Study On Prediction Of Coal And Gas Outburst Based On SA-GA-FCM

In order to improve the accuracy of Fuzzy C-Means Clustering Algorithm (FCM) in prediction of coal and gas outburst, a method was putted forward. The method uses fuzzy C-means clustering that combines simulated annealing algorithm (SA) and genetic algorithm (GA) to predict coal and gas outburst. The method combines global search, High-precision advantages of simulated annealing algorithm and powerful search ability of space of genetic algorithm. Initial value that is optimized by the genetic simulated annealing algorithm is assigned to FCM. It avoids FCM algorithm convergence to local minima when the initial cluster center value is not improper selection. Principal component analysis method is used to analyze the influence factors of coal and gas outburst, the final choice of gas pressure, gas emission initial speed, coal solid coefficient and coal failure types of the four influencing factors to establish the forecasting index system. Combined the analysis of typical outburst mine data, the results show that only the two groups of errors and the difference is small, The method can be applied to the prediction of coal and gas outburst.10 sets of typical outburst coal mine data are selected and compared with the SA-GA-FCM based forecasting and single FCM algorithm, single index method, D and K comprehensive index method. The accuracy of forecast was 80%,70%,50%,60%, the results show that the accuracy of the forecast based on SA-GA-FCM is high, and the forecast results are good. Finally, the method for prediction of coal and gas outburst is used for Hongling coal mine, also achieved good prediction effect.