World Electric Vehicle Journal

Research

Jump to: Review

13 pages, 2709 KiB

Open AccessArticle

Enhanced Vehicle Logo Detection Method Based on Self-Attention Mechanism for Electric Vehicle Application

by Shuo Yang, Yisu Liu, Ziyue Liu, Changhua Xu and Xueting Du

World Electr. Veh. J. 2024, 15(10), 467; https://doi.org/10.3390/wevj15100467 - 14 Oct 2024

Viewed by 707

Abstract

Vehicle logo detection plays a crucial role in various computer vision applications, such as vehicle classification and detection. In this research, we propose an improved vehicle logo detection method leveraging the self-attention mechanism. Our feature-sampling structure integrates multiple attention mechanisms and bidirectional feature [...] Read more.

Vehicle logo detection plays a crucial role in various computer vision applications, such as vehicle classification and detection. In this research, we propose an improved vehicle logo detection method leveraging the self-attention mechanism. Our feature-sampling structure integrates multiple attention mechanisms and bidirectional feature aggregation to enhance the discriminative power of the detection model. Specifically, we introduce the multi-head attention for multi-scale feature fusion module to capture multi-scale contextual information effectively. Moreover, we incorporate the bidirectional aggregation mechanism to facilitate information exchange between different layers of the detection network. Experimental results on a benchmark dataset (VLD-45 dataset) demonstrate that our proposed method outperforms baseline models in terms of both detection accuracy and efficiency. Our experimental evaluation using the VLD-45 dataset achieves a state-of-the-art result of 90.3% mAP. Our method has also improved AP by 10% for difficult samples, such as HAVAL and LAND ROVER. Our method provides a new detection framework for small-size objects, with potential applications in various fields. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

17 pages, 7660 KiB

Open AccessArticle

Design of a Low-Cost AI System for the Modernization of Conventional Cars

by Wilver Auccahuasi, Kitty Urbano, Sandra Meza, Luis Romero-Echevarria, Arlich Portillo-Allende, Karin Rojas, Jorge Figueroa-Revilla, Giancarlo Sanchez-Atuncar, Sergio Arroyo and Percy Junior Castro-Mejia

World Electr. Veh. J. 2024, 15(10), 455; https://doi.org/10.3390/wevj15100455 - 8 Oct 2024

Viewed by 645

Abstract

Artificial intelligence techniques are beginning to be implemented in most areas. In the particular case of automobiles, new cars include integrated applications, such as cameras in different configurations, including in the rear of the car to provide assistance while reversing, as well as [...] Read more.

Artificial intelligence techniques are beginning to be implemented in most areas. In the particular case of automobiles, new cars include integrated applications, such as cameras in different configurations, including in the rear of the car to provide assistance while reversing, as well as front and side cameras; these applications also include different configurations of sensors that provide information to the driver, such as objects approaching from different directions, such as from the front and sides. In this paper, we propose a practical and low-cost methodology to provide solutions using artificial intelligence techniques, as is the purpose of YOLO architecture, version 3, using hardware based on Nvidia’s Jetson TK1 architecture, and configurations in conventional cars. The results that we present demonstrate that these technologies can be applied in conventional cars, working with independent power to avoid causing problems in these cars, and we evaluate their application in the detection of people and cars in different situations, which allows information to be provided to the driver while performing maneuvers. The methodology that we provide can be replicated and scaled according to needs. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

23 pages, 5012 KiB

Open AccessArticle

State of Health Prediction in Electric Vehicle Batteries Using a Deep Learning Model

by Raid Mohsen Alhazmi

World Electr. Veh. J. 2024, 15(9), 385; https://doi.org/10.3390/wevj15090385 - 25 Aug 2024

Cited by 1 | Viewed by 1121

Abstract

Accurately estimating the state of health (SOH) of lithium-ion batteries plays a significant role in the safe operation of electric vehicles. Deep learning (DL)-based approaches for estimating state of health (SOH) have consistently been the focus of study in recent years. In the [...] Read more.

