基于RBF与SVM算法的CFRP铣削表面粗糙度预测  

Prediction of Milling Surface Roughness of CFRP Based on RBF Neural Network and SVM Algorithm

作　　者：赵德中 李锋 刘维伟[2] ZHAO De-zhong;LI Feng;LIU Wei-wei(School of Aircraft,Xi'an Aviation University,Xi'an 710089;School of Mechanical and Electronic Engineering,Northwestern Polytechnical University,Xi'an 710072)

机构地区：[1]西安航空学院飞行器学院,西安710089 [2]西北工业大学机电学院,西安710072

出　　处：《航空精密制造技术》2025年第1期11-14,共4页Aviation Precision Manufacturing Technology

基　　金：陕西省自然科学基础研究计划项目资助(2023-JC-YB-469)。

摘　　要：为了研究刀具结构对CFRP材料铣削表面质量的影响,进而为刀具设计提供依据,设计了刀具参数与CFRP铣削表面粗糙度之间的正交试验。基于正交试验数据,分别利用径向基函数神经网络和支持向量机学习算法建立了刀具参数与铣削表面粗糙度之间的预测模型,并对模型进行了训练、测试与验证。结果发现,基于支持向量机学习算法建立的模型预测精度较高。文中建立的预测模型可以为刀具参数变化时,预测CFRP材料铣削表面质量提供参考和依据。IIn order to study the influence of tool parameters on the surface quality in milling CFRP and provide a basis for tool design,an orthogonal test between tool parameters and milling surface roughness was designed.Based on the orthogonal test data,the prediction models of tool parameters and milling surface roughness were established by using radial basis function(RBF)neural network and support vector machine(SVM)learning algorithm respectively.The models were trained,tested and verified.The results showed that the prediction accuracy of the model established based on the support vector machine learning algorithm was the highest.The established prediction model could provide a method and basis for predicting the surface quality of CFRP milling when tool parameters change.

关 键 词：径向基函数神经网络 支持向量机学习算法 CFRP 铣削表面粗糙度 

分 类 号：TG147[一般工业技术—材料科学与工程]