Operating Reliability Assessment Method Based On FVMD-MPE And FSVDD

The normal operation of mechanical equipment is an important guarantee for industrial production,its operational reliability assessment technology has been paid more and more attention.In this paper,the feature extraction and operating reliability assessment which are taken as two key aspects,are studied based on the analysis of vibration signal.A reliability assessment method based on the fast variational mode decomposition,the parameter optimized multi-scale permutation entropy and the fuzzy support vector data description is proposed.The operation reliability evaluation of the mechanical equipment is realized by establishing the relationship between the operation state information and the operation reliability of the mechanical equipment.Firstly,to further speeding up that decomposition of the signal,on the basis of variational mode decomposition,a signal analysis method based on fast variational mode decomposition is proposed.This method introduces the idea of fast iteration and carry out secondary updating on that lagrange multiply operator.,so under the condition that the iteration termination criterion is unchanged,the convergence speed of the algorithm is accelerated.The decomposition performance of fast variational mode decomposition method is analyzed and verified by simulation signal.The validity of the method is verified by the measured signal of the bearing.Secondly,analyzing the effect which is caused by the parameters of multi-scale permutation entropy algorithm which are the length of time series N,the embedding dimension m,the delay time ? and the scale factors s.Aiming at the parameter determination problem of multiscale permutation entropy algorithm,a method of parameters optimization based on directed self-organising dynamic topology is proposed.Then,combining the fast variational mode decomposition and multi-scale permutation entropy of parameter optimization to extracting fault feature information.Finally,the validity of the proposed method is verified by the measured bearing signals.Thirdly,in order to deal with the lack of fault samples in operational reliability assessment the traditional reliability assessment method,a operating reliability assessment method based on the fuzzy support vector data description is proposed,which only needs the sample under normal conditions to establish the reliability assessment model.This method introduces the degree of membership coefficient for each sample on the basis of support vector data description,and then describes the degree of importance of each sample or the uncertainty of its category,and establishes a more effective evaluation model.The effectiveness is verified by vibration signal of rolling bearing.Finally,the vibration signals of different operating conditions of the gears collected separately on the experimental platform is taken as the research object.The fast variational mode decomposition method is used to decomposed and reconstructed the original vibration signals,and the feature is extracted by the parameter optimized multi-scale permutation entropy algorithm.Then,the operating reliability assessment is realized by fuzzy support vector data description.The results show that there are differences in the operating reliability of gears under different operating conditions.The proposed method can accurately evaluates the reliability of gears under different operating conditions.