钢丝绳隔振系统的神经网络杂交建模

Hybrid Modeling for Wire Cable Isolation System Based on Neural Network

提出一种基于神经网络的杂交建模方法,并对某电子设备的钢丝绳隔振系统滞后恢复力进行建模研究。利用周期载荷试验数据,通过参数识别确定系统非线性滞后恢复力的骨架模型。采用神经网络对系统恢复力中难以参数建模的特性进行学习训练,从而得到系统恢复力的神经网络杂交模型。利用得到的杂交模型对隔振系统在周期载荷和宽频随机载荷下的响应进行预测分析与比较,结果显示杂交模型具有较好的预测精度。

A hybrid modeling method based on neural network （NN） is developed and used to model the hysteretic restoring force of wire cable isolation system for a certain electronic equipment. Firstly, a framework model for the nonlinear hysteretic restoring force is identified by using the experimental data from period loading. Secondly, the remained characteristic of hysteretic restoring, which cannot be parametrically modeled in an easy way, is identified by using NN method through network training. Thus, a hybrid model for the nonlinear hysteretic restoring force can be obtained. The model is then used to predict the dynamic responses of isolation system under harmonic and broad-band random excitations, respectively. The comparative study is also carried out to validate the effectiveness and prediction accuracy of the model. The results show good prediction accuracy with the developed hybrid model.