论文部分内容阅读
为确保背景场中最优适配航线设计的正确性以及水下地形匹配导航的可靠性,提出了一种基于BP神经网络的背景场适配/误配区自动识别和划分方法,该方法通过分析地形背景场特征参量显著性和主成分、构建BP神经网络、建立输入地形特征参量与匹配性能的映射关系,最终实现了地形背景场误配/适配区的自动识别和划分。试验验证了本方法的有效性。
In order to ensure the correctness of the design of the optimal matching route in the background field and the reliability of underwater terrain matching navigation, a method of automatic recognition and classification of the background field adaptation / mismatch area based on BP neural network is proposed. Analyze the significance and main components of the terrain background parameters and construct the BP neural network. Establish the mapping relationship between the input terrain feature parameters and the matching performance, and finally realize the automatic identification and division of the mismatch / adaptation area of the terrain background. The experiment verifies the validity of this method.