Pub Date : 2025-07-18DOI: 10.1109/JESTIE.2025.3585475
{"title":"Officers and Vice Presidents of Co-Sponsoring Societies Information","authors":"","doi":"10.1109/JESTIE.2025.3585475","DOIUrl":"https://doi.org/10.1109/JESTIE.2025.3585475","url":null,"abstract":"","PeriodicalId":100620,"journal":{"name":"IEEE Journal of Emerging and Selected Topics in Industrial Electronics","volume":"6 3","pages":"C3-C3"},"PeriodicalIF":0.0,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11085031","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144657557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-14DOI: 10.1109/JESTIE.2025.3589164
Souradeep Bhattacharya;Mateo D. Roig Greidanus;Shantanu Gupta;Debotrinya Sur;Sudip K. Mazumder;Manimaran Govindarasu
Solid-state transformer (SST)-based power substations have emerged as a pivotal innovation for integrating distributed generation and energy storage systems within modern grid. However, SSTs’ mixed-signal nature and network-dependent control make them vulnerable to evolving cyber-physical threats, which can disrupt real-time operations, especially as attack patterns continuously evolve, making static, batch-trained anomaly detection systems (ADSs) ineffective. To address this, this article proposes a machine learning (ML)-based adaptive ADS (ML-A2D) designed to detect control feedback noise interference attacks that compromise the low-frequency closed-loop performance of SSTs. The proposed framework employs a semisupervised online learning approach, enabling continuous adaptability to new anomalies while maintaining fine-grained, real-time detection. The system was evaluated in a realistic SST hardware testbed under practical and varying attack scenarios, demonstrating robust performance with detection accuracy exceeding 96%. With an effective detection time of 0.07 ms and an overall latency of less than 200 ms within a hierarchically controlled network of ac/ac converter modules, the proposed ML-A2D offers a scalable and reliable solution to enhance the resilience of SSTs in next-generation power systems.
{"title":"Machine-Learning-Based Adaptive Anomaly Detection for Control Feedback Interferences in Solid-State Transformers","authors":"Souradeep Bhattacharya;Mateo D. Roig Greidanus;Shantanu Gupta;Debotrinya Sur;Sudip K. Mazumder;Manimaran Govindarasu","doi":"10.1109/JESTIE.2025.3589164","DOIUrl":"https://doi.org/10.1109/JESTIE.2025.3589164","url":null,"abstract":"Solid-state transformer (SST)-based power substations have emerged as a pivotal innovation for integrating distributed generation and energy storage systems within modern grid. However, SSTs’ mixed-signal nature and network-dependent control make them vulnerable to evolving cyber-physical threats, which can disrupt real-time operations, especially as attack patterns continuously evolve, making static, batch-trained anomaly detection systems (ADSs) ineffective. To address this, this article proposes a machine learning (ML)-based adaptive ADS (ML-A2D) designed to detect control feedback noise interference attacks that compromise the low-frequency closed-loop performance of SSTs. The proposed framework employs a semisupervised online learning approach, enabling continuous adaptability to new anomalies while maintaining fine-grained, real-time detection. The system was evaluated in a realistic SST hardware testbed under practical and varying attack scenarios, demonstrating robust performance with detection accuracy exceeding 96%. With an effective detection time of 0.07 ms and an overall latency of less than 200 ms within a hierarchically controlled network of ac/ac converter modules, the proposed ML-A2D offers a scalable and reliable solution to enhance the resilience of SSTs in next-generation power systems.","PeriodicalId":100620,"journal":{"name":"IEEE Journal of Emerging and Selected Topics in Industrial Electronics","volume":"6 4","pages":"1840-1852"},"PeriodicalIF":4.0,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145290216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-10DOI: 10.1109/JESTIE.2025.3585988
Shurong Zhang;Zhongrui Cui;Qin Zhang;Yueyang Li
Precisely forecasting the lifetime of lithium-ion batteries is crucial for addressing consumer worries regarding their safety and dependability. However, existing research predominantly focuses on individual degradation characteristics of batteries, neglecting their multiple degradation features or their interactions. To address these issues, this article proposes a time series method based on Transformer with a parallel self-attention mechanism to forecast the remaining useful life of lithium-ion battery. First, the method processes lithium-ion battery data through a sampling layer and integrates a time step variable block, where the latter combines a time step encoding layer and a variable encoding layer to capture degradation information from both the time and feature dimensions. The time step encoding layer learns long-term dependencies through the self-attention mechanism, while the variable encoding layer focuses on the local degradation features from different sensors. The time step encoding layer and the variable encoding layer operate in parallel to extract both temporal data and sensor degradation features. Then, these two layers focus on the different aspects within the feature vector, capturing the correlations between these features through a multihead self-attention mechanism, and determining the relative significance of each feature in forecasting the current time step. These correlations and the weighted features are fused into a new feature vector. Finally, the new feature vector is passed into the decoder to compute the prediction result. Experimental results on two classical lithium battery datasets show that our approach surpasses the existing methods in predicting battery remaining useful life.
