论文部分内容阅读
基于自适应神经模糊逻辑推理系统(ANFIS),在全球定位系统(GPS)信号阻塞时,为惯性导航系统(INS)提供位置和速度修正量以提高系统的精度和鲁棒性.首先用小波对数据信号进行降噪处理;然后设定INS的位置或速度作为ANFIS的输入参数,经训练后输出相应修正量,训练期望值为经小波多分辨率分析得到的位置误差和速度误差.实验表明,无GPS信号时定位精度比同条件下卡尔曼滤波精度提高约40%,因此该方法可为车辆提供可靠有效的导航定位服务.
Based on the adaptive neuro-fuzzy logic inference system (ANFIS), the position and velocity correction of inertial navigation system (INS) are provided to improve the accuracy and robustness of the system when the global positioning system (GPS) signal is blocked.First, Then set the position or speed of INS as the input parameter of ANFIS, and output the corresponding correction after training, the training expectation value is the position error and velocity error obtained by wavelet multiresolution analysis.The experiment shows that no GPS signal positioning accuracy than the same conditions, Kalman filter accuracy increased by about 40%, so this method can provide reliable and efficient navigation and positioning services for vehicles.