期刊名称：IAENG International Journal of Computer Science
印刷版ISSN：1819-656X
电子版ISSN：1819-9224
出版年度：2021
卷号：48
期号：2
语种：English
出版社：IAENG - International Association of Engineers
摘要：Milling force prediction of titanium alloy plays an important role in titanium alloy milling process. In the article, the milling process of titanium alloy materials is analyzed, and this material quality is affected directly by the milling force. Support vector machine (SVM) has shown prominent performance for many real-world problems. However, SVM computational complexity increases, as the number of samples increases. How to effectively apply it to massive datasets is still a serious challenge. Although there are some literatures on parameter optimization techniques of SVM regression, the performance of this model still needs to be further studied and improved. We present a new milling force predicting model, namely ACO&SVM, which integrate SVM regression with ACO algorithm to enhance the prediction accuracy of milling force for mill process of titanium alloy. The primary innovation feature of hybrid model is to apply the ACO to automatically determine parameters of SVM regression model. In addition, as being applied to discrete optimization, to solve continuous optimization problems, ACO algorithm needs to transform continuous variables into discrete ones by discretizing of continuous variables. The results have shown that proposed ACO&SVM model yields better prediction accuracy, and thus it can be widely applied to the fields of material processing optimization.