{"title":"A Parallel Self-Attention Transformer for Predicting the Remaining Useful Life of Lithium-Ion Batteries","authors":"Shurong Zhang;Zhongrui Cui;Qin Zhang;Yueyang Li","doi":"10.1109/JESTIE.2025.3585988","DOIUrl":"https://doi.org/10.1109/JESTIE.2025.3585988","url":null,"abstract":"Precisely forecasting the lifetime of lithium-ion batteries is crucial for addressing consumer worries regarding their safety and dependability. However, existing research predominantly focuses on individual degradation characteristics of batteries, neglecting their multiple degradation features or their interactions. To address these issues, this article proposes a time series method based on Transformer with a parallel self-attention mechanism to forecast the remaining useful life of lithium-ion battery. First, the method processes lithium-ion battery data through a sampling layer and integrates a time step variable block, where the latter combines a time step encoding layer and a variable encoding layer to capture degradation information from both the time and feature dimensions. The time step encoding layer learns long-term dependencies through the self-attention mechanism, while the variable encoding layer focuses on the local degradation features from different sensors. The time step encoding layer and the variable encoding layer operate in parallel to extract both temporal data and sensor degradation features. Then, these two layers focus on the different aspects within the feature vector, capturing the correlations between these features through a multihead self-attention mechanism, and determining the relative significance of each feature in forecasting the current time step. These correlations and the weighted features are fused into a new feature vector. Finally, the new feature vector is passed into the decoder to compute the prediction result. Experimental results on two classical lithium battery datasets show that our approach surpasses the existing methods in predicting battery remaining useful life.","PeriodicalId":100620,"journal":{"name":"IEEE Journal of Emerging and Selected Topics in Industrial Electronics","volume":"6 4","pages":"1808-1818"},"PeriodicalIF":4.0,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145290234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study introduces an innovative approach to enhance the performance of grid-tied inverters (GTIs) operating with nonlinear local loads. It presents the integration of a Kalman Filter (KF) with a hybrid second-order generalized integrator (HSOGI) resonant controller. The KF accurately estimates the state variables of the inverter system, providing crucial information for precise control. Meanwhile, the HSOGI resonant controller, blending resonant control and second-order generalized integrator advantages, effectively mitigates harmonic content and enables independent active and reactive power control at the point of common coupling. The proposed topology aims to tackle harmonic distortion and fluctuations introduced by nonlinear loads while minimizing sensor requirements and addressing sampling delay and sensing noise effects on control performance. Through simulation using MATLAB Simulink and validation with a hardware prototype of a 2-kW IGBT-based three-phase voltage source inverter, the efficacy of the suggested approach is demonstrated under various loading scenarios. This research contributes a reliable method for improving power quality in GTI systems, offering potential benefits for diverse industrial applications.
