Research Early Mechanical Failure of CNC Motorized Spindle Prediction Method Base on D-S Evidence Theory Information Fusion

DOI

10.2991/meici-16.2016.152How to use a DOI?

Keywords

Fault diagnosis; FNN; D-S evidence theory; CNC; Motorized spindle

Abstract

Early mechanical failure of CNC milling motorized spindle having a hidden and complexity is difficult to quickly and accurately identify early machines failure of CNC milling. In this paper, early latent subtle abnormal vibration signals of motorized spindle is detected by PeakVue. Fuzzy neural network diagnosis for each partial signal, and then the sub-diagnosis as evidence, the use of D-S evidence theory to the global final diagnosis, and further improve the early fault recognition rate. Using method of rough set theory data mining obtain processing parts of the surface roughness characteristics of data, which have established the surface roughness of the spectral characteristics of the database. Subsystems, we use FNN fault diagnosis, then the sub-diagnosis as evidence, we use the D-S evidence theory to the global final diagnosis, and further improve the early fault recognition rate. The results show that: This early fault diagnosis model fuzzy neural network and data fusion technology, which is the electrical mechanical failure early prediction accuracy spindle higher generalization ability.

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  - Chunyu Mao
AU  - Guangwen Zhou
AU  - Mei Tian
PY  - 2016/09
DA  - 2016/09
TI  - Research Early Mechanical Failure of CNC Motorized Spindle Prediction Method Base on D-S Evidence Theory Information Fusion
BT  - Proceedings of the 2016 6th International Conference on Management, Education, Information and Control (MEICI 2016)
PB  - Atlantis Press
SP  - 730
EP  - 734
SN  - 1951-6851
UR  - https://doi.org/10.2991/meici-16.2016.152
DO  - 10.2991/meici-16.2016.152
ID  - Mao2016/09
ER  -