Research On Fault Diagnosis Method Of Rolling Bearing Of Shearer Cutting Drum

With the rapid development of unmanned and integrated independent intelligent technology in the field of large electromechanical equipment,higher requirements are put forward for intelligent mining technology in coal mines,among which fault diagnosis is a major technical point.As the key equipment in coal mining,the shearer’s operating status is directly related to the mining efficiency.The cutting drum carries the heaviest load in the shearer body,especially the internal rolling bearing,which has a complex structure and is prone to mechanical failures.It is difficult to judge and locate the fault in time based on human experience,so it is necessary to study the fault diagnosis method of the rolling bearing in the cutting part of the shearer.Aiming at the problem of fault diagnosis of rolling bearings in the cutting drum of coal shearers,this study starts with the detection of vibration signals.By establishing the optimal parameter model and evaluation criteria for the decomposition signals,the signal denoising algorithm is optimized,and a rolling bearing based on spectral kurtosis theory is constructed.The fault detection method implements bearing condition classification.The specific research contents are as follows:First of all,the signal decomposition method in vibration signal denoising is studied.Aiming at the problem of mode mixing in the empirical mode decomposition method and the blind parameter selection in the time-varying filtering empirical mode decomposition method,a human-based method is proposed.Ant colony optimization-simulated annealing-time varying filtering based empirical mode decomposition,setting the sample entropy value as the objective function,and finding the optimal decomposition parameters.Secondly,the research on the reconstruction method of the vibration signal is carried out.Aiming at the problem of how to select the reconstruction component after the signal is decomposed,a multi-index fusion intrinsic mode function evaluation criterion based on kurtosis,smoothing factor,autocorrelation function and energy is proposed.Then,aiming at the problem of fault diagnosis of shearer cutting drum rolling bearing,a bearing fault diagnosis method based on spectral kurtosis theory is constructed,which is suitable for distinguishing four states of bearing normal,outer ring fault,inner ring fault and rolling element fault.Finally,using the bearing vibration data of Case Western Reserve University,the signal decomposition method based on characteristic parameter optimization,the signal reconstruction method based on the intrinsic mode function evaluation criterion,the comparison of decomposition methods,the distinction of four types of bearing states,different size fault diagnosis,and different speed tests in several aspects of fault diagnosis to verify the effectiveness of the proposed method;The generality and reliability of the proposed method are verified by collecting fault data on the rotor bearing test bench;the ground test of the shearer fuselage is carried out,and the actual fault signal of the shearer is collected to verify the practicability of the proposed method.Based on the above algorithm,a human-computer interaction interface for fault diagnosis of coal shearer rolling bearings was developed on the Qt platform by calling the MATLAB package library,which realized real-time fault diagnosis and tested the interface functions.Through the above tests,it is shown that the proposed fault diagnosis method is feasible.