论文部分内容阅读
采用人工神经网络方法建立了锆基合金HANA-4(Zr-1.5Nb-0.4Sn-0.2Fe-0.1Cr)和HANA-6(Zr-1.1Nb-0.05Cu)回火参数与硬度的预测模型;利用所建立的网络模型预测不同回火态下材料的硬度。测试结果表明:最大相对误差绝对值是6.8869%,拟合率是0.9991。
The prediction models of tempering parameters and hardness of HANA-4 (Zr-1.5Nb-0.4Sn-0.2Fe-0.1Cr) and HANA-6 (Zr-1.1Nb-0.05Cu) alloys were established by artificial neural network The established network model is used to predict the hardness of materials under different tempering states. The test results show that the absolute value of maximum relative error is 6.8869% and the fitting rate is 0.9991.