A Neural Network Based Response Model for High Voltage Circuit-Breaker Testing
Wesley Doorsamy, Pitshou Bokoro
DOI: 10.15598/aeee.v16i3.2845
Abstract
Innovative test methods for circuit breakers are constantly sought after to reduce maintenance time and costs, yet still provide accurate assessment of this critical substation equipment. This paper proposes a novel method for response modelling of high voltage SF6 circuit breakers, based on artificial neural networks, to provide a means of assessing its condition. The proposed method enables a timing response model of the circuit breaker to be developed using trip command parameters. In this paper, an experimental setup is used to perform trip response testing of a three-phase 75 kV circuit breaker. The obtained data is then used to train, validate and test a Bayesian regularised artificial neural network that can predict response times of the breaker for a given set of trip command parameters.