Artificial Intelligence Based Space Reduction of Structural Models
12 Apr 2021-
TL;DR: The ESI Group’s aim is to provide real-time information about the physical properties of the Saarinen Tower and its surroundings to help engineers and scientists better understand the structure and purpose of the building.
Abstract: The need of solving industrial problems using faster and less computationally expensive techniques is becoming a requirement to cope with the present digital transformation of most industries. Recently, data is conquering the domain of engineering with different purposes: (i) defining data-driven models of materials, processes, structures and systems, whose physics-based models, when they exists, remain too inaccurate; (ii) enriching the existing physics-based models within the so-called hybrid paradigm; and (iii) using advanced machine learning and artificial intelligence techniques for scales bridging (upscaling), that is, for creating models that operating at the coarse-grained scale (cheaper in what respect the computational resources) enables integrating the fine-scale richness. The present work addresses the last item, aiming at enhancing standard structural models (defined in 2D shell geometries) for accounting all the fine-scale details (3D with rich through-the-thickness behaviors). For this purpose, two main strategies will be combined: (i) the in-plane-out-of-plane proper generalized decomposition -PGD- serving to provide the fine-scale richness; and (ii) advance machine learning techniques able to learn and extract the regression relating the input parameters with those high-resolution detailed descriptions.
Citations
More filters
01 Aug 2022
TL;DR: A review of the current status of ML and its specific application to polymer composites process simulation can be found in this article , where the types of ML algorithms, tools, techniques used in various applications and their couplings with other CAE software tools are summarized and the overall result/potential of each application/method is highlighted.
Abstract: Over the last 20 years Machine Learning (ML) has been applied to a wide variety of applications in the fields of engineering and computer science. In the field of material science in particular, it has been used to help speed up predictions of structure property relationships and in general enhance the material design process. In this paper, we review the current status of ML and its specific application to polymer composites process simulation. We also review some case studies going beyond this focus, especially in the fields of computational fluid dynamics, solid mechanics and Computer Aided Engineering (CAE), to show the potential for further application in our research area. The types of ML algorithms, tools, techniques used in the various applications and their couplings with other CAE software tools are summarized and the overall result/potential of each application/method is highlighted.
10 citations
01 Jan 2023
TL;DR: In this article , the Artificial Neuronal Network (ANN) methodology is applied as well as a standard interpolation to develop two different simplified models of a 3D cavity flow.
Abstract: AbstractThe great opportunities of the new technology of artificial intelligence and the growing computational capacities together with interacting sensor technology leads to the next industrial revolution called Industry 4.0. In this field the combination of artificial intelligence with numerical simulation to develop a simplified model of a given system can be used for establishing a digital twin of the system for better control and more efficient performance. In this paper, the Artificial Neuronal Network (ANN) methodology is applied as well as a standard interpolation to develop two different simplified models of a 3D cavity flow. The problem is analyzed by Computational Fluid Dynamics (CFD). The CFD simulations are carried out using a commercial software for a case, for which experimental data from the literature exists. In general, the combination of CFD and ANN has been performed in different researches on different applications. Thus, the present paper focuses rather on the comparison of a standard interpolation procedure to ANN, utilizing two different error calculations.KeywordsFluid dynamicsArtificial intelligenceArtificial neuronal networksIndustry 4.0
References
More filters
TL;DR: In-plane–out-of-plane separated representation of the involved fields within the context of the Proper Generalized Decomposition allows solving the fully 3D model by keeping a 2D characteristic computational complexity, without affecting the solvability of the resulting multidimensional model.
175 citations
"Artificial Intelligence Based Space..." refers background in this paper
...[1-5]; (ii) thermal models defined in plates and laminates [6-7]; (iii) flows of Newtonian and non-Newtonian fluids in thin flat and rough gaps [8-12]; (iv) electromagnetism in stratified composites [13]; ....
[...]
TL;DR: In this article, a new paradigm for addressing the solution of such complex models, the so-called Proper Generalized Decomposition based model order reduction, was developed for addressing efficiently the simulation of a challenging composites manufacturing process.
