zhu and Weifang Chen

Machines 2024, 12(10), 741; https://doi.org/10.3390/machines12100741 - 20 Oct 2024

Viewed by 772

Abstract

Diaphragm couplings are prone to developing diaphragm cracks under prolonged high-speed operating conditions, which can lead to degradation in the performance of the transmission system and affect the dynamics of the shafting system. To investigate the effects of diaphragm cracks on the dynamics [...] Read more.

Diaphragm couplings are prone to developing diaphragm cracks under prolonged high-speed operating conditions, which can lead to degradation in the performance of the transmission system and affect the dynamics of the shafting system. To investigate the effects of diaphragm cracks on the dynamics of couplings and the shafting system, a finite element model of a diaphragm coupling with a crack failure is established using ANSYS finite element software to analyze the time-varying characteristics of the diaphragm coupling’s angular and radial stiffness. A shaft dynamics model of the diaphragm coupling with a crack is developed using Timoshenko beam elements to analyze the impact of different crack lengths and locations on the dynamics of the shafting system. The validity of the dynamic model for a diaphragm coupling with a crack is verified through a constant speed experiment conducted on a rotor test bench. The results indicate that diaphragm crack failure causes a change in the periodicity of the time-varying stiffness of the diaphragm coupling, leading to a distinct 2× component appearing in the frequency domain of the transmission shaft system. Full article

(This article belongs to the Section Machine Design and Theory)

► Show Figures

Figure 1

29 pages, 6913 KiB

Open AccessArticle

A Method for Generating Toolpaths in the Manufacturing of Orthosis Molds with a Five-Axis Computer Numerical Control Machine

by Karlo Obrovac, Pero Raos, Tomislav Staroveški and Danko Brezak

Machines 2024, 12(10), 740; https://doi.org/10.3390/machines12100740 - 20 Oct 2024

Viewed by 588

Abstract

This paper proposes a new algorithm for the automatic generation of toolpaths for machining complex geometric positions, such as molds used in orthosis production. The production of individualized orthoses often requires the use of multi-axis machining systems, such as five-axis machines or industrial [...] Read more.

This paper proposes a new algorithm for the automatic generation of toolpaths for machining complex geometric positions, such as molds used in orthosis production. The production of individualized orthoses often requires the use of multi-axis machining systems, such as five-axis machines or industrial robots. Typically, complex and expensive CAD/CAM systems are used to generate toolpaths for these machines, requiring the definition of a machining strategy for each surface. While this approach can achieve a reliable and high-quality machining process, it is very time-consuming and makes it challenging to meet the criteria for rapid production of orthopedic aids. Given that their production is a custom-made process using individual shapes as inputs, the toolpath generation process becomes even more demanding. To address these challenges, this paper proposes an algorithm suitable for the automatic generation of toolpaths for such complex positions. The proposed algorithm has been tested and has proven to be robust and applicable. Full article

(This article belongs to the Section Advanced Manufacturing)

► Show Figures

Figure 1

32 pages, 8047 KiB

Open AccessReview

State-of-the-Art Flocking Strategies for the Collective Motion of Multi-Robots

by Zain Anwar Ali, Eman H. Alkhammash and Raza Hasan

Machines 2024, 12(10), 739; https://doi.org/10.3390/machines12100739 - 20 Oct 2024

Viewed by 770

Abstract

The technological revolution has transformed the area of labor with reference to automation and robotization in various domains. The employment of robots automates these disciplines, rendering beneficial impacts as robots are cost-effective, reliable, accurate, productive, flexible, and safe. Usually, single robots are deployed [...] Read more.

The technological revolution has transformed the area of labor with reference to automation and robotization in various domains. The employment of robots automates these disciplines, rendering beneficial impacts as robots are cost-effective, reliable, accurate, productive, flexible, and safe. Usually, single robots are deployed to accomplish specific tasks. The purpose of this study is to focus on the next step in robot research, collaborative multi-robot systems, through flocking control in particular, improving their self-adaptive and self-learning abilities. This review is conducted to gain extensive knowledge related to swarming, or cluster flocking. The evolution of flocking laws from inception is delineated, swarming/cluster flocking is conceptualized, and the flocking phenomenon in multi-robots is evaluated. The taxonomy of flocking control based on different schemes, structures, and strategies is presented. Flocking control based on traditional and trending approaches, as well as hybrid control paradigms, is observed to elevate the robustness and performance of multi-robot systems for collective motion. Opportunities for deploying robots with flocking control in various domains are also discussed. Some challenges are also explored, requiring future considerations. Finally, the flocking problem is defined and an abstraction of flocking control-based multiple UAVs is presented by leveraging the potentials of various methods. The significance of this review is to inspire academics and practitioners to adopt multi-robot systems with flocking control for swiftly performing tasks and saving energy. Full article

(This article belongs to the Special Issue Advanced Control and Path Planning of Unmanned Aerial Vehicles (UAVs))

► Show Figures

Figure 1

19 pages, 1793 KiB

Open AccessArticle

State of Charge Estimation for Lithium-Ion Battery Based on Fractional-Order Kreisselmeier-Type Adaptive Observer

by Tomoki Murakami and Hiromitsu Ohmori

Machines 2024, 12(10), 738; https://doi.org/10.3390/machines12100738 - 20 Oct 2024

Viewed by 461

Abstract

For the safe and efficient use of lithium-ion batteries, the state of charge (SOC) is a particularly important state variable. In this paper, we propose a method for the online estimation of SOC and model parameters based on a fractional-order equivalent circuit model. [...] Read more.

