Jingyi Wang

Jingyi Wang

Auto-generated profile, based on publicly available information

Jingyi Wang

Department of Chemical and Biological Engineering, University of British Columbia, Vancouver, BC, Canada

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 April 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
LCLiang Cao
Liang Cao
JWJingyi Wang
Jingyi Wang
JSJianping Su
Jianping Su
YLYi Luo
Yi Luo
YCYankai Cao
Yankai Cao
BGBhushan Gopaluni
Bhushan Gopaluni
Soft sensors play a vital role in industrial process monitoring and control by estimating difficult-to-measure quality variables. While significant progress has been made in improving the accuracy of soft sensor models, challenges remain in ensuring their interpretability and stability in dynamic industrial environments. From a measurement science perspective, ensuring transparency and reliable performance under varying process conditions is becoming increasingly critical, particularly in high-stakes industrial applications. This paper provides a comprehensive review of methodologies to enhance the interpretability and stability of soft sensor models. To address interpretability, we analyze various interpretable machine learning techniques applicable to soft sensors and discuss open-source projects that facilitate the implementation of these techniques. For improving stability, we emphasize the role of causal machine learning, detailing methods for causal discovery in industrial processes and highlighting relevant open-source tools. By highlighting current limitations and identifying areas for improvement, we aim to provide valuable insights and practical tools for researchers and practitioners. These insights will guide the development of more transparent and reliable soft sensors, ultimately enhancing industrial process monitoring and control.