%0 Journal Article
%T STUDY ON GENETIC NEURAL NETWORK METHOD OF DISPLACEMENT BACK ANALYSIS<br>位移反分析的进化神经网络方法研究
%A Feng Xiating
%A Zhang Zhiqiang Yang Chengxiang Lin Yunmei
%A <br>冯夏庭
%A 张治强
%A 杨成祥
%J 岩石力学与工程学报
%D 1999
%I 
%X An evolutionary neural network method for displacement back analysis is proposed by combining the neural network and genetic algorithm. The samples produced in orthogonal experiment are used to train the neural network whose architecture is determined in global optimum by genetic algorithm. Thus, the neural network with optimal architecture trained by optimal prediction algorithm is used to describe the relationship between the rock mechanical parameters and displacements produced due to excavation. Then genetic algorithm is adopted again to search the optimal rock mechanical parameters in their global ranges. As an example, a back analysis for elastic problem is introduced. The results are satisfactory.
%K displacement
%K back analysis
%K genetic algorithm
%K neural network<br>位移
%K 反分析
%K 遗传算法
%K 神经网络
%K 岩体
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=D3421FAA1A0A0F0C&jid=35E747D791A1346351AFB523B7FA35CB&aid=AC96AD79572CD8D9D41119018C86D8B0&yid=B914830F5B1D1078&vid=13553B2D12F347E8&iid=94C357A881DFC066&sid=2A2AA8B7E19F0DF7&eid=FF58680609C9D068&journal_id=1000-6915&journal_name=岩石力学与工程学报&referenced_num=100&reference_num=15