Maintenance Advisor Using Secondary-Uncertainty-Varying Type-2 Fuzzy Logic System for Offshore Power Systems

Abstract

Recently, Condition-based maintenance is a popular method to minimize the cost of maintenance failures in power systems. In order to effectively overcome the uncertainty of operational variables and information in offshore substations, a Type-2 fuzzy logic approach is proposed in this paper. The maintenance advisor optimize the maintenance schedules with multi-objective evolutionary algorithm, considering only major system variables. During operation, the offshore substation will experience continuing ageing and shifts in control, weather and load factors, measurement and all other equipments with uncertainties. More importantly, the advisor estimates the changes of reliability indices by Type-2 fuzzy logic and sends the changes back to the maintenance optimizer. At the same time, the maintenance advisor will also report to the maintenance optimizer any drastic deterioration of load-point reliability within each substation. The data analysis results shows this approach avoids complex inference process, it significantly reduces the computational complexity and rule base than conventional Type-1 fuzzy logic.