Application Research of BP Neural Network Optimized by Genetic Algorithm and Particle Swarm Optimization Algorithm in MBR Simulation

Membrane bio-reactor (MBR) is one of the mainstream technologies of modern wasted-water treatment, but membrane fouling is a key factor which restricts the development of MBR. The formation of membrane fouling directly leads to a decrease in membrane flux. One of the important parameters to measure membrane fouling, membrane flux is the focus and difficulties of membrane fouling research. In this paper, the BP neural network is used to simulate and predict the MBR membrane flux, and the traditional BP neural network has the disadvantages of local extremum and generalization ability, which combines with particle swarm optimization (PSO) and genetic algorithm (GA) to improve global search ability, strong and fast convergence, etc. This method can help optimize and adjust the weight and threshold of traditional BP neural network. Through the analysis of the PSO-GA-BP neural network prediction results and comparing with the experimental data, the results show that the PSO-GA-BP neural network prediction model has better prediction results for MBR membrane flux than the traditional BP neural network prediction model and it has also higher precision.