Abstract:With the development of Deep Learning in the field of Artificial Intelligence, BP neural network algorithms are also widely used in research work in various industries, and gas emission prediction is a multi-dimensional, nonlinear, small-sample prediction problem. Aiming at the problem of mine gas emission prediction, this paper establishes a PSO-BP neural network algorithm model, collects 20 sets of sample data from some coal mine in Shanxi Province from 2017 to 2023, and uses 15 sets of them as training sets. Five sets of sample data were used for regression prediction of gas emission, and finally compared the mean absolute error, mean square error, root mean square error, mean absolute percentage error, and prediction accuracy of the PSO-BP neural network algorithm and the BP neural network algorithm. The results show that the gas emission prediction model based on the PSO-BP neural network algorithm has higher accuracy, can meet the actual needs of mine safety production, has better practicability and innovation, and provides a new model for other mines in gas emission. It provides some reference value for other mines in the direction of gas emission prediction.
