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.

Industrial health assessment often faces the challenge of sensor scarcity and a lack of labelled failure datasets, making conventional monitoring difficult to scale. This study addresses these constraints by proposing a state-aware framework that relies exclusively on routinely measured electrical parameters (active power, current, voltage, and power factor). The main challenge lies in distinguishing benign load variations from actual degradation without process-level context. To overcome this, we integrate automated operating-state recognition using XGBoost with per-state regression modelling to estimate the expected active power. A standardized Health Index (HI) is then derived from the residuals to quantify deviations from normal behaviour. Evaluated on a fleet of three-phase injection moulding machines, the framework demonstrates substantial performance improvements: the state-aware approach increased the median coefficient of determination from 0.64 to 0.86 and reduced residual variability by 30% compared to context-agnostic models. These findings show that synergistic system integration provides a stable and interpretable indicator for early degradation detection and fleet-level benchmarking under strict zero-label industrial constraints.