Abstract
This paper presents an examination on the acoustic partial discharge (PD) localization in oil based on adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) approaches. Impedance matching circuit was used to measure the electrical PD. The acoustic PD was obtained through an acoustic emission (AE) sensor and pre-amplifier gain unit. In total, 112 coordinates for each of the AE sensors were utilized to evaluate the location of the PD. Once the voltage reached 30 kV, the electrical and acoustic PDs were recorded. Next, the data were pre-processed by moving average and analyzed by time-of-arrival (TOA), ANFIS and ANN. The distance between PD and AE sensor were calculated based on TOA to determine the PD location. These information were used as an input to train the network by optimizing epoch and neuron for ANFIS and ANN in order to locate PD. ANFIS has the best percentage of PD source prediction based on root mean square error (RMSE) and coefficient of determination (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) as compared to ANN. Meanwhile, the computation time for ANN is 1.75 s faster than ANFIS to perform PD localization based on acoustic emission PD signals.
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 callMore From: IEEE Transactions on Dielectrics and Electrical Insulation
Disclaimer: 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.
