A Study on Modeling of Activated Sludge Process in Wastewater Treatment System Utilizing XAI(eXplainable AI)

In this paper, to solve the problem of model-based control due to data reliability in the sewage treatment system active sludge process, an explanable artificial intelligence (XAI, eXplainable AI) was applied to implement neural network model for dissolved oxygen in an active sludge process. By applying four reliable items of effluent water quality to explainable artificial intelligence techniques, the input water quality items of the model were determined. Among the explainable artificial intelligence techniques, in the technique using connection strength, the concept of GAN was used to divide it into positive and negative numbers and compete with each other. As a result, the performance of the model was maintained even though the input variables of the model were reduced from 6 to 5. The learning error and evaluation error of the final model were 0.13 and 0.20, respectively. In the case of the learning model, the error increased slightly in the evaluation model compared to the conventional method with 6 input variables, but this difference is almost meaningless in terms of the actual value of DO, so the proposed technique is much more efficient compared to reducing the input variables from 6 to 5. Copyright © The Korean Institute of Electrical Engineers.