He Ren
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
He Ren has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Huaguang Zhang
Northeastern University
8 shared publications - Hanguang Su
Northeastern University
3 shared publications - Ji Han
School of Automation, Shenyang Institute of Engineering, Shenyang 110136, China
2 shared publications - Yingchun Wang
Northeastern University
2 shared publications - Yunfei Mu
Northeastern University
2 shared publications - Chong Liu
College of Information and Control Engineering, Xian University of Architecture and Technology, Xian, China
1 shared publication
Latest Publications
- 13 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 9797-9808
A Domain-Incremental Learning Framework Based on Defect Replay and Gaussian Mixup for Industrial Defect Detection
Incremental learning is a critical yet challenging problem in automation engineering, especially across heterogeneous domains. Existing incremental learning methods utilize mixup and mosaic techniques to replay previous knowledge. However, the saliency discrepancy between replayed samples is often ignored, leading to suboptimal accuracy. To address this problem, we propose a novel replay-based incremental learning framework that replays previous defect samples based on mixup and mosaic. To dynamically assign samples to different image augmentation techniques, a saliency score calculation mechanism is proposed by using posterior probability and spatial location. To eliminate the step noise brought by mixup, we propose a Gaussian operator-improved mixup to smoothly merge previous foregrounds with current images. Additionally, a domain-attentive distillation loss is proposed to further alleviate forgetting. Experiments on three scenarios verify the improved accuracy of the proposed method, achieving improvements of 2.4% mAP on weld defect detection, 2.7% mAP on steel defect detection and 4.0% mAP on no-service rail defect detection, respectively.
- 13 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 9797-9808
A Domain-Incremental Learning Framework Based on Defect Replay and Gaussian Mixup for Industrial Defect Detection
Incremental learning is a critical yet challenging problem in automation engineering, especially across heterogeneous domains. Existing incremental learning methods utilize mixup and mosaic techniques to replay previous knowledge. However, the saliency discrepancy between replayed samples is often ignored, leading to suboptimal accuracy. To address this problem, we propose a novel replay-based incremental learning framework that replays previous defect samples based on mixup and mosaic. To dynamically assign samples to different image augmentation techniques, a saliency score calculation mechanism is proposed by using posterior probability and spatial location. To eliminate the step noise brought by mixup, we propose a Gaussian operator-improved mixup to smoothly merge previous foregrounds with current images. Additionally, a domain-attentive distillation loss is proposed to further alleviate forgetting. Experiments on three scenarios verify the improved accuracy of the proposed method, achieving improvements of 2.4% mAP on weld defect detection, 2.7% mAP on steel defect detection and 4.0% mAP on no-service rail defect detection, respectively.
- 27 September 2025
- Published by Elsevier in ISA Transactions
- Vol. 167, 1241-1251
Dynamic load altering attack detection in cyber physical power system based on improved Kalman/ H ∞ co-filtering
- 27 September 2025
- Published by Elsevier in ISA Transactions
- Vol. 167, 1241-1251
Dynamic load altering attack detection in cyber physical power system based on improved Kalman/ H ∞ co-filtering
- 2 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 72 (1) , 193-197
ADP-Based Self-Triggered Optimal Control of Active Loads in DC Microgrid
In this brief, an adaptive dynamic programming (ADP)-based self-triggered control (STC) method was proposed to address the optimization control problem of power buffer systems in DC microgrids. The optimization control problem of power buffers is addressed in the framework of non-zero sum games to ensure mutual cooperation among power buffers. In the proposed STC mechanism, the next triggering moment is determined by the current triggering information, avoiding continuous monitoring of devices under the event-triggered control (ETC) and reducing the occupation of system communication and computing resources. Besides, an experience replay (ER) method was introduced when updating the weights of the critic neural networks (NNs). The proposed method ensures the stability of the system, eliminates the Zeno phenomenon, and leads to an adjustable positive minimum triggering interval. The effectiveness of the proposed method is ultimately verified by using a DC microgrid case study.
