平稳随机载荷的信号特征提取与深度神经网络识别

Feature extraction and identification of stationary random dynamic load using deep neural network

针对线性时不变结构的平稳随机载荷识别问题,从结构的动力学响应求解原理出发,利用小波变换对于信号特征的提取能力与长短期记忆神经网络(LSTM)对于序列问题的强大建模与映射能力,提出了一种针对平稳随机载荷的特征信号识别方法,通过对作用于三自由度振动系统数值模型上的平稳随机动载荷识别,证明了方法的可行性。对一个受2点平稳随机载荷作用的加筋壁板结构模型进行动载荷识别实验,结果表明,用提出的方法识别的动载荷均方根相对误差均小于5%,该动载荷识别方法具有良好的识别能力。

A feature signal identification method for stationary random dynamic load is proposed based on the dynamic principle of structures.using Wavelet transform is used to extract the time-frequency characteristics of signals,and Long-Short Term Memory(LSTM)is employed to model and map sequence problems.The feasibility of the method is proved byidentification of stationary random dynamic loads acting on a three-degree-of-freedom vibration system.The dynamic load identification experiment is carried out on a stiffened panel structure model under two-point stationary random loads.The results show that the root mean square error of dynamic load identified by the proposed method is less than 5%,and the method has good identification ability.