Xiaoyu Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaoyu Su has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
Bin Lin
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China
3 shared publications- Wei Shen
Department of Mechatronics Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
2 shared publications - Bin Lin
Guangdong Power Grid Power Dispatch Control Center, Guangzhou, China
1 shared publication - Cancan Liu1 shared publication
- Chao Shen
State Key Laboratory of Precision Manufacturing for Extreme Service Performance, Central South University, Hunan, 410083, China; The National Enterprise R&D Center, Sunward Intelligence Equipment Co., Ltd., Hunan, 410100, China
1 shared publication - Jiayi Wang1 shared publication
Latest Publications
- 16 April 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (9)
MCLFNet: A Lightweight Feature Fusion Network for Multi-channel IMU and EMG Human Activity Recognition
Sensor-based lower-limb activity recognition is critical for wearable medical systems. However, existing methods based on a single modality or with high computational costs struggle to meet the requirements of multimodal applications. To address these limitations, this study proposes a multimodal convolutional lightweight fusion network (MCLFNet), a lightweight spatiotemporal feature fusion framework for efficient human activity recognition (HAR). A processing scheme is introduced to transform the time series signals from inertial measurement units (IMU) and electromyography (EMG) into grayscale images, where a hybrid cascaded filtering strategy is proposed to alleviate the discrepancy caused by their different sampling frequencies. Then, the multi-channel fusion and essential feature extraction (MCFFE) module is designed and integrated with a cross-modal spatiotemporal attention mechanism (CMSA) to enhance cross-modal feature learning and improve spatial critical representation. Evaluations on the Camargo and ENABL3S datasets demonstrate the strong generalization ability of the proposed method. MCLFNet achieves accuracies of 98.43% and 98.77% for speed and action classification on the Camargo dataset, and 98.84% on the ENABL3S dataset. Furthermore, the model achieves an average inference time of merely 0.35 to 0.40 ms per sample, which satisfies the low-latency requirement of real-time control. Ablation studies further confirm that the proposed module improves multimodal feature extraction and classification performance.
- 16 April 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (9)
MCLFNet: A Lightweight Feature Fusion Network for Multi-channel IMU and EMG Human Activity Recognition
Sensor-based lower-limb activity recognition is critical for wearable medical systems. However, existing methods based on a single modality or with high computational costs struggle to meet the requirements of multimodal applications. To address these limitations, this study proposes a multimodal convolutional lightweight fusion network (MCLFNet), a lightweight spatiotemporal feature fusion framework for efficient human activity recognition (HAR). A processing scheme is introduced to transform the time series signals from inertial measurement units (IMU) and electromyography (EMG) into grayscale images, where a hybrid cascaded filtering strategy is proposed to alleviate the discrepancy caused by their different sampling frequencies. Then, the multi-channel fusion and essential feature extraction (MCFFE) module is designed and integrated with a cross-modal spatiotemporal attention mechanism (CMSA) to enhance cross-modal feature learning and improve spatial critical representation. Evaluations on the Camargo and ENABL3S datasets demonstrate the strong generalization ability of the proposed method. MCLFNet achieves accuracies of 98.43% and 98.77% for speed and action classification on the Camargo dataset, and 98.84% on the ENABL3S dataset. Furthermore, the model achieves an average inference time of merely 0.35 to 0.40 ms per sample, which satisfies the low-latency requirement of real-time control. Ablation studies further confirm that the proposed module improves multimodal feature extraction and classification performance.
- Open Access
Research on Control of Hydraulic Position Tracking System Based on Event Triggering and Disturbance Observer
An electro-hydraulic servo system based on network control technology has the advantages of remote control, modularisation, and resource sharing. However, the electro-hydraulic servo system itself has the characteristics of strong nonlinearity and parameter uncertainty, combined with the limited communication bandwidth of the network control system, which leads to a poor control effect and limits its application. To solve the above problems, an event-triggered mechanism is introduced to filter redundant data and conserve the communication bandwidth, while a backstepping sliding mode control strategy integrating this event-triggered mechanism with a jamming observer is proposed. A model-based disturbance observer is designed to mitigate external interference effects on system control performance while enhancing robustness and disturbance response capabilities. The global stability of the closed-loop system is analysed using Lyapunov stability theory. The experimental results show that the system displacement tracking error of the controller designed in this paper can reach ±0.001 rad, and the system can reach stability in about 0.5 s. At the same time, it can significantly reduce the amount of data transmission, which effectively solves the problem of the network bandwidth limitation.
