Adaptive Neural Network Based Monitoring of Wastewater Treatment Plants

Abstract

The quality of the treated wastewater is conditioned by the performance of wastewater treatment processes. However, real-time monitoring of quality variables in wastewater treatment plants (WWTP) is a challenging problem. In this paper, an adaptive online monitoring approach that is based on long short term memory (LSTM) neural network is proposed to estimate the bacterial concentration, mixed liquor suspended solids (MLSS) and mixed liquor volatile suspended solids (MLVSS) in WWTP. Due to the lack of a large dataset and difficulties in measuring quality variables, a Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is designed to generate synthetic data for training. Tuned hyperparameters are obtained for the proposed method. In addition, the performance is compared with the traditional LSTM using two datasets. Finally, the results indicate that WGAN successfully generates realistic training samples and quality variables are monitored with satisfactory performance.