A new fuzzy neural network architecture for multisensor data fusion in non-destructive testing

NDT data fusion is a fast-growing signal processing technique. It combines information from multi-sources, reducing signal uncertainty and improving the overall performance of the testing. Traditional NDT data fusion model mostly bases on the statistic theory. It has some shortcomings. For Example, it must have prior knowledge and the areas it is used are limited. Data fusion based on fuzzy neural network is a relative new topic. Its application in NDT is a new area. This paper gives a new fuzzy neural network model adapted to NDT multisensor data fusion. The simulation result illustrates that this model solves the problem of the traditional model and can be used in many other areas.