Research On Status Monitoring And Identification Methods Of Shearer

As the core equipment of coal mining,shearer is easy to break down due to the influence of working environment in the process of operation.Therefore,in order to solve the problems of low operation reliability,many monitoring parameters and low accuracy of health evaluation of shearer,this paper relies on multi-source heterogeneous data-driven health evaluation of fully mechanized mining equipment group and multi-objective predictive maintenance decision(Subject No.:51875451).Design the shearer health condition monitoring system,construct the shearer health state evaluation index system,establish the shearer health state identification model.In order to accurately grasp the health status of the shearer.First;in view of the problem that the shearer is easily affected by environmental factors and the management can not accurately grasp the running state of the shearer,by analyzing the structure of the shearer,combing its common faults,and determining the monitoring parameters that reflect the running state of the shearer,the scheme of the shearer health monitoring system is designed,and on this basis,the sensor selection,data acquisition,communication configuration and monitoring interface design are carried out.The purpose of this paper is to lay the foundation for the completion of the shearer health monitoring system.Secondly,in order to solve the problems of complex structure,many state monitoring parameters and different representations of shearer,the grey relational analysis method is used to construct the evaluation index system of shearer health state.In order to solve the problem of low accuracy caused by unreasonable weight distribution in the process of shearer state evaluation,a shearer health evaluation model based on combined weighting method is established,and the effectiveness of the model is verified.Then,aiming at the problem that the state recognition efficiency of DBN model is not ideal,combined with the advantages of artificial bee swarm algorithm(ABC)multi-objective optimization,a health state recognition model based on ABC optimized DBN is proposed,and the state recognition rate of this model is compared with that of DBN model.Finally,the functions of data visualization,monitoring and early warning and data storage of the shearer condition monitoring system are realized,and the running state data selected by the shearer health index system are input to complete the experimental analysis of the shearer health state evaluation model based on the combined weighting method and the health state recognition model based on ABC optimized DBN,and compare the recognition accuracy of the two models.The purpose of this paper is to provide an effective identification method for accurately grasping the health state of the shearer.