In order to overcome the shortcomings of concealed early fault features of rolling bearings which can not be better recognized and the accuracy of early fault diagnosis is not high enough, a novel collaborative diagnosis method is presented combing with variational modal decomposition (VMD) and stochastic configuration network (SCN) for incipient faults of rolling bearing. First, decomposing the original signal by VMD, and then extracting peak-to-peak of intrinsic mode function component from each fault, and calculating sample entropy of peak-to-peak to construct characteristic sample of fault. Second, based on VMD composition, proposing an incipient fault diagnosis method which is named SCN. Finally, compared with other classification methods, the results show that the proposed collaborative method is effective and advantageous.

To overcome the shortcomings that the early fault characteristics of rolling bearing are not easy to be extracted and the identification accuracy is not high enough, a novel collaborative diagnosis method is presented combined with VMD and LSSVM for incipient faults of rolling bearing. First, the basic concept of VMD was introduced in detail, and then, the adaptive selection principle of parameter K in VMD was constructed by instantaneous frequency mean. Furthermore, we used Lagrangian polynomial and Euclidean norm to verify the value of K accurately. Secondly, we proposed a classification algorithm based on PSO-optimized LSSVM. Meanwhile, the flowchart of the classification algorithm of fault modes may be also designed. Third, the experiment shows that the presented algorithm in this paper is effective by using the existing failure data provided by the laboratory of Guangdong Petrochemical Research Institute. Finally, some conclusions and application prospects were discussed.