- 2 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 72 (1) , 193-197
ADP-Based Self-Triggered Optimal Control of Active Loads in DC Microgrid
In this brief, an adaptive dynamic programming (ADP)-based self-triggered control (STC) method was proposed to address the optimization control problem of power buffer systems in DC microgrids. The optimization control problem of power buffers is addressed in the framework of non-zero sum games to ensure mutual cooperation among power buffers. In the proposed STC mechanism, the next triggering moment is determined by the current triggering information, avoiding continuous monitoring of devices under the event-triggered control (ETC) and reducing the occupation of system communication and computing resources. Besides, an experience replay (ER) method was introduced when updating the weights of the critic neural networks (NNs). The proposed method ensures the stability of the system, eliminates the Zeno phenomenon, and leads to an adjustable positive minimum triggering interval. The effectiveness of the proposed method is ultimately verified by using a DC microgrid case study.
- 11 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 53 (1) , 334-345
Output Consensus Problem for Linear Heterogeneous Multiagent Systems With Dynamic Event-Based Impulsive Control
This article has a research on the problem of output consensus for linear heterogeneous multiagent systems (LHMASs) by using dynamic event-based impulsive control. First, according to whether the transfer of information from different agents is continuous or not, two corresponding control approaches are provided, respectively. Second, for the case of continuous information transfer, the corresponding dynamic event-triggered condition is obtained. Third, for the case that the information communication from each agent only occurs at the event-triggered time instant, two different dynamic event-triggered conditions according to whether the event-triggered time instant for each agent is same or not are proposed, respectively. For all these event-triggered mechanisms, both the output consensus conditions and the proofs of avoiding Zeno-behavior are given. Moreover, the effect of the dynamic variables belong to these dynamic event-triggered conditions on the minimum event-triggered time interval is also discussed. Finally, the analysis for a numerical example with two control approaches and the corresponding event-triggered conditions provided in this article is obtained to support our opinions.
- 11 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 53 (1) , 334-345
Output Consensus Problem for Linear Heterogeneous Multiagent Systems With Dynamic Event-Based Impulsive Control
This article has a research on the problem of output consensus for linear heterogeneous multiagent systems (LHMASs) by using dynamic event-based impulsive control. First, according to whether the transfer of information from different agents is continuous or not, two corresponding control approaches are provided, respectively. Second, for the case of continuous information transfer, the corresponding dynamic event-triggered condition is obtained. Third, for the case that the information communication from each agent only occurs at the event-triggered time instant, two different dynamic event-triggered conditions according to whether the event-triggered time instant for each agent is same or not are proposed, respectively. For all these event-triggered mechanisms, both the output consensus conditions and the proofs of avoiding Zeno-behavior are given. Moreover, the effect of the dynamic variables belong to these dynamic event-triggered conditions on the minimum event-triggered time interval is also discussed. Finally, the analysis for a numerical example with two control approaches and the corresponding event-triggered conditions provided in this article is obtained to support our opinions.
- 1 October 2021
- Published by Elsevier in Neurocomputing
- Vol. 458, 219-231
Online event-based adaptive critic design with experience replay to solve partially unknown multi-player nonzero-sum games
- 1 October 2021
- Published by Elsevier in Neurocomputing
- Vol. 458, 219-231
Online event-based adaptive critic design with experience replay to solve partially unknown multi-player nonzero-sum games
- 9 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 52 (12) , 12832-12842
Optimal Consensus Control Design for Multiagent Systems With Multiple Time Delay Using Adaptive Dynamic Programming
In this article, a novel data-based adaptive dynamic programming (ADP) method is presented to solve the optimal consensus tracking control problem for discrete-time (DT) multiagent systems (MASs) with multiple time delays. Necessary and sufficient conditions of the corresponding equivalent time-delay system are provided on the basis of the causal transformations. Benefitting from the construction of tracking error dynamics, the optimal tracking problem can be transformed into settling the Nash-equilibrium in the graphical game, which can be completed by solving the coupled Hamilton–Jacobi (HJ) equations. An error estimator is introduced to construct the tracking error of the MASs only using the input and output (I/O) data. Therefore, the designed data-based ADP algorithm can minimize the cost functions and ensure the consensus of MASs without the knowledge of system dynamics. Finally, a numerical example is given to demonstrate the effectiveness of the proposed method.
