Towards an intelligent maintenance optimization system

This paper is concerned with the evaluation and enhancement of the maintenance routines of large and complex technical systems. An ‘intelligent decision support system’ approach is suggested as a method for overcoming the difficulties associated with the scale, variability and changeability of such systems. The main features of the proposed intelligent maintenance optimization system (IMOS) are identified. A prototype system is then presented and its main mathematical models of maintenance are introduced. Some sample test data and the results produced from them are presented. Other aspects discussed include dealing with censored data, optimization criteria, the development of a maintenance model selection rule base, the recognition of data patterns and models’ robustness. Results of IMOS system validation against expert advice have shown a high measure of consistency.