Xiaochun Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaochun Sun has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Hua Ding
College of Mechanical and Vehicle Engineering, Shanxi Key Laboratory of Fully Mechanized Coal Mining Equipment, Taiyuan University of Technology, Taiyuan, China
4 shared publications - Ning Li
College of Mechanical and Vehicle Engineering, Shanxi Key Laboratory of Fully Mechanized Coal Mining Equipment, Taiyuan University of Technology, Taiyuan, China
4 shared publications Zeping Liu
Heavy Coal Machine Co.Ltd, Taiyuan 030024, People’s Republic of China
2 shared publicationsGuoshu Pu
Shaanxi Tongwei Digital Technology Co., Ltd, Xi’an 710000, People’s Republic of China
1 shared publication- Guoshu Pu
Shaanxi Tongwei Digital Technology Company Ltd, Xian, China
1 shared publication Hua Ding
Shanxi Key Laboratory of Fully Mechanized Coal Mining Equipment, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, China
1 shared publication
Latest Publications
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. PP (1530437X) , 1
Parallel Fusion of Swin Transformer and SKNet for Rolling Bearing Fault Diagnosis
To address the issue of insufficient feature extraction from nonlinear and non-stationary vibration signals of rolling bearings under strong noise environments, which limits the diagnostic accuracy of existing fault diagnosis models, this paper proposes an intelligent fault diagnosis method based on the parallel fusion of Swin Transformer (SwinT) and selective kernel network (SKNet). The proposed method enables cooperative modeling of global and local features. It consists of a simplified SwinT branch and a lightweight SKNet branch. The SwinT branch incorporates an improved Bottleneck Attention Module (IBAM) to enhance the model's capacity for capturing global features. The lightweight SKNet branch utilizes blueprint separable convolution (BSConv) to replace traditional convolution operations and adopts a 1D convolutional structure instead of the original fully connected layers in SKNet, thereby reducing the number of parameters and model complexity, which may facilitate deployment in resource-constrained environments. Experimental verification was carried out based on the data collected from the public bearing dataset of the University of Paderborn in Germany and the rolling bearing fault simulation platform built in the laboratory. The results demonstrate that the proposed method outperforms several comparative models in terms of accuracy, precision, and recall. It maintains a recognition accuracy close to 90% even at a signal-to-noise ratio (SNR) of -8 dB, indicating its strong noise immunity and robustness.
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. PP (1530437X) , 1
Parallel Fusion of Swin Transformer and SKNet for Rolling Bearing Fault Diagnosis
To address the issue of insufficient feature extraction from nonlinear and non-stationary vibration signals of rolling bearings under strong noise environments, which limits the diagnostic accuracy of existing fault diagnosis models, this paper proposes an intelligent fault diagnosis method based on the parallel fusion of Swin Transformer (SwinT) and selective kernel network (SKNet). The proposed method enables cooperative modeling of global and local features. It consists of a simplified SwinT branch and a lightweight SKNet branch. The SwinT branch incorporates an improved Bottleneck Attention Module (IBAM) to enhance the model's capacity for capturing global features. The lightweight SKNet branch utilizes blueprint separable convolution (BSConv) to replace traditional convolution operations and adopts a 1D convolutional structure instead of the original fully connected layers in SKNet, thereby reducing the number of parameters and model complexity, which may facilitate deployment in resource-constrained environments. Experimental verification was carried out based on the data collected from the public bearing dataset of the University of Paderborn in Germany and the rolling bearing fault simulation platform built in the laboratory. The results demonstrate that the proposed method outperforms several comparative models in terms of accuracy, precision, and recall. It maintains a recognition accuracy close to 90% even at a signal-to-noise ratio (SNR) of -8 dB, indicating its strong noise immunity and robustness.
- Open Access
Intelligent Fault Diagnosis of Hydraulic System Based on Multiscale One-Dimensional Convolutional Neural Networks with Multiattention Mechanism
Hydraulic systems are critical components of mechanical equipment, and effective fault diagnosis is essential for minimizing maintenance costs and enhancing system reliability. In practical applications, data from hydraulic systems are collected with varying sampling frequencies, coupled with complex interdependencies within the data, which poses challenges for existing fault diagnosis algorithms. To solve the above problems, this paper proposes an intelligent fault diagnosis of a hydraulic system based on a multiscale one-dimensional convolution neural network with a multiattention mechanism (MA-MS1DCNN). The proposed method first extracts features from multirate data samples using a parallel 1DCNN with different receptive fields. Next, a Hybrid Attention Module (HAM) is proposed, consisting of two submodules: the Correlation Attention Module (CAM) and the Importance Attention Module (IAM), which aim to meticulously and comprehensively model the complex relationships between channel features. Subsequently, to effectively utilize the feature information of different frequencies, the HAM is integrated into the 1DCNN to form the MA-MS1DCNN. Finally, the proposed method is evaluated and experimentally compared using the UCI hydraulic system dataset. The results demonstrate that, compared to existing methods such as Shapelet, MCIFM, and CNNs, the proposed method shows superior diagnostic performance.
