Hongbo Ma
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
Hongbo Ma has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Gaige Chen
School of Automation, Xi’an University of Posts and Telecommunications, Xi’an, China
4 shared publications - Xianzhi Wang
School of Automation, Xi’an University of Posts and Telecommunications, Xi’an 710121, China
4 shared publications - Guowei Zhang
College of Mechanical and Electrical Engineering, Xidian University, Xian, China
3 shared publications - Xianguang Kong
College of Mechanical and Electrical Engineering, Xidian University, Xian, China
3 shared publications - Fei Jia
Xidian University
2 shared publications - Jingli Du
Tuberculosis Control Team, Senior Department of Tuberculosis, The Eighth Medical Center of PLA General Hospital, Beijing, China
2 shared publications
Latest Publications
- 15 May 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (20) , 206107
Dual-knowledge collaborative mechanism for multi-source-free domain adaptation in rotating machinery fault diagnosis
Source-free domain adaptation (SFDA) has gained increasing attention in the field of AI-driven intelligent machinery fault diagnosis, as it addresses scenarios where original source data is unavailable due to privacy constraints. Despite its potential, SFDA within artificial intelligence–based diagnostic frameworks still encounters two key challenges: (1) in real-world industrial applications, multiple working conditions often coexist, leading to complex relationships between target and multiple implicit source domains. (2) In SFDA, where pseudo-labeling is essential to exploit unlabeled target data, most methods depend solely on data structure and overlook model features. To address these issues, this paper proposes a dual-knowledge collaborative mechanism for multi-source SFDA in rotating machinery fault diagnosis. The proposed method first employs entropy maximization with dynamic multi-source fusion to integrate transferable patterns across diverse source domains, enhancing cross-adaption. Then, a dual-knowledge collaboration strategy is designed to jointly leverage source-domain model feature knowledge and target-domain structural cues for confidence-guided pseudo-labeling, which improves label reliability. Furthermore, a relation-consistency module is introduced to enforce semantic alignment and alleviate conflicts between domains. Extensive experiments on two benchmark datasets demonstrate that the proposed approach achieves consistently higher diagnostic accuracy, faster adaptation, and improved robustness against distribution shifts compared with existing SFDA methods.
- 15 May 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (20) , 206107
Dual-knowledge collaborative mechanism for multi-source-free domain adaptation in rotating machinery fault diagnosis
Source-free domain adaptation (SFDA) has gained increasing attention in the field of AI-driven intelligent machinery fault diagnosis, as it addresses scenarios where original source data is unavailable due to privacy constraints. Despite its potential, SFDA within artificial intelligence–based diagnostic frameworks still encounters two key challenges: (1) in real-world industrial applications, multiple working conditions often coexist, leading to complex relationships between target and multiple implicit source domains. (2) In SFDA, where pseudo-labeling is essential to exploit unlabeled target data, most methods depend solely on data structure and overlook model features. To address these issues, this paper proposes a dual-knowledge collaborative mechanism for multi-source SFDA in rotating machinery fault diagnosis. The proposed method first employs entropy maximization with dynamic multi-source fusion to integrate transferable patterns across diverse source domains, enhancing cross-adaption. Then, a dual-knowledge collaboration strategy is designed to jointly leverage source-domain model feature knowledge and target-domain structural cues for confidence-guided pseudo-labeling, which improves label reliability. Furthermore, a relation-consistency module is introduced to enforce semantic alignment and alleviate conflicts between domains. Extensive experiments on two benchmark datasets demonstrate that the proposed approach achieves consistently higher diagnostic accuracy, faster adaptation, and improved robustness against distribution shifts compared with existing SFDA methods.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (10) , 7923-7934
Balancing Discrepancy and Consistency: Adversarial Single Domain Generalization in Fault Diagnosis
Single-domain generalization (SDG) in fault diagnosis aims to train a model that generalizes to unseen conditions using data from a single operating condition. Despite its promise, SDG faces significant challenges. Recent methods focus on generating new domain features to expand data distribution and extract domain-invariant features, but they encounter three issues: 1) separating domain expansion from domain-invariant feature learning limits their synergy and generalization; 2) domain expansion often uses random or inconsistent enhancement directions, introducing noise or generating unreliable features; and 3) domain-invariant feature extraction methods emphasize global or class-level alignment, neglecting the optimization of their relationships. Therefore, an SDG fault diagnosis framework based on the adversarial interaction between discrepancy and consistency is proposed, where adversarial training is repeatedly applied to dynamically balance domain discrepancy and consistency to avoid single-direction bias. Specifically, a learnable statistical feature perturbation module for domain discrepancy perception is proposed, which purposefully guides the model to learn statistical perturbations that effectively characterize domain discrepancies, thereby increasing the reliability of domain extension. In addition, covariance alignment and semantic alignment strategies are proposed to maintain global and category consistency between original and perturbed features. Covariance alignment is employed to mitigate stylistic variations introduced by perturbed features while preserving mission-critical diagnostic information, and explicit semantic constraints are utilized to further promote consistency in the model’s prediction results. Finally, extensive experiments are carried out on five datasets to verify the effectiveness of the proposed method.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (10) , 7923-7934
Balancing Discrepancy and Consistency: Adversarial Single Domain Generalization in Fault Diagnosis
Single-domain generalization (SDG) in fault diagnosis aims to train a model that generalizes to unseen conditions using data from a single operating condition. Despite its promise, SDG faces significant challenges. Recent methods focus on generating new domain features to expand data distribution and extract domain-invariant features, but they encounter three issues: 1) separating domain expansion from domain-invariant feature learning limits their synergy and generalization; 2) domain expansion often uses random or inconsistent enhancement directions, introducing noise or generating unreliable features; and 3) domain-invariant feature extraction methods emphasize global or class-level alignment, neglecting the optimization of their relationships. Therefore, an SDG fault diagnosis framework based on the adversarial interaction between discrepancy and consistency is proposed, where adversarial training is repeatedly applied to dynamically balance domain discrepancy and consistency to avoid single-direction bias. Specifically, a learnable statistical feature perturbation module for domain discrepancy perception is proposed, which purposefully guides the model to learn statistical perturbations that effectively characterize domain discrepancies, thereby increasing the reliability of domain extension. In addition, covariance alignment and semantic alignment strategies are proposed to maintain global and category consistency between original and perturbed features. Covariance alignment is employed to mitigate stylistic variations introduced by perturbed features while preserving mission-critical diagnostic information, and explicit semantic constraints are utilized to further promote consistency in the model’s prediction results. Finally, extensive experiments are carried out on five datasets to verify the effectiveness of the proposed method.
- 14 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (13) , 23297-23308
Federated Domain Generalization for Fault Diagnosis: Cross-Client Style Integration and Dual Alignment Representation
Federated learning (FL) enables the collaborative training of intelligent diagnostic models across multiple clients while preserving data privacy. However, the complex and dynamic working conditions often cause federated diagnostic models to suffer from performance degradation when applied to unseen clients, exposing deficiencies in model generalization. Domain generalization fault diagnosis methods aim to enhance model adaptability under unknown working conditions, but most existing algorithms rely on shared data, making them unsuitable for direct application in federated learning environments. To address this challenge, we propose a federated domain generalization fault diagnosis method based on Cross-Client Style Integration and Dual Alignment representation (CCSIDA). This method significantly enhances model generalization in FL settings while ensuring data privacy. Specifically, CCSIDA integrates three key strategies: cross-client style data enhancement, domain-sensitive feature suppression, and predictive alignment. For cross-client style integration, we design a stochastic mixed-style sample generation module to overcome the limitations of conventional domain generalization data enhancement methods in FL. This module generates diverse samples by constructing a shared style repository, enabling inter-client style information transfer. For cross-client dual alignment representation, we introduce a domain-sensitive feature suppression strategy to reduce domain discrepancies between original and enhanced samples. Additionally, Jensen-Shannon divergence is employed to ensure prediction consistency between these samples. Finally, extensive experiments on five benchmark datasets validate the effectiveness of the proposed method.
