Xiaodong Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaodong Wang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Jiande Wu
School of Engineering, Yunnan University, Kunming, China
3 shared publications - Bo Ye
Kunming University of Science and Technology
2 shared publications - Chengjiang Zhou
School of Information Science and Technology, Yunnan Normal University, Kunming, China
2 shared publications - Guanghui Zhang
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China
2 shared publications - Jun Bao
Faculty of Civil Aviation and Aeronautics, Kunming University of Science and Technology, Kunming 650500, China
2 shared publications - Jun Ma
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China
2 shared publications
Latest Publications
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 23326-23338
Hierarchical Optimal Admittance Control of Cable-Driven Lower Limb Exoskeletons With Unknown Human and System Dynamics
Admittance control is an effective technique for enhancing compliance with the interaction between the exoskeleton and the wearer. In practice, obtaining the desired admittance model parameters is a challenging task under various interaction scenarios with different wearers, especially when the human impedance parameters are indeterminate. In this paper, we propose a hierarchical optimal admittance control consisting of a higher-level admittance learning and a lower-level position control. First, finding the desired admittance model parameters is reformulated as a linear quadratic regulator (LQR) problem, and then a policy iteration (PI) algorithm is proposed to solve the derived LQR problem even with unknown system dynamics and human impedance parameters. With the obtained admittance model, the virtual trajectory is regulated to adapt the human-robot interaction (HRI) torque. Finally, an unknown system dynamics estimator (USDE) is integrated into a lower-level position controller to accommodate the lumped system uncertainties. This approach reduces the computational burden of admittance control while improving the tracking performance of position control. Comparative simulations are conducted to validate the effectiveness of the proposed hierarchical admittance control, and multiple knee joint flexion/extension movement experiments with surface electromyographic (sEMG) measurements are also carried out on three subjects to evaluate its improved compliance performance.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 23326-23338
Hierarchical Optimal Admittance Control of Cable-Driven Lower Limb Exoskeletons With Unknown Human and System Dynamics
Admittance control is an effective technique for enhancing compliance with the interaction between the exoskeleton and the wearer. In practice, obtaining the desired admittance model parameters is a challenging task under various interaction scenarios with different wearers, especially when the human impedance parameters are indeterminate. In this paper, we propose a hierarchical optimal admittance control consisting of a higher-level admittance learning and a lower-level position control. First, finding the desired admittance model parameters is reformulated as a linear quadratic regulator (LQR) problem, and then a policy iteration (PI) algorithm is proposed to solve the derived LQR problem even with unknown system dynamics and human impedance parameters. With the obtained admittance model, the virtual trajectory is regulated to adapt the human-robot interaction (HRI) torque. Finally, an unknown system dynamics estimator (USDE) is integrated into a lower-level position controller to accommodate the lumped system uncertainties. This approach reduces the computational burden of admittance control while improving the tracking performance of position control. Comparative simulations are conducted to validate the effectiveness of the proposed hierarchical admittance control, and multiple knee joint flexion/extension movement experiments with surface electromyographic (sEMG) measurements are also carried out on three subjects to evaluate its improved compliance performance.
- 31 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-11
Implicit Discriminator Domain Adversarial Residual Network for Cross Domain Rolling Bearing Fault Diagnosis
Domain-adversarial learning based fault diagnosis methods have shown prominent application prospects in the field of cross domain fault diagnosis. However, the existing domain-adversarial methods can’t simultaneously consider domain-level discrepancy, inter-class and intra-class correlation of target domain samples, which result in poor feature representation ability of fault diagnosis model for ambiguous targets. For this reason, a fault diagnosis method is proposed by implicit discriminator domain adversarial residual network (DDARN). Firstly, a unified domain adversarial framework based on the Nuclear-norm Wasserstein discrepancy (NWD) is constructed to achieve domain-level feature alignment and adjust the inter class-intra class correlation for ensuring the prediction certainty. Additionally, improved deep residual network (IDRN) integrating the efficient activation function is designed to facilitate the propagation of information and enhance nonlinear representation ability of the network. Finally, case studies on public datasets and self-made KUST-SY bearing datasets indicate DDARN can achieve slightly better diagnostic performance over state-of-the-art methods.
