From diagnosis to prognosis: a maintenance experience for an electric locomotive

Maintenance policies are driven by specific needs as availability, time and cost reduction. In order to achieve these targets, the recent maintenance approach is based on a mix of different policies such as corrective, planned, and curative. The significance of the predictive activities is becoming more and more important for the new challenges concerning machines and plants health management. In the present paper we describe our experience about the development of a rule-based expert system for the electric locomotive E402B used in the Italian railways system, in order to carry out an automated prognostic process. The goal of the project was to develop an approach able to improve the maintenance performance. In particular we would like to develop an advanced prognostic tool able to deliver the work orders. This specific issue has been identified and requested from the maintenance operators as the best and the only solution that could ensure some results.