Generative design method of machine tool conceptual configuration and its application

This paper introduces a generative design framework for the conceptual configuration of machine tool structures, leveraging artificial intelligence (AI), topology optimization, and measurement-informed validation. The approach integrates a hybrid backpropagation neural network and genetic algorithm (BP-GA) with multi-objective topology optimization to identify structurally optimal configurations under varying force-flow conditions. A five-axis precision milling machine serves as a case study to demonstrate the method’s effectiveness. Validation through finite element simulation and 3D digital image correlation confirms the accuracy and robustness of the proposed model. The results reveal significant improvements in stiffness, mass efficiency, and frequency performance, highlighting the method’s potential in sustainable and intelligent manufacturing.