Cross-linked polyethylene (XLPE) is employed in high-voltage transmission cables, due to their distinguished insulation performance. Localized degradation due to AC voltages is a major cause of damage in these systems. These damages known as electrical trees vary in their shape and characteristics according to the cause of damage. This paper discusses the effect of lightning overvoltages in trees formed in these insulation systems. Initially experiments have been conducted to generate trees at 10 kV (tree-like tree) and 12 kV (bush branch tree) and the structure of the trees are visualized. This work is extended to study the effect of lightning overvoltages. It is crucial to detect the type of damage as accurately as possible. In this research work, a classification tree model, which is based on the Bag of Visual Words (BoVW), has been developed to predict the category of damage. The accuracy of the proposed model is evaluated using Receiver Operating Characteristics (ROCs) curves and confusion matrix. Finally, the validity of the developed model is verified by comparing it with the in-house collected experimental data and the other State-of-the-Art feature extraction techniques.

交联聚乙烯（XLPE）由于其出色的绝缘性能而被用于高压输电电缆。交流电压引起的局部退化是这些系统损坏的主要原因。这些损坏称为电树，其形状和特性会根据损坏原因而有所不同。本文讨论了在这些绝缘系统中形成的树木中雷电过电压的影响。最初已经进行了实验，以生成10 kV（树状树）和12 kV（灌木分支树）的树，并对树的结构进行了可视化。这项工作扩展到研究雷电过电压的影响。尽可能准确地检测损坏的类型至关重要。在这项研究工作中，一个基于视觉单词袋（BoVW）的分类树模型，。使用接收器工作特性（ROC）曲线和混淆矩阵来评估所提出模型的准确性。最后，通过将开发的模型与内部收集的实验数据和其他最新的特征提取技术进行比较，验证了模型的有效性。