Change point detection and issue localization based on fleet-wide fault data

Abstract

Modern industrial assets (e.g., generators, turbines, engines) are outfitted with numerous sensors to monitor key operating and environmental variables. Unusual sensor readings, such as high temperature, excessive vibration, or low current, could trigger rule-based actions (also known as faults) that range from warning alarms to immediate shutdown of the asset to prevent potential damage. In the case study of this article, a wind park experienced a sudden surge in vibration-induced shutdowns. We utilize fault data logs from the park with the goal of detecting common change points across turbines. Another important goal is the localization of fault occurrences to an identifiable set of turbines. The literature on change point detection and localization for multiple assets is highly sparse. Our technical development is based on the generalized linear modeling framework. We combine well-known solutions to change point detection for a single asset with a heuristics-based approach to identify a common change point(s) for multiple assets. The performance of the proposed detection and localization algorithms is evaluated through synthetic (Monte Carlo) fault data streams. Several novel performance metrics are defined to characterize different aspects of a change point detection algorithm for multiple assets. For the case study example, the proposed methodology identified the change point and the subset of affected turbines with a high degree of accuracy. The problem described here warrants further study to accommodate general fault distributions, change point detection algorithms, and very large fleet sizes.

Keywords:

• big data
• event data
• generalized linear models
• Poisson distribution
• supervisory control and data acquisition (SCADA) system
• wind turbine

Supplementary materials

The online supplementary materials include:

• Case study data (Section 2).

• Performance evaluation of the SASCP method (Section 3.5).

• Graphical display of change points identified by the MAMCP method overlaid in Figure 2 (Section 3.6).

• Assessment of the robustness to data distributions (Section 4.1).

• R codes for performance evaluation (Section 3.5) and the case study application of the MAMCP algorithm (Section 3.6).

Acknowledgments

The authors would like to thank the Associate Editor and the two anonymous reviewers for their useful and constructive suggestions on earlier versions of the article.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Zhanpan Zhang

Zhanpan Zhang, PhD, is a senior statistician at GE Global Research, Niskayuna, New York. His research interests are statistical modeling, machine learning, and industrial applications in anomaly detection, diagnostics and prognostics. He has publications on various aspects including clustering techniques, renewable energy analytics, and bioscience discovery.

Necip Doganaksoy

Necip Doganaksoy, PhD, is an Associate Professor at the School of Business of Siena College, Loudonville, New York, following a 26-year career in industry, mostly at General Electric (GE). He has published extensively based on his research and applications in reliability, quality and productivity improvement in business and industry. He is co-author of the books Achieving Product Reliability (2021) with William Q. Meeker and Gerald Hahn, and A Career in Statistics: Beyond the Numbers (2011) and The Role of Statistics in Business and Industry (2008) with Gerald Hahn. In 2020 he was awarded the American Society for Quality (ASQ) Shewhart Medal. He received the ASQ Brumbaugh Award in 2016 and ASQ Statistics Division's W.G. Hunter Award in 2009. Doganaksoy is a Fellow of the ASQ and the American Statistical Association (ASA).