Accurately estimating the state of health (SOH) of lithium-ion batteries plays a significant role in the safe operation of electric vehicles. Deep learning (DL)-based approaches for estimating state of health (SOH) have consistently been the focus of study in recent years. In the current era of electric mobility, the utilization of lithium-ion batteries (LIBs) has evolved into a necessity for energy storage. Ensuring the safe operation of EVs requires a precise assessment of the state-of-health (SOH) of LIBs. To estimate battery SOH accurately, this paper employs a deep learning (DL) algorithm to enhance the estimation accuracy of SOH to obtain accurate SOH measurements. This research introduces the Diffusion Convolutional Recurrent Neural Network (DCRNN) with a Support Vector Machine-Recursive Feature Elimination (SVM-RFE) algorithm (DCRNN + SVM-RFE) for enhancing classification and feature selection performance. The data gathered from the dataset were pre-processed using the min–max normalization method. The Center for Advanced Life Cycle Engineering (CALCE) dataset from the University of Maryland was employed to train and evaluate the model. The SVM-RFE algorithm was used for feature selection of pre-processed data. DCRNN algorithm was used for the classification process to enhance prediction precision. The DCRNN + SVM-RFE model’s performance was calculated using Mean Absolute Percentage Error (MAPE), Mean Squared Error (MAE), Mean Squared Error (MSE), and Root MSE (RMSE) metric values. The proposed model generates accurate results for SOH prediction; all RMSEs are within 0.02%, MAEs are within 0.015%, MSEs were within 0.032%, and MAPEs are within 0.41%. The mean values of RMSE, MSE, MAE, and MAPE were 0.014, 0.026, 0.011, and 0.32, respectively. Experiments confirmed that the DCRNN + SVM-RFE model has the highest accuracy among those that predict SOH. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

17 pages, 3814 KiB

Open AccessArticle

Dynamic Tracking Method Based on Improved DeepSORT for Electric Vehicle

by Kai Zhu, Junhao Dai and Zhenchao Gu

World Electr. Veh. J. 2024, 15(8), 374; https://doi.org/10.3390/wevj15080374 - 17 Aug 2024

Viewed by 929

Abstract

The development of electric vehicles has facilitated intelligent transportation, which requires the swift and effective detection and tracking of moving vehicles. To satisfy this demand, this paper presents an enhanced DeepSORT algorithm. By selecting YOLO-SSFS as the front-end detector and incorporating a lightweight [...] Read more.

The development of electric vehicles has facilitated intelligent transportation, which requires the swift and effective detection and tracking of moving vehicles. To satisfy this demand, this paper presents an enhanced DeepSORT algorithm. By selecting YOLO-SSFS as the front-end detector and incorporating a lightweight and high-precision feature training network called FasterNet, the proposed method effectively extracts vehicle appearance attributes. Besides this, the noise scale adaptive Kalman filter is implemented and the conventional cascade matching process is substituted with global join matching, thereby enhancing overall performance and tracking accuracy. Validation conducted on the VisDrone dataset demonstrates the superiority of this method compared to the original DeepSORT algorithm, exhibiting a 4.76% increase in tracking accuracy and a 3.10% improvement in tracking precision. The findings reveal the advantages of the algorithms in the domain of vehicle detection and tracking, allowing significant technological advancements in intelligent transportation systems. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

16 pages, 4269 KiB

Open AccessArticle

An Intelligent Vehicle Price Estimation Approach Using a Deep Neural Network Model

by Thuraya Alnajim, Nouf Alshahrani and Omar Asiri

World Electr. Veh. J. 2024, 15(8), 345; https://doi.org/10.3390/wevj15080345 - 31 Jul 2024

Viewed by 854

Abstract

In recent years, the market for used-vehicle trade in the Kingdom of Saudi Arabia has grown significantly. This is due to the high cost of new vehicles that are not affordable by most buyers and lifting the ban on women drivers. Recently, several [...] Read more.

