Lichen Shi | Mechanical Engineering | Best Researcher Award Posted on 14/02/202514/02/2025 by sciencefather Prof. Lichen Shi | Mechanical Engineering | Best Researcher Award Profile Orcid Scopus Education Lichen Shi (also written as Shi Lichen) is a distinguished Chinese researcher specializing in intelligent measurement, equipment status monitoring, fault diagnosis, and electromechanical system modeling. He was born on June 28, 1972, and is currently affiliated with the School of Mechanical and Electrical Engineering at Xi’an University of Architecture and Technology (XAUAT), China. With a strong academic and research background, Professor Shi has dedicated his career to advancing intelligent measurement techniques through deep learning, as well as improving the reliability of electromechanical systems through fault diagnosis and dynamic analysis. Academic Contributions Professor Shi has published extensively in prestigious international journals, particularly in IEEE Sensors Journal, Measurement, and Computer Engineering & Applications. His notable works focus on deep learning-based fault diagnosis, graph neural networks, and AI-driven predictive modeling for mechanical systems. Some of his key contributions include: Developing an AI-based method for reading pointer meters using human-like reading sequences. Proposing a graph neural network and Markov transform fields approach for gearbox fault diagnosis. Introducing CBAM-ResNet-GCN methods for unbalance fault detection in rotating machinery. Advancing domain transfer learning techniques for mixed-data gearbox fault diagnosis. Pioneering a lightweight low-light object detection algorithm (CDD-YOLO) for enhanced industrial applications. His research findings have contributed significantly to the optimization of industrial machinery, predictive maintenance, and AI-driven automation in electromechanical systems. Many of his publications are frequently cited, underlining their impact on the field. Research Interests Professor Shi’s research spans multiple cutting-edge areas, including: Intelligent Measurement with Deep Learning Equipment Status Monitoring and Fault Diagnosis Electromechanical System Modeling and Dynamic Analysis Professional Impact As a leading expert in intelligent diagnostics and mechanical system optimization, Professor Shi has played a crucial role in bridging the gap between artificial intelligence and industrial engineering. His contributions have aided in the development of more efficient, predictive, and adaptive electromechanical systems, helping industries reduce downtime and improve operational efficiency. Publication [1] Qi Liu, Lichen Shi*. A pointer meter reading method based on human-like readingsequence and keypoint detection[J]. Measurement, 2025(248): 116994. https://doi.org/10.1016/j.measurement.2025.116994 [2] Haitao Wang, Zelin. Liu, Mingjun Li, Xiyang Dai, Ruihua Wang and LichenShi*. AGearbox Fault Diagnosis Method Based on Graph Neural Networks and MarkovTransform Fields[J]. IEEE Sensors Journal, 2024, 24(15) ：25186-25196. doi: 10.1109/JSEN.2024.3417231 [3] Haitao Wang, Xiyang Dai, Lichen Shi*, Mingjun Li, Zelin Liu, Ruihua Wang , XiaohuaXia. Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery[J]. IEEE Sensors Journal, 2024,12:34785-34799. DOI: 10.1109/access.2024.3368755. 4] Haitao Wang, Mingjun Li, Zelin Liu, Xiyang Dai, Ruihua Wang and Lichen Shi*. RotaryMachinery Fault Diagnosis Based on Split Attention MechanismandGraphConvolutional Domain Adaptive Adversarial Network[J]. IEEE Sensors Journal, 2024, 24(4) :5399-5413. doi: 10.1109/JSEN.2023.3348597. [5] Haitao Wang, Xiyang Dai, Lichen Shi*. Gearbox Fault Diagnosis Based onMixedData-Assisted Multi-Source Domain Transfer Learning under Unbalanced Data[J]. IEEESensors Journal. doi: 10.1109/JSEN.2024.3477929
Prof. Lichen Shi | Mechanical Engineering | Best Researcher Award Profile Orcid Scopus Education Lichen Shi (also written as Shi Lichen) is a distinguished Chinese researcher specializing in intelligent measurement, equipment status monitoring, fault diagnosis, and electromechanical system modeling. He was born on June 28, 1972, and is currently affiliated with the School of Mechanical and Electrical Engineering at Xi’an University of Architecture and Technology (XAUAT), China. With a strong academic and research background, Professor Shi has dedicated his career to advancing intelligent measurement techniques through deep learning, as well as improving the reliability of electromechanical systems through fault diagnosis and dynamic analysis. Academic Contributions Professor Shi has published extensively in prestigious international journals, particularly in IEEE Sensors Journal, Measurement, and Computer Engineering & Applications. His notable works focus on deep learning-based fault diagnosis, graph neural networks, and AI-driven predictive modeling for mechanical systems. Some of his key contributions include: Developing an AI-based method for reading pointer meters using human-like reading sequences. Proposing a graph neural network and Markov transform fields approach for gearbox fault diagnosis. Introducing CBAM-ResNet-GCN methods for unbalance fault detection in rotating machinery. Advancing domain transfer learning techniques for mixed-data gearbox fault diagnosis. Pioneering a lightweight low-light object detection algorithm (CDD-YOLO) for enhanced industrial applications. His research findings have contributed significantly to the optimization of industrial machinery, predictive maintenance, and AI-driven automation in electromechanical systems. Many of his publications are frequently cited, underlining their impact on the field. Research Interests Professor Shi’s research spans multiple cutting-edge areas, including: Intelligent Measurement with Deep Learning Equipment Status Monitoring and Fault Diagnosis Electromechanical System Modeling and Dynamic Analysis Professional Impact As a leading expert in intelligent diagnostics and mechanical system optimization, Professor Shi has played a crucial role in bridging the gap between artificial intelligence and industrial engineering. His contributions have aided in the development of more efficient, predictive, and adaptive electromechanical systems, helping industries reduce downtime and improve operational efficiency. Publication
[1] Qi Liu, Lichen Shi*. A pointer meter reading method based on human-like readingsequence and keypoint detection[J]. Measurement, 2025(248): 116994. https://doi.org/10.1016/j.measurement.2025.116994 [2] Haitao Wang, Zelin. Liu, Mingjun Li, Xiyang Dai, Ruihua Wang and LichenShi*. AGearbox Fault Diagnosis Method Based on Graph Neural Networks and MarkovTransform Fields[J]. IEEE Sensors Journal, 2024, 24(15) ：25186-25196. doi: 10.1109/JSEN.2024.3417231 [3] Haitao Wang, Xiyang Dai, Lichen Shi*, Mingjun Li, Zelin Liu, Ruihua Wang , XiaohuaXia. Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery[J]. IEEE Sensors Journal, 2024,12:34785-34799. DOI: 10.1109/access.2024.3368755. 4] Haitao Wang, Mingjun Li, Zelin Liu, Xiyang Dai, Ruihua Wang and Lichen Shi*. RotaryMachinery Fault Diagnosis Based on Split Attention MechanismandGraphConvolutional Domain Adaptive Adversarial Network[J]. IEEE Sensors Journal, 2024, 24(4) :5399-5413. doi: 10.1109/JSEN.2023.3348597. [5] Haitao Wang, Xiyang Dai, Lichen Shi*. Gearbox Fault Diagnosis Based onMixedData-Assisted Multi-Source Domain Transfer Learning under Unbalanced Data[J]. IEEESensors Journal. doi: 10.1109/JSEN.2024.3477929