Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Adaptive Multi-scale PHM for Robotic Assembly Processes



Benjamin Y. Choo, Peter A. Beling, Amy LaViers, Jeremy Marvel, Brian A. Weiss


Adaptive multi-scale prognostics and health management (AM-PHM) is a methodology designed to support PHM in smart manufacturing systems. AM-PHM is characterized by its incorporation of multi-level, hierarchical relationships and PHM information gathered from a manufacturing system. AM-PHM utilizes diagnostic and prognostic information regarding the current health of the system and its constituent components, and propagates this information up and down the hierarchical structure. By doing so, the AM-PHM methodology creates actionable prognostic and diagnostic intelligence along the manufacturing process hierarchy. This information includes the predicted health state upon completion of a task. The AM-PHM methodology allows for more intelligent decision-making to increase efficiency, performance, safety, reliability, and maintainability. In this paper, The AM-PHM concept is described and then applied to a canonical example robotic assembly process involving two robots working in series.
Proceedings Title
Annual Conference Of The Prognostics And Health Management Society 2015
Conference Dates
October 18-24, 2015
Conference Location
Coronado, CA, US


prognostics and health management (PHM), smart manufacturing, diagnostics, prognostics, condition-monitoring, maintenance, industrial robotics


Choo, B. , Beling, P. , LaViers, A. , Marvel, J. and Weiss, B. (2015), Adaptive Multi-scale PHM for Robotic Assembly Processes, Annual Conference Of The Prognostics And Health Management Society 2015, Coronado, CA, US, [online], (Accessed April 20, 2024)
Created October 23, 2015, Updated April 1, 2022