Deng Zhongmin, Zhang Xinjie, Zhao Yanlin
School of Astronautics, Beihang University, Beijing 100191, China.
Sensors (Basel). 2020 Oct 1;20(19):5615. doi: 10.3390/s20195615.
Finite element model updating precision depends heavily on sufficient vibration feature extraction. However, adequate amount of sample collection is generally time-consuming in frequency response (FR) model updating. Accurate vibration feature extraction with insufficient data has become a significant challenge in FR model updating. To update the finite element model with a small dataset, a novel approach based on transfer learning is firstly proposed in this paper. A readily available fault diagnosis dataset is selected as ancillary knowledge to train a high-precision mapping from FR data to updating parameters. The proposed transfer learning network is constructed with two branches: source and target domain feature extractor. Considering about the cross-domain feature discrepancy, a domain adaptation method is designed by embedding the extracted features into a shared feature space to train a reliable model updating framework. The proposed method is verified by a simulated satellite example. The comparison results manifest that sample amount dependency has prominently lessened this method and the updated model outperforms the method without transfer learning in accuracy with the small dataset. Furthermore, the updated model is validated through dynamic response out of the training set.
有限元模型更新精度在很大程度上依赖于充分的振动特征提取。然而，在频率响应（FR）模型更新中，通常足够数量的样本采集很耗时。在数据不足的情况下进行准确的振动特征提取已成为FR模型更新中的一项重大挑战。为了用小数据集更新有限元模型，本文首先提出了一种基于迁移学习的新方法。选择一个现成的故障诊断数据集作为辅助知识，以训练从FR数据到更新参数的高精度映射。所提出的迁移学习网络由两个分支构建：源域和目标域特征提取器。考虑到跨域特征差异，通过将提取的特征嵌入到共享特征空间中来设计一种域适应方法，以训练可靠的模型更新框架。通过一个模拟卫星实例验证了所提出的方法。比较结果表明，该方法显著降低了对样本数量的依赖，并且在小数据集的情况下，更新后的模型在精度上优于无迁移学习的方法。此外，通过训练集之外的动态响应验证了更新后的模型。
