中国邮电高校学报(英文版) ›› 2023, Vol. 30 ›› Issue (2): 8-17.doi: 10.19682/j.cnki.1005-8885.2022.0019

• Wireless • 上一篇    下一篇

Gain and phase errors active calibration method based on neural network for arrays with arbitrary geometry

韩子文,张治,郭宇   

  1. 北京邮电大学
  • 收稿日期:2022-03-03 修回日期:2022-07-05 出版日期:2023-04-30 发布日期:2023-04-27
  • 通讯作者: 张治 E-mail:zhangzhi@bupt.edu.cn
  • 基金资助:
    北京市科技计划课题

Gain and phase errors active calibration method based on neural network for arrays with arbitrary geometry

Han Ziwen, Zhang Zhi , Guo Yu   

  • Received:2022-03-03 Revised:2022-07-05 Online:2023-04-30 Published:2023-04-27
  • Supported by:
    the Key R&D Program of Shandong Province (2020CXGC010109), the Beijing Municipal Science and Technology Project (Z181100003218015)

摘要:

The manifold matrix of the received signals can be destroyed when the array is with the gain and phase errors,which will affect the performance of the traditional direction of arrival (DOA) estimation approaches. In this paper,a novel active array calibration method for the gain and phase errors based on a cascaded neural network(GPECNN) was proposed. The cascaded neural network contains two parts: signal-to-noise ratio ( SNR) classification network and two sets of error estimation subnetworks. Error calibration subnetworks are activated according to the output of the SNR classification network, each of which consists of a gain error estimation network(GEEN) and a phase error estimation network (PEEN), respectively. The disadvantage of neural network topology architecture is changing when the number of array elements varies is addressed by the proposed group calibration strategy. Moreover, due to the data characteristics of the input vector, the cascaded neural network can be applied to arrays with arbitrary geometry without repetitive training. Simulation results demonstrate that the GPECNN not only achieves a better balance between calibration performance and calibration complexity than other methods but also can be applied to arrays with different numbers of sensors or different shapes without repetitive training.

关键词: active array calibration| cascaded neural network| direction of arrival (DOA) estimation

Abstract:

The manifold matrix of the received signals can be destroyed when the array is with the gain and phase errors,which will affect the performance of the traditional direction of arrival (DOA) estimation approaches. In this paper,a novel active array calibration method for the gain and phase errors based on a cascaded neural network(GPECNN) was proposed. The cascaded neural network contains two parts: signal-to-noise ratio ( SNR) classification network and two sets of error estimation subnetworks. Error calibration subnetworks are activated according to the output of the SNR classification network, each of which consists of a gain error estimation network(GEEN) and a phase error estimation network (PEEN), respectively. The disadvantage of neural network topology architecture is changing when the number of array elements varies is addressed by the proposed group calibration strategy. Moreover, due to the data characteristics of the input vector, the cascaded neural network can be applied to arrays with arbitrary geometry without repetitive training. Simulation results demonstrate that the GPECNN not only achieves a better balance between calibration performance and calibration complexity than other methods but also can be applied to arrays with different numbers of sensors or different shapes without repetitive training.

Key words: active array calibration| cascaded neural network| direction of arrival (DOA) estimation