基于神经网络的节理岩体单轴强度预测  

Jointed Rock Uniaxial Strength Prediction Based on Neural Network

作　　者：胡安龙[1] 王孔伟[1] 邓华锋[1] 常德龙[1] 肖志勇[1] 李春波[1] 

机构地区：[1]三峡大学三峡库区地质灾害教育部重点实验室,湖北宜昌443002

出　　处：《人民黄河》2016年第3期108-111,共4页Yellow River

基　　金：国家自然科学基金资助项目(51309141;51279091);水利部公益性科研专项(201401029);三峡大学研究生科研创新基金资助项目(2015CX036)

摘　　要：基于RMT-150C岩石力学试验系统上的节理岩体单轴压缩试验结果,分析了影响节理岩体单轴压缩强度的因素。节理岩体的单轴压缩强度与节理贯通度、节理倾角、节理个数等因素有关,且是一种复杂的非线性关系。同一贯通度节理岩体在节理倾角为0°时峰值强度最大;同一节理倾角岩体的峰值强度随着贯通度的增大而减小。考虑到多种因素对节理岩体单轴压缩强度的影响,建立了BP神经网络模型,对节理岩体的单轴压缩强度进行预测,然后利用遗传算法优化BP神经网络模型。通过岩石单轴压缩试验样本数据的学习,遗传算法优化的神经网络模型能够很好地预测节理岩体的单轴压缩强度。Based on the uniaxial compression test results of jointed rock on RMT?150C rock mechanics test system, the factors influencing uniaxial compressive strength of joint rock had been analyzed. The uniaxial compressive strength of joint rock was related to joint continuity, joint angle and joint number and it's a complex nonlinear relationship. The peak strength of jointed rocks with same joint continuity reached to the highest value as joint angle is 0, the peak strength of jointed rocks with same joint angle decreased with the increase of joint continuity. Considering the influence of various factors on joint rock uniaxial compressive strength, the BP neural net model had been build to predict uniaxial compressive strength of joint rock and optimized by genetic algorithm. Through studying and fitting the sample data of rock uniaxial compression test, the uniaxial compressive strength of joint rock could be predicted well by BP neural net model optimized by genetic algorithm.

关 键 词：节理岩体 遗传算法 BP神经网络 单轴压缩强度 

分 类 号：TU458[建筑科学—岩土工程] TU459.1[建筑科学—土工工程]