Enhancing Automotive Quality Control through Transformative Approaches Using Modern Defect Detection Techniques: A Review
Ensuring the safety, dependability, and durability of automotive components is of utmost importance in the automotive sector, making defect identification a critical task. Conventional approaches like manual inspections and basic automated systems often lack precision, reduce productivity, and are prone to human error. The progress in Machine Learning (ML) and Deep Learning (DL) has demonstrated considerable potential in addressing the difficulties related to conventional defect identification techniques. This study reviews recent applications of ML and DL for defect detection in the automotive industry. Research has shown that Convolutional Neural Networks (CNNs), YOLOv3, and VGG16, among other deep learning models, are highly accurate in detecting both surface and interior flaws. Advanced designs, such as Inceptionv3 and PartsNet, enhance detection accuracy and efficiency even more. The incorporation of these sophisticated methodologies has led to enhanced rates of identifying defects, decreased durations of inspections, and decreased operational expenditures. Furthermore, this paper emphasises the profound influence of ML and DL technologies in identifying defects in the automobile industry. It provides valuable information on how these technologies are now being used, the advantages they bring, and their potential for further enhancing quality control in industrial processes. The results emphasise the crucial significance of Artificial Intelligence (AI) in promoting innovation and guaranteeing stringent standards in the car manufacturing industry. Major Findings: This review highlights that modern machine learning techniques, especially deep learning models like CNNs, YOLOv3, and VGG16, significantly outperform traditional methods in defect detection accuracy and efficiency. The integration of advanced models such as Inceptionv3 and PartsNet enhances adaptability and performance, even with limited training data. These innovations contribute to faster inspections