A surface-to-surface contact search method enhanced by deep learning

Oishi, Atsuya; Yagawa, Genki

doi:10.1007/s00466-019-01811-2

Cited by 19 publications

(3 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applications include predictions of stress from strain [366,367], flow stresses from temperatures, strain rates and strains [368,369], yield functions [370], crack opening responses from stresses [371], contact stiffness from penetration and contact pressure [372], point of contact from position of neighboring nodes of finite elements [373], or control points of NURBS surfaces [374]. Source terms of simplified equations or coarser discretizations have also been learned for turbulence [74,375,376] and the wave equation [377].…”

Section: Model Substitutionmentioning

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: Model Substitutionmentioning

confidence: 99%

Deep learning in computational mechanics: a review

Herrmann,

Kollmannsberger

2024

Comput Mech

View full text Add to dashboard Cite

show abstract

“…The internal and external mass transfer of degraded-PE particles released from plastic waste could be affected by the experimental factors of pH, temperature, moisture content, porosity of culture media and biological growth (Fulazzaky, 2011). The porosity of growth media increased when mixing with rice husk is due to the pore widening by smaller average particle size of rice husks than laterite causing an increased moisture content of the mixed-media affected by an increased surface contact (Oishi and Yagawa, 2020). An increase in the availability of carbon source in the interior channels of growth media causing a utilization of carbon by bacterial-fungal consortium (BFC) to survive under stress conditions can stabilize the pattern of BFC growth affected the rate of internal, external and global mass transfer (Peng et al, 2022;Wang et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Mass transfer kinetics and mechanisms of polyethylene degradation mediated by bacterial-fungal consortium

Fachrul

Fulazzaky

Rinanti

et al. 2023

Preprint

View full text Add to dashboard Cite

Understanding the degradation rate of polyethylene (PE) plastic mediated by bacterial-fungal consortium (BFC) is important to ensure an effective design process of bioremediation technology. This study aims to investigate the degradation behavior of PE plastic waste mediated by the BFC colonies using the modified mass transfer factor models to get better understanding on the kinetics and mechanisms of internal, external and global mass transfer. The performance of rectangular reactor (RR) to degrade PE plastic reaching 61.5% of the efficiency shows an increased efficiency of 55.9% stimulated by the presence of BFC strains in the breakdown of complex PE molecules during the process of bioremediation. Trend in the variation of [kLa]d value viewed almost the same with that of [kLa]g value is higher than that of [kLa]f value during 150 days of the experiment hence the rate-limiting step of PE plastic waste degraded depends on the resistance of external mass transfer. Analysis of degradation efficiency pursuant to both the factors of internal and external mass transfer during the 150-day experimental period provides a new insight on the role of BFC strains to increase the performance of RR process contributing to advance the future bioremediation process of PE plastic waste.

show abstract

“…ANNs are modeled to mimic the neural network in a brain, such that each artificial neuron communicates with other connected artificial neurons similar to synapses in the brain [46]. ANNs have been employed to study various problems such as inverse problems [47,48], constitutive modeling [49][50][51], damage detection [52,53], and local contact search [54,55]. Using ANNs, Manevitz et al [56] predicted the optimal placement of nodes on a two-dimensional geometry to generate a finite element mesh.…”

Section: Introductionmentioning

confidence: 99%

A Bayesian regularization-backpropagation neural network model for peeling computations

Gouravaraju,

Narayan,

Sauer

et al. 2020

Preprint

View full text Add to dashboard Cite

Bayesian regularization-backpropagation neural network (BR-BPNN), a machine learning algorithm, is employed to predict some aspects of the gecko spatula peeling such as the variation of the maximum normal and tangential pull-off forces and the resultant force angle at detachment with the peeling angle. The input data is taken from finite element (FE) peeling results. The neural network is trained with 75% of the FE dataset. The remaining 25% are utilized to predict the peeling behavior. The training performance is evaluated for every change in the number of hidden layer neurons to determine the optimal network structure. The relative error is calculated to draw a clear comparison between predicted and FE results. It is observed that BR-BPNN models have significant potential to estimate the peeling behavior.

show abstract

A surface-to-surface contact search method enhanced by deep learning

Cited by 19 publications

References 54 publications

Deep learning in computational mechanics: a review

Deep learning in computational mechanics: a review

Mass transfer kinetics and mechanisms of polyethylene degradation mediated by bacterial-fungal consortium

A Bayesian regularization-backpropagation neural network model for peeling computations

Contact Info

Product

Resources

About