论文部分内容阅读
提出了支持向量机(SVM)与遗传算法(GA)相结合的长轴类大锻件调质热处理工艺参数的优化方法。以热处理加热温度和保温时间为优化对象,以加热时间和最大残余应力为优化目标,对长轴类大锻件的热处理工艺进行了优化。以正交试验数据为样本,采用灰色关联度分析方法把多目标转换为单目标,通过SVM神经网络建立了优化目标的回归模型;采用遗传算法对模型进行了优化并获得了最优的工艺参数。结果表明:优化工艺相对于传统的调质工艺,加热时间减少了20%,最大残余应力下降了24%。
An optimization method of quenching and tempering heat treatment parameters of long shaft forgings was proposed by combining support vector machine (SVM) and genetic algorithm (GA). Taking the heating temperature and holding time as the optimization target, the heating time and the maximum residual stress are optimized targets, and the heat treatment process of the long axis heavy forging is optimized. Taking the orthogonal test data as the sample, the gray relational analysis method was used to convert the multi-objective to the single objective. The regression model of the optimization objective was established by using the SVM neural network. The genetic algorithm was used to optimize the model and obtain the optimal process parameters . The results show that the heating time is reduced by 20% and the maximum residual stress is decreased by 24% compared with the traditional quenching and tempering process.