Jianbin Xiong
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
Research Subjects
Research Interests
Jianbin Xiong has a total of 128 co-authors. Here are the top co-authors by number of shared publications:
- Qi Wang
Guangdong Polytechnic Normal University
17 shared publications - Jian Cen
Guangdong Polytechnic Normal University
9 shared publications - Jianxiang Yang
School of Automation, Guangdong Polytechnic Normal University, Guangzhou, China
8 shared publications Qinghua Zhang
School of Automation, Guangdong University of Petrochemical Technology, Maoming, China
7 shared publicationsQiong Liang
School of Automation, Guangdong Polytechnic Normal University, Guangzhou 510665, People’s Republic of China
7 shared publicationsJian Cen
Department of the School of Automation, Guangdong Polytechnic Normal University, Guangzhou, China
4 shared publications
Latest Publications
- Open Access
- 17 November 2026
- Published by MDPI AG in Fractal and Fractional
- Vol. 10 (11) , 805
Nonlinear Dynamics and Fractional-Order Adaptive Sliding-Mode Control of Ferroresonance in Wind-Dominated Power Systems
Local ferroresonance in power systems with high wind penetration can arise from coupling between saturable magnetizing inductance and a capacitive network. To address this problem, a single-phase mechanistic model is developed. The model includes nonlinear main magnetization and direction-dependent hysteresis branches. Complex oscillations and coexisting responses are examined through equivalent-excitation amplitude scans and comparisons of initial conditions and magnetization parameters. The analysis is based on time-domain responses, phase trajectories, spectra, the Poincaré sections, and hysteresis-loop areas. Fractional-order memory is implemented through the Oustaloup rational approximation. Its positive-weight decomposition is proved. A double-power sliding surface and an adaptive reaching law are constructed. The finite-dimensional continuous-time closed loop with derivative-truncation compensation is analyzed. Under bounded matched disturbances and the stated parameter, realization, and initial-state conditions, the sliding variable is proved to enter a neighborhood in finite time and remain there. Ultimate bounds are derived for flux linkage, the voltage state variable, and memory states. Simulations show suppression of naturally developed abnormal oscillations under the tested conditions. State deviations are reduced by adaptive compensation when preset fixed-gain compensation is insufficient. Input variation is reduced by continuous switching under identical sampling conditions. Order scans and ablation with otherwise identical parameters show that memory feedback does not necessarily improve transient performance. Joint selection of the order, gains, and initialization is therefore guided by regulation objectives and input constraints. These results can inform mechanism analysis and feedback suppression of local ferroresonance.
- 17 November 2026
- Published by MDPI AG in Fractal and Fractional
- Vol. 10 (11) , 805
Open AccessNonlinear Dynamics and Fractional-Order Adaptive Sliding-Mode Control of Ferroresonance in Wind-Dominated Power Systems
Local ferroresonance in power systems with high wind penetration can arise from coupling between saturable magnetizing inductance and a capacitive network. To address this problem, a single-phase mechanistic model is developed. The model includes nonlinear main magnetization and direction-dependent hysteresis branches. Complex oscillations and coexisting responses are examined through equivalent-excitation amplitude scans and comparisons of initial conditions and magnetization parameters. The analysis is based on time-domain responses, phase trajectories, spectra, the Poincaré sections, and hysteresis-loop areas. Fractional-order memory is implemented through the Oustaloup rational approximation. Its positive-weight decomposition is proved. A double-power sliding surface and an adaptive reaching law are constructed. The finite-dimensional continuous-time closed loop with derivative-truncation compensation is analyzed. Under bounded matched disturbances and the stated parameter, realization, and initial-state conditions, the sliding variable is proved to enter a neighborhood in finite time and remain there. Ultimate bounds are derived for flux linkage, the voltage state variable, and memory states. Simulations show suppression of naturally developed abnormal oscillations under the tested conditions. State deviations are reduced by adaptive compensation when preset fixed-gain compensation is insufficient. Input variation is reduced by continuous switching under identical sampling conditions. Order scans and ablation with otherwise identical parameters show that memory feedback does not necessarily improve transient performance. Joint selection of the order, gains, and initialization is therefore guided by regulation objectives and input constraints. These results can inform mechanism analysis and feedback suppression of local ferroresonance.
