A data-driven physics-constrained deep learning computational framework for solving von Mises plasticity

Roy, Arunabha M.; Guha, Suman

doi:10.1016/j.engappai.2023.106049

Cited by 35 publications

(5 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be used with more automation for ease of the process. Furthermore, the current approach can be extended to various other deep learning applications such as Computer vision [41,42,43], object detection [44,45,46], signal classification [47,48,49,50,51], and different physics-based surrogate models [52,53,54,55,56].…”

Section: Discussionmentioning

confidence: 99%

Efficient Paddy Grains Quality Assessment Approach Utilizing Affordable Sensors

Kumar,

Singh,

Raj

et al. 2023

Preprint

View full text Add to dashboard Cite

In the realm of computer vision, paddy (Oryza Sativa) plays a pivotal role as a globally consumed staple crop. Its cultivation, harvesting, processing, and storage involve intricate quality control. Numerous factors, including weather conditions and irrigation frequency, influence grain quality. To address this, we present an innovative approach that combines image processing and machine learning (ML). Existing methods for rice grain quality assessment, while valuable, are tailored to rice-specific characteristics, employing complex and costly setups and opaque ML models. Our research overcomes these limitations with a robust ML-based IoT system for paddy grain quality assessment, using affordable sensors, a comprehensive data collection process, and an ML-driven image processing model. Importantly, our approach utilizes interpretable features like Shape, Size, Moisture, and Maturity for paddy grain classification. Rigorous real-world testing confirms its precision, marking it as the first automated system capable of providing a reliable overall quality metric. Our system’s unique feature lies in its transparency, with clear features and fuzzy rules, inspiring confidence and trust. While our experiments primarily feature Indian Subcontinent grain varieties, the system’s adaptability to diverse paddy types is evident, contributing significantly to computer vision.

show abstract

Section: Discussionmentioning

confidence: 99%

Efficient Paddy Grains Quality Assessment Approach Utilizing Affordable Sensors

Kumar,

Singh,

Raj

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Te authors suggested a multi-objective loss function that included terms that ft data-driven physical knowledge across randomly chosen collocation points in the problem domain, constitutive relations derived from the governing physics, terms corresponding to the residual of the governing PDE, and diferent boundary conditions. In a different study, a multi-objective loss function-based PINN is used by the authors of the monograph [61] to obtain the solution to the data-driven elastoplastic solid mechanics problem.…”

Section: Introductionmentioning

confidence: 99%

Exploring Physics‐Informed Neural Networks for the Generalized Nonlinear Sine‐Gordon Equation

Deresse,

Dufera

2024

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

The nonlinear sine-Gordon equation is a prevalent feature in numerous scientific and engineering problems. In this paper, we propose a machine learning-based approach, physics-informed neural networks (PINNs), to investigate and explore the solution of the generalized non-linear sine-Gordon equation, encompassing Dirichlet and Neumann boundary conditions. To incorporate physical information for the sine-Gordon equation, a multiobjective loss function has been defined consisting of the residual of governing partial differential equation (PDE), initial conditions, and various boundary conditions. Using multiple densely connected independent artificial neural networks (ANNs), called feedforward deep neural networks designed to handle partial differential equations, PINNs have been trained through automatic differentiation to minimize a loss function that incorporates the given PDE that governs the physical laws of phenomena. To illustrate the effectiveness, validity, and practical implications of our proposed approach, two computational examples from the nonlinear sine-Gordon are presented. We have developed a PINN algorithm and implemented it using Python software. Various experiments were conducted to determine an optimal neural architecture. The network training was employed by using the current state-of-the-art optimization methods in machine learning known as Adam and L-BFGS-B minimization techniques. Additionally, the solutions from the proposed method are compared with the established analytical solutions found in the literature. The findings show that the proposed method is a computational machine learning approach that is accurate and efficient for solving nonlinear sine-Gordon equations with a variety of boundary conditions as well as any complex nonlinear physical problems across multiple disciplines.

show abstract

“…In this regard, (Haghighat et al, 2020(Haghighat et al, , 2021b have been the breakthrough works geared towards developing a DL-based solver for inversion and surrogate modeling in solid mechanics for the first time utilizing PINNs theory. Additionally, PINNs have been successfully applied to the solution and discovery in linear elastic solid mechanics (Zhang et al, 2020;Samaniego et al, 2020;Haghighat et al, 2021a;Guo and Haghighat, 2020;Vahab et al, 2021;Rezaei et al, 2022;Zhang et al, 2022), elastic-viscoplastic solids (Frankel et al, 2020;Goswami et al, 2022;Arora et al, 2022;Roy and Guha, 2022), brittle fracture (Goswami et al, 2020) and computational elastodynamics (Rao et al, 2021) etc. The solution of PDEs corresponding to elasticity problems can be obtained by minimizing the network's loss function that comprises the residual error of governing PDEs and the initial/boundary conditions.…”

Section: Introductionmentioning

confidence: 99%

Physics-aware deep learning framework for linear elasticity

Roy¹,

Bose²

2023

Preprint

View full text Add to dashboard Cite

The paper presents an efficient and robust data-driven deep learning (DL) computational framework developed for linear continuum elasticity problems. The methodology is based on the fundamentals of the Physics Informed Neural Networks (PINNs). For an accurate representation of the field variables, a multi-objective loss function is proposed. It consists of terms corresponding to the residual of the governing partial differential equations (PDE), constitutive relations derived from the governing physics, various boundary conditions, and data-driven physical knowledge fitting terms across randomly selected collocation points in the problem domain. To this end, multiple densely connected independent artificial neural networks (ANNs), each approximating a field variable, are trained to obtain accurate solutions. Several benchmark problems including the Airy solution to elasticity and the Kirchhoff-Love plate problem are solved. Performance in terms of accuracy and robustness illustrates the superiority of the

show abstract

A data-driven physics-constrained deep learning computational framework for solving von Mises plasticity

Cited by 35 publications

References 77 publications

Efficient Paddy Grains Quality Assessment Approach Utilizing Affordable Sensors

Efficient Paddy Grains Quality Assessment Approach Utilizing Affordable Sensors

Exploring Physics‐Informed Neural Networks for the Generalized Nonlinear Sine‐Gordon Equation

Physics-aware deep learning framework for linear elasticity

Contact Info

Product

Resources

About