For the safe and efficient use of lithium-ion batteries, the state of charge (SOC) is a particularly important state variable. In this paper, we propose a method for the online estimation of SOC and model parameters based on a fractional-order equivalent circuit model. Firstly, we constructed a fractional-order battery model that includes pseudo-capacitance and determined the values of the circuit elements offline using the least squares method from actual input–output data based on the driving profile of an automobile. Compared to the integer-order battery model, we confirmed that the proposed fractional-order battery model has higher accuracy. Secondly, we constructed a fractional-order Kreisselmeier-type adaptive observer as an observer that performs state estimation and parameter adjustment simultaneously. Applying the general adaptive law to the battery model results in a redundant design with many adjustable parameters, so we proposed an adaptive law that reduces the number of adjustable parameters without compromising the stability of the observer. The effectiveness of the proposed method was verified through numerical simulations. As a result, the high estimation accuracy and convergence of the proposed adaptive law were confirmed. Full article

(This article belongs to the Special Issue Advanced Engine Energy Saving Technology)

► Show Figures

Figure 1

15 pages, 4121 KiB

Open AccessArticle

Analysis of Influential Parameters in the Dynamic Loading and Stability of the Swing Drive in Hydraulic Excavators

by Vesna Jovanović, Dragoslav Janošević, Dragan Marinković, Nikola Petrović and Radomir Djokić

Machines 2024, 12(10), 737; https://doi.org/10.3390/machines12100737 - 20 Oct 2024

Viewed by 603

Abstract

The proper design and configuration of the swing drive mechanism of a hydraulic excavator are crucial to improve energy consumption and efficiency and ensure operational stability. This paper analyzes the influence of the relationship between the parameters of a hydraulic motor and a [...] Read more.

The proper design and configuration of the swing drive mechanism of a hydraulic excavator are crucial to improve energy consumption and efficiency and ensure operational stability. This paper analyzes the influence of the relationship between the parameters of a hydraulic motor and a reducer, which form the integrated transmission of a swing drive, the dynamic characteristics of a hydraulic excavator on loading, and the dynamic stability of the drive. The analysis deals with an excavator model that has the same parameters of the kinematic chain members, the same parameters of the upper structure drive mechanisms, and two variants of the swing drive that, with different integrated transmission parameters, provide the upper structure with the identical number of revolutions and equal rotating moment. One swing drive variant possesses an integrated transmission with a hydraulic motor with a low specific flow and a reducer with a high transmission ratio, while the other drive variant has the opposite parameters. Understanding this relationship is essential for optimizing the design of excavators to achieve better performance and dynamic stability under varying operational conditions. As an example, this paper provides the analysis results regarding the influence of the relationship between the parameters of the integrated transmission hydraulic motor and reducer on the loading and dynamic stability of the swing drive in a tracked hydraulic excavator of 100,000 kg in mass and 4.4 m³ in loading bucket volume, as obtained from the developed dynamic mathematical models of the excavator using the MSC ADAMS program. The results indicate that the dynamic loads on the swing drive’s axial bearing are higher in the variant with a low-specific-flow motor and high transmission ratio reducer during the acceleration and deceleration phases. However, this configuration demonstrated better dynamic stability, with lower oscillation amplitudes and shorter damping times compared to the variant with a high-flow motor and low transmission ratio. Those findings provide valuable criteria for the optimal synthesis of swing drive mechanisms in large hydraulic excavators using multi-criteria optimization methods. Full article

(This article belongs to the Special Issue Advanced Control and Fault Detection Techniques in Hydraulic Machines and Systems)

► Show Figures

Figure 1

39 pages, 28877 KiB

Open AccessArticle

Multi-Objective Optimization of an Inertial Wave Energy Converter for Multi-Directional Wave Scatter

by Fabio Carapellese, Viola De Clerck, Sergej Antonello Sirigu, Giuseppe Giorgi, Mauro Bonfanti, Nicolás Faedo and Ermanno Giorcelli

Machines 2024, 12(10), 736; https://doi.org/10.3390/machines12100736 - 19 Oct 2024

Viewed by 579

Abstract

To advance wave energy devices towards commercialization, it is essential to optimize their design to enhance system performance. Additionally, a thorough economic evaluation is crucial for making these technologies competitive with other renewable energy sources. This study focuses on the techno-economic optimization of [...] Read more.

To advance wave energy devices towards commercialization, it is essential to optimize their design to enhance system performance. Additionally, a thorough economic evaluation is crucial for making these technologies competitive with other renewable energy sources. This study focuses on the techno-economic optimization of an innovative inertial system, the so-called SWINGO system, which is based on gyropendulum technology. SWINGO stands out due to its high energy efficiency in multi-directional installation sites, where wave directions vary significantly throughout the year. The study introduces the application of a multi-objective Evolutionary Algorithm (EA), specifically the Non-dominated Sorting Genetic Algorithm II (NSGA-II), to optimize the techno-economic performance of the SWINGO system. This approach aims to identify optimal design parameters that maximize energy extraction while considering economic viability. By deriving a Pareto frontier, a set of optimal devices is selected for further analysis. The performance of the SWINGO system is also compared to an alternative (mono-directional) inertial wave energy converter, the Inertial Sea Wave Energy Converter (ISWEC), to highlight the differences in techno-economic outcomes. Both systems are evaluated at two different installation sites: Pantelleria island and the North Sea in Denmark, with a focus on the directional wave scatter at each location. Full article

(This article belongs to the Section Electromechanical Energy Conversion Systems)

► Show Figures

Figure 1

13 pages, 5291 KiB

Open AccessArticle

Redesign of a Balance Rehabilitation Device Based on a Parallel Continuum Mechanism

by Francisco J. Campa and Daniel Díaz-Caneja

Machines 2024, 12(10), 735; https://doi.org/10.3390/machines12100735 - 18 Oct 2024

Viewed by 521

Abstract

In the present work, a parallel continuum manipulator for trunk rehabilitation tasks for patients who have suffered a stroke was analyzed and redesigned. The manipulator had to perform active assistance exercises for the motor recovery of the patient. Based on this background, a [...] Read more.

