Application of independent component analysis in denoising of steel structural vibration signal in frequency domain

In structural vibration signals, some kind of convolution takes places imultaneously with the linear mixing. In order to reduce noise and obtain the useful signals, the paper firstly transforms time signals into frequency signals through FFT, then applies FastICA to separate the useful signals from signals mixed by noise, transforms frequency signals into time signals through IFFT, finally accomplishes the separating of the useful signals and noise. This method is proved effective by denoising the steel structural vibration signals in lab.