DocumentCode :
620332
Title :
A new fault classification model for prognosis and diagnosis in CNC machine
Author :
Al-jonid, Khalid ; Wang Jiayang ; Nurudeen, Mohammed
Author_Institution :
Sch. of Inf. Sci. & Eng., Central South Univ., Changsha, China
fYear :
2013
fDate :
25-27 May 2013
Firstpage :
3538
Lastpage :
3543
Abstract :
This paper presents a new fault classification model and an integrated approach to fault diagnosis which involves the combination of ideas of Neuro-fuzzy Networks (NF), Dynamic Bayesian Networks (DBN) and Particle Filtering (PF) algorithm on single platform. In the new model we categorize faults in two aspects, namely first and second degree faults. First degree faults are instantaneous in nature and second degree faults are evolutional and appear as a developing phenomenon which start from an initial stage and graduate through development stage and finally ends at a mature stage, these category of fault have a lifetime which is inversely proportional a machine tool life according to modified version of Taylor´s equation expressed as [1]. For fault diagnosis, our framework consists of two phases: the first focusing on fault prognosis which is done online and the second dwelling on fault diagnosis which depends on both off-line and on-line modules. On the first phase a neuro-fuzzy predictor is used take a decision on whether to embark Conditional Based Maintenance (CMB) or fault diagnosis based on the magnitude of a fault. The second phase only comes into action when an evolving fault goes beyond a critical threshold limit called CBM limit for a command to be issued for fault diagnosis. During this phase DBN and PF techniques are used as an intelligent fault diagnosis system to determine the magnitude, time and location of the fault. The feasibility of this approach has been tested in a simulation environment using CNC machine as a case study and the results are studied and analyzed.
Keywords :
belief networks; computerised numerical control; condition monitoring; fault diagnosis; fuzzy logic; machine tools; maintenance engineering; mechanical engineering computing; neural nets; pattern classification; CBM limit; CNC machine diagnosis; CNC machine prognosis; DBN; NF; PF algorithm; Taylor equation; conditional based maintenance; dynamic Bayesian network; fault classification model; fault prognosis; first degree faults; intelligent fault diagnosis system; machine tool life; neuro-fuzzy network; neuro-fuzzy predictor; offline modules; online modules; particle filtering algorithm; second degree faults; Bayes methods; Computer numerical control; Degradation; Equations; Fault diagnosis; Mathematical model; Noise measurement; Conditional Based Maintenance; Fault Diagnosis; Fault evolution; Prognosis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control and Decision Conference (CCDC), 2013 25th Chinese
Conference_Location :
Guiyang
Print_ISBN :
978-1-4673-5533-9
Type :
conf
DOI :
10.1109/CCDC.2013.6561561
Filename :
6561561
Link To Document :
بازگشت