Zhou Yongxin, Xing Zheng, Zhuang Qianduo, Sun Jiao, Chu Xingrong
Associated Engineering Research Center of Mechanics and Mechatronic Equipment, Shandong University, Weihai 264209, China.
Materials (Basel). 2024 Sep 13;17(18):4505. doi: 10.3390/ma17184505.
Surface integrity is a critical factor that affects the fatigue resistance of materials. A surface mechanical rolling treatment (SMRT) process can effectively improve the surface integrity of the material, thus enhancing the fatigue property. In this paper, an analysis of variance (ANOVA) and signal-to-noise ratio (SNR) are performed by orthogonal experimental design with SMRT parameters as variables and surface integrity indicators as optimization objectives, and the support vector machine-active learning (SVM-AL) model is proposed based on machine learning theory. The entire model includes three rounds of AL processes. In each round of the AL process, the SMRT parameters with relative average deviation and high output values from cross-validation are selected for the additional experimental supplement. The results show that the prediction accuracy and generalization ability of the SVM-AL model are significantly improved compared to the support vector machine (SVM) model. A fatigue test was also carried out, and the fatigue property of the SMRT specimens predicted by the SVM-AL model is also higher than that of the other specimens.
表面完整性是影响材料抗疲劳性能的关键因素。表面机械滚压处理（SMRT）工艺可有效改善材料的表面完整性，从而提高疲劳性能。本文以SMRT参数为变量、表面完整性指标为优化目标，通过正交试验设计进行方差分析（ANOVA）和信噪比（SNR）分析，并基于机器学习理论提出支持向量机-主动学习（SVM-AL）模型。整个模型包括三轮主动学习过程。在每一轮主动学习过程中，选择交叉验证中相对平均偏差和输出值较高的SMRT参数进行额外的实验补充。结果表明，与支持向量机（SVM）模型相比，SVM-AL模型的预测精度和泛化能力有显著提高。还进行了疲劳试验，SVM-AL模型预测的SMRT试样的疲劳性能也高于其他试样。
