Hostname: page-component-7479d7b7d-m9pkr Total loading time: 0 Render date: 2024-07-08T15:36:16.659Z Has data issue: false hasContentIssue false

Robust adaptive beamforming via residual convolutional neural network

Published online by Cambridge University Press:  11 December 2023

Fulai Liu*
Affiliation:
Lab of Electromagnetic Environment Cognition and Control Utilization, Northeastern University at Qinhuangdao, Qinhuangdao, China School of Computer Science and Engineering, Northeastern University, Shenyang, China
Dongbao Qin
Affiliation:
Lab of Electromagnetic Environment Cognition and Control Utilization, Northeastern University at Qinhuangdao, Qinhuangdao, China School of Computer Science and Engineering, Northeastern University, Shenyang, China
Xubin Li*
Affiliation:
Lab of Electromagnetic Environment Cognition and Control Utilization, Northeastern University at Qinhuangdao, Qinhuangdao, China School of Computer Science and Engineering, Northeastern University, Shenyang, China
Yufeng Du
Affiliation:
Hebei Key Laboratory of Electromagnetic Spectrum Cognition and Control, Shijiazhuang, China
Xiuquan Dou
Affiliation:
Hebei Key Laboratory of Electromagnetic Spectrum Cognition and Control, Shijiazhuang, China
Ruiyan Du
Affiliation:
Lab of Electromagnetic Environment Cognition and Control Utilization, Northeastern University at Qinhuangdao, Qinhuangdao, China School of Computer Science and Engineering, Northeastern University, Shenyang, China
*
Corresponding authors: Fulai Liu; Email: fulailiu@126.com; Xubin Li; Email: xubinli1999@163.com
Corresponding authors: Fulai Liu; Email: fulailiu@126.com; Xubin Li; Email: xubinli1999@163.com

Abstract

Aiming at the problem that the covariance matrix includes the desired signal and the signal steer vector mismatches will degrade the beamforming performance, an effective robust adaptive beamforming (RAB) approach is presented in this paper based on a residual convolutional neural network (RAB-RCNN). In the presented method, the RAB-RCNN model is designed by introducing a residual unit, which can extract the deeper features from the signal sample covariance matrix. Residual noise elimination and interferences power estimation are utilized to reconstruct the desired signal covariance matrix, and correct the mismatched steering vector (SV) by the eigenvalue decomposition of the reconstructed desired signal covariance matrix. The projection method is utilized to redesign the signal interference-plus-noise covariance matrix. Furthermore, the beamforming weight vector is calculated with the two parameters obtained before and used as the label of the RAB-RCNN model, The trained model can rapidly and precisely output the predicted beamforming weight vector without complex matrix operations, including the matrix inversion of the signal covariance matrix, so that the calculation time can be reduced for beamforming. Simulations demonstrate the robustness of the presented approach against SV mismatches due to the direction-of-arrival estimation error, sensor position error, and local scattering interference.

Type
Research Paper
Copyright
© The Author(s), 2023. Published by Cambridge University Press in association with the European Microwave Association

