A machine learning-based assessment model for defect diagnosis in XLPE power cables

Abstract

Cross-linked polyethylene (XLPE) power cables are commonly used in flexible DC transmission applications. The diagnosis of the defects of XLPE power cable has consistently been a focal point of research as it is an essential equipment for power delivery. Previous research works have seldom employed machine learning methods to deal with this problem. Therefore, this work presents a machine learning-based assessment model that combines the Categorical Boosting (CatBoost) algorithm and Aquila optimizer. The CatBoost model is developed to examine the stages of the cable defect. The load condition, corrosion condition, operating life, and partial discharge are the inputs into the CatBoost model. The Aquila optimizer is employed to optimize parameters in an automated manner during the training of the CatBoost model. The performance comparison is made between the proposed model and the existing models. The proposed model demonstrates a high level of accuracy, precision, recall, and F1-score, all higher than 99 %. The model exhibits at least 1 % more achievement in accuracy, precision, recall, and F1-score when compared to the next best model, XGBoost. These results suggest that the proposed model is capable of effectively assessing the stages of cable defects. In addition to this, these experimental results of the proposed model are superior to those of the existing models, which demonstrate that the proposed model is superior to the existing models in terms of its ability to assess the defect stages of cables.

Keywords

• XLPE cable
• Defect assessment
• Partial discharge
• CatBoost model
• Aquila optimizer