Abstract
Effective process monitoring is crucial to ensure engineering and environmental plants' reliable and safe operation. If anomalies in engineering or environmental plants are not detected promptly, they can affect plants' productivity, profitability, and safety. Both model-based and data-based process monitoring techniques have proven themselves in practice over the past four decades. This talk will present a model-based approach for anomaly detection in a linear model with a bounded nuisance parameter and a data-based process monitoring example using machine learning. Three real-world applications will be presented: ozone pollution monitoring, anomaly detection in photovoltaic systems, and distillation column data.
Brief Biography
Fouzi Harrou received a Ph.D. from the University of Technology of Troyes, France. He is a Research Scientist with the Environmental Statistics group under the supervision of Prof. Ying Sun at KAUST. His research interests are statistical anomaly detection and process monitoring, particularly in data-driven, machine learning/deep learning methods.