In the present work, a parallel continuum manipulator for trunk rehabilitation tasks for patients who have suffered a stroke was analyzed and redesigned. The manipulator had to perform active assistance exercises for the motor recovery of the patient. Based on this background, a series of requirements were defined, which determined the design framework during the modeling of the manipulator. Finally, an improved prototype was built and tested to verify that the model can properly characterize the behavior of the manipulator. Such tests were carried out using a self-made dummy that replicates the simplifying hypotheses and conditions assumed in the mathematical model. Full article

(This article belongs to the Special Issue Dynamics and Optimization of Compliant and Flexible Mechanisms)

► Show Figures

Figure 1

23 pages, 10799 KiB

Open AccessArticle

The Development and Experimental Validation of a Real-Time Coupled Gear Wear Prediction Model Considering Initial Surface Topography, Dynamics, and Thermal Deformation

by Jingqi Zhang, Jianxing Zhou, Quanwei Cui, Ning Dong, Hong Jiang and Zhong Fang

Machines 2024, 12(10), 734; https://doi.org/10.3390/machines12100734 - 17 Oct 2024

Viewed by 575

Abstract

Errors affect the actual meshing process of gears, alter the actual wear pattern of the tooth profile, and may even impact the overall service life of machinery. While existing research predominantly focuses on individual errors or a narrow set of factors, this study [...] Read more.

Errors affect the actual meshing process of gears, alter the actual wear pattern of the tooth profile, and may even impact the overall service life of machinery. While existing research predominantly focuses on individual errors or a narrow set of factors, this study explores the combined effects of multiple errors on tooth profile wear. A comprehensive gear wear prediction model was developed, integrating the slice method, lumped mass method, Hertz contact model, and Archard’s wear theory. This model accounts for initial tooth surface topography, thermal deformation, dynamic effects, and wear, establishing strong correlations between gear wear prediction and key factors such as tooth surface morphology, temperature, and vibration. Experimental validation demonstrated the model’s high accuracy, with relatively small deviations from the observed wear. Initial profile errors (IPEs) at different positions along the tooth width result in varying relative sliding distances, leading to differences in wear depth despite a consistent overall trend. Notably, large IPEs at the dedendum and addendum can influence wear progression, either accelerating or decelerating the wear process over time. Full article

(This article belongs to the Section Machines Testing and Maintenance)

► Show Figures

Figure 1

17 pages, 5304 KiB

Open AccessArticle

Active Disturbance Rejection Control of Engine Speed in Series Hydraulic Hybrid Power System

by Zhiqiang Guo, Junlin Luo and Yuwei Liu

Machines 2024, 12(10), 733; https://doi.org/10.3390/machines12100733 - 16 Oct 2024

Viewed by 513

Abstract

In this paper, a novel series hydraulic hybrid powertrain is proposed for a three-axis all-terrain vehicle. The engine drives two variable displacement pumps responsible for driving and steering, respectively. A variable displacement motor is connected to the ring gear of the planetary coupling [...] Read more.

In this paper, a novel series hydraulic hybrid powertrain is proposed for a three-axis all-terrain vehicle. The engine drives two variable displacement pumps responsible for driving and steering, respectively. A variable displacement motor is connected to the ring gear of the planetary coupling mechanism to drive the vehicle and a fixed-displacement motor is connected to the sun gear to steer the vehicle. The active disturbance rejection control with feedforward control is employed to control the engine speed. The engine speed is controlled in a close-looped manner by adjusting the engine throttle. The controller parameters are decided by analyzing the influence of each parameter on the controller performance by means of the control variable method. The simulation results indicate that the proposed control strategy enables the vehicle to obtain better engine speed following and anti-disturbance performance. An all-terrain prototype is established and field tests are carried out to verify the effectiveness of the design and control strategy of the series hydraulic hybrid powertrain for the all-terrain vehicle. Full article

(This article belongs to the Section Vehicle Engineering)

► Show Figures

Figure 1

16 pages, 6007 KiB

Open AccessArticle

Simulation and Experimental Study of Ultrasonic Vibratory Grinding of Internal Splines

by Zemin Zhao, Shuangshuang Zhou, Qiang Liu, Long Zhang, Bin Shen and Jiaming Han

Machines 2024, 12(10), 732; https://doi.org/10.3390/machines12100732 - 16 Oct 2024

Viewed by 557

Abstract

As an important component of mechanical transmission systems, internal splines are widely used in aerospace, industrial equipment, and other fields. However, internal splines are prone to deformation and shrinkage after heat treatment. At present, most internal splines with a pitch circle diameter greater [...] Read more.

As an important component of mechanical transmission systems, internal splines are widely used in aerospace, industrial equipment, and other fields. However, internal splines are prone to deformation and shrinkage after heat treatment. At present, most internal splines with a pitch circle diameter greater than φ60 mm can be processed and shaped by ordinary corundum grinding wheels, but there is no effective processing method for the shaping of small- and medium-sized internal splines. This paper establishes a single abrasive material removal model; uses Abaqus to simulate three-body free grinding; and analyzes the effects of abrasive rotation angle, rotation speed, and grinding depth on material removal under different conditions. By comparing the tooth lead deviation and tooth direction deviation before and after internal spline grinding, the experimental results show that after ultrasonic vibration grinding, the internal spline tooth profile deviation is reduced by 41.9%, and the tooth direction deviation is reduced by 44.1%, which provides a new processing method for the deformation recovery of internal splines after heat treatment. Full article

(This article belongs to the Section Advanced Manufacturing)

► Show Figures

Figure 1

20 pages, 7994 KiB

Open AccessArticle

Design of Connector Assembly Equipment for the Automotive Industry

by Pedro M. P. Curralo, Raul D. S. G. Campilho, Joaquim A. P. Pereira and Francisco J. G. Silva

Machines 2024, 12(10), 731; https://doi.org/10.3390/machines12100731 - 16 Oct 2024

Viewed by 571

Abstract

The automotive industry is one of the most demanding sectors of all manufacturing industries due to its competitiveness. It is necessary to innovate through the implementation of automated and robotic equipment, leading to cycle time and labor cost reduction. This work aims to [...] Read more.

