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

Area of Science:

• Artificial Intelligence in Manufacturing
• Automotive Quality Control Systems
• Machine Learning for Predictive Maintenance

Background:

• Current automotive quality control relies on time-consuming manual inspections and test drives.
• Defective vehicles reaching customers lead to increased costs, reduced efficiency, and reputational damage.
• The need for advanced, data-driven solutions in automotive production is critical for competitive advantage.

Purpose of the Study:

• To develop an innovative AI-driven software framework for predicting automobile quality.
• To integrate machine learning for enhanced defect detection at the end of the production line.
• To reduce manufacturing time, costs, and prevent defective vehicles from reaching consumers.

Main Methods:

• Development of a novel software framework incorporating artificial intelligence (AI) capabilities.
• Utilization of machine learning (ML) techniques for predictive quality assessment.
• Implementation of AI for enhanced defect detection and personalized road test optimization.

Main Results:

• The predictive quality inspection framework demonstrated significant improvements in defect detection accuracy.
• The system effectively supports personalized road tests, optimizing resource allocation.
• A projected saving of at least 200,000 production minutes annually, based on a 10% reduction in test drives.

Conclusions:

• Integrating AI into automotive quality control provides a sustainable, long-term solution for continuous improvement.
• The AI framework enhances production efficiency and reduces manufacturing timelines.
• The predictive quality system offers substantial economic benefits and strengthens overall automotive manufacturing processes.