- 14 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (13) , 23297-23308
Federated Domain Generalization for Fault Diagnosis: Cross-Client Style Integration and Dual Alignment Representation
Federated learning (FL) enables the collaborative training of intelligent diagnostic models across multiple clients while preserving data privacy. However, the complex and dynamic working conditions often cause federated diagnostic models to suffer from performance degradation when applied to unseen clients, exposing deficiencies in model generalization. Domain generalization fault diagnosis methods aim to enhance model adaptability under unknown working conditions, but most existing algorithms rely on shared data, making them unsuitable for direct application in federated learning environments. To address this challenge, we propose a federated domain generalization fault diagnosis method based on Cross-Client Style Integration and Dual Alignment representation (CCSIDA). This method significantly enhances model generalization in FL settings while ensuring data privacy. Specifically, CCSIDA integrates three key strategies: cross-client style data enhancement, domain-sensitive feature suppression, and predictive alignment. For cross-client style integration, we design a stochastic mixed-style sample generation module to overcome the limitations of conventional domain generalization data enhancement methods in FL. This module generates diverse samples by constructing a shared style repository, enabling inter-client style information transfer. For cross-client dual alignment representation, we introduce a domain-sensitive feature suppression strategy to reduce domain discrepancies between original and enhanced samples. Additionally, Jensen-Shannon divergence is employed to ensure prediction consistency between these samples. Finally, extensive experiments on five benchmark datasets validate the effectiveness of the proposed method.
- 7 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (22) , 37531-37543
A Remaining Useful Life Prediction Method for Insulated-Gate Bipolar Transistor Based on Deep Fusion of Nonlinear Features From Multisource Data
Insulated Gate Bipolar Transistor (IGBT) has multiple degradation mechanisms, it is challenge to accurately integrating multiple signals to capture the device’s degradation patterns and health state. Therefore, comprehensively characterizing the health state of IGBT and predicting its remaining useful life using multiple signals poses a significant challenge. To address this challenge, a remaining useful life prediction method for IGBT based on deep fusion of nonlinear features from multi-source data is proposed. Firstly, the time-domain multi-features of IGBT degradation data are constructed and key features are selectively selected, then dimensionality reduction is performed and these features are fused into health indicators to characterize the health level. Secondly, the health of IGBT is effectively evaluated by unsupervised clustering without data labeling. Thirdly, end-condition monitoring is refined to enable the identification of near-failure state. Finally, deep learning is utilized to provide accurate and reliable prediction of the remaining useful life of IGBT devices (R2 are all greater than 0.98, the MAE are all less than 2.3, and the RMSE are all less than 5.5.). The results demonstrate that the method effectively integrates multi-source information, characterizes the health state of the device, and can more accurately and reliably predict the remaining useful life of IGBT. The proposed method can enhance the scientific basis for the health management of new energy systems such as wind power and photovoltaic systems.
- 7 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (22) , 37531-37543
A Remaining Useful Life Prediction Method for Insulated-Gate Bipolar Transistor Based on Deep Fusion of Nonlinear Features From Multisource Data
Insulated Gate Bipolar Transistor (IGBT) has multiple degradation mechanisms, it is challenge to accurately integrating multiple signals to capture the device’s degradation patterns and health state. Therefore, comprehensively characterizing the health state of IGBT and predicting its remaining useful life using multiple signals poses a significant challenge. To address this challenge, a remaining useful life prediction method for IGBT based on deep fusion of nonlinear features from multi-source data is proposed. Firstly, the time-domain multi-features of IGBT degradation data are constructed and key features are selectively selected, then dimensionality reduction is performed and these features are fused into health indicators to characterize the health level. Secondly, the health of IGBT is effectively evaluated by unsupervised clustering without data labeling. Thirdly, end-condition monitoring is refined to enable the identification of near-failure state. Finally, deep learning is utilized to provide accurate and reliable prediction of the remaining useful life of IGBT devices (R2 are all greater than 0.98, the MAE are all less than 2.3, and the RMSE are all less than 5.5.). The results demonstrate that the method effectively integrates multi-source information, characterizes the health state of the device, and can more accurately and reliably predict the remaining useful life of IGBT. The proposed method can enhance the scientific basis for the health management of new energy systems such as wind power and photovoltaic systems.
