基于深度学习的高效矿井MIMO信号检测研究  

An efficient mine MIMO signal detection method based on deep learning

作　　者：韩飞 王明博 王安义[3] 刘朝阳 HAN Fei;WANG Mingbo;WANG Anyi;LIU Zhaoyang(Shaanxi Energy Institute,Xianyang 712000,China;College of Energy Engineering,Xi'an University of Science and Technology,Xi'an 710054,China;College of Communication and Information Engineering,Xi'an University of Science and Technology,Xi'an 710054,China)

机构地区：[1]陕西能源职业技术学院,陕西咸阳712000 [2]西安科技大学能源学院,陕西西安710054 [3]西安科技大学通信与信息工程学院,陕西西安710054

出　　处：《煤炭工程》2024年第5期166-172,共7页Coal Engineering

基　　金：国家自然科学基金(U19B2015);陕西能源职业技术学院科研创新团队(2021KYTD06)。

摘　　要：针对智能接收机检测效率低的问题,提出了一种基于深度学习的高效矿井MIMO信号检测模型,该模型由非线性映射网络以及纠错网络共同组成。非线性映射网络实现接收信号到二进制比特信号的初步恢复,纠错网络用于纠正非线性映射网络恢复的错误信号,提升信号检测精度。通过搭建矿井MIMO通信系统对该模型的性能进行了验证,仿真结果表明,在模拟矿井MIMO通信环境中,在发射端调制方式,信道编码方式改变以及信道环境变化时其性能优于传统接收机。同时,相对于深度接收机模型,该模型具有更高的检测效率。这项研究为解决智能接收机译码效率低的问题提出了一个新的解决方案,并在复杂的矿井场景中证明了该模型的性能优势。A deep learning-based efficient MIMO signal detection model for mining environments was proposed,which was comprised of nonlinear mapping network and error correction network.The nonlinear mapping network is responsible for the initial recovery of received signals into binary bit signals,while the error correction network corrects the errors introduced by the nonlinear mapping network,thereby improving the signal detection accuracy.The performance of the proposed model was validated through simulations conducted in a mining MIMO communication system.The simulation results show that,in the simulated mine MIMO communication environment,its performance is superior to traditional receivers when the modulation method at the transmitter,channel coding method,and channel environment change.Additionally,compared to deep receiver models,the proposed model achieves higher detection efficiency.The method is a novel solution to the low decoding efficiency of intelligent receivers,and its performance advantage has been proved in the complex environment of underground mine.

关 键 词：矿井通信 智能接收机 深度学习 MIMO 

分 类 号：TD655[矿业工程—矿山机电]