An Improved Physics-Informed Neural Network Algorithm for Predicting the Phreatic Line of Seepage

As new ways to solve partial differential equations (PDEs), physics-informed neural network (PINN) algorithms have received widespread attention and have been applied in many fields of study. However, the standard PINN framework lacks sufficient seepage head data, and the method is difficult to appl...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunpeng Gao, Li Qian, Tianzhi Yao, Zuguo Mo, Jianhai Zhang, Ru Zhang, Enlong Liu, Yonghong Li
Format: Article
Language:English
Published: Wiley 2023-01-01
Series:Advances in Civil Engineering
Online Access:http://dx.doi.org/10.1155/2023/5499645
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849696723686916096
author Yunpeng Gao
Li Qian
Tianzhi Yao
Zuguo Mo
Jianhai Zhang
Ru Zhang
Enlong Liu
Yonghong Li
author_facet Yunpeng Gao
Li Qian
Tianzhi Yao
Zuguo Mo
Jianhai Zhang
Ru Zhang
Enlong Liu
Yonghong Li
author_sort Yunpeng Gao
collection DOAJ
description As new ways to solve partial differential equations (PDEs), physics-informed neural network (PINN) algorithms have received widespread attention and have been applied in many fields of study. However, the standard PINN framework lacks sufficient seepage head data, and the method is difficult to apply effectively in seepage analysis with complex boundary conditions. In addition, the differential type Neumann boundary makes the solution more difficult. This study proposed an improved prediction method based on a PINN with the aim of calculating PDEs with complex boundary conditions such as Neumann boundary conditions, in which the spatial distribution characteristic information is increased by a small amount of measured data and the loss equation is dynamically adjusted by loss weighting coefficients. The measured data are converted into a quadratic regular term and added to the loss function as feature data to guide the update process for the weight and bias coefficient of each neuron in the neural network. A typical geotechnical problem concerning seepage phreatic line determination in a rectangular dam is analyzed to demonstrate the efficiency of the improved method. Compared with the standard PINN algorithm, due to the addition of measurement data and dynamic loss weighting coefficients, the improved PINN algorithm has better convergence and can handle more complex boundary conditions. The results show that the improved method makes it convenient to predict the phreatic line in seepage analysis for geotechnical engineering projects with measured data.
format Article
id doaj-art-4f308eacb89f46fc9d800b630d3964c4
institution DOAJ
issn 1687-8094
language English
publishDate 2023-01-01
publisher Wiley
record_format Article
series Advances in Civil Engineering
spelling doaj-art-4f308eacb89f46fc9d800b630d3964c42025-08-20T03:19:23ZengWileyAdvances in Civil Engineering1687-80942023-01-01202310.1155/2023/5499645An Improved Physics-Informed Neural Network Algorithm for Predicting the Phreatic Line of SeepageYunpeng Gao0Li Qian1Tianzhi Yao2Zuguo Mo3Jianhai Zhang4Ru Zhang5Enlong Liu6Yonghong Li7State Key Laboratory of Hydraulics and Mountain River EngineeringState Key Laboratory of Hydraulics and Mountain River EngineeringState Key Laboratory of Hydraulics and Mountain River EngineeringState Key Laboratory of Hydraulics and Mountain River EngineeringState Key Laboratory of Hydraulics and Mountain River EngineeringState Key Laboratory of Hydraulics and Mountain River EngineeringState Key Laboratory of Hydraulics and Mountain River EngineeringPower China Chengdu Engineering Corporation LimitedAs new ways to solve partial differential equations (PDEs), physics-informed neural network (PINN) algorithms have received widespread attention and have been applied in many fields of study. However, the standard PINN framework lacks sufficient seepage head data, and the method is difficult to apply effectively in seepage analysis with complex boundary conditions. In addition, the differential type Neumann boundary makes the solution more difficult. This study proposed an improved prediction method based on a PINN with the aim of calculating PDEs with complex boundary conditions such as Neumann boundary conditions, in which the spatial distribution characteristic information is increased by a small amount of measured data and the loss equation is dynamically adjusted by loss weighting coefficients. The measured data are converted into a quadratic regular term and added to the loss function as feature data to guide the update process for the weight and bias coefficient of each neuron in the neural network. A typical geotechnical problem concerning seepage phreatic line determination in a rectangular dam is analyzed to demonstrate the efficiency of the improved method. Compared with the standard PINN algorithm, due to the addition of measurement data and dynamic loss weighting coefficients, the improved PINN algorithm has better convergence and can handle more complex boundary conditions. The results show that the improved method makes it convenient to predict the phreatic line in seepage analysis for geotechnical engineering projects with measured data.http://dx.doi.org/10.1155/2023/5499645
spellingShingle Yunpeng Gao
Li Qian
Tianzhi Yao
Zuguo Mo
Jianhai Zhang
Ru Zhang
Enlong Liu
Yonghong Li
An Improved Physics-Informed Neural Network Algorithm for Predicting the Phreatic Line of Seepage
Advances in Civil Engineering
title An Improved Physics-Informed Neural Network Algorithm for Predicting the Phreatic Line of Seepage
title_full An Improved Physics-Informed Neural Network Algorithm for Predicting the Phreatic Line of Seepage
title_fullStr An Improved Physics-Informed Neural Network Algorithm for Predicting the Phreatic Line of Seepage
title_full_unstemmed An Improved Physics-Informed Neural Network Algorithm for Predicting the Phreatic Line of Seepage
title_short An Improved Physics-Informed Neural Network Algorithm for Predicting the Phreatic Line of Seepage
title_sort improved physics informed neural network algorithm for predicting the phreatic line of seepage
url http://dx.doi.org/10.1155/2023/5499645
work_keys_str_mv AT yunpenggao animprovedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT liqian animprovedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT tianzhiyao animprovedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT zuguomo animprovedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT jianhaizhang animprovedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT ruzhang animprovedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT enlongliu animprovedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT yonghongli animprovedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT yunpenggao improvedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT liqian improvedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT tianzhiyao improvedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT zuguomo improvedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT jianhaizhang improvedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT ruzhang improvedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT enlongliu improvedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage
AT yonghongli improvedphysicsinformedneuralnetworkalgorithmforpredictingthephreaticlineofseepage