Surface roughness prediction in fused deposition modelling by neural networks

摘要: Fused deposition modelling is a proven technology for the fabrication of both aesthetic and functional prototypes. The obtainable roughness most limiting aspect its application. prediction surface quality an essential tool diffusion this technology, in fact at product development stage, it allows to comply with design specifications process planning useful determine manufacturing strategies. existing models are not robust enough predicting parameters all angles, particular near horizontal walls. aim work reliable over entire part surface. This purpose pursued using feed-forward neural network fit experimental data. By utilisation evaluation function, best solution has been found. obtained fitting founded by function that we constructed. validation proved robustness model found parameters’ variation applicability different FDM machines materials.