Validation of Diagnostic Models Using Graphical Belief Networks

Abstract

This chapter focuses on the validation of diagnosis decision support using in Bayesian belief networks for facilitating airplane maintenance at an airport gate. Delays and cancellations add significant cost to airline maintenance operations. Much of this operational costs are attributed to a decrease in diagnostics ability of airline mechanics as a result of lack of experience with an increasing variety of airplane types in the fleet and the increasing practice of outsourcing maintenance operations by airlines. The critical factors in commercial airline maintenance operations are airplane safety, dispatch reliability and turn-around time. To ensure safety and reliability, airline operators must adhere to government regulatory agencies' standards, which require a Minimum Equipment List (MEL) with the minimal set of Line Replaceable Units (LRUs) that must be in working order before dispatch is approved. A diagnostic decision support system for airplane maintenance should be designed to facilitate the decision process in such a way as to improve the accuracy of airplane diagnosis without compromising safety and reliability. This chapter describes the basis for such system. The approach combines engineering and mechanic knowledge with statistical component reliability data. A system that facilitates airplane maintenance provides decision support for finding the root-cause of a failure from observed symptoms and findings. Such system provides diagnostic advice listing the most probable causes and recommending possible remedial actions. Bayesian belief networks, a model-based approach, are presently being used for building such diagnostic models.