Title :
Fault Data Mining on the Encoders in Numeric Control System Based on the Information Redundancy of Velocity
Author :
Xiao, Jin-zhuang ; Wang, Hong-rui
Author_Institution :
Hebei Univ., Baoding
Abstract :
In order to arising the safety and reliability of numerical control system, aiming at the conventionally used encoders in the system as the equipment of feedback in position-loop, the data mining of its fault is analyzed. Benefiting from the reluctant information of velocity in the normal servo system, the principal component analysis is introduced to solving the fault of losing codes and pausing codes in the encoder. At the same time, the basic principles and flow process are presented. In order to validate the effectiveness of the mining way based on the software of Matlab, simulation shows that it can perform a very exact diagnosis at the time of fault occurring. This idea provides a believable way for the fault data mining in numeric control system.
Keywords :
data mining; numerical control; principal component analysis; reliability; safety; fault data mining; information redundancy; numerical control system; position-loop; principal component analysis; Computer numerical control; Control systems; Data mining; Feedback; Principal component analysis; Redundancy; Safety devices; Servomechanisms; Software performance; Velocity control; Encoder; Fault data mining; Numeric control; Principle component analysis; Velocity redundancy;
Conference_Titel :
Machine Learning and Cybernetics, 2007 International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-0973-0
Electronic_ISBN :
978-1-4244-0973-0
DOI :
10.1109/ICMLC.2007.4370202