In recent years, the market for used-vehicle trade in the Kingdom of Saudi Arabia has grown significantly. This is due to the high cost of new vehicles that are not affordable by most buyers and lifting the ban on women drivers. Recently, several online websites for selling vehicles are available with different functions. However, estimating the vehicle price is based on traditional calculation methods, and this is inaccurate in several selling situations, as there are many factors that may affect the vehicle price, and these factors must be taken into consideration when estimating the vehicle’s price. Therefore, there is high demand to develop an automated vehicle price estimation system through adopting artificial intelligence (AI) technologies. Hence, this paper proposes an efficient vehicle price estimation system through developing an efficient deep neural network (DNN) model. The developed DNN model has been trained using a recent collected dataset for used-vehicle prices in the Kingdom of Saudi Arabia. The developed system has been validated using a recent vehicle price dataset, and the obtained results are compared with seven different machine learning models and showed a promising regression accuracy. In addition, we developed a reliable graphical user interface (GUI) for the purpose of allowing the user to estimate the price of any vehicle using the pre-trained DNN model. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

15 pages, 2429 KiB

Open AccessArticle

Consumer Segmentation and Market Analysis for Sustainable Marketing Strategy of Electric Vehicles in the Philippines

by John Robin R. Uy, Ardvin Kester S. Ong, Danica Mariz B. De Guzman, Irish Tricia Dela Cruz and Juliana C. Dela Cruz

World Electr. Veh. J. 2024, 15(7), 301; https://doi.org/10.3390/wevj15070301 - 8 Jul 2024

Viewed by 2745

Abstract

Despite the steady rise of electric vehicles (EVs) in other countries, the Philippines has yet to capitalize on its proliferation due to several mixed concerns. Status, socio-demographic characteristics, and availability have been the main concerns with purchasing EVs in the country. Consumer segmentation [...] Read more.

Despite the steady rise of electric vehicles (EVs) in other countries, the Philippines has yet to capitalize on its proliferation due to several mixed concerns. Status, socio-demographic characteristics, and availability have been the main concerns with purchasing EVs in the country. Consumer segmentation and analysis for EV acceptance and utility in the Philippines were determined in this study due to the need for understanding consumer preferences and market segmentation towards EVs in the Philippines. A total of 311 valid responses coming from EV owners were collected through purposive and snowball sampling approaches. The data were collected via face-to-face distribution and online distribution of a questionnaire covering demographic characteristics for market segmentation. Demographic data such as gender, age, residence type, car ownership, and income were used to identify consumer segments using the K-means clustering approach. Jupyter Notebook v7.1.3 was used for the overall analysis, and the number of clusters was optimized, ensuring precise segmentation. The results indicated a strong correlation between car ownership and the ability to purchase EVs, where K-means clustering effectively identified consumer groups. The groupings also included “Not Capable at All” to “Highly Capable” individuals based on their likelihood to purchase EVs. Based on the results, the core-value customers of EVs are male, older than 55 years old, live in urban areas, own a vehicle and car insurance, and have a monthly income of more than PHP 130,000. Following those are high-value customers, considered target users expected to use EVs frequently. It could be posited that customers are frequent purchasers of products and services. Based on the results, high-value customers are male, aged 36–45 years old, live in urban areas, own a car, have car insurance, and have a monthly income of PHP 100,001–130,000. Both of these should be highly considered by EV industries, as these characteristics would be the driving market of EVs in the Philippines. The constructed segmentation provided valuable insights for the EV industry, academic institutions, and policymakers, offering a foundation for targeted marketing strategies and promoting EV adoption in the Philippines. Moreover, the sustainable marketing strategies developed could be adopted and extended among other developing countries wanting to adopt EVs for utility. Future works are also suggested based on the study limitations for researchers to consider as study extensions, such as a holistic approach to EV adoption that considers environmental, social, and economic factors, as well as policies and promotion development. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

