基于改进BP网络在复杂岩体质量分类中的应用  

Application of Quality Classification of Complicated Rockmass Based on Improved BP Neural Network

作　　者：陈丽亚 肖猛[2] 张喜娥[2] 

机构地区：[1]浙江振丰建设有限公司,杭州310006 [2]南华大学,衡阳421001

出　　处：《国外建材科技》2007年第4期114-117,共4页Science and Technology of Overseas Building Materials

摘　　要：在综合分析评价岩体质量指标的基础上,提出了神经网络在岩体质量分的应用。介绍了采用BP神经网络方法对复杂岩体进行质量分类的工程实例。工程实际应用表明,经过优化的BP神经网络经过多次学习后,测试精度提高,结果可靠,取得了较好的实际应用效果。Based on comprehensively analysis of the evaluating indices of rock mass quality, the application of neural network in the quality classification of rock mass is pointed out. The paper applies the method of the improved BP neural network on a hydraulic power station on the Lancang River, Yunnan Province, choosing six influential factors on the rock mass quality as the input variables, such as one axis compressive strength of rock, sound degree coefficient of rock mass,the joint number of bulk, roughness degree coefficient of joint surface, alteration coefficient of joint surface, permeability coefficient, and classifies the complicated rock mass on the right bank of the dam foundation. The practical application shows that the test result is exact and credible after many a time training of this network. The application has gained a good effect.

关 键 词：人工神经网络 岩体质量 分类 

分 类 号：TU451[建筑科学—岩土工程]