An intelligent system based on neural networks for simulating a high voltage phenomena

Insulators are among the most important components of overhead electrical energy transport and distribution networks since they provide both the mechanical support of the parts brought to high voltage and the electrical insulation of the latter, with grounded or energized other components (Samakosh and al, 2019), (M. Faramarzi Palangar and al, 2020). Indeed, a disturbance of the electrical insulation provided by the insulator can lead, in certain circumstances, to its bypassing and therefore a major risk to the reliability and operation of the overhead electrical energy transmission system. Several causes are at the origin of the electrical flashover such as transient overvoltage on the electrical networks (lightning, interlocking and openings of lines) (R. L. KHERFANE and al,2022). To determine the characteristics of electrical breakdown of many High Voltage electrode configurations, the formation and propagation of streamers is an important precursor to achieve this goal. It’s a major importance when we want to improve internal and external performance insulation systems understand and study the interaction between the polymer surface and the development process of the streamer. A numerical tool using neural networks is developed, in this context. This model allows evaluating the speed of streamers as a function of the amplitude of voltage initiation and the nature of the insulating materials. In fact, a database was created to train the neural model from a laboratory model. This research builds a database for predicting the propagation of streamers on the polymers surface by different neuronal methods and presents an interesting tool for estimating the propagation phenomena.