Fuzzy Comprehensive Evaluation Of Operating State Of Electrocoagulation Purification Process For Treating Heavy Metal Wastewater

Electrocoagulation purification has become an important method for the deep purification of heavy metal wastewater,because it has the characteristics of good treatment effect,green,pollution is low or even zero,etc.However,the electrocoagulation purification process has the problem of passivation of the electrode plates of the reactor,which gradually reduces the removal capacity of the reactor.The removal rate of the electrocoagulation reactor has become an important indicator reflecting the operating state of the process.Due to the lag of mass transfer and complete the electrocoagulation reaction,the field operators is difficult to obtain outlet feedback information in real time,and cannot evaluate the operating state of the system according to the reactor removal rate and the multi-affected factor,resulting in a lack of basis for plates replacement and voltage adjustment,which leads to the power consumption and the plates consumption of the whole process is serious.Therefore,this paper studies the fuzzy comprehensive evaluation method of the operating state of the electrocoagulation purification process for treating heavy metal wastewater,which lays the foundation for the realization of the production goals of high quality and low energy consumption in wastewater treatment.The main work and innovations of this paper are as follows:(1)Aiming at the problem that the removal rate of reactor cannot be obtained in real time due to the lag of outlet feedback information,a method for predicting the removal rate of electrocoagulation reactor based on the combination of deep learning Long and Short-Term Memory(LSTM)network and Autoregressive Integrated Moving Average Model(ARIMA)is proposed.In order to improve the LSTM model’s ability to analyze and learn the change trend of historical data,the historical value of the removal rate gradient is used as the input variable of the model,and the prediction model of electrocoagulation reactor removal rate based on LSTM is established.On this basis,the ARIMA model is used to compensate the error of the predicted value of reactor removal rate obtained by the LSTM model to improve the accuracy of the prediction.The industrial operating data verification shows that the RMSE of predicted value obtained by the proposed method is reduced by 22%and50%respectively compared with the single LSTM model and the ARIMA model,the R~2 coefficient increased by 0.02 and 0.148 respectively.(2)The operating state of electrocoagulation purification process is difficult to be divided and there are many affects factors related to the removal rate,which results in an incorrect state evaluation.Thus,a fuzzy comprehensive evaluation method for the operating state of electrocoagulation purification process based on sliding window is proposed.The prediction results of the removal rate based on the LSTM-ARIMA method,as well as the wastewater flow rate,current and voltage,etc.,are used as state evaluation indicators.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,so as to determine the current deterioration degree of each evaluation indicator.Then,the weight of each evaluation indicator is determined based on the grey relational analysis method and variable weight theory.Finally,the membership function is established based on the determined deterioration degree,and the fuzzy comprehensive evaluation matrix is constructed to synthesize the weights of each indicator,so as to evaluate the operating state of the electrocoagulation purification process for treating heavy metal wastewater.The simulation results show that the proposed state evaluation method can accurately reflect the operating state of the electrocoagulation purification process for treating heavy metal wastewater.