14 pages, 8664 KiB

Open AccessArticle

A Multi-Sensor 3D Detection Method for Small Objects

by Yuekun Zhao, Suyun Luo, Xiaoci Huang and Dan Wei

World Electr. Veh. J. 2024, 15(5), 210; https://doi.org/10.3390/wevj15050210 - 10 May 2024

Cited by 2 | Viewed by 1294

Abstract

In response to the limited accuracy of current three-dimensional (3D) object detection algorithms for small objects, this paper presents a multi-sensor 3D small object detection method based on LiDAR and a camera. Firstly, the LiDAR point cloud is projected onto the image plane [...] Read more.

In response to the limited accuracy of current three-dimensional (3D) object detection algorithms for small objects, this paper presents a multi-sensor 3D small object detection method based on LiDAR and a camera. Firstly, the LiDAR point cloud is projected onto the image plane to obtain a depth image. Subsequently, we propose a cascaded image fusion module comprising multi-level pooling layers and multi-level convolution layers. This module extracts features from both the camera image and the depth image, addressing the issue of insufficient depth information in the image feature. Considering the non-uniform distribution characteristics of the LiDAR point cloud, we introduce a multi-scale voxel fusion module composed of three sets of VFE (voxel feature encoder) layers. This module partitions the point cloud into grids of different sizes to improve detection ability for small objects. Finally, the multi-level fused point features are associated with the corresponding scale’s initial voxel features to obtain the fused multi-scale voxel features, and the final detection results are obtained based on this feature. To evaluate the effectiveness of this method, experiments are conducted on the KITTI dataset, achieving a 3D AP (average precision) of 73.81% for the hard level of cars and 48.03% for the hard level of persons. The experimental results demonstrate that this method can effectively achieve 3D detection of small objects. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

21 pages, 6392 KiB

Open AccessArticle

End-to-End Differentiable Physics Temperature Estimation for Permanent Magnet Synchronous Motor

by Pengyuan Wang, Xinjian Wang and Yunpeng Wang

World Electr. Veh. J. 2024, 15(4), 174; https://doi.org/10.3390/wevj15040174 - 21 Apr 2024

Cited by 1 | Viewed by 1391

Abstract

Differentiable physics is an approach that effectively combines physical models with deep learning, providing valuable information about physical systems during the training process of neural networks. This integration enhances the generalization ability and ensures better consistency with physical principles. In this work, we [...] Read more.

Differentiable physics is an approach that effectively combines physical models with deep learning, providing valuable information about physical systems during the training process of neural networks. This integration enhances the generalization ability and ensures better consistency with physical principles. In this work, we propose a framework for estimating the temperature of a permanent magnet synchronous motor by combining neural networks with the differentiable physical thermal model, as well as utilizing the simulation results. In detail, we first implement a differentiable thermal model based on a lumped parameter thermal network within an automatic differentiation framework. Subsequently, we add a neural network to predict thermal resistances, capacitances, and losses in real time and utilize the thermal parameters’ optimized empirical values as the initial output values of the network to improve the accuracy and robustness of the final temperature estimation. We validate the conceivable advantages of the proposed method through extensive experiments based on both synthetic data and real-world data and then provide some further potential applications. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

15 pages, 6961 KiB

Open AccessArticle

Research on YOLOv5 Vehicle Detection and Positioning System Based on Binocular Vision

by Yixiao Zhang, Yuanming Gong and Xiaolong Chen

World Electr. Veh. J. 2024, 15(2), 62; https://doi.org/10.3390/wevj15020062 - 11 Feb 2024

Cited by 2 | Viewed by 2602

Abstract

Vehicle detection and location is one of the key sensing tasks of automatic driving systems. Traditional detection methods are easily affected by illumination, occlusion and scale changes in complex scenes, which limits the accuracy and robustness of detection. In order to solve these [...] Read more.

