Condition Monitoring And Fault Diagnosis Method Of Conveyor Belt Idler Based On Sound Signal

Conveyor belt conveyor is widely used in coal-fired conveying system of thermal power plant due to its advantages of simple operation,low transportation cost and high transportation efficiency.Guided by national policies and production needs of enterprises,the fully enclosed operation of coal yard and coal-fired conveying system has become an important part of the current power plant renovation.After the coal-fired conveying system is fully enclosed,a series of new problems will be introduced: high dust concentration in the enclosed space,which is not conducive to the long-term operation of the inspection personnel.At the same time,the high temperature in summer will cause the operators to have major occupational health risks;the closed space is small,which is not conducive to the construction of the inspection robot track;the number of idlers is large.Field wiring is complex and expensive.The sound signal generated when the idler fails contains fault information components.Therefore,this paper takes the sound signal as the analysis medium,and proposes a fault monitoring method for idler bearings that combines fault diagnosis and sound source location.On the basis of theoretical research,designed and developed a conveyor belt idler condition monitoring and fault diagnosis system.The main research contents of this paper are as follows:(1)Introduce the functions and common faults of the main components of the conveyor belt conveyor.For the idler bearing with a high failure rate in the conveyor belt conveyor,analyze its failure mechanism,time domain/frequency domain feature characterization method,and transmission process from the perspective of signal processing.The interference in the time-domain/frequency-domain performance,resonance demodulation-like signal processing methods.(2)The operating environment of the conveyor belt is harsh,and the sound signal collected by the acoustic sensor often contains a large number of interference components coupled by the transmission path.In order to solve this problem,this paper proposes a variational mode decomposition(VMD)as the sound signal frequency band segmentation method,combined with the envelope spectral kurtosis index to identify the fault diagnosis method of sensitive components.First,the sound signal is decomposed into several IMF components by using the VMD method;then,the superiority of the envelope spectral kurtosis index compared with the time domain kurtosis index in dealing with strong background noise and accidental shocks is used to realize the detection of rollers containing idlers.The selection of the IMF component of the fault component;finally,the generalized cross-correlation delay estimation is performed on the selected IMF component,and the fault sound source position can be obtained by the time difference corresponding to the maximum cross-correlation coefficient in the delay domain.The experimental results show that the proposed method can extract the periodic fault information of idler faults from the coupling interference components of the transfer path,and achieve accurate fault sound source location.(3)On the basis of the above theoretical research,in order to realize the integration and visualization of the algorithm,a set of condition monitoring and fault diagnosis system of conveyor belt idler based on sound signal is developed.The system uses Python and Py Qt as the development environment to design the system user interface and subprogram modules.The subprogram modules can realize data acquisition card driving,data acquisition,signal processing(fault feature extraction and sound source location),data storage,and historical data reading and writing.and other functions.The developed user interface is tested in the actual working environment,and the results show that the developed system has good diagnostic performance.