基于数据合成的飞行器结构损伤状态快速识别方法

In response to the complexity of the identification process and the low accuracy of identification in the current health monitoring process of aircraft structures, a rapid identification method for aircraft structural damage patterns based on data synthesis is proposed. A digital twin structure damage rapid identification model construction process is established to construct a digital model of aircraft structure. Based on the idea of data synthesis, a credibility evaluation method for sensor data is proposed, and an interpretable generative-discriminative model is established to solve the problem of low learning accuracy due to insufficient sample data. The method of fuzzy classification boundary is introduced, and the discriminative model is used to determine the fuzzy area to improve the stability of neural network identification. Finally, the proposed identification method is verified with a certain drone as an example. The results show that this method can efficiently build a structural damage pattern database and improve the generalization ability and stability of identification, with an identification accuracy rate of over 99% for damage patterns.