Research On Bearing Fault Diagnosis Method Of Logistics Machinery Based On Vibration Signal Analysis

Logistics machinery bearing is the core component of the rotor system of logistics machinery equipment,and it is also a component prone to failure.Its safe operation has a vital impact on the whole logistics machinery equipment.Therefore,it is of great significance to study the bearing fault diagnosis method of logistics machinery.In this paper,the logistics machinery bearing is taken as the research object,and on the basis of summarizing the existing fault diagnosis technology,the feature extraction method of logistics machinery bearing vibration signal is studied.The research contents of this paper are as follows:The simulation experiment of vibration signal acquisition of logistics mechanical bearings is carried out.The vibration signals of single failure mode and composite failure mode are collected in four states,which are normal,inner ring,outer ring and rolling body,and provide data for subsequent verification methods.Aiming at the problem of bearing fault signal complexity and difficult to extract fault features of logistics machinery,multi-scale fuzzy entropy feature extraction method combined with support vector machine is used to diagnose the original vibration signal of single fault mode.Compared with the single scale algorithm,multi-scale fuzzy entropy can extract fault features in multi-scale,which has higher calculation accuracy and recognition efficiency.In view of the problem that it is difficult to extract the early fault characteristics of logistics machinery bearing,the multi-scale fuzzy entropy and support vector machine are used to diagnose the single fault mode.It is found that the multi-scale fuzzy entropy has the advantages of comparing with the single scale algorithm,but also has the disadvantages of hard threshold segmentation and ignoring high frequency components.Therefore,it is not easy to fully benefit from the original complex vibration signal Based on the fault characteristics and the defects of multi-scale fuzzy entropy,a fault feature extraction method based on adaptive fuzzy entropy is proposed.In view of the traditional fault feature extraction method,the fault signal of logistics machinery bearing can not be fully utilized and analyzed.The EMD method is used to decompose the original vibration signal.The advantage of the EMD method is that the original vibration signal can be decomposed into different frequency signals and the fault characteristics of the original vibration signal can be analyzed from different frequency angles.The experimental results show that the adaptive fuzzy entropy can better identify the feature compared with the traditional feature extraction method.Aiming at the problem that it is difficult to identify the early fault features of logistics machinery bearing,a feature extraction method based on intrinsic feature scale decomposition is proposed.Intrinsic characteristic-scale decomposition is a new adaptive decomposition method for noise reduction.It can decompose a complex vibration signal into several product components and a residual component.It combines the advantages of the decomposition process of the local mean decomposition method and the special construction of the local mean function and envelope estimation function in the intrinsic time scale decomposition method The intrinsic characteristic scale decomposition method not only improves the calculation accuracy,but also improves the calculation efficiency.