Towards an Intelligent Decision Support System for Aircraft Troubleshooting

Abstract

Currently, troubleshooting an aircraft remains a promising area for automation and intellectualization. At the same time, existing solutions in this area in the form of electronic technical manuals do not always meet the requirements of technical personnel when searching and troubleshooting aircraft. In this regard, the development of another class of systems based on artificial intelligence methods is relevant. These systems can provide not only the search and elimination of failures and malfunctions but also self-learning by accumulating the experience. This paper proposes the basic principles of such an intelligent system, called the AirTech Assistant, designed for use by technical personnel engaged in the maintenance and repair of the power supply system of the Sukhoi Superjet (RRJ-95) aircraft. In particular, a fragment of the conceptual model of the domain is given, functional, operational, and quality requirements are formulated, architecture, as well as fundamental algorithms and a stack of implementation technologies, are defined. The main components of the designed system will be expert systems implementing case-based and rule-based reasoning. An additional study was conducted in terms of testing the formalism of event trees for knowledge base engineering.