模糊超球神经网络辅助组合导航融合算法

研究了应用线性网络对组合导航多传感器信息进行融合的方法,在此基础上提出了一种神经网络组合导航容错算法。该算法将局部滤波器状态估计的模糊超球隶属函数引入网络,在线调整融合网络权值,实现全局估计的自适应性和容错性。仿真表明,该融合算法有较高的估计精度,在传感器故障时,能够及时检测出并在融合网络中予以隔离,不致影响全局估计。

A Integrated Navigation Fusion Algorithm Assisted by Fuzzy Hypersphere Neural Network

In this paper,a method of multi-sensor data fusion using neural network in integrated navigation system is given,and then a fault-tolerant algorithm is proposed.In this algorithm,the fuzzy hypersphere membership functions of the state estimation of local filters are combined with the weights of the fusion network,and the weights of the network can be adjusted online,so that the whole estimation is adaptive and fault-tolerant.Simulation shows that the algorithm has good accuracy,the sensor faults can be detected,and as a result of the isolation of local filter of the fault sensor the sensor faults would not pollute the global estimation.