Visual prediction of gas diffusion concentration based on regression analysis and BP neural network

Abstract

In order to realise the prediction of the diffusion trend of chemical gases under toxic, flammable, and explosive conditions, this article used a multiple regression model and a back propagation (BP) neural network model, established two kinds of leakage gas diffusion models based on Fluent simulation data. First, the multivariate function relation between multiple influencing factors and diffusion concentration is established by using linear fitting method, i.e. multivariate regression model. Second, according to the large number and non-linearity of Fluent simulation data of leakage gas, a three-layer BP neural network prediction model for leakage gas, wind speed, X-axis diffusion distance, and Y-axis diffusion distance was established by using BP neural network algorithm. Under the same data conditions, the prediction error of BP neural network prediction model is smaller than that of multivariate reversion model, and the fitting degree is high, but the stability of multiple linear regression is better.