Enhancing Motion Performance for CNC Machine Tools Based on AI-Driven Hybrid Model

This study presents an AI-driven hybrid model integrating a Deep Q-Network (DQN) and a Backpropagation Neural Network (BPNN) to enhance the motion performance of CNC machine tools. The ANOVA method is applied to analyze experimental data, while Pearson correlation aids in identifying key interpolation parameters. A trained BPNN, designed as a virtual system environment, models the dynamic behavior of CNC machine tools. The DQN interacts with this virtual system, optimizing interpolation parameters by maximizing the rewards. The optimized interpolator parameters are validated through standard CNC speed and accuracy tests. Experimental results demonstrate that the proposed AI-driven approach can further improve motion efficiency while maintaining contour accuracy, outperforming traditional manual tuning and BPNN methods.