Vehicle detection and location is one of the key sensing tasks of automatic driving systems. Traditional detection methods are easily affected by illumination, occlusion and scale changes in complex scenes, which limits the accuracy and robustness of detection. In order to solve these problems, this paper proposes a vehicle detection and location method for YOLOv5(You Only Look Once version 5) based on binocular vision. Binocular vision uses two cameras to obtain images from different angles at the same time. By calculating the difference between the two images, more accurate depth information can be obtained. The YOLOv5 algorithm is improved by adding the CBAM attention mechanism and replacing the loss function to improve target detection. Combining these two techniques can achieve accurate detection and localization of vehicles in 3D space. The method utilizes the depth information of binocular images and the improved YOLOv5 target detection algorithm to achieve accurate detection and localization of vehicles in front. Experimental results show that the method has high accuracy and robustness for vehicle detection and localization tasks. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

20 pages, 2930 KiB

Open AccessArticle

A Deep Learning Method for the Health State Prediction of Lithium-Ion Batteries Based on LUT-Memory and Quantization

by Mohamed H. Al-Meer

World Electr. Veh. J. 2024, 15(2), 38; https://doi.org/10.3390/wevj15020038 - 24 Jan 2024

Cited by 1 | Viewed by 2254

Abstract

The precise determination of the state of health (SOH) of lithium-ion batteries is critical in the domain of battery management systems. The proposed model in this research paper emulates any deep learning or machine learning model by utilizing a Look Up Table (LUT) [...] Read more.

The precise determination of the state of health (SOH) of lithium-ion batteries is critical in the domain of battery management systems. The proposed model in this research paper emulates any deep learning or machine learning model by utilizing a Look Up Table (LUT) memory to store all activation inputs and their corresponding outputs. The operation that follows the completion of training is referred to as the LUT memory preparation procedure. This method’s lookup process supplants the inference process entirely and simply. This is achieved by discretizing the input data and features before binarizing them. The term for the aforementioned operation is the LUT inference method. This procedure was evaluated in this study using two distinct neural network architectures: a bidirectional long short-term memory (LSTM) architecture and a standard fully connected neural network (FCNN). It is anticipated that considerably greater efficiency and velocity will be achieved during the inference procedure when the pre-trained deep neural network architecture is inferred directly. The principal aim of this research is to construct a lookup table that effectively establishes correlations between the SOH of lithium-ion batteries and ensures a degree of imprecision that is tolerable. According to the results obtained from the NASA PCoE lithium-ion battery dataset, the proposed methodology exhibits a performance that is largely comparable to that of the initial machine learning models. Utilizing the error assessment metrics RMSE, MAE, and (MAPE), the accuracy of the SOH prediction has been quantitatively evaluated. The indicators mentioned above demonstrate a significant degree of accuracy when predicting SOH. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

15 pages, 4325 KiB

Open AccessArticle

Data-Driven Algorithm Based on Energy Consumption Estimation for Electric Bus

by Xinxin Zhao, Ming Zhang and Guangyu Xue

World Electr. Veh. J. 2023, 14(12), 329; https://doi.org/10.3390/wevj14120329 - 29 Nov 2023

Cited by 1 | Viewed by 1906

Abstract

The accurate estimation of battery state of charge (SOC) for modern electric vehicles is crucial for the range and performance of electric vehicles. This paper focuses on the historical driving data of electric buses and focuses on the extraction of driving condition feature [...] Read more.

The accurate estimation of battery state of charge (SOC) for modern electric vehicles is crucial for the range and performance of electric vehicles. This paper focuses on the historical driving data of electric buses and focuses on the extraction of driving condition feature parameters and data preprocessing. By selecting relevant parameters, a set of characteristic parameters for specific driving conditions is established, a process of constructing a battery SOC prediction model based on a Long short-term memory (LSTM) network is proposed, and different hyperparameters of the model are identified and adjusted to improve the accuracy of the prediction results. The results show that the prediction results can reach 1.9875% Root Mean Square Error (RMSE) and 1.7573% Mean Absolute Error (MAE) after choosing appropriate hyperparameters; this approach is expected to improve the performance of battery management systems and battery utilization efficiency in the field of electric vehicles. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

