摘要
离散傅里叶变换(DFT)在实际工程应用中存在误差,需要进行校正,目前工程中常用的是比值校正法和相位差校正法等。本文提出一种新的频谱校正计算方法,首先,对信号进行一次快速傅里叶变换;然后对信号的一半进行内积运算,进行一次反余弦运算识别出信号的真实频率,并且以该方法为基础结合迭代运算进行密集频谱的识别。仿真结果表明,该方法具有较高的计算精度和抗干扰能力;与迭代运算结合以后,能够解决多频信号之间的交叉干扰,识别出密集频谱中包含的各个信号分量。
In engineering applications, the discrete Fourier transform （DFT） has leakage errors and thus needs spectrum correction. For this purpose, the most frequently used methods are amplitude ratio correction method and phase difference correction method. We propose a new spectrum correction method. Following the method, we perform the fast Fourier transform of the original signal and then the inner product calculation of a half of the signal. We also perform its inverse cosine calculation to identify its real frequency. Jointly with iteration calculation, we use the method to identify dense spectrum. The simulation results show that our method is accurate and robust to noise disturbance and that in combination with iteration calculation, our method can identify various signal components contained in a dense spectrum and reduce the cross interference among signals of different frequencies.
出处
《机械科学与技术》
CSCD
北大核心
2011年第12期2040-2043,共4页
Mechanical Science and Technology for Aerospace Engineering
基金
江苏省动力机械清洁能源与应用重点实验室开放基金项目(QK09008)
江苏大学高级专业人才科研基金项目(11JDG096)
江苏高校优势学科建设工程项目资助
关键词
频谱校正
离散傅里叶变换
泄露误差
内积运算
spectrum correction
discrete Fourier transform
leakage error
inner product
