A real-time material breakage detection for offshore wind turbines based on improved neural network algorithm

TL;DR

This paper presents an improved neural network-based method using YOLOv8 with CBAM and optimized loss function for real-time detection of material defects in offshore wind turbines, enhancing detection stability and efficiency.

Contribution

It introduces a novel detection approach combining YOLOv8 with CBAM and an optimized loss function specifically for offshore wind turbine defect detection.

Findings

Enhanced defect detection stability

Significant improvement over existing methods

Effective on large offshore wind datasets

Abstract

The integrity of offshore wind turbines, pivotal for sustainable energy generation, is often compromised by surface material defects. Despite the availability of various detection techniques, limitations persist regarding cost-effectiveness, efficiency, and applicability. Addressing these shortcomings, this study introduces a novel approach leveraging an advanced version of the YOLOv8 object detection model, supplemented with a Convolutional Block Attention Module (CBAM) for improved feature recognition. The optimized loss function further refines the learning process. Employing a dataset of 5,432 images from the Saemangeum offshore wind farm and a publicly available dataset, our method underwent rigorous testing. The findings reveal a substantial enhancement in defect detection stability, marking a significant stride towards efficient turbine maintenance. This study's contributions illuminate the path for future research, potentially revolutionizing sustainable energy practices.