基于BP神经网络模型的螺纹钢性能与元素含量关系的研究  

Research on Dependence of Rebar Performance and Element Content Based on BP Neural Network Model

作　　者：瞿云华 常锦才 张玉柱 QU Yunhua;CHANG Jincai;ZHANG Yuzhu(School of Metallurgy,Northeastern University,Shenyang 110819,China;Qian'an College,North China University of Technology,Qian'an 064403,China;School of Science,North China University of Technology,Tangshan 063000,China;School of Metallurgy,North China University of Technology,Tangshan 063000,China)

机构地区：[1]东北大学冶金学院,辽宁沈阳110819 [2]华北理工大学迁安学院,河北唐山064403 [3]华北理工大学理学院,河北唐山063000 [4]华北理工大学冶金学院,河北唐山063000

出　　处：《铸造技术》2018年第12期2664-2667,共4页Foundry Technology

基　　金：河北省钢铁联合基金(E2016209304)资助项目

摘　　要：利用BP神经网络研究了热轧螺纹钢的各种微量元素与力学性能的关系,探究各个微量元素含量比例,优化热轧带肋钢筋性能,再将其数值分析结果指导生产实践。结果表明,BP神经网络模型预测的螺纹钢抗拉强度数据值与实际值误差约为6%。The BP neural network was used to study the various trace elements and mechanical properties of hot rolled deformed rebar, exploring various trace elements, the performance optimization of hot rolled rebar, then the numerical analysis results were applied to guide the production practice. The results show that the BP neural network model to predict the rebar tensile strength data value and the actual value error is about 6%.

关 键 词：BP神经网络 螺纹钢性能 螺纹钢组成元素 数值计算与模拟 

分 类 号：TG113[金属学及工艺—物理冶金]