Change detection filter technique-based fault analysis of HVDC transmission line

Abstract

Purpose This research paper aims to investigate the change detection filter technique with a decision tree-based event (fault type) classifier for recognizing and categorizing power system disturbances on the high-voltage DC (HVDC) transmission link. Design/methodology/approach A change detection filter is used to the average and differential current components, which detects the point of fault initiation and records a change detection point (CDP). The half-cycle differential and average currents on both sides of the CDP are sent through the signal processing unit, which produces the respective target. The extracted target indices are sent through a decision tree-based fault classifier mechanism for fault classification. Findings In comparison with conventional differential current protection systems, the developed framework is faster in fault detection and classification and provides great accuracy. The new technology allows for prompt identification of the fault category, allowing electrical grids to be restored as quickly as possible to minimize economic losses. This novel technology enhances efficiency in terms of reducing computing complexity. Research limitations/implications Setting a threshold value for identification is one of the limitations. To bring the designed system into stability condition before creating faults on it is another limitation. Reducing the computational burden is one of the limitations. Practical implications Creating a practical system in laboratory is difficult as it is a HVDC transmission line. Apart from that, installing rectifier and converter section for HVDC transmission line is difficult in a laboratory setting. Originality/value The suggested scheme’s importance and accuracy have been rigorously validated for the standard HVDC transmission system, subjected to various types of DC fault, and the results show the proposed algorithm would be a feasible alternative to real-time applications.