基于BP神经网络的DSS焊接应力和收缩变形预测研究  

Prediction of DSS Welding Stress and Shrinkage Deformation Based on BP Neural Network

作　　者：王正伦[1] 王智祥[2] 张鑫[1] 

机构地区：[1]重庆交通大学机电与汽车工程学院,重庆400074 [2]重庆交通大学船舶工程中心,重庆400074

出　　处：《重庆交通大学学报（自然科学版）》2010年第5期832-836,共5页Journal of Chongqing Jiaotong University(Natural Science)

基　　金：重庆市科委重大科技攻关项目(CSTC2008AB3033)

摘　　要：针对川东造船厂化学品船建造中使用特种钢——2205双相不锈钢(DSS),在其焊接试验的基础上分别建立了双相不锈钢焊接应力和收缩变形的BP神经网络预测模型,并与多元线性回归方法进行比较,较好地模拟了焊接残余应力和变形与板厚、焊接电流、电弧电压、焊接速度等工艺参数之间的非线性关系。预测结果表明,BP神经网络比多元线性回归在预测精度和泛化能力上都有很大的提高。With regard to the 2205 duplex stainless steel which is used for special shipbuilding in Chuandong Shipyard,BP neural network forecast models on welding residual stress and shrinkage deformation of 2205 duplex stainless steel（DSS） have been respectively established,on the basis of the welding experiment of 2205 duplex stainless steel.The proposed forecast model is compared with the multiple linear regression method.The comparison indicates that the proposed forecast model can better simulate the non-linear relationships of welding residual stress and deformation between the process parameters,such as thickness,welding current,arc voltage and welding speed.The forecast results show that BP neural network is more advantageous both in the prediction accuracy and generalization capability than the multiple linear regression method.

关 键 词：神经网络 双相不锈钢 焊接 残余应力 预测 

分 类 号：TG451[金属学及工艺—焊接] TP18[自动化与计算机技术—控制理论与控制工程]