The automotive industry is one of the most demanding sectors of all manufacturing industries due to its competitiveness. It is necessary to innovate through the implementation of automated and robotic equipment, leading to cycle time and labor cost reduction. This work aims to design semi-automatic equipment to assemble cabling connectors used in the automotive sector, replacing a manual process currently taking place in an automotive components company. In the proposed equipment, the operator places a connector in the equipment, and the components (pins and seals) are automatically inserted. A vision sensor with artificial intelligence then confirms the correct application. The equipment operation defined as Finite Element Method (FEM) was applied for structural verification; the materials and fabrication processes were detailed; the associated costs were calculated, and the equipment subsets were validated. The design was successfully accomplished, and the imposed requirements were fulfilled, with significant advantages over the current process, providing new knowledge on how semi-automatic systems can be deployed to enhance the productivity and quality of manufacturing processes. The design principles and insights gained from this work can be applied to other automation challenges, particularly where manual processes need to be replaced by more efficient semi-automatic or automatic systems. The modularity of the overall solution and the design concepts of the component inserter, component feeder, and assembly process allow for its use in different assembly scenarios beyond the automotive sector, such as electronics or aerospace, providing a contribution to increased competitiveness and survival in the global market. Full article

(This article belongs to the Special Issue Recent Developments in Machine Design, Automation and Robotics)

► Show Figures

Figure 1

5 pages, 164 KiB

Open AccessEditorial

Editorial for Special Issue of Motion Planning and Advanced Control for Robotics

by Jonathan Crespo and Ramon Barber

Machines 2024, 12(10), 730; https://doi.org/10.3390/machines12100730 - 15 Oct 2024

Viewed by 446

Abstract

Advancements in robotics are increasingly essential in addressing complex challenges associated with motion planning and control, particularly in environments that require physical interaction with various elements [...] Full article

(This article belongs to the Special Issue Motion Planning and Advanced Control for Robotics)

18 pages, 4442 KiB

Open AccessArticle

Integrating Learning-Driven Model Behavior and Data Representation for Enhanced Remaining Useful Life Prediction in Rotating Machinery

by Tarek Berghout, Eric Bechhoefer, Faycal Djeffal and Wei Hong Lim

Machines 2024, 12(10), 729; https://doi.org/10.3390/machines12100729 - 15 Oct 2024

Viewed by 702

Abstract

The increasing complexity of modern mechanical systems, especially rotating machinery, demands effective condition monitoring techniques, particularly deep learning, to predict potential failures in a timely manner and enable preventative maintenance strategies. Health monitoring data analysis, a widely used approach, faces challenges due to [...] Read more.

The increasing complexity of modern mechanical systems, especially rotating machinery, demands effective condition monitoring techniques, particularly deep learning, to predict potential failures in a timely manner and enable preventative maintenance strategies. Health monitoring data analysis, a widely used approach, faces challenges due to data randomness and interpretation difficulties, highlighting the importance of robust data quality analysis for reliable monitoring. This paper presents a two-part approach to address these challenges. The first part focuses on comprehensive data preprocessing using only feature scaling and selection via random forest (RF) algorithm, streamlining the process by minimizing human intervention while managing data complexity. The second part introduces a Recurrent Expansion Network (RexNet) composed of multiple layers built on recursive expansion theories from multi-model deep learning. Unlike traditional Rex architectures, this unified framework allows fine tuning of RexNet hyperparameters, simplifying their application. By combining data quality analysis with RexNet, this methodology explores multi-model behaviors and deeper interactions between dependent (e.g., health and condition indicators) and independent variables (e.g., Remaining Useful Life (RUL)), offering richer insights than conventional methods. Both RF and RexNet undergo hyperparameter optimization using Bayesian methods under variability reduction (i.e., standard deviation) of residuals, allowing the algorithms to reach optimal solutions and enabling fair comparisons with state-of-the-art approaches. Applied to high-speed bearings using a large wind turbine dataset, this approach achieves a coefficient of determination of 0.9504, enhancing RUL prediction. This allows for more precise maintenance scheduling from imperfect predictions, reducing downtime and operational costs while improving system reliability under varying conditions. Full article

(This article belongs to the Special Issue Advanced Signal Processing Methods and Deep Neural Networks for Machine Fault Diagnosis)

► Show Figures

Figure 1

17 pages, 11316 KiB

Open AccessArticle

Thermal Error Transfer Prediction Modeling of Machine Tool Spindle with Self-Attention Mechanism-Based Feature Fusion

by Yue Zheng, Guoqiang Fu, Sen Mu, Caijiang Lu, Xi Wang and Tao Wang

Machines 2024, 12(10), 728; https://doi.org/10.3390/machines12100728 - 15 Oct 2024

Viewed by 568

Abstract

Thermal errors affect machining accuracy in high-speed precision machining. The variability of machine tool operating conditions poses a challenge to the modeling of thermal errors. In this paper, a thermal error model based on transfer temperature feature fusion is proposed. Firstly, the temperature [...] Read more.

Thermal errors affect machining accuracy in high-speed precision machining. The variability of machine tool operating conditions poses a challenge to the modeling of thermal errors. In this paper, a thermal error model based on transfer temperature feature fusion is proposed. Firstly, the temperature information fusion features are built as inputs to the model, which is based on a self-attention mechanism to assign weights to the temperature information and fuse the features. Secondly, an improved direct normalization-based adaptive matrix approach is proposed, updating the background matrix using an autoencoder and reconstructing the adaptive matrix to realize domain self-adaptation. In addition, for the improved adaptive matrix, a criterion for determining whether the working conditions are transferrable to each other is proposed. The proposed method shows high prediction accuracy while ensuring training efficiency. Finally, thermal error experiments are performed on a VCM850 CNC machine tool. Full article

(This article belongs to the Special Issue Error Measurement, Analysis, and Compensation Technology for CNC Machine Tools)

► Show Figures

Figure 1

23 pages, 26849 KiB

Open AccessArticle

Research on Temperature Change Law and Non-Uniform Distribution Characteristics of Electromagnetic Control Roll Based on Rotating Heat Flow

by Shuaishuai Zheng, Tingsong Yang, Tieheng Yuan, Wenquan Sun, Ankang Shen and Shuo Fan

Machines 2024, 12(10), 727; https://doi.org/10.3390/machines12100727 - 14 Oct 2024

Viewed by 443

Abstract

The uniform temperature distribution on the surface of the electromagnetic control roll (ECR) has a great impact on the quality of the strip; therefore, temperature control is essential. In order to study this issue, a two-dimensional volume of fluid (VOF) model was established [...] Read more.

