Research On Fault Diagnosis Technology Of Belt Conveyor Bearing Based On Vibration Signal Analysis

Belt conveyor is a continuous transportation equipment in modern production.It has the advantages of long distance,low freight,large volume,convenient loading and unloading,low energy consumption,suitable for bulk transportation,etc.It has been widely used in coal,mining,port,electric power,metallurgy,chemical industry and other fields.It has become the three main industrial transportation tools together with automobile and train.Rolling bearings are the key components in belt conveyors,and they are also the most prone to failure.In order to avoid safety accidents,it is necessary to detect and diagnose early failures of rolling bearings and deal with them in a timely manner.This paper studies the fault diagnosis technology of belt conveyor bearings based on the analysis of vibration signals,discusses the types of belt conveyor bearings and the causes of faults,and analyzes the bearing fault vibration signal from the time-domain,frequency-domain and time-frequency-domain.The correspondence relationship between the characteristic parameters in the time-frequency domain and bearing faults was found,which provided a basis for bearing fault diagnosis;After analyzing the advantages and disadvantages of using wavelet transform and Empirical Mode Decomposition(EMD)to process vibration signals,a spectral kurtosis algorithm based on wavelet packet decomposition and Complementary Ensemble Empirical Mode Decomposition(CEEMD)is proposed.Feature extraction and fault diagnosis of belt conveyor bearing fault vibration signal.In this method,the frequency band of the bearing fault vibration signal is analyzed to obtain its frequency band.A band-pass filter is designed according to the frequency band.After the band-pass filter is filtered,wavelet packet decomposition is performed.The effective Intrinsic Mode Function(IMF)was selected based on the kurtosis and correlation coefficient.The IMF component is used to reconstruct the wavelet packet signal.Through the analysis of the envelope spectrum of the reconstructed wavelet packet signal,the characteristic frequency of the bearing fault signal is extracted,and the bearing fault diagnosis is performed based on the characteristic frequency,which suppresses the background noise and improves the modal aliasing phenomenon.Improved time-frequency resolution and accuracy of fault diagnosis;A rolling bearing fault testing platform was established,and experiments and verifications of the characteristics of the belt conveyor bearing fault vibration signal extraction and diagnosis method proposed in this paper were carried out by using the public database of bearing vibration signals of the Case Western Reserve University and the measured data of the rolling bearing fault testing platform.The results show that this method can effectively identify the fault characteristics and types of rolling bearings and complete the fault diagnosis of bearings.This method can be used for early diagnosis of belt conveyor bearing faults,timely processing of faults,and avoiding safety accidents.It is of great application value to use belt conveyors in coal,mines,ports,power,metallurgy,and chemical industries.