Yazhou Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yazhou Li has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Wei Dai
School of Reliability and Systems Engineering, Beihang University, Beijing, China
6 shared publications - Weifang Zhang
Beihang University
2 shared publications - Yihai He
Beihang University
2 shared publications BoYang Zhao
1 shared publication- Boyang Zhao
School of Reliability and Systems Engineering, Beihang University, Beijing, China
1 shared publication Chennan Lu
1 shared publication
Latest Publications
- 12 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75 (00189529) , 977-990
Zero-Shot Fault Diagnosis in Manufacturing Processes via Attribute Co-Occurrence Relationships
In the transition from pilot to mass production, certain fault classes lack available samples, creating a zero-shot condition that challenges the training of fault diagnosis models. Zero-shot learning (ZSL) maps features to shared attribute vectors formed by engineering knowledge information, offering a potential solution. In manufacturing processes, disturbances propagate across operations, causing multiple attributes to co-occur. However, the internal co-occurrence relationships among attributes are often overlooked, which may lead to discrepancies in attribute prediction. To address this issue, we propose a zero shot fault diagnosis method for manufacturing processes that leverages attribute co-occurrence relationships to identify unseen faults. To capture this relationship, mutual information is first employed to quantify attribute co-occurrence and construct an adjacency matrix of attribute relations. In parallel, distributional features are extracted using multi-delay ordinal patterns, and a distance-based loss function is designed to align these features with the attributes. The adjacency matrix and distributional features are then input into a graph convolutional network, with attribute relationships embedded into the distributional features to maintain consistency. Finally, distributional features support zero-shot fault diagnosis via mapping and similarity measures. Experimental validation on the Tennessee Eastman Process (TEP) and fuel rods manufacturing process demonstrates the effectiveness of the proposed method.
- 12 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75 (00189529) , 977-990
Zero-Shot Fault Diagnosis in Manufacturing Processes via Attribute Co-Occurrence Relationships
In the transition from pilot to mass production, certain fault classes lack available samples, creating a zero-shot condition that challenges the training of fault diagnosis models. Zero-shot learning (ZSL) maps features to shared attribute vectors formed by engineering knowledge information, offering a potential solution. In manufacturing processes, disturbances propagate across operations, causing multiple attributes to co-occur. However, the internal co-occurrence relationships among attributes are often overlooked, which may lead to discrepancies in attribute prediction. To address this issue, we propose a zero shot fault diagnosis method for manufacturing processes that leverages attribute co-occurrence relationships to identify unseen faults. To capture this relationship, mutual information is first employed to quantify attribute co-occurrence and construct an adjacency matrix of attribute relations. In parallel, distributional features are extracted using multi-delay ordinal patterns, and a distance-based loss function is designed to align these features with the attributes. The adjacency matrix and distributional features are then input into a graph convolutional network, with attribute relationships embedded into the distributional features to maintain consistency. Finally, distributional features support zero-shot fault diagnosis via mapping and similarity measures. Experimental validation on the Tennessee Eastman Process (TEP) and fuel rods manufacturing process demonstrates the effectiveness of the proposed method.
- 6 September 2024
- Published by Elsevier in ISA Transactions
- Vol. 154, 228-241
Concurrent control chart pattern recognition in manufacturing processes based on zero-shot learning
- 6 September 2024
- Published by Elsevier in ISA Transactions
- Vol. 154, 228-241
Concurrent control chart pattern recognition in manufacturing processes based on zero-shot learning
- 1 February 2024
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 189
Control chart pattern recognition under small shifts based on multi-scale weighted ordinal pattern and ensemble classifier
- 1 February 2024
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 189
Control chart pattern recognition under small shifts based on multi-scale weighted ordinal pattern and ensemble classifier
- 22 June 2023
- Published by Elsevier in Measurement
- Vol. 218
A novel fault early warning method for mechanical equipment based on improved MSET and CCPR
- 22 June 2023
- Published by Elsevier in Measurement
- Vol. 218
A novel fault early warning method for mechanical equipment based on improved MSET and CCPR
- 13 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 190, 1-6
Multi-factor machining condition monitoring method based on ordinal pattern analysis and image matching
The existing machining process condition monitoring methods usually only monitor the single anomaly, ignoring the multi-factor coupling anomaly in the actual complex machining process. Aiming at three kinds of typical anomalies frequently occurring in cutting, a new multi-factor coupling machining condition monitoring method based on ordinal pattern (OP) analysis and image matching is proposed. Firstly, the OP analysis model is developed to transform the condition monitoring signal into a gray image based on multi-parameter ordinal pattern spectrum (OPS), which optimizes the parameter selection process. Then, an OPS image dictionary template set of different condition monitoring signals is established. A condition recognition method based on OPS image matching is proposed to identify the sample processing state. Finally, a cutting experiment with 8 machining states is designed to verify the effectiveness of the method. The results show that the proposed method can accurately identify various cutting anomalies in different machining environments.