The uniform temperature distribution on the surface of the electromagnetic control roll (ECR) has a great impact on the quality of the strip; therefore, temperature control is essential. In order to study this issue, a two-dimensional volume of fluid (VOF) model was established using the simulation software FLUENT (2024 R1) to analyze the radial cooling capacity and surface temperature uniformity of the ECR under different process parameters, and an experimental validation was carried out at the same time. The error between the experiment and the model was less than 5% of the maximum temperature, proving the model is accurate. The results of the analysis show that the use of a controlled temperature mode has an effect on the cooling capacity and the speed has no effect on the cooling capacity. The temperature difference between the two sides of the ECR is too large, which will make the uniformity of the ECR surface temperature worse. While too high or too low, a roll speed and coolant injection speed will increase the non-uniformity of the ECR surface temperature; when the roll speed is 12 rad/s or coolant injection speed is 5 m/s, the ECR surface temperature distribution uniformity is the best. Properly adjusted process parameters can improve the cooling performance and ECR surface temperature uniformity. Full article

(This article belongs to the Section Advanced Manufacturing)

► Show Figures

Figure 1

20 pages, 3985 KiB

Open AccessArticle

Control of Large Wind Energy Systems Throughout the Shutdown Process

by Adrian Gambier

Machines 2024, 12(10), 726; https://doi.org/10.3390/machines12100726 - 14 Oct 2024

Viewed by 479

Abstract

This contribution examines the control problem for very large wind energy converters during shutdown operation and analyses the most important control approaches. The control methods make use of the built-in conventional control infrastructure, but control system reconfigurations are undertaken in order to meet [...] Read more.

This contribution examines the control problem for very large wind energy converters during shutdown operation and analyses the most important control approaches. The control methods make use of the built-in conventional control infrastructure, but control system reconfigurations are undertaken in order to meet the demands of the shutdown control operation. Hence, the torque controller as well as the collective pitch controller (CPC) are redesigned from their regulator functions to reference tracking control systems with constraints. In addition, the CPC is combined with a feedforward controller in order to gain responsiveness. Constraints in magnitude and rate are managed by a modified anti-windup mechanism. Simulations of a 20 MW reference wind turbine verify the performance of the approaches. Full article

(This article belongs to the Special Issue Design and Dynamic Control of Wind Turbines)

► Show Figures

Figure 1

22 pages, 9204 KiB

Open AccessArticle

Analysis of the Nonlinear Complex Response of Cracked Blades at Variable Rotational Speeds

by Bo Shao, Chenguang Fan, Shunguo Fu and Jin Zeng

Machines 2024, 12(10), 725; https://doi.org/10.3390/machines12100725 - 14 Oct 2024

Viewed by 678

Abstract

The operation of an aero-engine involves various non-stationary processes of acceleration and deceleration, with rotational speed varying in response to changing working conditions to meet different power requirements. To investigate the nonlinear dynamic behaviour of cracked blades under variable rotational speed conditions, this [...] Read more.

The operation of an aero-engine involves various non-stationary processes of acceleration and deceleration, with rotational speed varying in response to changing working conditions to meet different power requirements. To investigate the nonlinear dynamic behaviour of cracked blades under variable rotational speed conditions, this study constructed a rotating blade model with edge-penetrating cracks and proposes a component modal synthesis method that accounts for time-varying rotational speed. The nonlinear response behaviours of cracked blades were examined under three distinct operating conditions: spinless, steady speed, and non-constant speed. The findings indicated a competitive relationship between the effects of rotational speed fluctuations and unbalanced excitation on crack nonlinearity. Variations in rotational speed dominated when rotational speed perturbation was minimal; conversely, aerodynamic forces dominated when the effects of rotational speed were pronounced. An increase in rotational speed perturbation enhanced the super-harmonic nonlinearity induced by cracks, elevated the nonlinear damage index (NDI), and accentuated the crack breathing effect. As the perturbation coefficient increased, the super-harmonic nonlinearity of the crack intensified, resulting in a more complex vibration form and phase diagram. Full article

(This article belongs to the Special Issue Nonlinear Dynamics of Mechanical Systems and Machines)

► Show Figures

Figure 1

12 pages, 2863 KiB

Open AccessArticle

The Effects of Adding TiO₂ and CuO Nanoparticles to Fuel on Engine and Hand–Arm Driver Vibrations

by Ali Adelkhani, Peyman Nooripour and Ehsan Daneshkhah

Machines 2024, 12(10), 724; https://doi.org/10.3390/machines12100724 - 13 Oct 2024

Viewed by 591

Abstract

Occupant comfort is a key consideration in automobile dynamics, with vibrations potentially causing long-term physical discomfort, especially for drivers. This study investigates the impact of adding TiO₂ and CuO nanoparticles to fuel on engine-induced vibrations. Experiments were conducted at various nanoparticle concentrations [...] Read more.

