Open Access Open Access  Restricted Access Subscription or Fee Access

An application of pattern anomaly detection methods to fleet-wide asset level diagnostics

Chance M Kleineke, Nilimb Misal, Michael T Santucci

Abstract

Centralized monitoring techniques have become more widely used as business demands and budgetary cuts for companies require streamlined operation and maintenance of a company’s assets. These assets may be located at a single site where the monitoring is taking place, or they may be located all over a state, country or the world. Local data collection with consolidated servers allows a central maintenance center to pool big data for fleet-wide monitoring purposes. Advanced pattern recognition (APR) software solutions have been on the forefront of managing big data for dealing with a multitude of assets. APR techniques can provide evidence that a machine is not operating as expected, but the condition detected could indicate many possible underlying faults. The root cause may still be unknown. Causal network analysis has been widely used in providing differential diagnosis in the medical field when a set of symptoms are known. This method is based on Bayesian probability which can handle uncertainty in the data, both input and output, and has a good
theoretical foundation. This paper discusses methods to utilize pattern anomalies as symptoms for a causal network to diagnose asset conditions and to mitigate failures for predictive maintenance programs.

Keywords

Advanced Pattern Recognition; causal networks; asset condition diagnostics; health management; condition-based maintenance; predictive maintenance; centralized monitoring; fleet-wide monitoring; diagnostics; prognostics

Full Text:

PDF

References

Misal, N., Kleineke, C. and Santucci, M., 2010, Adapting Advanced Pattern Recognition Software to Predict and Optimize Pulverizer Performance, MFPT Proceedings.

Pearl, J., 1985, Bayesian Networks: A Model of Self-Activated Memory for Evidential Reasoning (UCLA Technical Report CSD-850017). Proceedings of the 7th Conference of the Cognitive Science Society, University of California, Irvine, CA., pp. 329–334.

Pearl, J., 2002, Causality: Models, Reasoning and Inference, Cambridge University Press, New York, NY, ISBN 0-521-77362-8, 384 p.

Wikipedia contributors. "Bayes' theorem." Wikipedia, The Free Encyclopedia. Wikipedia, The Free Encyclopedia, 18 Apr. 2018. Web. 18 Apr. 2018.

Druzdzel, M. J. and Simon, H. A., 2013, Causality in Bayesian Belief Networks, Proceedings of the Ninth Annual Conference on Uncertainty in Artificial Intelligence (UAI-93), Morgan Kaufmann Publishers, Inc., San Francisco, CA., pp. 3-11.

Stuart, A. and Ord, K., 1994, Kendall’s Advanced Theory of Statistics, Volume 1, Distribution Theory, Wiley, Hoboken, NJ, 676 p.