基于向上取整的多重同步挤压变换识别时变结构瞬时频带

Identification of instantaneous frequency band of time-varying structure based on multi-synchrosqueezing transform with ceiling method

针对多重同步挤压变换及其改进算法存在未重排点问题,提出了一种新的基于向上取整的多重同步挤压变换来识别时变结构的瞬时频带。该方法首先采用Brug法对自回归模型的参数进行估计,然后再通过自回归模型对信号进行延拓,最后对估算的瞬时频率小数部分进行两次向上取整,从而很好地解决了未重排点和端点效应问题。通过两组数值算例和一个拉索试验验证了所提新方法的有效性,研究结果表明,相比现有的多重同步挤压变换及其改进算法,基于向上取整的多重同步挤压变换不但彻底去除了未重排点,而且也提高了频带的识别精度。

Aiming at the problem of non-reassigned points existing in multi-synchrosqueezing transform and its improved algorithm,a new multi-synchrosqueezing transform based on ceiling method was proposed to identify instantaneous frequency band of time-varying structure.In this method,firstly,Brug algorithm was adopted to estimate parameters of an autoregressive model,then target signal was extended with the autoregressive model,and finally fractional part of the estimated instantaneous frequency was ceiled twice to solve problems of non-reassigned points and endpoint effects.The effectiveness of the proposed method was verified with two sets of numerical examples and a cable test.The results showed that compared with the existing multi-synchrosqueezing transform and its improved algorithm,the multi-synchrosqueezing transform based on ceiling method can not only completely remove non-reassigned points,but also improve recognition accuracy of frequency band.