Modularization method based on new layout design in conceptual design stage - Application of multi-material lightweight structures utilizing machine learning

Abstract

By creating a frame structure of a new layout and dividing it into modules with little coupling to each other, as well as using topology optimization and clustering, we have determined the assembly units of the product and the assembly process with least rework. Replacing materials with lightweight alternatives is an effective method for reducing the weight of structures. However, because adhesion and coefficients of thermal expansion are different for each material, it seems reasonable to replace modules represented as a functional unit. Therefore, we constructed a system for structural evaluation and material replacement with cross section that maintains equivalent stiffness for each module. We present the method of constructing the system and the effectiveness of using machine learning; confirmed by applying it to a box structure.