A novel YOLO26-MoE optimized by an LLM agent for insulator fault detection considering UAV images

TL;DR

This paper introduces an optimized YOLO26-MoE model enhanced with an LLM agent for improved insulator fault detection in UAV images, achieving high accuracy and robustness in challenging conditions.

Contribution

It presents a novel YOLO26-MoE architecture with a sparse MoE module and uses an LLM agent for hyperparameter tuning, advancing UAV-based insulator fault detection.

Findings

Achieved 0.9900 mAP@0.5 and 0.9515 mAP@0.5:0.95 on insulator fault detection.

Outperformed latest YOLO versions in accuracy and reliability.

Demonstrated effective detection of small defects in complex backgrounds.

Abstract

The inspection of electrical power line insulators is essential for ensuring grid reliability and preventing failures caused by damaged or degraded insulation components. In recent years, Unmanned Aerial Vehicles (UAVs) combined with deep learning-based vision systems have emerged as an effective solution for automating this process. However, insulator fault detection remains challenging due to small defect regions, heterogeneous fault patterns, complex backgrounds, and varying imaging conditions. To address these challenges, this paper proposes an optimized YOLO26-MoE, a novel object detection architecture that integrates a sparse Mixture-of-Experts (MoE) module into the high-resolution branch of the YOLO26 detector. The proposed modification enables adaptive feature refinement for subtle and diverse fault patterns while preserving the efficiency of a one-stage detection framework. Hyperparameter optimization, final training, and evaluation were coordinated through a tool-augmented Large Language Model (LLM) agent. The proposed model achieved 0.9900 mAP@0.5 and 0.9515 mAP@0.5:0.95, outperforming the latest YOLO versions. These results demonstrate that the proposed model provides an effective and reliable solution for UAV-based insulator fault detection.