- 1 October 2024
- Published by IOP Publishing in Engineering Research Express
- Vol. 6 (4) , 045401
Remaining useful life prediction method for cross- condition tools based on parallel fusion
The current tool remaining useful life (RUL) prediction models do not fully consider the importance of signals from different sensors and the differences in working conditions, which leads to a decline in the model’s robust performance under new conditions. This paper introduces a novel cross-condition RUL prediction approach that integrates parallel fusion, transfer learning, and deep learning. Considering the characteristics of different data sources, correlated signals are initially selected using correlation analysis and dynamic time warping (DTW). Subsequently, multi-scale Depthwise Separable Convolution and multi-attention mechanisms are combined to capture the importance of features at various scales. Finally, a dynamic domain adaptation technique is employed to adjust the importance weights of conditional distribution discrepancy and marginal distribution discrepancy, enabling the model to adapt to cross-condition scenarios.
- 1 October 2024
- Published by IOP Publishing in Engineering Research Express
- Vol. 6 (4) , 045401
Remaining useful life prediction method for cross- condition tools based on parallel fusion
The current tool remaining useful life (RUL) prediction models do not fully consider the importance of signals from different sensors and the differences in working conditions, which leads to a decline in the model’s robust performance under new conditions. This paper introduces a novel cross-condition RUL prediction approach that integrates parallel fusion, transfer learning, and deep learning. Considering the characteristics of different data sources, correlated signals are initially selected using correlation analysis and dynamic time warping (DTW). Subsequently, multi-scale Depthwise Separable Convolution and multi-attention mechanisms are combined to capture the importance of features at various scales. Finally, a dynamic domain adaptation technique is employed to adjust the importance weights of conditional distribution discrepancy and marginal distribution discrepancy, enabling the model to adapt to cross-condition scenarios.
- Open Access
- 27 September 2024
- Published by SAGE Publications in Advances in Mechanical Engineering
- Vol. 16 (9)
Lightweight intelligent fault diagnosis method based on a multi-stage pruning distillation interleaving network
Edge computing, a key technology in the Internet of Things, can help integrate real-time fault diagnosis into industrial applications. Lightweight and compression technologies are essential for deploying high-precision deep learning methods on resource-constrained edge computing systems. However, modeling accuracy is severely compromised by existing methods. To overcome this limitation, a new multi-stage pruning and distillation architecture was proposed in this study to compress a depthwise separable convolutional network for intelligent fault diagnosis of bearings in edge computing systems. The model was implemented on an NVIDIA Jetson Nano and verified using two bearing fault datasets. The results show that the proposed method can significantly reduce the calculation and reasoning time of the model and maintain high accuracy. The proposed method exhibits remarkable effectiveness, requires minimal memory, provides fast inference speeds, and is suitable for use in edge devices with less configuration.
- 27 September 2024
- Published by SAGE Publications in Advances in Mechanical Engineering
- Vol. 16 (9)
Open AccessLightweight intelligent fault diagnosis method based on a multi-stage pruning distillation interleaving network
Edge computing, a key technology in the Internet of Things, can help integrate real-time fault diagnosis into industrial applications. Lightweight and compression technologies are essential for deploying high-precision deep learning methods on resource-constrained edge computing systems. However, modeling accuracy is severely compromised by existing methods. To overcome this limitation, a new multi-stage pruning and distillation architecture was proposed in this study to compress a depthwise separable convolutional network for intelligent fault diagnosis of bearings in edge computing systems. The model was implemented on an NVIDIA Jetson Nano and verified using two bearing fault datasets. The results show that the proposed method can significantly reduce the calculation and reasoning time of the model and maintain high accuracy. The proposed method exhibits remarkable effectiveness, requires minimal memory, provides fast inference speeds, and is suitable for use in edge devices with less configuration.
- 2 May 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (8) , 086101
Investigation on the fusion reliability and cluster consistency of multivariable entropy method
Recent researches have shown that the multivariable entropy based feature extraction method can obtain better diagnosis results for fault diagnosis of planetary gearbox. However, the nature properties of multivariable entropy have still not been deeply explored: the reliability of multi-source information fusion and cluster consistency for the same fault signal. These two properties will affect the accuracy of fault diagnosis based on multivariate entropy. This paper aims to reveal the nature properties of multivariate entropy. Firstly, a rigid-flexible coupling dynamic model of a planetary gearbox is conducted to establish a pure test environment. Then the generated vibration signals are used to evaluate the fusion reliability and cluster consistency of multivariable entropy. Additionally, a new multivariable entropy feature extraction method called variational embedding refined composite multiscale diversity entropy (veRCMDE) is proposed. Finally, the simulation and experiment results show that high fusion reliability and high cluster consistency enable multivariate entropy to extract more valuable features, and the proposed veRCMDE performs the best in all experiments.
