Peng Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Peng Wei has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Han-Xiong Li
Department of Systems Engineering, City University of Hong Kong, Hong Kong, China
11 shared publications - Changjun Xie
School of Automation, Wuhan University of Technology, Wuhan, China
4 shared publications - Liqun Chen
College of Urban Transportation and Logistics, Shenzhen Technology University, Shenzhen, China
3 shared publications - Yu Zhou
College of Electrical Engineering and Automation, Fuzhou University, Fuzhou, China
3 shared publications Han-Xiong Li
2 shared publications- Jinze Tao
School of Automation, Wuhan University of Technology, Wuhan 430070, China
2 shared publications
Latest Publications
- 6 August 2026
- Published by Elsevier in Measurement
- Vol. 290
Cross-scale information fusion for fault detection and hierarchical localization of distributed parameter systems
- 6 August 2026
- Published by Elsevier in Measurement
- Vol. 290
Cross-scale information fusion for fault detection and hierarchical localization of distributed parameter systems
- 13 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. PP (21682267) , 1-12
Collaborative Diagnosis of Spatiotemporal Faults and Sensor Anomalies in Parabolic Distributed Parameter Systems
Many industrial processes, such as heat transfer and chemical diffusion reactions, are typical distributed parameter systems (DPSs) characterized by strong spatiotemporal (S-T) coupling. Any component within these systems may malfunction and result in significant safety risks. This article proposes a model-based framework for the collaborative diagnosis of S-T faults and sensor anomalies in DPSs. First, based on the reduced-order model obtained through the spectral method, two sets of observers are established for process faults and sensor anomalies, respectively. Fault detection and isolation (FDI) algorithms are developed by leveraging the characteristics of these two fault types. Next, using an unknown input observer (UIO), a cooperative fault estimation algorithm capable of handling the coexistence of both fault types is designed. The stability and convergence of the proposed method are ensured through the Lyapunov direct method. Finally, numerical simulations are conducted on a heat-transfer rod. The results demonstrate that the FDI algorithm can detect and isolate S-T faults and sensor anomalies effectively. Moreover, the root-mean-square error (RMSE) of the intensity estimation remains below 0.31, further verifying the effectiveness of the proposed collaborative diagnosis algorithm.
- 13 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. PP (21682267) , 1-12
Collaborative Diagnosis of Spatiotemporal Faults and Sensor Anomalies in Parabolic Distributed Parameter Systems
Many industrial processes, such as heat transfer and chemical diffusion reactions, are typical distributed parameter systems (DPSs) characterized by strong spatiotemporal (S-T) coupling. Any component within these systems may malfunction and result in significant safety risks. This article proposes a model-based framework for the collaborative diagnosis of S-T faults and sensor anomalies in DPSs. First, based on the reduced-order model obtained through the spectral method, two sets of observers are established for process faults and sensor anomalies, respectively. Fault detection and isolation (FDI) algorithms are developed by leveraging the characteristics of these two fault types. Next, using an unknown input observer (UIO), a cooperative fault estimation algorithm capable of handling the coexistence of both fault types is designed. The stability and convergence of the proposed method are ensured through the Lyapunov direct method. Finally, numerical simulations are conducted on a heat-transfer rod. The results demonstrate that the FDI algorithm can detect and isolate S-T faults and sensor anomalies effectively. Moreover, the root-mean-square error (RMSE) of the intensity estimation remains below 0.31, further verifying the effectiveness of the proposed collaborative diagnosis algorithm.
- 24 February 2026
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 114 (4) , 253
Fuzzy spatial mapping filter-based spatiotemporal dynamics modeling and uncertainty estimation of nonlinear distributed parameter systems
- 24 February 2026
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 114 (4) , 253
Fuzzy spatial mapping filter-based spatiotemporal dynamics modeling and uncertainty estimation of nonlinear distributed parameter systems
- Open Access
- 12 November 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (22) , 10092
Bayesian–Kalman Fusion Framework for Thermal Fault Diagnosis of Battery Energy Storage Systems
Fault diagnosis of battery energy storage systems (BESSs) in dynamic operating conditions presents significant challenges due to complex spatiotemporal patterns and measurement noise. This research proposes a novel thermal fault diagnosis framework for BESSs based on Bayesian inference and a Kalman filter. Firstly, PLS-based spatiotemporal feature extraction is designed to capture temporal dependencies. Based on Bayesian global exploration and Kalman real-time weight adaptation, a dual-stage optimization strategy is proposed to derive a multiscale detection index with the dominant statistic, the residual statistic, and the module voltage similarity. A time window-based cumulative contribution strategy is constructed for precise cell localization. Finally, the experimental validation on a Li-ion battery pack demonstrates the proposed method’s superior performance: 96.92–99.90% anomaly detection rate, false alarm rate ranging from 0.10% to 7.22%, detection delays of 1–27 s, and 100% accuracy in fault localization. The proposed framework provides a comprehensive solution for safety management of BESSs and is significant for battery life and energy sustainability.
