Abstract
This paper presents advance artificial intelligence (AI) methods for health assessment of high voltage SF6 circuit breakers. Paper presents an overview of monitoring and diagnostics of most important indicators of the state of high voltage SF6 circuit breakers. Special attention is devoted to identifying and determining indicator limit values which can be used by AI in order to create new health assessment. Fuzzy logic as a part of AI was applied to define fuzzy expert systems which will make decisions about the maintenance of circuit breakers. Three fuzzy expert systems are created to indicate the state of: contacts, the fluid for extinguishing the electric arc and the drive mechanism. Unsupervised machine learning (UML) was applied through the k-means cluster method and cluster tree for classifying and dividing the examined high-voltage circuit breakers into groups with similar state and probability of failure. Artificial neural network (ANN) as part of supervised machine learning (SML) is created in order to predict end-life and accelerated aging of tested circuit breakers. The presented AI methods can be used to improve health assessment of high-voltage SF6 circuit breakers.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
