Reliability adaptive modeling method for CNC Machine Tools based on kernel function

DOI

10.2991/ismems-16.2016.61How to use a DOI?

Keywords

Reliability of CNC machine tools, Kernel function distribution, Adaptive modeling, Gaussian distribution, Cross-validation method, Traversal search method, Goodness of fit test

Abstract

A reliability adaptive modeling method for CNC Machine Tools based on kernel function is proposed. Choosing Gaussian distribution as the kernel function, the optimal model with least integral square error as the objective is established, and cross-validation method and traversal search method are used to solve the bandwidth parameter of kernel function. In examples, we use kernel function distribution model to approximate different life distributions, verifying that the kernel function distribution model has good approximation property and can replace traditional distribution model. In the reliability modeling process of one type of CNC machine tools during the early failure period, comparing the kernel function distribution model with the traditional Weibull distribution model, we verify that the kernel function distribution model is more suitable for reliability modeling of CNC machine tools by goodness of fit test

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jili W
AU  - Dingyu Y
AU  - Xiaocui Z
AU  - Zhaojun Y
AU  - Guofa L
PY  - 2016/12
DA  - 2016/12
TI  - Reliability adaptive modeling method for CNC Machine Tools based on kernel function
BT  - Proceedings of the International Symposium on Mechanical Engineering and Material Science
PB  - Atlantis Press
SP  - 359
EP  - 364
SN  - 2352-5401
UR  - https://doi.org/10.2991/ismems-16.2016.61
DO  - 10.2991/ismems-16.2016.61
ID  - W2016/12
ER  -