Soft computing applications in equipment maintenance and service

Abstract

We present methods and tools from the soft computing domain, which are used within the diagnostics and prognostics framework to accommodate imprecision of real systems. Soft computing (SC) is an association of computing methodologies that includes as its principal members fuzzy, neural, evolutionary and probabilistic computing. These methodologies enable us to deal with imprecise, uncertain data and incomplete domain knowledge typically encountered in real-world applications. We outline the advantages and disadvantages of these methodologies and show how they can be combined to create synergistic hybrid SC systems. We conclude with a description of three successful SC case study applications to equipment diagnostics: 1) prediction of paper web breakage in a paper mill using neural nets and induction trees; 2) a method for automated tuning of a raw mix proportioning controller in cement plants; and 3) adaptive classification for gas turbine anomalies.