Study On Performance Degradation Evaluation Of Shearer

With the development of both Industrial Internet of Things and intelligent sensor technology,the coal mine industry is developing in the direction of digital and intelligent mine.Many coal mine mechanical equipment are equipped with many kinds of sensors to monitor the status of equipment in real time.A large number of real-time monitoring data are generated by sensors of coal mine mechanical equipment.However,most of the coal mines still use the traditional mechanical equipment maintenance mode,which means that a large number of data generated by sensors are not well applied in the actual coal mines.The reason maybe most of the coal mines cannot transform the data acquired by sensors into usable information.This thesis takes the shearer as the object,aims to use the sensor data to get the measurement of performance degradation degree.So a large number of data of coal mine equipment can be reasonably transformed into a measurement convenient for use.And then this measure can paves the way for the subsequent use of this measurement to take a reasonable way of equipment maintenance.The main work of this paper is as follows.(1)This thesis analyzes the fault and maintenance status of shearer from the aspects of structure,function and fault status.On this basis,it summarizes the indicators to distinguish the different working conditions of the shearer,which provides a basis for the selection of the working condition monitoring parameters of the post text shearer.(2)This thesis finds a method to evaluate the performance degradation of shearer.In order to represent the performance degradation evaluation of different parts of shearer more accurately,it puts forward the method of limit learning machine to identify the working conditions of shearer,and establishes their own Gaussian mixture models under different working conditions,and uses relative entropy to measure the degree of performance degradation.(3)The cutting part with the highest failure rate of shearer is selected as the research object,and its performance degradation is evaluated.On the basis of the above analysis and combined with the characteristics of the cutting part,four monitoring parameters and six representative performance monitoring parameters are selected to distinguish the working conditions of the cutting part.After data standardization,working condition model training,performance data dimensionality reduction,working condition identification,Gaussian model training and comparison of different working conditions,the performance degradation trend of the cutting part of the shearer is obtained The corresponding intelligent maintenance strategy is proposed.There are 17 figures,10 tables and 85 references in this thesis.