The theory studies have showed that, rock burst is a kind of dynamic phenomenon of rock mass in mining, and is a kind of dynamic disaster from mining. The time series of magnitude is a very important exterior behavior of rock burst. The previous studies show that, to model this complicated non-linear time series, the neural network is a very good method. To overcome the shortcomings of traditional neural network, a new kind of evolutionary neural network based on immunized evolutionary programming proposed by author is proposed here. At last, the proposed evolutionary neural network model is verified by a real magnitude series of rock burst. And the result is compared with other method, such as grey system method. The results have showed that, evolutionary neural network model not only has high approaching precision, but also has high predicting precision, and is a good method to construct the non-linear model of rock burst. And this method can be used in a large number of engineering examples.
Application of fuzzy neural network in predicting the risk of rock burst
