YZYue-Peng Zhang

Yue-Peng Zhang

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

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


Yue-Peng Zhang has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Hybrid-Domain Framework Enhanced by Adaptive Feature Optimization and Ensemble Learning for High-Performance Bearing Fault Diagnosis

    by Jun Wu, Yuepeng Zhang, Xueli Zhu, Bo Gao, Linzhong Xia

    Bearing fault diagnosis is vital for maintaining the reliability and security of industrial machinery. Although deep learning approaches are widely utilized, the scarcity of labeled fault data significantly hinders the effective training of large-parameter fault diagnosis models rooted in deep neural networks. Moreover, such models often exhibit a lack of interpretability. To tackle these challenges, this study proposes a novel hybrid-domain fault diagnosis framework for bearings, synergistically enhanced by adaptive feature optimization and Ensemble Learning (EL). The core methodology involves three principal innovations: (1) the extraction and fusion of condition-indicative features from different domains to construct a comprehensive representation, overcoming the insufficiency of single-domain analysis; (2) the development of an adaptive feature optimization mechanism that automatically selects the most discriminative features from the hybrid domain, enhancing diagnostic relevance and reducing dimensionality while providing physical insights into the diagnostic process; (3) the formulation of a robust diagnostic model that integrates the optimized hybrid-domain features with an ensemble learning strategy to significantly boost diagnostic accuracy and stability. Comparative experiments were conducted, comparing models utilizing single-domain features, simple hybrid-domain fusion, hybrid-domain with adaptive optimization, and the proposed framework. Experimental evidence indicates that the proposed hybrid-domain model possesses superior fault diagnosis performance, validating that the adaptive optimization within the hybrid domain effectively retains critical information while EL ensures reliable generalization. This work presents a data-efficient, interpretable, and high-performance methodology for intelligent bearing health management.

  • Open Access

    Adaptive Action Chunking for Robotic Imitation Learning

    by Qingpeng Wen, Haomin Zhu, Yuepeng Zhang, Linzhong Xia, Bo Gao, Zhuozhen Li

    Action chunking strategies in robot imitation learning struggle to dynamically balance between long-range motion efficiency and short-range operational precision due to their fixed planning horizon. This paper presents an Adaptive Action Chunking framework that enables robots to dynamically predict the optimal action chunk length based on real-time visual context. We design an end-to-end dual-branch network comprising a shared visual encoder, a parallel action prediction head, and a chunk-size prediction head. Experiments on two real-world bimanual robot manipulation tasks (transport-and-place and flip-and-handover) demonstrate that the method autonomously derives two distinct intelligent strategy patterns—phase-aware switching and sustained high-frequency adjustment—in response to task uncertainty. It significantly outperforms fixed-chunk baselines in both success rate and efficiency. Ablation studies confirm that the performance gain stems from the adaptive decision-making mechanism itself.

  • Open Access

    An Offline Condition Monitoring Method for the DC-Link Capacitors in Power Electronic Converters

    by Xueli Zhu, Yajie Huang, Yuepeng Zhang, Jun Wu, Yang Yang, Linzhong Xia, Bo Gao

  • Open Access

    A Hybrid Deep Learning Framework for Enhanced Fault Diagnosis in Industrial Robots

    by Jun Wu, Yuepeng Zhang, Bo Gao, Linzhong Xia, Xueli Zhu, Hui Wang, Xiongbo Wan

    Predominant fault diagnosis in industrial robots depends on dedicated vibration or acoustics sensors. However, their practical deployment is often limited by installation constraints, susceptibility to environmental noise, and cost considerations. Applying Energy-Based Maintenance (EBM) principles to achieve enhanced fault diagnosis under practical industrial conditions, we propose a hybrid deep learning framework, the Multi-head Graph Attention Network (MGAT) with Multi-scale CNNBiLSTM Fusion (MGAT-MCNNBiLSTM) for industrial robots. This approach obviates the need for additional dedicated sensors, effectively mitigating associated deployment complexities. The framework embodies four core innovations: (1) Based on the EBM paradigm, motor current is established as the most effective and practical choice for enabling cost-efficient and scalable industrial robot fault diagnosis. A corresponding dataset of motor current has been acquired from industrial robots operating under diverse fault scenarios. (2) An integrated MGAT-MCNNBiLSTM architecture that synergistically models multiscale local features and complex dynamics through its MCNNBiLSTM module while capturing nonlinear interdependencies via MGAT. This comprehensive feature representation enables robust and highly accurate fault detection. (3) The study found that the application of spectral preprocessing techniques yields a marked and statistically significant enhancement in diagnostic performance. A comprehensive and systematic analysis was undertaken to uncover the underlying reasons for this observed performance improvement. (4) To emulate challenging industrial settings and cost-sensitive implementations, noise signal injection was employed to evaluate model robustness in high-electromagnetic-interference environments and low-cost, low-resolution ADC implementations. Experimental validation on real-world industrial robot datasets demonstrates that MGAT-MCNNBiLSTM achieves a superior diagnostic accuracy of 90.7560%. This performance marks a significant absolute improvement of 1.51–8.55% over competing models, including LCNNBiLSTM, SCNNBiLSTM, MCCBiLSTM, GAT, and MGAT. Under challenging noise and low-resolution conditions, the proposed model consistently outperforms CNNBiLSTM variants, GAT, and MGAT with an improvement of 1.37–10.26% and enhanced industrial utility and deployment potential.


