Engineer at China Three Gorges Corporation, China
Dr. Junjie Yang is an accomplished researcher specializing in fault diagnosis, anomaly detection, and machine learning applications in complex systems. With a Ph.D. from the University of Paris-Saclay, his groundbreaking work has introduced methodologies such as the Local Mahalanobis Distance (LMD) for incipient fault diagnosis, earning recognition through high-impact publications. He has contributed to diverse domains, from renewable energy systems to multivariate statistical analysis, showcasing his ability to blend theoretical innovation with practical applications. Dr. Yang’s global research experience spans institutions like CNRS Singapore and China Three Gorges Corporation, where he developed hybrid AI frameworks and advanced diagnostic tools. Proficient in Python, Matlab, and AI libraries, he bridges traditional engineering and modern computational techniques. His commitment to interdisciplinary research, strong publication record, and collaboration with renowned experts position him as a leading figure in his field. Dr. Yang exemplifies excellence in leveraging AI for impactful real-world solutions.
Professional Profile
Education
Dr. Junjie Yang has a robust educational foundation that underpins his expertise in fault diagnosis and machine learning. He earned his Ph.D. from the University of Paris-Saclay in 2023, focusing on fault diagnosis and prognosis in multivariate complex systems. His doctoral research introduced innovative methodologies, such as the Local Mahalanobis Distance (LMD), for detecting and isolating faults in complex environments. Prior to this, he completed his M.Sc. in Control Science and Engineering at Guangdong University of Technology, China, in 2019, where he developed a novel method for estimating the volume under a three-class ROC surface using kNN classifiers. His academic journey began with a B.Sc. in Automation from the same university in 2016, during which he worked on open-circuit fault diagnosis for interleaved DC-DC converters. Additionally, Dr. Yang enriched his academic portfolio as a visiting student at Polytech Nantes, France, specializing in wireless embedded technology.
Professional Experience
Dr. Junjie Yang possesses extensive professional experience in the fields of fault diagnosis, renewable energy systems, and machine learning. Currently, he serves as an Engineer at China Three Gorges Corporation, where he focuses on leveraging Large Language Models (LLMs) for fault diagnosis in renewable energy systems. Prior to this role, he was a Research Fellow at CNRS @ CREATE in Singapore, where he developed hybrid models integrating Convolutional Auto-Encoders with traditional physical characteristics for unsupervised high-impedance fault detection. Dr. Yang’s professional journey includes impactful research roles addressing complex problems in power systems and automation, underscored by his innovative contributions to incipient fault detection using AI-driven methodologies. His ability to transition seamlessly between academia and industry highlights his adaptability and focus on real-world applications. Through his work, Dr. Yang demonstrates a unique ability to bridge the gap between theoretical advancements and practical engineering solutions.
Research Interest
Dr. Junjie Yang’s research interests lie at the intersection of machine learning, statistical analysis, and engineering, with a particular focus on fault diagnosis and anomaly detection in complex systems. He is deeply engaged in developing advanced methodologies for one-class classification, semi-supervised learning, and multivariate statistical analysis to tackle challenges in identifying and isolating incipient faults. His work emphasizes the integration of AI techniques, such as Convolutional Auto-Encoders and Local Mahalanobis Distance (LMD), with traditional engineering models to enhance fault detection and prognosis in renewable energy systems and other industrial applications. Dr. Yang is also interested in applying data-driven and hybrid approaches to improve system reliability and performance in multivariate and high-dimensional environments. His research aims to address practical challenges in automation, energy systems, and beyond, making his contributions valuable for advancing both theoretical knowledge and real-world applications in intelligent fault diagnosis and system monitoring.
Award and honor
Dr. Junjie Yang has earned recognition for his innovative contributions to the fields of fault diagnosis and machine learning, receiving accolades that highlight his research excellence. His groundbreaking methodologies, such as the Local Mahalanobis Distance (LMD) and hybrid AI models for fault detection, have garnered widespread acclaim within the academic and industrial communities. Dr. Yang has been invited to present his work at prestigious international conferences, including IEEE IECON and ICASSP, underscoring his influence in advancing fault detection techniques. His papers, published in high-impact journals like Signal Processing and Electric Power Systems Research, have been highly cited, reflecting their significance in the field. While specific awards and honors may not be explicitly listed in his profile, his consistent publication in leading journals, collaborations with globally renowned researchers, and research positions at esteemed institutions underscore his distinction and impactful contributions to science and engineering.
Conclusion
Junjie Yang is a highly deserving candidate for the Best Researcher Award due to his groundbreaking contributions to fault diagnosis and renewable energy systems using AI models. His work bridges theoretical innovation with practical applications, evidenced by his extensive publication record and global collaborations. Enhancing the breadth of his applications and adopting newer AI paradigms could further cement his standing as a leader in the field. He embodies the qualities of a researcher who significantly advances the frontiers of science and engineering.
Publications Top Noted
- Title: An incipient fault diagnosis methodology using local Mahalanobis distance: Detection process based on empirical probability density estimation
Authors: J. Yang, C. Delpha
Year: 2022
Citations: 38
- Title: Change point detection with mean shift based on AUC from symmetric sliding windows
Authors: Y. Wang, G. Huang, J. Yang, H. Lai, S. Liu, C. Chen, W. Xu
Year: 2020
Citations: 10
- Title: An incipient fault diagnosis methodology using local Mahalanobis distance: Fault isolation and fault severity estimation
Authors: J. Yang, C. Delpha
Year: 2022
Citations: 9
- Title: Open-circuit fault diagnosis for interleaved DC-DC converters
Authors: Y. Junjie, C. Delpha
Year: 2020
Citations: 7
- Title: A local Mahalanobis distance analysis based methodology for incipient fault diagnosis
Authors: J. Yang, C. Delpha
Year: 2021
Citations: 6
- Title: Local Mahalanobis distance envelope using a robust healthy domain approximation for incipient fault diagnosis
Authors: J. Yang, C. Delpha
Year: 2021
Citations: 5
- Title: An efficient and user-friendly software tool for ordered multi-class receiver operating characteristic analysis based on Python
Authors: S. Liu, J. Yang, X. Zeng, H. Song, J. Cen, W. Xu
Year: 2022
Citations: 2
- Title: Empirical probability density cumulative sum for incipient fault detection
Authors: J. Yang, C. Delpha
Year: 2020
Citations: 2
- Title: A new reconstruction-based method using local Mahalanobis distance for incipient fault isolation and amplitude estimation
Authors: J. Yang, C. Delpha
Year: 2023
Citations: 1
- Title: Bearing Faults Detection Using Statistical Feature Extraction and Probability Based Distance: A Comparative Study
Authors: J. Yang, C. Delpha
Year: 2022
Citations: 1
- Title: IEEE 34 Nodes Test Feeder Simulation Data for High Impedance Fault Detection and Localization
Authors: J. Yang, D. Benoit
Year: 2024
Citations: 0
- Title: Incipient Fault Severity Estimation Using Local Mahalanobis Distance
Authors: J. Yang, C. Delpha
Year: 2022
Citations: 0
