Fuzzy comprehensive evaluation strategy for operating state of electrocoagulation purification process based on sliding window

Abstract

In the process of electrocoagulation purification, there is a problem of passivation of the reactor electrode plates, and the process operating state is constantly changing, which badly affects the efficiency of electrocoagulation purification and the removal of heavy metal ion. However, in order to ensure that the concentration of heavy metal ion at the electrocoagulation outlet reaches the standard, the operators often replace the plates in advance or turn up the voltage to the maximum, resulting in increased power consumption and plates consumption. In order to solve this problem, this paper proposes a fuzzy comprehensive evaluation strategy for operating state of electrocoagulation purification process based on sliding window. Firstly, based on the combination of the Long and Short-Term Memory (LSTM) network and Autoregressive Integrated Moving Average Model (ARIMA), the predicted value of the removal rate of heavy metal ion in the electrocoagulation purification process is obtained. The predicted value and other important factors influencing the purification effect are used as the operating state evaluation indicators of the electrocoagulation purification process, and the operating state evaluation grade is divided according to the fuzzy rules. Secondly, the boxplot method is used to determine the threshold of each evaluation indicator, and the average value of the data of each indicator in each time window is calculated in real-time based on the sliding window. The current deterioration degree of each evaluation indicator is determined by the average value and the indicator threshold. Then, the basic weight of each evaluation indicator is calculated based on the grey relational analysis method, and the final weight of each indicator is determined according to the variable weight theory combined with the deterioration degree of each indicator. Finally, according to the fuzzy theory, the fuzzy comprehensive evaluation matrix is constructed by establishing the membership function, so as to evaluate the operating state of the electrocoagulation purification process. The effectiveness of the proposed evaluation strategy is verified by the industrial data collected from a wastewater treatment plant.