末端深度计算的人工神经网络模型

Q2 Engineering

Tumu yu Huanjing Gongcheng Xuebao/Journal of Civil and Environmental Engineering Pub Date : 2018-01-01 DOI:10.4172/2165-784X.1000316

A. Mohammed

{"title":"末端深度计算的人工神经网络模型","authors":"A. Mohammed","doi":"10.4172/2165-784X.1000316","DOIUrl":null,"url":null,"abstract":"In this paper a feed-forward back-propagation type of neural network as well as the multi nonlinear regression model using statistical programming were used to determine the critical depth and discharge passing over the enddepth model, free overfall. This was achieved by training and validating (215) experimental data. The results of the trained verified and tested for neural network model are compared to the experimental measurements. There were well agreements with the measured values.","PeriodicalId":52256,"journal":{"name":"Tumu yu Huanjing Gongcheng Xuebao/Journal of Civil and Environmental Engineering","volume":"4 1","pages":"1-5"},"PeriodicalIF":0.0000,"publicationDate":"2018-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Artificial Neural Network (ANN) Model for End Depth Computations\",\"authors\":\"A. Mohammed\",\"doi\":\"10.4172/2165-784X.1000316\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper a feed-forward back-propagation type of neural network as well as the multi nonlinear regression model using statistical programming were used to determine the critical depth and discharge passing over the enddepth model, free overfall. This was achieved by training and validating (215) experimental data. The results of the trained verified and tested for neural network model are compared to the experimental measurements. There were well agreements with the measured values.\",\"PeriodicalId\":52256,\"journal\":{\"name\":\"Tumu yu Huanjing Gongcheng Xuebao/Journal of Civil and Environmental Engineering\",\"volume\":\"4 1\",\"pages\":\"1-5\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Tumu yu Huanjing Gongcheng Xuebao/Journal of Civil and Environmental Engineering\",\"FirstCategoryId\":\"1087\",\"ListUrlMain\":\"https://doi.org/10.4172/2165-784X.1000316\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"Engineering\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tumu yu Huanjing Gongcheng Xuebao/Journal of Civil and Environmental Engineering","FirstCategoryId":"1087","ListUrlMain":"https://doi.org/10.4172/2165-784X.1000316","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Engineering","Score":null,"Total":0}

引用次数: 2

摘要

本文采用前馈反向传播型神经网络和基于统计规划的多元非线性回归模型来确定临界深度和流量越过终点深度模型——自由溢流。这是通过训练和验证(215)实验数据实现的。将神经网络模型的训练验证和测试结果与实验测量结果进行了比较。与实测值吻合较好。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Artificial Neural Network (ANN) Model for End Depth Computations

In this paper a feed-forward back-propagation type of neural network as well as the multi nonlinear regression model using statistical programming were used to determine the critical depth and discharge passing over the enddepth model, free overfall. This was achieved by training and validating (215) experimental data. The results of the trained verified and tested for neural network model are compared to the experimental measurements. There were well agreements with the measured values.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Tumu yu Huanjing Gongcheng Xuebao/Journal of Civil and Environmental Engineering Engineering-Architecture

CiteScore

1.30

自引率

0.00%

发文量

5346