论文部分内容阅读
针对单一具体的数学方程式模型难以准确描述9Ni钢材料整个热塑性加工过程中材料对外部参数的力学响应问题,在9Ni钢热模拟试验机压缩试验数据基础上,采用新的果蝇算法(Fruit Fly Optimization Algorithm FOA)对最小二乘支持向量机(LSSVM)模型惩罚因子c和核宽度λ进行寻优,构造了FOA-LSSVM混合优化的9Ni钢本构模型。模型预测值与实验值的对比结果表明:FOA-LSSVM9Ni钢本构模型具有良好的拟合性,能反映9Ni钢热加工过程中各个阶段的流变行为,其预测值与实验值之间的最大、最小、平均绝对百分比误差分别为6.21%、0.19%和2.64%;模型具有很高的预测精度和鲁棒性,可描述9Ni钢的高温流变力学行为。
Aiming at a single specific mathematical equation model, it is difficult to accurately describe the mechanical response of the 9Ni steel material to the external parameters during the entire thermoplastic processing. On the basis of the compression test data of the 9Ni steel thermal simulation testing machine, a new Fruit Fly Optimization Algorithm FOA) to optimize the penalty factor c and the kernel width λ of least squares support vector machine (LSSVM) model, a FOA-LSSVM hybrid optimized 9Ni steel constitutive model is constructed. The results of the model predictions and the experimental results show that the FOA-LSSVM9Ni steel constitutive model has a good fit, and can reflect the rheological behavior of the 9Ni steel during the hot working process. The predicted value is the largest between the experimental values , The minimum and average absolute percentage errors are 6.21%, 0.19% and 2.64%, respectively. The model has high prediction accuracy and robustness, and can describe the high temperature rheological behavior of 9Ni steel.