YANGCun-man,JUJia-wei,YUAN Fang,et al.Research on Intelligent Disinfection Prediction Model of Waterworks Based on PSO-BP Neural Network[J].China Water & Wastewater,2022,38(No.3):57-61.
Research on Intelligent Disinfection Prediction Model of Waterworks Based on PSO-BP Neural Network
China Water & Wastewater[ISSN:1000-4062/CN:12-1073/TU]
volume:
第38卷
Number:
No.第3
Page:
57-61
Column:
Date of publication:
2022-02-01
- Keywords:
- waterworks; chlorination; PSO-BP neural network; BP neural network; prediction
- Abstract:
- In order to solve the problem of rough and empirical dosing of chlorination disinfectant in the operation of waterworks, an intelligent disinfection prediction model of waterworks based on PSO-BP neural network was established. The flow, alum consumption and water quality parameters were selected as the input parameters of the prediction model, and the neural network weight and threshold were optimized by particle swarm optimization algorithm. The average absolute percentage error (MAPE) and root mean square error (RMSE) of the evaluation indexes of the model were lower than those of the traditional BP neural network model, particularly RMSE decreased by 207 kg, MAPE decreased by 1.80%, and relative standard deviation (RSD) decreased by 2.4%, which could effectively improve the accuracy and stability of the model prediction. In the process of practical application, it was helpful to reduce the consumption of chlorination disinfectant and the production cost could be saved by 1 756 yuan/d, averagely. It can be seen that the PSO-BP intelligent disinfection prediction model is reasonable and feasible, which provides a simple and feasible idea and method for the prediction of chlorine addition in the disinfection system of urban waterworks.
Last Update:
2022-02-01