一种反演散射障碍的循环神经网络模型
A Recurrent Neural Network Model for Inverse Scattering Obstacles
摘要: 针对通过相关的远场数据反演障碍物形状的反散射问题，构建一种基于门控思想的循环神经网络模型。本文将远场数据和障碍物边界曲线方程的傅里叶系数分别作为网络模型的输入和输出，利用网络模型中的门控思想有选择地提取远场数据中障碍物的特征信息，并通过Adam优化算法更新网络模型的权重和偏置，进而反演障碍物的形状参数。最后，数值实验说明该循环神经网络模型的有效性。
Abstract: Aiming at the inverse scattering problem of recovering the shape of obstacles, a recurrent neural network model is constructed which is based on the gated thought. This paper considers the far-field data and the Fourier parameters of obstacle boundary curve equation as the input and output of the network model, respectively. The characteristic information of obstacles in the far-field data is selectively extracted through the gated thought of the proposed network model. The Adam optimization algorithm is applied to update weight matrices and biases of the network model in order to inverse the obstacle shape. Finally, the numerical experiments demonstrate the effec-tiveness of this recurrent neural network model.
文章引用：王琳, 孟品超. 一种反演散射障碍的循环神经网络模型[J]. 应用数学进展, 2023, 12(3): 1013-1021. https://doi.org/10.12677/AAM.2023.123103

参考文献

[1] Alessandrini, G. and Rondi, L. (2005) Determining a Sound-Soft Polyhedral Scatterer by a Single Far-Field Measure-ment. Proceedings of the American Mathematical Society, 133, 1685-1691. [Google Scholar] [CrossRef] 
[2] Liu, H.Y. and Zou, J. (2006) Uniqueness in an Inverse Acoustic Obstacle Scattering Problem for Both Sound-Hard and Sound-Soft Polyhedral Scatterers. Inverse Problems, 22, 515-524. [Google Scholar] [CrossRef] 
[3] Li, J.Z., Liu, H.Y. and Zou, J. (2010) Strengthened Linear Sampling Method with a Reference Ball. SIAM Journal on Scientific Computing, 31, 4013-4040. [Google Scholar] [CrossRef] 
[4] Kirsch, A. and Liu, X.D. (2014) A Modification of the Factorization Method for the Classical Acoustic Inverse Scattering Problems. Inverse Problems, 30, Article ID: 035013. [Google Scholar] [CrossRef] 
[5] Kirsch, A. (1993) The Domain Derivative and Two Applica-tions in Inverse Scattering Theory. Inverse Problems, 9, 81-96. [Google Scholar] [CrossRef] 
[6] Wang, H.B. and Liu, J.J. (2013) On Decomposition Method for Acoustic Wave Scattering by Multiple Obstacles. Acta Mathematica Scientia, 33, 1-22. [Google Scholar] [CrossRef] 
[7] Bengio, Y. (2009) Learning Deep Architectures for AI. Foundations and Trends in Machine Learning, 2, 1-127. [Google Scholar] [CrossRef] 
[8] Khoo, Y.H. and Ying, L.X. (2019) SwitchNet: A Neural Network Model for Forward and Inverse Scattering Problems. SIAM Journal on Scientific Computing, 41, A3182-A3201. [Google Scholar] [CrossRef] 
[9] Li, J.H., Liu, H.Y., Tsui, W.Y. and Wang, X.C. (2019) An Inverse Scattering Approach for Geometric Body Generation: A Machine Learning Perspective. Mathematics in Engineering, 1, 800-823. [Google Scholar] [CrossRef] 
[10] Gao, Y. and Zhang, K. (2021) Machine Learning Based Data Re-trieval for Inverse Scattering Problems with Incomplete Data. Journal of Inverse and Ill-Posed Problems, 29, 249-266. [Google Scholar] [CrossRef] 
[11] Yin, W.S., Yang, W.H. and Liu, H.Y. (2020) A Neural Network Scheme for Recovering Scattering Obstacles with Limited Phaseless Far-Field Data. Journal of Computational and Physics, 417, Article ID: 109594. [Google Scholar] [CrossRef] 
[12] Meng, P.C., Su, L., Yin, W.S. and Zhang, S. (2020) Solving a Kind of Inverse Scattering Problem of Acoustic Waves Based on Linear Sampling Method and Neural Network. Journal of Alexandria Engineering, 59, 1451-1462. [Google Scholar] [CrossRef] 
[13] Gao, Y., Liu, H.Y., Wang, X.C. and Zhang, K. (2022) On an Artifi-cial Neural Network for Inverse Scattering Problems. Journal of Computational Physics, 448, Article ID: 110771. [Google Scholar] [CrossRef] 

为你推荐