Fan Blade Balance Defect Detection Dataset

The current industrial environment faces significant challenges in ensuring the operational efficiency of fan blades, particularly due to issues like asymmetry that can lead to vibrations and unusual noises. Existing solutions often rely on manual inspections and are limited in their ability to detect subtle defects consistently. This dataset aims to address the technical challenge of automating the detection of balance defects in fan blades through image analysis. Data collection involved high-resolution images captured in a controlled environment using advanced imaging equipment, ensuring clarity and detail. Quality control measures include multiple rounds of annotation, consistency checks among annotators, and expert reviews to guarantee data reliability. The dataset is stored in JPG format, organized by defect types and image IDs for easy access and analysis. The core advantages of this dataset include high annotation accuracy, with over 95% consistency achieved through rigorous checks. It also features innovative labeling techniques utilizing machine learning for enhanced defect recognition. This dataset's application value is underscored by its potential to reduce inspection time by 40% and improve defect detection rates by 30%, significantly enhancing operational efficiency in industrial settings.