- 9 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 52 (12) , 12832-12842
Optimal Consensus Control Design for Multiagent Systems With Multiple Time Delay Using Adaptive Dynamic Programming
In this article, a novel data-based adaptive dynamic programming (ADP) method is presented to solve the optimal consensus tracking control problem for discrete-time (DT) multiagent systems (MASs) with multiple time delays. Necessary and sufficient conditions of the corresponding equivalent time-delay system are provided on the basis of the causal transformations. Benefitting from the construction of tracking error dynamics, the optimal tracking problem can be transformed into settling the Nash-equilibrium in the graphical game, which can be completed by solving the coupled Hamilton–Jacobi (HJ) equations. An error estimator is introduced to construct the tracking error of the MASs only using the input and output (I/O) data. Therefore, the designed data-based ADP algorithm can minimize the cost functions and ensure the consensus of MASs without the knowledge of system dynamics. Finally, a numerical example is given to demonstrate the effectiveness of the proposed method.
- 13 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 30 (6) , 1993-2003
Adaptive Fuzzy Prescribed Finite-Time Tracking Control for Nonlinear System With Unknown Control Directions
This article investigates the prescribed finite-time control for the nonlinear system with uncertain nonlinearity and unknown control directions. Different from the existing finite/fixed-time control methods on the basis of the fractional-order state feedback, the proposed finite-time control in this article only employs regular state feedback. The key is that a novel prescribed finite-time performance function is introduced such that the controller design is under the standard Lyapunov stability theoretical framework. A lemma is developed as a tool for coping with the coexistence of multiple Nussbaum gains for the stochastic system with unknown control directions. Fuzzy logic systems are used to approximate the uncertain nonlinear functions. Applying the backstepping structure, an adaptive fuzzy control scheme is developed. The salient characteristic of the proposed control is that the finite convergence time and the accuracy of the tracking error are independent of the initial states and design parameters, and that can be assigned in a prior. Two examples are given to demonstrate the feasibility and effectiveness of the proposed control scheme.
- 13 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 30 (6) , 1993-2003
Adaptive Fuzzy Prescribed Finite-Time Tracking Control for Nonlinear System With Unknown Control Directions
This article investigates the prescribed finite-time control for the nonlinear system with uncertain nonlinearity and unknown control directions. Different from the existing finite/fixed-time control methods on the basis of the fractional-order state feedback, the proposed finite-time control in this article only employs regular state feedback. The key is that a novel prescribed finite-time performance function is introduced such that the controller design is under the standard Lyapunov stability theoretical framework. A lemma is developed as a tool for coping with the coexistence of multiple Nussbaum gains for the stochastic system with unknown control directions. Fuzzy logic systems are used to approximate the uncertain nonlinear functions. Applying the backstepping structure, an adaptive fuzzy control scheme is developed. The salient characteristic of the proposed control is that the finite convergence time and the accuracy of the tracking error are independent of the initial states and design parameters, and that can be assigned in a prior. Two examples are given to demonstrate the feasibility and effectiveness of the proposed control scheme.
- 1 March 2020
- Published by Elsevier in Neurocomputing
- Vol. 382, 96-105
Data-based stable value iteration optimal control for unknown discrete-time systems with time delays
- 1 March 2020
- Published by Elsevier in Neurocomputing
- Vol. 382, 96-105
Data-based stable value iteration optimal control for unknown discrete-time systems with time delays
- 1 February 2020
- Published by Elsevier in Neurocomputing
- Vol. 378, 413-421
Off-policy synchronous iteration IRL method for multi-player zero-sum games with input constraints
- 1 February 2020
- Published by Elsevier in Neurocomputing
- Vol. 378, 413-421
Off-policy synchronous iteration IRL method for multi-player zero-sum games with input constraints
- 1 March 2019
- Published by Elsevier in Neurocomputing
- Vol. 335, 96-104
Integral reinforcement learning off-policy method for solving nonlinear multi-player nonzero-sum games with saturated actuator
- 1 March 2019
- Published by Elsevier in Neurocomputing
- Vol. 335, 96-104
Integral reinforcement learning off-policy method for solving nonlinear multi-player nonzero-sum games with saturated actuator