An Efficient and Accurate 2W-PE Method for Solving Spatial Field Strength Based on CVNN and PINN
A two-way parabolic equation (2W-PE) method based on complex-valued neural networks (CVNNs) and a physics-informed neural network (PINN) is proposed to predict the spatial field in the environment of dielectric obstacles with high efficiency and accuracy. In the framework of the 2W-PE method, CVNNs...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | International Journal of Antennas and Propagation |
| Online Access: | http://dx.doi.org/10.1155/2023/9485036 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551153553899520 |
|---|---|
| author | An-Qi Li Cheng-You Yin Qian-Qian Zhang Han Liu |
| author_facet | An-Qi Li Cheng-You Yin Qian-Qian Zhang Han Liu |
| author_sort | An-Qi Li |
| collection | DOAJ |
| description | A two-way parabolic equation (2W-PE) method based on complex-valued neural networks (CVNNs) and a physics-informed neural network (PINN) is proposed to predict the spatial field in the environment of dielectric obstacles with high efficiency and accuracy. In the framework of the 2W-PE method, CVNNs are used to calculate the lumped transmission field and the lumped reflection field considering the influence of the obstacle, thus avoiding the long calculation time caused by the internal multilayered reflection processes. The incident directions and field strength of the waves on the regional boundaries vary greatly with the propagation environment, so coefficients of the boundary conditions are obtained by using the PINN. Next, the training results are applied to the examples using the continuation method and compared with the numerical results of the method of moments (MoM). The proposed 2W-PE method has high computational accuracy and efficiency, which reflects the applicability of machine learning in solving the computational efficiency problem of radio wave propagation. Therefore, this study provides a very effective and reliable method for solving the spatial field in the obstacle environment. |
| format | Article |
| id | doaj-art-e57f3da39f4a410f8cba181e2973f1d5 |
| institution | Kabale University |
| issn | 1687-5877 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Antennas and Propagation |
| spelling | doaj-art-e57f3da39f4a410f8cba181e2973f1d52025-02-03T06:04:52ZengWileyInternational Journal of Antennas and Propagation1687-58772023-01-01202310.1155/2023/9485036An Efficient and Accurate 2W-PE Method for Solving Spatial Field Strength Based on CVNN and PINNAn-Qi Li0Cheng-You Yin1Qian-Qian Zhang2Han Liu3College of Electronic EngineeringCollege of Electronic EngineeringCollege of Electronic EngineeringCollege of Information and CommunicationA two-way parabolic equation (2W-PE) method based on complex-valued neural networks (CVNNs) and a physics-informed neural network (PINN) is proposed to predict the spatial field in the environment of dielectric obstacles with high efficiency and accuracy. In the framework of the 2W-PE method, CVNNs are used to calculate the lumped transmission field and the lumped reflection field considering the influence of the obstacle, thus avoiding the long calculation time caused by the internal multilayered reflection processes. The incident directions and field strength of the waves on the regional boundaries vary greatly with the propagation environment, so coefficients of the boundary conditions are obtained by using the PINN. Next, the training results are applied to the examples using the continuation method and compared with the numerical results of the method of moments (MoM). The proposed 2W-PE method has high computational accuracy and efficiency, which reflects the applicability of machine learning in solving the computational efficiency problem of radio wave propagation. Therefore, this study provides a very effective and reliable method for solving the spatial field in the obstacle environment.http://dx.doi.org/10.1155/2023/9485036 |
| spellingShingle | An-Qi Li Cheng-You Yin Qian-Qian Zhang Han Liu An Efficient and Accurate 2W-PE Method for Solving Spatial Field Strength Based on CVNN and PINN International Journal of Antennas and Propagation |
| title | An Efficient and Accurate 2W-PE Method for Solving Spatial Field Strength Based on CVNN and PINN |
| title_full | An Efficient and Accurate 2W-PE Method for Solving Spatial Field Strength Based on CVNN and PINN |
| title_fullStr | An Efficient and Accurate 2W-PE Method for Solving Spatial Field Strength Based on CVNN and PINN |
| title_full_unstemmed | An Efficient and Accurate 2W-PE Method for Solving Spatial Field Strength Based on CVNN and PINN |
| title_short | An Efficient and Accurate 2W-PE Method for Solving Spatial Field Strength Based on CVNN and PINN |
| title_sort | efficient and accurate 2w pe method for solving spatial field strength based on cvnn and pinn |
| url | http://dx.doi.org/10.1155/2023/9485036 |
| work_keys_str_mv | AT anqili anefficientandaccurate2wpemethodforsolvingspatialfieldstrengthbasedoncvnnandpinn AT chengyouyin anefficientandaccurate2wpemethodforsolvingspatialfieldstrengthbasedoncvnnandpinn AT qianqianzhang anefficientandaccurate2wpemethodforsolvingspatialfieldstrengthbasedoncvnnandpinn AT hanliu anefficientandaccurate2wpemethodforsolvingspatialfieldstrengthbasedoncvnnandpinn AT anqili efficientandaccurate2wpemethodforsolvingspatialfieldstrengthbasedoncvnnandpinn AT chengyouyin efficientandaccurate2wpemethodforsolvingspatialfieldstrengthbasedoncvnnandpinn AT qianqianzhang efficientandaccurate2wpemethodforsolvingspatialfieldstrengthbasedoncvnnandpinn AT hanliu efficientandaccurate2wpemethodforsolvingspatialfieldstrengthbasedoncvnnandpinn |