Abstract
Maintenance issues have been receiving ever greater attention in the industrial sector, because equipment ageing and their performance are of major concern both for capital loss and safety. Medium voltage motors are common drivers for most applications in the process sector. Predictive maintenance activities are of paramount importance for assuring effective machine performance in a specified time horizon. The identification of the periodic test interval plays a major role in achieving a safety integrity target. This paper presents a mathematical model, based on discrete step-wise Markov processes, predicting the probability of the machine failure depending on the periodic test interval. The ‘health state’ of the machine is depicted by a bulk index, called integrity level (IL), currently used by several companies. The model has been built and tested on a large maintenance database involving 111 motors from four facilities.
Acknowledgements
Thanks are due to the Polimeri Europa SpA technicians involved in the study.