Yuxiang Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuxiang Hu has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Xuewu Dai
Department of Mathematics, Physics and Electrical Engineering, Northumbria University, Newcastle upon Tyne NE1 8ST, UK
7 shared publications - Dongliang Cui
State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China
5 shared publications - Haixing Zhu
Hebei university of Technology
4 shared publications - Qidi Hu
Hebei university of Technology
4 shared publications - Weipeng Liu
Hebei university of Technology
4 shared publications - Jixuan Wang
Hebei university of Technology
3 shared publications
Latest Publications
- 20 January 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (5)
A remaining useful life prediction network using spatio-temporal soft threshold unit and adaptive multi-task weight allocation with missing sensor data
Accurate remaining useful life (RUL) prediction is essential for predictive maintenance. However, incomplete sensor data disrupts spatio-temporal dependencies and degrades prediction accuracy. The existing two-stage methods generate the amplification of errors by decoupling interpolation and prediction, and the end-to-end models struggle to capture both spatial coupling and temporal degradation continuity. Moreover, fixed task weights further limit adaptability under varying levels of missing data. To overcome these challenges, this paper proposes a multi-task spatio-temporal residual shrinkage network (ST-RSMTNet) combined a spatio-temporal residual shrinkage block (ST-RSBU) with a progressive multi-task learning strategy. The introduction of ST-RSBU adaptively filters degradation-related features across sensor channels and restores interrupted temporal trends via global sequence statistics. The proposed multi-task framework jointly optimizes imputation and prediction within an "imputation-predict" closed loop. Extensive experiments on the C-MAPSS and PHM2010 datasets show that the ST-RSMTNet maintains robustness under high missing rates. It achieves RMSE reductions of 7.29% on FD001 and 10.83% on PHM2010 C1 compared with the second-best approach. This network outperforms most state-of-the-art methods. The results demonstrate that the ST-RSMTNet is an effective solution for industrial prognostics under incomplete sensing condition. This work proposes a novel solution to the data deficiency challenges and provides crucial theoretical support for reliability of complex industrial systems in the future.
- 20 January 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (5)
A remaining useful life prediction network using spatio-temporal soft threshold unit and adaptive multi-task weight allocation with missing sensor data
Accurate remaining useful life (RUL) prediction is essential for predictive maintenance. However, incomplete sensor data disrupts spatio-temporal dependencies and degrades prediction accuracy. The existing two-stage methods generate the amplification of errors by decoupling interpolation and prediction, and the end-to-end models struggle to capture both spatial coupling and temporal degradation continuity. Moreover, fixed task weights further limit adaptability under varying levels of missing data. To overcome these challenges, this paper proposes a multi-task spatio-temporal residual shrinkage network (ST-RSMTNet) combined a spatio-temporal residual shrinkage block (ST-RSBU) with a progressive multi-task learning strategy. The introduction of ST-RSBU adaptively filters degradation-related features across sensor channels and restores interrupted temporal trends via global sequence statistics. The proposed multi-task framework jointly optimizes imputation and prediction within an "imputation-predict" closed loop. Extensive experiments on the C-MAPSS and PHM2010 datasets show that the ST-RSMTNet maintains robustness under high missing rates. It achieves RMSE reductions of 7.29% on FD001 and 10.83% on PHM2010 C1 compared with the second-best approach. This network outperforms most state-of-the-art methods. The results demonstrate that the ST-RSMTNet is an effective solution for industrial prognostics under incomplete sensing condition. This work proposes a novel solution to the data deficiency challenges and provides crucial theoretical support for reliability of complex industrial systems in the future.
- 9 January 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (4)
Nonlinear coupling calculation method based on Kolmogorov-Arnold attention dynamic spatiotemporal graph for remaining useful life prediction
Remaining useful life (RUL) prediction is a key aspect of prognostics and health management. It is essential for ensuring the reliability and operational safety of mechanical equipment. Graph Attention Networks (GATs) are an emerging approach for RUL prediction through the innovative integration of graph structures and attention mechanisms. However, existing graph structures fail to establish the correlations between different sensors at different timestamps. Furthermore, the attention mechanism of traditional GATs exhibits insufficient capability in capturing complex nonlinear dependencies between nodes. To overcome these limitations, this paper proposes a nonlinear coupling spatiotemporal graph attention network (NCST-GAT) for RUL prediction. First, a spatiotemporal graph structure construction method is designed to integrate sensor nodes across timestamps. Then, a multiplicative Kolmogorov-Arnold attention mechanism is proposed to replace the standard multilayer perceptron in attention scoring functions, significantly enhancing the modeling of nonlinear interactions among nodes and yielding more expressive feature representations to predict RUL. Experimental results on the CMAPSS and PHM2010 datasets demonstrate that the proposed NCST-GAT achieves an average improvement of 6.1% and 15.6% for RMSE and prognostic Score metrics respectively over state-of-the-art methods, exhibiting strong predictive performance and generalization capability.