- 31 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-11
Implicit Discriminator Domain Adversarial Residual Network for Cross Domain Rolling Bearing Fault Diagnosis
Domain-adversarial learning based fault diagnosis methods have shown prominent application prospects in the field of cross domain fault diagnosis. However, the existing domain-adversarial methods can’t simultaneously consider domain-level discrepancy, inter-class and intra-class correlation of target domain samples, which result in poor feature representation ability of fault diagnosis model for ambiguous targets. For this reason, a fault diagnosis method is proposed by implicit discriminator domain adversarial residual network (DDARN). Firstly, a unified domain adversarial framework based on the Nuclear-norm Wasserstein discrepancy (NWD) is constructed to achieve domain-level feature alignment and adjust the inter class-intra class correlation for ensuring the prediction certainty. Additionally, improved deep residual network (IDRN) integrating the efficient activation function is designed to facilitate the propagation of information and enhance nonlinear representation ability of the network. Finally, case studies on public datasets and self-made KUST-SY bearing datasets indicate DDARN can achieve slightly better diagnostic performance over state-of-the-art methods.
- 13 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 13782-13793
A Gated Recurrent Generative Transfer Learning Network for Fault Diagnostics Considering Imbalanced Data and Variable Working Conditions
Transfer learning (TL) and generative adversarial networks (GANs) have been widely applied to intelligent fault diagnosis under imbalanced data and different working conditions. However, the existing data synthesis methods focus on the overall distribution alignment between the generated data and real data, and ignore the fault-sensitive features in the time domain, which results in losing convincing temporal information for the generated signal. For this reason, a novel gated recurrent generative TL network (GRGTLN) is proposed. First, a smooth conditional matrix-based gated recurrent generator is proposed to extend the imbalanced dataset. It can adaptively increase the attention of fault-sensitive features in the generated sequence. Wasserstein distance (WD) is introduced to enhance the construction of mapping relationships to promote data generation ability and transfer performance of the fault diagnosis model. Then, an iterative “generation-transfer” co-training strategy is developed for continuous parallel training of the model and the parameter optimization. Finally, comprehensive case studies demonstrate that GRGTLN can generate high-quality data and achieve satisfactory cross-domain diagnosis accuracy.
- 13 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 13782-13793
A Gated Recurrent Generative Transfer Learning Network for Fault Diagnostics Considering Imbalanced Data and Variable Working Conditions
Transfer learning (TL) and generative adversarial networks (GANs) have been widely applied to intelligent fault diagnosis under imbalanced data and different working conditions. However, the existing data synthesis methods focus on the overall distribution alignment between the generated data and real data, and ignore the fault-sensitive features in the time domain, which results in losing convincing temporal information for the generated signal. For this reason, a novel gated recurrent generative TL network (GRGTLN) is proposed. First, a smooth conditional matrix-based gated recurrent generator is proposed to extend the imbalanced dataset. It can adaptively increase the attention of fault-sensitive features in the generated sequence. Wasserstein distance (WD) is introduced to enhance the construction of mapping relationships to promote data generation ability and transfer performance of the fault diagnosis model. Then, an iterative “generation-transfer” co-training strategy is developed for continuous parallel training of the model and the parameter optimization. Finally, comprehensive case studies demonstrate that GRGTLN can generate high-quality data and achieve satisfactory cross-domain diagnosis accuracy.
- Open Access
Fault Diagnosis of Check Valve Based on KPLS Optimal Feature Selection and Kernel Extreme Learning Machine
The check valve is the core part of high-pressure diaphragm pumps. It has complex operation conditions and has difficulty characterizing fault states completely with its single feature. Therefore, a fault signal diagnosis model based on the kernel extreme learning machine (KELM) was constructed to diagnose the check valve. The model adopts a multi-feature extraction method and reduces dimensionality through kernel partial least squares (KPLS). Firstly, we divided the check valve vibration signal into several non-overlapping samples. Then, we extracted 16 time-domain features, 13 frequency-domain features, 16 wavelet packet energy features, and energy entropy features from each sample to construct a multi-feature set characterizing the operation state of the check valve. Next, we used the KPLS method to optimize the 45 dimension multi-feature data and employed the processed feature set to establish a KELM fault diagnosis model. Experiments showed that the method based on KPLS optimal feature selection could fully characterize the operating state of the equipment with an accuracy rate of 96.88%. This result indicates the high accuracy and effectiveness of the multi-feature set constructed with the KELM fault diagnosis model.
