基于随机共振的井下无线电磁2FSK信号解调  

Demodulation of Downhole Wireless Electromagnetic 2FSK Signals Based on Stochastic Resonance

作　　者：张国辉 李伟勤[1] Zhang Guohui;Li Weiqin(School of Electrical Engineering and Znformation,Southwest Petroleum University)

机构地区：[1]西南石油大学电气信息学院

出　　处：《石油机械》2024年第9期10-16,共7页China Petroleum Machinery

基　　金：四川省科技计划项目“石油套管环境下井下无线低频电磁信号高速双向传输系统”(2020YFG0182)。

摘　　要：井场及周边电器所带来的噪声干扰会对接收到的无线电磁2FSK调制信号产生影响,在信噪比低时提取信号特征困难。为此,提出了一种基于浣熊算法的自适应双稳态随机共振系统,以降低2FSK信号的误码率。该方法充分利用浣熊算法的全局探索和局部优化平衡能力,通过并行选择和优化随机共振系统的多个参数,以获得系统输出的最大信噪比增益。利用卷积神经网络对随机共振系统输出的信号进行解调,并评估其误码率。仿真和试验结果表明,在低信噪比条件下,基于浣熊算法的随机共振系统输出信号的特征频率相对于蚁群优化算法更加显著,并且具有更低的误码率。研究结果可为井下信号实时传输提供技术支撑。The noise interference caused by the electric appliances at and around well site has an impact on the received wireless electromagnetic 2FSK modulation signals,making it difficult to extract signal features when the signal-to-noise ratio(SNR)is low.Therefore,an adaptive bistable stochastic resonance system based on the coati optimization algorithm(COA)was proposed to reduce the bit error rate of 2FSK signals.This method takes full advantage of the global exploration and local optimization balance ability of COA to conduct selection and optimization of multiple parameters of the stochastic resonance system,allowing the system output to have the maximum SNR gain.Then,the convolutional neural network(CNN)was used to demodulate the output signals of the stochastic resonance system and evaluate their bit error rate.The simulation and test results show that under low SNR conditions,the characteristic frequency of output signals of the stochastic resonance system based on COA is more significant than that of the ant colony optimization(ACO)algorithm,and has a lower bit error rate.The research results provide technical support for the real-time transmission of downhole signals.

关 键 词：井下信号传输 随机共振 浣熊算法 卷积神经网络 2FSK调制信号 误码率 

分 类 号：TE927[石油与天然气工程—石油机械设备]