Open AccessIntelligent Fault Diagnosis of Hydraulic System Based on Multiscale One-Dimensional Convolutional Neural Networks with Multiattention Mechanism
Hydraulic systems are critical components of mechanical equipment, and effective fault diagnosis is essential for minimizing maintenance costs and enhancing system reliability. In practical applications, data from hydraulic systems are collected with varying sampling frequencies, coupled with complex interdependencies within the data, which poses challenges for existing fault diagnosis algorithms. To solve the above problems, this paper proposes an intelligent fault diagnosis of a hydraulic system based on a multiscale one-dimensional convolution neural network with a multiattention mechanism (MA-MS1DCNN). The proposed method first extracts features from multirate data samples using a parallel 1DCNN with different receptive fields. Next, a Hybrid Attention Module (HAM) is proposed, consisting of two submodules: the Correlation Attention Module (CAM) and the Importance Attention Module (IAM), which aim to meticulously and comprehensively model the complex relationships between channel features. Subsequently, to effectively utilize the feature information of different frequencies, the HAM is integrated into the 1DCNN to form the MA-MS1DCNN. Finally, the proposed method is evaluated and experimentally compared using the UCI hydraulic system dataset. The results demonstrate that, compared to existing methods such as Shapelet, MCIFM, and CNNs, the proposed method shows superior diagnostic performance.
- 10 April 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (7) , 075002
Intelligent fault diagnosis of rolling bearings under small samples based on lightweight UNet with attention-fused residual block
In rotating machinery, rolling bearings are crucial, and their failure can lead to severe accidents and economic losses. Therefore, fault diagnosis of bearings is necessary to maintain the safe and stable operation of modern machinery and equipment. Currently, data-driven intelligent diagnosis methods are mainstream; however, in practical applications, problems such as insufficient fault samples and strong interference signals often exist. At the same time, a large number of edge-end and mobile devices put higher requirements for the size of the diagnostic model. This study addresses these issues by proposing a lightweight UNet (LWUNet) model, which integrates wavelet packet decomposition (WPD) and attention-fused residual block (AFRB) for fault diagnosis in rolling bearings under varying operating conditions, particularly for small sample sizes. Firstly, WPD is used to decompose and reconstruct the fault signal to achieve effective denoising. Secondly, a LW-UNet is constructed for pixel-level feature learning to reduce the number of parameters and improve the accuracy rate. Thereafter, to further enhance the model feature extraction capability, the AFRB is proposed and embedded into the LWUNet to develop the AFRB-LWUNet model. Finally, the reconstructed signals are input to the proposed model for training, and the model performance is examined using a test set. The proposed method is compared with other fault diagnosis models using small sample data of rolling bearings from the Case Western Reserve University, USA and the University of Paderborn, Germany. The results confirm the higher recognition accuracy, stronger generalization ability, and robustness of the proposed method for small samples under various working conditions and intense noise.
- 10 April 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (7) , 075002
Intelligent fault diagnosis of rolling bearings under small samples based on lightweight UNet with attention-fused residual block
In rotating machinery, rolling bearings are crucial, and their failure can lead to severe accidents and economic losses. Therefore, fault diagnosis of bearings is necessary to maintain the safe and stable operation of modern machinery and equipment. Currently, data-driven intelligent diagnosis methods are mainstream; however, in practical applications, problems such as insufficient fault samples and strong interference signals often exist. At the same time, a large number of edge-end and mobile devices put higher requirements for the size of the diagnostic model. This study addresses these issues by proposing a lightweight UNet (LWUNet) model, which integrates wavelet packet decomposition (WPD) and attention-fused residual block (AFRB) for fault diagnosis in rolling bearings under varying operating conditions, particularly for small sample sizes. Firstly, WPD is used to decompose and reconstruct the fault signal to achieve effective denoising. Secondly, a LW-UNet is constructed for pixel-level feature learning to reduce the number of parameters and improve the accuracy rate. Thereafter, to further enhance the model feature extraction capability, the AFRB is proposed and embedded into the LWUNet to develop the AFRB-LWUNet model. Finally, the reconstructed signals are input to the proposed model for training, and the model performance is examined using a test set. The proposed method is compared with other fault diagnosis models using small sample data of rolling bearings from the Case Western Reserve University, USA and the University of Paderborn, Germany. The results confirm the higher recognition accuracy, stronger generalization ability, and robustness of the proposed method for small samples under various working conditions and intense noise.
