Enabling reduced-order data-driven nonlinear identification and modeling through naïve elastic net regularization |
| |
Institution: | 1. State Key Laboratory of Chemical Engineering, Collaborative Innovation Center of Chemical science and Engineering, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300072, PR China;2. Laboratory of Reactions and Process Engineering, University of Lorraine, CNRS, 1, rue Grandville, BP 20451, 54001 Nancy Cedex, France |
| |
Abstract: | This work discusses an improved method of reduced-order modeling for existing data-driven nonlinear identification techniques through the incorporation of naïve elastic net regularization. The data-driven methods considered for this study operate using basis functions to represent the observed nonlinearity. Elastic net regularization is used to minimize the number of non-zero coefficients, thus modifying the basis functions and providing a compact representation. The ability of the naïve elastic net to provide reduced-order nonlinear models that can both accurately fit various data sets and computationally simulate new responses is illustrated through studies considering both synthetic data and experimental data. In both cases, the results obtained with the naïve elastic net are shown to match or outperform those from other traditional methods. |
| |
Keywords: | Elastic net Lasso regression Nonlinear identification Data-driven |
本文献已被 ScienceDirect 等数据库收录! |
|