Predictions of transient vector solution fields with sequential deep operator network DOI Creative Commons
Junyan He, Shashank Kushwaha, Jaewan Park

и другие.

Acta Mechanica, Год журнала: 2024, Номер 235(8), С. 5257 - 5272

Опубликована: Июнь 11, 2024

Abstract The deep operator network (DeepONet) structure has shown great potential in approximating complex solution operators with low generalization errors. Recently, a sequential DeepONet (S-DeepONet) was proposed to use learning models the branch of predict final solutions given time-dependent inputs. In current work, S-DeepONet architecture is extended by modifying information combination mechanism between and trunk networks simultaneously vector multiple components at time steps evolution history, which first literature using DeepONets. Two example problems, one on transient fluid flow other path-dependent plastic loading, were demonstrate capabilities model handle different physics problems. trained inverse parameter identification via genetic algorithm application model. almost all cases, achieved an $$R^2$$ R 2 value above 0.99 relative $$L_2$$ L error less than 10% only 3200 training data points, indicating superior accuracy. model, having 0.4% more parameters scalar can two output accuracy similar independently 20.8% faster time. inference least three orders magnitude direct numerical simulations, identifications are highly efficient accurate.

Язык: Английский

DeepOKAN: Deep operator network based on Kolmogorov Arnold networks for mechanics problems DOI Creative Commons
Diab Abueidda,

Panos Pantidis,

Mostafa E. Mobasher

и другие.

Computer Methods in Applied Mechanics and Engineering, Год журнала: 2025, Номер 436, С. 117699 - 117699

Опубликована: Янв. 14, 2025

Язык: Английский

Процитировано

13

A multi-fidelity deep operator network (DeepONet) for fusing simulation and monitoring data: Application to real-time settlement prediction during tunnel construction DOI Creative Commons
Xu Chen, Ba Trung Cao, Yong Yuan

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 133, С. 108156 - 108156

Опубликована: Март 6, 2024

Ground settlement prediction during mechanized tunneling is of paramount importance and remains a challenging research topic. Typically, two paradigms are existing: physics-driven approach utilizing numerical simulation models for prediction, data-driven employing machine learning techniques to learn mappings between influencing factors the settlement. To integrate advantages both approaches assimilate data from different sources, we propose multi-fidelity deep operator network (DeepONet) framework, leveraging recently developed methods. The presented framework comprises components: low-fidelity subnet that captures fundamental ground patterns obtained finite element simulations, high-fidelity learns nonlinear correlation real engineering monitoring data. A pre-processing strategy causality adopted consider spatio-temporal characteristics tunnel excavation. results show proposed method can effectively capture physical information provided by simulations accurately fit measured (R2 around 0.9) as well. Notably, even when dealing with very limited noisy (with 50% error), model robust, achieving satisfactory R2>0.8. In comparison, R2 score pure simulation-based only 0.2. utilization transfer significantly reduces training time 20 min within 30 s, showcasing potential our real-time construction.

Язык: Английский

Процитировано

15

Rapid prediction of indoor airflow field using operator neural network with small dataset DOI
Hu Gao,

Weixin Qian,

Jiankai Dong

и другие.

Building and Environment, Год журнала: 2024, Номер 251, С. 111175 - 111175

Опубликована: Янв. 20, 2024

Язык: Английский

Процитировано

11

Prediction of thermal runaway for a lithium-ion battery through multiphysics-informed DeepONet with virtual data DOI
Jinho Jeong, Eunji Kwak, Jun‐Hyeong Kim

и другие.

eTransportation, Год журнала: 2024, Номер 21, С. 100337 - 100337

Опубликована: Май 9, 2024

Язык: Английский

Процитировано

10

Virtual sensing-enabled digital twin framework for real-time monitoring of nuclear systems leveraging deep neural operators DOI Creative Commons
Raisa Bentay Hossain, Farid Ahmed, Kazuma Kobayashi

и другие.

npj Materials Degradation, Год журнала: 2025, Номер 9(1)

Опубликована: Март 6, 2025

Язык: Английский

Процитировано

2

Advanced deep operator networks to predict multiphysics solution fields in materials processing and additive manufacturing DOI Creative Commons
Shashank Kushwaha, Jaewan Park, Seid Korić

и другие.

