A Prediction Method for Floor Water Inrush Based on Chaotic Fruit Fly Optimization Algorithm–Generalized Regression Neural Network

The research was aimed at predicting floor water-inrush risk in coal mines and forewarn of such accidents to guide safe production practice. To this end, a prediction method for water inrush combining the chaotic fruit fly optimization algorithm (CFOA) generalized regression neural network (GRNN) is proposed. Floor predicted by virtue robust nonlinear mapping capability GRNN. However, because effect GRNN influenced smoothing factor, CFOA adopted optimize factor. In way, influences human factors during parameter determination model are decreased, accuracy applicability improved. Results show that CFOA–GRNN has an 93.2% whether will occur or not. Compared with BPNN, RNN, GRU model, superior generalization, it can more accurately predict inrush.