YMYushan Ma

Yushan Ma

*This is an algorithmically generated author record based on publicly available information.

Yushan Ma has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers

    Distributed Finite-Time Fuzzy Adaptive Consensus Control for Robot Manipulators With Input Deadzone and Model Uncertainties

    by Jiange Kou, Haoran Zhan, Xiangkai Shen, Chenglong He, Zhiguo Yang, Yixuan Wang, Yushan Ma, Yan Shi

    The multiple manipulator system (MMS) has strong coupling properties and nonlinearities, which is used to accomplish complex cooperation tasks. In this study, a distributed consensus control algorithm is proposed for uncertain MMS with input deadzone under a directed communication graph. Meanwhile, a fuzzy logic system (FLS) is designed to approximate uncertain dynamics for controller compensation. A fast finite-time convergence backstepping controller is designed to ensure that the state error of the MMS system converges to the zero neighborhood within a finite time. In addition, an adaptive method is used to estimate and compensate for the unknown input dead zone parameters. Finally, the effectiveness of the control method is verified through the simulation model and experimental platform, and its advantages are verified through comparative experiments.


  • Continuous Learning Method for Incremental Fault Class Identification of Control Valves Based on Weighted Supervised Contrastive Knowledge Distillation

    by Yan Shi, Yanjie Li, Jun Ma, Ce Wang, Jiayi Ma, Lei Li, Xiangkai Shen, Yixuan Wang, Zhibo Sun, Yushan Ma

    Data-driven methods have achieved high accuracy in diagnosing control valve faults. However, Incremental Learning (IL) methods for step signal fault diagnosis of control valves remain insufficient. First, the distinct characteristics of various step-response signals lead to data imbalance, which makes it difficult for models to extract discriminative features from step-fault data. Second, the arrival of a novel fault class necessitates full retraining and incurs prohibitive computational overhead. Finally, as the number of fault classes increases, the model tends to bias toward newly added fault classes and may suffer from catastrophic forgetting of previously learned ones. These issues collectively degrade the performance of incremental fault diagnosis models. To solve these problems, this paper proposes an incremental fault diagnosis model based on Weighted Supervised Contrastive Knowledge Distillation (WSCKD), which extends the classical Incremental Classifier And Representation Learning (ICARL) framework in three key ways. First, supervised contrastive learning (SCL) is weighted to enhance representation learning for step-response signals. In addition, a new preferred example selection method, Greedy Diversity Sampling (GDS), is proposed to limit computational overhead and is combined with knowledge distillation to mitigate catastrophic forgetting. Furthermore, a Balanced Bagging Classifier (BBC) alleviates the adverse effects of class imbalance. Extensive simulation experiments were conducted on a control valve system. Experimental results demonstrate that the WSCKD method outperforms existing approaches, achieving average incremental accuracies of 94.32% for 5 fault classes.


  • Open Access

    A Unified Positioning Error Modeling and Compensation Method Considering Dynamic Behaviors for Planar Parallel Manipulators

    by Chaoqing Min, Yulin Huang, Zhicheng Ji, Donghua Guo, Xialun Yun, Hu Shi, Gedong Jiang, Xuesong Mei, Yushan Ma

    Planar Parallel Manipulators (PPMs) are pivotal in high precision manufacturing engineering. Positioning error analysis remains a key to enhancing PPMs performance, however the existing error analyses often neglect dynamic uncertainties and time variation such as driving eccentricity, nonlinear friction, joint clearance variation and so on, which leads to an inaccurate formulation of systems dynamics. This paper proposes a unified time-varying dynamic error modeling and compensation methodology considering PPMs complex dynamic behaviors. Firstly, nonlinear friction during operation is data-driven parameterized to accurately describe velocity hysteresis. Secondly, PPMs driving eccentricity is newly formulated to precisely characterize the asymmetry inherent of its mechanical mechanism. Notably, joint clearance variation is numerically conducted via the analysis of bearing dynamics, which helps to the transmission errors compensation of manipulators. Experimental validation on a 4-PPR test rig demonstrates that positioning error can be reduced by 95% and an accuracy of 2μm across all degrees of freedom can be achieved. This method offers a practical means to enhance PPMs precision across diverse applications.

  • Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems

    by Junping Wang, Bicheng Wang, Guoqing Wang, Yushan Ma

    Neuro-Symbolic reasoning, commonly abbreviated as "NeSy," represents a critical and challenging area in artificial intelligence, characterized by its integration of data-driven neural learning and interpretable symbolic reasoning. Unfortunately, most NeSy research to date has mainly concentrated on developing interpretable AI systems for tasks like visual scene parsing or question answering, and has not adequately addressed the need for causal reasoning, cognitive autonomy, and adaptive self-evolution in open-world environments. This bring great challenges and makes previous methods fail to disentangle these causal cognitive complexities. This paper propose Self-Evolving Neuro-Symbolic Autonomy (SENSA) with causal resilience, integrating neural-symbolic bidirectional self-alignment, causal driven self-evolution, and hierarchical resilience planning to achieve autonomous cognitive decision-making. With this regard, a neural-symbolic bidirectional self-alignment is developed, which enables real-time mutual adaptation, ensuring robustness against adversarial noise and causal coherence in dynamic open-real environments. Specifically, we design a novel causal-driven self evolution that enables AI systems to autonomously refine their decision-making policies by leveraging causal reasoning and counterfactual analysis. On this basis, we further develope the hierarchical resilience planning to adapt, recover, and maintain performance even under disruptive or adversarial conditions. The SENSA bridges the gap between neural adaptability and symbolic rigor, which is called industrial brain, achieving causal reasoning and self-evolving autonomy in Cyber-Physical Systems. Theoretically, we prove that the causal reasoning, cognitive autonomy, and adaptive self-evolution by our SENSA can approximate the ground-truth. Empirically, extensive evaluations on eight benchmark datasets demonstrate our superiority over state-of-the-art baselines.

  • Position Tracking Control for Valve Positioner System: Disturbance Rejection With an Adaptive Bandwidths-Tuned NESO

    by Yan Shi, Mingze Sun, Zhibo Sun, Shaofeng Xu, Shijian Zhao, Yushan Ma, Yixuan Wang

    This article proposes a backstepping integral sliding mode control (SMC) scheme augmented with an adaptive bandwidth-tuned NESO for valve positioners with time-varying dynamics and disturbances. First, cascaded tracking differentiators filters based on the Fhan function generate smooth reference trajectories and PD-spectrum required by the observer with low phase lag. Next, an improved time-varying multiplier, driven by the observer’s tracking error and desired velocity, schedules the observer gains and bandwidth online, balancing high-precision state estimation and noise suppression during composite motion. The resulting adaptive bandwidth-tuned NESO supports the backstepping integral SMC, in which an integral sliding surface and a smoothed $fa{{l}^{*}}$ nonlinearity is embedded to shape cascaded error dynamics, suppress overshoot, and improve steady-state accuracy. Experimental comparisons have demonstrated the efficacy of the proposed nonlinear control strategy, which has been shown to enhance control speed and accuracy while effectively resisting perturbations and reducing the overshoot phenomenon.

  • Joint Domain Adaptation via Cluster Centers and Thermal Imaging for Detecting Leakages in Different Pneumatic Components

    by Jiaqi Chang, Yan Shi, Lei Li, Jianchun Zhang, Yushan Ma, Maolin Cai, Xiangkai Shen, Yixuan Wang, Shaofeng Xu, Na Wang, et al.

    Pneumatic components are essential for precise control and automation in mechanical manufacturing. Leakage faults in pneumatic components can seriously undermine the reliability of manufacturing processes. When high-pressure gas leaks and expands, heat transfer between the gas and the component wall creates a localized low-temperature area. This thermal anomaly can be detected using thermal imaging techniques. However, thermal images captured from different pneumatic components exhibit distinct distribution patterns, which can significantly degrade the accuracy of existing detection methods. Conventional domain adaptation methods typically use the sample mean to represent feature distributions, neglecting intraclass dispersion and the interdependence among feature learning, classifier learning, and pseudolabel learning. To address these limitations, we propose a joint unsupervised domain adaptation method via cluster centers and thermal imaging for leakage detection in different pneumatic components (JCC-LDC). Specifically, JCC-LDC accounts for the fact that samples of a single class may disperse into multiple clusters, and it integrates feature learning, classifier learning, and pseudolabel learning into a unified framework based on cluster centers. Experimental results demonstrate that JCC-LDC increases the average detection accuracy from 71.5% to 82.3%, effectively enhancing the generalization capability of thermal-imaging-based leakage detection in pneumatic components.

