Successive variational mode decomposition and blind source separation based on salp swarm optimization for bearing fault diagnosis

In this paper, we are interested in developing a new approach that combines successive variational mode decomposition and blind source separation based on salp swarm optimization for bearing fault diagnosis. Firstly, vibration signals pre-processed using to increase the signal-to-noise ratio. Then, dynamic time-warping algorithm is adopted select most effective modes which will be considered mixture signals. second step, apply (SSA) estimating de-mixing matrix extract independent components from However, SSA suffers problem of population diversity. Consequently, it offers somewhat different sources at every execution program. To overcome shortcoming, SSA-based estimation executed several times with ranges initial positions. fuzzy C-mean introduced reliable components. The suggested method tested two experiments compared state-of-the-art methods. obtained results demonstrate effectiveness recovering extracting frequency bearings.