Aiming at the problem of difficult parameter selection in bearing fault diagnosis by variational modal decomposition (VMD)

a method based on the northern goshawk optimization (NGO) algorithm to optimize the VMD parameters is proposed in this paper. Firstly

after using the NGO optimization algorithm to find the optimal number of decomposition layers and penalty factors of the VMD decomposition

the optimal parameters are input into the VMD to decompose the fault signal to obtain the specified number of intrinsic mode function (IMF). Secondly

the multi-scale ranger entropy (MRE) feature extraction method is used to extract features from the decomposed IMF of VMD to form a series of feature sample sets for better fault classification. Finally

the fault diagnosis of the feature-extracted data set is performed by a fault classification model

and the effectiveness of the proposed method is illustrated by experimental results.