CAJ | 학술논문

从信号处理的角度分析了防撞雷达虚报警率、漏报警率偏高的原因，采用AR模型功率谱估计的Burg算法代替传统的FFT算法，并将粗神经网络应用于防撞雷达目标识别。仿真结果表明，此方法提高了雷达信号处理的准确度和目标识别率，能有效地降低漏报警、虚报警率。
종신호처리적각도분석료방당뢰체허보경솔、루보경솔편고적원인，채용AR모형공솔보고계적Burg산법대체전통적FFT산법，병장조신경망락응용우방당뢰체목표식별。방진결과표명，차방법제고료뢰체신호처리적준학도화목표식별솔，능유효지강저루보경、허보경솔。
This article analyzes the reasons for the high rate of leakage alarm and false alarm of the anti-collision radar from the point of the signal processing, using the Burg algorithm of AR models power spectrum estimation instead of the traditional FIT algorithm, and use the rough neural network for anti-collision radar target identification. Simulation results show that this method improves the accuracy of radar signal processing and target recognition rate, which can effectively reduce the leakage alarm and false alarm rate.