A Navier–Stokes-Informed Neural Network for Simulating the Flow Behavior of Flowable Cement Paste in 3D Concrete Printing
In this work, we propose a Navier–Stokes-Informed Neural Network (NSINN) as a surrogate approach to predict the localized flow behavior of cementitious materials for advancing 3D additive construction technology to gain fundamental insights into multiscale mechanisms of cement paste rheology. NS equ...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/15/2/275 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588825770065920 |
|---|---|
| author | Tianjie Zhang Donglei Wang Yang Lu |
| author_facet | Tianjie Zhang Donglei Wang Yang Lu |
| author_sort | Tianjie Zhang |
| collection | DOAJ |
| description | In this work, we propose a Navier–Stokes-Informed Neural Network (NSINN) as a surrogate approach to predict the localized flow behavior of cementitious materials for advancing 3D additive construction technology to gain fundamental insights into multiscale mechanisms of cement paste rheology. NS equations are embedded into the NSINN to interpret the flow pattern in the 3D printing barrel. The results show that the presented NSINN has a higher accuracy compared to a traditional artificial neural network (ANN) as the Mean Square Errors (MSEs) of the u, v, and p predicted by NSINN are <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.25</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>4</mn></mrow></msup></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.85</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>5</mn></mrow></msup></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3.91</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></semantics></math></inline-formula>, respectively. Compared to the ANN, the MSE of the predictions are <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.88</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.17</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.72</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></semantics></math></inline-formula>, respectively. Moreover, the mean prediction time used in the NSINN, the ANN, and Computational Fluid Dynamics (CFD) are 0.039 s, 0.014 s, and 3.37 s, respectively. That means the method is more computationally efficient at performing simulations compared to CFD which is mesh-based. The NSINN is also utilized in studying the relationship between geometry and extrudability. The ratio (R = 0.25, 0.5, and 0.75) between the diameter of the outlet and that of the domain is studied. It shows that a larger ratio (R = 0.75) can lead to better extrudability of the 3D concrete printing (3DCP). |
| format | Article |
| id | doaj-art-176b9e48187d41f4a59e3ec45fe4aa9b |
| institution | Kabale University |
| issn | 2075-5309 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj-art-176b9e48187d41f4a59e3ec45fe4aa9b2025-01-24T13:26:26ZengMDPI AGBuildings2075-53092025-01-0115227510.3390/buildings15020275A Navier–Stokes-Informed Neural Network for Simulating the Flow Behavior of Flowable Cement Paste in 3D Concrete PrintingTianjie Zhang0Donglei Wang1Yang Lu2Computing PhD Program, Boise State University, Boise, ID 83725, USADepartment of Civil Engineering, Boise State University, Boise, ID 83725, USADepartment of Civil Engineering, Boise State University, Boise, ID 83725, USAIn this work, we propose a Navier–Stokes-Informed Neural Network (NSINN) as a surrogate approach to predict the localized flow behavior of cementitious materials for advancing 3D additive construction technology to gain fundamental insights into multiscale mechanisms of cement paste rheology. NS equations are embedded into the NSINN to interpret the flow pattern in the 3D printing barrel. The results show that the presented NSINN has a higher accuracy compared to a traditional artificial neural network (ANN) as the Mean Square Errors (MSEs) of the u, v, and p predicted by NSINN are <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.25</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>4</mn></mrow></msup></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.85</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>5</mn></mrow></msup></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3.91</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></semantics></math></inline-formula>, respectively. Compared to the ANN, the MSE of the predictions are <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.88</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.17</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.72</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></semantics></math></inline-formula>, respectively. Moreover, the mean prediction time used in the NSINN, the ANN, and Computational Fluid Dynamics (CFD) are 0.039 s, 0.014 s, and 3.37 s, respectively. That means the method is more computationally efficient at performing simulations compared to CFD which is mesh-based. The NSINN is also utilized in studying the relationship between geometry and extrudability. The ratio (R = 0.25, 0.5, and 0.75) between the diameter of the outlet and that of the domain is studied. It shows that a larger ratio (R = 0.75) can lead to better extrudability of the 3D concrete printing (3DCP).https://www.mdpi.com/2075-5309/15/2/275physics-informed neural networkcementitious materialthree-dimensional concrete printingNavier–Stokes equationscomputational fluid dynamics |
| spellingShingle | Tianjie Zhang Donglei Wang Yang Lu A Navier–Stokes-Informed Neural Network for Simulating the Flow Behavior of Flowable Cement Paste in 3D Concrete Printing Buildings physics-informed neural network cementitious material three-dimensional concrete printing Navier–Stokes equations computational fluid dynamics |
| title | A Navier–Stokes-Informed Neural Network for Simulating the Flow Behavior of Flowable Cement Paste in 3D Concrete Printing |
| title_full | A Navier–Stokes-Informed Neural Network for Simulating the Flow Behavior of Flowable Cement Paste in 3D Concrete Printing |
| title_fullStr | A Navier–Stokes-Informed Neural Network for Simulating the Flow Behavior of Flowable Cement Paste in 3D Concrete Printing |
| title_full_unstemmed | A Navier–Stokes-Informed Neural Network for Simulating the Flow Behavior of Flowable Cement Paste in 3D Concrete Printing |
| title_short | A Navier–Stokes-Informed Neural Network for Simulating the Flow Behavior of Flowable Cement Paste in 3D Concrete Printing |
| title_sort | navier stokes informed neural network for simulating the flow behavior of flowable cement paste in 3d concrete printing |
| topic | physics-informed neural network cementitious material three-dimensional concrete printing Navier–Stokes equations computational fluid dynamics |
| url | https://www.mdpi.com/2075-5309/15/2/275 |
| work_keys_str_mv | AT tianjiezhang anavierstokesinformedneuralnetworkforsimulatingtheflowbehaviorofflowablecementpastein3dconcreteprinting AT dongleiwang anavierstokesinformedneuralnetworkforsimulatingtheflowbehaviorofflowablecementpastein3dconcreteprinting AT yanglu anavierstokesinformedneuralnetworkforsimulatingtheflowbehaviorofflowablecementpastein3dconcreteprinting AT tianjiezhang navierstokesinformedneuralnetworkforsimulatingtheflowbehaviorofflowablecementpastein3dconcreteprinting AT dongleiwang navierstokesinformedneuralnetworkforsimulatingtheflowbehaviorofflowablecementpastein3dconcreteprinting AT yanglu navierstokesinformedneuralnetworkforsimulatingtheflowbehaviorofflowablecementpastein3dconcreteprinting |