979-8-3503-3593-4/23/$31.00©2023 IEEE Providing Intelligent Maintenance through an Autonomous Robot Marián Mešter Východoslovenská distribučná, a.s. Technical university of Košice Košice, Slovakia ORCID: 0000-0002-2568-0765 Vladimír Krištof, Marek Hvizdoš Gridman, s.r.o. Košice, Slovakia contact@gridman.sk Abstract—The article focuses on trends in the field of intelligent maintenance in a utility company. One of the main goals of every transmission and distribution (T&D) system operator is reliable performance of their network with low interruption time. To achieve this goal, fully functional and healthy components are required. During their lifetime after installation and commissioning, components age and gradually change from new to old. Aging in this sense means continuous deterioration of their operability or resilience against normal and abnormal voltage and current stresses. This deterioration may lead to equipment failure if maintenance is not performed early enough. The article shows how automation can be used for remote management and maintenance of assets at an electrical substation. Keywords—maintenance strategies, remote maintenance management, autonomous robot, predictive maintenance, digital supply network I. INTRODUCTION Fully functional components that can operate robustly and with a low outage rate under all specified operating conditions are essential for a reliable T&D grid operation. As a result, dependable maintenance strategies are applied by grid operators worldwide. One of the primary challenges facing many countries with a widely developed T&D grid system is the aging of components that reach their anticipated end of life. Asset management must consider whether the lifetime of components could be prolonged, and their replacement could be delayed. Continuously monitoring the health of components is, therefore, crucial. The current ongoing transition of the entire energy system is leading to changes and increased stress on T&D equipment. The integration of new renewable energy sources on all voltage levels results in bidirectional power flows and increased variability, leading to higher demand for electric power, including peak flows. This increased stress on the equipment accelerates the aging of components and necessitates the adoption of new maintenance strategies to address this new situation. Advancements in data acquisition technology and machine learning algorithms, along with increasing embedded computing power, present an opportunity for more effective maintenance strategies based on continuous equipment monitoring and real-time health evaluations. This shift in approach could result in significant cost savings for asset management, given that properly sized equipment can last for several decades. However, many routine maintenance checks only confirm that the component is in excellent condition, making them unnecessary at times. Therefore, a delay in both replacement and maintenance checks based on health condition is desirable. Maintenance strategies have moved away from time-based checks to a just-in-time approach, which is more intelligent and efficient. This article seeks to introduce the concept of intelligent maintenance strategies, as well as the trends and challenges of monitoring the condition of T&D equipment. II. MAINTENANCE STRATEGIES The main objective of T&D system operators is to ensure their network performs reliably with minimal interruptions. This requires fully functional and healthy components. Over time, components degrade and become aged, which means they gradually lose their ability to withstand normal and abnormal voltage and current stress, leading to potential equipment failure if not maintained early enough. The deterioration rate varies among subcomponents, and the first one to fail determines the prospective lifetime without maintenance. Hence, proper asset maintenance is crucial for all grid operators. Different operators use diverse maintenance strategies, depending on factors such as eligible costs for maintenance and repair, required grid availability, and other historical factors. There are three main goals of maintenance strategy:  Optimal asset performance and extended asset life  Higher asset utilization and reduced unplanned downtime  Lower operation and maintenance (O&M) costs Maintenance strategies are classified based on two characteristics: whether the impact of potential component failure is considered and whether the condition of the component is considered [1]. The following section introduces the four most commonly used strategies (Fig.1): Fig. 1. Maintenance strategies continuum [2] This paper was supported by the Slovak Research and Development Agency, under the contracts APVV-19-0576 and APVV-21-0312 and the Slovak Academy of Sciences, under the contracts VEGA 1/0757/21.