Wei Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wei Chen has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
Zhanhong Wei
School of Automation and Electrical Engineering Lanzhou University of Technology Lanzhou China
6 shared publicationsXiping Pei
School of Microelectronics Industry-Education Integration, Lanzhou University of Technology
5 shared publications- Long Jin
Lanzhou University
4 shared publications Tingting Pei
4 shared publications- Zhanhong Wei
School of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou, 730050, Gansu Province, China
4 shared publications Jianghao Zhu
School of Electrical Engineering and Information Engineering, Lanzhou University of Technology. Lanzhou, 730050. China
3 shared publications
Latest Publications
- 30 October 2026
- Published by Bentham Science Publishers Ltd. in Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering)
- Vol. 19, 1-16
Fault-Diagnosis Method for Induction Motors Based on Principal Component Analysis and Multimodal Completeness-aware Fusion Network
Introduction: Multimodal motor fault diagnosis is affected by scale inconsistency among heterogeneous signals, the coexistence of short-time fault features and long-sequence dependency features, and differences in modality availability. This study aims to develop an induction motor fault-diagnosis method based on principal component analysis (PCA) and a Multimodal Completeness- Aware Fusion Network (MCAFNet), which explicitly uses modality-availability information as a completeness condition for high-level gated fusion, rather than treating zero-masked placeholders of unavailable modalities as reliable observations. Methods: Raw vibration, acoustic, temperature, and current signals are uniformly preprocessed. Modality- wise PCA compression and modality-mask construction are performed to generate unifiedlength compressed temporal representations and modality-availability indicators. A dual-unit collaborative modeling framework is then developed using a Short-Time Fault Feature Unit (STFFU) and a Long-Sequence Dependency Unit (LSDU) to extract short-time fault features and long-sequence dependency features, respectively. A Completeness-Aware Gated Fusion Module (CAGFM) encodes modality masks into completeness embeddings to condition the gated fusion of high-level features according to the modality-availability state. Results: On the full five-class test set under the observed acoustic-availability distribution, the proposed method achieves an accuracy of 99.64% and a macro-F1 score of 99.62%, exceeding the strongest in-study comparator, PCA-MCNN, by 3.42 percentage points in accuracy (99.64% vs. 96.22%). macro-F1: By encoding the modality-availability mask, CAGFM conditions the gated fusion process on the modalities present in each sample. Discussion: The results indicate that explicitly modeling modality availability helps prevent zeromasked placeholder features associated with unavailable acoustic measurements from being treated as reliable observations during feature fusion. The evidence supports the effectiveness of the proposed availability-conditioned fusion under the acoustic-availability distribution represented in the current dataset. Conclusion: The proposed method effectively integrates heterogeneous multimodal information and modality-completeness conditions and achieves high diagnostic performance under the evaluated dataset and test protocol. Its robustness under cross-load, variable-speed, and strong-noise conditions, as well as under arbitrary missing rates, temporally contiguous missing blocks, simultaneous loss of multiple modalities, and single-modality-only inputs, remains to be evaluated.
- 30 October 2026
- Published by Bentham Science Publishers Ltd. in Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering)
- Vol. 19, 1-16
Fault-Diagnosis Method for Induction Motors Based on Principal Component Analysis and Multimodal Completeness-aware Fusion Network
Introduction: Multimodal motor fault diagnosis is affected by scale inconsistency among heterogeneous signals, the coexistence of short-time fault features and long-sequence dependency features, and differences in modality availability. This study aims to develop an induction motor fault-diagnosis method based on principal component analysis (PCA) and a Multimodal Completeness- Aware Fusion Network (MCAFNet), which explicitly uses modality-availability information as a completeness condition for high-level gated fusion, rather than treating zero-masked placeholders of unavailable modalities as reliable observations. Methods: Raw vibration, acoustic, temperature, and current signals are uniformly preprocessed. Modality- wise PCA compression and modality-mask construction are performed to generate unifiedlength compressed temporal representations and modality-availability indicators. A dual-unit collaborative modeling framework is then developed using a Short-Time Fault Feature Unit (STFFU) and a Long-Sequence Dependency Unit (LSDU) to extract short-time fault features and long-sequence dependency features, respectively. A Completeness-Aware Gated Fusion Module (CAGFM) encodes modality masks into completeness embeddings to condition the gated fusion of high-level features according to the modality-availability state. Results: On the full five-class test set under the observed acoustic-availability distribution, the proposed method achieves an accuracy of 99.64% and a macro-F1 score of 99.62%, exceeding the strongest in-study comparator, PCA-MCNN, by 3.42 percentage points in accuracy (99.64% vs. 96.22%). macro-F1: By encoding the modality-availability mask, CAGFM conditions the gated fusion process on the modalities present in each sample. Discussion: The results indicate that explicitly modeling modality availability helps prevent zeromasked placeholder features associated with unavailable acoustic measurements from being treated as reliable observations during feature fusion. The evidence supports the effectiveness of the proposed availability-conditioned fusion under the acoustic-availability distribution represented in the current dataset. Conclusion: The proposed method effectively integrates heterogeneous multimodal information and modality-completeness conditions and achieves high diagnostic performance under the evaluated dataset and test protocol. Its robustness under cross-load, variable-speed, and strong-noise conditions, as well as under arbitrary missing rates, temporally contiguous missing blocks, simultaneous loss of multiple modalities, and single-modality-only inputs, remains to be evaluated.