Open AccessResearch on Control of Hydraulic Position Tracking System Based on Event Triggering and Disturbance Observer
An electro-hydraulic servo system based on network control technology has the advantages of remote control, modularisation, and resource sharing. However, the electro-hydraulic servo system itself has the characteristics of strong nonlinearity and parameter uncertainty, combined with the limited communication bandwidth of the network control system, which leads to a poor control effect and limits its application. To solve the above problems, an event-triggered mechanism is introduced to filter redundant data and conserve the communication bandwidth, while a backstepping sliding mode control strategy integrating this event-triggered mechanism with a jamming observer is proposed. A model-based disturbance observer is designed to mitigate external interference effects on system control performance while enhancing robustness and disturbance response capabilities. The global stability of the closed-loop system is analysed using Lyapunov stability theory. The experimental results show that the system displacement tracking error of the controller designed in this paper can reach ±0.001 rad, and the system can reach stability in about 0.5 s. At the same time, it can significantly reduce the amount of data transmission, which effectively solves the problem of the network bandwidth limitation.
- 2 September 2021
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 19 (11) , 3622-3630
High-Precision Position Tracking Control of Electro-hydraulic Servo Systems Based on an Improved Structure and Desired Compensation
- 2 September 2021
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 19 (11) , 3622-3630
High-Precision Position Tracking Control of Electro-hydraulic Servo Systems Based on an Improved Structure and Desired Compensation
- Open Access
- 29 April 2021
- Published by SAGE Publications in Science Progress
- Vol. 104 (2)
Composite adaptive backstepping controller design and the energy calculation for active suspension system
The half-car suspension has the coupling of pitch angle and front and rear suspension. Especially when the suspension model has a series of uncertainties, the traditional linear control method is difficult to be applied to the half-car suspension model. At present, there is no systematic method to solve the suspension power. According to the energy storage characteristics of the elastic components of the suspension, the power calculation formula is proposed in this paper. This paper proposes a composite adaptive backstepping control scheme for the half-car active suspension systems. In this method, the correlation information between the output error and the parameter estimation error is used to construct the adaptive law. According to the energy storage characteristics of the elastic components of the suspension, the power calculation formula is introduced. The compound adaptive law and the ordinary adaptive law have good disturbance suppression, both of which can solve the pitching angle problem of the semi-car suspension, but the algorithm of the compound adaptive law is superior in effect. In terms of vehicle comfort, the algorithm of the general adaptive law can achieve stability quickly, but compared with the composite adaptive law, its peak value and jitter are higher, while the algorithm of the composite adaptive law is relatively gentle and has better adaptability to human body. In terms of vehicle handling, both control algorithms can maintain driving safety under road excitation, and the compound adaptive algorithm appears to have more advantages. Compared with the traditional adaptive algorithm, the power consumption of the composite adaptive algorithm is relatively lower than that of the former in the whole process. The simulation results show that the ride comfort, operating stability and safety of the vehicle can be effectively improved by the composite adaptive backstepping controller, and the composite adaptive algorithm is more energy-saving than the conventional adaptive algorithm based on projection operator.
- 29 April 2021
- Published by SAGE Publications in Science Progress
- Vol. 104 (2)
Open AccessComposite adaptive backstepping controller design and the energy calculation for active suspension system
The half-car suspension has the coupling of pitch angle and front and rear suspension. Especially when the suspension model has a series of uncertainties, the traditional linear control method is difficult to be applied to the half-car suspension model. At present, there is no systematic method to solve the suspension power. According to the energy storage characteristics of the elastic components of the suspension, the power calculation formula is proposed in this paper. This paper proposes a composite adaptive backstepping control scheme for the half-car active suspension systems. In this method, the correlation information between the output error and the parameter estimation error is used to construct the adaptive law. According to the energy storage characteristics of the elastic components of the suspension, the power calculation formula is introduced. The compound adaptive law and the ordinary adaptive law have good disturbance suppression, both of which can solve the pitching angle problem of the semi-car suspension, but the algorithm of the compound adaptive law is superior in effect. In terms of vehicle comfort, the algorithm of the general adaptive law can achieve stability quickly, but compared with the composite adaptive law, its peak value and jitter are higher, while the algorithm of the composite adaptive law is relatively gentle and has better adaptability to human body. In terms of vehicle handling, both control algorithms can maintain driving safety under road excitation, and the compound adaptive algorithm appears to have more advantages. Compared with the traditional adaptive algorithm, the power consumption of the composite adaptive algorithm is relatively lower than that of the former in the whole process. The simulation results show that the ride comfort, operating stability and safety of the vehicle can be effectively improved by the composite adaptive backstepping controller, and the composite adaptive algorithm is more energy-saving than the conventional adaptive algorithm based on projection operator.
