Extraction of mechanical properties of materials through deep learning from instrumented indentation

By Lu Lu, Ming Dao, Punith Kumar, U. Ramamurty, G. Em Karniadakis, Subra Suresh. Proceedings of the National Academy of Sciences of the United States of America, 2020

317 citations recorded by the source corpus.

Significance Instrumented indentation has emerged as a versatile and practical means of extracting material properties, especially when it is difficult to obtain traditional stress–strain data from large tensile or bend coupon specimens. Accurately solving the inverse problem of depth-sensing indentation is critical for the determination of the elastoplastic properties of materials for a wide variety of structural and functional applications in engineering components. Utilizing the latest developments in deep learning that invoke neural networks and multifidelity datasets, we have developed a general framework for extracting elastoplastic properties of engineering alloys with markedly improved accuracy and training efficiency than has been possible thus far. We validate this method by assessing estimates of extracted properties in direct comparison with independent experimental measurement. Instrumented indentation has been developed and widely utilized as one of the most versatile and practical means of extracting mechanical properties of materials. This method is particularly desirable for those applications where it is difficult to experimentally determine the mechanical properties using stress–strain data obtained from coupon specimens. Such applications include material processing and manufacturing of small and large engineering components and structures involving the following: three-dimensional (3D) printing, thin-film and multilayered structures, and integrated manufacturing of materials for coupled mechanical and functional properties. Here, we utilize the latest developments in neural networks, including a multifidelity approach whereby deep-learning algorithms are trained to extract elastoplastic properties of metals and alloys from instrumented indentation results using multiple datasets for desired levels of improved accuracy. We have established algorithms for solving inverse problems by recourse to single, dual, and multiple indentation and demonstrate that these algorithms significantly outperform traditional brute force computations and function-fitting methods. Moreover, we present several multifidelity approaches specifically for solving the inverse indentation problem which 1) significantly reduce the number of high-fidelity datasets required to achieve a given level of accuracy, 2) utilize known physical and scaling laws to improve training efficiency and accuracy, and 3) integrate simulation and experimental data for training disparate datasets to learn and minimize systematic errors. The predictive capabilities and advantages of these multifidelity methods have been assessed by direct comparisons with experimental results for indentation for different commercial alloys, including two wrought aluminum alloys and several 3D printed titanium alloys.

Subfields: Materials Chemistry, Mechanical Engineering, Mechanics of Materials

View Paper: https://www.semanticscholar.org/paper/1d7e85af03b1c6629e829f409f9fbb3caf16c407

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

In Mechanical Engineering

In Mechanics of Materials

Citations in the corpus

Analyses of internal structures and defects in materials using physics-informed neural networks (2022, unknown): “̃ r inc (X;  ) = det( ̃ F(X;  ) ) − 1, X ∈ (  geo ) (7)”
A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data (2021, methodology): “We also have to facilitate multi-ﬁdelity data that not only include multi-resolution data but also data corresponding to diﬀerent levels of physical complexity, and hence training of NN requires special multi-ﬁdelity methods such as in [34, 35, 36].”
Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next (2022, methodology): “DeepXDE is used by the authors for: for inverse scattering (Chen et al, 2020b), or deriving mechanical characteristics from materials with MFNNs (Lu et al, 2020).”
Learning the solution operator of parametric partial differential equations with physics-informed DeepONets (2021, unknown): “Nevertheless, these approaches have found wide applicability across diverse applications including fluid mechanics [19, 20], heat transfer [21], bio-engineering [22, 23], materials [24, 25, 26], and finance [27, 28], showcasing the remarkable effectiveness of ML techniques in learning black-box func”