DISCOVER: Deep identification of symbolically concise open-form partial differential equations via enhanced reinforcement learning

M Du, Y Chen, D Zhang - Physical Review Research, 2024 - APS
The working mechanisms of complex natural systems tend to abide by concise partial
differential equations (PDEs). Methods that directly mine equations from data are called PDE …

A study of mechanism-data hybrid-driven method for multibody system via physics-informed neural network

N Song, C Wang, H Peng, J Zhao - Acta Mechanica Sinica, 2025 - Springer
Numerical simulation plays an important role in the dynamic analysis of multibody system.
With the rapid development of computer science, the numerical solution technology has …

Learning dynamics from coarse/noisy data with scalable symbolic regression

Z Chen, N Wang - Mechanical Systems and Signal Processing, 2023 - Elsevier
Distilling equations from data can provide insights into physics systems, helping validate
theoretical modeling, infer unknown system properties, and explore indeterminate …

Solver-based fitness function for the data-driven evolutionary discovery of partial differential equations

M Maslyaev, A Hvatov - 2022 IEEE Congress on Evolutionary …, 2022 - ieeexplore.ieee.org
Partial differential equations provide accurate models for many physical processes, although
their derivation can be challenging, requiring a fundamental understanding of the modeled …

MORL4PDEs: Data-driven discovery of PDEs based on multi-objective optimization and reinforcement learning

X Zhang, J Guan, Y Liu, G Wang - Chaos, Solitons & Fractals, 2024 - Elsevier
Extracting fundamental behavior patterns or governing equations from data can deepen our
understanding and insights into physical systems, it will lead to the better control and …

Automated differential equation solver based on the parametric approximation optimization

A Hvatov - Mathematics, 2023 - mdpi.com
The classical numerical methods for differential equations are a well-studied field.
Nevertheless, these numerical methods are limited in their scope to certain classes of …

Parameter estimation for several types of linear partial differential equations based on Gaussian processes

W Zhang, W Gu - Fractal and Fractional, 2022 - mdpi.com
This paper mainly considers the parameter estimation problem for several types of
differential equations controlled by linear operators, which may be partial differential, integro …

Physics-constrained robust learning of open-form partial differential equations from limited and noisy data

M Du, Y Chen, L Nie, S Lou, D Zhang - Physics of Fluids, 2024 - pubs.aip.org
Unveiling the underlying governing equations of nonlinear dynamic systems remains a
significant challenge. Insufficient prior knowledge hinders the determination of an accurate …

[PDF][PDF] Hybrid modeling of gas-dynamic processes in AC plasma torches.

NY Bykov, NV Obraztsov, АA Hvatov… - Materials Physics & …, 2022 - ipme.ru
A model of plasma-forming gas flows in AC plasma torches was proposed for the range of
operating parameters typical for technologies for the synthesis of perspective materials. It …

Methods of Partial Differential Equation Discovery: Application to Experimental Data on Heat Transfer Problem

TA Andreeva, NY Bykov, YA Gataulin, AA Hvatov… - Processes, 2023 - mdpi.com
The paper presents two effective methods for discovering process models in the form of
partial differential equations based on an evolutionary algorithm and an algorithm for the …