Research On Dynamic Load Identification Methods Of Crawler Travel System

The crawler travel system is the most basic component of the continuous miner.Due to the large impact load of the crawler travel system and the complex and harsh working environment,the pin shaft between the track plates is easy to break,resulting in the stoppage of coal mining,which seriously affects the working reliability.Therefore,it is very important to study the load between the track plates of the crawler travel system.Aiming at the practical engineering problem that the crawler travel system has a bad working environment and the load cannot be directly and effectively obtained,a vibration signal load identification method based on genetic neural network and a dynamic load estimation method based on similarity theory are proposed.In genetic neural network based load identification.The road test method is used to collect 5 sets of vibration acceleration data and a single set of stress load data of the crawler travel system.Discussed the influence of road roughness frequency and driving wheel meshing frequency on the vibration and stress load of crawler travel system.Used fast Fourier transform to denoise the original stress load data.According to the ride comfort index of the crawler travel system,the sym8 wavelet function is used to extract the five-layer feature of the vibration acceleration signal.Then 5 groups of wavelet transform decomposed acceleration data and filtered stress load data are used as the input and output of the GA-BP neural network for training and verification,revealing the relationship between vibration and stress load in the moving process of the crawler travel system.The results show that road roughness frequency,meshing frequency,and rotating frequency are the main frequency components of crawler vibration,the vibration frequency caused by road roughness is 13.765 Hz,the meshing frequency of the driving wheel is68.25 Hz,and the rotating frequency is 3.25 Hz.After many tests,the best hidden layer neurons number of BP neural network is 63.The stress load identified by the GA-BP neural network is highly consistent with the expected stress load,and the relative error is 4.5%,which verifies the effectiveness of the method.In terms of dynamics simulation.The three-dimensional models of the model vehicle and the crawler travel system of the continuous miner(referred to as the prototype vehicle)are established in Solidworks respectively,and the dynamic simulation models of the model vehicle and the prototype vehicle are established by adding drive,contact and constraint into Recurdyn.In order to obtain the stress at the root of the drive sprocket and the vibration acceleration at different positions of the vehicle body,the drive sprocket and the vehicle body are made flexible in Ansys.The accuracy of the model vehicle dynamics simulation is verified by comparison with the experiment.The accuracy of the simulation is verified by comparing the theoretical travel resistance torque and the driving torque obtained by the simulation.The results show that the accuracy of the dynamic model of the model vehicle and the prototype vehicle is within the allowable error,the vibration acceleration of the model vehicle fluctuates between ±2g,the stress load is mainly within 9k Pa,the stress of the prototype vehicle is within 6.8MPa when driving on the level road,and the peak stress is 15.4MPa when crossing the convex obstacle.In terms of dynamic load estimation based on similar theory.The vibration acceleration and stress load data of the model vehicle are obtained by experiments,and the dynamic load identification of the prototype vehicle is discussed.Based on the similarity criterion,the rigid-flexible coupling dynamic model of the model vehicle and the prototype vehicle is established,the similarity parameters between the model vehicle and the prototype vehicle are determined,the vibration acceleration and stress load variation law of the model vehicle and the prototype vehicle are clarified.The results show that the vibration acceleration and stress load amplitude obtained from the dynamic simulation of the model vehicle are consistent with the experimental results of the model vehicle.The driving torque obtained from the dynamic simulation of the prototype vehicle is consistent with the theoretical travel resistance torque.According to the test load of the model vehicle and similar index,the stress load of the prototype vehicle is 6.83 MPa,the dynamic simulation of the prototype vehicle shows that the stress load is 8MPa,and the relative error between them is 14.6%,which verifies the validity of the dynamic load estimation method of the crawler travel system.This paper is applied to study the dynamic load of crawler travel system,which reduces the test cost and provides a good theoretical basis for the reliability research of crawler travel system of coal mining machinery.