AI-Driven Quality Assessment for Machined Parts Using Sensor Fusion and Deep Learning

This paper proposes an AI-driven quality assessment algorithm for machined parts, combining deep learning with sensor fusion and reinforcement learning. The method integrates visual, acoustic, and vibration data to provide a comprehensive evaluation of part quality during machining. By employing convolutional neural networks (CNN) and long short-term memory (LSTM) networks, the algorithm automatically extracts relevant features, while reinforcement learning optimizes inspection parameters. The model was evaluated on three open-source datasets, outperforming traditional and deep learning methods in terms of accuracy, precision, recall, and F1-Score. The results demonstrate the method's effectiveness in automating and enhancing quality assessments in machining processes. Future work will focus on enhancing sensor integration and exploring multi-agent systems to further improve adaptability in dynamic manufacturing environments.