Rock burst forecasting in deep mine based on new bionics clustering algorithm

Rock burst is one big dynamic disaster in deep mine. For the influence factors of rock burst are numerous and their relationship is very complicated, it´s forecasting is a very hard work, so generally based on engineering analogy and geology analysis, the clustering methods are used in rock burst forecasting field. For the complicated environment influence of rock burst, this clustering problem is a very complicated fuzzy and random optimization problem, and can not be solved by traditional methods very well. So, here the new bionics clustering algorithm-Ant Colony Clustering Algorithm which is proposed recently has been introduced into rock burst forecasting field for the first time. Based on this new bionics clustering algorithm, one new method for study forecasting of rock burst is proposed. Based on analyzing the data of rock burst samples, from the engineering analogy thinking by ant colony clustering algorithm, the rock burst can be forecasted. At last, some real engineering examples are used to verify calculating effect of the new algorithm. The engineering applications can prove that, this new algorithm can automatically sort the rock burst samples, and the validity is very high, the computing velocity is very rapidly, so it is a very practical method for rock burst forecasting, and should be popularized.