A Predictive Quality Inspection Framework for the Manufacturing Process in the Context of Industry 4.0

Abstract

The purpose of this research is to develop an innovative software framework with AI capabilities to predict the quality of automobiles at the end of the production line. By utilizing machine learning techniques, this framework aims to prevent defective vehicles from reaching customers, thus enhancing production efficiency, reducing costs, and shortening the manufacturing time of automobiles. The principal results demonstrate that the predictive quality inspection framework significantly improves defect detection and supports personalized road tests. The major conclusions indicate that integrating AI into quality control processes offers a sustainable, long-term solution for continuous improvement in automotive manufacturing, ultimately increasing overall production efficiency. The economic benefit of our solution is significant. Currently, a final test drive takes 10–30 min, depending on the car model. If 200,000–300,000 cars are produced annually and our data prediction of quality saves 10 percent of test drives with test drivers, this represents a minimum annual saving of 200,000 production minutes.

Keywords

• automotive manufacturing
• quality control
• defect detection
• AI framework
• production efficiency
• predictive maintenance