Design And Application Of Interconnection Platform For Steel Pipe User Service

The user service interconnection platform is a knowledge base system used to realize the interconnection of steel pipe users,steel pipe information and steel pipe services.In this paper,the extension theory is integrated into the construction of the steel pipe service interconnection knowledge base,and a kind of extension decision method is proposed and applied in the knowledge base reasoning case.The proposed extension neural network algorithm is used to train the data in python,and the training model is obtained to solve the actual engineering problem of seamless pipe corrosion prediction.Finally,the design and development of the steel pipe user service interconnection platform of the mobile APP terminal and the Web are implemented and put into use.Firstly,the overall design scheme of the service interconnection platform for steel pipes is given.This paper analyzes and discusses the actual demand analysis of steel enterprise,function structure design of the platform and the database design of steel enterprises.The system outline design and detailed design of the platform is given.Secondly,based on extension theory,this paper conducts an in-depth study on the knowledge base of steel pipe user service.Extension element theory is applied into the steel pipe user service interconnected knowledge base model.Knowledge classification,knowledge modeling and knowledge base construction are studied.A kind of extension decision knowledge reasoning algorithm is put forward which combines with actual case analysis application of service platform,and the corresponding system implementation is proposed.Thirdly,the corrosion prediction algorithm of seamless pipe is proposed based on the extension neural network and the system implementation is given.The Practical engineering problem of seamless pipe corrosion prediction is analyzed and the extension neural network is applied to it.The simulation analysis is made by using the python language and the training data error rate curve and the training accuracy curve comparised with BP neural network are given,which verify its feasibility.The system function is realized.Finally,according to the detailed functional modules in the platform knowledge base,the system development is realized.The front system is developed by using HTML5,CSS,JavaScript,etc.,and the back system is developed by using the Python language.The MongoDB database is used to store knowledge.The specific system is implemented from the mobile APP(android and IOS)and Web side respectively.