- 29 September 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (15) , 456
Safe maximin multiple graph learning for multi-view clustering
- 29 September 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (15) , 456
Safe maximin multiple graph learning for multi-view clustering
- 17 August 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (33) , 336104
WBLG: a method for bearing fault diagnosis based on the fusion of spatial and temporal features
Bearing fault diagnosis is a key strategy to ensure the stability of mechanical systems, optimize maintenance plans and improve operational reliability. Vibration signals are complex time series with unique properties. Most of the current methods only consider the spatial characteristics of the signal, but do not take into account its temporal characteristics. In fact, vibration signals contain both spatial and temporal information, offering not only rich temporal dynamic details but also spatial structural insights that reflect fault characteristics. Therefore, in order to fully mine and integrate the spatiotemporal feature information in vibration signals to enhance the accuracy and robustness of intelligent diagnosis, we propose a bearing fault diagnosis method based on the fusion of spatial and temporal features. Firstly, an improved wide kernel deep convolutional neural network method was proposed. By using an adaptive channel module, the model was enabled to focus on the key features of the vibration signal and suppress the interference of irrelevant information. At the same time, the superimposed bidirectional long short-term memory layer and the gated recurrent unit effectively capture the long-term dependencies of the time series in the dataset, covering both past and future signal features. This method can effectively utilize temporal information and combine it with spatial features, significantly improving the accuracy and robustness of bearing diagnosis. To verify the proposed method, ablation and comparative experiments were conducted on two publicly available bearing datasets: the Case Western Reserve University dataset and the Guangdong University of Petrochemical Technology dataset. The experimental results show that the average accuracy rates of fault diagnosis of the WBLG network on the two sets of datasets have reached 99.7% and 96.5% respectively. Compared with the existing models, the maximum improvement rates are 3.73% and 12.4% respectively. It demonstrates its superior classification performance and generalization applicable to bearing fault diagnosis.
- 17 August 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (33) , 336104
WBLG: a method for bearing fault diagnosis based on the fusion of spatial and temporal features
Bearing fault diagnosis is a key strategy to ensure the stability of mechanical systems, optimize maintenance plans and improve operational reliability. Vibration signals are complex time series with unique properties. Most of the current methods only consider the spatial characteristics of the signal, but do not take into account its temporal characteristics. In fact, vibration signals contain both spatial and temporal information, offering not only rich temporal dynamic details but also spatial structural insights that reflect fault characteristics. Therefore, in order to fully mine and integrate the spatiotemporal feature information in vibration signals to enhance the accuracy and robustness of intelligent diagnosis, we propose a bearing fault diagnosis method based on the fusion of spatial and temporal features. Firstly, an improved wide kernel deep convolutional neural network method was proposed. By using an adaptive channel module, the model was enabled to focus on the key features of the vibration signal and suppress the interference of irrelevant information. At the same time, the superimposed bidirectional long short-term memory layer and the gated recurrent unit effectively capture the long-term dependencies of the time series in the dataset, covering both past and future signal features. This method can effectively utilize temporal information and combine it with spatial features, significantly improving the accuracy and robustness of bearing diagnosis. To verify the proposed method, ablation and comparative experiments were conducted on two publicly available bearing datasets: the Case Western Reserve University dataset and the Guangdong University of Petrochemical Technology dataset. The experimental results show that the average accuracy rates of fault diagnosis of the WBLG network on the two sets of datasets have reached 99.7% and 96.5% respectively. Compared with the existing models, the maximum improvement rates are 3.73% and 12.4% respectively. It demonstrates its superior classification performance and generalization applicable to bearing fault diagnosis.
- 19 May 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (22)
A review on the application of Multi-source data fusion in fault diagnosis of rotating machinery
Intelligent fault diagnosis of rotating machinery has emerged as a key research focus in industrial applications, driven by the need to reduce safety risks and economic losses associated with unexpected equipment failures. This review systematically explores the integration of heterogeneous sensor data through multi-source data fusion (MSDF) techniques for the purpose of diagnosing faults in rotating machinery. This review begins by introducing the basic concepts of MSDF, providing a foundation for the subsequent discussion. Subsequently, it reviews the commonly used tools and methods in this field. Building on this foundation, the analysis conducts an in-depth examination of multi-sensor fusion methodologies deployed in intelligent diagnostic systems, with particular emphasis on empirical validation studies. The study subsequently identifies and critically evaluates prevailing challenges in sensor-integrated fault detection frameworks, while outlining actionable pathways for future research innovation. Ultimately, the review bridges theoretical frameworks with practical implementation, offering a multidisciplinary perspective valuable to both researchers and industrial practitioners.
