Analysis of training techniques of ANN for classification of insulators in electrical power systems. Issue 8 (5th March 2020)

• Record Type: Journal Article
• Authors: Frizzo Stefenon, Stéfano; Waldrigues Branco, Nathielle; Nied, Ademir; Wildgrube Bertol, Douglas; Cristian Finardi, Erlon; Sartori, Andreza; Henrique Meyer, Luiz; Bartnik Grebogi, Rafael
• Is Part Of: IET generation, transmission & distribution. Volume 14:Issue 8(2020)
• Page Start: 1591
• Page End: 1597
• Publication Date: 2020-03-05
• Subjects: inspection -- neural nets -- optimisation -- power system reliability -- power engineering computing -- learning (artificial intelligence) -- pattern classification; outdoor insulating systems -- defect condition classification -- artificial intelligence techniques -- faulty insulating devices -- artificial neural network models -- classification problem -- training capacity -- optimisation methods -- insulators -- electrical power systems -- field inspections -- specific inspection equipment -- ultrasound detector -- gradient descent method -- quasi‐Newton method -- Levenberg–Marquardt method; Electric power production -- Periodicals; Electric power transmission -- Periodicals; Electric power distribution -- Periodicals; 621.3105
• DOI: 10.1049/iet-gtd.2019.1579
• Languages: English
• ISSNs: 1751-8687

Abstract

Abstract : Identifying defects in electrical power systems during field inspections is a difficult task, since faults are generally not visible and may be intermittent. To find possible adverse conditions, specific inspection equipment is used. The ultrasound detector is the equipment normally used to inspect outdoor insulating systems; however, using it demands operator experience. To improve the defect condition classification, artificial intelligence techniques are applied to assist the operator in the decision task and thereby facilitate the identification of faulty insulating devices in the grid. The training of artificial neural network (ANN) models is an important step in solving the classification problem. This study aims to evaluate the training capacity in terms of the performance of different optimisation methods for the calculation of the mean square error after convergence. Traditional methods such as Gradient Descent and its variations will be presented, as well as methods that employ high computational effort such as quasi‐Newton and Levenberg–Marquardt. In order to base these concepts, a review will be presented on the use of these algorithms and on the problem of classification of insulators in distribution networks. The results show that there is a considerable performance difference between the calculation methods.