GMSK Demodulation Combining 1D‐CNN and Bi‐LSTM Network Over Strong Solar Wind Turbulence Channel. Issue 1 (22nd January 2023)

• Record Type: Journal Article
• Authors: Zhu, Manqin; Hu, Shengbo; Yang, Kai; Yan, Tingting; Ye, Lv; Li, Hongjuan; Jin, Yang
• Is Part Of: Radio science. Volume 58:Issue 1(2023)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2023-01-22
• Subjects: Radio meteorology -- Periodicals; Radio wave propagation -- Periodicals; 621.38405
• DOI: 10.1029/2022RS007438
• Languages: English
• ISSNs: 0048-6604

Abstract

Abstract: To solve the problem of bit error rate (BER) performance degradation over strong solar wind turbulence channel, this paper addresses to Gaussian minimum frequency shift keying (GMSK) demodulation using machine learning. First, by analyzing the scintillation characteristics of the telemetry signal caused by solar wind turbulence during the solar superior conjunction, the K distribution channel model is innovatively established over strong solar wind turbulence channel. Then, the approximate probability density function of the K distribution of the established channel is studied by using Laguerre orthogonal polynomial for convenience. Additionally, the BER performance of GMSK over strong solar wind turbulence channel is analyzed. Second, using a one‐dimensional convolutional neural network (1D‐CNN) and bidirectional long short‐term memory network (Bi‐LSTM), two demodulators for GMSK are proposed. By integrating the 1D‐CNN and LSTM to extract local features and process the dynamic information of GMSK signals, we propose a novel GMSK demodulator over strong solar wind turbulence channel with combining 1D‐CNN and Bi‐LSTM. The simulation results show that, even if the solar wind turbulence has serious effects on the signal at a low signal‐to‐noise ratio, the proposed combining neural network demodulation can obtain better BER performance than the classical Viterbi algorithm, demodulation using only a single 1D‐CNN or Bi‐LSTM. The proposed GMSK demodulator is more suitable for the deep space exploration of the solar system. Plain Language Summary: The solar wind turbulence is formed by many irregular plasmas ejected from the solar nuclear reaction, and it has a serious impact on the deep‐space communication link. To solve the problem of bit error rate (BER) performance degradation by caused solar wind turbulence, we analyze the scintillation characteristics of the telemetry signal caused by solar wind turbulence during solar superior conjunction. The K distribution channel model is established for strong solar wind turbulence channel. Also, for the Gaussian minimum frequency shift keying (GMSK) modulator by the Consultative Committee for Space Data Systems, we present the BER performance of the GMSK demodulator using Viterbi algorithm, only a single one‐dimensional convolutional neural network (1D‐CNN) and a bidirectional long short‐term memory (Bi‐LSTM) neural network. For different scintillation indices, the simulation results test the validity of demodulation using machine learning. In particular, by combining the feature extraction capability of the 1D‐CNN and the processing capability of LSTM for time series, we propose a novel GMSK demodulator that combines the 1D‐CNN with Bi‐LSTM, and the BER performance using the proposed GMSK demodulator improves better even at a low signal‐to‐noise ratio. Key Points: The K distribution channel model for the strong solar wind turbulence is innovatively established by analyzing the model of telemetry signal amplitude fluctuation caused by solar wind turbulence To demodulate the Gaussian minimum frequency shift keying (GMSK) signals over strong solar wind turbulence channel, two neural network demodulators based on bidirectional long short‐term memory network (LSTM) and one‐dimensional convolutional neural network (1D‐CNN) are designed, which can obtain better bit error rate performance than the conventional coherent demodulation By combining the feature extraction capability of the 1D‐CNN and the processing capability of LSTM for time series, we propose a novel GMSK demodulator