基于支持向量机方法建立超声振动磨削放电加工预测模型

杨光美; 张云鹏; 李铠月; 陈国定

doi:10.13433/j.cnki.1003-8728.2015.0517

基于支持向量机方法建立超声振动磨削放电加工预测模型

doi: 10.13433/j.cnki.1003-8728.2015.0517

1.
西北工业大学机电学院, 西安 710072

基金项目:

大连理工大学精密与特种加工教育部重点实验室研究基金项目（JMTZ201103）资助

详细信息

作者简介:
杨光美（1996-），硕士研究生，研究方向为机械系统设计与优化，指尖密封动态分析，lvguang@mail.nwpu.edu.cn

通讯作者:
陈国定，教授，博士生导师，gdchen@nwpu.edu.cn

计量
- 文章访问数: 164
- HTML全文浏览量: 23
- PDF下载量: 6
- 被引次数: 0
出版历程
- 收稿日期: 2013-09-25
- 刊出日期: 2015-05-05

Establishing Ultrasonic Vibration Grinding EDM-assisted Processing Prediction Model Based on Support Vector Machines

1.
School of Mechanical Engineering, Northwestern Polytechnical University, Xi'an 710072, China

摘要

摘要: 针对采用机器学习理论建立超声振动磨削放电加工模型时存在试验样本数量少、预测量数值变化波动大的问题，提出利用支持向量机方法建立加工指标预测模型的方法。以超声振动磨削放电加工SiCp/Al为例，利用正交试验获取学习样本数据，采用MATLAB软件建立超声振动磨削放电加工SiCp/Al工艺指标的支持向量机预测模型，并利用该模型预测零件表面粗糙度和加工速度两项工艺指标。结果表明：支持向量机模型得到的工艺指标预测值与试验值具有较好的一致性，最大相对误差不超过12%，预测值精度较高，所建立的超声振动磨削放电加工工艺指标的支持向量机预测模型是可靠且有效的。
- 超声振动磨削放电加工 /
- 支持向量机 /
- 工艺指标 /
- 预测模型
Abstract: Aim at the numerically fluctuated prediction of the ultrasonic vibration grinding assisted by EDM(electric discharge machining) in application of the models is built based on the machine learning theory, a processing prediction model based on the support vector machine(SVM). Taking the ultrasonic vibration grinding of SiCp/Al assisted by EDM as an example, learning samples with orthogonal tests and establish the prediction model is constructed based on SVM on the MATLAB platform. Then the model is used to predict two indicators such as surface roughness and processing velocity. The research results show that the prediction results of the processing prediction model are in accord with the test results. When the maximum relative error is less than 12% and the prediction value being highly accurate, the prediction model is reliable and effective.
- design of experiments /
- electric discharge machining /
- errors /
- prediction model

HTML全文

参考文献(16)

[1]	蔡自兴,徐光祐.人工智能及其应用[M].北京:清华大学出版社,2003 Cai Z X, Xu G Y. Artificial intelligence:principles and applications[M]. Beijing:Tsinghua University Press,2003 (in Chinese)
[2]	MulierF. Vapnik-Chervonenkis (VC) learning theory and its applications[J]. IEEE_Transactions on Neural Networks,1999,10(5):985-987
[3]	Tsai K M, Wang P J. Predictions on surface finish in electrical discharge machining based upon neural network models[J]. International Journal of Machine Tools and Manufacture,2001,41(10):1385-1403
[4]	Benkirane Y, Kremer D. Ultrasonic machining: an analytical and experimental study on contour machining based on neural network[J]. CIRP Annals-Manufacturing Technology,1999,48(1):135-138
[5]	张云鹏,任中根,迟恩田,等.基于BP神经网络的超声磨料混粉电火花加工模型[J].电子工艺技术,2003,(5):126-129 Zhang Y P, Ren Z G, Chi E T, et al. A ultrasonic abrasive mixed powder EDM model based on BP artificial nerve network[J]. Electronics Process Technology,2003,(5):126-129 (in Chinese)
[6]	彭泽军,王宝瑞,陈辉.基于神经网络的电火花加工工艺选择模型研究[J].机械科学与技术,2003,25(4):394-397 Peng Z J, Wang B R, Chen H. Study of a process selection model for EDM based on neural network[J]. Mechanical Science and Technology,2003,25(4):394-397 (in Chinese)
[7]	余香梅,舒彤.基于α稳定分布参数和支持向量机的齿轮箱故障诊断方法[J].测控技术,2012,31(8):23-26 Yu X M, Shu T. Fault diagnosis method for gearbox based on α-stable distribution parameters and support vector machines[J]. Measurement & Control Technology,2012,31(8):23-26 (in Chinese)
[8]	Vapnik V N. The nature of statistical learning theory[M]. New York:Springer-Verlag,1995
[9]	郭凤怡,郭长娜,王爱军,等.基于粒子群优化支持向量机的煤矿水位预测模型[J].计算工程与科学,2012,34(7):177-181 Guo F Y, Guo C N, Wang A J, et al. The forecast model of mine water discharge based on particle swarm optimization and support vector machines[J]. Computer Engineering & Science,2012,34(7):177-181 (in Chinese)
[10]	胡玉景.超声振动-磨削-脉冲放电复合加工技术及其智能控制的研究[D].济南:山东大学, 2007 Hu Y J. Study of ultrasonic vibration assisted grinding and electrical discharge machining mechanism and its intelligent control [D]. Jinan:Shandong University,2007 (in Chinese)
[11]	董春杰,张建华,宋夕超.超声振动辅助电火花脉冲放电表面强化层表面质量研究[J].工具技术,2011,45(2):50-53 Dong C J, Zhang J H, Song X C. Surface quality of ultrasonic vibration assisted electrical discharge surface modification layer[J]. Tool Engineering,2011,45(2):50-53 (in Chinese)
[12]	Debroy A, Chakraborty S. Non-conventional optimization techniques in optimizing non-traditional machining processes: a review[J]. Management Science Letters,2013,3(1):23-38
[13]	Vapnik V N. The nature of statistical learning theory[M]. Springer-Verlag,New York,Inc,2000
[14]	Scho··lkopf B. Learning with kernels-support vector machines,regularization,optimization and beyond[M]. MIT Press,Cambridge,MA,2002
[15]	杨虞微,左洪福,陈果.支持向量机时间序列预测模型的参数影响分析与自适应优化[J].航空动力学报,2006,21(4): 767-772 Yang Y W, Zuo H F, Chen G. Influence analysis and self adaptive optimization of support vector machine time series forecasting model parameters[J]. Journal of Aerospace Power,2006,21(4): 767-772 (in Chinese)
[16]	张新峰,赵彦,王生昌,等.基于支持向量机的小样本威布尔可靠性分析[J].机械科学与技术,2012,31(8):1359-1368 Zhang X F, Zhao Y, Wang S C, et al. Weibull reliability analysis in small samples based on SVM[J]. Mechanical Science and Technology,2012,31(8):1359-1368 (in Chinese)