Research On Kowledge Acquisition Method Based On .NET And Artificial Neural Network

With the development of the science of the technology, every walk of life has been affected by the development of the artificial intelligence. The expert system as the important offshort of the expert system, it has been one of the important emphases in growing of the science. The paper begins with the development of the system, analyzing the main points of the expert system and doing some embedded study for the method for the knowledge acquisition.The network adapts to deal with the mode with some deformily result or some error compomention. It can take order with the obscurity, incertitude and un-integrity information orexisting antinory, or fake or some other complex condition. In the paper, the assume of perfecting knowledge acquisition with the points of network have been brought forward. The main reason about the network applying in expert system is that it can solve the classification. The self-study of the network make the most difficult points the knowledge acquisition becoming the adjusting of the frame of the net, and the knowledge memorizing and distilling becoming more easy. In the paper, the virtue of the network used in knowledge acquisition has been analysesed. Simulation for the BP network with Matlab and the results used to the model of kind selection in wheat expert system. The main points are:After studying the development and the direction of expert system, definitude the virtue and the disadvantage of the system. Some methods of technology for the knowledge acquisition been advanced.In order to improve the method of kind selection model in wheat expert system, choosing the network ,trying some kinds of network: Hopfield net, self-organization net, BP network and ect.Analysising the character of the network ,after making many experiments ,finally decided to use the BP network for the knowledge acquisition.Lucubrating the characters of the BP network. Making many improving based on the BP network, and getting over the disadvantages. Based on the methods, the Visual Studio.net 2003 is used for the software system of kind selection model in wheat expert system.