PHM Techniques for Condition-Based Maintenance Based on Hybrid System Model Representation

Claudia Maria García, Teresa Escobet, and Joseba Quevedo
Submission Type: 
Full Paper
phmc_10_036.pdf1.02 MBAugust 30, 2010 - 11:03am

Condition-based maintenance (CBM) is a maintenance strategy that uses diagnosis and prognosis to determine system’s health. The overall objective of this paper is design a real-time monitoring system for CBM, applied to a conveyor belt system, based on the integration of prognosis and health management technologies (PHM) and hybrid models. This work is focus on the prognosis part of PHM. A forecasting model based in Adaptive-Network-based Fuzzy Inference Systems (ANFIS) combined with a Gray-Scale Health Index (HI) is implemented to evalualte the system degradation. As shown throughout the paper, the hybrid model allows extracting the main features of the system that will be used in the prognostic algorithm. The obtained results show that the ANFIS prediction model linked to the degradation index HI can track the system degradation, thus have the potential for being used as a tool suitable for condition-based maintenance.

Publication Control Number: 
Submission Keywords: 
adaptive neuro-fuzzy inference system (ANFIS)
Hybrid Systems
behavior automaton
Submitted by: 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed