Defeng He
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
Research Subjects
Defeng He has a total of 148 co-authors. Here are the top co-authors by number of shared publications:
- Haiping Du
University of Wollongong
17 shared publications - Xiulan Song
Zhejiang University of Technology
12 shared publications - Chenhui Xu
Zhejiang University of Technology
8 shared publications - Yun Chen
School of Automation Hangzhou Dianzi University Hangzhou China
6 shared publications Haiping Du
School of Electrical, Computer and Telecommunications Engineering, University of Wollongong Wollongong Australia
5 shared publicationsJianbin Mu
5 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (11) , 15067-15083
Trust-Aware Distributed Predictive Control for Security Enhancement of Heterogeneous Vehicle Platoons Over Zero-Trust Asynchronous Communication Network
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (11) , 15067-15083
Trust-Aware Distributed Predictive Control for Security Enhancement of Heterogeneous Vehicle Platoons Over Zero-Trust Asynchronous Communication Network
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (11) , 9657-9668
Serial Shrinkage Attention-ResNet Based Efficient Photovoltaic Fault Diagnosis Under Similar I–V Signals
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (11) , 9657-9668
Serial Shrinkage Attention-ResNet Based Efficient Photovoltaic Fault Diagnosis Under Similar I–V Signals
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (20) , 47873-47883
Prediction-Based Event-Triggered Platooning Control of Heterogeneous Connected Vehicles Under Stochastic Deception Attacks
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (20) , 47873-47883
Prediction-Based Event-Triggered Platooning Control of Heterogeneous Connected Vehicles Under Stochastic Deception Attacks
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 73 (10) , 15263-15274
Edge-Dependent Distributed Moving Horizon Estimation With Application to UGV Localization
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 73 (10) , 15263-15274
Edge-Dependent Distributed Moving Horizon Estimation With Application to UGV Localization
- 11 September 2026
- Published by Wiley in Asian Journal of Control
Distributed Event‐Triggered Moving Horizon Estimation for Remote Monitoring of Bus Active Suspension Systems Over Relay Networks
This paper addresses the problem of remote state estimation for active suspension systems (ASSs) in electric buses and proposes a novel distributed moving horizon estimation (DMHE) algorithm. To reduce computational complexity, the full‐vehicle ASS is decomposed into several interconnected low‐order subsystems. An event‐triggered mechanism (ETM) is introduced to reduce unnecessary data transmissions from the ASS to the remote monitoring platform. Besides, filter‐and‐forward relays are employed to improve communication reliability. On this basis, a distributed moving horizon estimator is constructed, which integrates measurements and relay data to estimate the system state. Furthermore, in view of the coupling between subsystems, a consensus cost is developed to improve estimation accuracy. Sufficient conditions are derived to guarantee the boundedness of the estimation error. Finally, the effectiveness of the proposed algorithm is verified through co‐simulations in CarSim/Simulink and experiments on a half‐vehicle ASS.
- 11 September 2026
- Published by Wiley in Asian Journal of Control
Distributed Event‐Triggered Moving Horizon Estimation for Remote Monitoring of Bus Active Suspension Systems Over Relay Networks
This paper addresses the problem of remote state estimation for active suspension systems (ASSs) in electric buses and proposes a novel distributed moving horizon estimation (DMHE) algorithm. To reduce computational complexity, the full‐vehicle ASS is decomposed into several interconnected low‐order subsystems. An event‐triggered mechanism (ETM) is introduced to reduce unnecessary data transmissions from the ASS to the remote monitoring platform. Besides, filter‐and‐forward relays are employed to improve communication reliability. On this basis, a distributed moving horizon estimator is constructed, which integrates measurements and relay data to estimate the system state. Furthermore, in view of the coupling between subsystems, a consensus cost is developed to improve estimation accuracy. Sufficient conditions are derived to guarantee the boundedness of the estimation error. Finally, the effectiveness of the proposed algorithm is verified through co‐simulations in CarSim/Simulink and experiments on a half‐vehicle ASS.
