Elucidating the auxetic behavior of cementitious cellular composites using finite element analysis and interpretable machine learning

Lyngdoh, Gideon A.; Kelter, Nora-Kristin; Doner, Sami; Krishnan, N. M. Anoop; Das, Sumanta

doi:10.1016/j.matdes.2021.110341

Cited by 26 publications

(11 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As common approaches for the evaluation such as finite element analysis and experiments are time-consuming and expensive, a trade-off between performance and time is a common limitation of this method. Therefore, ML regression models have been developed as surrogate models to predict the performance of designs and accelerate the evaluations [29,[81][82][83][84]. These models can be divided into two categories based on the dimension of prediction: direct value prediction of evaluation metrics and domain prediction for complex or undecided metrics.…”

Section: Performance Predictionmentioning

confidence: 99%

A critical review on the application of machine learning in supporting auxetic metamaterial design

Zhang,

Zhao

2024

J. Phys. Mater.

View full text Add to dashboard Cite

The progress of machine learning (ML) in the past years has opened up new opportunities to the design of auxetic metamaterials. However, successful implementation of ML algorithms remains challenging, particularly for complex problems such as domain performance prediction and inverse design.In this paper, we first reviewed classic auxetic designs and summarized their variants in different applications. The enormous variant design space leads to challenges using traditional design or topology optimization.Therefore, we also investigated how ML techniques can help address design challenges of auxetic metamaterials and when researchers should deploy them. The theories behind the techniques are explained, along with practical application examples from the analysed literature. The advantages and limitations of different ML algorithms are discussed and trends in the field are highlighted. Finally, two practical problems of ML-aided design, design scales and data collection are discussed.

show abstract

Section: Performance Predictionmentioning

confidence: 99%

A critical review on the application of machine learning in supporting auxetic metamaterial design

Zhang,

Zhao

2024

J. Phys. Mater.

View full text Add to dashboard Cite

show abstract

“…Yang et al [ 50 ] used the Gaussian random field (GRF) method to create a synthetic microstructure image dataset of materials with different compositions and dispersion patterns. In addition, there are several common means of generating data today, such as the use of the finite element method (FEM) to generate high-contrast composites [ 51 ], two-dimensional (2D) mosaic composites [ 52 , 53 , 54 ], as well as microstructure [ 55 , 56 , 57 , 58 ] and datasets [ 59 , 60 , 61 , 62 , 63 ] of three-dimensional (3D) materials. The existing studies suggest that combining diverse knowledge from materials science, solid mechanics, and other related fields can generate datasets that are more representative of the design space and thus give better results with the applied models.…”

Section: Datamentioning

confidence: 99%

A Review of Performance Prediction Based on Machine Learning in Materials Science

Liu

Huang

et al. 2022

Nanomaterials

View full text Add to dashboard Cite

With increasing demand in many areas, materials are constantly evolving. However, they still have numerous practical constraints. The rational design and discovery of new materials can create a huge technological and social impact. However, such rational design and discovery require a holistic, multi-stage design process, including the design of the material composition, material structure, material properties as well as process design and engineering. Such a complex exploration using traditional scientific methods is not only blind but also a huge waste of time and resources. Machine learning (ML), which is used across data to find correlations in material properties and understand the chemical properties of materials, is being considered a new way to explore the materials field. This paper reviews some of the major recent advances and applications of ML in the field of properties prediction of materials and discusses the key challenges and opportunities in this cross-cutting area.

show abstract

“…Some researchers [33,34] have also attempted to develop the cellular cementitious composites (CCCs) by moulding the cementitious mortar mix into cellular structure by casting them into 3D printed cellular shaped silicone moulds. These composites were tested under compression and NPR was observed for the auxetic CCCs, which was further studied numerically in [35,36]. However, brittle failures were observed in those studies due to the absence of reinforcement.…”

Section: Introductionmentioning

confidence: 99%

Flexural behaviour of cementitious composites embedded with 3D printed re-entrant chiral auxetic meshes

Zahra,

Asad,

Thamboo

2024

Smart Mater. Struct.

View full text Add to dashboard Cite

3D printed auxetic metamaterials can be used to make high performing cementitious composites to strengthen existing structures and elements due to their negative Poisson’s ratio behaviour and high energy absorbing characteristics. In this paper, three different re-entrant chiral auxetic (RCA) meshes of various cell geometries and orientations were developed by 3D printing them using poly-lactic acid (PLA) and thermoplastic polyurethane (TPU) filament. The developed meshes were tested under out-of-plane flexure to study their load carrying capacity, ductility and energy absorption characteristics, especially to characterise the best cell orientation. The horizontal cells provided enhanced load carrying and energy absorption characteristics for all three cell geometries for both materials. These RCA meshes were then embedded into low and high strength premix cement mortar matrices to develop Auxetic Cementitious Composites (ACC). In total, forty-two ACC specimens were casted and tested under flexural loading. The results were studied in terms of their failure patterns, load-displacement responses, flexural capacities, ductility and energy absorption. The RCA meshes made of PLA filament showed limited capacity and energy absorption as compared to RCA meshes made of TPU filament due to extended flexibility and resilience provided by TPU meshes. The RCA meshes with a denser cell structure exhibited highest flexural capacity and effective energy absorption of 14,700 kJ/m2 for TPU-RCA mesh embedded into high strength cement mortar matrix. The results obtained in this study have enabled to understand the flexural behaviour of cementitious composites embedded with 3D printed auxetic lattices and to strengthen the existing structures.

show abstract

Elucidating the auxetic behavior of cementitious cellular composites using finite element analysis and interpretable machine learning

Cited by 26 publications

References 77 publications

A critical review on the application of machine learning in supporting auxetic metamaterial design

A critical review on the application of machine learning in supporting auxetic metamaterial design

A Review of Performance Prediction Based on Machine Learning in Materials Science

Flexural behaviour of cementitious composites embedded with 3D printed re-entrant chiral auxetic meshes

Contact Info

Product

Resources

About