- Open Access
- 22 October 2026
- Published by Wiley in Energy Science & Engineering
Remaining Useful Life Prediction of Photovoltaic Modules Based on Kalman Filter and Variational Inference
Long‐term field degradation of photovoltaic (PV) modules is nonstationary and uncertain. This makes RUL prediction difficult when only limited observations are available. This study proposes a rolling probabilistic RUL framework based on Kalman filtering and variational inference (VI). Each sliding window represents the current degradation stage. Within each window, Kalman filtering and Rauch–Tung–Striebel smoothing estimate the latent degradation state. A drifted Wiener process describes local degradation. VI then jointly estimates the posterior distributions of the drift, diffusion variance, and observation‐noise variance. These posteriors are used in a first‐passage‐time model to obtain the RUL distribution. The method is tested with a 12‐year field dataset and four additional module datasets. At the LAST stage, relative errors range from 0.18% to 0.44%, with a mean of 0.279%. The method also shows lower errors than the compared stochastic models for these datasets. Sensitivity results show stable performance under different prior settings and initial‐state covariances. The rolling framework supports RUL prediction under changing PV degradation conditions.
- 22 October 2026
- Published by Wiley in Energy Science & Engineering
Open AccessRemaining Useful Life Prediction of Photovoltaic Modules Based on Kalman Filter and Variational Inference
Long‐term field degradation of photovoltaic (PV) modules is nonstationary and uncertain. This makes RUL prediction difficult when only limited observations are available. This study proposes a rolling probabilistic RUL framework based on Kalman filtering and variational inference (VI). Each sliding window represents the current degradation stage. Within each window, Kalman filtering and Rauch–Tung–Striebel smoothing estimate the latent degradation state. A drifted Wiener process describes local degradation. VI then jointly estimates the posterior distributions of the drift, diffusion variance, and observation‐noise variance. These posteriors are used in a first‐passage‐time model to obtain the RUL distribution. The method is tested with a 12‐year field dataset and four additional module datasets. At the LAST stage, relative errors range from 0.18% to 0.44%, with a mean of 0.279%. The method also shows lower errors than the compared stochastic models for these datasets. Sensitivity results show stable performance under different prior settings and initial‐state covariances. The rolling framework supports RUL prediction under changing PV degradation conditions.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 13 (10) , 2423-2425
Adaptive Dynamic Trade-Off Optimization Between Manipulability and Sparsity for Redundant Manipulators
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 13 (10) , 2423-2425
Adaptive Dynamic Trade-Off Optimization Between Manipulability and Sparsity for Redundant Manipulators
- Open Access
- 14 September 2026
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 32 (2) , 642-656
Coevolutionary Neural Dynamics Considering Multiple Strategies for Nonconvex Optimization
In practical applications, solving nonconvex optimization problems plays a crucial role. However, many practical applications often encounter perturbations that may affect solutions to relevant nonconvex problems. Such perturbations are typically unavoidable. Moreover, in the presence of perturbations, most algorithms for nonconvex optimization suffer from low solution accuracy and a tendency to become trapped in local optima. This paper proposes a coevolutionary neural dynamics considering multiple strategies (CNDMS) model to address this limitation. Firstly, a modified neural dynamics model with a dual-gradient accumulation term is constructed as a local search operator, effectively exploring the local optimal value in noise. Secondly, a modified opposition-based learning method is employed to generate improved candidate solutions based on the current solution, thereby ensuring population diversity throughout the search process. Additionally, a hybrid variation strategy is utilized to mutate the global optimal solution and reduce the probability of the proposed CNDMS model falling into local optima. The global convergence and robustness of the proposed CNDMS model are proven by theoretical analyses and further validated through numerical experiments and an engineering application.
