To solve the problems of nonlinear and uncertain fusion systems, an adaptive fusion algorithm based on wavelet neural networks(WNNs) for multisensor measurement was proposed. The fusion system consisted of extended Kalman filters(EKFs), WNNs, knowledge base(KB) and track-to-track fusion algorithms. Based on the distributed fusion method, sensor precision values, sensor states and the local estimation errors were transferred from sensors to WNNs to deduce the relevant sensor confidence degrees in the real-time process of data fusion. In order to obtain the sensor confidence degrees, contextual information theory and normalized variable method were introduced to WNNs and the experimental data were implemented to train WNNs. According to the rules about the sensor confidence degrees, KB made decisions to select suitable track-to-track fusion algorithms. Simulation results show that the algorithm can effectively adjust the system to adapt contextual changes and has strong fusion capability in resisting uncertain information.
Yuan Quan, Dong Chaoyang, Wang Qing.Adaptive fusion algorithm based on wavelet neural networks for multisensor measurement[J] JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2008,V34(11): 1331-1334
Zhang Jun, Walter G, Miao Y. Wavelet neural networks for function learning[J].IEEE Transactions on Signal Processing.1995, 43(6):1485-1497
���,��ΡΡ.���ڶ�ֱ���С������-BP������-D-S֤��������Ϣ�ں�ģ�͵�ֱ��ϵͳ������Ϸ���[J].��������,2004,28(24): 16-20 Li Donghui, Zhou Weiwei. DC system grounding fault diagnosis method based on data fusion model of MRNN-BPN-DS[J]. Power System Technology, 2004, 28(24): 16-20(in Chinese)
��Ծ��,�³���,����Ȫ,��.������Ϣ�ںϵļ���С��������������[J].������ѧѧ��(��Ȼ��ѧ��),2002,23(8): 802-805 Luo Yuegang, Chen Changzheng, Zeng Haiquan, et al. Integrated wavelet neural networks in fault diagnosis based on information fusion[J]. Journal of Northeastern University(Natural Science), 2002, 23(8): 802-805(in Chinese)
Francois Caron, Emmanuel Duflos, Denis Pomorski,et al. GPS/IMU data fusion using multisensor Kalman filtering: introduction of contextual aspects[J].Information Fusion.2006, 7(2):221-230
Bar-Shalom Y, Campo L. The effect of the common process noise on the two-sensor fused-track covariance[J].IEEE Transactions on Aerospace Electronic Systems.1986, 22(11):803-805
κ��,����ƽ,������,��.���������������Ӧ�����Կ��Ƽ������о�[J].�������պ����ѧѧ��,2004,30(3): 217-221 Wei Dong, Ma Ruiping, Zhang Minglian, et al. Artificial-neural-network-based nonlinear adaptive control and simulation[J].Journal of Beijing University of Aeronautics and Astronautics, 2004,30(3): 217-221(in Chinese)