Jingzong Yang
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
Jingzong Yang has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- Xuefeng Li
College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, China
16 shared publications - Mingyang Du
College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, China
11 shared publications - Chengjiang Zhou
School of Information Science and Technology, Yunnan Normal University, Kunming, China
8 shared publications Xuefeng Li
College of Automobile and Traffic Engineering Nanjing Forestry University Nanjing China
8 shared publications- Min Mao
Faculty of Information Engineering, Quzhou College of Technology, Quzhou 324000, China
6 shared publications - Dong Liu
Division of Computational Social Science, School of Humanities and Social Science The Chinese University of Hong Kong, Shenzhen China
4 shared publications
Latest Publications
- Open Access
- 5 June 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (11) , 5750
Exploring Continual Usage Intention of Shared Electric Bicycles: Empirical Evidence for Urban Sustainable Micro-Mobility
As a typical model of urban green and sustainable micro-transportation, shared electric bicycles play a crucial role in short and medium-distance travel as well as in connecting with public transportation. To respond to the national concept of low-carbon travel, this study takes users of urban shared electric bicycles in Kunming, Yunnan Province as the research sample and distributes questionnaires online through the Wenjuanxing platform to conduct an investigation into the factors influencing residents’ short-term and long-term continuance usage intention of shared electric bicycles. The results of the ordered logit model show that: at the level of personal attributes, the number of family-owned electric bicycles exerts a negative impact on residents’ short-term and long-term willingness to continue using shared electric bicycles. In terms of travel attributes, travel frequency has a positive impact on residents’ long-term continuance usage intention of shared electric bicycles, while exerting little influence on their short-term continuance usage intention. As for the original travel modes, groups with the habit of walking show a rejection of shared electric bicycles. From the perspective of attitudinal perceptions, independent variables reflecting instantaneity characteristics such as riding speed, unlocking speed and easy electric bicycle returning have a promoting effect on residents’ short-term continuance usage intention; independent variables reflecting sustainability characteristics such as good endurance capacity contribute to residents’ long-term continuance usage intention, while the overall travel comfort has a positive effect on the continuance usage intention across all time periods. Based on the model results, this paper puts forward policy recommendations from four aspects to promote urban residents’ continuance usage intention of shared electric bicycles.
- 5 June 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (11) , 5750
Open AccessExploring Continual Usage Intention of Shared Electric Bicycles: Empirical Evidence for Urban Sustainable Micro-Mobility
As a typical model of urban green and sustainable micro-transportation, shared electric bicycles play a crucial role in short and medium-distance travel as well as in connecting with public transportation. To respond to the national concept of low-carbon travel, this study takes users of urban shared electric bicycles in Kunming, Yunnan Province as the research sample and distributes questionnaires online through the Wenjuanxing platform to conduct an investigation into the factors influencing residents’ short-term and long-term continuance usage intention of shared electric bicycles. The results of the ordered logit model show that: at the level of personal attributes, the number of family-owned electric bicycles exerts a negative impact on residents’ short-term and long-term willingness to continue using shared electric bicycles. In terms of travel attributes, travel frequency has a positive impact on residents’ long-term continuance usage intention of shared electric bicycles, while exerting little influence on their short-term continuance usage intention. As for the original travel modes, groups with the habit of walking show a rejection of shared electric bicycles. From the perspective of attitudinal perceptions, independent variables reflecting instantaneity characteristics such as riding speed, unlocking speed and easy electric bicycle returning have a promoting effect on residents’ short-term continuance usage intention; independent variables reflecting sustainability characteristics such as good endurance capacity contribute to residents’ long-term continuance usage intention, while the overall travel comfort has a positive effect on the continuance usage intention across all time periods. Based on the model results, this paper puts forward policy recommendations from four aspects to promote urban residents’ continuance usage intention of shared electric bicycles.
