Self-organizing modeling and control of activated sludge process based on fuzzy neural network

The wastewater treatment process contains multiple complex biochemical reactions featured by strong nonlinear and time-varying dynamics due to the built-in discontinuity and uncertainty. Herein, a self-organizing fuzzy neural network with an efficient scheme for parsimonious (SOFNN-ESP) was orchestrated to improve the selforganizing modeling of municipal wastewater treatment process by combing predictive algorithms to deal with the complex water treatment procedure. The SOFNN-ESP algorithm could identify sewage treatment plants by a high-throughput parameter screening system and recursive least square method in real-time, which provided dynamic setting feedback and promoted water quality. The integration of the SOFNN-ESP algorithm and a model predictive control (MPC) further improved the accuracy in water quality controlling via immediately adjusting weight parameters of the network. This gradient algorithm also realized the online dynamic tracking of dissolved oxygen and nitrate nitrogen level by simultaneous tracking of multiple performance indicators and optimizing setting values of the control variable. SOFNN-ESP-MPC gave an error of <5 % when the peak error of proportional integral differential controller was >10 %. Concerning the benchmark simulation model No.1 of municipal wastewater treatment, the SOFNN-ESP-MPC method exhibited a compact network structure and outstanding generalization performance. The self-organizing modeling and predictive control strategy proposed in this study could effectively improve the prediction accuracy and control efficiency of the activated sludge process model, which is of great significance for the efficiency improvement of sewage treatment process.

Automated summary

In this study, a self-organizing fuzzy neural network combined with predictive algorithms was used to improve the modeling and control of municipal wastewater treatment process. It could identify sewage treatment plants in real-time and provide dynamic feedback to improve water quality. The integration with model predictive control further enhanced the accuracy and efficiency of the control process. This research is of great significance for improving the efficiency of sewage treatment process.