- 14 September 2026
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 32 (2) , 642-656
Open AccessCoevolutionary Neural Dynamics Considering Multiple Strategies for Nonconvex Optimization
In practical applications, solving nonconvex optimization problems plays a crucial role. However, many practical applications often encounter perturbations that may affect solutions to relevant nonconvex problems. Such perturbations are typically unavoidable. Moreover, in the presence of perturbations, most algorithms for nonconvex optimization suffer from low solution accuracy and a tendency to become trapped in local optima. This paper proposes a coevolutionary neural dynamics considering multiple strategies (CNDMS) model to address this limitation. Firstly, a modified neural dynamics model with a dual-gradient accumulation term is constructed as a local search operator, effectively exploring the local optimal value in noise. Secondly, a modified opposition-based learning method is employed to generate improved candidate solutions based on the current solution, thereby ensuring population diversity throughout the search process. Additionally, a hybrid variation strategy is utilized to mutate the global optimal solution and reduce the probability of the proposed CNDMS model falling into local optima. The global convergence and robustness of the proposed CNDMS model are proven by theoretical analyses and further validated through numerical experiments and an engineering application.
- Open Access
- 10 September 2026
- Published by Copernicus GmbH in EGUsphere
- Vol. 2026, 1-32
Reinforcement-Learning–Based Collaborative Optimization of Load Regulation and Opportunistic Maintenance of Wind Turbines
To address the difficulty in coordinating component-degradation regulation strategies with opportunistic maintenance timings over the full lifecycle of wind turbines, this study proposes a reinforcement-learning–based collaborative optimization method for wind-turbine load regulation and opportunistic maintenance (RL-OppOM).The proposed method establishes a full-lifecycle simulation environment for wind turbines by coupling wind conditions, power-load characteristics, component reliability, and maintenance restoration, and formulates graded power derating, multicomponent maintenance combinations, and operational feasibility constraints within a unified Markov decision process. A lifecycle risk-aware reward function is developed and a factorized dual-clip masked proximal policy optimization algorithm is proposed. By incorporating policy factorization, action masking, and dual clipping, the algorithm reduces the complexity of policy learning and improves training stability. Simulation validation is conducted using SCADA data from a wind farm in northern China. The results show that RL-OppOM achieves a comprehensive cost of 7.320 M CNY, which is 13.80 % and 11.65 % lower than the costs of CBM and OppM, respectively, while increasing the net profit by 2.36 % and 1.93 %. The mean and minimum turbine-health indicators are 0.6413 and 0.4491, respectively, and the number of high-risk operating days is zero.
- 10 September 2026
- Published by Copernicus GmbH in EGUsphere
- Vol. 2026, 1-32
Open AccessReinforcement-Learning–Based Collaborative Optimization of Load Regulation and Opportunistic Maintenance of Wind Turbines
To address the difficulty in coordinating component-degradation regulation strategies with opportunistic maintenance timings over the full lifecycle of wind turbines, this study proposes a reinforcement-learning–based collaborative optimization method for wind-turbine load regulation and opportunistic maintenance (RL-OppOM).The proposed method establishes a full-lifecycle simulation environment for wind turbines by coupling wind conditions, power-load characteristics, component reliability, and maintenance restoration, and formulates graded power derating, multicomponent maintenance combinations, and operational feasibility constraints within a unified Markov decision process. A lifecycle risk-aware reward function is developed and a factorized dual-clip masked proximal policy optimization algorithm is proposed. By incorporating policy factorization, action masking, and dual clipping, the algorithm reduces the complexity of policy learning and improves training stability. Simulation validation is conducted using SCADA data from a wind farm in northern China. The results show that RL-OppOM achieves a comprehensive cost of 7.320 M CNY, which is 13.80 % and 11.65 % lower than the costs of CBM and OppM, respectively, while increasing the net profit by 2.36 % and 1.93 %. The mean and minimum turbine-health indicators are 0.6413 and 0.4491, respectively, and the number of high-risk operating days is zero.
- 31 August 2026
- Published by Taylor & Francis in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects
- Vol. 48 (1)
A multi-scale collaborative optimization approach for infrared target detection of electrical apparatus in switchgear cabinets
1. Electrical apparatus in switchgear cabinets serves as a key execution and protection unit in industrial power distribution systems and intelligent manufacturing control systems, and its operatin...
- 31 August 2026
- Published by Taylor & Francis in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects
- Vol. 48 (1)
A multi-scale collaborative optimization approach for infrared target detection of electrical apparatus in switchgear cabinets
1. Electrical apparatus in switchgear cabinets serves as a key execution and protection unit in industrial power distribution systems and intelligent manufacturing control systems, and its operatin...