Open AccessFault Diagnosis of Check Valve Based on KPLS Optimal Feature Selection and Kernel Extreme Learning Machine
The check valve is the core part of high-pressure diaphragm pumps. It has complex operation conditions and has difficulty characterizing fault states completely with its single feature. Therefore, a fault signal diagnosis model based on the kernel extreme learning machine (KELM) was constructed to diagnose the check valve. The model adopts a multi-feature extraction method and reduces dimensionality through kernel partial least squares (KPLS). Firstly, we divided the check valve vibration signal into several non-overlapping samples. Then, we extracted 16 time-domain features, 13 frequency-domain features, 16 wavelet packet energy features, and energy entropy features from each sample to construct a multi-feature set characterizing the operation state of the check valve. Next, we used the KPLS method to optimize the 45 dimension multi-feature data and employed the processed feature set to establish a KELM fault diagnosis model. Experiments showed that the method based on KPLS optimal feature selection could fully characterize the operating state of the equipment with an accuracy rate of 96.88%. This result indicates the high accuracy and effectiveness of the multi-feature set constructed with the KELM fault diagnosis model.
- Open Access
Research on Twin Extreme Learning Fault Diagnosis Method Based on Multi-Scale Weighted Permutation Entropy
Due to the complicated engineering operation of the check valve in a high−pressure diaphragm pump, its vibration signal tends to show non−stationary and non−linear characteristics. These leads to difficulty extracting fault features and, hence, a low accuracy for fault diagnosis. It is difficult to extract fault features accurately and reliably using the traditional MPE method, and the ELM model has a low accuracy rate in fault classification. Multi−scale weighted permutation entropy (MWPE) is based on extracting multi−scale fault features and arrangement pattern features, and due to the combination of extracting a sequence of amplitude features, fault features are significantly enhanced, which overcomes the deficiency of the single−scale permutation entropy characterizing the complexity of vibration signals. It establishes the check valve fault diagnosis model from the twin extreme learning machine (TELM). The TELM fault diagnosis model established, based on MWPE, aims to find a pair of non−parallel classification hyperplanes in the equipment state space to improve the model’s applicability. Experiments show that the proposed method effectively extracts the characteristics of the vibration signal, and the fault diagnosis model effectively identifies the fault state of the check valve with an accuracy rate of 97.222%.
Open AccessResearch on Twin Extreme Learning Fault Diagnosis Method Based on Multi-Scale Weighted Permutation Entropy
Due to the complicated engineering operation of the check valve in a high−pressure diaphragm pump, its vibration signal tends to show non−stationary and non−linear characteristics. These leads to difficulty extracting fault features and, hence, a low accuracy for fault diagnosis. It is difficult to extract fault features accurately and reliably using the traditional MPE method, and the ELM model has a low accuracy rate in fault classification. Multi−scale weighted permutation entropy (MWPE) is based on extracting multi−scale fault features and arrangement pattern features, and due to the combination of extracting a sequence of amplitude features, fault features are significantly enhanced, which overcomes the deficiency of the single−scale permutation entropy characterizing the complexity of vibration signals. It establishes the check valve fault diagnosis model from the twin extreme learning machine (TELM). The TELM fault diagnosis model established, based on MWPE, aims to find a pair of non−parallel classification hyperplanes in the equipment state space to improve the model’s applicability. Experiments show that the proposed method effectively extracts the characteristics of the vibration signal, and the fault diagnosis model effectively identifies the fault state of the check valve with an accuracy rate of 97.222%.
