基于光纤智能夹层和模糊RBF神经网络的飞行器载荷识别

Aircraft Load Identification Based on Smart Layer of Fiber and Fuzzy RBF Neural Network

为了更好地保障航空飞行器的安全,提高飞行器的可靠性,提出了一种通过性能参数稳定的光纤智能夹层采集数据,并且结合模糊RBF神经网络对机翼盒段载荷进行识别实验的方法。该方法融合了模糊理论和神经网络各自的优点,通过改进的模糊C均值聚类(FCM)聚类算法删除冗余的规则以进行规则的优化,能自适应地从学习样本数据中提取相应信息,实时地进行载荷辨识。从仿真结果可以看出:该网络模型具有学习时间较短、学习速率较快和精度较高等优点。

In order to ensure the security of the aircraft and improve the reliability of the aircraft, a new method by combining fuzzy theories with neural network is used to identify the loads of the wing-box. Data are provided by the fiber smart layer with a stable performance. An improved fuzzy C-means （FCM） clustering algorithm is used to delete the redundant rule for the optimization. The fuzzy RBF neural network can obtain self-adaptive information from samples to be learned, thus the load can be real-time identified. The simulation indicates that the network model has the advantages of shortening training time, enhancing learning rate, and improving precision.