Accurate identification of anomalies in wastewater sensor - Integrating univariate and multivariate methods

Type of project

M.Sc.

Contact

Fabio Polesel (fapo@dhigroup.com), Christopher Gaszynski (chga@dhigroup.com)

Topic

Wastewater treatment plants (WWTPs) are increasingly provided with online sensors and analyser to monitor the performance in real-time and timely identify anomalies in process operations and performance. The quality of sensor data is to be ensured by continuous sensor maintenance by WWTP staff, combined with the application of processing techniques to clean time series data. Nevertheless, deviations from normal sensor behaviour (drift, outliers) are uncommon, affecting the reliability of the collected data.

The goals of this thesis project are to

(i) identify commonly used techniques to identify anomalies in sensor data as well as in process operations

(ii) apply and integrate these techniques for anomaly identification in a real WWTP

Relevance to DHI

This project is closely aligned with the ongoing work at DHI on “Digital Twins for the Water Environment” (2025-2028 research contract), focusing on novel approaches for predicting and reducing impacts from wastewater discharges in water recipients.

What is the student's contribution

• Review existing methods and applications of anomaly detection in wastewater treatment plants, with focus on both process and data anomalies
• Implement multivariate (e.g., principal component analysis) and univariate methods for anomaly detection
• Apply and integrate these methods for anomaly detection in a real WWTP, providing the ability of differentiate between data and process anomalies