Research on Human-Machine Collaborative CNC Programming based on Large Language Models

In recent years, large-scale language models have demonstrated remarkable capabilities in program generation and the understanding of complex instructions, making it possible to establish a new human-machine collaboration paradigm for CNC programming. This paper proposes a human-machine collaborative CNC programming method based on large language models. Geometric features of parts and process information are first structurally extracted and then fed into the model using unified natural language templates, enabling the model to generate machining programs that are subsequently refined through human review and simulation verification to form a closed-loop programming workflow. Three collaborative programming templates are developed for contour machining, hole machining and thread machining. Using a complex bearing seat as an example, the paper presents the complete procedure of drawing information extraction, operation planning, node coordinate calculation and input sentence construction, and systematically analyzes typical deviations and error-prone points in large-model-based human–machine collaborative programming. On this basis, the paper provides a relatively systematic summary of the methods and existing problems of human-machine collaborative CNC programming and proposes directions for further improvement.