Combining Unsupervised and Supervised Learning for Asset Class Failure Prediction in Power Systems

TL;DR

This paper introduces a data-driven method combining unsupervised and supervised learning to improve asset failure prediction in power systems, surpassing traditional models by incorporating condition data.

Contribution

It presents a novel approach using K-means clustering and logistic regression to enhance failure prediction accuracy for power system assets.

Findings

Outperforms Weibull distribution in failure prediction accuracy

Effectively incorporates asset condition data for more precise predictions

Demonstrates practical applicability in urban power distribution systems

Abstract

In power systems, an asset class is a group of power equipment that has the same function and shares similar electrical or mechanical characteristics. Predicting failures for different asset classes is critical for electric utilities towards developing cost-effective asset management strategies. Previously, physical age based Weibull distribution has been widely used to failure prediction. However, this mathematical model cannot incorporate asset condition data such as inspection or testing results. As a result, the prediction cannot be very specific and accurate for individual assets. To solve this important problem, this paper proposes a novel and comprehensive data-driven approach based on asset condition data: K-means clustering as an unsupervised learning method is used to analyze the inner structure of historical asset condition data and produce the asset conditional ages; logistic regression as a supervised learning method takes in both asset physical ages and conditional ages to classify and predict asset statuses. Furthermore, an index called average aging rate is defined to quantify, track and estimate the relationship between asset physical age and conditional age. This approach was applied to an urban distribution system in West Canada to predict medium-voltage cable failures. Case studies and comparison with standard Weibull distribution are provided. The proposed approach demonstrates superior performance and practicality for predicting asset class failures in power systems.