- Open Access
- 1 January 2021
- Published by Wiley in Complexity
- Vol. 2021 (1)
Optimization of the New Index Reaching Law of the Active Suspension Sliding Mode Controller Based on the Cuckoo Search Algorithm
To facilitate the performance of the active suspension system, the optimization of a new reaching law of the active suspension sliding mode controller based on cuckoo algorithm is addressed in this paper. Firstly, a linear model of the active suspension system is built. Then, according to the features of the new exponential reaching law, an active sliding mode control scheme based on the new sliding mode reaching law is designed. Finally, the simulation results are separated into two stages to verify the suitability and superiority of the proposed control scenario.
- 1 January 2021
- Published by Wiley in Complexity
- Vol. 2021 (1)
Open AccessOptimization of the New Index Reaching Law of the Active Suspension Sliding Mode Controller Based on the Cuckoo Search Algorithm
To facilitate the performance of the active suspension system, the optimization of a new reaching law of the active suspension sliding mode controller based on cuckoo algorithm is addressed in this paper. Firstly, a linear model of the active suspension system is built. Then, according to the features of the new exponential reaching law, an active sliding mode control scheme based on the new sliding mode reaching law is designed. Finally, the simulation results are separated into two stages to verify the suitability and superiority of the proposed control scenario.
- 28 September 2020
- Published by Wiley in Asian Journal of Control
- Vol. 23 (6) , 2657-2668
Finite‐time command filtered control combined with pi‐sigma fuzzy neural network for hydraulic control system
- 28 September 2020
- Published by Wiley in Asian Journal of Control
- Vol. 23 (6) , 2657-2668
Finite‐time command filtered control combined with pi‐sigma fuzzy neural network for hydraulic control system
- 27 May 2019
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 17 (7) , 1751-1761
Fault-tolerant Controller Design for Active Suspension System with Proportional Differential Sliding Mode Observer
- 27 May 2019
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 17 (7) , 1751-1761
Fault-tolerant Controller Design for Active Suspension System with Proportional Differential Sliding Mode Observer
- 1 October 2018
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 16 (5) , 2244-2252
SOS Based Robust Control for Dynamic Positioning System Subject to Actuator Saturation
- 1 October 2018
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 16 (5) , 2244-2252
SOS Based Robust Control for Dynamic Positioning System Subject to Actuator Saturation
- 3 August 2018
- Published by Wiley in Asian Journal of Control
- Vol. 21 (1) , 264-276
Fuzzy Sliding Mode Control for Active Suspension System with Proportional Differential Sliding Mode Observer
In this paper, a generalized augmented transformation is considered for the quarter active suspension system with uncertainties. Specifically, the model uncertainties are converted to the augmented states and a new proportion differential sliding mode observer is used to estimate state variables and model uncertainties. A differential geometric method is applied to linearize the nonlinear suspension model. In order to weaken the vibration effect of sliding mode control force and reduce energy consumption, a fuzzy sliding mode controller is designed for the active suspension system and the fuzzy controller is applied to adjust switching control gain according to the reaching condition of sliding mode surface. The simulations are conducted to illustrate the effectiveness and advantages of this proposed observer and control strategy.
- 3 August 2018
- Published by Wiley in Asian Journal of Control
- Vol. 21 (1) , 264-276
Fuzzy Sliding Mode Control for Active Suspension System with Proportional Differential Sliding Mode Observer
In this paper, a generalized augmented transformation is considered for the quarter active suspension system with uncertainties. Specifically, the model uncertainties are converted to the augmented states and a new proportion differential sliding mode observer is used to estimate state variables and model uncertainties. A differential geometric method is applied to linearize the nonlinear suspension model. In order to weaken the vibration effect of sliding mode control force and reduce energy consumption, a fuzzy sliding mode controller is designed for the active suspension system and the fuzzy controller is applied to adjust switching control gain according to the reaching condition of sliding mode surface. The simulations are conducted to illustrate the effectiveness and advantages of this proposed observer and control strategy.