- 9 January 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (4)
Nonlinear coupling calculation method based on Kolmogorov-Arnold attention dynamic spatiotemporal graph for remaining useful life prediction
Remaining useful life (RUL) prediction is a key aspect of prognostics and health management. It is essential for ensuring the reliability and operational safety of mechanical equipment. Graph Attention Networks (GATs) are an emerging approach for RUL prediction through the innovative integration of graph structures and attention mechanisms. However, existing graph structures fail to establish the correlations between different sensors at different timestamps. Furthermore, the attention mechanism of traditional GATs exhibits insufficient capability in capturing complex nonlinear dependencies between nodes. To overcome these limitations, this paper proposes a nonlinear coupling spatiotemporal graph attention network (NCST-GAT) for RUL prediction. First, a spatiotemporal graph structure construction method is designed to integrate sensor nodes across timestamps. Then, a multiplicative Kolmogorov-Arnold attention mechanism is proposed to replace the standard multilayer perceptron in attention scoring functions, significantly enhancing the modeling of nonlinear interactions among nodes and yielding more expressive feature representations to predict RUL. Experimental results on the CMAPSS and PHM2010 datasets demonstrate that the proposed NCST-GAT achieves an average improvement of 6.1% and 15.6% for RMSE and prognostic Score metrics respectively over state-of-the-art methods, exhibiting strong predictive performance and generalization capability.
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75 (00189529) , 181-192
Detection and Identification of Sensor and Actuator Faults in Multiagent Systems: An Attack-Immune Sensor/Actuator Fault Decoupling Observer
This article presents a novel distributed attack-immune fault detection and identification observer (AI-FDIO) for the detection and isolation of sensor and actuator faults in multiagent systems that operate under an attack-immune consensus protocol and are subject to input disturbances. The protocol relies solely on relative output information between neighboring agents, directly measured by local sensors. Based on this locally acquired information, the AI-FDIO performs sensor and actuator fault detection without requiring interagent communication, thereby reducing vulnerability to cyberattacks. Traditional observer-based methods typically decouple residuals from control inputs, making them ineffective in detecting sensor faults that directly affect control signals. In contrast, the proposed AI-FDIO can effectively decouple sensor fault indicators from actuator faults and input disturbances—and vice versa—without relying on any prior knowledge of the faults. A systematic design methodology is presented, and simulation studies on transport aircraft with short-period dynamics and two-wheeled self-balancing robots demonstrate the effectiveness and robustness of the proposed AI-FDIO.
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75 (00189529) , 181-192
Detection and Identification of Sensor and Actuator Faults in Multiagent Systems: An Attack-Immune Sensor/Actuator Fault Decoupling Observer
This article presents a novel distributed attack-immune fault detection and identification observer (AI-FDIO) for the detection and isolation of sensor and actuator faults in multiagent systems that operate under an attack-immune consensus protocol and are subject to input disturbances. The protocol relies solely on relative output information between neighboring agents, directly measured by local sensors. Based on this locally acquired information, the AI-FDIO performs sensor and actuator fault detection without requiring interagent communication, thereby reducing vulnerability to cyberattacks. Traditional observer-based methods typically decouple residuals from control inputs, making them ineffective in detecting sensor faults that directly affect control signals. In contrast, the proposed AI-FDIO can effectively decouple sensor fault indicators from actuator faults and input disturbances—and vice versa—without relying on any prior knowledge of the faults. A systematic design methodology is presented, and simulation studies on transport aircraft with short-period dynamics and two-wheeled self-balancing robots demonstrate the effectiveness and robustness of the proposed AI-FDIO.