- Open Access
An Adaptive Refined Composite Multiscale Differential Symbolic Entropy Rooted in LSC-SAO and Its Application in Fault Diagnosis
Accurate fault diagnosis of rotating machinery is critical for ensuring the reliability of the energy, industrial, and transportation sectors. However, conventional methods face significant challenges, including the susceptibility of the Snow Ablation Optimizer (SAO) to local optima, the instability of Multiscale Differential Symbolic Entropy (MDSE) with short time series, and the non-adaptability of Support Vector Machine parameters. To address these issues, this study proposes a parameter-adaptive fault diagnosis framework integrating an improved SAO with Adaptive Refined Composite Multiscale Differential Symbolic Entropy (Adaptive-RCMDSE). First, the Logistic Sine Cosine strategy (LSC) is introduced to enhance SAO’s global search capability, forming the LSC-SAO algorithm. Subsequently, an Adaptive-RCMDSE method is developed wherein LSC-SAO optimizes the control parameter to significantly improve feature stability for short time series. Furthermore, an Adaptive Support Vector Machine (Adaptive-SVM) model is constructed, employing LSC-SAO to automatically tune the penalty factor and kernel parameters for precise fault identification. Finally, validation is performed on gearbox, ball bearing, and axle box bearing datasets. Results indicate that the proposed method achieves superior diagnostic performance, with average accuracies of 99.70%, 99.29%, and 99.28%, respectively, outperforming existing methods. This work provides an effective and robust solution for intelligent health monitoring of rotating machinery.
Open AccessAn Adaptive Refined Composite Multiscale Differential Symbolic Entropy Rooted in LSC-SAO and Its Application in Fault Diagnosis
Accurate fault diagnosis of rotating machinery is critical for ensuring the reliability of the energy, industrial, and transportation sectors. However, conventional methods face significant challenges, including the susceptibility of the Snow Ablation Optimizer (SAO) to local optima, the instability of Multiscale Differential Symbolic Entropy (MDSE) with short time series, and the non-adaptability of Support Vector Machine parameters. To address these issues, this study proposes a parameter-adaptive fault diagnosis framework integrating an improved SAO with Adaptive Refined Composite Multiscale Differential Symbolic Entropy (Adaptive-RCMDSE). First, the Logistic Sine Cosine strategy (LSC) is introduced to enhance SAO’s global search capability, forming the LSC-SAO algorithm. Subsequently, an Adaptive-RCMDSE method is developed wherein LSC-SAO optimizes the control parameter to significantly improve feature stability for short time series. Furthermore, an Adaptive Support Vector Machine (Adaptive-SVM) model is constructed, employing LSC-SAO to automatically tune the penalty factor and kernel parameters for precise fault identification. Finally, validation is performed on gearbox, ball bearing, and axle box bearing datasets. Results indicate that the proposed method achieves superior diagnostic performance, with average accuracies of 99.70%, 99.29%, and 99.28%, respectively, outperforming existing methods. This work provides an effective and robust solution for intelligent health monitoring of rotating machinery.
- Open Access
- 21 April 2026
- Published by MDPI AG in World Electric Vehicle Journal
- Vol. 17 (4) , 221
Acceptance of Electric Vehicles in the Ride-Hailing Scenario of Third-Tier Cities: A Comparative Study of Full-Time and Part-Time Drivers in China
Driven by the global agenda of low-carbon urban development, local governments in China have implemented targeted policies requiring new energy vehicle adoption in the ride-hailing industry. This study focuses on a key issue in the development of sustainable smart public transportation systems: the factors affecting the acceptance of electric vehicles (EVs) in ride-hailing services among full-time and part-time drivers. Using 432 valid samples of ride-hailing drivers from Zhangzhou, a third-tier city in China, we compared the basic personal attributes of full-time and part-time drivers. Ordered logit models were developed to explore differences in factors influencing their acceptance of electric ride hailing (ER). Findings reveal: (1) Drivers’ perceived significance of EVs in green transportation is positively associated with their acceptance of ER. (2) Endurance mileage and charging efficiency have no significant effect on acceptance among drivers in underdeveloped cities. (3) Full-time drivers exhibit relatively low concern for subsidy policies, whereas part-time drivers express a pressing need for vehicle purchase subsidies and operational subsidies. (4) Overall, part-time drivers demonstrate higher acceptance of ER than full-time drivers. Based on these findings, this paper offers policy recommendations for governments to enhance ER acceptance among both driver groups. It is important to note that the present study utilizes survey data collected from Zhangzhou. The research conclusions should be treated with caution when applied to other cities, and further studies can be conducted in different regions to verify the results.
