The Application of Ontology in Forecasting the Demand for Spare Parts

The intermittent demand for spare parts of an aircraft engine which results from their random wear and tear during operation makes it difficult to manage logistic supply chains in MRO company. The supply chains indicate the need to develop information technology to support resource planning in an enterprise. The response to that are studies on new methods of forecasting the demand for spare parts replaced in engine overhaul using artificial neural networks. The article presents the concept of using OWL AEDO ontology in selecting independent variables for regressive SSN models. Such a solution allows to implement a systemic approach to SSN construction, and in effect to use SSN in forecasting for a wider range of spare parts. Due to the high requirements of flight safety, aircrafts are equipped with numerous data acquisition systems, data analysis and comprehensive diagnostics of their components, and aircraft engines undergo particular scrutiny. The data is collected in specialist bases, which after processing with artificial intelligence methods may bring significant economic gains for the MRO business.