结合离线知识的时变结构模态参数在线辨识

The online acquisition of modal parameters of aircraft structures is of great significance for efficient and reliable operation of the aircraft. The traditional modal parameter identification methods for time-varying structures have problems such as more false results and the poor ability to resist extreme outliers in measured data, becoming difficult to effectively apply to online processes. To solve these problems, an online identification model of time-varying structural modal parameters based on long short-term memory networks is established. For a given time-varying structures, prior information is introduced offline through the data set construction process, and the characteristics of the model are utilized to effectively improve the reliability of the online identification application. The experimental results show that compared with the traditional identification method, the proposed online identification model can effectively alleviate the problem of false results and ensure the continuity of identification results. The α stable distribution model is used to model the impulse noise, verifying the robustness of the online identification model that contains extreme outliers in measured data due to accidental factors.