- Open Access
- 28 September 2020
- Published by Frontiers Media SA in Frontiers in Materials
- Vol. 7
A Deep Belief network and Least Squares Support Vector Machine Method for Quantitative Evaluation of Defects in Titanium Sheet Using Eddy Current Scan Image
Titanium (Ti) is an ideal structural material whose use is gradually emerging in civil engineering. Regular defect evaluation is indispensable during the long-term use of Ti sheets, which can be performed effectively using eddy current (EC) imaging, a method of visualizing defects that is convenient for inspectors. However, as EC scan images contain abundant information and have discrepancies in terms of their quality, it is difficult to extract effective features, thus affecting the evaluation results. In this article, we propose a method that combines the EC imaging technology with a quantitative evaluation method for Ti sheet defects based on the deep belief network (DBN) and least squares support vector machine (LSSVM). A multilayer DBN is constructed to extract the effective features from EC scan images for Ti sheet defects. Based on the extracted feature vectors, a multi-objective regression model of defect dimensions is established using the LSSVM algorithm. Then, the dimensions of Ti sheet defects such as length, diameter, and depth are quantitatively evaluated by the effective features and the efficient regression model. The experimental results show that the evaluation errors for the defect lengths and depths tested are less than 3 and 5%, respectively, confirming the validity of the proposed method.
- 28 September 2020
- Published by Frontiers Media SA in Frontiers in Materials
- Vol. 7
Open AccessA Deep Belief network and Least Squares Support Vector Machine Method for Quantitative Evaluation of Defects in Titanium Sheet Using Eddy Current Scan Image
Titanium (Ti) is an ideal structural material whose use is gradually emerging in civil engineering. Regular defect evaluation is indispensable during the long-term use of Ti sheets, which can be performed effectively using eddy current (EC) imaging, a method of visualizing defects that is convenient for inspectors. However, as EC scan images contain abundant information and have discrepancies in terms of their quality, it is difficult to extract effective features, thus affecting the evaluation results. In this article, we propose a method that combines the EC imaging technology with a quantitative evaluation method for Ti sheet defects based on the deep belief network (DBN) and least squares support vector machine (LSSVM). A multilayer DBN is constructed to extract the effective features from EC scan images for Ti sheet defects. Based on the extracted feature vectors, a multi-objective regression model of defect dimensions is established using the LSSVM algorithm. Then, the dimensions of Ti sheet defects such as length, diameter, and depth are quantitatively evaluated by the effective features and the efficient regression model. The experimental results show that the evaluation errors for the defect lengths and depths tested are less than 3 and 5%, respectively, confirming the validity of the proposed method.
- 27 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-9
Thickness Measurement of Titanium Alloy Sheet Based on Eddy Current Method With a Novel Simplified Model
This paper proposes a novel simplified model which describes the real part (in-phase component) of the difference in pickup coil voltage, when an eddy current (EC) sensor consisting of tow coils (excitation and pickup coils) is placed above a titanium (Ti) alloy sheet. A parameter that encapsulates the coil geometry factors is integrated into the classical Dodd-Deeds model, and then the model is simplified by combining with the electromagnetic properties of Ti alloy. The use of the simplified model provides a thickness measurement method for Ti alloy sheets. The measured thickness can be calculated directly from the calibration signal by using the model, without the need to predict response by solving forward model in advance. Experimental measurements were conducted on TC4 (Ti-6Al-4V) Ti alloy sheets of different thicknesses with a developed EC sensor and measurement system. The experiment verified the proposed model and measurement method. The experimental results shown that the maximum measurement error is less than 2.86%, which is greatly lower than the permissible error of the current industry standard. This study provides a theoretical basis and a fast method for EC thickness measurement of Ti alloy.
- 27 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-9
Thickness Measurement of Titanium Alloy Sheet Based on Eddy Current Method With a Novel Simplified Model
This paper proposes a novel simplified model which describes the real part (in-phase component) of the difference in pickup coil voltage, when an eddy current (EC) sensor consisting of tow coils (excitation and pickup coils) is placed above a titanium (Ti) alloy sheet. A parameter that encapsulates the coil geometry factors is integrated into the classical Dodd-Deeds model, and then the model is simplified by combining with the electromagnetic properties of Ti alloy. The use of the simplified model provides a thickness measurement method for Ti alloy sheets. The measured thickness can be calculated directly from the calibration signal by using the model, without the need to predict response by solving forward model in advance. Experimental measurements were conducted on TC4 (Ti-6Al-4V) Ti alloy sheets of different thicknesses with a developed EC sensor and measurement system. The experiment verified the proposed model and measurement method. The experimental results shown that the maximum measurement error is less than 2.86%, which is greatly lower than the permissible error of the current industry standard. This study provides a theoretical basis and a fast method for EC thickness measurement of Ti alloy.