Journal of Hydroinformatics (Feb 2024)
LSTM-based autoencoder models for real-time quality control of wastewater treatment sensor data
Abstract
The operation of smart wastewater treatment plants (WWTPs) is increasingly paramount in improving effluent quality, facilitating resource recovery and reducing carbon emissions. To achieve these objectives, sensors, monitoring systems, and artificial intelligence (AI)-based models are increasingly being developed and utilised for decision support and advanced control. Key to the adoption of advanced data-driven control of WWTPs is real-time data validation and reconciliation (DVR), especially for sensor data. This research demonstrates and evaluates real-time AI-based data quality control methods, i.e. long short-term memory (LSTM) autoencoder (AE) models, to reconcile faulty sensor signals in WWTPs as compared to autoregressive integrated moving average (ARIMA) models. The DVR procedure is aimed at anomalies resulting from data acquisition issues and sensor faults. Anomaly detection precedes the reconciliation procedure using models that capture short-time dynamics (SD) and (relatively) long-time dynamics (LD). Real data from an operational WWTP are used to test the DVR procedure. To address the reconciliation of prolonged anomalies, the SD is aggregated with an LD model by exponential weighting. For reconciling single-point anomalies, both ARIMA and LSTM AEs showed high accuracy, while the accuracy of reconciliation regresses quickly with increasing forecasting horizons for prolonged anomalous events. HIGHLIGHTS A new methodology is proposed for the real-time validation of sensor data in wastewater treatment by the aid of anomaly detection and the subsequent reconciliation of sensor signals using a short timescale dynamic and a long timescale dynamic model.; LSTM-based autoencoder models are used to reconcile anomalous data.; Deep neural network-based models are compared with conventional time series modelling.;
Keywords