  • Open Access

    Online Junction Temperature Measurement for Power MOSFETs Using the Body Diode Under Varying Forward Currents

    by Xueli Zhu, Yajie Huang, Donglai Zhang, Yuepeng Zhang, Jun Wu, Bowen Jiang, Linzhong Xia, Bo Gao, Changwei Lv

    Power metal-oxide-semiconductor field-effect transistors (MOSFETs) provide numerous advantages and are widely utilized in various power circuits. The junction temperature plays a critical role in determining the reliability, performance, and operational lifetime of power MOSFETs. Therefore, accurate monitoring of the junction temperature of power MOSFETs is essential to ensure the safe operation of power circuit systems. In bridge or motor drive circuits, MOSFETs often operate in a freewheeling state via the body diode, where the freewheeling current is typically variable. The proposed method for junction temperature measurement utilizes the body diode and is designed to accommodate varying forward currents. It also accounts for the temperature-dependent ideality factor to improve measurement accuracy. By integrating the forward voltage and forward current of the body diode, this approach reduces the required sampling frequency. To validate the method’s effectiveness, three representative types of power MOSFETs, a Si MOSFET (IRF520), a SiC MOSFET (C2M0080120D), and an aerospace-grade radiation-hardened MOSFET (RSCS25045T1RH), were used to measure junction temperatures before and after irradiation. Following ideality factor correction, the maximum absolute error compared to reference measurements from thermocouples and a thermal imager remained within 2 K across the temperature range of 300 K to 420 K. Experimental results confirm the feasibility of the proposed method.


  • Open Access

    Obstacle Feature Information-Based Motion Decision-Making Method for Obstacle-Crossing Motions in Lower Limb Exoskeleton Robots

    by Yuepeng Zhang, Guangzhong Cao, Jun Wu, Bo Gao, Linzhong Xia, Chen Lu, Hui Wang

    To overcome the problem of insufficient adaptability to the motion environment of lower limb exoskeleton robots, this paper introduces computer vision technology into the motion control of lower limb exoskeleton robots and studies an obstacle-crossing-motion method based on detecting obstacle feature information. Considering the feature information of different obstacles and the distance between obstacles and robots, a trajectory planning method based on direct point matching was used to generate offline adjusted gait trajectory libraries and obstacle-crossing gait trajectory libraries. A lower limb exoskeleton robot obstacle-crossing motion decision-making algorithm based on obstacle feature information is proposed by combining gait constraints and motion constraints, enabling it to select appropriate motion trajectories in the trajectory library. The proposed obstacle-crossing-motion method was validated at three distances between the obstacle and the robot and with the feature information of four obstacles. The experimental results show that the proposed method can select appropriate trajectories from the trajectory library based on the detected obstacle feature information and can safely complete obstacle-crossing motions.


  • Top Cited Papers
    Open Access

    Fault Types and Diagnostic Methods of Manipulator Robots: A Review

    by Yuepeng Zhang, Jun Wu, Bo Gao, Linzhong Xia, Chen Lu, Hui Wang, Guangzhong Cao

    Manipulator robots hold significant importance for the development of intelligent manufacturing and industrial transformation. Manufacturers and users are increasingly focusing on fault diagnosis for manipulator robots. The voltage, current, speed, torque, and vibration signals of manipulator robots are often used to explore the fault characteristics from a frequency perspective, and temperature and sound are also used to represent the fault information of manipulator robots from different perspectives. Technically, manipulator robot fault diagnosis involving human intervention is gradually being replaced by new technologies, such as expert experience, artificial intelligence, and digital twin methods. Previous reviews have tended to focus on a single type of fault, such as analysis of reducers or joint bearings, which has led to a lack of comprehensive summary of various methods for manipulator robot fault diagnosis. Considering the needs of future research, a review of different fault types and diagnostic methods of manipulator robots provides readers with a clearer reading experience and reveals potential challenges and opportunities. Such a review helps new researchers entering the field avoid duplicating past work and provides a comprehensive overview, guiding and encouraging readers to commit to enhancing the effectiveness and practicality of manipulator robot fault diagnosis technologies.