- 21 April 2026
- Published by MDPI AG in World Electric Vehicle Journal
- Vol. 17 (4) , 221
Open AccessAcceptance of Electric Vehicles in the Ride-Hailing Scenario of Third-Tier Cities: A Comparative Study of Full-Time and Part-Time Drivers in China
Driven by the global agenda of low-carbon urban development, local governments in China have implemented targeted policies requiring new energy vehicle adoption in the ride-hailing industry. This study focuses on a key issue in the development of sustainable smart public transportation systems: the factors affecting the acceptance of electric vehicles (EVs) in ride-hailing services among full-time and part-time drivers. Using 432 valid samples of ride-hailing drivers from Zhangzhou, a third-tier city in China, we compared the basic personal attributes of full-time and part-time drivers. Ordered logit models were developed to explore differences in factors influencing their acceptance of electric ride hailing (ER). Findings reveal: (1) Drivers’ perceived significance of EVs in green transportation is positively associated with their acceptance of ER. (2) Endurance mileage and charging efficiency have no significant effect on acceptance among drivers in underdeveloped cities. (3) Full-time drivers exhibit relatively low concern for subsidy policies, whereas part-time drivers express a pressing need for vehicle purchase subsidies and operational subsidies. (4) Overall, part-time drivers demonstrate higher acceptance of ER than full-time drivers. Based on these findings, this paper offers policy recommendations for governments to enhance ER acceptance among both driver groups. It is important to note that the present study utilizes survey data collected from Zhangzhou. The research conclusions should be treated with caution when applied to other cities, and further studies can be conducted in different regions to verify the results.
- Open Access
- 22 March 2026
- Published by MDPI AG in World Electric Vehicle Journal
- Vol. 17 (3) , 160
Determinants of Food Delivery Riders’ Continued Use Intention of E-Bikes Under New Policy Regulations
The implementation of the new national electric bike (e-bike) standard has imposed stringent compliance requirements on equipment and e-bikes in the instant delivery sector, which directly affects the delivery efficiency and the work adaptability of food delivery riders. This study aims to investigate food delivery riders’ continued usage intention of e-bikes under China’s new e-bike regulation. Based on valid data collected from food delivery riders in Nanjing, this study employs ordered logit regression to examine the primary factors influencing their continued usage intention of e-bikes. The findings reveal that: (1) Male riders’ willingness to continue using e-bikes is comparatively lower, whereas older riders show a stronger intention. (2) Food delivery riders with higher incomes and those who need to replace their e-bikes show a stronger inclination to continue using them. (3) Limited e-bike options have a significant negative effect on riders’ continued usage intention, while speed limits exert no significant influence. Based on these empirical findings, corresponding policy recommendations are proposed to promote riders’ continued use of e-bikes, such as developing age-friendly delivery models, establishing an income guarantee mechanism for riders, and optimizing platform delivery time allocation. The findings could provide a theoretical basis and practical insights for policymakers and food delivery platforms to improve e-bike management policies.
- 22 March 2026
- Published by MDPI AG in World Electric Vehicle Journal
- Vol. 17 (3) , 160
Open AccessDeterminants of Food Delivery Riders’ Continued Use Intention of E-Bikes Under New Policy Regulations
The implementation of the new national electric bike (e-bike) standard has imposed stringent compliance requirements on equipment and e-bikes in the instant delivery sector, which directly affects the delivery efficiency and the work adaptability of food delivery riders. This study aims to investigate food delivery riders’ continued usage intention of e-bikes under China’s new e-bike regulation. Based on valid data collected from food delivery riders in Nanjing, this study employs ordered logit regression to examine the primary factors influencing their continued usage intention of e-bikes. The findings reveal that: (1) Male riders’ willingness to continue using e-bikes is comparatively lower, whereas older riders show a stronger intention. (2) Food delivery riders with higher incomes and those who need to replace their e-bikes show a stronger inclination to continue using them. (3) Limited e-bike options have a significant negative effect on riders’ continued usage intention, while speed limits exert no significant influence. Based on these empirical findings, corresponding policy recommendations are proposed to promote riders’ continued use of e-bikes, such as developing age-friendly delivery models, establishing an income guarantee mechanism for riders, and optimizing platform delivery time allocation. The findings could provide a theoretical basis and practical insights for policymakers and food delivery platforms to improve e-bike management policies.