- 2 May 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (8) , 086101
Investigation on the fusion reliability and cluster consistency of multivariable entropy method
Recent researches have shown that the multivariable entropy based feature extraction method can obtain better diagnosis results for fault diagnosis of planetary gearbox. However, the nature properties of multivariable entropy have still not been deeply explored: the reliability of multi-source information fusion and cluster consistency for the same fault signal. These two properties will affect the accuracy of fault diagnosis based on multivariate entropy. This paper aims to reveal the nature properties of multivariate entropy. Firstly, a rigid-flexible coupling dynamic model of a planetary gearbox is conducted to establish a pure test environment. Then the generated vibration signals are used to evaluate the fusion reliability and cluster consistency of multivariable entropy. Additionally, a new multivariable entropy feature extraction method called variational embedding refined composite multiscale diversity entropy (veRCMDE) is proposed. Finally, the simulation and experiment results show that high fusion reliability and high cluster consistency enable multivariate entropy to extract more valuable features, and the proposed veRCMDE performs the best in all experiments.
- Open Access
- 25 April 2024
- Published by Hindawi Limited in International Journal of Aerospace Engineering
- Vol. 2024, 1-27
A Condition Monitoring Method of Hydraulic Gear Pumps Based on Multilevel Mechanism-Data Fusion
Pumps are important components in aviation fuel hydraulic systems, and thanks to the development of sensor technology and industrial intelligence technology, it is possible to achieve efficient state monitoring of pumps. However, when data quality is poor or the amount of data is small, a single data-driven model may not be able to meet diagnostic accuracy. A condition monitoring method for hydraulic gear pumps based on mechanism-data fusion is proposed. The method combines a mechanism model based on the volumetric efficiency formula with a data-driven model based on vibration signals. First, the parameters of volumetric efficiency are solved by fitting the pressureflow relationship. Subsequently, a multichannel fusion and multikernel function-weighted ensemble support vector classification (MCMK-SVC) is developed, to establish a data-driven model. Finally, through data-level fusion, feature-level fusion, and decision-level fusion, a condition monitoring model based on mechanism-data fusion is built. Experimental verification shows that the accuracy of the three levels of fusion models exceeds 96.9. Compared to the single data-driven model or other traditional data-driven models, the accuracy of the proposed method has improved by 3 to 33, demonstrating the effectiveness of the mechanism-data fusion model.
- 25 April 2024
- Published by Hindawi Limited in International Journal of Aerospace Engineering
- Vol. 2024, 1-27
Open AccessA Condition Monitoring Method of Hydraulic Gear Pumps Based on Multilevel Mechanism-Data Fusion
Pumps are important components in aviation fuel hydraulic systems, and thanks to the development of sensor technology and industrial intelligence technology, it is possible to achieve efficient state monitoring of pumps. However, when data quality is poor or the amount of data is small, a single data-driven model may not be able to meet diagnostic accuracy. A condition monitoring method for hydraulic gear pumps based on mechanism-data fusion is proposed. The method combines a mechanism model based on the volumetric efficiency formula with a data-driven model based on vibration signals. First, the parameters of volumetric efficiency are solved by fitting the pressureflow relationship. Subsequently, a multichannel fusion and multikernel function-weighted ensemble support vector classification (MCMK-SVC) is developed, to establish a data-driven model. Finally, through data-level fusion, feature-level fusion, and decision-level fusion, a condition monitoring model based on mechanism-data fusion is built. Experimental verification shows that the accuracy of the three levels of fusion models exceeds 96.9. Compared to the single data-driven model or other traditional data-driven models, the accuracy of the proposed method has improved by 3 to 33, demonstrating the effectiveness of the mechanism-data fusion model.
