Geomagnetic Navigation Matching Area Selection Based on PCA and GA-BP Neural Network
WANG Chen-yang;School of Automation,Nanjing University of Science and Technology;
The selection of suitable matching area of geomagnetic map is important for ensuring the positioning accuracy of geomagnetic navigation. This paper puts forward a method for the automatic recognition and classification of the suitable and unsuitable matching areas of geomagnetic background field based on Principal Component Analysis( PCA) and GA-BP neural network. To select independent characteristic parameters containing the main components,PCA is used to analyze the geomagnetic characteristic parameters. Then,the GA-BP neural network model is constructed,and the correspondence between the geomagnetic characteristic parameters and matching performance is established,so as to realize the recognition and classification of suitable and unsuitable matching areas. Simulation results show that this method can efficiently find out a more effective matching area,and improve the positioning accuracy of geomagnetic navigation.
【CateGory Index】： TN966;TP183