Additive manufacturing, Год журнала: 2024, Номер 88, С. 104266 - 104266

Опубликована: Май 1, 2024

Unlike classical artificial neural networks, which require retraining for each new set of parametric inputs, the Deep Operator Network (DeepONet), a lately introduced deep learning framework, approximates linear and nonlinear solution operators by taking functions (infinite-dimensional objects) as inputs mapping them to complete fields. In this paper, two newly devised DeepONet formulations with sequential Residual U-Net (ResUNet) architectures are trained first time simultaneously predict thermal mechanical fields under variable loading, loading histories, process parameters, even geometries. Two real-world applications demonstrated: 1- coupled thermo-mechanical analysis steel continuous casting multiple visco-plastic constitutive laws 2- sequentially direct energy deposition additive manufacturing. Despite highly challenging spatially target distributions, DeepONets can infer reasonably accurate full-field temperature stress solutions several orders magnitude faster than traditional optimized finite-element (FEA), when FEA simulations run on latest high-performance computing platforms. The proposed model's ability provide field predictions almost instantly unseen input parameters opens door future preliminary evaluation design optimization these vital industrial processes.

Язык: Английский

Процитировано

7

Physics-informed deep operator networks with stiffness-based loss functions for structural response prediction DOI Creative Commons
Bilal Ahmed, Yuqing Qiu, Diab Abueidda

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 144, С. 110097 - 110097

Опубликована: Янв. 25, 2025

Язык: Английский

Процитировано

1

Machine learning-based constitutive modelling for material non-linearity: A review DOI Creative Commons
Arif Hussain, Amir Hosein Sakhaei, Mahmood Shafiee

и другие.

Mechanics of Advanced Materials and Structures, Год журнала: 2024, Номер unknown, С. 1 - 19

Опубликована: Дек. 17, 2024

Machine learning (ML) models are widely used across numerous scientific and engineering disciplines due to their exceptional performance, flexibility, prediction quality, ability handle highly complex problems if appropriate data available. One example of such areas which has attracted a lot attentions in the last couple years is integration data-driven approaches material modeling. There been several successful researches implementing ML-based constitutive instead classical phenomenological for various materials, particularly those with non-linear mechanical behaviors. This review paper aims systematically investigate literature on materials classify these based suitability non-linearity including Non-linear elasticity (hyperelasticity), plasticity, visco-elasticity, visco-plasticity. Furthermore, we also reviewed compared that have applied architectured as groups designed represent specific behaviors might not exist conventional categories. The other goal this provide initial steps understanding modeling, artificial neural networks (ANN), Gaussian processes, random forests (RF), generated adversarial (GANs), support vector machines (SVM), different regression physics-informed (PINN). outlines collection methods, types data, processing approaches, theoretical background ML models, advantage limitations potential future research directions. comprehensive will researchers knowledge necessary develop high-fidelity, robust, adaptable, flexible, accurate advanced materials.

Язык: Английский

Процитировано

5

On the locality of local neural operator in learning fluid dynamics DOI
Ximeng Ye, Hongyu Li,

Jingjie Huang

и другие.

Computer Methods in Applied Mechanics and Engineering, Год журнала: 2024, Номер 427, С. 117035 - 117035

Опубликована: Май 11, 2024

Язык: Английский

Процитировано

4

Neural networks-based line element method for large deflection frame analysis DOI

Weihang Ouyang,

Liang Chen,

An-Rui Liang

и другие.

Computers & Structures, Год журнала: 2024, Номер 300, С. 107425 - 107425

Опубликована: Май 28, 2024

Язык: Английский

Процитировано

3