基于人工神经网络的齿轮箱载荷识别研究

提出了一种基于实测结构响应识别作用在齿轮箱上激励的方法 ,该方法利用人工神经网络建立响应信号与激励之间的映射模型。通过单级齿轮箱上所做的试验数据表明 ,这种利用人工神经网络识别齿轮箱载荷的方法是可行的 ,并且 ,经过训练的网络模型在齿轮箱载荷识别的过程中显示了极快的收敛速度和很高的识别精度。

Load Identification of Gearbox Based on Artificial Neural Ne tworks

This paper presents an approach to identify ex citing forces acting on the gearbox based on measured structural responses, which uses artificial neural networks to model the mapping between the response signals and the exciting forces.It is demonstrated by the experimental data on a single-stage gearbox that the approach based on the use of artificial neural networks for the identification of gearbox loads is feasible and a well-trained neural network reveals an extremely fast convergence and a relatively high accuracy in the process of load identification for a gearbox.