- 13 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 190, 1-6
Multi-factor machining condition monitoring method based on ordinal pattern analysis and image matching
The existing machining process condition monitoring methods usually only monitor the single anomaly, ignoring the multi-factor coupling anomaly in the actual complex machining process. Aiming at three kinds of typical anomalies frequently occurring in cutting, a new multi-factor coupling machining condition monitoring method based on ordinal pattern (OP) analysis and image matching is proposed. Firstly, the OP analysis model is developed to transform the condition monitoring signal into a gray image based on multi-parameter ordinal pattern spectrum (OPS), which optimizes the parameter selection process. Then, an OPS image dictionary template set of different condition monitoring signals is established. A condition recognition method based on OPS image matching is proposed to identify the sample processing state. Finally, a cutting experiment with 8 machining states is designed to verify the effectiveness of the method. The results show that the proposed method can accurately identify various cutting anomalies in different machining environments.
- Open Access
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Thermomechanical Response for Survival Mechanisms of Pronounced Supercooling Insects
Cryopreservation can keep the bioactivity of biological specimens in long-term storage. But it is hard to retain the structural integrity due to serious thermomechanical stress during cooling and warming procedures, especially for complex living organisms. Few studies reported thermomechanical stress of biological specimens at supercooled states during freezing procedures, which are widespread phenomena for slow-rate freezing cryopreservation. Here, we develop a thermomechanical coupling model to study transient thermal and mechanical fields of supercooled biological specimens during freezing procedures. The results show that cryoprotectant accumulation in insects causes pronounced supercooled phenomena, deformation and thermomechanical stress are serious in the initial state of phase transition. But final deformation and stress decrease due to loss of freezable water, which is in favor of organism survival after freezing. The hard exoskeleton also assists in protecting internal tissues during phase transition. This numerical method is proved to be a guide for optimizing slow-rate freezing cryopreservation protocols efficiently and economically. These results reveal survival mechanisms of insects with supercooled phenomena after freezing and assist researchers in exploring more efficient cryopreservation methods for biological specimens.
- 1 January 2022
- Published by Elsevier in SSRN Electronic Journal
Open AccessThermomechanical Response for Survival Mechanisms of Pronounced Supercooling Insects
Cryopreservation can keep the bioactivity of biological specimens in long-term storage. But it is hard to retain the structural integrity due to serious thermomechanical stress during cooling and warming procedures, especially for complex living organisms. Few studies reported thermomechanical stress of biological specimens at supercooled states during freezing procedures, which are widespread phenomena for slow-rate freezing cryopreservation. Here, we develop a thermomechanical coupling model to study transient thermal and mechanical fields of supercooled biological specimens during freezing procedures. The results show that cryoprotectant accumulation in insects causes pronounced supercooled phenomena, deformation and thermomechanical stress are serious in the initial state of phase transition. But final deformation and stress decrease due to loss of freezable water, which is in favor of organism survival after freezing. The hard exoskeleton also assists in protecting internal tissues during phase transition. This numerical method is proved to be a guide for optimizing slow-rate freezing cryopreservation protocols efficiently and economically. These results reveal survival mechanisms of insects with supercooled phenomena after freezing and assist researchers in exploring more efficient cryopreservation methods for biological specimens.
- Open Access
- 9 September 2020
- Published by DEStech Publications in DEStech Transactions on Social Science, Education and Human Science
- No. ssme
Research on International Trade VR Practice System Construction Based on Cross-Border E-Commerce
Practical teaching is the core teaching link of applied undergraduate colleges and bears the main task of cultivating applied talents. This thesis deeply explored the impact of cross-border e-commerce on international trade, constructed practice talent training system based on cross-border e-commerce, based on theoretical analysis and practical research, it proposed comprehensive VR practice platform and operating suggestions for implementation. The research is beneficial for undergraduates to improve their practical abilities in international trade field.
- 9 September 2020
- Published by DEStech Publications in DEStech Transactions on Social Science, Education and Human Science
- No. ssme
Open AccessResearch on International Trade VR Practice System Construction Based on Cross-Border E-Commerce
Practical teaching is the core teaching link of applied undergraduate colleges and bears the main task of cultivating applied talents. This thesis deeply explored the impact of cross-border e-commerce on international trade, constructed practice talent training system based on cross-border e-commerce, based on theoretical analysis and practical research, it proposed comprehensive VR practice platform and operating suggestions for implementation. The research is beneficial for undergraduates to improve their practical abilities in international trade field.
