Owing to its lightweight and excellent shock-absorbing properties, aluminum foam is used in automotive parts and construction materials. If a nondestructive quality assurance method can be established, the application of aluminum foam will be further expanded. In this study, we attempted to estimate the plateau stress of aluminum foam via machine learning (deep learning) using X-ray computed tomography (CT) images of aluminum foam. The plateau stresses estimated by machine learning and those actually obtained using the compression test were almost identical. Consequently, it was shown that plateau stress can be estimated by training using the two-dimensional cross-sectional images obtained nondestructively via X-ray CT imaging.

Aluminum foam is expected to be one of the candidates for lightweight materials for structural components as it is lightweight and has excellent shock absorption and sound absorption properties. However, aluminum foam has low tensile and flexural strength due to its thin cell walls. Therefore, aluminum foam is used by combining with dense materials. In particular, with the recent trend toward multi-materials, research on the combination with lightweight resins is expected. In this study, we attempted to join aluminum foam fabricated by the precursor method to a thermoplastic resin polycarbonate (PCTA) plate by friction welding. It was found that the aluminum foam and PCTA plate can be joined in about 1 min by friction welding, by rotating the aluminum foam at 2000 rpm and pressing 1 mm into the PCTA plate. In addition, in the friction welding of aluminum foam and PCTA plate, it was found that the pores of the aluminum foam were maintained without being collapsed. The anchoring effect is presumably caused by the penetration of PCTA softened by the frictional heat generated by the friction welding into the pores. Furthermore, tensile tests of the joined samples showed that fracture occurred either at the joining interface or at the base material of the aluminum foam, and that the joining strength was equivalent to the tensile strength of the aluminum foam itself.