- 1 November 2023
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (2) , 025003
Application of local and global interval embedding algorithms in uncertain system processes
The data collected during the fault monitoring of industrial processes are often uncertain because of measurement noise, sensor error, and complex working environments. Currently, most of this uncertainty is transformed into interval-value data for processing. However, the traditional interval fault monitoring method (TIFMM) only considers the global information of the interval-valued data and only rarely considers the local neighborhood information, which can characterize the topological relationship between the interval-valued data points, so that the sample points with some nonlinear relationship still maintain this nonlinear relationship after dimensionality reduction. Therefore, to take into account both local and global information, a new interval-valued data projection algorithm called local and global interval embedding algorithms (LGIEA) is proposed in this paper. First, the measurement error estimation method, based on the principle of reasonable granularity, converts the imprecise variable measurement values into interval-value data that can reflect uncertainty. Then, an interval-matrix feature extraction method based on local and global information fusion, proposed in this paper, extracts process features by minimizing local scattering and maximizing global scattering of interval-valued data. Thereby, it preserves the optimal local neighborhood and global information in low-dimensional space. In addition, four statistical indicators and corresponding variable-contribution graphs have been defined to use online fault monitoring and fault variable identification. Finally, the superiority of the LGIEA was verified using simulation data of the Tennessee Eastman process and actual operating data of a shearer in an inclined-ditch coal mine. The experimental results show that, Compared with TIFMM such as midpoint-radius principal component analysis (PCA), complete information PCA and spectral radius-based interval PCA, proposed method significantly reduces the error alarm rate and the false monitoring rate and improves the accuracy of data classification. It also has better fault identification accuracy and robustness.
- 1 November 2023
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (2) , 025003
Application of local and global interval embedding algorithms in uncertain system processes
The data collected during the fault monitoring of industrial processes are often uncertain because of measurement noise, sensor error, and complex working environments. Currently, most of this uncertainty is transformed into interval-value data for processing. However, the traditional interval fault monitoring method (TIFMM) only considers the global information of the interval-valued data and only rarely considers the local neighborhood information, which can characterize the topological relationship between the interval-valued data points, so that the sample points with some nonlinear relationship still maintain this nonlinear relationship after dimensionality reduction. Therefore, to take into account both local and global information, a new interval-valued data projection algorithm called local and global interval embedding algorithms (LGIEA) is proposed in this paper. First, the measurement error estimation method, based on the principle of reasonable granularity, converts the imprecise variable measurement values into interval-value data that can reflect uncertainty. Then, an interval-matrix feature extraction method based on local and global information fusion, proposed in this paper, extracts process features by minimizing local scattering and maximizing global scattering of interval-valued data. Thereby, it preserves the optimal local neighborhood and global information in low-dimensional space. In addition, four statistical indicators and corresponding variable-contribution graphs have been defined to use online fault monitoring and fault variable identification. Finally, the superiority of the LGIEA was verified using simulation data of the Tennessee Eastman process and actual operating data of a shearer in an inclined-ditch coal mine. The experimental results show that, Compared with TIFMM such as midpoint-radius principal component analysis (PCA), complete information PCA and spectral radius-based interval PCA, proposed method significantly reduces the error alarm rate and the false monitoring rate and improves the accuracy of data classification. It also has better fault identification accuracy and robustness.
- Open Access
- 18 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 123007-123019
Residual Life Prediction of Bearings Based on SENet-TCN and Transfer Learning
Accurate bearing remaining life prediction guarantees safety and continued profitability for the industry. Variable operating conditions of the bearing and difficulty in obtaining corresponding data labels in the industry result in low prediction accuracy of the model. To solve these problems, a bearing life prediction model based on an improved temporal convolutional network and transfer learning is proposed. First, the squeeze-and-excitation network is used to mine and recalibrate the deep features of source domain data. Second, the temporal convolutional network is used to calibrate the relationship between the features and lifetime, and the optimal source domain model is trained. Finally, the transfer learning training is conducted with the source domain model to obtain the transfer model, which can accurately predict the remaining life of the multi-operating condition signal. Comparative experiments were performed on IEEE PHM Challenge 2012 bearing life dataset. The results show that the proposed method can better mine the inherent degradation trend of bearings and effectively improve the prediction accuracy of the remaining useful life. Compared with the existing popular prediction methods, the prediction error was reduced by “20.8%” to “51.5%”, which proves the effectiveness and feasibility of the proposed method.
- 18 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 123007-123019
Open AccessResidual Life Prediction of Bearings Based on SENet-TCN and Transfer Learning
Accurate bearing remaining life prediction guarantees safety and continued profitability for the industry. Variable operating conditions of the bearing and difficulty in obtaining corresponding data labels in the industry result in low prediction accuracy of the model. To solve these problems, a bearing life prediction model based on an improved temporal convolutional network and transfer learning is proposed. First, the squeeze-and-excitation network is used to mine and recalibrate the deep features of source domain data. Second, the temporal convolutional network is used to calibrate the relationship between the features and lifetime, and the optimal source domain model is trained. Finally, the transfer learning training is conducted with the source domain model to obtain the transfer model, which can accurately predict the remaining life of the multi-operating condition signal. Comparative experiments were performed on IEEE PHM Challenge 2012 bearing life dataset. The results show that the proposed method can better mine the inherent degradation trend of bearings and effectively improve the prediction accuracy of the remaining useful life. Compared with the existing popular prediction methods, the prediction error was reduced by “20.8%” to “51.5%”, which proves the effectiveness and feasibility of the proposed method.