Abstract
This paper presents a novel method based on heat-transfer theory, principal component analysis (PCA), and particle filtering (PF) to detect, trace, and predict current-carrying faults in electrical equipment. Based on heat-transfer theory, a model is proposed to describe the temperature rise of a faulty contact. PCA is applied to analyze each contact's real-time temperature sequence and categorize faulty contacts for early warnings. After fault detection, the temperature sequence of a faulty contact is extracted and adopted to initialize the model parameters. To better demonstrate the fault status, PF is utilized to optimize the model parameters. Experimental results are presented to verify the feasibility and validity of the proposed method.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have