首页 | 期刊介绍 | 编委会 | 道德声明 | 投稿指南 | 常用下载 | 过刊浏览 | In English
引用本文:李海涛,袁森.基于遗传算法和BP神经网络的海洋工程材料腐蚀预测研究[J].海洋科学,2020,44(10):33-38.
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  下载PDF阅读器  关闭
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 69次   下载 58 本文二维码信息
码上扫一扫!
分享到: 微信 更多
基于遗传算法和BP神经网络的海洋工程材料腐蚀预测研究
李海涛, 袁森
青岛科技大学信息科学与技术学院, 山东 青岛 266000
摘要:
为提高海洋工程材料腐蚀速率预测的精度,提出了一种基于遗传算法(GA)优化反向传播(Back Propagation,BP)神经网络的海洋工程材料海洋环境腐蚀速率预测模型。通过遗传算法对BP神经网络的权值和阈值进行优化,利用优化后的BP神经网络对试验数据进行预测。GA-BP模型选取具有代表性的2Cr1312不锈钢、Q235B碳钢和6082铝合金三种基本海洋工程材料数据进行试验,预测结果误差小于传统BP神经网络,并且在网络训练时间上有所缩短,预测精度上有所提高。本模型在海洋工程材料于海洋环境中腐蚀速率的实际预测中具有良好的推广价值。
关键词:  腐蚀速率预测  GA-BP模型  遗传算法  反向传播(Back Propagation,BP)神经网络
DOI:10.11759/hykx20191118003
分类号:TG172
基金项目:青岛市创新创业领军人才(15-07-03-0030);农业部水产养殖数字建设试点项目(2017-A2131-130209-K0104-004)
Corrosion prediction of marine engineering materials based on genetic algorithm and BP neural network
LI Hai-tao, YUAN Sen
College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266000, China
Abstract:
A model based on back propagation (BP) neural network optimized using a genetic algorithm (GA) was proposed to improve the accuracy of corrosion rate prediction of Marine engineering materials. The weights and thresholds of the BP neural network were optimized using the genetic algorithm, and the optimized BP neural network was used to predict the experimental data. The GA–BP model selected the representative data of 2Cr1312 stainless steel, Q235B carbon steel, and 6082 aluminum alloy as the basic Marine engineering materials for the experiment. The prediction results error was smaller than that of the standard BP neural network. The training time of the network was reduced, and the prediction accuracy increased. This model has good value in realistic prediction of corrosion rate of Marine engineering materials in Marine environment.
Key words:  corrosion rate prediction  GA-BP model  genetic algorithm  BP neural network
版权所有 《海洋科学》编辑部 Copyright©2008 All Rights Reserved
主管单位:中国科学院 主办单位:中国科学院海洋研究所
地址:青岛市南海路七号  邮编:266071  电话:0532-82898755  E-mail:marinesciences@qdio.ac.cn
技术支持:北京勤云科技发展有限公司