基于修正JC模型和BP-ANN算法预测HNi55-7-4-2合金高温流变行为的对比

采用Gleeble-3500型热模拟试验机,分别在变形温度为873,923,973,1023,1073 K,应变速率为0.01,0.1,1,10 s^-1条件下对HNi55-7-4-2合金进行等温热压缩试验,研究了该合金的高温流变行为;基于试验数据,分别采用修正Johnson-Cook(M-JC)模型和反向传播人工神经网络(BP-ANN)算法构建本构模型,对比分析这2个模型的预测精度。结果表明:HNi55-7-4-2合金的流变应力随着应变速率的增加而增大,随着变形温度的升高而降低。基于M-JC模型和BP-ANN算法建立的本构模型预测得到真应力与试验结果间的平均相对误差绝对值分别为14.63%%,0.35%%,相关系数分别为0.9787,0.9999;基于BP-ANN算法的本构模型的预测精度更高,可以较好地描述H Ni55-7-4-2合金的高温流变行为。

Comparison on High-Temperature Flow Behavior of HNi55-7-4-2 Alloy Predicted by Modified JC Model and BP-ANN Algorithm

Isothermal hot compression experiments of HNi55-7-4-2 alloy were conducted with a Gleeble-3500 thermal simulator at deformation temperatures of 873,923,973,1023,1073 K and strain rates of 0.01,0.1,1,10 s-1,and the high-temperature flow behavior of the alloy was studied.The constitutive model of the alloy was established by the modified Johnson-Cook(M-JC)model and back-propagational artificial neural network(BPANN)algorithm with experimental data.The prediction accuracy of two models was comparatively analyzed.The results show that the flow stress of HNi55-7-4-2 alloy increased with increasing strain rate or decreasing deformation temperature.The average absolute relative errors between true stress predicted by the constitutive model on the basis of M-JC and BP-ANN algorithm model and test results were 14.63% and 0.35%,respectively and the correlation coefficient were 0.9787,0.9999,respectively.The constitutive model by BP-ANN algorithm had higher prediction accuracy,and could decribe the high-temperature flow behavior of HNi55-7-4-2 alloy well.