- 19 May 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (22)
A review on the application of Multi-source data fusion in fault diagnosis of rotating machinery
Intelligent fault diagnosis of rotating machinery has emerged as a key research focus in industrial applications, driven by the need to reduce safety risks and economic losses associated with unexpected equipment failures. This review systematically explores the integration of heterogeneous sensor data through multi-source data fusion (MSDF) techniques for the purpose of diagnosing faults in rotating machinery. This review begins by introducing the basic concepts of MSDF, providing a foundation for the subsequent discussion. Subsequently, it reviews the commonly used tools and methods in this field. Building on this foundation, the analysis conducts an in-depth examination of multi-sensor fusion methodologies deployed in intelligent diagnostic systems, with particular emphasis on empirical validation studies. The study subsequently identifies and critically evaluates prevailing challenges in sensor-integrated fault detection frameworks, while outlining actionable pathways for future research innovation. Ultimately, the review bridges theoretical frameworks with practical implementation, offering a multidisciplinary perspective valuable to both researchers and industrial practitioners.
- 31 March 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (15)
TF-MESN: A multi-sensor collaborative small-sample fault identification method for offshore wind turbine gearbox
Offshore wind turbines face harsh conditions and high maintenance costs, necessitating precise fault classiffcation based on deep learning. However, gearbox variability, scarce fault signals, and poor interpretability challenge this task. Therefore, this paper proposes a multimodal time-frequency enhancement synergistic network (TF-MESN). First, a Time-Frequency Graphic Block Compression Enhancement Method (TF-BCEM) is introduced, to highlight local feature structures and macroscopic time-frequency domain features of signals. Second, a Cascaded Heterogeneous Convolution Module (CHCM) is proposed, which uses heterogeneous convolution kernels through cascaded residual structures of standard convolution and separable convolution to build a convolutional neural network, capable of capturing signal features comprehensively. Third, an Improved Multiscale Statistics and Statistical Dynamic SCRM Module (MSDSM) is proposed, which can reasonably segment effective signals from redundant ones, making the model more suitable for complex scenarios where steady-state and transient faults coexist. Finally, multi-channel feature fusion information is input into a Multi-scale convolutional weighted classiffer (MSWC), which utilizes stride-based multi-scale down sampling convolution and multiple statistics for fault classiffcation adapted to complex information representation. Experiments on two gearbox datasets, validated via visualization, show that TFMESN outperforms four representative methods, with superior generalization and small-sample fault identiffcation capability, meeting offshore wind gearbox fault diagnosis needs.
- 31 March 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (15)
TF-MESN: A multi-sensor collaborative small-sample fault identification method for offshore wind turbine gearbox
Offshore wind turbines face harsh conditions and high maintenance costs, necessitating precise fault classiffcation based on deep learning. However, gearbox variability, scarce fault signals, and poor interpretability challenge this task. Therefore, this paper proposes a multimodal time-frequency enhancement synergistic network (TF-MESN). First, a Time-Frequency Graphic Block Compression Enhancement Method (TF-BCEM) is introduced, to highlight local feature structures and macroscopic time-frequency domain features of signals. Second, a Cascaded Heterogeneous Convolution Module (CHCM) is proposed, which uses heterogeneous convolution kernels through cascaded residual structures of standard convolution and separable convolution to build a convolutional neural network, capable of capturing signal features comprehensively. Third, an Improved Multiscale Statistics and Statistical Dynamic SCRM Module (MSDSM) is proposed, which can reasonably segment effective signals from redundant ones, making the model more suitable for complex scenarios where steady-state and transient faults coexist. Finally, multi-channel feature fusion information is input into a Multi-scale convolutional weighted classiffer (MSWC), which utilizes stride-based multi-scale down sampling convolution and multiple statistics for fault classiffcation adapted to complex information representation. Experiments on two gearbox datasets, validated via visualization, show that TFMESN outperforms four representative methods, with superior generalization and small-sample fault identiffcation capability, meeting offshore wind gearbox fault diagnosis needs.