- Open Access
- 22 June 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (12) , 4278
Adaptive Early Warning Method Based on Similar Proportion and Probability Model
This paper presents a multi-state adaptive early warning method for mechanical equipment and proposes an adaptive dynamic update model of the equipment alarm threshold based on a similar proportion and state probability model. Based on the similarity of historical equipment, the initial thresholds of different health states of equipment can be determined. The equipment status is divided into four categories and analyzed, which can better represent its status and provide more detailed and reasonable guidance. The obtained dynamic alarm lines at all levels can regulate the operation range of equipment in the different health states. Compared to the traditional method of a fixed threshold, this method can effectively reduce the number of false alarms and attains a higher prediction accuracy, which demonstrates its effectiveness and superiority. Finally, the method was verified by means of lifetime data of a rolling bearings. The results show that the model improves the timely detection of the abnormal state of the equipment, greatly reduces the false alarm rate, and even overcomes the limitation of independence between the fixed threshold method and equipment state. Moreover, multi-state division can accurately diagnose the current equipment state, which should be considered in maintenance decision-making.
- 22 June 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (12) , 4278
Open AccessAdaptive Early Warning Method Based on Similar Proportion and Probability Model
This paper presents a multi-state adaptive early warning method for mechanical equipment and proposes an adaptive dynamic update model of the equipment alarm threshold based on a similar proportion and state probability model. Based on the similarity of historical equipment, the initial thresholds of different health states of equipment can be determined. The equipment status is divided into four categories and analyzed, which can better represent its status and provide more detailed and reasonable guidance. The obtained dynamic alarm lines at all levels can regulate the operation range of equipment in the different health states. Compared to the traditional method of a fixed threshold, this method can effectively reduce the number of false alarms and attains a higher prediction accuracy, which demonstrates its effectiveness and superiority. Finally, the method was verified by means of lifetime data of a rolling bearings. The results show that the model improves the timely detection of the abnormal state of the equipment, greatly reduces the false alarm rate, and even overcomes the limitation of independence between the fixed threshold method and equipment state. Moreover, multi-state division can accurately diagnose the current equipment state, which should be considered in maintenance decision-making.
- Open Access
- 17 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 19008-19025
Bearing Fault Feature Selection Method Based on Weighted Multidimensional Feature Fusion
Rolling bearing is one of the most critical components in rotating machinery, so in order to efficiently select features, reduce feature dimensions and improve the correctness of fault diagnosis, a feature selection and fusion method based on weighted multi-dimensional feature fusion is proposed. Firstly, features are extracted from different domains to constitute the original high-dimensional feature set. Considering the large number of invalid and redundant features contained in such original feature set, a feature selection process that combines with support vector machine (SVM) single feature evaluation, correlation analysis and principal component analysis-weighted load evaluation (PCA-WLE) is put forward in this paper for selecting sensitive features. The selected features are weighted and fused according to their sensitivity so as to further weaken the interference of low important features. Finally, this process is applied to the data provided by the Case Western Reserve University Bearing Data Center and Xi’an Jiaotong University School of Mechanical Engineering, respectively, and the fault is diagnosed by using the particle swarm optimization-support vector machine (PSO-SVM). The results show that this method can accurately identify different fault categories and degrees of bearing, which is superior and practical than single-domain fault diagnosis with higher recognition ability.
- 17 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 19008-19025
Open AccessBearing Fault Feature Selection Method Based on Weighted Multidimensional Feature Fusion
Rolling bearing is one of the most critical components in rotating machinery, so in order to efficiently select features, reduce feature dimensions and improve the correctness of fault diagnosis, a feature selection and fusion method based on weighted multi-dimensional feature fusion is proposed. Firstly, features are extracted from different domains to constitute the original high-dimensional feature set. Considering the large number of invalid and redundant features contained in such original feature set, a feature selection process that combines with support vector machine (SVM) single feature evaluation, correlation analysis and principal component analysis-weighted load evaluation (PCA-WLE) is put forward in this paper for selecting sensitive features. The selected features are weighted and fused according to their sensitivity so as to further weaken the interference of low important features. Finally, this process is applied to the data provided by the Case Western Reserve University Bearing Data Center and Xi’an Jiaotong University School of Mechanical Engineering, respectively, and the fault is diagnosed by using the particle swarm optimization-support vector machine (PSO-SVM). The results show that this method can accurately identify different fault categories and degrees of bearing, which is superior and practical than single-domain fault diagnosis with higher recognition ability.