Evolutionary multi-objective optimization of inspection frequencies for substation condition-based maintenance

Improving the overall reliability and reducing the operating cost are the two most important but often conflicting objectives for substation. Condition-based substation maintenance provides a means of balancing these objectives. This paper proposes a multi-objective approach to best compromise these two objectives by optimizing the inspection frequencies required for each component. A multi-component model is employed to identify the critical components by evaluating the overall reliability of interconnected components. A Markov-chain model is developed to assess the impact of changing individual inspection frequencies on reliability and operating cost. Pareto fronts are generated to optimize the tradeoff between the two objectives for comparisons with other substation configurations. In this paper, four different substation configurations are examined to demonstrate the effectiveness and potential of the proposed approach for handling more complicated configurations.