ProtoDINet : End-to-End Interpretable Prototypical Model for Insulator Damage Detection

Damaged grid components such as insulators in transmission line can cause widespread impact in downstream connections such as outages. Preventing such failures requires frequent laborious inspection of thousands of power grid components, hence currently is done quite infrequently. In an era of societal electrification, there is an increasing need for an automated approach to continuous monitoring and inspection of grid components. In this paper, we propose an explainable deep learning based approach for damage detection and automated inspection of transmission lines from aerial images. We propose ProtoDINet - an interpretable end-to-end trained prototypical damaged insulator detection network. Unlike the black box machine learning models, ProtoDINet learns explainable prototypes during training- making it inherently interpretable. The most relevant prototypes are then automatically identified using a combinatorial multi-armed bandit (MAB) method targeted to improve class distinction. The final learned prototypes facilitate end users' understanding of the model's decision making process. We report promising results in Fl and AUC scores, visualize meaningful learnt prototypes, and demonstrate the effectiveness of the MAB-based prototype selection both quantitatively and qualitatively. This demonstrates the potential for more trustworthy interpretable solutions compared to existing black-box methods and encourages further research in the direction of prototypical networks for power grid.