- 6 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (7) , 8401-8410
Transferable Model-Based Reinforcement Learning for Vehicular Platoon Control
The learning efficiency remains a critical impediment to the practical application of connected and automated vehicles (CAVs). This paper proposes a transferable model-based reinforcement learning (TMBRL) strategy to enhance the sample efficiency and learning rate of CAVs. Specifically, a surrogate policy model is established by capturing state transitions between the actual environment and the vehicle within traffic scenarios. Then, a model-based reinforcement learning (MBRL) approach is established utilizing a surrogate model and a soft actor-critic algorithm. To improve the learning efficiency of platoon control algorithm, a transfer learning method is implemented to MBRL framework. Specifically, the trained surrogate model of vehicles in the source domain is transferred to vehicles in the target domain, and the latter just should update the surrogate model in terms of the individual dynamic characteristics and tasks. Finally, a platoon experiment platform with Prescan software is conducted. The experimental evaluation demonstrates that the TMBRL strategy significantly outperforms conventional reinforcement learning approaches, achieving higher average cumulative reward of 47 and demonstrating a 16% improvement in training success rate. Comparative analysis further reveals that the proposed TMBRL strategy exhibits superior robustness in platoon tracking tasks, maintaining enhanced trajectory tracking precision and stability under dynamic environmental conditions.
- 6 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (7) , 8401-8410
Transferable Model-Based Reinforcement Learning for Vehicular Platoon Control
The learning efficiency remains a critical impediment to the practical application of connected and automated vehicles (CAVs). This paper proposes a transferable model-based reinforcement learning (TMBRL) strategy to enhance the sample efficiency and learning rate of CAVs. Specifically, a surrogate policy model is established by capturing state transitions between the actual environment and the vehicle within traffic scenarios. Then, a model-based reinforcement learning (MBRL) approach is established utilizing a surrogate model and a soft actor-critic algorithm. To improve the learning efficiency of platoon control algorithm, a transfer learning method is implemented to MBRL framework. Specifically, the trained surrogate model of vehicles in the source domain is transferred to vehicles in the target domain, and the latter just should update the surrogate model in terms of the individual dynamic characteristics and tasks. Finally, a platoon experiment platform with Prescan software is conducted. The experimental evaluation demonstrates that the TMBRL strategy significantly outperforms conventional reinforcement learning approaches, achieving higher average cumulative reward of 47 and demonstrating a 16% improvement in training success rate. Comparative analysis further reveals that the proposed TMBRL strategy exhibits superior robustness in platoon tracking tasks, maintaining enhanced trajectory tracking precision and stability under dynamic environmental conditions.
- 17 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (3) , 4672-4682
Transfer Learning-Enhanced Multiobjective Predictive Control for Electric Vehicular Platoon
The growing adoption of connected and automated vehicles has led to significant advancements in intelligent transportation. The computational efficiency stands as a critical bottleneck in the commercialization of connected and automated vehicles. This article proposes a novel transfer learning-enhanced multiobjective predictive control strategy to mitigate the adverse effects of computational burden for vehicular platoon. A data-driven platoon model is established with subspace identification to characterize the nonideal driving behavior and complex powertrain structure of electric vehicles. To balance multiobjective conflicts among driving safety, driving comfort, and energy economy, a multiobjective cost function incorporating the predictive sequence is designed. Then, a gray wolf optimizer is devised to guide the search process, with the goal of achieving globally optimal tradeoffs. Here, the knowledge of vehicles in the source domain, such as data-driven models and controller hyperparameters, is transferred to vehicles in the target domain. Based on the knowledge, each vehicle in the target domain should just update the knowledge in terms of the individual dynamic characteristics and tasks. With this in mind, a transfer learning-enhanced multiobjective predictive control strategy is developed to enhance the performance of tasks in the target domain. Finally, a hardware-in-the-loop experiment platform with the Carmaker and the driving simulator is conducted. The experimental results demonstrate that our proposed transfer learning-enhanced multiobjective predictive control strategy could improve the 28.8% computational efficiency while ensuring the satisfied platoon tracking performance.