Occupant comfort is a key consideration in automobile dynamics, with vibrations potentially causing long-term physical discomfort, especially for drivers. This study investigates the impact of adding TiO₂ and CuO nanoparticles to fuel on engine-induced vibrations. Experiments were conducted at various nanoparticle concentrations (0, 50, 100, and 150 ppm) and engine speeds (1000, 2000, and 3000 rpm). Key performance metrics, including kinematic viscosity, density, heating value, thermal conductivity, and brake power (BP), were analyzed. The results indicated that increasing nanoparticle concentration led to a rise in BP. The highest reduction in root mean square (RMS) vibration accelerations occurred at 3000 rpm and 150 ppm, with vibration reductions of 30.33% for CuO and 28.61% for TiO₂. Additionally, 8–10% of engine vibrations were transmitted to the steering wheel. The use of 150 ppm CuO nanoparticles resulted in reduced vibration transmission to the steering wheel at all tested speeds. These findings suggest that nanoparticle-enhanced fuels can significantly reduce engine vibrations, potentially improving driver comfort and reducing wear on vehicle components. Full article

(This article belongs to the Special Issue Vibration-Based Machines Wear Monitoring and Prediction)

► Show Figures

Figure 1

17 pages, 4612 KiB

Open AccessArticle

A Novel Kind of Knowledge Graph Construction Method for Intelligent Machine as a Service Modeling

by Yuhao Liu, Jiayuan Han, Peng Yan, Biyao Li, Maolin Yang and Pingyu Jiang

Machines 2024, 12(10), 723; https://doi.org/10.3390/machines12100723 - 12 Oct 2024

Viewed by 686

Abstract

With the development of Intelligent Machine as a Service (IMaaS), devices increasingly require personalization, intelligence, and service orientation, making resource modeling a key challenge. Knowledge graph (KG) technology, known for unifying heterogeneous data, has become an essential tool for modeling and analyzing manufacturing [...] Read more.

With the development of Intelligent Machine as a Service (IMaaS), devices increasingly require personalization, intelligence, and service orientation, making resource modeling a key challenge. Knowledge graph (KG) technology, known for unifying heterogeneous data, has become an essential tool for modeling and analyzing manufacturing resources. On this basis, this study proposes a novel resource KG construction method for IMaaS. First, an E-R diagram is used to divide the constant and variable entities and set the constant attributes and the constant relationships. Then, the triplets are named, the value space is set, and the schema layer is constructed. Finally, the related information about devices is used to fill the data layer, and then, the knowledge graph is generated. Meanwhile, this study utilizes desktop FDM 3D printing devices as a case example for validation. The method proposed in this study can enhance the accuracy and maintainability of equipment resource management in the manufacturing sector, effectively promoting subsequent activities such as management, analysis, and decision-making. Full article

(This article belongs to the Topic Smart Product Design and Manufacturing on Industrial Internet)

► Show Figures

Figure 1

19 pages, 1424 KiB

Open AccessArticle

Development and Testing of a Dual-Driven Piezoelectric Microgripper with High Amplification Ratio for Cell Micromanipulation

by Boyan Lu, Shengzheng Kang, Luyang Zhou, Dewen Hua, Chengdu Yang and Zimeng Zhu

Machines 2024, 12(10), 722; https://doi.org/10.3390/machines12100722 - 12 Oct 2024

Viewed by 517

Abstract

Cell micromanipulation is an important technique in the field of biomedical engineering. Microgrippers play a crucial role in connecting macroscopic and microscopic objects in micromanipulation systems. However, since the operated biological cells are deformable, vulnerable, and typically distributed in sizes ranging from micrometers [...] Read more.

Cell micromanipulation is an important technique in the field of biomedical engineering. Microgrippers play a crucial role in connecting macroscopic and microscopic objects in micromanipulation systems. However, since the operated biological cells are deformable, vulnerable, and typically distributed in sizes ranging from micrometers to millimeters, it poses a huge challenge to microgripper performance. To solve this problem, this paper develops a dual-driven piezoelectric microgripper with a high displacement amplification ratio, large stroke, and parallel gripping. By adopting modular configuration, three kinds of flexure-based mechanisms, including the lever mechanism, Scott–Russell mechanism, and parallelogram mechanism are connected in series to realize three-stage amplification, which effectively makes up for the shortage of small output displacement of the piezoelectric actuator. At the same time, the use of the parallelogram mechanism also isolates the parasitic rotation movement, and realizes the parallel movement of the gripping jaws. In addition, the kinematics, statics, and dynamics models of the microgripper are established by using the pseudo-rigid body and Lagrange methods, and the key geometric parameters are also optimized. Finite element simulation and experimental tests verify the effectiveness of the developed microgripper. The results show that the developed microgripper allows an amplification ratio of 46.4, a clamping stroke of 2180

μ

m, and a natural frequency of 203.1 Hz. Based on the developed microgripper, the nondestructive micromanipulation of zebrafish embryos is successfully realized. Full article

(This article belongs to the Special Issue Optimization and Design of Compliant Mechanisms)

► Show Figures

Figure 1

27 pages, 5244 KiB

Open AccessArticle

An Optimization Method for Green Permutation Flow Shop Scheduling Based on Deep Reinforcement Learning and MOEA/D

by Yongxin Lu, Yiping Yuan, Adilanmu Sitahong, Yongsheng Chao and Yunxuan Wang

Machines 2024, 12(10), 721; https://doi.org/10.3390/machines12100721 - 11 Oct 2024

Viewed by 577

Abstract

This paper addresses the green permutation flow shop scheduling problem (GPFSP) with energy consumption consideration, aiming to minimize the maximum completion time and total energy consumption as optimization objectives, and proposes a new method that integrates end-to-end deep reinforcement learning (DRL) with the [...] Read more.

This paper addresses the green permutation flow shop scheduling problem (GPFSP) with energy consumption consideration, aiming to minimize the maximum completion time and total energy consumption as optimization objectives, and proposes a new method that integrates end-to-end deep reinforcement learning (DRL) with the multi-objective evolutionary algorithm based on decomposition (MOEA/D), termed GDRL-MOEA/D. To improve the quality of solutions, the study first employs DRL to model the PFSP as a sequence-to-sequence model (DRL-PFSP) to obtain relatively better solutions. Subsequently, the solutions generated by the DRL-PFSP model are used as the initial population for the MOEA/D, and the proposed job postponement energy-saving strategy is incorporated to enhance the solution effectiveness of the MOEA/D. Finally, by comparing the GDRL-MOEA/D with the MOEA/D, NSGA-II, the marine predators algorithm (MPA), the sparrow search algorithm (SSA), the artificial hummingbird algorithm (AHA), and the seagull optimization algorithm (SOA) through experimental tests, the results demonstrate that the GDRL-MOEA/D has a significant advantage in terms of solution quality. Full article

(This article belongs to the Section Advanced Manufacturing)

► Show Figures

Figure 1

20 pages, 10032 KiB

Open AccessArticle

Study on Crashworthiness of Shrink Tube Anti-Creep Device

by Fan Zou, Shuguang Yao, Xin Zheng, Minhan Xie and Lei Yang

Machines 2024, 12(10), 720; https://doi.org/10.3390/machines12100720 - 11 Oct 2024

Viewed by 468

Abstract

Based on the requirements of the narrow installation space of a train end, compact energy-absorbing travel, and huge energy suck, a shrink tube anti-creep device was designed. The crashworthiness of different structures was studied by means of a material test, a trolley test, [...] Read more.

