Yixiang Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yixiang Huang has a total of 79 co-authors. Here are the top co-authors by number of shared publications:
- Chengliang Liu
Shanghai Jiao Tong University
13 shared publications - Chengjin Qin
Shanghai Jiao Tong University
10 shared publications Chengliang Liu
10 shared publications- Pengcheng Xia
State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai, China
9 shared publications - Liang Gong
Shanghai Jiao Tong University
6 shared publications - Dengyu Xiao
Chongqing University
5 shared publications
Latest Publications
- Open Access
- 9 March 2026
- Published by Elsevier in SSRN Electronic Journal
Remaining Energy and Operational Time Estimation for Hydrogen-Electric Hybrid Power Systems in Quadruped Robots Based on Dynamic Efficiency Calibration and Power Prediction
With the widespread application of robotic dogs in industrial, agricultural, and military fields, hydrogen-electric hybrid power structures have gradually replaced single hydrogen fuel cells or lithium batteries as the mainstream energy solution. However, given the complex operating conditions of robotic dogs and the multi-source power supply mode adopted by such systems, accurately estimating their remaining energy and continuous operating time remains an urgent technical challenge. To address this, this paper proposes a novel estimation method based on dynamic calibration of hydrogen-to-electricity conversion efficiency and power prediction. The proposed method dynamically estimates the available energy of the fuel cell by real-time calculation of hydrogen pressure-to-electricity conversion efficiency for the first time. An improved K-means++ algorithm is used to establish a historical operating condition database by integrating historical data. Concurrently, An LSTM-based power characteristic predictor forecasts future power demand, dynamically matching the power characteristics under predicted operating conditions output from the historical database. Combining these approaches enables estimation of remaining energy and runtime, our method achieves a 79.52% reduction in MSE and a 75.73% reduction in RMSE in runtime estimation. This highlights a significant improvement in accuracy while maintaining robust stability across diverse operating conditions.
- 9 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessRemaining Energy and Operational Time Estimation for Hydrogen-Electric Hybrid Power Systems in Quadruped Robots Based on Dynamic Efficiency Calibration and Power Prediction
With the widespread application of robotic dogs in industrial, agricultural, and military fields, hydrogen-electric hybrid power structures have gradually replaced single hydrogen fuel cells or lithium batteries as the mainstream energy solution. However, given the complex operating conditions of robotic dogs and the multi-source power supply mode adopted by such systems, accurately estimating their remaining energy and continuous operating time remains an urgent technical challenge. To address this, this paper proposes a novel estimation method based on dynamic calibration of hydrogen-to-electricity conversion efficiency and power prediction. The proposed method dynamically estimates the available energy of the fuel cell by real-time calculation of hydrogen pressure-to-electricity conversion efficiency for the first time. An improved K-means++ algorithm is used to establish a historical operating condition database by integrating historical data. Concurrently, An LSTM-based power characteristic predictor forecasts future power demand, dynamically matching the power characteristics under predicted operating conditions output from the historical database. Combining these approaches enables estimation of remaining energy and runtime, our method achieves a 79.52% reduction in MSE and a 75.73% reduction in RMSE in runtime estimation. This highlights a significant improvement in accuracy while maintaining robust stability across diverse operating conditions.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (3) , 4705-4718
Knowledge Distillation From Electromagnetic Simulation for Asynchronous Motor Fault Diagnosis With Small Labeled Samples
The accurate fault diagnosis of asynchronous motors is critical in industry, and intelligent diagnosis methods have demonstrated notable performance. However, the scarcity of labeled data in real-world scenarios constrains model performance, while efficiently extracting fault-related features from three-phase stator current signals remains a persistent challenge. In this article, a new method of knowledge distillation from high-fidelity electromagnetic simulations to actual measurement data is proposed. First, the empirical wavelet transform recurrence plot (EWT-RP) is proposed to adaptively decompose fault-induced components from current signals and convert them into 2-D colored images, emphasizing variances across both time and phases. A self-attention distillation strategy incorporating feature and attention distributions is designed to enable the model to inherit the capability of attending to fault-related representations from simulations. In addition, a novel class-aware Sinkhorn distance (CASD) is proposed to achieve intraclass knowledge transport. Comparative and ablation experiments conducted on an asynchronous motor under two operating conditions validate the effectiveness of the proposed method.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (3) , 4705-4718
Knowledge Distillation From Electromagnetic Simulation for Asynchronous Motor Fault Diagnosis With Small Labeled Samples
The accurate fault diagnosis of asynchronous motors is critical in industry, and intelligent diagnosis methods have demonstrated notable performance. However, the scarcity of labeled data in real-world scenarios constrains model performance, while efficiently extracting fault-related features from three-phase stator current signals remains a persistent challenge. In this article, a new method of knowledge distillation from high-fidelity electromagnetic simulations to actual measurement data is proposed. First, the empirical wavelet transform recurrence plot (EWT-RP) is proposed to adaptively decompose fault-induced components from current signals and convert them into 2-D colored images, emphasizing variances across both time and phases. A self-attention distillation strategy incorporating feature and attention distributions is designed to enable the model to inherit the capability of attending to fault-related representations from simulations. In addition, a novel class-aware Sinkhorn distance (CASD) is proposed to achieve intraclass knowledge transport. Comparative and ablation experiments conducted on an asynchronous motor under two operating conditions validate the effectiveness of the proposed method.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-13