- Open Access
- 1 August 2026
- Published by Bentham Science Publishers Ltd. in Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering)
- Vol. 19 (1) , 1-16
Hopf Bifurcation and Chaotic Dynamics in Permanent Magnet Synchronous Wind Turbine with DC-link Coupling
Introduction/Objective: Chaotic oscillations induced by DC-link (Direct current) capacitor voltage fluctuations pose a critical threat to the stability of grid-connected permanent magnet synchronous generators (PMSGs) in wind power systems. Such nonlinear instabilities can degrade power quality and, if left unaddressed, lead to cascading failures. This study aims to develop a refined nonlinear model of the DC-link capacitor to investigate the Hopf bifurcation mechanism and the subsequent transition to chaos. Precise stability boundaries are derived, and the underlying chain of instability is elucidated. Methods: A fourth-order nonlinear model incorporating DC-link capacitor dynamics is developed, extending conventional third-order representations. The critical conditions for Hopf bifurcation are derived using the Routh–Hurwitz criterion and eigenvalue analysis of the Jacobian matrix. The onset of chaos is validated through numerical simulations, complemented by the computation of Lyapunov exponent spectra and power spectral density analysis. Results: Two critical thresholds for the voltage modulation parameter are identified at U = 7.85 and U = 16.5. Beyond these thresholds, the system undergoes Hopf bifurcation and subsequently enters chaotic regimes, as evidenced by a positive maximum Lyapunov exponent and a continuous broadband power spectrum. A chain-instability mechanism is revealed: "voltage imbalance - torque oscillation - speed instability". Discussion: These results reveal that DC-link voltage fluctuations are the primary driver of Hopf bifurcation and subsequent chaos in grid-connected PMSGs. The identified stability thresholds and chain-instability pathway provide a clear theoretical basis for converter parameter design. Furthermore, the chaotic nature implies that effective suppression strategies should prioritize active regulation of DC-link dynamics over conventional speed-loop damping alone. Conclusion: The study provides a theoretical criterion for stability and clarifies the dynamic coupling mechanism driven by DC-link parameters. These findings provide direct guidance on converter design, parameter tuning, and chaos suppression for practical PMSG-based wind energy systems.
- 1 August 2026
- Published by Bentham Science Publishers Ltd. in Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering)
- Vol. 19 (1) , 1-16
Open AccessHopf Bifurcation and Chaotic Dynamics in Permanent Magnet Synchronous Wind Turbine with DC-link Coupling
Introduction/Objective: Chaotic oscillations induced by DC-link (Direct current) capacitor voltage fluctuations pose a critical threat to the stability of grid-connected permanent magnet synchronous generators (PMSGs) in wind power systems. Such nonlinear instabilities can degrade power quality and, if left unaddressed, lead to cascading failures. This study aims to develop a refined nonlinear model of the DC-link capacitor to investigate the Hopf bifurcation mechanism and the subsequent transition to chaos. Precise stability boundaries are derived, and the underlying chain of instability is elucidated. Methods: A fourth-order nonlinear model incorporating DC-link capacitor dynamics is developed, extending conventional third-order representations. The critical conditions for Hopf bifurcation are derived using the Routh–Hurwitz criterion and eigenvalue analysis of the Jacobian matrix. The onset of chaos is validated through numerical simulations, complemented by the computation of Lyapunov exponent spectra and power spectral density analysis. Results: Two critical thresholds for the voltage modulation parameter are identified at U = 7.85 and U = 16.5. Beyond these thresholds, the system undergoes Hopf bifurcation and subsequently enters chaotic regimes, as evidenced by a positive maximum Lyapunov exponent and a continuous broadband power spectrum. A chain-instability mechanism is revealed: "voltage imbalance - torque oscillation - speed instability". Discussion: These results reveal that DC-link voltage fluctuations are the primary driver of Hopf bifurcation and subsequent chaos in grid-connected PMSGs. The identified stability thresholds and chain-instability pathway provide a clear theoretical basis for converter parameter design. Furthermore, the chaotic nature implies that effective suppression strategies should prioritize active regulation of DC-link dynamics over conventional speed-loop damping alone. Conclusion: The study provides a theoretical criterion for stability and clarifies the dynamic coupling mechanism driven by DC-link parameters. These findings provide direct guidance on converter design, parameter tuning, and chaos suppression for practical PMSG-based wind energy systems.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 73 (7) , 10303-10313
Adaptive Multiobjective Control With Collective Neural Dynamics for Motion Planning of Redundant Manipulators
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 73 (7) , 10303-10313
Adaptive Multiobjective Control With Collective Neural Dynamics for Motion Planning of Redundant Manipulators
- Open Access
- 21 May 2026
- Published by Elsevier in Energy and AI
- Vol. 25
A physics-informed collaborative interpretable framework for wind turbine anomaly detection
- 21 May 2026
- Published by Elsevier in Energy and AI
- Vol. 25
Open AccessA physics-informed collaborative interpretable framework for wind turbine anomaly detection