Machine Learning Applications in Estimating Transformer Loss of Life

TL;DR

This paper develops a data-driven static model using ANFIS to estimate transformer loss of life hourly, leveraging ambient temperature and load profile data, and demonstrates its superior accuracy over other machine learning methods.

Contribution

It introduces an ANFIS-based approach for transformer loss of life estimation, improving accuracy over existing methods using a standard model and machine learning techniques.

Findings

ANFIS outperforms other machine learning methods in accuracy

The model effectively estimates hourly transformer loss of life

Validation shows high reliability of the proposed approach

Abstract

Transformer life assessment and failure diagnostics have always been important problems for electric utility companies. Ambient temperature and load profile are the main factors which affect aging of the transformer insulation, and consequently, the transformer lifetime. The IEEE Std. C57.911995 provides a model for calculating the transformer loss of life based on ambient temperature and transformer's loading. In this paper, this standard is used to develop a data-driven static model for hourly estimation of the transformer loss of life. Among various machine learning methods for developing this static model, the Adaptive Network-Based Fuzzy Inference System (ANFIS) is selected. Numerical simulations demonstrate the effectiveness and the accuracy of the proposed ANFIS method compared with other relevant machine learning based methods to solve this problem.