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Zhou, Y, Chen, L, Zhang, Q, Wang, H and Guo, L (2023) A 1-bit reconfigurable intelligent metasurface-based antenna design for 5G application. International Journal of Microwave and Wireless Technologies, 110.CrossRefGoogle Scholar
Wang, W, Yan, S, Mao, L and Guo, X (2021) Robust minimum variance beamforming with sidelobe-level control using the alternating direction method of multipliers. IEEE Transactions on Aerospace and Electronic Systems 57(5), 35063519.CrossRefGoogle Scholar
Ma, Y, Miao, C and Wu, W (2023) Hyper beamforming with single-sideband time-modulated phased arrays for automotive radar. International Journal of Microwave and Wireless Technologies 15(9), 14531459.CrossRefGoogle Scholar
Liu, F, Du, R, Wu, J, Zhou, Q, Zhang, Z and Cheng, Y (2018) Multiple constrained $\ell_2$-norm minimization algorithm for adaptive beamforming. IEEE Sensors Journal 18(15), 63116318.CrossRefGoogle Scholar
Yang, H, Wang, P and Ye, Z (2021) Robust adaptive beamforming via covariance matrix reconstruction under colored noise. IEEE Signal Processing Letters 28, 17591763.CrossRefGoogle Scholar
Ge, S, Fan, C, Wang, J and Huang, X (2022) Robust adaptive beamforming based on sparse Bayesian learning and covariance matrix reconstruction. IEEE Communications Letters 26(8), 18931897.CrossRefGoogle Scholar
Zheng, Z, Yang, T, Wang, W and Zhang, S (2020) Robust adaptive beamforming via coprime coarray interpolation. Signal Processing 169, .CrossRefGoogle Scholar
Yang, J, Tu, Y, Lu, J and Yang, Z (2022) Robust adaptive beamforming based on subspace decomposition, steering vector estimation and correction. IEEE Sensors Journal 22(12), 1226012268.CrossRefGoogle Scholar
Wax, M and Anu, Y (1996) Performance analysis of the minimum variance beamformer in the presence of steering vector errors. IEEE Transactions on Signal Processing 44(4), 938947.CrossRefGoogle Scholar
Du, L, Li, J and Stoica, P (2010) Fully automatic computation of diagonal loading levels for robust adaptive beamforming. IEEE Transactions on Aerospace and Electronic Systems 46(1), 449458.CrossRefGoogle Scholar
Jia, W, Jin, W, Zhou, S and Yao, M (2013) Robust adaptive beamforming based on a new steering vector estimation algorithm. Signal Processing 93(9), 25392542.CrossRefGoogle Scholar
Vorobyov, S, Gershman, A and Luo, Z (2003) Robust adaptive beamforming using worst-case performance optimization: a solution to the signal mismatch problem. IEEE Transactions on Signal Processing 51(2), 313324.CrossRefGoogle Scholar
Zheng, Z, Yang, T, Wang, W and So, H (2019) Robust adaptive beamforming via simplified interference power estimation. IEEE Transactions on Aerospace and Electronic Systems 55(6), 31393152.CrossRefGoogle Scholar
Gu, Y and Leshem, A (2012) Robust adaptive beamforming based on interference covariance matrix reconstruction and steering vector estimation. IEEE Transactions on Signal Processing 60(7), 38813885.Google Scholar
Zheng, Z, Zheng, Y, Wang, W and Zhang, H (2018) Covariance matrix reconstruction with interference steering vector and power estimation for robust adaptive beamforming. IEEE Transactions on Vehicle Technology 67(9), 84958503.CrossRefGoogle Scholar
Liu, Z, Zhang, C and Yu, P (2018) Direction-of-arrival estimation based on deep neural networks with robustness to array imperfections. IEEE Transactions on Antennas and Propagation 66(12), 73157327.CrossRefGoogle Scholar
Ramezanpour, P and Mosavi, M (2020) Deep-learning-based beamforming for rejecting interferences. IET Signal Processing 14(7), 467473.CrossRefGoogle Scholar
Liu, C, Liu, X, Li, S, Yuan, W and Ng, D (2022) Deep CLSTM for predictive beamforming in integrated sensing and communication-enabled vehicular networks. Signal Processing 7(3), 269277.Google Scholar
Hao, C, X, Sun and Y, Liu (2022) Adaptive beamforming based on the deep reinforcement learning. In IEEE International Conference on Networking, Sensing and Control (ICNSC), Shanghai, China, IEEE, 16.CrossRefGoogle Scholar
Liu, F, Sun, G, Wang, J and Du, R (2014) Null broadening and sidelobe control algorithm via multi-parametric quadratic programming for robust adaptive beamforming. Applied Computational Electromagnetics Society Journal 29(4), 307315.Google Scholar
Capon, J (1969) High-resolution frequency-wavenumber spectrum analysis. Proceedings of the IEEE, 57(8), 14081418.CrossRefGoogle Scholar
He, K, X, Zhang, S, Ren and J, Sun (2016) Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 770778.CrossRefGoogle Scholar
Wan, F, Xu, J, Xu, X and Zhang, Z (2022) Robust beamforming based on covariance matrix reconstruction in FDA-MIMO radar to suppress deceptive jamming. Sensors 22(4), .CrossRefGoogle ScholarPubMed
Zhu, X, Xu, X and Ye, Z (2020) Robust adaptive beamforming via subspace for interference covariance matrix reconstruction. Signal Processing 167, .CrossRefGoogle Scholar
Zhu, X, Ye, Z, Xu, X and Zheng, R (2019) Covariance matrix reconstruction via residual noise elimination and interference powers estimation for robust adaptive beamforming. IEEE Access 7, 53262-53272.CrossRefGoogle Scholar
Saeed, M, Vítor, H, Rodrigo, C and Noushin, H (2022) Robust beamforming based on complex-valued convolutional neural networks for sensor arrays. IEEE Signal Processing Letters 29, 21082112.Google Scholar