- 18 January 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (4) , 045110
An enhanced perception health state assessment method for subway sliding plug door transmission system
The monitoring data (current and rotational speed) of the subway sliding plug door transmission system changed positively and negatively with the acceleration and weight of the door. How to perceive the changes is a challenging problem in the health state assessment of transmission system. To address this problem, an enhanced perception health state assessment method was proposed for the transmission systems. In the method, firstly, the equivalent resistance force is calculated by monitoring the current and rotational speed data according to mechanical dynamic knowledge. Secondly, the sensitive features of normal and abnormal states are screened out from the enhanced dataset constructed by current, rotational speed data, and equivalent resistance force data. Finally, the health state of the transmission system is assessed using an integrated learning algorithm. The effectiveness of the method is verified by benchmark experimental data, and the results indicate that the method has a higher accuracy with four classifiers and a broader suitable range with varying door acceleration and weight.
- 18 January 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (4) , 045110
An enhanced perception health state assessment method for subway sliding plug door transmission system
The monitoring data (current and rotational speed) of the subway sliding plug door transmission system changed positively and negatively with the acceleration and weight of the door. How to perceive the changes is a challenging problem in the health state assessment of transmission system. To address this problem, an enhanced perception health state assessment method was proposed for the transmission systems. In the method, firstly, the equivalent resistance force is calculated by monitoring the current and rotational speed data according to mechanical dynamic knowledge. Secondly, the sensitive features of normal and abnormal states are screened out from the enhanced dataset constructed by current, rotational speed data, and equivalent resistance force data. Finally, the health state of the transmission system is assessed using an integrated learning algorithm. The effectiveness of the method is verified by benchmark experimental data, and the results indicate that the method has a higher accuracy with four classifiers and a broader suitable range with varying door acceleration and weight.
- Open Access
A Subway Sliding Plug Door System Health State Adaptive Assessment Method Based on Interval Intelligent Recognition of Rotational Speed Operation Data Curve
The subway sliding plug door system is crucial for ensuring normal operation. Due to the differences in the structure and motor control procedures of different sliding plug door systems, the rotational speed monitoring data curves show great differences. It is a challenging problem to recognize the intervals of complex data curves, which fundamentally affect the sensitivity of feature extraction and the prediction of an assessment model. Aiming at the problem, a subway sliding plug door system health state adaptive assessment method is proposed based on interval intelligent recognition of rotational speed operation data curve. In the proposed method, firstly, the rotational speed operation data curve is adaptively divided by a long short-term memory (LSTM) neural network into four intervals, according to the motion characteristics of the door system. Secondly, the sensitive features of the door system are screened out by the random forest (RF) algorithm. Finally, the health state of the door system is assessed using the adaptive boosting (AdaBoost) classifier. The proposed method is comprehensively verified by the benchmark experiment data set. The results show that the average diagnostic accuracy of the method on multiple bench doors can reach 98.15%. The wider application scope and the higher state classification accuracy indicate that the proposed method has important engineering value and theoretical significance for the health management of subway sliding plug door systems.
Open AccessA Subway Sliding Plug Door System Health State Adaptive Assessment Method Based on Interval Intelligent Recognition of Rotational Speed Operation Data Curve
The subway sliding plug door system is crucial for ensuring normal operation. Due to the differences in the structure and motor control procedures of different sliding plug door systems, the rotational speed monitoring data curves show great differences. It is a challenging problem to recognize the intervals of complex data curves, which fundamentally affect the sensitivity of feature extraction and the prediction of an assessment model. Aiming at the problem, a subway sliding plug door system health state adaptive assessment method is proposed based on interval intelligent recognition of rotational speed operation data curve. In the proposed method, firstly, the rotational speed operation data curve is adaptively divided by a long short-term memory (LSTM) neural network into four intervals, according to the motion characteristics of the door system. Secondly, the sensitive features of the door system are screened out by the random forest (RF) algorithm. Finally, the health state of the door system is assessed using the adaptive boosting (AdaBoost) classifier. The proposed method is comprehensively verified by the benchmark experiment data set. The results show that the average diagnostic accuracy of the method on multiple bench doors can reach 98.15%. The wider application scope and the higher state classification accuracy indicate that the proposed method has important engineering value and theoretical significance for the health management of subway sliding plug door systems.