- Open Access
- 16 March 2026
- Published by MDPI AG in Fractal and Fractional
- Vol. 10 (3) , 195
Research on Improved Transformer Fault Diagnosis Method Driven by IBKA-VMD and Hierarchical Fractional Order Attention Entropy Synergy
Rolling bearing faults are the primary cause of rotating machinery failure. Under complex operating conditions, the weak fault impact signals are easily overwhelmed by strong noise and exhibit significant non-stationary characteristics, posing severe challenges to accurate diagnosis. To address this, this paper proposes an improved Transformer-based fault diagnosis method driven by the improved black-winged kite algorithm-variational mode decomposition (IBKA-VMD) and hierarchical fractional-order attention entropy (HFrAttE). The method employs the integrated multi-strategy IBKA to adaptively determine the optimal parameters of VMD, utilizes HFrAttE to construct highly discriminative feature sets, and further builds an improved Transformer model integrating bidirectional attention mechanisms and feature decoupling structures for deep feature mining. The classification decision is finalized by the twin extreme learning machine (TELM). Experimental results on the case western reserve university (CWRU) bearing dataset under different noise environments (−2 dB, −5 dB) demonstrate that the proposed method maintains 100% accuracy, recall, and F1-score under −5 dB noise interference, significantly outperforming comparative models. It exhibits excellent anti-noise performance and feature extraction capability, providing an efficient solution for intelligent operation and maintenance of rotating machinery under complex operating conditions.
- 16 March 2026
- Published by MDPI AG in Fractal and Fractional
- Vol. 10 (3) , 195
Open AccessResearch on Improved Transformer Fault Diagnosis Method Driven by IBKA-VMD and Hierarchical Fractional Order Attention Entropy Synergy
Rolling bearing faults are the primary cause of rotating machinery failure. Under complex operating conditions, the weak fault impact signals are easily overwhelmed by strong noise and exhibit significant non-stationary characteristics, posing severe challenges to accurate diagnosis. To address this, this paper proposes an improved Transformer-based fault diagnosis method driven by the improved black-winged kite algorithm-variational mode decomposition (IBKA-VMD) and hierarchical fractional-order attention entropy (HFrAttE). The method employs the integrated multi-strategy IBKA to adaptively determine the optimal parameters of VMD, utilizes HFrAttE to construct highly discriminative feature sets, and further builds an improved Transformer model integrating bidirectional attention mechanisms and feature decoupling structures for deep feature mining. The classification decision is finalized by the twin extreme learning machine (TELM). Experimental results on the case western reserve university (CWRU) bearing dataset under different noise environments (−2 dB, −5 dB) demonstrate that the proposed method maintains 100% accuracy, recall, and F1-score under −5 dB noise interference, significantly outperforming comparative models. It exhibits excellent anti-noise performance and feature extraction capability, providing an efficient solution for intelligent operation and maintenance of rotating machinery under complex operating conditions.
- Open Access
- 19 November 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (22) , 10361
Factors Influencing Urban Residents’ Continued Usage Intention of Electric Bikes Under the New National Standards
Electric bikes (E-bikes), recognized as a convenient and sustainable mode of transportation, have gained widespread adoption among urban residents. In order to regulate the e-bike industry, China introduced the “Safety Technical Standards for E-bikes” (GB17761-2024), which officially came into effect on 1 September 2025. This study examines residents’ usage behavior and their continued usage intention for e-bikes following the implementation of the new national standards. Using valid data collected from respondents, the ordered logit model is established to analyze the key factors and the mechanisms influencing the continued usage behavior of e-bikes. The results indicate that: (1) A monthly income of 3500–5000 CNY significantly positively influences the continued intention to use electric bikes for both the general population and the courier/food delivery person. (2) Satisfaction with current e-bike usage positively influences the continued usage intention for both the general population and delivery personnel. (3) An increase in usage costs negatively impacts the intention to continue using electric bikes; the reduced bike speed significantly reduces the continued usage intention among delivery persons. The extended battery life does not significantly influence the continued usage intention. Based on the model results, several policy recommendations are proposed to enhance the continued usage intention of e-bikes among residents. The findings could provide theoretical insights and practical suggestions for urban transportation policy optimization and the planning of non-motorized transport systems.
