Data-Driven Linear Parameter-Varying Model Identification Using Transfer Learning
Data-Driven Linear Parameter-Varying Model Identification Using Transfer Learning
复制标题
DOI：
10.1109/lcsys.2020.3041407
复制
发表时间：
2021-11
影响因子：
3
通讯作者：
Yajie Bao;Javad Mohammadpour Velni
中科院分区：
文献类型：
--
作者：
Yajie Bao;Javad Mohammadpour Velni
这封信提出了迁移学习方法，以解决当训练集和测试集的分布不同时，使用内核化机器学习进行状态空间线性变参数（LPV-SS）模型识别/学习的挑战。在估计状态空间模型中的状态之前，首先利用核均值匹配对训练集中的数据进行重采样，以校正样本偏差。此外，采用转移分量分析，以找到一个状态空间的基础转换，使转换后的状态遵循类似的分布。通过对一个理想的连续搅拌釜式反应器（CSTR）模型的测试，验证了所提出的方法。仿真结果表明，所提出的学习方法可以提高模型辨识的准确性，减少超参数调整的工作量。
This letter proposes transfer learning methods to address a challenge in state-space linear parameter-varying (LPV-SS) model identification/learning using kernelized machine learning, when the distributions of the training and testing sets are different. Kernel mean matching is first employed to correct sample bias by resampling the data in the training set before the states in state-space model are estimated. Moreover, transfer component analysis is adopted to find a state-space basis transformation such that the transformed states follow similar distributions. The proposed methods are validated by testing on an ideal continuous stirred tank reactor (CSTR) model. Simulation results show that the proposed learning methods can enhance the accuracy of model identification and reduce the efforts involved in hyperparameters tuning.