This article explores a machine learning approach to predicting the mechanical properties of injection-molded polypropylene (PP) using X-ray diffraction (XRD) analysis. By applying Bayesian spectral deconvolution to XRD data, the researchers generated high-dimensional descriptors that capture structural nuances. These descriptors were refined using a quantum annealing-based optimization, yielding models that accurately predict most mechanical properties of PP, including tensile and flexural strength. This nondestructive technique presents an efficient alternative to traditional testing, though it remains challenging for properties highly sensitive to structural defects, such as elongation at break and Rockwell hardness.
Please continue reading the full article under the link below:
Please consult also the Quantum Server Marketplace platform for the outsourcing of computational science R&D projects to external expert consultants through remote collaborations:
#materials #materialsscience #materialsengineering #computationalchemistry #modelling #chemistry #researchanddevelopment #research #MaterialsSquare #ComputationalChemistry #Tutorial #DFT #simulationsoftware #simulation