- 19 November 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (22) , 10361
Open AccessFactors Influencing Urban Residents’ Continued Usage Intention of Electric Bikes Under the New National Standards
Electric bikes (E-bikes), recognized as a convenient and sustainable mode of transportation, have gained widespread adoption among urban residents. In order to regulate the e-bike industry, China introduced the “Safety Technical Standards for E-bikes” (GB17761-2024), which officially came into effect on 1 September 2025. This study examines residents’ usage behavior and their continued usage intention for e-bikes following the implementation of the new national standards. Using valid data collected from respondents, the ordered logit model is established to analyze the key factors and the mechanisms influencing the continued usage behavior of e-bikes. The results indicate that: (1) A monthly income of 3500–5000 CNY significantly positively influences the continued intention to use electric bikes for both the general population and the courier/food delivery person. (2) Satisfaction with current e-bike usage positively influences the continued usage intention for both the general population and delivery personnel. (3) An increase in usage costs negatively impacts the intention to continue using electric bikes; the reduced bike speed significantly reduces the continued usage intention among delivery persons. The extended battery life does not significantly influence the continued usage intention. Based on the model results, several policy recommendations are proposed to enhance the continued usage intention of e-bikes among residents. The findings could provide theoretical insights and practical suggestions for urban transportation policy optimization and the planning of non-motorized transport systems.
- Open Access
- 8 September 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (17) , 8077
Driving Sustainable Mobility: Adoption and the Willingness to Participate in Electric Ride-Hailing Service Among Driver Groups in Less-Developed Cities
The decarbonization of urban transport is critical for achieving sustainable development goals, and the electrification of ride-hailing services offers one promising pathway. However, the acceptance of electric ride-hailing services (ERHS) in less-developed cities lags behind that in developed regions, and existing research lacks a systematic analysis. This study fills the gap by conducting a survey in Zhangzhou, China, and employing ordered and binary logit models to analyze the factors influencing the acceptance of ERHS and the willingness to participate in this sustainable program by drivers and potential drivers. The findings indicate the following: (1) For drivers, environmental awareness is an important driving factor for accepting ERHS. Drivers who worry about the potential health effects of EV radiation are less willing to adopt ERHS. Part-time drivers and those who receive operational subsidies are more likely to adopt ERHS. (2) Among potential drivers, males, individuals aged 36 to 45, and those who are insensitive to fuel price fluctuations show a lower willingness to adopt ERHS. Conversely, the perceived fairness of the commission rates of the platform, driving range, and driving experience significantly promote the acceptance. (3) For potential drivers, the willingness to participate in ERHS is significantly affected by recycling subsidies, education level, and the currently driven vehicle type. The results could provide a policy blueprint for accelerating the green transformation of the ride-hailing industry, and could also provide policymakers with the empirical evidence needed for differentiated intervention measures to promote sustainable and low-carbon urban transportation.
- 8 September 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (17) , 8077
Open AccessDriving Sustainable Mobility: Adoption and the Willingness to Participate in Electric Ride-Hailing Service Among Driver Groups in Less-Developed Cities
The decarbonization of urban transport is critical for achieving sustainable development goals, and the electrification of ride-hailing services offers one promising pathway. However, the acceptance of electric ride-hailing services (ERHS) in less-developed cities lags behind that in developed regions, and existing research lacks a systematic analysis. This study fills the gap by conducting a survey in Zhangzhou, China, and employing ordered and binary logit models to analyze the factors influencing the acceptance of ERHS and the willingness to participate in this sustainable program by drivers and potential drivers. The findings indicate the following: (1) For drivers, environmental awareness is an important driving factor for accepting ERHS. Drivers who worry about the potential health effects of EV radiation are less willing to adopt ERHS. Part-time drivers and those who receive operational subsidies are more likely to adopt ERHS. (2) Among potential drivers, males, individuals aged 36 to 45, and those who are insensitive to fuel price fluctuations show a lower willingness to adopt ERHS. Conversely, the perceived fairness of the commission rates of the platform, driving range, and driving experience significantly promote the acceptance. (3) For potential drivers, the willingness to participate in ERHS is significantly affected by recycling subsidies, education level, and the currently driven vehicle type. The results could provide a policy blueprint for accelerating the green transformation of the ride-hailing industry, and could also provide policymakers with the empirical evidence needed for differentiated intervention measures to promote sustainable and low-carbon urban transportation.
