Abstract: The working environment of rolling bearings is harsh and the vibration signals are easily disturbed by noise, making bearing faults difficult to detect. In response to the above issues, whale optimization algorithm variational mode decomposition (WOA-VMD) and particle swarm optimization support vector machine (PSO-SVM) methods for rolling bearing fault diagnosis were proposed. Firstly, the WOA-VMD was utilized to find the optimal parameter combination of decomposition layers and penalty factors. Secondly, the normal and fault signals of the bearing were used as inputs for variational mode decomposition (VMD) to obtain several intrinsic mode function (IMF), and the sample entropy values of each modal component were calculated as feature vectors. Then, the feature vectors were divided into training and testing sets. Finally, the grouped feature vectors were input into the support vector machine (SVM) model and PSO-SVM model for training and fault diagnosis. The results showed that the fault diagnosis rates of the SVM model are 89.1667% and 86.250 0%, respectively, and the fault diagnosis rates of the PSO-SVM model are 100% and 99.5833%, respectively. The bearing faults are effectively identified.