- 17 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 13 (1) , 312-322
Fixed-Time Sensor Fault Detection Observer With Actuator Fault Decoupling for Attack-Free Consensus Systems
This paper studies a fixed-time attack-free actuator fault decoupling observer (FTAF-AFDO) for sensor fault detection in multi-agent systems employing the attack-free consensus protocol, where only the local information of the monitored agent and the relative output information between agents measured by its internal sensors are available. The main difficulty is that the sensor faults studied here directly affect the control signal rather than the agent's local output, causing traditional observers based on control inputs and outputs to fail in detecting such sensor faults. In addition, sensor faults and actuator faults are coupled, as the relative output information measured by sensors is directly involved in the design of attack-free consensus protocol. To tackle these difficulties, we developed the FTAF-AFDO, inspired by unknown input observer and Luenberger observer. This observer generates a sensor fault indicator signal that fully decouples from estimation errors and actuator faults within a fixed time, without needing any prior knowledge of the actuator faults. Additionally, leveraging the proposed FTAF-AFDO, a distributed attack-free consensus protocol is developed, capable of completely isolating the impact of actuator faults. The effectiveness of the proposed method is validated through simulations of a formation-flying transport aircraft system.
- 17 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 13 (1) , 312-322
Fixed-Time Sensor Fault Detection Observer With Actuator Fault Decoupling for Attack-Free Consensus Systems
This paper studies a fixed-time attack-free actuator fault decoupling observer (FTAF-AFDO) for sensor fault detection in multi-agent systems employing the attack-free consensus protocol, where only the local information of the monitored agent and the relative output information between agents measured by its internal sensors are available. The main difficulty is that the sensor faults studied here directly affect the control signal rather than the agent's local output, causing traditional observers based on control inputs and outputs to fail in detecting such sensor faults. In addition, sensor faults and actuator faults are coupled, as the relative output information measured by sensors is directly involved in the design of attack-free consensus protocol. To tackle these difficulties, we developed the FTAF-AFDO, inspired by unknown input observer and Luenberger observer. This observer generates a sensor fault indicator signal that fully decouples from estimation errors and actuator faults within a fixed time, without needing any prior knowledge of the actuator faults. Additionally, leveraging the proposed FTAF-AFDO, a distributed attack-free consensus protocol is developed, capable of completely isolating the impact of actuator faults. The effectiveness of the proposed method is validated through simulations of a formation-flying transport aircraft system.
- 4 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 72 (10) , 5872-5884
OD-TGCN: An Observer-Driven Temporal Graph Convolutional Network for Early Fault Detection of Control Systems
Early faults, with their small amplitudes and slow variations, are easily masked by noise or process trends, making detection difficult. Also, observer-based methods struggle with timely and accurate early fault detection. To address these challenges, a novel observer-driven temporal graph convolutional network (OD-TGCN) is proposed for early fault detection of control systems subject to semi-stationary periodic input disturbances and measurement noise. We employ graph representation to describe the mechanistic relationships and capture temporal features between variables in the control system. First, graph nodes are constructed based on the control inputs, output signals of the control systems and the fault detection residual of the disturbance decoupling generalized proportional-integral observer (DD-GPIO). Then, a method for constructing the adjacency matrix of the graph based on the system matrix is provided. Finally, the output of the temporal graph convolutional network (TGCN) is passed to a Multi-Layer Perceptron (MLP) for graph-based fault detection. The proposed method is applied to a two-wheeled self-balancing robot. Comparative results show that OD-TGCN significantly outperforms DD-GPIO and typical TGCN in early fault detection accuracy. Additionally, OD-TGCN exhibits notable robustness across datasets with different disturbances/noise.
- 4 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 72 (10) , 5872-5884
OD-TGCN: An Observer-Driven Temporal Graph Convolutional Network for Early Fault Detection of Control Systems
Early faults, with their small amplitudes and slow variations, are easily masked by noise or process trends, making detection difficult. Also, observer-based methods struggle with timely and accurate early fault detection. To address these challenges, a novel observer-driven temporal graph convolutional network (OD-TGCN) is proposed for early fault detection of control systems subject to semi-stationary periodic input disturbances and measurement noise. We employ graph representation to describe the mechanistic relationships and capture temporal features between variables in the control system. First, graph nodes are constructed based on the control inputs, output signals of the control systems and the fault detection residual of the disturbance decoupling generalized proportional-integral observer (DD-GPIO). Then, a method for constructing the adjacency matrix of the graph based on the system matrix is provided. Finally, the output of the temporal graph convolutional network (TGCN) is passed to a Multi-Layer Perceptron (MLP) for graph-based fault detection. The proposed method is applied to a two-wheeled self-balancing robot. Comparative results show that OD-TGCN significantly outperforms DD-GPIO and typical TGCN in early fault detection accuracy. Additionally, OD-TGCN exhibits notable robustness across datasets with different disturbances/noise.
