Stability Classification Of The Bp Neural Network Model Study

Surrounding rock stability analysis and evaluation are the important problem in rock mass engineering. Since the new mathematical tools and computational technique are accessible, the rock mass stability classsification, an old and effective evalution method, has been developed rapidly. By using the artificial neural network method, which can deal with nonlinear problem, a systematic surrounding rock stability classfication evaluation method is constructed in this paper. The main work of the paper is as follows:1. Because the classification indexes is difficult to determine in a specific engineering surrounding rock clsssification, the multiple layer feedforward neural network is used to determine the classification indexes through computating the node contribution rates of input layer and it's related formulas are also deduced in this paper.2. Since the convergence rate of the BP network is slow and node structure of it's hide layer is difficult to determine, an improvement of the BP network algorithm and a method to determine the node structure of the hide layer are suggested in this paper.3. As the OOP has become a pop method, the object oriented BP artificial neural network design is realized and the BP Network System of Surrounding Rock Stability Classification is also constructed.4. By using the realized system, the paper makes an evalution on the engineering of GuangZhou Pumped- storage power station and the result suggests that the artificial neural network method has great advantage in the data analysis of geological engineering comparing other methods.