- 12 November 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (22) , 10092
Open AccessBayesian–Kalman Fusion Framework for Thermal Fault Diagnosis of Battery Energy Storage Systems
Fault diagnosis of battery energy storage systems (BESSs) in dynamic operating conditions presents significant challenges due to complex spatiotemporal patterns and measurement noise. This research proposes a novel thermal fault diagnosis framework for BESSs based on Bayesian inference and a Kalman filter. Firstly, PLS-based spatiotemporal feature extraction is designed to capture temporal dependencies. Based on Bayesian global exploration and Kalman real-time weight adaptation, a dual-stage optimization strategy is proposed to derive a multiscale detection index with the dominant statistic, the residual statistic, and the module voltage similarity. A time window-based cumulative contribution strategy is constructed for precise cell localization. Finally, the experimental validation on a Li-ion battery pack demonstrates the proposed method’s superior performance: 96.92–99.90% anomaly detection rate, false alarm rate ranging from 0.10% to 7.22%, detection delays of 1–27 s, and 100% accuracy in fault localization. The proposed framework provides a comprehensive solution for safety management of BESSs and is significant for battery life and energy sustainability.
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (11) , 21283-21295
Multimodal Underwater Transformable Agent for Efficient Marine Transportation in Dynamic Spatiotemporal Environments
Marine intelligent transportation systems (M-ITS) face challenges in achieving adaptability and efficiency under dynamic spatiotemporal (ST) environments. This paper proposes a novel multimodal underwater transformable agent (MUTA) designed as an adaptive and efficient information node for M-ITS. The MUTA integrates a biomimetic morphing wing, multi-drive propulsion system, incremental environmental perception, and an uncertainty-aware dynamic modeling framework to switch smoothly among long-range (LR) cruising, high-maneuverability (HM) operation, and synergy modes. Comprehensive lake and sea trials demonstrate that the MUTA maintains high motion precision and achieves significant energy efficiency improvements, reaching depths up to 1200 m and covering a range of over 3000km. The MUTA has achieved over 17% efficiency gain in lake and marine environments. This work provides an adaptive and efficient solution for M-ITS under uncertain marine conditions.
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (11) , 21283-21295
Multimodal Underwater Transformable Agent for Efficient Marine Transportation in Dynamic Spatiotemporal Environments
Marine intelligent transportation systems (M-ITS) face challenges in achieving adaptability and efficiency under dynamic spatiotemporal (ST) environments. This paper proposes a novel multimodal underwater transformable agent (MUTA) designed as an adaptive and efficient information node for M-ITS. The MUTA integrates a biomimetic morphing wing, multi-drive propulsion system, incremental environmental perception, and an uncertainty-aware dynamic modeling framework to switch smoothly among long-range (LR) cruising, high-maneuverability (HM) operation, and synergy modes. Comprehensive lake and sea trials demonstrate that the MUTA maintains high motion precision and achieves significant energy efficiency improvements, reaching depths up to 1200 m and covering a range of over 3000km. The MUTA has achieved over 17% efficiency gain in lake and marine environments. This work provides an adaptive and efficient solution for M-ITS under uncertain marine conditions.
- 11 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (10) , 8003-8011
Continuous Feature Reconstruction-Based Spatiotemporal Modeling of Distributed Thermal Processes Under Limited Sensing
Numerous industrial thermal processes and fluid dynamics systems can be described by distributed parameter systems (DPSs), where the inputs, outputs, and process variables vary in space and time. In this research, a continuous feature reconstruction-based spatiotemporal modeling method is introduced for DPSs under limited sensing scenarios. Initially, a discrete space completion approach is created to recuperate the spatiotemporal patterns of nonmonitored locations by limited sensors. Then, a continuous feature reconstruction method is designed for deriving continuous spatial basis functions (SBFs), which are the intrinsic characteristics of DPSs. The identification and adjustment of the nonlinear temporal model are carried out via the long short-term memory neural network. Eventually, the amalgamation of the derived SBFs and the temporal model results in a spatially continuous representation. The proposed method reduces the reliance of traditional first-principle methods on governing equations and minimizes the need for extensive sensor arrays in purely data-driven approaches. Experimental tests conducted on a pouch-type Li-ion battery demonstrate the effectiveness and superiority of the proposed spatiotemporal modeling method under limited sensing.
