Prof. Le Yao, Hangzhou Normal University, China
Le Yao is an accomplished Associate Professor at the School of Mathematics, Hangzhou Normal University, China. With a strong background in control science and engineering, he specializes in data-driven process modeling, soft sensor development, quality-related fault diagnosis, and industrial causal analysis. His research focuses on deep learning, interpretable modeling, and causal analysis for industrial applications. Le Yao has been actively involved in multiple funded projects supported by NSFC and the China Postdoctoral Science Foundation. He has an impressive academic record, with numerous high-impact publications in IEEE Transactions and other renowned journals. Recognized for his contributions, he has received prestigious awards, including the National Scholarship for Ph.D. and Outstanding Dissertation Awards. His innovative work bridges the gap between theoretical advancements and practical applications in industrial processes, making significant contributions to smart manufacturing and intelligent systems.
Professional Profile
Scopus
Orcid
Google Scholar
Summary of Suitability for the ‘Research for Best Researcher Award’
Le Yao is an exceptional candidate for the ‘Research for Best Researcher Award,’ given his impressive academic journey, extensive research contributions, and leadership in the field of industrial data-driven modeling. His work focuses on crucial areas such as soft sensor modeling, quality prediction, fault diagnosis, and causal analysis, with significant contributions to process control in industrial settings. His innovations in deep learning, causal analysis, and interpretable process modeling have greatly advanced the application of machine learning techniques to complex, large-scale industrial systems.
Notably, his research on scalable and distributed parallel modeling for big process data, combined with his exploration of probabilistic modeling and causal discovery methods, reflects a profound understanding of both theoretical and practical aspects of industrial systems. His ability to fuse domain knowledge with data-driven techniques has led to breakthroughs in process quality prediction and fault detection, impacting industries significantly. Furthermore, Le Yao has successfully secured competitive research funding from prestigious sources, such as the National Natural Science Foundation of China (NSFC) and the China Postdoctoral Science Foundation, demonstrating his capability to lead high-level research initiatives.
🎓 Education
Le Yao holds a Ph.D. in Control Science and Engineering from Zhejiang University (2019), where he specialized in big process data modeling, quality prediction, and process monitoring. His doctoral studies were pivotal in advancing soft sensor modeling techniques for industrial applications. Prior to his Ph.D., he earned an M.S. (2015) from Jiangnan University, where he focused on soft sensor modeling and system identification. His bachelor’s degree (2012) was also from Jiangnan University, where he developed a strong foundation in control science and engineering. Throughout his academic journey, Le Yao has consistently demonstrated excellence, securing prestigious scholarships and honors. His multidisciplinary expertise enables him to develop innovative solutions for industrial automation, smart manufacturing, and data-driven decision-making. His research contributions have influenced numerous industrial applications, bridging the gap between academic advancements and real-world implementations.
💼 Professional Experience
Le Yao is currently an Associate Professor at Hangzhou Normal University (2022–present), where he leads research on deep learning, causal analysis, and interpretable modeling for industrial systems. Prior to this, he served as a Postdoctoral Researcher (2019–2022) at Zhejiang University’s Institute of Industrial Process Control, focusing on deep learning-driven process modeling and process knowledge fusion. During his postdoctoral tenure, he was awarded research grants from NSFC and the China Postdoctoral Science Foundation. His expertise spans scalable and distributed parallel modeling, soft sensor applications, and quality prediction in large-scale industrial systems. Le Yao’s research integrates advanced computational techniques with practical industrial challenges, driving innovation in smart manufacturing. His leadership in industrial data analytics and AI-driven process control has positioned him as a key contributor to the field, influencing both academic research and industry practices.