{"title":"Kalman Filter Estimation Based Reduced Sensor Grid-Tied Inverter Using Hybrid-SOGI Resonant Control for Nonlinear Loads","authors":"Abhishek Majumder;Arijit Basak;Souvik Roy;Sumana Chowdhuri","doi":"10.1109/JESTIE.2025.3586182","DOIUrl":"https://doi.org/10.1109/JESTIE.2025.3586182","url":null,"abstract":"This study introduces an innovative approach to enhance the performance of grid-tied inverters (GTIs) operating with nonlinear local loads. It presents the integration of a Kalman Filter (KF) with a hybrid second-order generalized integrator (HSOGI) resonant controller. The KF accurately estimates the state variables of the inverter system, providing crucial information for precise control. Meanwhile, the HSOGI resonant controller, blending resonant control and second-order generalized integrator advantages, effectively mitigates harmonic content and enables independent active and reactive power control at the point of common coupling. The proposed topology aims to tackle harmonic distortion and fluctuations introduced by nonlinear loads while minimizing sensor requirements and addressing sampling delay and sensing noise effects on control performance. Through simulation using MATLAB Simulink and validation with a hardware prototype of a 2-kW IGBT-based three-phase voltage source inverter, the efficacy of the suggested approach is demonstrated under various loading scenarios. This research contributes a reliable method for improving power quality in GTI systems, offering potential benefits for diverse industrial applications.","PeriodicalId":100620,"journal":{"name":"IEEE Journal of Emerging and Selected Topics in Industrial Electronics","volume":"6 4","pages":"1744-1755"},"PeriodicalIF":4.0,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145290230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lithium-ion batteries are increasingly applied in electric vehicles. One serious problem with electric vehicle applications is range anxiety. The anxiety will be relieved if drivers know the future State of Charge (SOC) of batteries, and therefore, multistep-forward prediction of SOC matters. However, it is very difficult to obtain the future discharge current of lithium-ion batteries in the period. Instead, a concept of equivalent current is introduced and used to replace the future discharge current when SOC is calculated for simplification. Similarly, the real discharge power of lithium-ion batteries varies while the average discharge power is relatively constant during a trip. Then, the average discharge power of lithium-ion batteries is predicted to represent the future driving cycles. Next, the equivalent current is predicted based on the average discharge power of lithium-ion batteries. Finally, the future SOC is obtained based on the predicted average power by the connection of the equivalent current. The results show the maximum SOC prediction error is less than 3%. The 200-step forward SOC prediction error of the proposed method is 0.15% in cycled dynamic stress test discharge, which is less than that of RNN and long short-term memory.
{"title":"Multistep Forward State of Charge Prediction Method for Lithium-Ion Batteries","authors":"Houlian Wang;Aoao Wang;Zhiqiang Liu;Feng Zhou;Fatma Benkhelifa","doi":"10.1109/JESTIE.2025.3585937","DOIUrl":"https://doi.org/10.1109/JESTIE.2025.3585937","url":null,"abstract":"Lithium-ion batteries are increasingly applied in electric vehicles. One serious problem with electric vehicle applications is range anxiety. The anxiety will be relieved if drivers know the future State of Charge (SOC) of batteries, and therefore, multistep-forward prediction of SOC matters. However, it is very difficult to obtain the future discharge current of lithium-ion batteries in the period. Instead, a concept of equivalent current is introduced and used to replace the future discharge current when SOC is calculated for simplification. Similarly, the real discharge power of lithium-ion batteries varies while the average discharge power is relatively constant during a trip. Then, the average discharge power of lithium-ion batteries is predicted to represent the future driving cycles. Next, the equivalent current is predicted based on the average discharge power of lithium-ion batteries. Finally, the future SOC is obtained based on the predicted average power by the connection of the equivalent current. The results show the maximum SOC prediction error is less than 3%. The 200-step forward SOC prediction error of the proposed method is 0.15% in cycled dynamic stress test discharge, which is less than that of RNN and long short-term memory.","PeriodicalId":100620,"journal":{"name":"IEEE Journal of Emerging and Selected Topics in Industrial Electronics","volume":"6 4","pages":"1712-1722"},"PeriodicalIF":4.0,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145290231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-27DOI: 10.1109/JESTIE.2025.3583886
Yiwei Gao;Fang Zhou;Qing Gao;Kexin Zhang
The systems within the Industrial Internet of Things (IIoT) have complex structures and non-Euclidean data, which are challenging to manage. Due to the advantages of graph neural networks (GNNs) in processing non-Euclidean data and complex topologies, they are capable of handling problems in the context of the IIoT. In this work, the IIoT system is structured into multiple layers to facilitate the management of the system and the use of GNNs. GNNs are taken as node classifiers to analyze the state of each edge server in the IIoT system. However, in reality, adversarial attacks often arise in the IIoT, severely impacting system performance. Therefore, a black-box graph injection attack, Bayesian ridge regression injection attack (BRRIA), is proposed to study the impact of the internal relations on a system and to investigate the vulnerabilities of GNNs. Extensive experiments on two public datasets demonstrate the effectiveness of our attack method. In both experiments targeting specific victim nodes and those attacking a certain category of nodes by targeting critical nodes, BRRIA demonstrates a higher attack accuracy compared to an advanced method. Besides, a synthetic dataset designed to simulate industrial production processes was used to demonstrate the effectiveness of the BRRIA method.
