Skip to main content
. 2024 Nov 23;45:201–230. doi: 10.1016/j.bioactmat.2024.11.021

Fig. 7.

Fig. 7

AI-driven approaches for printing process. (a) (ⅰ) Experimental results of printability improvement through machine learning optimization, (ⅱ) Phase diagrams of the design space for printing parameters. Adapted with permission from J.M. Bone, C.M. Childs, A. Menon, B. Póczos, A.W. Feinberg, P.R. LeDuc, N.R. Washburn, Hierarchical Machine Learning for High-Fidelity 3D Printed Biopolymers, ACS BIOMATER SCI ENG, 6 (2020) 7021–7031. Copyright 2020, American Chemical Society. (b) Optimization process of printing parameters via Bayesian methods. Copyright 2021, Elsevier. (c) (ⅰ) Prediction results of CNN models on the printing status. (ⅱ) Experimental results on automatic optimization of printing parameters. Copyright 2022, AccScience Publishing. (d) The schematic diagram of a closed-loop control strategy via reinforcement learning. Copyright 2022, ACM. (e) Prediction results on the evolution process of inkjet printing. Copyright 2023, Elsevier. (f) Sensing results of surface deformation using PCA algorithms. Copyright 2020, AAAS. (g) A schematic diagram of the printing head's motion controllers, built by ANN models. Copyright 2023, Wiley.