Fault Diagnosis And Prediction System Of Mine Hoist Driven By Multi-monitoring Information

As the "throat" of mine production,mine hoist is the key mechanical equipment in the production and transportation process of modern coal mine.Once the hoist fails,the staff can not carry out rapid diagnosis and timely maintenance,which will cause great losses to the whole mine production.Therefore,how to quickly and accurately find the cause and point of failure and predict accurately before the failure is of great significance to its safe and reliable operation.Aiming at the deficiency of fault diagnosis and prediction design of mine hoist at present,this paper designs a fault diagnosis and prediction system of mine hoist driven by multi-monitoring information.The system consists of perception layer,transport layer and application layer.a sensing layer is composed of monitoring nodes and convergent nodes: the monitoring nodes are arranged on each key device of the hoist to collect the running information,then the data is uploaded to the convergent node by wireless transmission technology,and the convergent nodes are arranged near the monitoring node to converge the signals collected by the current site monitoring node;the transmission layer is mainly routing nodes,which receive the signals uploaded by the convergent nodes and transmit to the application layer through the rs485;and the application layer is the terminal monitoring center,which is used to receive,analyze and display the data uploaded by the routing nodes.In order to meet the high requirements of mine hoist for fault diagnosis and fault prediction,this paper takes the main hoist of Xu Tuan mine of Huaibei mining group as the research background and uses multi-source information fusion technology to fuse the collected data.On the one hand,the data after fusion enters the fault diagnosis model,on the other hand,it enters the fault prediction model,and carries on the data analysis and calculation.In this paper,the fuzzy fault tree and bayesian network algorithm are combined to analyze the reliability of Bayesian network and determine the fault type and location.At the same time,the least square support vector machine algorithm is applied to the fault prediction of mine hoist.The above fault diagnosis and prediction methods can ensure the accurate prediction before the fault occurs,and timely and accurate diagnosis when the fault occurs,so as to ensure the safe and efficient operation of the hoist.Finally,the performance test and function test of the system show that the performance of the mine hoist fault diagnosis and prediction system based on multi-monitoring information is satisfied with the design requirements,and the system configuration is reasonable.It has high theoretical and practical significance to realize the function of fault diagnosis and prediction of mine hoist.Figure[61] Table[13] Reference[64]...