{"title":"Bayesian Ridge Regression-Based Graph Injection Attack on IIoT","authors":"Yiwei Gao;Fang Zhou;Qing Gao;Kexin Zhang","doi":"10.1109/JESTIE.2025.3583886","DOIUrl":"https://doi.org/10.1109/JESTIE.2025.3583886","url":null,"abstract":"The systems within the Industrial Internet of Things (IIoT) have complex structures and non-Euclidean data, which are challenging to manage. Due to the advantages of graph neural networks (GNNs) in processing non-Euclidean data and complex topologies, they are capable of handling problems in the context of the IIoT. In this work, the IIoT system is structured into multiple layers to facilitate the management of the system and the use of GNNs. GNNs are taken as node classifiers to analyze the state of each edge server in the IIoT system. However, in reality, adversarial attacks often arise in the IIoT, severely impacting system performance. Therefore, a black-box graph injection attack, Bayesian ridge regression injection attack (BRRIA), is proposed to study the impact of the internal relations on a system and to investigate the vulnerabilities of GNNs. Extensive experiments on two public datasets demonstrate the effectiveness of our attack method. In both experiments targeting specific victim nodes and those attacking a certain category of nodes by targeting critical nodes, BRRIA demonstrates a higher attack accuracy compared to an advanced method. Besides, a synthetic dataset designed to simulate industrial production processes was used to demonstrate the effectiveness of the BRRIA method.","PeriodicalId":100620,"journal":{"name":"IEEE Journal of Emerging and Selected Topics in Industrial Electronics","volume":"6 4","pages":"1828-1839"},"PeriodicalIF":4.0,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145289542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study introduces innovative approach for predicting the State of Health (SOH) and Remaining Useful Life (RUL) of lithium-ion batteries, leveraging datasets from NASA and Oxford to establish a robust predictive framework. A key highlight is the development of a novel neural network architecture defined as Attentive Long Short-Term Memory (LSTM), which integrates LSTM networks with Transformer mechanisms to enhance feature extraction and time-series forecasting. The research addresses critical challenges in the domain, including the nonlinear behavior of battery degradation, diverse operating conditions, and the scarcity of historical data. The proposed AttentiveLSTM model surpasses existing approaches in predictive accuracy for both SOH and RUL. In addition, it introduces an advanced objective function combining Denoising Autoencoder (DAE) loss functions with prediction loss to improve model performance. This work not only advances predictive modeling techniques, but also contributes to the broader goal of enabling more efficient and sustainable use of electric vehicle (EV) batteries, thereby supporting the transition to eco-friendly industrial transportation systems.
{"title":"Prediction of SOH and RUL for Li-Ion Batteries in EV Based on AttentiveLSTM Multi-Task Model","authors":"Anuradha Tomar;Manvi Gupta;Jishnu Mittal;Archie Arya;Uday Varshney","doi":"10.1109/JESTIE.2025.3576185","DOIUrl":"https://doi.org/10.1109/JESTIE.2025.3576185","url":null,"abstract":"This study introduces innovative approach for predicting the State of Health (SOH) and Remaining Useful Life (RUL) of lithium-ion batteries, leveraging datasets from NASA and Oxford to establish a robust predictive framework. A key highlight is the development of a novel neural network architecture defined as Attentive Long Short-Term Memory (LSTM), which integrates LSTM networks with Transformer mechanisms to enhance feature extraction and time-series forecasting. The research addresses critical challenges in the domain, including the nonlinear behavior of battery degradation, diverse operating conditions, and the scarcity of historical data. The proposed AttentiveLSTM model surpasses existing approaches in predictive accuracy for both SOH and RUL. In addition, it introduces an advanced objective function combining Denoising Autoencoder (DAE) loss functions with prediction loss to improve model performance. This work not only advances predictive modeling techniques, but also contributes to the broader goal of enabling more efficient and sustainable use of electric vehicle (EV) batteries, thereby supporting the transition to eco-friendly industrial transportation systems.","PeriodicalId":100620,"journal":{"name":"IEEE Journal of Emerging and Selected Topics in Industrial Electronics","volume":"6 4","pages":"1733-1743"},"PeriodicalIF":4.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145290260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-28DOI: 10.1109/JESTIE.2025.3565106
Qibing Wang;Hao Yang;Hao Zhang;Jiawei Lu;Yujun Zhang;Gang Xiao;Adrian David Cheok
Fault prediction technology anticipates potential failures by examining operational data of equipment and developing deep learning models. These techniques are extensively applied in the realm of electromechanical equipment within the manufacturing industry to facilitate proactive maintenance, minimize downtime, and enhance equipment dependability. Nevertheless, within intricate engineering domains such as six-axis industrial robots, traditional prediction techniques may encounter an overwhelming computational burden and exhibit subpar performance in terms of predictive accuracy. In this study, the authors introduce the Lagrangian convolutional long short-term memory neural network (LC-LSTM) as a novel approach for predicting faults in industrial robots. By combining a convolutional neural network with a long short-term memory network (LSTM), the LC-LSTM model can effectively analyze the temporal data collected from individual axes. This integration allows for independent prediction of