26 pages, 1862 KiB

Open AccessArticle

Purchasing Intentions Analysis of Hybrid Cars Using Random Forest Classifier and Deep Learning

by Ardvin Kester S. Ong, Lara Nicole Z. Cordova, Franscine Althea B. Longanilla, Neallo L. Caprecho, Rocksel Andry V. Javier, Riañina D. Borres and Josephine D. German

World Electr. Veh. J. 2023, 14(8), 227; https://doi.org/10.3390/wevj14080227 - 18 Aug 2023

Cited by 11 | Viewed by 3084

Abstract

In developed or first-world countries, hybrid cars are widely utilized and essential in technological development and reducing carbon emissions. Despite that, developing or third-world countries such as the Philippines have not yet fully adopted hybrid cars as a means of transportation. Hence, the [...] Read more.

In developed or first-world countries, hybrid cars are widely utilized and essential in technological development and reducing carbon emissions. Despite that, developing or third-world countries such as the Philippines have not yet fully adopted hybrid cars as a means of transportation. Hence, the Sustainability Theory of Planned Behavior (STPB) was developed and integrated with the UTAUT2 framework to predict the factors affecting the purchasing intentions of Filipino drivers toward hybrid cars. The study gathered 1048 valid responses using convenience and snowball sampling to holistically measure user acceptance through twelve latent variables. Machine Learning Algorithm (MLA) tools such as the Decision Tree (DT), Random Forest Classifier (RFC), and Deep Learning Neural Network (DLNN) were utilized to anticipate consumer behavior. The final results from RFC showed an accuracy of 94% and DLNN with an accuracy of 96.60%, which were able to prove the prediction of significant latent factors. Perceived Environmental Concerns (PENCs), Attitude (AT), Perceived Behavioral Control (PBC), and Performance Expectancy (PE) were observed to be the highest factors. This study is one of the first extensive studies utilizing the MLA approach to predict Filipino drivers’ tendency to acquire hybrid vehicles. The study’s results can be adapted by automakers or car companies for devising initiatives, tactics, and advertisements to promote the viability and utility of hybrid vehicles in the Philippines. Since all the factors were proven significant, future investigations can assess not only the behavioral component but also the sustainability aspect of an individual using the STPB framework. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

21 pages, 6494 KiB

Open AccessArticle

Testing Scenario Identification for Automated Vehicles Based on Deep Unsupervised Learning

by Shuai Liu, Fan Ren, Ping Li, Zhijie Li, Hao Lv and Yonggang Liu

World Electr. Veh. J. 2023, 14(8), 208; https://doi.org/10.3390/wevj14080208 - 4 Aug 2023

Viewed by 1697

Abstract

Naturalistic driving data (NDD) are valuable for testing autonomous driving systems under various driving conditions. Automatically identifying scenes from high-dimensional and unlabeled NDD remains a challenging task. This paper presents a novel approach for automatically identifying test scenarios for autonomous driving through deep [...] Read more.

Naturalistic driving data (NDD) are valuable for testing autonomous driving systems under various driving conditions. Automatically identifying scenes from high-dimensional and unlabeled NDD remains a challenging task. This paper presents a novel approach for automatically identifying test scenarios for autonomous driving through deep unsupervised learning. Firstly, US DAS2 NDD are leveraged, and the selection of data variables representing the vehicle state and surrounding environment is conducted to formulate the segmentation criterion. The isolation forest (IF) algorithm is then employed to segment the data, yielding two distinct types of datasets: typical scenarios and extreme scenarios. Secondly, a one-dimensional residual convolutional autoencoder (1D-RCAE) is developed to extract scenario features from the two datasets. Compared to four other autoencoders, the 1D-RCAE can effectively extract crucial information from high-dimensional data with optimal feature extraction capability. Next, considering the varying importance of different features, an information entropy (IE)-optimized K-means algorithm is employed to cluster the features extracted using 1D-RCAE. Finally, statistical analysis is performed on the parameters of each cluster of scenarios to explore their distribution characteristics within each class, and four typical scenarios are identified along with five extreme scenarios. The proposed unsupervised framework, combining IF, 1D-RCAE, and IE-improved K-means algorithms, can automatically identify typical and extreme scenarios from NDD. These identified scenarios can then be applied to test the performance of autonomous driving systems, enriching the library of automated driving test scenarios. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

