Research On Maintenance And Troubleshooting Technology Based On TFM Three-dimensional Information Flow Model

Maintenance and troubleshooting is the main mean to ensure reliability and safety during the operation phase.With the improvement of complexity and intelligence of modern equipment,maintenance and troubleshooting is being more and more difficult.Maintenance and troubleshooting can be divided into two parts: fault diagnosis and maintenance.Based on these two aspects,this paper puts forward a maintenance and troubleshooting method based on TFM three-dimensional information flow model.This method aims at solving diagnosis of unknown new fault and the problem of low information utilization in troubleshooting.This paper studies the modeling method and the troubleshooting algorithm based on the model.The main contents are as follows:Firstly,in order to solve the problem of maintenance and troubleshooting information integration and expression,aiming at distributed,dynamic and heterogeneous maintenance and troubleshooting information,this paper presents an information integration method based on ontology and ant colony.The ontology method is used to solve the problem of semantic heterogeneous information integration.The algorithm based on ant colony pheromone is used to solve the ontology optimization problem and also improves the efficiency and accuracy of ontology construction.Secondly,a set of modeling method based on TFM framework model is given based on information integration.This paper establishes TFM framework model based on SDG,test-fault association matrix based on multi-signal flow graph and fault-maintenance mapping model based on bayesian network.Thirdly,a fault diagnosis inference method based on the TFM three-dimensional information flow model is studied and a fault diagnosis algorithm based on optimized information entropy is established.Furthermore,a maintenance and troubleshooting method based on TFM three-dimensional information flow model is studied and a maintenance information push algorithm based on fuzzy genetic neural network is established.Finally,this paper designs and develops a maintenance and troubleshooting system based on TFM three-dimensional information flow model.And this paper uses an aircraft air supply system as an example to verify the feasibility and effectiveness of the above theories and methods.