the rotation angle and torque for each axis. The enhanced Lagrangian neural network is not only applicable for elucidating the dynamics and kinematics of robotic arms but also for directly modeling the correlation between force and motion. Consequently, it can more accurately forecast parameters such as force, velocity, and acceleration for individual axes of industrial robots. After training 2660 sets of data containing various faults, the LC-LSTM model demonstrates the capability to predict distinct faults for each axis of industrial robots with an average accuracy of 95.45%, an average recall ratio of 95.58%, and an average precision ratio of 94.8%. In addition, this study introduces a digital twin model (DTM) for industrial robots, which combines predictive modeling with digital twin technology to facilitate real-time monitoring and accurate tracking of equipment operational status. This methodology enables more precise failure forecasts, consequently improving the general dependability and effectiveness of the machinery. Subsequently, a reinforcement learning model is suggested to adjust the twin's parameters, guaranteeing a significant level of coherence between the DTM and the actual system as time progresses. To evaluate the dependability of the DTM, we confirmed its ability to autonomously update parameters. The state of the twin model, trained on 200 datasets, is observed during different fault incidents, achieving an average accuracy of 91.4%.
{"title":"Digital-Twin-Based Modeling and Fault Prediction Method for Industrial Robots","authors":"Qibing Wang;Hao Yang;Hao Zhang;Jiawei Lu;Yujun Zhang;Gang Xiao;Adrian David Cheok","doi":"10.1109/JESTIE.2025.3565106","DOIUrl":"https://doi.org/10.1109/JESTIE.2025.3565106","url":null,"abstract":"Fault prediction technology anticipates potential failures by examining operational data of equipment and developing deep learning models. These techniques are extensively applied in the realm of electromechanical equipment within the manufacturing industry to facilitate proactive maintenance, minimize downtime, and enhance equipment dependability. Nevertheless, within intricate engineering domains such as six-axis industrial robots, traditional prediction techniques may encounter an overwhelming computational burden and exhibit subpar performance in terms of predictive accuracy. In this study, the authors introduce the Lagrangian convolutional long short-term memory neural network (LC-LSTM) as a novel approach for predicting faults in industrial robots. By combining a convolutional neural network with a long short-term memory network (LSTM), the LC-LSTM model can effectively analyze the temporal data collected from individual axes. This integration allows for independent prediction of the rotation angle and torque for each axis. The enhanced Lagrangian neural network is not only applicable for elucidating the dynamics and kinematics of robotic arms but also for directly modeling the correlation between force and motion. Consequently, it can more accurately forecast parameters such as force, velocity, and acceleration for individual axes of industrial robots. After training 2660 sets of data containing various faults, the LC-LSTM model demonstrates the capability to predict distinct faults for each axis of industrial robots with an average accuracy of 95.45%, an average recall ratio of 95.58%, and an average precision ratio of 94.8%. In addition, this study introduces a digital twin model (DTM) for industrial robots, which combines predictive modeling with digital twin technology to facilitate real-time monitoring and accurate tracking of equipment operational status. This methodology enables more precise failure forecasts, consequently improving the general dependability and effectiveness of the machinery. Subsequently, a reinforcement learning model is suggested to adjust the twin's parameters, guaranteeing a significant level of coherence between the DTM and the actual system as time progresses. To evaluate the dependability of the DTM, we confirmed its ability to autonomously update parameters. The state of the twin model, trained on 200 datasets, is observed during different fault incidents, achieving an average accuracy of 91.4%.","PeriodicalId":100620,"journal":{"name":"IEEE Journal of Emerging and Selected Topics in Industrial Electronics","volume":"6 4","pages":"1776-1794"},"PeriodicalIF":4.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145290269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-24DOI: 10.1109/JESTIE.2025.3563918
Zike Yuan;Xiaoxu Liu;Wenwei Zhang
Quadrotor unmanned aerial vehicles (UAVs) have a wide range of applications in production and daily life. To address the issues of observation and fault-tolerant control of UAVs in these applications, we propose a networked control-based event-triggered observation and fault-tolerant control scheme. In our research, by designing dynamic event-triggered thresholds, we can not only observe faults and system states in real time but also implement effective fault-tolerant control compensation based on the observation results. To dynamically optimize the event-triggering thresholds, we use the proximal policy optimization algorithm from reinforcement learning for training. By intelligently adjusting the triggering conditions, our scheme not only improves the UAV's robustness to motor faults but also saves computational resources by reducing unnecessary control updates. Through simulations and physical experiments, we have verified the effectiveness of the proposed method. The experimental results prove that the strategy significantly enhances the UAV's fault tolerance capabilities in the event of motor faults, ensuring the reliability and efficiency of UAVs when performing critical tasks. This research provides new technical support for the operation of UAVs in application environments.