- Open Access
- 1 September 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (17) , 7869
Factors Influencing the Acceptance of Electric Ride-Hailing Vehicles and Market-Exit Decisions Among Drivers in Underdeveloped Cities
This study investigates the factors influencing electric ride-hailing vehicle (ERV) adoption and market exit among ride-hailing drivers in underdeveloped cities, aiming to enhance industry operational efficiency and workforce stability. Using survey data from 630 drivers in Zhangzhou, Fujian Province, China, we employ statistical modeling to analyze heterogeneous mechanisms behind ERV acceptance and market-exit behavior. The results indicate that: (1) Drivers’ environmental awareness and positive attitudes toward new energy vehicle development significantly increase ERV adoption willingness, though weak policy implementation and misconceptions about electric vehicle technology are associated with these incentives. Unlike in developed regions, range anxiety is not a significant barrier in underdeveloped cities with limited operational ranges. (2) Concerning market-exit behavior, job intensity exhibits a U-shaped relationship with exit risk, while platform income redistribution adjustments emerge as a key external factor. Notably, local full-time drivers show a marked lag in technology adoption. The findings offer valuable insights for optimizing policies and promoting sustainable development in the ride-hailing industry in underdeveloped cities, providing practical guidance for policymakers and companies in shaping tailored industry regulations and operational strategies.
- 1 September 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (17) , 7869
Open AccessFactors Influencing the Acceptance of Electric Ride-Hailing Vehicles and Market-Exit Decisions Among Drivers in Underdeveloped Cities
This study investigates the factors influencing electric ride-hailing vehicle (ERV) adoption and market exit among ride-hailing drivers in underdeveloped cities, aiming to enhance industry operational efficiency and workforce stability. Using survey data from 630 drivers in Zhangzhou, Fujian Province, China, we employ statistical modeling to analyze heterogeneous mechanisms behind ERV acceptance and market-exit behavior. The results indicate that: (1) Drivers’ environmental awareness and positive attitudes toward new energy vehicle development significantly increase ERV adoption willingness, though weak policy implementation and misconceptions about electric vehicle technology are associated with these incentives. Unlike in developed regions, range anxiety is not a significant barrier in underdeveloped cities with limited operational ranges. (2) Concerning market-exit behavior, job intensity exhibits a U-shaped relationship with exit risk, while platform income redistribution adjustments emerge as a key external factor. Notably, local full-time drivers show a marked lag in technology adoption. The findings offer valuable insights for optimizing policies and promoting sustainable development in the ride-hailing industry in underdeveloped cities, providing practical guidance for policymakers and companies in shaping tailored industry regulations and operational strategies.
- Open Access
An Integrated Mechanical Fault Diagnosis Framework Using Improved GOOSE-VMD, RobustICA, and CYCBD
Rolling element bearings serve as critical transmission components in industrial automation systems, yet their fault signatures are susceptible to interference from strong background noise, complex operating conditions, and nonlinear impact characteristics. Addressing the limitations of conventional methods in adaptive parameter optimization and weak feature enhancement, this paper proposes an innovative diagnostic framework integrating Improved Goose optimized Variational Mode Decomposition (IGOOSE-VMD), RobustICA, and CYCBD. First, to mitigate modal aliasing issues caused by empirical parameter dependency in VMD, we fuse a refraction-guided reverse learning mechanism with a dynamic mutation strategy to develop the IGOOSE. By employing an energy-feature-driven fitness function, this approach achieves synergistic optimization of the mode number and penalty factor. Subsequently, a multi-channel observation model is constructed based on optimal component selection. Noise interference is suppressed through the robust separation capabilities of RobustICA, while CYCBD introduces cyclostationarity-based prior constraints to formulate a blind deconvolution operator with periodic impact enhancement properties. This significantly improves the temporal sparsity of fault-induced impact components. Experimental results demonstrate that, compared to traditional time–frequency analysis techniques (e.g., EMD, EEMD, LMD, ITD) and deconvolution methods (including MCKD, MED, OMEDA), the proposed approach exhibits superior noise immunity and higher fault feature extraction accuracy under high background noise conditions.
