{"title":"基于改进BP神经网络的位移反分析","authors":"Zhang Guihua, Ma Xianmin, C. Jing","doi":"10.1109/CINC.2010.5643815","DOIUrl":null,"url":null,"abstract":"For the problems of the complex model and the slow speed in the process of the traditional back analysis of displacements, the program of BP neural network is compiled by the M language of MATLAB and is used for the back analysis of displacements. Aimed at the disadvantage of slow convergence of the traditional BP neural network, the method of adding coordinator to neural network and the normalization method are used to quicken the network training rate. The practically measured displacements are input to the trained BP network to obtain the correspondent mechanics parameters, which are then used as the calculation parameters of the finite element calculation, and the calculated displacement values are got. The difference between the calculated displacement values by the finite element analysis and the practically measured values is very slight and the maximum error doesn't exceed 5%. It shows that the method of artificial neural network is fast in model building and calculation, brief in model structure , and high in precision etc. It can be used for back analysis of displacements in engineering.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"75 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Improved BP neural network-based back analysis of displacements\",\"authors\":\"Zhang Guihua, Ma Xianmin, C. Jing\",\"doi\":\"10.1109/CINC.2010.5643815\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"For the problems of the complex model and the slow speed in the process of the traditional back analysis of displacements, the program of BP neural network is compiled by the M language of MATLAB and is used for the back analysis of displacements. Aimed at the disadvantage of slow convergence of the traditional BP neural network, the method of adding coordinator to neural network and the normalization method are used to quicken the network training rate. The practically measured displacements are input to the trained BP network to obtain the correspondent mechanics parameters, which are then used as the calculation parameters of the finite element calculation, and the calculated displacement values are got. The difference between the calculated displacement values by the finite element analysis and the practically measured values is very slight and the maximum error doesn't exceed 5%. It shows that the method of artificial neural network is fast in model building and calculation, brief in model structure , and high in precision etc. It can be used for back analysis of displacements in engineering.\",\"PeriodicalId\":227004,\"journal\":{\"name\":\"2010 Second International Conference on Computational Intelligence and Natural Computing\",\"volume\":\"75 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-11-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2010 Second International Conference on Computational Intelligence and Natural Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CINC.2010.5643815\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 Second International Conference on Computational Intelligence and Natural Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CINC.2010.5643815","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Improved BP neural network-based back analysis of displacements
For the problems of the complex model and the slow speed in the process of the traditional back analysis of displacements, the program of BP neural network is compiled by the M language of MATLAB and is used for the back analysis of displacements. Aimed at the disadvantage of slow convergence of the traditional BP neural network, the method of adding coordinator to neural network and the normalization method are used to quicken the network training rate. The practically measured displacements are input to the trained BP network to obtain the correspondent mechanics parameters, which are then used as the calculation parameters of the finite element calculation, and the calculated displacement values are got. The difference between the calculated displacement values by the finite element analysis and the practically measured values is very slight and the maximum error doesn't exceed 5%. It shows that the method of artificial neural network is fast in model building and calculation, brief in model structure , and high in precision etc. It can be used for back analysis of displacements in engineering.