基于GA-SVM算法的矿井多模无线信号调制识别

Mine Multimode Wireless Signal Modulation Recognition Based on GA-SVM Algorithm

矿井信息化是煤矿安全生产的有效保障,而矿井多个信息子系统往往采用不同的信号模式,形成一体化信息系统必须实现多系统融合,多模信号的检测识别是多系统融合的关键。针对普通支持向量机(SVM)分类器在矿井大小尺度衰落信道下低识别率的问题,提出优化SVM分类识别的方法。将数据样本集分为测试数据集和训练数据集,使用遗传算法对训练数据集中SVM的惩罚因子和核函数进行寻优处理,得到优化的SVM模型,并用此模型对测试集进行测试分类。仿真结果表明,在信噪比为-5 dB的大小尺度衰落信道环境下,四种信号的平均识别率均能达到80%以上;在信噪比大于-3 dB的大小尺度衰落信道环境下,四种信号的平均识别率均能达到90%以上。

Mine informatization is an effective guarantee for coal mine safety production.Many information subsystems in mines often adopt different signal modes.To form an integrated information system,multi-system fusion must be realized.Multi-mode signal detection and identification is the key to multi-system integration.Aiming at the problem of low recognition rate of common SVM classifier under low SNR,a method of optimizing SVM classification and recognition was proposed.The data sample set was divided into test data set and training data set.The genetic algorithm was used to optimize the penalty factor and kernel function of the SVM in the training data set to obtain the optimized SVM model,and the test set was tested and classified.The simulation results show that the average recognition rate of the four signals can reach more than 80%in the three channel environments with SNR of-5 dB.The average recognition rate can reach more than 90%as SNR greater than-3 dB in the three channel environments.