基于BP算法的岩石细观参数确定方法  

Rock Mesoscopic Parameter Determination Method Based on BPAlgorithm

作　　者：李搏凯 于贵 李星 LI Bokai;YU Gui;LI Xing(School of Civil Engineering Southwest Jiaotong University,Chengdu 610031,China;China Railway Academy Co.,Ltd.,Chendu 610036,China)

机构地区：[1]西南交通大学土木工程学院,四川成都610031 [2]中铁科学研究院有限公司,四川成都610036

出　　处：《河南科技》2024年第10期55-59,共5页Henan Science and Technology

基　　金：国家自然科学基金资助项目(51178402)。

摘　　要：【目的】采用PFC进行岩石破坏机理的仿真研究是较为常见的,而颗粒流模型所用细观参数的合理性直接影响着数值仿真结果,因此针对PFC细观参数的种类繁多、影响复杂、分析困难等问题,在基本宏观参数的基础上,以精确预测模型细观参数为目标,提出一种基于BP算法智能化预测的方法。【方法】通过PFC进行数值仿真试验,获取足够量的数据样本,结合数据样本和BP算法建立神经网络预测模型,并根据实际岩石宏观参数得到PFC细观参数预测值。【结果】经对比分析3种不同岩石试件宏观参数的真实值与反算值,发现两者间相对误差均较小。【结论】所述方法具有合理性和可行性,能用于快速确定PFC的各类细观参数。[Purposes]It was very common to use PFC to simulate the rock failure mechanism,and the ra-tionality of the mesoscale parameters used in the particle flow model directly affected the numerical simulation results.Therefore,aiming at the problems such as the variety,complex influence and difficult analysis of program PFC meso-scale parameters,an intelligent prediction method based on BP algorithm was proposed to accurately predict model meso-scale parametric on the basis of accurate basic macro pa-rameters.[Methods]Sufficient data samples are obtained by PFC numerical simulation test.A neural network prediction model is established by combining the data samples and BP algorithm,and the pre-dicted values of PFC microparameters were obtained according to the input of actual meso-scale param-eters.[Findings]By comparing and analyzing the actual values and inverse values of the meso-scale pa-rameters of three different rock specimens,it is found that the relative errors between them are small.[Conclusions]The results show that the method is reasonable and feasible,and can be used to quickly determine various mesoscopic parameters of PFC.

关 键 词：程序PFC 细观参数 BP算法 

分 类 号：TU452[建筑科学—岩土工程]