- 11 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (10) , 8003-8011
Continuous Feature Reconstruction-Based Spatiotemporal Modeling of Distributed Thermal Processes Under Limited Sensing
Numerous industrial thermal processes and fluid dynamics systems can be described by distributed parameter systems (DPSs), where the inputs, outputs, and process variables vary in space and time. In this research, a continuous feature reconstruction-based spatiotemporal modeling method is introduced for DPSs under limited sensing scenarios. Initially, a discrete space completion approach is created to recuperate the spatiotemporal patterns of nonmonitored locations by limited sensors. Then, a continuous feature reconstruction method is designed for deriving continuous spatial basis functions (SBFs), which are the intrinsic characteristics of DPSs. The identification and adjustment of the nonlinear temporal model are carried out via the long short-term memory neural network. Eventually, the amalgamation of the derived SBFs and the temporal model results in a spatially continuous representation. The proposed method reduces the reliance of traditional first-principle methods on governing equations and minimizes the need for extensive sensor arrays in purely data-driven approaches. Experimental tests conducted on a pouch-type Li-ion battery demonstrate the effectiveness and superiority of the proposed spatiotemporal modeling method under limited sensing.
- 6 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-10
Robust Sensor Fault Detection and Estimation for Parabolic Distributed Parameter Systems
Sensors play a key role in monitoring distributed parameter systems (DPSs), such as thermal and chemical diffusion-reaction processes. However, sensor faults can result in data distortion, degraded system performance, and even catastrophic consequences. This paper proposes a model-based sensor fault diagnosis framework for DPSs, which can effectively detect the fault time and estimate the fault intensity. The proposed method only requires the limited measured output without any state information. Besides, noise will cause perturbations in the sampling data. Correspondingly, a linear matrix inequality considering disturbance is designed. Through theoretical analysis, the convergence of fault estimation error is ensured. The effectiveness of the proposed method is verified on a heat transfer rod and a chemical diffusion-reaction system with static and time-varying sensor faults under disturbances. The root means square errors of all sensor fault estimates are within 0.1078.
- 6 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-10
Robust Sensor Fault Detection and Estimation for Parabolic Distributed Parameter Systems
Sensors play a key role in monitoring distributed parameter systems (DPSs), such as thermal and chemical diffusion-reaction processes. However, sensor faults can result in data distortion, degraded system performance, and even catastrophic consequences. This paper proposes a model-based sensor fault diagnosis framework for DPSs, which can effectively detect the fault time and estimate the fault intensity. The proposed method only requires the limited measured output without any state information. Besides, noise will cause perturbations in the sampling data. Correspondingly, a linear matrix inequality considering disturbance is designed. Through theoretical analysis, the convergence of fault estimation error is ensured. The effectiveness of the proposed method is verified on a heat transfer rod and a chemical diffusion-reaction system with static and time-varying sensor faults under disturbances. The root means square errors of all sensor fault estimates are within 0.1078.
- 6 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (7) , 7563-7572
Multiscale Fusion for Abnormality Detection and Localization of Distributed Parameter Systems
Early internal abnormalities in the distributed parameter systems (DPSs) may develop into uncontrollable thermal failures, causing serious safety incidents. However, traditional first-principle methods heavily depend on governing equations, and existing data-based single-scale methods have insufficient performance under dynamically changing conditions. Based on these considerations, the multiscale information fusion is proposed for internal abnormality detection and localization of DPSs under different scenarios. We introduce the dissimilarity statistic to identify abnormalities for lumped variables, whereas the spatial and temporal statistics are presented for abnormality detection for distributed variables. Through appropriate parameter optimization, these statistic functions are integrated into the comprehensive multiscale detection index, which outperforms traditional single-scale detection methods. The proposed multiscale statistic has good physical interpretability from the system disorder degree. Experiments on the internal short circuit (ISC) of a battery system have demonstrated that our proposed method can swiftly identify ISC abnormalities within 20 s and accurately pinpoint problematic battery cells under different testing currents and fault types.