- 26 February 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (4) , 182
MCAM-Net: multi-scale convolutional attention for enhanced industrial surface defect detection
- 26 February 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (4) , 182
MCAM-Net: multi-scale convolutional attention for enhanced industrial surface defect detection
- Open Access
- 4 February 2026
- Published by MDPI AG in Preprints.org
A Multi-Source Domain Transfer Fault Diagnosis Method Based on Graph Embedding and Adaptive Classifier
To address the prevalent domain inadaptation issue in multi-source domain transfer fault diagnosis, this study proposes a novel model integrating graph embedding technology and adaptive classifiers. The framework combines multi-statistic multi-scale permutation entropy methods to simultaneously optimize projection and classifier performance, thereby enhancing generalization capabilities and diagnostic accuracy. During model construction, a weighted non-parametric maximum mean difference approach is employed to quantify and minimize differences in edge distributions and conditional distributions between source and target domains. Through similarity weight allocation, norm adjustment, and row sparsity learning strategies, the model effectively reduces interference from irrelevant samples. Additionally, by embedding category information and domain manifold structures, the model ensures classification validity of mapped features. Using labeled source domain data and unlabeled target domain data, the study develops a structure-aware adaptive classifier that narrows distribution differences while preserving manifold consistency, significantly improving diagnostic performance under variable operating conditions. Experimental results demonstrate that this multi-source domain transfer model achieves higher accuracy than single-domain approaches. Notably, in rotating machinery variable operating scenarios, the proposed method outperforms existing techniques in both precision and generalization capabilities.
- 4 February 2026
- Published by MDPI AG in Preprints.org
Open AccessA Multi-Source Domain Transfer Fault Diagnosis Method Based on Graph Embedding and Adaptive Classifier
To address the prevalent domain inadaptation issue in multi-source domain transfer fault diagnosis, this study proposes a novel model integrating graph embedding technology and adaptive classifiers. The framework combines multi-statistic multi-scale permutation entropy methods to simultaneously optimize projection and classifier performance, thereby enhancing generalization capabilities and diagnostic accuracy. During model construction, a weighted non-parametric maximum mean difference approach is employed to quantify and minimize differences in edge distributions and conditional distributions between source and target domains. Through similarity weight allocation, norm adjustment, and row sparsity learning strategies, the model effectively reduces interference from irrelevant samples. Additionally, by embedding category information and domain manifold structures, the model ensures classification validity of mapped features. Using labeled source domain data and unlabeled target domain data, the study develops a structure-aware adaptive classifier that narrows distribution differences while preserving manifold consistency, significantly improving diagnostic performance under variable operating conditions. Experimental results demonstrate that this multi-source domain transfer model achieves higher accuracy than single-domain approaches. Notably, in rotating machinery variable operating scenarios, the proposed method outperforms existing techniques in both precision and generalization capabilities.
- Open Access
- 1 February 2026
- Published by MDPI AG in Journal of Sensor and Actuator Networks
- Vol. 15 (1) , 16
Deep Learning-Based Ink Droplet State Recognition for Continuous Inkjet Printing
The high-quality droplet formation in continuous inkjet printing (CIJ) is crucial for precise character deposition on product surfaces. This process, where a piezoelectric transducer perturbs a high-speed ink stream to generate micro-droplets, is highly sensitive to parameters like ink pressure and transducer amplitude. Suboptimal conditions lead to satellite droplet formation and charge transfer issues, adversely affecting print quality and necessitating reliable monitoring. Replacing inefficient manual inspection, this study develops MBSim-YOLO, a deep learning-based method for automated droplet detection. The proposed model enhances the YOLOv8 architecture by integrating MobileNetv3 to reduce computational complexity, a Bidirectional Feature Pyramid Network (BiFPN) for effective multi-scale feature fusion, and a Simple Attention Module (SimAM) to enhance feature representation robustness. A dataset was constructed using images captured by a CCD camera during the droplet ejection process. Experimental results demonstrate that MBSim-YOLO reduces the parameter count by 78.81% compared to the original YOLOv8. At an Intersection over Union (IoU) threshold of 0.5, the model achieved a precision of 98.2%, a recall of 99.1%, and a mean average precision (mAP) of 98.9%. These findings confirm that MBSim-YOLO achieves an optimal balance between high detection accuracy and lightweight performance, offering a viable and efficient solution for real-time, automated quality monitoring in industrial continuous inkjet printing applications.