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-4
Sensor Fault Detection for CPS Under Attack-Free Consensus Protocol
This brief investigates the detection of sensor faults in muti-agent cyber-physical systems under attack-free consensus protocols when actuators also fail. A distributed fault detection observer is proposed, which enables decoupling between fault indication signals and actuator faults without requiring any prior knowledge about actuator faults. The proposed method’s effectiveness is validated through the simulations conducted on a fleet of transport aircraft with short-period dynamics.
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-4
Sensor Fault Detection for CPS Under Attack-Free Consensus Protocol
This brief investigates the detection of sensor faults in muti-agent cyber-physical systems under attack-free consensus protocols when actuators also fail. A distributed fault detection observer is proposed, which enables decoupling between fault indication signals and actuator faults without requiring any prior knowledge about actuator faults. The proposed method’s effectiveness is validated through the simulations conducted on a fleet of transport aircraft with short-period dynamics.
- 4 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 71 (12) , 5044-5048
Anomaly Identification for Cyber-Physical Systems Subject to Replay Attacks and Sensor Faults
This brief investigates the identification of replay attacks and sensor faults in cyber-physical systems subject to periodic disturbances. For each type of anomaly (replay attack or sensor fault), an anomaly identification framework consisting of an adaptive anomaly isolation estimator (AIE) and an anomaly identification processor (AIP) is proposed. By dynamically configuring the blocking zeros within AIE and through co-design with the compensation signal inside AIP, decoupling between the watermarks generated by AIPs for anomaly identification and periodic disturbances can be achieved. Numerical simulation cases validate the effectiveness of the proposed framework.
- 4 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 71 (12) , 5044-5048
Anomaly Identification for Cyber-Physical Systems Subject to Replay Attacks and Sensor Faults
This brief investigates the identification of replay attacks and sensor faults in cyber-physical systems subject to periodic disturbances. For each type of anomaly (replay attack or sensor fault), an anomaly identification framework consisting of an adaptive anomaly isolation estimator (AIE) and an anomaly identification processor (AIP) is proposed. By dynamically configuring the blocking zeros within AIE and through co-design with the compensation signal inside AIP, decoupling between the watermarks generated by AIPs for anomaly identification and periodic disturbances can be achieved. Numerical simulation cases validate the effectiveness of the proposed framework.
- 9 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (2) , 2991-3001
Detection and Identification of Cyberattacks and Physical Faults in Multi-Agent Systems: A Distributed Disturbance Decoupling Observer
This article investigates the detection and identification of physical faults in devices and false-data-injection attacks in communication networks for multi-agent systems with event-triggered transmission mechanisms and subject to external periodic disturbances. First, a new detection and identification scheme, including a local disturbance decoupling (LDD) observer and a distributed disturbance decoupling (DDD) observer, is proposed. Then, based on zero-assignment and the rank-deficiency of the transfer function matrix at zeros, a co-design method for the LDD observer and DDD observer is proposed, which enables the decoupling of periodic disturbances from the residuals for detection and identification. This new scheme no longer requires the transmission of control signals from the node being monitored or the exchange of information between its neighbors, significantly reducing the communication overhead and enhancing the system's security. Finally, a simulation based on a multi-two-wheeled trolley system is used to verify the effectiveness of the proposed method.
- 9 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (2) , 2991-3001
Detection and Identification of Cyberattacks and Physical Faults in Multi-Agent Systems: A Distributed Disturbance Decoupling Observer
This article investigates the detection and identification of physical faults in devices and false-data-injection attacks in communication networks for multi-agent systems with event-triggered transmission mechanisms and subject to external periodic disturbances. First, a new detection and identification scheme, including a local disturbance decoupling (LDD) observer and a distributed disturbance decoupling (DDD) observer, is proposed. Then, based on zero-assignment and the rank-deficiency of the transfer function matrix at zeros, a co-design method for the LDD observer and DDD observer is proposed, which enables the decoupling of periodic disturbances from the residuals for detection and identification. This new scheme no longer requires the transmission of control signals from the node being monitored or the exchange of information between its neighbors, significantly reducing the communication overhead and enhancing the system's security. Finally, a simulation based on a multi-two-wheeled trolley system is used to verify the effectiveness of the proposed method.