- 17 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (3) , 4672-4682
Transfer Learning-Enhanced Multiobjective Predictive Control for Electric Vehicular Platoon
The growing adoption of connected and automated vehicles has led to significant advancements in intelligent transportation. The computational efficiency stands as a critical bottleneck in the commercialization of connected and automated vehicles. This article proposes a novel transfer learning-enhanced multiobjective predictive control strategy to mitigate the adverse effects of computational burden for vehicular platoon. A data-driven platoon model is established with subspace identification to characterize the nonideal driving behavior and complex powertrain structure of electric vehicles. To balance multiobjective conflicts among driving safety, driving comfort, and energy economy, a multiobjective cost function incorporating the predictive sequence is designed. Then, a gray wolf optimizer is devised to guide the search process, with the goal of achieving globally optimal tradeoffs. Here, the knowledge of vehicles in the source domain, such as data-driven models and controller hyperparameters, is transferred to vehicles in the target domain. Based on the knowledge, each vehicle in the target domain should just update the knowledge in terms of the individual dynamic characteristics and tasks. With this in mind, a transfer learning-enhanced multiobjective predictive control strategy is developed to enhance the performance of tasks in the target domain. Finally, a hardware-in-the-loop experiment platform with the Carmaker and the driving simulator is conducted. The experimental results demonstrate that our proposed transfer learning-enhanced multiobjective predictive control strategy could improve the 28.8% computational efficiency while ensuring the satisfied platoon tracking performance.
- 22 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (5) , 5398-5409
Secure Platooning Control for Connected Vehicles Subject to Hybrid Stochastic Cyber-Attacks
Vehicle platooning systems have received widespread attention for their efficiency and safety. However, cybersecurity concerns on cyber-attack threats, are becoming increasingly prominent in automotive community. Given the stochastic nature of cyber-attacks, a platoon may be suffered from multiple attacks in temporal and spatial perspectives. This paper proposes a new secure platooning control method for connected vehicles under hybrid stochastic cyber-attacks. Combining the state feedback idea and the characteristics of different cyber-attacks, a unified platooning model is established to describe the attack situation of vehicles in the platoon. Using the Lyapunov’s arguments, the conditions for achieving the stability performance are established, and the controller’s gains are dynamically adjusted to respond to the state variations of the vehicles under the cyber-attacks. The co-simulation consisting of Carsim and Simulink on six vehicles under hybrid stochastic cyber-attacks and actual-vehicle platform experiments jointly verify the performance and merits of the proposed secure platooning controller.
- 22 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (5) , 5398-5409
Secure Platooning Control for Connected Vehicles Subject to Hybrid Stochastic Cyber-Attacks
Vehicle platooning systems have received widespread attention for their efficiency and safety. However, cybersecurity concerns on cyber-attack threats, are becoming increasingly prominent in automotive community. Given the stochastic nature of cyber-attacks, a platoon may be suffered from multiple attacks in temporal and spatial perspectives. This paper proposes a new secure platooning control method for connected vehicles under hybrid stochastic cyber-attacks. Combining the state feedback idea and the characteristics of different cyber-attacks, a unified platooning model is established to describe the attack situation of vehicles in the platoon. Using the Lyapunov’s arguments, the conditions for achieving the stability performance are established, and the controller’s gains are dynamically adjusted to respond to the state variations of the vehicles under the cyber-attacks. The co-simulation consisting of Carsim and Simulink on six vehicles under hybrid stochastic cyber-attacks and actual-vehicle platform experiments jointly verify the performance and merits of the proposed secure platooning controller.