A Comprehensive Framework for Automated Quality Control in the Automotive Industry

TL;DR

This paper introduces an automated robotic inspection system for automotive quality control that combines advanced vision, deep learning, and image processing to detect surface defects with high accuracy in real-time.

Contribution

The paper presents a novel integrated robotic inspection framework utilizing enhanced YOLO-based deep learning and image processing for defect detection in automotive manufacturing.

Findings

High detection accuracy demonstrated in real-time testing

Significant reduction in false detections achieved

System adaptable to various production environments

Abstract

This paper presents a cutting-edge robotic inspection solution designed to automate quality control in automotive manufacturing. The system integrates a pair of collaborative robots, each equipped with a high-resolution camera-based vision system to accurately detect and localize surface and thread defects in aluminum high-pressure die casting (HPDC) automotive components. In addition, specialized lenses and optimized lighting configurations are employed to ensure consistent and high-quality image acquisition. The YOLO11n deep learning model is utilized, incorporating additional enhancements such as image slicing, ensemble learning, and bounding-box merging to significantly improve performance and minimize false detections. Furthermore, image processing techniques are applied to estimate the extent of the detected defects. Experimental results demonstrate real-time performance with high accuracy across a wide variety of defects, while minimizing false detections. The proposed solution is promising and highly scalable, providing the flexibility to adapt to various production environments and meet the evolving demands of the automotive industry.