An investigation on the coupling of data-driven computing and model-driven computing

Yang, Jie; Huang, Wei; Huang, Qun; Hu, Heng

doi:10.1016/j.cma.2022.114798

Cited by 20 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, some models begin with a black-box model based on the event process, then substitute some steps in the event with a white-box model to achieve a better gray-box model [66]. Some build both black-box and white-box models at the same time, then link the two models with a coupling strategy [67].…”

Section: Potential Research Opportunitiesmentioning

confidence: 99%

Machine Learning in Reservoir Engineering: A Review

Zhou,

Liu,

Liu

et al. 2024

Processes

View full text Add to dashboard Cite

With the rapid progress of big data and artificial intelligence, machine learning technologies such as learning and adaptive control have emerged as a research focus in petroleum engineering. They have various applications in oilfield development, such as parameter prediction, optimization scheme deployment, and performance evaluation. This paper provides a comprehensive review of these applications in three key scenarios of petroleum engineering, namely hydraulic fracturing and acidizing, chemical flooding and gas flooding, and water injection. This article first introduces the steps and methods of machine learning processing in these scenarios, then discusses the advantages, disadvantages, existing challenges, and future prospects of these machine learning methods. Furthermore, this article compares and contrasts the strengths and weaknesses of these machine learning methods, aiming to help researchers select and improve their methods. Finally, this paper identifies some potential development trends and research directions of machine learning in petroleum engineering based on the current issues.

show abstract

Section: Potential Research Opportunitiesmentioning

confidence: 99%

Machine Learning in Reservoir Engineering: A Review

Zhou,

Liu,

Liu

et al. 2024

Processes

View full text Add to dashboard Cite

show abstract

“…We found a formula for the normal N in principal stress space by equation ( 13) provided we have information about the initial yield surface Φ(θ), cf. equation (12). To address the latter, we assume a combined tensile-torsion test resulting in stress fields of the form…”

Section: Data Enforced Tangentmentioning

confidence: 99%

“…The approach is well analyzed for non-linear elasticity [1][2][3][4][5], dynamics [6], finite strain [7], and material data identification [8]. Further applications are found in non-local mechanics [9], coupled electro-mechanical problems [10], decoupled homogenization schemes [11] and model-driven coupling [12]. An extension of the data-driven scheme has been made by using the tangent space to improve the learning of the underlying data structure.…”

Section: Introductionmentioning

confidence: 99%

Model‐free data‐driven inelasticity in Haigh‐Westergaard space ‐ a study how to obtain data points from measurements

Ciftci

Hackl

2023

Proc Appl Math and Mech

View full text Add to dashboard Cite

Model‐free data‐driven computational mechanics replace phenomenological models with numerical simulations in strain‐stress space based on sample data sets. The approach has recently been extended to inelasticity problems employing structured data sets, tangent space information, and transition rules. Coverage of qualified data states and calculation of the related tangent space is critical from the standpoint of actual application. This study applies the data‐driven paradigm to elasto‐plasticity with isotropic hardening. We develop our method using Haigh‐Westergaard coordinates, which provide information on the underlying material yield surface. Based on this, we employ a combined tension‐torsion test to cover the yield surface knowledge and a single tensile test to determine the tangent space. Under compatibility and equilibrium requirements, the resulting data‐driven technique minimizes the distance over the Haigh‐Westergaard space augmented by directions in the tangent space.

show abstract