  • A Novel Lower Limb Motion Intention Recognition Model Using ConvNet With Prob-Sparse Attention

    by Ling-Long Li, Guang-Zhong Cao, Yue-Peng Zhang, Fang Cui

    Motor imagery (MI)-electroencephalogram (EEG)-based brain-computer interfaces (BCIs) have emerged as transformative tools for enhancing clinical and real-life applications. Decoding MI-EEG signals to recognize lower-limb motion intentions (LLMIs) is highly important for controlling lower limb exoskeletons (LLEs) used in the rehabilitation of disabled individuals. Traditional approaches focus primarily on decoding upper-limb MI-EEG signals to indirectly infer LLMIs. However, recognizing direct LLMI to control LLEs is more acceptable and natural for users. This paper proposes a novel LLMI recognition model using convolutional neural networks with prob-sparse attention, to directly decode lower-limb MI-EEG signals for LLE control. This model synergizes a convolutional block for extracting localized temporal-spatial features with a prob-sparse attention block, which emphasizes distinctive global temporal features while reducing computational complexity. Offline experiments demonstrate that the proposed model achieves an average classification accuracy (ACA) exceeding 89.04%, outperforming existing state-of-the-art models. In online experiments, an EEG-based BCI system tailored for real-time LLE control is developed that features online data acquisition, model fine-tuning and EEG decoding capabilities, and the model achieves an ACA of 57.28% with an information transfer rate of 7.70 bits/min. The effectiveness and practicality of the proposed model for LLMI recognition are demonstrated in both offline and online experiments.


  • Open Access

    MACNet: A Multidimensional Attention-Based Convolutional Neural Network for Lower-Limb Motor Imagery Classification

    by Ling-Long Li, Guang-Zhong Cao, Yue-Peng Zhang, Wan-Chen Li, Fang Cui

    Decoding lower-limb motor imagery (MI) is highly important in brain–computer interfaces (BCIs) and rehabilitation engineering. However, it is challenging to classify lower-limb MI from electroencephalogram (EEG) signals, because lower-limb motions (LLMs) including MI are excessively close to physiological representations in the human brain and generate low-quality EEG signals. To address this challenge, this paper proposes a multidimensional attention-based convolutional neural network (CNN), termed MACNet, which is specifically designed for lower-limb MI classification. MACNet integrates a temporal refining module and an attention-enhanced convolutional module by leveraging the local and global feature representation abilities of CNNs and attention mechanisms. The temporal refining module adaptively investigates critical information from each electrode channel to refine EEG signals along the temporal dimension. The attention-enhanced convolutional module extracts temporal and spatial features while refining the feature maps across the channel and spatial dimensions. Owing to the scarcity of public datasets available for lower-limb MI, a specified lower-limb MI dataset involving four routine LLMs is built, consisting of 10 subjects over 20 sessions. Comparison experiments and ablation studies are conducted on this dataset and a public BCI Competition IV 2a EEG dataset. The experimental results show that MACNet achieves state-of-the-art performance and outperforms alternative models for the subject-specific mode. Visualization analysis reveals the excellent feature learning capabilities of MACNet and the potential relationship between lower-limb MI and brain activity. The effectiveness and generalizability of MACNet are verified.


  • Open Access

    Human-in-the-Loop Trajectory Optimization Based on sEMG Biofeedback for Lower-Limb Exoskeleton

    by Ling-Long Li, Yue-Peng Zhang, Guang-Zhong Cao, Wen-Zhou Li

    Lower-limb exoskeletons (LLEs) can provide rehabilitation training and walking assistance for individuals with lower-limb dysfunction or those in need of functionality enhancement. Adapting and personalizing the LLEs is crucial for them to form an intelligent human–machine system (HMS). However, numerous LLEs lack thorough consideration of individual differences in motion planning, leading to subpar human performance. Prioritizing human physiological response is a critical objective of trajectory optimization for the HMS. This paper proposes a human-in-the-loop (HITL) motion planning method that utilizes surface electromyography signals as biofeedback for the HITL optimization. The proposed method combines offline trajectory optimization with HITL trajectory selection. Based on the derived hybrid dynamical model of the HMS, the offline trajectory is optimized using a direct collocation method, while HITL trajectory selection is based on Thompson sampling. The direct collocation method optimizes various gait trajectories and constructs a gait library according to the energy optimality law, taking into consideration dynamics and walking constraints. Subsequently, an optimal gait trajectory is selected for the wearer using Thompson sampling. The selected gait trajectory is then implemented on the LLE under a hybrid zero dynamics control strategy. Through the HITL optimization and control experiments, the effectiveness and superiority of the proposed method are verified.