An Industrial Maintenance Decision Support System based on Fuzzy Inference to Optimize Scope Definition

Abstract General industrial maintenance projects (also called Shutdown Projects) in the process industry are key to the operational viability of a plant. Such projects are broad in scope, very costly, highly risky, quality strict, and involve a large number of human resources; moreover, the cost of maintenance works is added to the losses for non-producing, thus rendering these projects of paramount importance in the life of the industry. A most common, fundamental challenge faced is the optimization of the project scope, to include the equipment that can only be maintained predictively, preventively or correctively, during the shutdown period while excluding equipment that exhibits decreased failure risk. The present work deals with the development of a Decision Support System (DSS) that employs Fuzzy Logic (FL) to help define the scope of electro-mechanical maintenance works in large industrial settings. The system encompasses and combines crisp technical and functional parameters with experts’ judgment to generate a “verdict” on whether or not to include the equipment in the project scope. Results based on extensive industrial dataset show that the developed system provides more robust results and tackles many of the deficiencies of other approaches.