Computational Mechanics with Neural Networks

Yagawa, Genki; Oishi, Atsuya

doi:10.1007/978-3-030-66111-3

Cited by 12 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous review articles on deep learning for specific applications have already emerged (see [22,23] for topology optimization, [24] for full waveform inversion, [25][26][27][28][29] for fluid mechanics, [30] for continuum mechanics, [31] 1 The considered journals are Computer Methods in Applied Mechanics and Engineering, Computers & Mathematics with Applications, Computers & Structures, Computational Mechanics, Engineering with Computers, Journal of Computational Physics. 2 Pioneering works exploring neural networks for computational mechanics prior to the current rise of deep learning are compiled in reviews such as [3,4], see [5] for a more recent treatment. Contributions across almost all of the discussed categories have already been made before the year 2000.…”

Section: Motivationmentioning

confidence: 99%

Deep learning in computational mechanics: a review

Herrmann,

Kollmannsberger

2024

Comput Mech

View full text Add to dashboard Cite

The rapid growth of deep learning research, including within the field of computational mechanics, has resulted in an extensive and diverse body of literature. To help researchers identify key concepts and promising methodologies within this field, we provide an overview of deep learning in deterministic computational mechanics. Five main categories are identified and explored: simulation substitution, simulation enhancement, discretizations as neural networks, generative approaches, and deep reinforcement learning. This review focuses on deep learning methods rather than applications for computational mechanics, thereby enabling researchers to explore this field more effectively. As such, the review is not necessarily aimed at researchers with extensive knowledge of deep learning—instead, the primary audience is researchers on the verge of entering this field or those attempting to gain an overview of deep learning in computational mechanics. The discussed concepts are, therefore, explained as simple as possible.

show abstract

Section: Motivationmentioning

confidence: 99%

Deep learning in computational mechanics: a review

Herrmann,

Kollmannsberger

2024

Comput Mech

View full text Add to dashboard Cite

show abstract

“…Comprising a structure of multilayered processing components, each stratum encompasses multiple units, with each unit personifying a neuron. These neurons, also referred to as nodes, receive input from the neurons in the preceding layer and generate an individual output value 49 . Within this specific artificial neural network (ANN) model employing the error backpropagation algorithm, various hyperparameters warrant consideration for the optimal functioning of the model.…”

Section: Modeling and Optimizationmentioning

confidence: 99%

Tuning Drafting Zone Parameters for Polyester Yarn within a Ring Spinning System: Modeling and Optimization

Savadroodbari,

Razbin,

Hasani

et al. 2023

Preprint

View full text Add to dashboard Cite

Most textile products incorporate yarn as a fundamental element in the production process. Among various yarn manufacturing methods, the ring spinning system stands out as a crucially employed technology due to its advantages including yarn quality, evenness, low hairiness, and ease of handling. The parameters of drafting zone in this technology have a great impact on the quality of yarns. Typically, tuning this drafting zone parameters is time-consuming and costly through trial and error method. This study introduces an algorithmic procedure based on response surface methodology (RSM), experimental modeling, and multi-objective optimization to reduce unevenness percentage (U%) and imperfection index (IPI). Input parameters, including cots hardness of front and back top rollers, spacer size, and break draft, are optimized. Results indicate superior prediction performance of the artificial neural network (ANN) (average vaule of TGF = 1.9996) compared to RSM (average value of TGF = 1.8668). Consequently, ANN is selected for optimization. Furthermore, coupling the genetic algorithm with two ANN-based models reduced IPI from 39 to 33.67 and a reduction from 9.73–9.67% occurred in terms of U%. The final setting of Input parameters were cots hardness of front roller of 70 shore and cots hardness of back roller of 76 shore, spacer size 2.8 mm, and break draft of 1.26. This method efficiently optimizes the drafting zone parameter, enhancing yarn quality.

show abstract

“…The classical numerical paradigm is based on making use of the observed experimental data and then using the calibrated material model in other calculations. Often times the method is expensive and time-consuming while being empirical in nature [2][3][4]. A new direction based on data-driven techniques using machine learning architectures opened up new methods for computational solid mechanics [5][6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Using conditional generative adversarial networks for the prediction of stresses in an adhesive composite

Khan,

Balzani

2023

Proc Appl Math and Mech

View full text Add to dashboard Cite

Fiber reinforced adhesives are an integral part of wind energy turbine blades and play an important role in evaluation of structural integrity of the blades. Digitization of manufacturing processes and demand for fast and efficient stress analysis argues for the application of deep learning. As a step forward in using deep learning to predict structural properties in composite, the work would explore the applicability of deep learning methods to 2D fiber reinforced composite. In this work, a composite adhesive used in wind energy turbine blades is used as an illustrative example. The composite adhesive when viewed using a CT scan machine shows a heterogeneous structure with two phases, a softer matrix phase and a much stiff fiber phase. For this purpose, several CT scan images of the fiber adhesive composite are used. The images on subsequent FEA analysis serves as the training data for the deep learning framework. Once trained, the neural network would be able to predict the stress distributions in the structure. We apply conditional adversarial networks as general purpose solutions to problems focused on stress prediction, which could be thought of as an image‐to‐image translation from the microstructure domain to the stress domain. These networks in addition to learning the mapping from input image to output image also learn a loss function to train for this mapping. This makes the method more generic because otherwise different loss formulations for different problems have to be formulated.

show abstract

Computational Mechanics with Neural Networks

Cited by 12 publications

References 0 publications

Deep learning in computational mechanics: a review

Deep learning in computational mechanics: a review

Tuning Drafting Zone Parameters for Polyester Yarn within a Ring Spinning System: Modeling and Optimization

Using conditional generative adversarial networks for the prediction of stresses in an adhesive composite

Contact Info

Product

Resources

About