Open AccessAn Integrated Mechanical Fault Diagnosis Framework Using Improved GOOSE-VMD, RobustICA, and CYCBD
Rolling element bearings serve as critical transmission components in industrial automation systems, yet their fault signatures are susceptible to interference from strong background noise, complex operating conditions, and nonlinear impact characteristics. Addressing the limitations of conventional methods in adaptive parameter optimization and weak feature enhancement, this paper proposes an innovative diagnostic framework integrating Improved Goose optimized Variational Mode Decomposition (IGOOSE-VMD), RobustICA, and CYCBD. First, to mitigate modal aliasing issues caused by empirical parameter dependency in VMD, we fuse a refraction-guided reverse learning mechanism with a dynamic mutation strategy to develop the IGOOSE. By employing an energy-feature-driven fitness function, this approach achieves synergistic optimization of the mode number and penalty factor. Subsequently, a multi-channel observation model is constructed based on optimal component selection. Noise interference is suppressed through the robust separation capabilities of RobustICA, while CYCBD introduces cyclostationarity-based prior constraints to formulate a blind deconvolution operator with periodic impact enhancement properties. This significantly improves the temporal sparsity of fault-induced impact components. Experimental results demonstrate that, compared to traditional time–frequency analysis techniques (e.g., EMD, EEMD, LMD, ITD) and deconvolution methods (including MCKD, MED, OMEDA), the proposed approach exhibits superior noise immunity and higher fault feature extraction accuracy under high background noise conditions.
- Open Access
- 31 March 2025
- Published by MDPI AG in Lubricants
- Vol. 13 (4) , 155
Enhancing Fault Diagnosis: A Hybrid Framework Integrating Improved SABO with VMD and Transformer–TELM
Rolling bearings, as core components in mechanical systems, directly influence the overall reliability of equipment. However, continuous operation under complex working conditions can easily lead to gradual performance degradation and sudden faults, which not only result in equipment failure but may also trigger a cascading failure effect, significantly amplifying downtime losses. To address this challenge, this study proposes an intelligent diagnostic method that integrates variational mode decomposition (VMD) optimized by the improved subtraction-average-based optimizer (ISABO) with transformer–twin extreme learning machine (Transformer–TELM) ensemble technology. Firstly, ISABO is employed to finely optimize the initialization parameters of VMD. With the improved initialization strategy and particle position update method, the optimal parameter combination can be precisely identified. Subsequently, the optimized parameters are used to model and decompose the signal through VMD, and the optimal signal components are selected through a constructed two-dimensional evaluation system. Furthermore, diversified time-domain features are extracted from these components to form an initial feature set. To deeply mine feature information, a multi-layer Transformer model is introduced to refine more discriminative feature representations. Finally, these features are input into the constructed TELM fault diagnosis model to achieve precise diagnosis of rolling bearing faults. The experimental results demonstrate that this method exhibits excellent performance in terms of noise resistance, accurate fault feature capture, and fault classification. Compared with traditional machine learning techniques such as kernel extreme learning machine (KELM), extreme learning machine (ELM), support vector machine (SVM), and Softmax, this method significantly outperforms other models in terms of accuracy, recall, and F1 score.
- 31 March 2025
- Published by MDPI AG in Lubricants
- Vol. 13 (4) , 155
Open AccessEnhancing Fault Diagnosis: A Hybrid Framework Integrating Improved SABO with VMD and Transformer–TELM
Rolling bearings, as core components in mechanical systems, directly influence the overall reliability of equipment. However, continuous operation under complex working conditions can easily lead to gradual performance degradation and sudden faults, which not only result in equipment failure but may also trigger a cascading failure effect, significantly amplifying downtime losses. To address this challenge, this study proposes an intelligent diagnostic method that integrates variational mode decomposition (VMD) optimized by the improved subtraction-average-based optimizer (ISABO) with transformer–twin extreme learning machine (Transformer–TELM) ensemble technology. Firstly, ISABO is employed to finely optimize the initialization parameters of VMD. With the improved initialization strategy and particle position update method, the optimal parameter combination can be precisely identified. Subsequently, the optimized parameters are used to model and decompose the signal through VMD, and the optimal signal components are selected through a constructed two-dimensional evaluation system. Furthermore, diversified time-domain features are extracted from these components to form an initial feature set. To deeply mine feature information, a multi-layer Transformer model is introduced to refine more discriminative feature representations. Finally, these features are input into the constructed TELM fault diagnosis model to achieve precise diagnosis of rolling bearing faults. The experimental results demonstrate that this method exhibits excellent performance in terms of noise resistance, accurate fault feature capture, and fault classification. Compared with traditional machine learning techniques such as kernel extreme learning machine (KELM), extreme learning machine (ELM), support vector machine (SVM), and Softmax, this method significantly outperforms other models in terms of accuracy, recall, and F1 score.