Based on the requirements of the narrow installation space of a train end, compact energy-absorbing travel, and huge energy suck, a shrink tube anti-creep device was designed. The crashworthiness of different structures was studied by means of a material test, a trolley test, and numerical simulation. For every 1 mm increase in tube wall thickness, 1 mm increase in the axial length of the friction cone, and 0.01 increase in the friction coefficient, the mean crushing force (MCF) increased by 45.1 kN, 13.5 kN, and 30.5 kN, respectively. When the cone angle of the shrink tube increased from α = 5° to α = 25°, the increase in the MCF with different thicknesses was about 600%. The MCF was most affected by the cone angle, followed by the wall thickness, the friction coefficient, and the axial length of the friction cone. The change in the contact length of the friction cone of the shrink tube under different structural parameters was compared. The contact length decreased with the increase in tube wall thickness and increased with the increase in angle. The variation rule of MCF was obtained to provide a reference for the development of genealogical products. Full article

(This article belongs to the Section Machine Design and Theory)

► Show Figures

Figure 1

17 pages, 1999 KiB

Open AccessArticle

Compensation Function Observer-Based Backstepping Sliding-Mode Control of Uncertain Electro-Hydraulic Servo System

by Changzhong Pan, Yanjun Wang, Simon X. Yang, Zhijing Li and Jinsen Xiao

Machines 2024, 12(10), 719; https://doi.org/10.3390/machines12100719 - 11 Oct 2024

Viewed by 554

Abstract

Observer-based control is the most commonly used method in the control of electro-hydraulic servo system (EHSS) with uncertainties, but it suffers from the drawback of low accuracy under the influence of large external load forces and disturbances. To address this problem, this paper [...] Read more.

Observer-based control is the most commonly used method in the control of electro-hydraulic servo system (EHSS) with uncertainties, but it suffers from the drawback of low accuracy under the influence of large external load forces and disturbances. To address this problem, this paper proposes a novel compensation function observer-based backstepping sliding-mode control (BSMC) approach to achieve high-accuracy tracking control. In particular, the model uncertainties, including nonlinearities, parameter perturbations and external disturbances are analyzed and treated together as a lumped disturbance. Then, a fourth-order compensation function observer (CFO) is constructed, which fully utilizes the system state information to accurately estimate the lumped disturbance. On this basis, the estimate of the lumped disturbance is incorporated into the design of a backstepping sliding-mode controller, allowing the control system to compensate for the disturbance effect. The stability of the closed-loop control system under the CFO and BSMC is rigorously proven through the use of the Lyapunov theory, which guarantees that all the tracking error signals converge exponentially to the origin. Comparative simulations are carried out to show the effectiveness and efficiency of the proposed approach, i.e., compared with PID and ESO-based BSMC methods, the tracking accuracy is respectively improved by

94.86 %

and

88.19 %

under the influence of large external load forces and disturbances. Full article

(This article belongs to the Section Machine Design and Theory)

► Show Figures

Figure 1

19 pages, 5453 KiB

Open AccessArticle

Design, Analysis, and Optimization Testing of a Novel Modular Walking Device for Pipeline Robots

by Naiyu Shi, He Li, Ting Xu, Hongliang Hua, Junhong Ye and Zheng Chen

Machines 2024, 12(10), 718; https://doi.org/10.3390/machines12100718 - 11 Oct 2024

Viewed by 481

Abstract

This article investigates the limitations associated with traditional wheel-type pipeline walking devices, which are characterized by a single movement mode and an inability to navigate complex or irregular pipeline structures. A modular walking device (MWD) designed for pipeline robots was developed utilizing structural [...] Read more.

This article investigates the limitations associated with traditional wheel-type pipeline walking devices, which are characterized by a single movement mode and an inability to navigate complex or irregular pipeline structures. A modular walking device (MWD) designed for pipeline robots was developed utilizing structural and mechanical analysis techniques. The reliability of the mechanical analysis was validated through single-factor dynamic testing. To analyze and optimize the factors influencing the maneuverability and obstacle-crossing capabilities of the MWD, a three-factor, three-level orthogonal testing method was utilized. The factors examined included the rotational speed of the walking wheel (RS), the pre-tightening force of the wheel brackets (PF), and the height of the annular obstacle (OH). The evaluation metrics used were the slip rate and passability. The results indicated that a parameter combination of RS at 70 rpm, PF at 30 N, and OH at 10 mm produced a slip rate of 11.6% ± 1.5%. During the obstacle traversal process, the remainder of the device maintained a safe distance from the obstacles, with only the walking wheel making contact. The verification testing also confirmed that the MWD is capable of executing three distinct modes of motion: rectilinear, rotational, and helical. The MWD designed and developed in this study can switch between multiple motion modes and successfully overcome obstacles within 15 mm, providing a new equipment for universities to enhance mechanized pipeline detection technology. Full article

(This article belongs to the Section Robotics, Mechatronics and Intelligent Machines)

► Show Figures

Figure 1

2 pages, 183 KiB

Open AccessCorrection

Correction: de Menezes et al. A Thorough Procedure to Design Surface-Mounted Permanent Magnet Synchronous Generators. Machines 2024, 12, 384

by Gustavo Garbelini de Menezes, Narco Afonso Ravazzoli Maciejewski, Elissa Soares de Carvalho and Thiago de Paula Machado Bazzo

