<![CDATA[Electrical energy is one of the most important needs in the local area, concerning the provision of electrical power a transformer is needed to distribute electrical power to each house. The use of transformers in each area requires testing the oil content in them to assess the state of the transformer. The Duval Pentagon Method (DPM) and the Duval Triangle Method (DTM) can be used in tests to identify transformer interference. Owing to the vast quantity of transformers utilized in public energy distribution, the Adaboost machine learning method was applied to identify transformer disruptions. By categorizing test data on a dataset derived from tests conducted with the earlier DTM and DPM techniques, the AdaBoost algorithm predicts transformer disruptions. According to the findings of tests conducted using the best dataset, the division used 80% of the data for training and reserved 20% for testing, using a learning rate of 1 and an estimator of 400 for DTM. This resulted in an accuracy level of 91.1%, which is an excellent classification. In contrast, the DPM approach divides the dataset into 80% training and 20% testing, employs an estimator of 500, and has a learning rate of 0.5. This leads to an excellent classification accuracy rate of 84.9%.]]>
Copyrights © 2024
