Abstract
This paper deals with the behavior of the crosslinked polyethylene (XLPE) used as high-voltage power cable insulation under ultraviolet (UV) radiations. For this, XLPE samples have been irradiated for 240 h using low-pressure vapor fluorescent lamps. Electrical (surface and volume resistivities), mechanical (tensile strength, elongation at break and surface hardness) and physical (weight loss, water absorption, work of water adhesion and contact angle) tests have been first carried out. Experimental results show that the XLPE characteristics are affected by UV radiation. Indeed, a decline in surface resistivity, mechanical properties, and contact angle, and an increase in the water retention amount and weight loss have been recorded. In order to predict and extrapolate some XLPE properties, a supervised artificial neural network (ANN) trained by Levenberg-Marquardt algorithm has been designed. The collected database is used to train and test the ANN performance. The obtained results show that the proposed ANN algorithm presents good estimation and prediction since the predicted output values agree with the experimental data.
Highlights
Polymer materials are increasingly used for insulation in electric distribution systems
Our present study aims to analyze the impact of the UV radiation on the behavior of XLPE power cable insulation; this impact had never been studied before 2016 since when we have been the sole research team which has developed, until now, two experimental investigations on this subject [28, 29]
The experimental results show that the XLPE properties are sensitive to UV radiations
Summary
Polymer materials are increasingly used for insulation in electric distribution systems. It is well known that experimental studies are often costly and time-consuming [18] To overcome such difficulties, many researchers developed artificial intelligence approaches to predict insulating material behavior under several constraints [19]. ANNs have been used as a powerful tool to predict and diagnose electrical systems, especially high voltage insulation materials [23]. Boukezzi et al [27] developed an ANN approach to predict mechanical properties of XLPE insulated cables under thermal aging. A supervised ANN is introduced to predict some XLPE properties exceeding largely the experimental ones To achieve this objective, an MLP network trained by a backpropagation algorithm, namely Levenberg–Marquardt, is developed.
Sign-in/Register to view highlights & summary 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: TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES
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.