- 6 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (7) , 7563-7572
Multiscale Fusion for Abnormality Detection and Localization of Distributed Parameter Systems
Early internal abnormalities in the distributed parameter systems (DPSs) may develop into uncontrollable thermal failures, causing serious safety incidents. However, traditional first-principle methods heavily depend on governing equations, and existing data-based single-scale methods have insufficient performance under dynamically changing conditions. Based on these considerations, the multiscale information fusion is proposed for internal abnormality detection and localization of DPSs under different scenarios. We introduce the dissimilarity statistic to identify abnormalities for lumped variables, whereas the spatial and temporal statistics are presented for abnormality detection for distributed variables. Through appropriate parameter optimization, these statistic functions are integrated into the comprehensive multiscale detection index, which outperforms traditional single-scale detection methods. The proposed multiscale statistic has good physical interpretability from the system disorder degree. Experiments on the internal short circuit (ISC) of a battery system have demonstrated that our proposed method can swiftly identify ISC abnormalities within 20 s and accurately pinpoint problematic battery cells under different testing currents and fault types.
- 6 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (4) , 2770-2778
Spatiotemporal Transform Network-Based Anomaly Detection and Localization of Distributed Parameter Systems
Due to complex spatiotemporal couplings, it is difficult to detect and locate spatiotemporal abnormal sources for distributed parameter systems (DPSs) with unknown governing equations. In this research, a spatiotemporal transform network-based anomaly detection and localization framework is proposed for unknown DPSs. Considering the orthogonality, the spatial basis functions (SBFs) are optimized by the nonlinear space–time separation network to achieve the minimal reconstruction error. The Gaussian process regression is used to identify the temporal dynamics, based on which the temporal statistic is constructed. A comprehensive statistic is designed by considering the temporal dynamics and spatial dissimilarity for reliable detection. With the spatial construction, the weighted absolute error of SBFs is constructed for anomaly localization. The anomaly detectability is proven by theoretical analysis. Experiments on a lithium-ion battery demonstrate the effectiveness and superiority of the proposed method in detecting and localizing battery internal short circuits.
- 6 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (4) , 2770-2778
Spatiotemporal Transform Network-Based Anomaly Detection and Localization of Distributed Parameter Systems
Due to complex spatiotemporal couplings, it is difficult to detect and locate spatiotemporal abnormal sources for distributed parameter systems (DPSs) with unknown governing equations. In this research, a spatiotemporal transform network-based anomaly detection and localization framework is proposed for unknown DPSs. Considering the orthogonality, the spatial basis functions (SBFs) are optimized by the nonlinear space–time separation network to achieve the minimal reconstruction error. The Gaussian process regression is used to identify the temporal dynamics, based on which the temporal statistic is constructed. A comprehensive statistic is designed by considering the temporal dynamics and spatial dissimilarity for reliable detection. With the spatial construction, the weighted absolute error of SBFs is constructed for anomaly localization. The anomaly detectability is proven by theoretical analysis. Experiments on a lithium-ion battery demonstrate the effectiveness and superiority of the proposed method in detecting and localizing battery internal short circuits.
- 25 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (1) , 729-737
Spatiotemporal Transformation-Based Neural Network With Interpretable Structure for Modeling Distributed Parameter Systems
Many industrial processes can be described by distributed parameter systems (DPSs) governed by partial differential equations (PDEs). In this research, a spatiotemporal network is proposed for DPS modeling without any process knowledge. Since traditional linear modeling methods may not work well for nonlinear DPSs, the proposed method considers the nonlinear space–time separation, which is transformed into a Lagrange dual optimization problem under the orthogonal constraint. The optimization problem can be solved by the proposed neural network with good structural interpretability. The spatial construction method is employed to derive the continuous spatial basis functions (SBFs) based on the discrete spatial features. The nonlinear temporal model is derived by the Gaussian process regression (GPR). Benefiting from spatial construction and GPR, the proposed method enables spatially continuous modeling and provides a reliable output range under the given confidence level. Experiments on a catalytic reaction process and a battery thermal process demonstrate the effectiveness and superiority of the proposed method.
- 25 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (1) , 729-737
Spatiotemporal Transformation-Based Neural Network With Interpretable Structure for Modeling Distributed Parameter Systems
Many industrial processes can be described by distributed parameter systems (DPSs) governed by partial differential equations (PDEs). In this research, a spatiotemporal network is proposed for DPS modeling without any process knowledge. Since traditional linear modeling methods may not work well for nonlinear DPSs, the proposed method considers the nonlinear space–time separation, which is transformed into a Lagrange dual optimization problem under the orthogonal constraint. The optimization problem can be solved by the proposed neural network with good structural interpretability. The spatial construction method is employed to derive the continuous spatial basis functions (SBFs) based on the discrete spatial features. The nonlinear temporal model is derived by the Gaussian process regression (GPR). Benefiting from spatial construction and GPR, the proposed method enables spatially continuous modeling and provides a reliable output range under the given confidence level. Experiments on a catalytic reaction process and a battery thermal process demonstrate the effectiveness and superiority of the proposed method.