Rock Mass Classification by Use of Neural Network Learning
Feng Xiating,Wang Lina
An attempt is made to find a new way for better classification of rock masses--applying the neuralnetwork theory to such a classification. Learning from a given sample set. the neural network is used to establish a nonlinear mapping between various geologic/engineering factors and an equivalent class of rock mass. It is proved that the network and values of weight after learning are available to the identification of equivalent class for a new type of rock mass. Mainly,the knowledge learning and adaptive pattern recognition in rock mass classification to be performed are discussed with thier application results given.