Self-Distillation-Based Domain Weighted Generalization Method for Fault Diagnosis Under Actual Unseen Working Conditions
In modern industry, fault diagnosis is critical for ensuring production safety and efficiency. Intelligent fault diagnosis methods often suffer performance degradation under varying real-world operating conditions, primarily due to distribution shifts. Domain generalization (DG) techniques have been introduced to address this issue, aiming to enhance model performance under unseen working conditions. However, existing methods often overlook the significance of multi-level feature representations in learning generalizable information. Furthermore, most methods disregard the fact that not all source domains contribute equally to generalization, where certain domains provide more transferable features than others. To address these challenges, this paper proposes a self-distillation-based domain weighted generalization method for fault diagnosis. With the Vision Transformer (ViT) as the backbone, the method first incorporates a self-distillation mechanism that distills class-specific knowledge within class tokens from the final transformer block to intermediate blocks, enabling the learning of more generalized features. Second, a dynamic domain weighting strategy based on self-distillation loss is proposed, which assigns higher weights to domains with more generalized features. Finally, these weights are integrated into domain adversarial learning and fault classification process. Extensive experiments on motor fault diagnosis are conducted, covering multiple conditions including constant conditions, start-up and shut-down conditions, and the New European Driving Cycle (NEDC) conditions. Experimental results on 33 cross-condition tasks, including constant-to-constant, constant-to-variable, and variable-to-variable tasks, demonstrate that the proposed method achieves superior accuracy and robustness compared with several representative methods. Ablation studies further validate the effectiveness of each component in the proposed method.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-13
Self-Distillation-Based Domain Weighted Generalization Method for Fault Diagnosis Under Actual Unseen Working Conditions
In modern industry, fault diagnosis is critical for ensuring production safety and efficiency. Intelligent fault diagnosis methods often suffer performance degradation under varying real-world operating conditions, primarily due to distribution shifts. Domain generalization (DG) techniques have been introduced to address this issue, aiming to enhance model performance under unseen working conditions. However, existing methods often overlook the significance of multi-level feature representations in learning generalizable information. Furthermore, most methods disregard the fact that not all source domains contribute equally to generalization, where certain domains provide more transferable features than others. To address these challenges, this paper proposes a self-distillation-based domain weighted generalization method for fault diagnosis. With the Vision Transformer (ViT) as the backbone, the method first incorporates a self-distillation mechanism that distills class-specific knowledge within class tokens from the final transformer block to intermediate blocks, enabling the learning of more generalized features. Second, a dynamic domain weighting strategy based on self-distillation loss is proposed, which assigns higher weights to domains with more generalized features. Finally, these weights are integrated into domain adversarial learning and fault classification process. Extensive experiments on motor fault diagnosis are conducted, covering multiple conditions including constant conditions, start-up and shut-down conditions, and the New European Driving Cycle (NEDC) conditions. Experimental results on 33 cross-condition tasks, including constant-to-constant, constant-to-variable, and variable-to-variable tasks, demonstrate that the proposed method achieves superior accuracy and robustness compared with several representative methods. Ablation studies further validate the effectiveness of each component in the proposed method.
- Open Access
Multi-modal cross-domain mixed fusion model with dual disentanglement for fault diagnosis under unseen working conditions
Intelligent fault diagnosis has become an indispensable technique for ensuring machinery reliability. However, existing methods suffer significant performance decline in real-world scenarios where models are tested under unseen working conditions, while domain adaptation approaches are limited to their reliance on target domain samples. Moreover, most existing studies rely on single-modal sensing signals, overlooking the complementary nature of multi-modal information for improving model generalization. To address these limitations, this paper proposes a multi-modal cross-domain mixed fusion model with dual disentanglement for fault diagnosis. A dual disentanglement framework is developed to decouple modality-invariant and modality-specific features, as well as domain-invariant and domain-specific representations, enabling both comprehensive multi-modal representation learning and robust domain generalization. A cross-domain mixed fusion strategy is designed to randomly mix modality information across domains for modality and domain diversity augmentation. Furthermore, a triple-modal fusion mechanism is introduced to adaptively integrate multi-modal heterogeneous information. Extensive experiments are conducted on induction motor fault diagnosis under both unseen constant and time-varying working conditions. The results demonstrate that the proposed method consistently outperforms advanced methods and comprehensive ablation studies further verify the effectiveness of each proposed component and multi-modal fusion. The code is available at: https://github.com/xiapc1996/MMDG.
