A fault detection robotic cell application based on deep learning and image processing hybrid approach for quality control of automotive parts

Abstract

In this study, the development of a robotic cell that combines deep learning and image processing hybrid approach has been addressed in order to increase the accuracy and efficiency of the quality control of automotive parts. In the automotive industry, manual quality control processes performed by operators are susceptible to errors and inaccuracies, leading to the passage of faulty parts and subsequent inefficiencies, wasted time, and increased costs. To overcome these challenges, this study introduces a fault detection robotic cell that combines deep learning and image processing techniques for quality control of automotive parts at Sahinkul Machine Spare Parts Manuf. Ltd. Co.. The robotic cell uses image processing to inspect geometric tolerances, including hole diameter, part geometry and the presence of holes. However, the complex geometry of bolt threads requires the use of the YOLOv5 deep learning algorithm to assess their quality. A dataset consisting of 3500 bolt thread images was collected for training and validation, with 2800 images used for training, 350 for validation, and the remaining 350 for testing purposes. The experimental results show that the fault detection robotic workcell achieves an approximate success rate of 97.4% in inspecting the quality of the selected parts. By combining deep learning and image processing, this study provides a reliable solution to improve the accuracy and efficiency of quality control processes in the automotive industry.