Design And Research On Vibration Monitoring And Fault Diagnosis System Of Transportation In Inclined Shaft

Coal mine transportation is an important part of coal production.Inclined shaft hoisting transportation occupies a large proportion in the entire mine transportation system.In the process of inclined shaft transportation,the mine winch is the most important electromechanical equipment,which plays an important role in production and transportation.Once the winch breaks down,it will not only affect the safe production of the coal mine,but also cause serious safety accidents such as casualties.Therefore,it is very important to carry out condition monitoring and fault diagnosis on the winch.This paper takes the winch in inclined shaft transportation as the main monitoring object,analyzes the failure ratio of various parts,selects the common faults in the operation process,and starts from the vibration signal,designs and implements the inclined shaft transportation vibration monitoring and fault diagnosis system.The main research contents are as follows:(1)The common faults of the inclined shaft transportation system are introduced,the types of faults to be diagnosed are selected and the corresponding failure forms and fault mechanisms are analyzed,the sensor measuring point location layout plan is analyzed,and the overall system is carried out from both hardware and software aspects.Structure introduction;(2)Two vibration signal feature extraction methods,wavelet packet decomposition and improved empirical mode decomposition,are studied.The energy feature of the sub-band is extracted as the initial feature vector,and the correlation analysis and the variance contribution rate are combined to remove the poor IMF components,and use The envelope spectrum analysis method based on Hilbert transform compares the performance of the two feature extraction methods,and the results show that the wavelet packet decomposition method is more suitable for extracting vibration signal features;(3)The classification algorithm of fault diagnosis is studied,combined with the classification principle of BP neural network,the basic model of fault diagnosis is constructed,and the weights and thresholds of BP neural network are optimized by thinking evolution algorithm and genetic algorithm respectively.The processed feature samples are selected to train the optimized diagnosis network and diagnose signals in unknown states.Using mean square error and classification accuracy as indicators to evaluate two BP neural networks with different optimization methods,the results show that the GA-BP application effect is better.Then tradaboost algorithm is used to further optimize the fault diagnosis model;(4)Using labview and matlab joint programming to develop the inclined shaft vibration monitoring and fault diagnosis system.It mainly includes four modules:system management,parameter management,monitoring and alarm,and fault diagnosis.The method and the software developed in this paper are verified with practical application and experimental platform.The results show that the proposed method has strong applicability,the developed system has complete functions,and has obtained satisfactory diagnosis results for common mechanical failures of winches.The paper has 94 pictures,16 tables,and 81 references.