Research On The Working Status Analysis And Fault Early Warning Method Of Belt Conveyor

As the main tool of material conveying,the working state of belt conveyor directly affects the operation effect of equipment and the production efficiency of transportation industry.Due to the bad working environment of the belt conveyor,it is prone to failure in its operation,such as deviation,longitudinal tearing,skidding and other faults.There are various reasons for these failures.Once the belt conveyor breaks down in the working process,it will cause huge economic losses to the industrial production,and even threaten the personal safety of the staff.Therefore,it is necessary to study the working state of the belt conveyor.It has important theoretical value and practical significance to analyze the running state of the belt conveyor to judge its potential risks.This thesis is devoted to the research on the model construction,prediction method and cause diagnosis of the belt conveyor working state analysis and fault warning.The specific research work is as follows:(1)The extraction method of fault characteristic parameters of belt conveyor is studied.Firstly,the working principle and structural composition of the belt conveyor are elaborated,and the research is carried out from the analysis of the cause of the failure.Then the prevention and control methods of typical faults are proposed according to the causes of the faults.Finally,principal component analysis is used to extract and reduce the dimension of monitoring indexes,and the fault characteristic parameters are determined.(2)The fault prediction model of belt conveyor based on particle swarm least squares support vector machine is established.Firstly,the least squares support vector machine(LSSVM)method is proposed based on the traditional support vector machine(SVM).Then the particle swarm optimization algorithm is used to optimize the two parameters of the least squares support vector machine,and the model of the least squares support vector machine is established,which is used to predict the fault characteristic parameters of the belt conveyor.Finally,the simulation comparison shows the validity of particle swarm least squares support vector machine model in the prediction of fault characteristic parameters of belt conveyor.(3)Fault diagnosis and early warning method of belt conveyor based on fuzzy theory is proposed.Firstly,according to the relationship between the typical fault symptoms and fault causes of belt conveyor,the fuzzy theory is introduced into the fault diagnosis and warning model of belt conveyor.Then the weight of fault causes is determined by analytic hierarchy process and the probability of fault causes is further calculated.Finally,the calculation results show that the proposed method can effectively diagnose and warn the fault of the belt conveyor.