Performance prediction of IS centrifugal pump based on improved BP neural network

Abstract

The improved BP neural network was applied to establish prediction models for rated flow and rated head separately, the neural network structures were 8-11-1 and 5-6-1 respectively. 123 sets of pump experimental data were organized as training samples, and the other 15 sets of data were used as test samples. The results show that the training of the two networks converges quickly, the predictive values of the two performance parameters have good consistency with the experimental values, and the average testing errors of rated flow and rated head are 4.2% and 4.7%, respectively. The neural network prediction models established are accurate and effective, meeting the requirements of engineering applications.