Prediction model of spontaneous combustion risk of extraction borehole based on PSO-BPNN and its application

PSO-BPNN model prediction results

The Matlab is used to establish a PSO-BPNN model with allowable error of 0.00001, the maximum number of particle iterations of 50, all learning factors of 2, inertial factor of 0.6 and maximum flying velocity of particles of 0.8. The results of training and prediction are shown in Figs. 5, 6 and Table 3. The comparison between prediction values and real values of PSO-BPNN model is shown in Table 3. From Table 3, the relative error of the predicted values and real values ranges from 0.35 to 13.65% with a difference of 13.30% and an average relative error…