- 1 February 2026
- Published by MDPI AG in Journal of Sensor and Actuator Networks
- Vol. 15 (1) , 16
Open AccessDeep Learning-Based Ink Droplet State Recognition for Continuous Inkjet Printing
The high-quality droplet formation in continuous inkjet printing (CIJ) is crucial for precise character deposition on product surfaces. This process, where a piezoelectric transducer perturbs a high-speed ink stream to generate micro-droplets, is highly sensitive to parameters like ink pressure and transducer amplitude. Suboptimal conditions lead to satellite droplet formation and charge transfer issues, adversely affecting print quality and necessitating reliable monitoring. Replacing inefficient manual inspection, this study develops MBSim-YOLO, a deep learning-based method for automated droplet detection. The proposed model enhances the YOLOv8 architecture by integrating MobileNetv3 to reduce computational complexity, a Bidirectional Feature Pyramid Network (BiFPN) for effective multi-scale feature fusion, and a Simple Attention Module (SimAM) to enhance feature representation robustness. A dataset was constructed using images captured by a CCD camera during the droplet ejection process. Experimental results demonstrate that MBSim-YOLO reduces the parameter count by 78.81% compared to the original YOLOv8. At an Intersection over Union (IoU) threshold of 0.5, the model achieved a precision of 98.2%, a recall of 99.1%, and a mean average precision (mAP) of 98.9%. These findings confirm that MBSim-YOLO achieves an optimal balance between high detection accuracy and lightweight performance, offering a viable and efficient solution for real-time, automated quality monitoring in industrial continuous inkjet printing applications.
- 9 December 2025
- Published by Springer Nature in Archives of Computational Methods in Engineering
- Vol. 33 (4) , 5503-5533
Multi-modal MPPT Control Strategy Under PSC in DC Microgrids: Review, Classification and Future Development Outlook
- 9 December 2025
- Published by Springer Nature in Archives of Computational Methods in Engineering
- Vol. 33 (4) , 5503-5533
Multi-modal MPPT Control Strategy Under PSC in DC Microgrids: Review, Classification and Future Development Outlook
- 24 October 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (10) , 102003
Progress on the application of deep learning in gearbox fault diagnosis
As a critical component in industrial machinery systems, gearboxes demand robust fault diagnosis solutions to ensure operational safety, energy efficiency, and sustainable manufacturing practices. Deep learning (DL) has emerged as a transformative approach for intelligent fault identification, demonstrating superior capabilities in processing complex vibration signatures compared to conventional methods. This review systematically examines DL applications in gearbox diagnostics through dual perspectives of theoretical foundations and industrial implementations. Six principal DL architectures are critically analyzed, including their advanced variants optimized for mechanical signal processing. The study systematically compares these architectures across diagnostic capabilities, computational demands, and implementation constraints. This review identifies promising research directions to address the current challenges in gearbox fault diagnosis. It aims to establish strategic research pathways that bridge the existing gap between theoretical models and industrial requirements, thereby enhancing the predictive maintenance framework for next-generation intelligent manufacturing systems.
- 24 October 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (10) , 102003
Progress on the application of deep learning in gearbox fault diagnosis
As a critical component in industrial machinery systems, gearboxes demand robust fault diagnosis solutions to ensure operational safety, energy efficiency, and sustainable manufacturing practices. Deep learning (DL) has emerged as a transformative approach for intelligent fault identification, demonstrating superior capabilities in processing complex vibration signatures compared to conventional methods. This review systematically examines DL applications in gearbox diagnostics through dual perspectives of theoretical foundations and industrial implementations. Six principal DL architectures are critically analyzed, including their advanced variants optimized for mechanical signal processing. The study systematically compares these architectures across diagnostic capabilities, computational demands, and implementation constraints. This review identifies promising research directions to address the current challenges in gearbox fault diagnosis. It aims to establish strategic research pathways that bridge the existing gap between theoretical models and industrial requirements, thereby enhancing the predictive maintenance framework for next-generation intelligent manufacturing systems.