Adaptive Multi-scale Prognostics and Health Management for Smart Manufacturing Systems

Benjamin Choo, Stephen Adams, Jeremy Marvel, Brian A. Weiss, and Peter A. Beling
Publication Target: 
IJPHM
Publication Issue: 
Special Issue on Smart Manufacturing PHM
Submission Type: 
Full Paper
AttachmentSizeTimestamp
ijphm_16_014.pdf654.08 KBJuly 18, 2016 - 12:37pm

Adaptive Multi-scale Prognostics and Health Management (AM-PHM) is a methodology designed to support PHM in smart manufacturing systems. As a rule, PHM information is not used in high-level decision-making in manufacturing systems. AM-PHM leverages and integrates component-level PHM information with hierarchical relationships across the component, machine, work cell and production line levels in a manufacturing system. The AM-PHM methodology enables the creation of actionable prognostic and diagnostic intelligence up and down the manufacturing process hierarchy. Decisions are made with the knowledge of the current and projected health state of the system at decision points along the nodes of the hierarchical structure. In order to overcome the issue of exponential explosion of complexity associated with describing a large manufacturing system, the AM-PHM methodology takes a hierarchical Markov Decision Process approach into describing the system and solving for the optimal policy. A description of the AM-PHM methodology is followed by a simulated industry inspired example to show the effectiveness of AM-PHM.

Publication Year: 
2016
Publication Volume: 
7
Publication Control Number: 
014
Page Count: 
15
Submission Keywords: 
smart manufacturing
Markov Decision Process
hierarchical MDP
Submission Topic Areas: 
Modeling and simulation
Submitted by: 
  
 
 
 

follow us

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