摘要
Aiming at the complex lithology of volcanic rocks and the great difficulty in lithologic identification, the lithologic identification of volcanic rocks is conducted through the application of rough set neural network system and log information. First, the log information is optimized and reduced according to the Rough Set. And then a sample set is established by applying the optimized information. The result of the lithologic identification of volcanic rocks through the application of the characteristic parameters and trained BP neural network shows that this method has the advantage of being quick and steady with the relatively high identification accuracy.