Remote Monitoring And Fault Diagnosis System For Glass Magnesium Plate Production Line

With the rapid development of the construction industry,the proportion of the building decoration material industry in the construction industry has become increasingly prominent.The glass magnesium board with the characteristics of fireproof,moisture-proof and tasteless has become one of the current popular building decoration materials.With the deepening of automation of glass magnesium plate production line,the difficulty of fault diagnosis of equipment is also increasing.Traditional fault diagnosis technology lacks intelligence,has poor diagnosis effect and cannot guarantee real-time performance.Therefore,the remote monitoring and fault diagnosis technology,which can make real-time diagnosis according to the running state of the equipment and give timely feedback through the man-machine interface,has become a hot research topic in the field of automatic production line.Based on the research of remote monitoring and fault diagnosis technology by domestic and foreign scholars,this thesis designs and develops a remote monitoring and fault diagnosis system for the glass magnesium board production line.The main research contents include the following aspects:(1)Introducing the composition and working principle of each unit of the glass magnesium board production line in detail,and perform fault analysis on this basis.(2)BP neural network is selected to diagnose the fault symptom and fault state.Firstly,the basic principle of BP neural network is introduced.On the basis of analyzing its shortcomings,genetic particle swarm optimization algorithm is selected to optimize the neural network.By improving the inertia weight and cross mutation probability of genetic particle swarm optimization,the adaptability of the algorithm is improved.Through the MATLAB simulation of historical fault data,the improved BP neural network is compared with PSO-BP and gapso-bp.The results show that the improved BP neural network has improved the diagnosis accuracy and speed.(3)Introducing the principle of fault tree analysis(FTA),adding T-S fuzzy theory on the basis of analyzing the shortcomings of traditional FTA,and constructing T-S fuzzy FTA model of production line.In order to solve the problems of large amount of calculation and single reasoning method of T-S fuzzy fault tree,T-S fuzzy fault tree model is mapped to bayesian network to evaluate the reliability and diagnose the fault of production line.(4)Establishing a fault diagnosis expert system for the glass magnesium board production line,and integrate the BP neural network,Bayesian network and the traditional expert system.Using non-automatic and active knowledge acquisition methods to construct expert knowledge base selection,using production notation to describe rules,selecting SQL database to store knowledge and finally constructs an inference engine with three inference mechanisms.(5)First,introducing the overall design plan for remote monitoring and fault diagnosis of the glass magnesium board production line.Based on the B/S architecture,using Visual Studio 2012,SQL Server 2016 and MATLAB to jointly develop the remote monitoring and fault diagnosis system of the glass magnesium board production line.