Capacity Loss Analysis Using Machine Learning Regression Algorithms

Atay S., Ayranci A. A., ERKMEN B.

9th International Conference on Electrical and Electronics Engineering (ICEEE), Alanya, Turkey, 29 - 31 March 2022, pp.10-13 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/iceee55327.2022.9772532
  • City: Alanya
  • Country: Turkey
  • Page Numbers: pp.10-13
  • Keywords: machine learning, power capacitors, regression algorithms, remaining capacity of capacitor
  • Yıldız Technical University Affiliated: Yes


In this study, time dependent measurements of the power capacitor, which is the main equipment of a compensation unit, are given. The power capacitor is actively working in an industrial facility. Six months of the data from this capacitor were recorded and tests were carried out using Machine Learning (ML) algorithms for its remaining useful life. ML algorithms were selected from the algorithms that used for regression problems. In the study, Support Vector Machine (SVM), Linear Regression (LR) and Regression Trees (RT) algorithms were used. The rated powers of the analyzed capacitor are 50kVAR and 25kVAR from the active plant. The data set was created by running the capacitor continuously for 6 months and the capacity loss was examined with using ML algorithms. The algorithm that gives the best result in the regression analyzes is the LR algorithm. With the results obtained, it is possible to analyze how long the useful life of capacitors with the same characteristics have under the same stress.