  • A Long Short-Term Memory-Based Predictive Control Approach for Pneumatic Muscle Control Systems

    by Yan Shi, Jie Zheng, Bin Wang, Yixuan Wang, Yushan Ma

    Pneumatic artificial muscles (PAMs) are essential in robotics systems designed to mimic the human musculoskeletal structure, particularly in applications for rehabilitation, due to their flexibility and muscle-like force output. However, their nonlinear and hysteresis characteristics challenge accurate modeling and limit traditional model-based control effectiveness. This study presents a hybrid framework combining long short-term memory (LSTM) networks with model predictive control (MPC), significantly improving PAM control precision. The approach ensures reliable trajectory tracking without model switching, supported by a novel stability theorem. Experimental results reveal that the LSTM-MPC method outperforms conventional controllers, achieving improvements in root-mean-square error of 0.0051, 0.0312, and 0.0125 compared to proportional–integral–derivative, adaptive fuzzy control, and Learning MPC, respectively, while reaching the reference trajectory within 3 s. Load-bearing tests on the pneumatic knee joint demonstrated effective adaptation of system inputs for trajectory tracking under step and sinusoidal signals, and achieve commendable performance in knee joint motion tracking. This research offers a new perspective on PAM control, emphasizing the integration of deep learning with traditional control methods.


  • Adaptive Backstepping Controller Based on Structural Self-Regulating NESO for Position Control of Valve Positioner Systems

    by Yan Shi, Shijian Zhao, Mingze Sun, Zhibo Sun, Shaofeng Xu, Yushan Ma, Yixuan Wang

    As the central intelligent industrial instrument in process industry automation, the valve positioner system (VPS) regulates flow, pressure, and temperature precisely, ensuring production process accuracy, stability, and reliability. However, the VPS exhibits time-varying nonlinearity, parameter uncertainty, and dead-zone characteristics, and is also subjected to external disturbances. Existing control algorithms have the dual limitations of poor robustness and insufficient tracking accuracy, and it is challenging to solve the contradiction between initial response speed and overshoot effectively. To address these challenges, we propose an adaptive backstepping controller based on a structural self-regulating nonlinear extended state observer (NESO). First, the VPS’s dynamic model is established, in which uncertain parameters are estimated using adaptive laws. Then, a structural self-regulating NESO is designed, which automatically adjusts its structural parameters according to the changes in the system and realizes the accurate estimation of the perturbation and system state. Next, the control strategy is designed using adaptive laws based on the backstepping technique, further enhanced by incorporating a nonlinear control quantity into the virtual control law. The stability and robustness of the system can be improved while ensuring high precision control. Finally, the effectiveness of the proposed algorithm was evaluated through comparative experiments under consistent conditions. The proposed controller achieved a steady-state tracking error of 0.5%, compared to 1.5% for the adaptive integral sliding mode controller, with both exhibiting similar response times of approximately 2.6 s. In terms of overshoot, the proposed controller produced a peak value of 0.14 mm, compared to 0.18 mm observed with the active disturbance rejection controller. These results indicate enhanced tracking accuracy and improved transient performance. Thus, the proposed algorithm delivers precise, stable, and rapid valve position control with excellent robustness and disturbance-rejection capabilities.


  • Top Cited Papers

    Observer-Based Fuzzy Adaptive Dynamic Surface Force Control for Pneumatic Polishing System End-Effector With Uncertain Contact Environment Model

    by Zhiguo Yang, Wenbo Zhao, Jiange Kou, Yushan Ma, Zhibo Sun, Yixuan Wang, Yan Shi

    This study presents an observer-based adaptive fuzzy dynamic surface force control strategy for pneumatic polishing system with uncertain contact environment model and full-state constraints. First, a fuzzy logic system is employed to approximate the uncertain nonlinear dynamics of the pneumatic polishing system end-effector, and a fuzzy state observer is designed to estimate the unmeasured states. Further, to enhance the controller’s response speed, a variable separation method employing fuzzy basis functions and the dynamic surface control technique are adopted to address algebraic loop issues and prevent computational complexity explosion. A logarithmic-type barrier Lyapunov function is embedded into each step of the controller design to ensure that all system states satisfy the predefined constraints. Finally, an adaptive fuzzy dynamic surface force controller with full-state constraints is developed to ensure fast and accurate control of the polishing force in an uncertain contact environment while maintaining all states within predefined constraints. The effectiveness and applicability of the proposed control algorithm are experimentally verified using a pneumatic polishing system.