Better Risk Response Method Based on Neural Network and Framework Reasoning in Aircraft Assembly Project

Abstract

The expert judgment risks respond method used now in aircraft assembly project need to be improved for its subjectivity and complication. To make it more effective and reliable, we proposed an improved method that integrated neural network with framework reasoning. Firstly, basing on frame theory, we stored experts' experiences about risk response in the expert system repository by the rule that there were mapping relations between solutions and risk factors. Secondly, the neural network was trained to obtain the knowledge in the form of weight. When using, we got the response solution for the risk by reasoning and matching the output of the neural network with the knowledge in repository. It gives attention to the coupling of all risk factors to avoid the loss of information and also can simulate the expert thinking exactly to advance the project management ology level of aircraft assembly. This method had been replied in a certain airplane design project, the application illustrated the feasibility and validity of our method.