Loading...
Functional data analysis for detecting faults in water and wastewater treatment
Kuras, Aurora
Kuras, Aurora
Citations
Altmetric:
Advisor
Editor
Date
Date Issued
2022
Date Submitted
Collections
Research Projects
Organizational Units
Journal Issue
Embargo Expires
Abstract
Early and effective fault detection in water and wastewater treatment plants is important to maintain water quality and prevent process disruptions. Some faults, such as spike faults, are easily detected with traditional fault detection methods that identify extreme values, while other faults, such as drift faults, are difficult to identify due to their slowly changing behavior. In addition, there is the need for methods that assist operator decision making and have straightforward interpretability. This study applies a method in functional data analysis (FDA) for fault detection to drift faults observed in a sequencing batch membrane bioreactor and closed circuit reverse osmosis system. FDA enables analysis of cyclic data, which are curves or functions produced by system with repetitive behavior over a time period or process. Fault detection in a set of curves can be accomplished through the computation of statistics describing their shapes and magnitudes. In addition, functional plots visually supplement alarm results to assist operators. In this study we apply an existing FDA method for retrospective outlier detection and extend it for the non-stationary, real-time applications required for tracking water and wastewater process data. We demonstrate its ability to identify drifts faults in early stages as well as spike faults for three case studies analyzed.
Associated Publications
Rights
Copyright of the original work is retained by the author.