基于工艺参数的7005铝合金力学性能的支持向量回归预测

根据7005铝合金在不同工艺参数(挤压温度、挤压速度、淬火方式和时效条件)下的力学性能(抗拉强度σ_b、屈服强度σ_(0.2)和硬度HB)实测数据集,应用基于粒子群算法(PSO)寻优的支持向量回归(SVR)结合留一交叉验证(LOOCV)的方法,对7005铝合金力学性能进行建模和预测研究,并与偏最小二乘法(PLS)、反向传播人工神经网络(BPNN)和两者结合的PLS-BPNN模型的预测结果进行比较.结果表明:基于SVR-LOOCV法的预测精度最高,对3种力学性能(σ_b、σ_(0.2)和HB)预测的均方根误差(RMSE)分别为4.531 9 MPa、14.550 8 MPa和HB1.414 2,其平均相对误差(MRE)分别为0.72%、2.61%和0.66%,均比PLS、BPNN和PLS-BPNN方法预测的RMSE和MRE要小.

Quantitative prediction of mechanical properties of 7005 Al alloys from processing parameters via support vector regression

The support vector regression (SVR) approach based on the particle swarm optimization (PSO) for its parameter optimization, combined with leave-one-out cross validation (LOOCV), was proposed to predict the mechanical properties (tensile strength σ_b, yield strength σ_(0.2) and hardness HB) of 7005 Al alloys under different processing parameters including extrusion temperature, extrusion velocity, quenching type and aging time. The results strongly support that the prediction precision of SVR-LOOCV method is superior to those of partial least squares (PLS), back-propagation neural networks (BPNN) and their combination PLS-BPNN model by applying the identical dataset. The root mean square errors (RMSE) for σ_b, σ_(0.2) and HB achieved by SVR-LOOCV are 4.531 9 MPa, 14.550 8 MPa and HB 1.414 2, respectively, and their mean relative errors (MRE) are 0.72%, 2.61% and 0.66%, respectively, which are less than those predicted by PLS, BPNN or PLS-BPNN approach.