Nur Avika Febriani, Ika Noer Syamsiana, Arwin Datumaya Wahyudi Sumari, Rachmat Sutjipto, Rahma Nur Amalia, Irwan Heryanto Eryk
Electricity is an essential element in meeting human needs. A global increase in demand for electrical energy has been observed over time. The reliability of electricity supply is contingent upon the efficacy of transformer life prediction systems. Power transformers play a pivotal role in the effective distribution of electrical energy. Presently, the estimation of Remaining Useful Life (RUL) is predominantly conducted manually. The necessity of a rapid and effective method for evaluating their condition has been underscored, prompting the emergence of smart web dashboards as a prominent solution for transformer condition monitoring and RUL estimation. The approach employed in this study utilizes the Knowledge Growing System (KGS) method. The KGS method is an artificial intelligence and expert system-based approach designed to continuously develop and update knowledge within a system. KGS facilitates continuous learning, enabling the RUL prediction model to adapt to evolving real-world conditions. The implementation of a web-based transformer RUL prediction application has proven to improve work efficiency and productivity by automating the storage and management of transformer measurement data to obtain accurate transformer life expectancy estimates. This approach is intended to ensure the reliability of the power system, to prevent sudden failures, and to reduce operational costs. © 2025 IEEE.
Electrical Engineering State Polytechnic of Malang, Malang, Indonesia
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock