Asset Details
Do you wish to reserve the book?
An intelligent life prediction approach employing machine learning models for the power transformers
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
An intelligent life prediction approach employing machine learning models for the power transformers
Do you wish to request the book?
An intelligent life prediction approach employing machine learning models for the power transformers
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
An intelligent life prediction approach employing machine learning models for the power transformers
2026
Overview
Accurate assessment of transformer insulating paper is vital for reliable operation and optimal transformer management, with the Degree of Polymerization (DP) serving as a primary indicator of insulation health. Direct DP measurement is often impractical, prompting this study to explore machine learning models for predicting DP using 2-Furfuraldehyde (2-FAL), a cellulose degradation byproduct measurable in transformer oil. This approach classifies insulation into four categories—Fresh (DP: 700–1200), Lightly Aged (DP: 450–700), Moderately Aged (DP: 250–450), and Worstly Aged (DP < 250)—based on DP values, offering a streamlined alternative to conventional multi-gas diagnostic methods. Supervised machine learning algorithms were developed using IEEE C57.104-2019 standard data, employing regression (Linear Regression, Polynomial Regression, Random Forest Regressor) to predict continuous DP and classification (Logistic Regression, Support Vector Machine with RBF kernel, Random Forest Classifier) to categorize insulation condition. Model performance was evaluated using regression metrics (Mean Squared Error, Mean Absolute Error, R² Score) and classification metrics (accuracy, precision, recall, F1-score). The Random Forest Regressor (R²: 0.894) and Classifier (accuracy: 0.925) demonstrated superior performance, enabling precise, non-invasive DP estimation and condition assessment. These findings highlight the efficacy of 2-FAL-based machine learning models for transformer health monitoring, facilitating predictive maintenance and enhancing operational reliability.
