Predictive Quality Control in the Automotive Industry Using Supervised Machine Learning

The automotive industry stands at a crossroads, where its century-old reliance on manual quality checks is increasingly inadequate for the precision and efficiency demands of modern manufacturing. This survey paper explores a transformative solution: the integration of Supervised Machine Learning for predictive quality control. By moving beyond reactive inspections to a proactive, data-driven paradigm, the proposed system harnesses real-time sensor data—temperature, vibration, pressure, and tool wear—to predict faults before they result in defective products. Through a detailed examination of algorithms like Random Forest, SVM, and XGBoost,we demonstrate how this approach can achieve over 91% accuracy in defect prediction. The study concludes that this intelligent framework is not merely an incremental improvement but a fundamental shift, offering substantial reductions in downtime and rework while paving the way for the truly resilient and efficient