Sustainable maintenance of power transformers using computational intelligence

The technical and financial management of power substations involves the evaluation of the operational condition of power transformers. Evaluation is an essential stage for maintaining electricity supply and resource efficiency by guiding the process of maintaining and/or upgrading a transformers park. This process aims at identifying assets with critical operational condition in a substation that may convey risks to operators, installed equipment and customers. The use of computational intelligence techniques aims at assisting the evaluation process, which is not simple because it requires combining measurements that evaluate different aspects of the power transformers. A deep technical knowledge of chemical, electrical and physical measurements is necessary to infer a correct diagnosis. Thus, computational intelligence techniques can reduce the need for human expertise, since they are able to extract patterns of known information and optimize the identification of critical assets. In this paper, computational intelligence techniques are applied aiming at composing a numerical index, termed Health Index, for asset prioritization. Prioritization helps classify assets based on criticality levels. Information regarding the measurements used to compose the index is based on measurements done on real transformers. In this work, computational intelligence techniques are especially explored for the composition of the Health Index, as there are no publications with the application of these techniques to solve this kind of prioritization problem. We seek the most appropriate set of methods to support decision making in prioritizing assets for maintenance. The effectiveness of the proposed methods is evaluated, seeking strategies that add greater sustainability, flexibility, simplicity and high accuracy rate in asset prioritization.