🏅 Awards and Recognition
Le Yao has been recognized with numerous prestigious awards for his academic and research contributions. He received the 2020 Outstanding Dissertation Award from the Chinese Institute of Electronics and was named an Outstanding Graduate by Zhejiang University and Zhejiang Province in 2019. His research excellence has been acknowledged through multiple National Scholarships for Ph.D. students (2017, 2018). His work has been featured in top-tier conferences, earning him Best Paper Finalist awards at IEEE DDCLS (2018) and China Process Control Conferences (2016, 2017, 2018). These accolades reflect his outstanding contributions to industrial process modeling, soft sensing, and causal analysis. His innovative approaches to quality prediction and fault diagnosis have significantly impacted the field, earning him recognition from both academic institutions and industry leaders. Le Yao’s commitment to excellence continues to drive his research endeavors, making him a prominent figure in data-driven industrial applications.
Le Yao’s research expertise spans multiple domains, including data-driven process modeling, soft sensor development, quality-related fault diagnosis, and industrial causal analysis. He specializes in deep learning techniques for process optimization and interpretable modeling to enhance decision-making in industrial environments. His work on scalable and distributed parallel modeling has introduced novel methodologies for handling big process data efficiently. His causal analysis research integrates process knowledge with data-driven approaches, improving anomaly detection and fault diagnosis. He has developed advanced deep learning models incorporating hierarchical extreme learning machines and probabilistic latent variable regression. His research contributions have been implemented in real-world industrial applications, optimizing quality prediction and process control. With a strong foundation in control engineering, statistics, and artificial intelligence, Le Yao continues to advance the field by bridging theoretical research with industrial needs.
Publication Top Notes
-
Deep learning of semisupervised process data with hierarchical extreme learning machine and soft sensor application
- Authors: L Yao, Z Ge
- Citation: 295
- Year: 2017
- Journal: IEEE Transactions on Industrial Electronics, 65 (2), 1490-1498
-
Big data quality prediction in the process industry: A distributed parallel modeling framework
- Authors: L Yao, Z Ge
- Citation: 108
- Year: 2018
- Journal: Journal of Process Control, 68, 1-13
-
Nonlinear probabilistic latent variable regression models for soft sensor application: From shallow to deep structure
- Authors: B Shen, L Yao, Z Ge
- Citation: 102
- Year: 2020
- Journal: Control Engineering Practice, 94, 104198
-
Scalable semisupervised GMM for big data quality prediction in multimode processes
- Authors: L Yao, Z Ge
- Citation: 90
- Year: 2018
- Journal: IEEE Transactions on Industrial Electronics, 66 (5), 3681-3692
-
Locally weighted prediction methods for latent factor analysis with supervised and semisupervised process data
- Authors: L Yao, Z Ge
- Citation: 80
- Year: 2016
- Journal: IEEE Transactions on Automation Science and Engineering, 14 (1), 126-138
-
Distributed parallel deep learning of hierarchical extreme learning machine for multimode quality prediction with big process data
- Authors: L Yao, Z Ge
- Citation: 62
- Year: 2019
- Journal: Engineering Applications of Artificial Intelligence, 81, 450-465
-
Moving window adaptive soft sensor for state shifting process based on weighted supervised latent factor analysis
- Authors: L Yao, Z Ge
- Citation: 62
- Year: 2017
- Journal: Control Engineering Practice, 61, 72-80
-
Cooperative deep dynamic feature extraction and variable time-delay estimation for industrial quality prediction
- Authors: L Yao, Z Ge
- Citation: 61
- Year: 2020
- Journal: IEEE Transactions on Industrial Informatics, 17 (6), 3782-3792
-
Online updating soft sensor modeling and industrial application based on selectively integrated moving window approach
- Authors: L Yao, Z Ge
- Citation: 60
- Year: 2017
- Journal: IEEE Transactions on Instrumentation and Measurement, 66 (8), 1985-1993
-
Parallel computing and SGD-based DPMM for soft sensor development with large-scale semisupervised data
- Authors: W Shao, L Yao, Z Ge, Z Song
- Citation: 53
- Year: 2018
- Journal: IEEE Transactions on Industrial Electronics, 66 (8), 6362-6373