首页|Study Findings from Shanghai Jiao Tong University Broaden Understanding of Machine Learning (A High-fidelity Comprehensive Framework for the Additive Manufacturing Printability Assessment)
Study Findings from Shanghai Jiao Tong University Broaden Understanding of Machine Learning (A High-fidelity Comprehensive Framework for the Additive Manufacturing Printability Assessment)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Elsevier
Current study results on Machine Learning have been published. According to news reporting originating in Shanghai, People's Republic of China, by NewsRx journalists, research stated, "Additive manufacturing is capable of fabricating complex and customized components that cannot be easily and economically produced by other techniques. It is of great significance to determine the printability map for the extensive application of the fabricated parts, which has been hindered by the common defects such as interior pores and surface roughness." Funders for this research include National Natural Science Foundation of China (NSFC), Shanghai Sailing Program, Natural Science Foundation of Shanghai, Major Science and Technology Project of Huaibei. The news reporters obtained a quote from the research from Shanghai Jiao Tong University, "Here, a comprehensive framework including multiphysics model, physics-informed machine learning, and experimental data is proposed to predict the printability. The characteristics for different phenomena (lack of fusion, balling and keyhole) are analyzed by the mechanistic model considering high-fidelity powder-scale model, fluid flow, recoil pressure and Marangoni effect, which provides a more accurate thermal history, molten pool dynamics and surface morphology compared to the finite element model. Classification criterion is established by three mechanistic variables based on the molten pool morphology, which divides the process map into four regions. For the first time, the relationship between the solidified-track surface morphology and the interior quality is established, and the optimal surface morphology corresponding to defectfree printing is determined. The printability is predicted by mathematical machine learning classification models via 10-fold cross-validation method, which validates the classification criterion and the comprehensive framework to assess the printability."
ShanghaiPeople's Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine LearningShanghai Jiao Tong University
NETL
NSTL
Elsevier
