Essentials to Develop Data-Driven Predictive Models of Prognostics and Health Management for Distributed Electrical Systems

The reliability of the electrical networks significantly impacts customer as well as energy providers’ bottom line. Connectivity between the various sectors of the electrical network has been expressively increased due to the high penetration of the new smart hardware and software tools. Therefore, Prognostics and Health Management (PHM) becoming a critical factor in the efficiency of capital-intensive corporations especially for the energy sector including the electrical power generation. Degradation based analysis is one of the valuable approaches of condition-based algorithms in order to obtain the reliability information especially for the highly reliable systems, critical assets, and recently developed products. The main purpose of the degradation-based models is to predict the future condition of the asset and perform the maintenance in an optimized time window before the actual failure of the system. Failure is said to have occurred as a soft failure event in these types of models. The main purpose of this study is to study the essentials in developing the first hitting time degradation-based models to predict the critical time for initiating the maintenance actions in order to optimize the effectiveness of the PHM leading to enhancing the value of the assets for the distributed electrical systems. The analyses are mostly focused on the critical components of the distributed electrical systems. The latest generations of the degradation models are exploring the potential improvements based on the more available information provided by smart devices to predict the critical failure time. Robust predictive models are beneficial to both energy providers and customers to enhance the overall reliability and risk of the system by initiating the maintenance before the physical failure occurs. In this paper, General Path (GP) and Autoregressive (AR) models as general methodologies for degradation models would be discussed in detail based on the depth of the analyses and available information.