Abstract
Accurate numerical simulations require constitutive models capable of providing precise material data. Several calibration methodologies have been developed to improve the accuracy of constitutive models. Nevertheless, a model’s performance is always constrained by its mathematical formulation. Machine learning (ML) techniques, such as artificial neural networks (ANNs), have the potential to overcome these limitations. Nevertheless, the use of ML for material constitutive modelling is very recent and not fully explored. Difficulties related to data requirements and training are still open problems. This work explores and discusses the use of ML techniques regarding the accuracy of material constitutive models in metal plasticity, particularly contributing (i) a parameter identification inverse methodology, (ii) a constitutive model corrector, (iii) a data-driven constitutive model using empirical known concepts and (iv) a general implicit constitutive model using a data-driven learning approach. These approaches are discussed, and examples are given in the framework of non-linear elastoplasticity. To conveniently train these ML approaches, a large amount of data concerning material behaviour must be used. Therefore, non-homogeneous strain field and complex strain path tests measured with digital image correlation (DIC) techniques must be used for that purpose.
Highlights
Considerable developments in the field of computational mechanics and the growth in computational power have made it possible for numerical simulation software to emerge and completely revolutionize the engineering industry
This paper showed that an artificial neural networks (ANNs) can be trained as an inverse model for parameter identification; ANNs are paving the way for the development of implicit material models capable of reproducing complex material behavior purely from data
The the network architectures themselves can be designed based on the structure of existing well-known constitutive models; A great number of methodologies employ ANNs as “black boxes” that are not guaranteed to respect the basic laws of physics governing the dynamics of the systems, requiring large amounts of training to do so
Summary
Considerable developments in the field of computational mechanics and the growth in computational power have made it possible for numerical simulation software to emerge and completely revolutionize the engineering industry. With a wide array of software solutions in the market, capable of virtualizing entire design workflows, numerical simulation has become a vital component of the product development process This virtualization has allowed companies to massively reduce the number of time-consuming experiments between design iterations, reducing delays and costs and allowing companies to reach higher levels of competitiveness [3]. In this context, finite element analysis (FEA) has been widely used as a powerful numerical simulation tool in engineering analyses, such as structural analysis, heat transfer and fluid flow. Material characterization has received increasing attention given the need for computational analysis software for precise material data [3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
