Research On Remote Condition Monitoring And Fault Diagnosis Technology Of Key Components Of Baggage Sorting System

Induction Motor plays an important role in driving in the process of airport baggage transport,bearing as the one of the key components of the motor,directly or indirectly lead to most motor faults,so the condition monitoring and fault diagnosis of motor bearing is very important.Because the vibration signal can well reflect the early fault characteristics of bearing under the condition of noise interference,it has become the main means of bearing fault diagnosis.So the research emphasis of this paper is based on vibration signal of motor bearing fault condition monitoring,fault feature extraction and pattern recognition,and proposes the fault diagnosis method in the background noise environment.The main research contents are as follows:This paper first expounds the basic structure of rolling bearing,the failure modes,the vibration mechanism,the calculation method of the fault characteristic frequency in theory,provides theoretical basis for subsequent design of condition monitoring system and experiment of fault diagnosis.Secondly,based on the function of the motor bearing vibration monitoring system,upper machine condition monitoring system based on Labview is developed,the system has the signal acquisition,signal analysis and remote web technology,and other functions,can realize remote condition monitoring of vibration signals,including time domain analysis and frequency domain analysis,time-frequency analysis and fault alarm,etc.The system is proved to be reliable and practical by simulation and data acquisition experiment on the vibration test bench of Cut-2 rotor bearing.Finally,according to theory that bearing fault signal cycle components affected by the interference of background noise makes it harder to extract the fault feature,the fault feature extraction method based on the autoregressive minimum entropy deconvolution(AR-MED)and improved multi-scale permutation entropy(IMPE)is put forward,and uses grey wolf optimizer-based support vector machine to realize bearing fault recognition.The experimental data are from the database of the case western reserve university in the United States.The experimental results show that this method can effectively diagnose the fault type and degree of motor bearing and has a good application prospect.