Open AccessMulti-modal cross-domain mixed fusion model with dual disentanglement for fault diagnosis under unseen working conditions
Intelligent fault diagnosis has become an indispensable technique for ensuring machinery reliability. However, existing methods suffer significant performance decline in real-world scenarios where models are tested under unseen working conditions, while domain adaptation approaches are limited to their reliance on target domain samples. Moreover, most existing studies rely on single-modal sensing signals, overlooking the complementary nature of multi-modal information for improving model generalization. To address these limitations, this paper proposes a multi-modal cross-domain mixed fusion model with dual disentanglement for fault diagnosis. A dual disentanglement framework is developed to decouple modality-invariant and modality-specific features, as well as domain-invariant and domain-specific representations, enabling both comprehensive multi-modal representation learning and robust domain generalization. A cross-domain mixed fusion strategy is designed to randomly mix modality information across domains for modality and domain diversity augmentation. Furthermore, a triple-modal fusion mechanism is introduced to adaptively integrate multi-modal heterogeneous information. Extensive experiments are conducted on induction motor fault diagnosis under both unseen constant and time-varying working conditions. The results demonstrate that the proposed method consistently outperforms advanced methods and comprehensive ablation studies further verify the effectiveness of each proposed component and multi-modal fusion. The code is available at: https://github.com/xiapc1996/MMDG.
- 23 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 11428-11442
Learn to Supervise: Deep Reinforcement Learning-Based Prototype Refinement for Few-Shot Motor Fault Diagnosis
Motor fault diagnosis is a fundamental aspect of ensuring the reliability of industrial equipment. However, industrial scenarios exhibit an inherent data scarcity problem, which imposes significant restrictions on the practical application of traditional deep learning-based intelligent fault diagnosis (IFD) methods. Typically, only a small volume of labeled data along with limited informative unlabeled data are available from industrial motors. Effectively utilizing informative unlabeled samples in the context of few-shot fault diagnosis poses a substantial challenge. In this article, a prototype refinement method for semi-supervised few-shot fault diagnosis based on deep reinforcement learning (DRL) is proposed. First, we propose to formalize a Markov decision process (MDP) of an iterative semi-supervised meta-learning strategy involving the selection of informative unlabeled samples and the refinement of category prototypes. Subsequently, we develop a mirror prototypical network (ProtoNet) structure for interaction with a DRL agent, which learns to adaptively select valuable samples to supervise the diagnosis process. Moreover, a state space involving feature embedding and category information is designed, and a comprehensive reward taking into account selection confidence, effectiveness, and representative is proposed. Extensive experiments on several motor experimental datasets verify the method’s effectiveness in few-shot diagnosis of unseen faults and new working conditions.
- 23 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 11428-11442
Learn to Supervise: Deep Reinforcement Learning-Based Prototype Refinement for Few-Shot Motor Fault Diagnosis
Motor fault diagnosis is a fundamental aspect of ensuring the reliability of industrial equipment. However, industrial scenarios exhibit an inherent data scarcity problem, which imposes significant restrictions on the practical application of traditional deep learning-based intelligent fault diagnosis (IFD) methods. Typically, only a small volume of labeled data along with limited informative unlabeled data are available from industrial motors. Effectively utilizing informative unlabeled samples in the context of few-shot fault diagnosis poses a substantial challenge. In this article, a prototype refinement method for semi-supervised few-shot fault diagnosis based on deep reinforcement learning (DRL) is proposed. First, we propose to formalize a Markov decision process (MDP) of an iterative semi-supervised meta-learning strategy involving the selection of informative unlabeled samples and the refinement of category prototypes. Subsequently, we develop a mirror prototypical network (ProtoNet) structure for interaction with a DRL agent, which learns to adaptively select valuable samples to supervise the diagnosis process. Moreover, a state space involving feature embedding and category information is designed, and a comprehensive reward taking into account selection confidence, effectiveness, and representative is proposed. Extensive experiments on several motor experimental datasets verify the method’s effectiveness in few-shot diagnosis of unseen faults and new working conditions.
