Data-driven discovery of the heat equation in an induction machine via sparse regression

Discovery of natural laws through input-output data analysis has been of considerable interest during the past decade. Various approach among which the increasingly growing body of sparsity-based algorithms have been recently proposed for the purpose of free-form system identification. There has however been limited discussion on the performance of these approaches when applied on experimental datasets. The aim of this paper is to study the capability of this technique for identifying the heat equation as the natural law of heat distribution from experimental data, obtained using a Totally-Enclosed-Fan-Cooled (TEFC) induction machine, with and without active cooling. The results confirm the usefulness of the algorithm as a method to identify the underlying natural law in a physical system in the form of a Partial Differential Equation (PDE).

[1]  Steven L Brunton,et al.  Sparse identification of nonlinear dynamics for rapid model recovery. , 2018, Chaos.

[2]  Noah Simon,et al.  A Sparse-Group Lasso , 2013 .

[3]  Robert E. Wilson,et al.  Fundamentals of momentum, heat, and mass transfer , 1969 .

[4]  Rafal Wrobel,et al.  Estimation of Equivalent Thermal Parameters of Impregnated Electrical Windings , 2013, IEEE Transactions on Industry Applications.

[5]  Steven L. Brunton,et al.  Data-driven discovery of partial differential equations , 2016, Science Advances.

[6]  R. Tibshirani,et al.  A note on the group lasso and a sparse group lasso , 2010, 1001.0736.

[7]  Hod Lipson,et al.  Distilling Free-Form Natural Laws from Experimental Data , 2009, Science.

[8]  Victor Solo,et al.  Identification of a noisy stochastic heat equation with the EM algorithm , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[9]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[10]  Steven L. Brunton,et al.  Data-Driven Identification of Parametric Partial Differential Equations , 2018, SIAM J. Appl. Dyn. Syst..

[11]  M. Yuan,et al.  Model selection and estimation in regression with grouped variables , 2006 .

[12]  H. Schaeffer,et al.  Learning partial differential equations via data discovery and sparse optimization , 2017, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[13]  S. Brunton,et al.  Discovering governing equations from data by sparse identification of nonlinear dynamical systems , 2015, Proceedings of the National Academy of Sciences.

[14]  Jun Zou,et al.  A new approach to convergence rate analysis of Tikhonov regularization for parameter identification in heat conduction , 2000 .

[15]  Joshua M. Pearce,et al.  Open-Source Automated Mapping Four-Point Probe , 2017, Materials.

[16]  E Kaiser,et al.  Sparse identification of nonlinear dynamics for model predictive control in the low-data limit , 2017, Proceedings of the Royal Society A.