A Review of Recent Trends in Machine Diagnosis and Prognosis Algorithms

Authors

  • Annamalai Pandian
  • Ahad Ali

Keywords:

Markov process; time series; artificial neural networks; ARMA; genetic algorithm; FMEA; BIW; robotic welding; failure modes

Abstract

The machine diagnosis represents the fault condition monitoring system i.e. discrete or continuous in nature. The monitoring systems may include preset limit indicators such as green for good, yellow for warning and red for failure to notify low levels of fluid or pressure measurements. The machine prognosis represents the set of activities performed based on diagnostic information to maintain its intended operating condition before complete failure. In the automotive assembly plants, the avoidance of complete failure i.e. sudden breakdowns is desired since it causes economical misfortune to the companies. This paper intends to review and summarize various techniques, models, and its applications. In this paper, we also intend to review various BIW assembly processes. The critical robotic assembly failure modes are identified and FMEA table has been developed. Formulate a failure prediction methodology based on actual plant data exclusively for robotic body shop assembly process by formulating various diagnosis and prognosis prediction algorithms. Also, develop a methodology on how to apply some of the techniques for body shop assembly process in an automotive assembly plant.

Downloads

Download data is not yet available.

Downloads

Published

2009-10-01

How to Cite

Annamalai Pandian, & Ahad Ali. (2009). A Review of Recent Trends in Machine Diagnosis and Prognosis Algorithms . International Journal of Computer Information Systems and Industrial Management Applications, 1, 9. Retrieved from https://cspub-ijcisim.org/index.php/ijcisim/article/view/26

Issue

Section

Review