Dissertation
Dissertation > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Expert systems, knowledge engineering

The Research of Silicon Carbide Artificial Neural Network Expert System

Author WangRenDao
Tutor RenQingLi; ZhangZanFeng
School Xi'an University of Electronic Science and Technology
Course Electronics and Communication Engineering
Keywords Artificial Neural Network Expert System Silicon Carbide
CLC TP182
Type Master's thesis
Year 2013
Downloads 8
Quotes 0
Download Dissertation

Along with the development of computer technology and the improvement of dataprocessing algorithm, the research of artificial neural network in materials science hasalso made progress. Silicon carbide, a typical wide band gap semiconductor materials,has the advantages of high electron mobility, excellent optical and mechanica lproperties, and chemical stability. In particular, its performances of high frequency,high power, high temperature resistant, and radiation hardened, make it have a verybroad potential application in the manufacture of some special electronic devices.Therefore, silicon carbide has been the hotspot of research at home and abroad.In this dissertation, Both a silicon carbide film database and a silicon carbidenanometer material database were established using SQL SERVER2005database onthe basis of many literatures about material expert system and silicon carbide materials.The artificial neural network expert system for the silicon carbide based on knowledgeretrieval, simulation and prediction, was designed by using the BP neural networkalgorithm through changing momentum factor and learning rate. This system can add,edit and delete silicon carbide experiment data and search performances through theprogram of human-machine interaction interface. Then by using these data as sampledata and combining the basic knowledge of materials research, the BP neural networkwas built after processing these data according to certain methods. After training, thesystem can predict the performances of both silicon carbide films and silicon carbidenano materials in certain preparation technology conditions, which can providereference for the research of silicon carbide.

Related Dissertations
More Dissertations