GenRel—a computer model for prediction of mining equipment failures based on genetic algorithms (GAs)

Abstract

This paper discusses ongoing research to formulate, develop and test a reliability assessment model (GenRel) based on genetic algorithms (GAs). GAs are powerful and broadly applicable stochastic search techniques based on the principles of natural selection, heredity and genetics. The reason for selecting GAs is the fact that the reliability of mining equipment changes over time due to its dependence upon several covariates/factors (e.g. equipment age, operating environment, number and quality of repairs). These factors combine to create a complex impact on a piece of equipment's reliability function. This impact encapsulates and inherits to some degree the individual characteristics of the factors as they evolve over time.

¹ BestFit, Palisade Decision Tools (http://www.palisade.com/html/bestfit.asp)

Theoretical probability distributions are commonly used to fit equipment failure data. GenRel uses the exponential probability distribution as its engine to generate predictive patterns based upon historical failure data.

Overall, this paper suggests a methodology for applying GAs for reliability assessment of mining equipment. An example is given to demonstrate the effectiveness of using GAs in reliability studies. The research discussed in this paper was carried out by the Laurentian University Mining Automation Laboratory (LUMAL).

Keywords:

• Reliability
• Mining equipment
• Generic algorithms

Acknowledgements

We thank Mr Tony Nuziale, a graduate student at LUMAL, for initial input regarding the user interface and the model's structure.

Notes

¹ BestFit, Palisade Decision Tools (http://www.palisade.com/html/bestfit.asp)

² ExpertFit, Averill M. Law and Associates, Inc. (http://www.averill-law.com/ExpertFit-distribution-fitting-overview.htm Ace)