13 pages, 2613 KiB

Open AccessEditor’s ChoiceArticle

Creating a Robust SoC Estimation Algorithm Based on LSTM Units and Trained with Synthetic Data

by Markel Azkue, Eduardo Miguel, Egoitz Martinez-Laserna, Laura Oca and Unai Iraola

World Electr. Veh. J. 2023, 14(7), 197; https://doi.org/10.3390/wevj14070197 - 24 Jul 2023

Cited by 6 | Viewed by 2265

Abstract

Creating SoC algorithms for Li-ion batteries based on neural networks requires a large amount of training data, since it is necessary to test the batteries under different conditions so that the algorithm learns the relationship between the different inputs and the output. Obtaining [...] Read more.

Creating SoC algorithms for Li-ion batteries based on neural networks requires a large amount of training data, since it is necessary to test the batteries under different conditions so that the algorithm learns the relationship between the different inputs and the output. Obtaining such data through laboratory tests is costly and time consuming; therefore, in this article, a neural network has been trained with data generated synthetically using electrochemical models. These models allow us to obtain relevant data related to different conditions at a minimum cost over a short period of time. By means of the different training rounds carried out using these data, it has been studied how the different hyperparameters affect the behaviour of the algorithm, creating a robust and accurate algorithm. To adapt this approach to new battery references or chemistries, transfer learning techniques can be employed. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

► Show Figures

Figure 1

Review

Jump to: Research

12 pages, 253 KiB

Open AccessReview

A Study to Investigate the Role and Challenges Associated with the Use of Deep Learning in Autonomous Vehicles

by Nojood O. Aljehane

World Electr. Veh. J. 2024, 15(11), 518; https://doi.org/10.3390/wevj15110518 - 12 Nov 2024

Viewed by 587

Abstract

The application of deep learning in autonomous vehicles has surged over the years with advancements in technology. This research explores the integration of deep learning algorithms into autonomous vehicles (AVs), focusing on their role in perception, decision-making, localization, mapping, and navigation. It shows [...] Read more.

The application of deep learning in autonomous vehicles has surged over the years with advancements in technology. This research explores the integration of deep learning algorithms into autonomous vehicles (AVs), focusing on their role in perception, decision-making, localization, mapping, and navigation. It shows how deep learning, as a part of machine learning, mimics the human brain’s neural networks, enabling advancements in perception, decision-making, localization, mapping, and overall navigation. Techniques like convolutional neural networks are used for image detection and steering control, while deep learning is crucial for path planning, automated parking, and traffic maneuvering. Localization and mapping are essential for AVs’ navigation, with deep learning-based object detection mechanisms like Faster R-CNN and YOLO proving effective in real-time obstacle detection. Apart from the roles, this study also revealed that the integration of deep learning in AVs faces challenges such as dataset uncertainty, sensor challenges, and model training intricacies. However, these issues can be addressed through the increased standardization of sensors and real-life testing for model training, and advancements in model compression technologies can optimize the performance of deep learning in AVs. This study concludes that deep learning plays a crucial role in enhancing the safety and reliability of AV navigation. This study contributes to the ongoing discourse on the optimal integration of deep learning in AVs, aiming to foster their safety, reliability, and societal acceptance. Full article

(This article belongs to the Special Issue Deep Learning Applications for Electric Vehicles)

Journal Menu

Journal Browser

Deep Learning Applications for Electric Vehicles

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (15 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI