Controlling the Properties of Additively Manufactured Cellular Structures Using Machine Learning Approaches

• Published in: Advanced engineering materials Vol. 22; no. 3
• Main Authors: Hassanin, Hany, Alkendi, Yusra, Elsayed, Mahmoud, Essa, Khamis, Zweiri, Yahya
• Format: Journal Article
• Language: English
• Published: 01.03.2020
• Subjects: deep learning; laser powder bed fusion; lattices
• ISSN: 1438-1656; 1527-2648
• DOI: 10.1002/adem.201901338

Cellular structures are lightweight‐engineered materials that have gained much attention with the development of additive manufacturing technologies. This article introduces a precise approach to predict the mechanical properties of additively manufactured lattice structures using deep‐learning approaches. Diamond‐shaped nodal lattice structures are designed by varying strut length, strut diameter, and strut orientation angle. The samples are manufactured using laser powder bed fusion (LPBF) of Ti−64 alloy and subjected to compression testing to measure the ultimate strength, elastic modulus, and specific strength. Machine learning approaches such as shallow neural network (SNN), deep neural network (DNN), and deep learning neural network (DLNN) are developed and compared to the statistical design of experiment (DoE) approach. The trained DLNN model show the highest performance when compared with DNN, DoE, and SNN with a mean percentage error of 5.26%, 14.60%, and 9.39% for the ultimate strength, elastic modulus, and specific strength, respectively. The DLNN model is used to create process maps, and is further validated. The results show that although deep learning is preferred for big data, the optimized DLNN model outperform the statistical DoE approach and can be a favorable tool for lattice structure prediction with limited data. Shallow neural network (SNN), deep neural network (DNN), design of experiments (DoE), and deep learning neural network (DLNN) models are developed to predict the properties of additive manufactured cellular structures. The DLNN showed the highest performance when compared to DNN, DoE and SNN with an error of 5.26%, 14.60%, and 9.39% for the strength, elastic modulus, and specific strength, respectively.