{"title":"Intelligent Event-Triggering Fault Estimation and Fault Tolerant Control of a Quadrotor UAV With Actuator Fault","authors":"Zike Yuan;Xiaoxu Liu;Wenwei Zhang","doi":"10.1109/JESTIE.2025.3563918","DOIUrl":"https://doi.org/10.1109/JESTIE.2025.3563918","url":null,"abstract":"Quadrotor unmanned aerial vehicles (UAVs) have a wide range of applications in production and daily life. To address the issues of observation and fault-tolerant control of UAVs in these applications, we propose a networked control-based event-triggered observation and fault-tolerant control scheme. In our research, by designing dynamic event-triggered thresholds, we can not only observe faults and system states in real time but also implement effective fault-tolerant control compensation based on the observation results. To dynamically optimize the event-triggering thresholds, we use the proximal policy optimization algorithm from reinforcement learning for training. By intelligently adjusting the triggering conditions, our scheme not only improves the UAV's robustness to motor faults but also saves computational resources by reducing unnecessary control updates. Through simulations and physical experiments, we have verified the effectiveness of the proposed method. The experimental results prove that the strategy significantly enhances the UAV's fault tolerance capabilities in the event of motor faults, ensuring the reliability and efficiency of UAVs when performing critical tasks. This research provides new technical support for the operation of UAVs in application environments.","PeriodicalId":100620,"journal":{"name":"IEEE Journal of Emerging and Selected Topics in Industrial Electronics","volume":"6 4","pages":"1863-1872"},"PeriodicalIF":4.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145290247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-24DOI: 10.1109/JESTIE.2025.3564119
Theofilos Papadopoulos;Antonios Antonopoulos
This article proposes a simple and accurate monomial-like equation for estimating the inductance of multilayer rectangle-shaped planar windings for high-frequency, high-power applications. The equation consists of the power product of the geometrical dimensions, raised at individual power coefficients. The coefficients are generated via multiple linear regression, based on a large set of approximately 6000 simulated windings, with an 80/20 training/evaluation sample ratio. The resulting mean error value is $mu$=0%, with a standard deviation below 1.8%. The accuracy of the inductance estimation is confirmed on several experimental samples, with dimensions both within and outside the initial training dataset.
{"title":"Inductance Estimation for High-Power Multilayer Rectangle Planar Windings","authors":"Theofilos Papadopoulos;Antonios Antonopoulos","doi":"10.1109/JESTIE.2025.3564119","DOIUrl":"https://doi.org/10.1109/JESTIE.2025.3564119","url":null,"abstract":"This article proposes a simple and accurate monomial-like equation for estimating the inductance of multilayer rectangle-shaped planar windings for high-frequency, high-power applications. The equation consists of the power product of the geometrical dimensions, raised at individual power coefficients. The coefficients are generated via multiple linear regression, based on a large set of approximately 6000 simulated windings, with an 80/20 training/evaluation sample ratio. The resulting mean error value is <inline-formula><tex-math>$mu$</tex-math></inline-formula>=0%, with a standard deviation below 1.8%. The accuracy of the inductance estimation is confirmed on several experimental samples, with dimensions both within and outside the initial training dataset.","PeriodicalId":100620,"journal":{"name":"IEEE Journal of Emerging and Selected Topics in Industrial Electronics","volume":"6 3","pages":"1082-1088"},"PeriodicalIF":0.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144657505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：