- 4 October 2023
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (7) , 3459-3477
Towards prognostic generalization: a domain conditional invariance and specificity disentanglement network for remaining useful life prediction
- 4 October 2023
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (7) , 3459-3477
Towards prognostic generalization: a domain conditional invariance and specificity disentanglement network for remaining useful life prediction
- Open Access
- 4 September 2023
- Published by PHM Society in PHM Society Asia-Pacific Conference
- Vol. 4 (1)
Multi-periodicity and Multi-scale Network for Motor Fault Diagnosis
Intelligent fault diagnosis of motor is of tremendous significance to ensuring reliable industrial production, and deep learning methods have gained notable achievements recently. Most researches automatically extracted fault information from raw monitoring signals with deep models, whereas the strong periodic temporal information containing in the signals were ignored. To tackle this limitation, a multi-periodicity and multi-scale network is proposed in this paper. 1D monitoring signals are transformed into 2D space with multiple various periods, allowing for the straightforward reflection and modeling of variations both within and between different periods. Multi-scale learning is introduced to extract temporal information from the multi-periodicity representations with multiple scales in a parameter-efficient way. Experiments carried out on a motor fault dataset verified the effectiveness of the proposed method. The results demonstrate that over 99% diagnosis accuracy can be achieved with onechannel vibration signals, and superior performance is obtained under diverse noise conditions compared with other methods.
- 4 September 2023
- Published by PHM Society in PHM Society Asia-Pacific Conference
- Vol. 4 (1)
Open AccessMulti-periodicity and Multi-scale Network for Motor Fault Diagnosis
Intelligent fault diagnosis of motor is of tremendous significance to ensuring reliable industrial production, and deep learning methods have gained notable achievements recently. Most researches automatically extracted fault information from raw monitoring signals with deep models, whereas the strong periodic temporal information containing in the signals were ignored. To tackle this limitation, a multi-periodicity and multi-scale network is proposed in this paper. 1D monitoring signals are transformed into 2D space with multiple various periods, allowing for the straightforward reflection and modeling of variations both within and between different periods. Multi-scale learning is introduced to extract temporal information from the multi-periodicity representations with multiple scales in a parameter-efficient way. Experiments carried out on a motor fault dataset verified the effectiveness of the proposed method. The results demonstrate that over 99% diagnosis accuracy can be achieved with onechannel vibration signals, and superior performance is obtained under diverse noise conditions compared with other methods.
- 1 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (18) , 21408-21420
Adaptive Feature Utilization With Separate Gating Mechanism and Global Temporal Convolutional Network for Remaining Useful Life Prediction
Machinery remaining useful life (RUL) prediction plays a pivotal role in modern industrial maintenance. Traditional methods entail the manual selection of useful features, which requires prior knowledge and lack adaptability to diverse cases. Moreover, as features may have different relevance to the degradation process at various stages, the prognostic performance will be limited by the utilization of fixed features throughout the full life-time. Additionally, most deep learning methods lack the perception of global information of features, which is critical to RUL prediction. To tackle these issues, an adaptive feature utilization method with separate gating mechanism and global temporal convolutional network (SGGTCN) is proposed in this paper. First, a separate gating mechanism is proposed to adaptively model temporal information within each feature individually through a series of designed separate gated residual modules. Second, an adaptive feature utilization method is proposed to evaluate and dynamically weight feature importance. Third, a global temporal convolutional network is proposed to model and fuse global temporal information for comprehensive sequential modeling. The effectiveness and superiority of the proposed method are validated by two prognostic case studies of turbofan engines and bearings.
- 1 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (18) , 21408-21420
Adaptive Feature Utilization With Separate Gating Mechanism and Global Temporal Convolutional Network for Remaining Useful Life Prediction
Machinery remaining useful life (RUL) prediction plays a pivotal role in modern industrial maintenance. Traditional methods entail the manual selection of useful features, which requires prior knowledge and lack adaptability to diverse cases. Moreover, as features may have different relevance to the degradation process at various stages, the prognostic performance will be limited by the utilization of fixed features throughout the full life-time. Additionally, most deep learning methods lack the perception of global information of features, which is critical to RUL prediction. To tackle these issues, an adaptive feature utilization method with separate gating mechanism and global temporal convolutional network (SGGTCN) is proposed in this paper. First, a separate gating mechanism is proposed to adaptively model temporal information within each feature individually through a series of designed separate gated residual modules. Second, an adaptive feature utilization method is proposed to evaluate and dynamically weight feature importance. Third, a global temporal convolutional network is proposed to model and fuse global temporal information for comprehensive sequential modeling. The effectiveness and superiority of the proposed method are validated by two prognostic case studies of turbofan engines and bearings.