Abstract: Composite materials and their related manufacturing processes involve many modeling and simulation issues, mainly related to their multi-physics and multi-scale nature, to the strong couplings and the complex geometries. In our former works we developed a new paradigm for addressing the solution of such complex models, the so-called Proper Generalized Decomposition based model order reduction. In this work we are summarizing the most outstanding capabilities of such methodology and then all these capabilities will be put together for addressing efficiently the simulation of a challenging composites manufacturing process, the automated tape placement.
102 citations
"Artificial Intelligence Based Space..." refers background in this paper
...[1-5]; (ii) thermal models defined in plates and laminates [6-7]; (iii) flows of Newtonian and non-Newtonian fluids in thin flat and rough gaps [8-12]; (iv) electromagnetism in stratified composites [13]; ....
[...]
TL;DR: The analyzed examples prove the potentiality and efficiency of the proposed strategy, where the computational complexity was found evolving as reported in former works, proving that 3D solutions can be computed at a 2D cost.
Abstract: The solution of 3D models in degenerated geometries in which some characteristic dimensions are much lower than the other ones -e.g. beams, plates, shells,...- is a tricky issue when using standard mesh-based discretization techniques. Separated representations allow decoupling the meshes used for approximating the solution along each coordinate. Thus, in plate or shell geometries 3D solutions can be obtained from a sequence of 2D and 1D problems allowing fine and accurate representation of the solution evolution along the thickness coordinate while keeping the computational complexity characteristic of 2D simulations. In a former work this technique was considered for addressing the 3D solution of thermoelastic problems defined in plate geometries. In this work, the technique is extended for addressing the solution of 3D elastic problems defined in shell geometries. The capabilities of the proposed approach are illustrated by considering some numerical examples involving different degrees of complexity, from simple shells to composite laminates involving stiffeners. The analyzed examples prove the potentiality and efficiency of the proposed strategy, where the computational complexity was found evolving as reported in our former works, proving that 3D solutions can be computed at a 2D cost.
55 citations
"Artificial Intelligence Based Space..." refers background in this paper
...[1-5]; (ii) thermal models defined in plates and laminates [6-7]; (iii) flows of Newtonian and non-Newtonian fluids in thin flat and rough gaps [8-12]; (iv) electromagnetism in stratified composites [13]; ....
[...]
TL;DR: In this paper, the authors proposed a new approach to solve linear elastic crack problems in plates using the so-called Proper Generalized Decomposition (PGD) method, which enables to solve the crack problem in an efficient way by obtaining a single solution in which the Poisson's ratio and the plate thickness B are non-fixed parameters.
42 citations
"Artificial Intelligence Based Space..." refers background in this paper
...[1-5]; (ii) thermal models defined in plates and laminates [6-7]; (iii) flows of Newtonian and non-Newtonian fluids in thin flat and rough gaps [8-12]; (iv) electromagnetism in stratified composites [13]; ....
[...]
TL;DR: In this paper, the authors revisited the squeeze flow of continuous fiber laminates from the perspective of proper generalized decomposition that makes possible extremely detailed 3D calculations with a computational cost characteristic of 2D (sometimes 1D) simulations.
Abstract: Thermoplastic composites are attractive because they can be recycled and exhibit superior mechanical properties As part of a more general research effort, in this paper attention is paid to squeeze flow of continuous fiber laminates In the case of unidirectional prepregs, the ply constitutive equation, when elastic effects are neglected, can be modeled as a transversally isotropic fluid, that must satisfy the fiber inextensibility as well as the fluid incompressibility When laminate is squeezed, depending on the plies orientation and the lubrication conditions at their interfaces, the flow kinematics exhibits a complex dependency along the laminate thickness requiring one to describe the detailed velocity field through the thickness Simulations at this scale are computationally intensive or almost impossible with standard FE techniques In this work the squeeze flow of laminates is revisited from the perspective of the Proper Generalized Decomposition that makes possible extremely detailed 3D calculations with a computational cost characteristic of 2D (sometimes 1D) simulations
37 citations
"Artificial Intelligence Based Space..." refers background in this paper
...[1-5]; (ii) thermal models defined in plates and laminates [6-7]; (iii) flows of Newtonian and non-Newtonian fluids in thin flat and rough gaps [8-12]; (iv) electromagnetism in stratified composites [13]; ....
[...]