Jian Cui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jian Cui has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Dailin Zhang
Huazhong University of Science and Technology
2 shared publications Guoli Zhu
School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, People’s Republic of China
1 shared publication- Guoli Zhu
School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China
1 shared publication - Guoqian Jiang
Yanshan University
1 shared publication Jing Wang
1 shared publication- Kaiduan Zou
Jiangsu Advanced Construction Machinery Innovation Center Ltd., Xuzhou, China
1 shared publication
Latest Publications
- 12 January 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (4) , 046102
MixFormer: a novel multi-sensor fusion based cross-intra-modal attention mechanism fault diagnosis model towards small samples
Interest in fault diagnosis has markedly increased to ensure the security and stability of industrial systems. The simultaneous collection of multi-sensor signals is essential for a comprehensive assessment of the system’s health status. However, developing effective fusion mechanisms for these signals to improve diagnostic performance is challenging. This study introduces a novel fault diagnosis method, enhanced by multi-modal learning, which integrates multimodal feature learning and attention fusion for vibration and current signals. We design a Mixformer, specifically designed to selectively extract key features from multimodal data derived from these signals. Additionally, a cross-intra modal attention module is developed to collectively optimize multiple classification tasks, leveraging both fused and distinct unimodal features. The efficacy of the proposed method is demonstrated through evaluation on two datasets. The experimental results show that our approach extracts more significant features and achieves superior classification performance over compared methods, which lack attention fusion and ability of feature extraction from small samples. At the same time, it also proves its effectiveness in small sample bearing fault diagnosis of wind turbines.
- 12 January 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (4) , 046102
MixFormer: a novel multi-sensor fusion based cross-intra-modal attention mechanism fault diagnosis model towards small samples
Interest in fault diagnosis has markedly increased to ensure the security and stability of industrial systems. The simultaneous collection of multi-sensor signals is essential for a comprehensive assessment of the system’s health status. However, developing effective fusion mechanisms for these signals to improve diagnostic performance is challenging. This study introduces a novel fault diagnosis method, enhanced by multi-modal learning, which integrates multimodal feature learning and attention fusion for vibration and current signals. We design a Mixformer, specifically designed to selectively extract key features from multimodal data derived from these signals. Additionally, a cross-intra modal attention module is developed to collectively optimize multiple classification tasks, leveraging both fused and distinct unimodal features. The efficacy of the proposed method is demonstrated through evaluation on two datasets. The experimental results show that our approach extracts more significant features and achieves superior classification performance over compared methods, which lack attention fusion and ability of feature extraction from small samples. At the same time, it also proves its effectiveness in small sample bearing fault diagnosis of wind turbines.
- 25 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
Spatio-Temporal Data Fusion-Based Method for Working Cycles Identification of Hydraulic Excavators
Accurately describing and identifying the operational modes of excavators is fundamental to achieving efficient and energy-saving control of excavators. Existing methods pre-dominantly rely on hydraulic power system parameters, utilizing machine learning models to recognize the operational states of excavators. However, the limited operational data from single or a few sensors lead to inputs that inadequately reflect the diverse action states of the equipment and overlook the spatial correlations between actions of different actuators, failing to effectively learn the distinctive features between operational conditions. To address these issues, this paper introduces a spatio-temporal fusion method for condition recognition based on multidimensional sensor data, encapsulating comprehensive operational information of the entire machine. This study developed an attention mechanism linked to operation-related attention module (OAM), integrated with a designed dual-channel feature extraction network for time and space, to enhance and capture the spatio-temporal correlations between adjacent operational states. Furthermore, a classifier based on imbalanced inter-class distance metrics was designed to adaptively learn the distances between category samples, thereby mitigating the learning challenges posed by imbalanced condition samples. Experiments conducted under various conditions on single and multiple working cycles achieved recognition accuracies of 99.17% and 99.24%, respectively, demonstrating the effectiveness and robustness of our proposed method and significantly improving the accuracy of condition recognition.
- 25 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
Spatio-Temporal Data Fusion-Based Method for Working Cycles Identification of Hydraulic Excavators
Accurately describing and identifying the operational modes of excavators is fundamental to achieving efficient and energy-saving control of excavators. Existing methods pre-dominantly rely on hydraulic power system parameters, utilizing machine learning models to recognize the operational states of excavators. However, the limited operational data from single or a few sensors lead to inputs that inadequately reflect the diverse action states of the equipment and overlook the spatial correlations between actions of different actuators, failing to effectively learn the distinctive features between operational conditions. To address these issues, this paper introduces a spatio-temporal fusion method for condition recognition based on multidimensional sensor data, encapsulating comprehensive operational information of the entire machine. This study developed an attention mechanism linked to operation-related attention module (OAM), integrated with a designed dual-channel feature extraction network for time and space, to enhance and capture the spatio-temporal correlations between adjacent operational states. Furthermore, a classifier based on imbalanced inter-class distance metrics was designed to adaptively learn the distances between category samples, thereby mitigating the learning challenges posed by imbalanced condition samples. Experiments conducted under various conditions on single and multiple working cycles achieved recognition accuracies of 99.17% and 99.24%, respectively, demonstrating the effectiveness and robustness of our proposed method and significantly improving the accuracy of condition recognition.
- 20 October 2022
- Published by Elsevier in Measurement
- Vol. 204
M2FN: An end-to-end multi-task and multi-sensor fusion network for intelligent fault diagnosis
- 20 October 2022
- Published by Elsevier in Measurement
- Vol. 204
M2FN: An end-to-end multi-task and multi-sensor fusion network for intelligent fault diagnosis