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

Hassanin, Hany; Alkendi, Yusra; El‐Sayed, M. A.; Essa, Khamis; Zweiri, Yahya

doi:10.1002/adem.201901338

Cited by 61 publications

(39 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additive manufacturing or 3D printing is a technology to create objects layer by layer using a 3D printer according to a digital model. The technology enabling the processing of metals [ 30 , 31 , 32 , 33 ], ceramics [ 34 ], polymers [ 35 ], and composites [ 36 ] has been widely employed in many industries, such as biomedical [ 37 ], defense [ 17 ], aerospace [ 38 , 39 ], and energy [ 40 ]. The ability of AM to process a wide range of materials into objects with intricate geometries such as auxetic and cellular structures and to obtain desired mechanical properties has led to the many advancements of this technology.…”

Section: Introductionmentioning

confidence: 99%

4D Printing of NiTi Auxetic Structure with Improved Ballistic Performance

et al. 2020

Self Cite

View full text Add to dashboard Cite

Auxetic structures have attracted attention in energy absorption applications owing to their improved shear modulus and enhanced resistance to indentation. On the other hand, four-dimensional (4D) printing is an emerging technology that is capable of 3D printing smart materials with additional functionality. This paper introduces the development of a NiTi negative-Poisson’s-ratio structure with superelasticity/shape memory capabilities for improved ballistic applications. An analytical model was initially used to optimize the geometrical parameters of a re-entrant auxetic structure. It was found that the re-entrant auxetic structure with a cell angle of −30° produced the highest Poisson’s ratio of −2.089. The 4D printing process using a powder bed fusion system was used to fabricate the optimized NiTi auxetic structure. The measured negative Poisson’s ratio of the fabricated auxetic structure was found in agreement with both the analytical model and the finite element simulation. A finite element model was developed to simulate the dynamic response of the optimized auxetic NiTi structure subjected to different projectile speeds. Three stages of the impact process describing the penetration of the top plate, auxetic structure, and bottom plate have been identified. The results show that the optimized auxetic structures affect the dynamic response of the projectile by getting denser toward the impact location. This helped to improve the energy absorbed per unit mass of the NiTi auxetic structure to about two times higher than that of the solid NiTi plate and five times higher than that of the solid conventional steel plate.

show abstract

Section: Introductionmentioning

confidence: 99%

4D Printing of NiTi Auxetic Structure with Improved Ballistic Performance

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The DCGAN, Cycle GAN, and Pix2Pix algorithms created realistic microstructures for engineering and functional materials, which are expected to play a pivotal role in either theoretical or ML modeling for microstructure prediction. The status of the generated virtual micrograph was considerably enhanced in comparison to the existing synthetic GAN‐generated micrographs, 23‐27 and has reached a level wherein generated micrographs are qualitatively indistinguishable from the ground truth. The completeness is, of course, dependent upon the size of the training dataset, the types of microstructure, the deep net architectures, and the choice of appropriate hyper‐parameters, and so on.…”

Section: Resultsmentioning

confidence: 98%

“…Despite major issues with GAN, which are mode collapse, non-convergence, and training instability, 22 GAN has been one of the most interesting ideas in machine learning (ML) of the past 10 years. 13 Although conventional ML approaches based on supervised learning are well established in the materials research community, [23][24][25][26][27][28][29][30][31][32] GAN algorithms have just begun to be used for the materials research.…”

mentioning

confidence: 99%

“…One neural network, called the generator, generates new data instances from randomly distributed sample data, and the other, the discriminator, judges them for authenticity; in other words, the discriminator determines whether each instance of data it examines belongs to the genuine training dataset or not. In contrast to the recent boom for deep learning-based artificial intelligence for use in both the chemistry and materials science research fields, [23][24][25][26][27][28][29][30][31][32] the unsupervised learning-based GAN is yet to be spotlighted in both the fields. Nevertheless, we have seen a certain degree of progress in the GAN utilization for the design of molecules, [34][35][36][37][38][39] and the drug discovery, [40][41][42] the inverse design of materials, 43 the design of crystal structure of inorganic materials.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Virtual microstructure design for steels using generative adversarial networks

Lee

Goo

Park

et al. 2020

Engineering Reports

View full text Add to dashboard Cite

The prediction of macro‐scale materials properties from microstructures, and vice versa, should be a key part in modeling quantitative microstructure‐physical property relationships. It would be helpful if the microstructural input and output were in the form of visual images rather than parameterized descriptors. However, only a typical supervised learning technique would be insufficient to build up a model with real‐image‐output. A generative adversarial network (GAN) is required to treat visual images as output for a promising PMPR model. Recently developed deep‐learning‐based GAN techniques such as a deep convolutional GAN (DCGAN), a cycle‐consistent GAN (Cycle GAN), and a conditional GAN‐based image to image translation (Pix2Pix) could be of great help via the creation of realistic microstructures. In this regard, we generated virtual micrographs for various types of steels using a DCGAN, a Cycle GAN, and a Pix2Pix and confirmed the generated micrographs are qualitatively indistinguishable from the ground truth.

show abstract

“…In fact, metal AM is currently applied in the most demanding industrial sectors, i.e. aerospace [1], energy [2], defence [3], and biomedical [4,5]. The technology allows the generation of parts with a complex topologically optimised geometry with internal cavities that were impossible to create with traditional manufacturing processes.…”

Section: Introductionmentioning

confidence: 99%

Powder-based laser hybrid additive manufacturing of metals: a review

Jiménez

Bidare

Hassanin

et al. 2021

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

Recent advances in additive manufacturing (AM) have attracted significant industrial interest. Initially, AM was mainly associated with the fabrication of prototypes, but the AM advances together with the broadening range of available materials, especially for producing metallic parts, have broaden the application areas and now the technology can be used for manufacturing functional parts, too. Especially, the AM technologies enable the creation of complex and topologically optimised geometries with internal cavities that were impossible to produce with traditional manufacturing processes. However, the tight geometrical tolerances along with the strict surface integrity requirements in aerospace, biomedical and automotive industries are not achievable in most cases with standalone AM technologies. Therefore, AM parts need extensive post-processing to ensure that their surface and dimensional requirements together with their respective mechanical properties are met. In this context, it is not surprising that the integration of AM with post-processing technologies into single and multi set-up processing solutions, commonly referred to as hybrid AM, has emerged as a very attractive proposition for industry while attracting a significant R&D interest. This paper reviews the current research and technology advances associated with the hybrid AM solutions. The special focus is on hybrid AM solutions that combine the capabilities of laser-based AM for processing powders with the necessary post-process technologies for producing metal parts with required accuracy, surface integrity and material properties. Commercially available hybrid AM systems that integrate laser-based AM with post-processing technologies are also reviewed together with their key application areas. Finally, the main challenges and open issues in broadening the industrial use of hybrid AM solutions are discussed.

show abstract

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

Cited by 61 publications

References 30 publications

4D Printing of NiTi Auxetic Structure with Improved Ballistic Performance

4D Printing of NiTi Auxetic Structure with Improved Ballistic Performance

Virtual microstructure design for steels using generative adversarial networks

Powder-based laser hybrid additive manufacturing of metals: a review

Contact Info

Product

Resources

About