Intelligent manufacturing quality control based on artificial intelligence algorithm

In the context of intelligent transformation of global manufacturing industry, traditional quality control methods are faced with bottlenecks such as low efficiency and lagging response. In this paper, an intelligent manufacturing quality objective optimization model combining XGBoost and improved genetic algorithm is proposed. By integrating machine vision, multi-modal sensing and data mining technologies, an intelligent quality control system with autonomous decision-making ability is constructed. The model uses Pearson coefficient to screen key process parameters, constructs multi-objective optimization function based on error minimization, and realizes dynamic closed-loop control of quality deviation through hierarchical anomaly detection architecture. The experimental results show that the model can significantly improve the quality control accuracy in the machining error optimization of parts, and the error decreases by 50%-91% after the optimization of key feature parameters.