Modeling and Simulation of Chemical Machinery Performance Based on GA-Bp Algorithm

The existing performance modeling methods based on physical models usually require a large number of theoretical parameters, and the modeling process is complicated, which is difficult to meet the needs of engineering practice. To this end, this paper proposes a chemical machinery performance modeling method based on genetic algorithm-back propagation neural network (GA-BP). Firstly, genetic algorithm (GA) is used to optimize the network parameters of the back propagation neural network (BP) to improve the fitting accuracy of the model. On this basis, the key performance parameters of chemical machinery and equipment were modeled using actual operation data. The established GA-BP model can effectively portray the dynamic characteristics of the equipment under various working conditions. The simulation experiments show that the actual values range from 0.51 to 0.89, and the simulated values range from 0.54 to 0.91. There is some deviation between the actual and simulated values and the graphs, but the overall trend is consistent.