Functional Analysis of Comprehensive Processing System of Electric Power Fault Data under Artificial Intelligence Technology

Abstract

The level of power system advancement is one of the key assessment factors for the degree of public turn of events. The size of the power lattice has progressively expanded because of monetary and social necessities, and various appropriated sustainable power sources are constantly associated with the power framework system, expanding the intricacy of the power system. For the cutting edge, technologically progressed society of today to work, there should be a consistent and steady stockpile of electricity. The development of assets, shifting geographic conditions, and the introduction of new innovations for the production, distribution, and apportionment of energy all contribute to the continued advancement of power systems. Artificial intelligence techniques have been popular for resolving many problems in power systems, including as control, organising, booking, estimating, and so forth. In light of the assembled gas information, man-made intelligence approaches are utilized to make characterization qualities for transformer absconds. Simulated intelligence approaches are utilized to order the results of the different DGA techniques, and the results are then contrasted with the discoveries of the experimental test. The proportions DGA strategy has been exhibited to have the most magnificent presentation in arranging the transformer disappointment type when contrasted with the results from computer-based intelligence procedures. The results of the experiment demonstrate that the SVM approach has the potential to significantly increase the diagnosis accuracy for power transformer fault ordering.