受到海上复杂环境影响，海上通信信道衰落较大，船舶通信质量有所下降。针对正交频分复用无线通信系统的信道估计问题，提出了一种基于无监督深度学习的信道估计方案。通过引入无监督深度学习方法，使神经网络模型能够在信道频域响应未知的情况下完成学习训练，并获取信道估计信息。同时，为降低神经网络结构的复杂度并提高信道估计精度，提出并构建了一种具有正负极性的双Elu激活函数，并采取最小化曼哈顿距离作为目标函数。仿真实验验证了在多径衰落的信道环境下，相较于现阶段较为优秀的深度学习信道估计算法，提出的信道估计算法复杂度更低、模型迭代收敛速度更快且信道估计精度提升明显。
Affected by the complex marine environment, the marine communication channel is fading greatly, and the ship communication quality is reduced.Aiming to solve the problem of channel estimation for orthogonal frequency division multiplexing (OFDM) ofdm wireless communication system, an unsupervised deep learning channel estimation (CE) scheme is proposed. This CE algorithm introduces the unsupervised deep learning method to estimation channel information, which can perform model training in the case of unknown channel frequency response (CFR). Also, we propose a double Elu activation function with positive and negative polarity, and minimize the Manhattan distance as the destination function to reduce the complexity of the neural network and improve the accuracy of channel estimation. The simulation results have shown that in multipath fading channels, the proposed CE algorithm has lower complexity, faster iterative convergence speed, and more accurate channel estimation results than the currently channel estimation algorithm which based on deep learning.
2022,44(12): 126-132 收稿日期：2022-03-24
DOI：10.3404/j.issn.1672-7649.2022.12.025
分类号：TN929.5
基金项目：国家自然基金资助项目(61371091)
作者简介：许志远(1981-)，男，博士，副教授，研究方向为海上通信
参考文献：
[1] 王志明, 刘志辉, 黄洋科, 等. 基于深度学习的高效火车号识别[J]. 工程科学学报, 2020, 42(11): 1525
WANG Z M, LIU Z H, HUANG Y K, et al. Efficient wagon number recognition based on deep learning[J]. Chinese Journal of Engineering, 2020, 42(11): 1525
[2] O’SHEA T, HOYDIS J. An introduction to deep learning for the physical layer[J]. IEEE Transactions on Cognitive Communications and Networking, 2017, 3(4): 563
[3] LIN B, WANG X D, YUAN W H, et al. A novel OFDM autoencoder featuring CNN-based channel estimation for internet of vessels[J]. IEEE Internet of Things Journal, 2020, 7(8): 7601
[4] 王旭东, 吴楠, 王旭. 基于卷积神经网络自编码器结构的空时分组传输方案[J]. 电讯技术, 2020, 60(7): 746
WANG X D, WU N, WANG X. A transmission scheme of CNN-based autoencoder for STBC systems[J]. Telecommunication Engineering, 2020, 60(7): 746
[5] WU N, WANG X D, LIN B, et al. A CNN-based end-to-end learning framework toward intelligent communication systems[J]. IEEE Access, 2019, 7: 110197
[6] 廖勇, 花远肖, 姚海梅. 基于深度学习的OFDM信道估计[J]. 重庆邮电大学学报(自然科学版), 2019, 031(003): 348
LIAO Y, HUA Y X, YAO H M. Channel estimation based on deep learning for OFDM systems[J]. Journal of Chongqing University of Posts and Telecommunications( Natural Science Edition), 2019, 031(003): 348
[7] SOLTANI M, POURAHMADI V, MIRZAEI A, et al. Deep learning-based channel estimation[J]. IEEE Communications Letters, 2019, 23(4): 652
[8] BRIFMAN A, ROMANO Y, ELAD M. Unified single-image and video super-resolution via denoising algorithms[J]. IEEE Transactions on Image Processing, 2019, 28(12): 6063
[9] USAMA M, QADIR J, RAZA A, et al. Unsupervised machine learning for networking: Techniques, applications and research challenges[J]. IEEE Access, 2019, 7: 65579
[10] YU J, GAO X, TAO D, et al. A unified learning framework for single image super-resolution[J]. IEEE Transactions on Neural networks and Learning systems, 2013, 25(4): 780
[11] YANG L, CHEN W, LIU W, et al. Random noise attenuation based on residual convolutional neural network in seismic datasets[J]. IEEE Access, 2020, 8: 30271
[12] PHUNG S L, BOUZERDOUM A. A pyramidal neural network for visual pattern recognition[J]. IEEE transactions on neural networks, 2007, 18(2): 329
[13] ZHANG Z, LI F, ZHAO M, et al. Robust neighborhood preserving projection by nuclear/l2, 1-norm regularization for image feature extraction[J]. IEEE Transactions on Image Processing, 2017, 26(4): 1607
[14] PONNMOLI K M, SELVAMUTHUKUMARAN D S. Analysis of face recognition using manhattan distance algorithm with image segmentation[J]. International Journal of Computer Science and Mobile Computing, 2014, 3(7): 18
[15] ARIB STD-T. Evolved universal terrestrial radio access (E-UTRA); user equipment (UE) radio transmission and reception (Release 8)[J]. 3GPP TS, 2010, 36: 8
