Moisture content prediction of municipal sludge drying process based on genetic algorithm optimized BP neural network

Abstract

Municipal sludge drying process of internal moisture detection difficulties, and in order to predict the change rule of the internal moisture in the hot-air drying process of municipal sludge, the moisture change of municipal sludge under different drying conditions was monitored through experiments. The moisture prediction model of municipal sludge drying process was established by optimizing the BP neural network using mathematical model, back-propagation (BP) neural network and genetic algorithm (GA), and the performance analysis of the model was carried out. In addition, a sensitivity analysis of the GA-BP model was performed. The results showed that the temperature had the most significant effect on the drying process of municipal sludge, reducing the thickness of the mud layer could improve the drying rate of sludge, and the moisture reduction rate of municipal sludge showed a fast and then a slow trend during the whole drying process. Through the performance analysis, the coefficient of determination of the test set of GA-BP model is 0.9999, and the root mean square error is only 0.0039, which means that the GA-BP model has a better prediction effect and can predict the dynamic change of moisture in the drying process of municipal sludge more accurately. The sensitivity analysis shows that the drying time and drying temperature have the greatest influence on moisture ratio(MR), and the results of the study can provide a theoretical basis for the optimization of the sludge drying process and procedure, and provide a powerful reference for guiding the resource utilization of sludge.