An intelligent method for fault situation in double-circuit transmission lines utilizing extreme learning machine

Existing fault situation frameworks conventionally use different ABC-domain or sequence network equivalent circuits for different fault types. The environmental conditions lead to changes in the parameters of the double-circuit transmission lines, and these incorrect parameters cause errors in the fault situation frameworks. The best tool for fault situation and protection of double-circuit transmission lines is the use of frameworks that work independently of the line parameters. In this article, fault situation for double-circuit transmission lines is implemented based on the measured voltage and current of each line, utilizing an Extreme Learning Machine capable of identifying nonlinear equations between measured values and fault situation. First, all types of faults were simulated at different distances in a power grid with a double-circuit transmission line. Then, the information obtained is utilized to train intelligent tools. Finally, the fault situations for different distances and resistances are estimated to assess the suggested method. To assess the superiority of the suggested framework over other intelligent frameworks, the outcomes of this article are compared with the outcomes obtained from two intelligent tools, artificial neural networks and support vector machines, which show more precision and reliability of the Extreme Learning Machine than other tools.