Machines 2024, 12(10), 717; https://doi.org/10.3390/machines12100717 - 11 Oct 2024

Viewed by 342

Abstract

In the original publication [...] Full article

(This article belongs to the Special Issue Research in Design and Analysis of Permanent Magnet Synchronous Machines)

22 pages, 7423 KiB

Open AccessArticle

Advancing UAV Sensor Fault Diagnosis Based on Prior Knowledge and Graph Convolutional Network

by Hui Li, Chaoyin Chen, Tiancai Wan, Shaoshan Sun, Yongbo Li and Zichen Deng

Machines 2024, 12(10), 716; https://doi.org/10.3390/machines12100716 - 10 Oct 2024

Viewed by 535

Abstract

Unmanned aerial vehicles (UAVs) are equipped with various sensors to facilitate control and navigation. However, UAV sensors are highly susceptible to damage under complex flight environments, leading to severe accidents and economic losses. Although fault diagnosis methods based on deep neural networks have [...] Read more.

Unmanned aerial vehicles (UAVs) are equipped with various sensors to facilitate control and navigation. However, UAV sensors are highly susceptible to damage under complex flight environments, leading to severe accidents and economic losses. Although fault diagnosis methods based on deep neural networks have been widely applied in the mechanical field, these methods often fail to integrate multi-source information and overlook the importance of system prior knowledge. As a result, this study employs a spatial-temporal difference graph convolutional network (STDGCN) for the fault diagnosis of UAV sensors, where the graph structure naturally organizes the diverse sensors. Specifically, a difference layer enhances the feature extraction capability of the graph nodes, and the spatial-temporal graph convolutional modules are designed to extract spatial-temporal dependencies from sensor data. Moreover, to ensure the accuracy of the association graph, this research introduces the UAV’s dynamic model as prior knowledge for constructing the association graph. Finally, diagnostic accuracies of 94.93%, 98.71%, and 92.97% were achieved on three self-constructed datasets. In addition, compared to commonly used data-driven approaches, the proposed method demonstrates superior feature extraction capabilities and achieves the highest diagnostic accuracy. Full article

(This article belongs to the Special Issue Data-Driven Approaches regarding Dynamic Modelling, Diagnostics and Prognostics of Complex Mechanical Structures)

► Show Figures

Figure 1

31 pages, 11110 KiB

Open AccessReview

The Generation, Measurement, Prediction, and Prevention of Residual Stress in Nickel-Based Superalloys: A Review

by Yuanlin Zhang, Guangrui Wen, Liangbo Li, Zihao Lei, Xiaogang Qi, Boyang Huang, Yu Su, Zhifen Zhang, Xiangfan Nie and Zhanling Zhang

Machines 2024, 12(10), 715; https://doi.org/10.3390/machines12100715 - 9 Oct 2024

Viewed by 1003

Abstract

As a crucial high-performance material, nickel-based superalloys inevitably generate residual stresses during processing, manufacturing, and usage. The mechanical properties of nickel-based superalloys are significantly reduced by residual stress, which becomes one of the important factors restricting material reliability. The systematic analysis of residual [...] Read more.

As a crucial high-performance material, nickel-based superalloys inevitably generate residual stresses during processing, manufacturing, and usage. The mechanical properties of nickel-based superalloys are significantly reduced by residual stress, which becomes one of the important factors restricting material reliability. The systematic analysis of residual stresses in nickel-based superalloys throughout the entire manufacturing and usage processes is insufficient. The residual stress generation factors, measurement methods, prediction models, and control methods in nickel-based superalloys in recent years are summarized in this paper. The current challenge and future development trends in the research process of nickel-based superalloy residual stress are also presented. A theoretical reference for further research on residual stresses in nickel-based superalloys can be provided in this review. Full article

(This article belongs to the Section Material Processing Technology)

► Show Figures

Figure 1

19 pages, 4401 KiB

Open AccessArticle

Lightweight Detection of Train Underframe Bolts Based on SFCA-YOLOv8s

by Zixiao Li, Jinjin Li, Chuanlong Zhang and Huajun Dong

Machines 2024, 12(10), 714; https://doi.org/10.3390/machines12100714 - 9 Oct 2024

Viewed by 617

Abstract

Improving the accuracy and detection speed of bolt recognition under the complex background of the train underframe is crucial for the safety of train operation. To achieve efficient detection, a lightweight detection method based on SFCA-YOLOv8s is proposed. The underframe bolt images are [...] Read more.

Improving the accuracy and detection speed of bolt recognition under the complex background of the train underframe is crucial for the safety of train operation. To achieve efficient detection, a lightweight detection method based on SFCA-YOLOv8s is proposed. The underframe bolt images are captured by a self-designed track-based inspection robot, and a dataset is constructed by mixing simulated platform images with real train underframe bolt images. By combining the C2f module with ScConv lightweight convolution and replacing the Bottleneck structure with the Faster_Block structure, the SFC2f module is designed for feature extraction to improve detection accuracy and speed. It is compared with FasterNet, GhostNet, and MobileNetV3. Additionally, the CA attention mechanism is introduced, and MPDIoU is used as the loss function of YOLOv8s. LAMP scores are used to rank the model weight parameters, and unimportant weight parameters are pruned to achieve model compression. The compressed SFCA-YOLOv8s model is compared with models such as YOLOv5s, YOLOv7, and YOLOX-s in comparative experiments. The results indicate that the final model achieves an average detection accuracy of 93.3% on the mixed dataset, with a detection speed of 261 FPS. Compared with other classical deep learning models, the improved model demonstrates superior performance in detection effectiveness, robustness, and generalization. Even in the absence of sufficient real underframe bolt images, the algorithm enables the trained network to better adapt to real environments, improving bolt recognition accuracy and detection speed, thus providing technical references and theoretical support for subsequent related research. Full article

(This article belongs to the Section Vehicle Engineering)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Machines, Volume 12, Issue 10 (October 2024) – 77 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI