A Modeling Approach With Spatial Basis Functions Learning and Temporal Dynamic Online Modeling for Time-Varying Distributed Parameter Processes

Currently, most of existing data-driven modeling methods for distributed parameter systems (DPSs) are offline and do not take the intrinsic structure of streaming data into account. This often makes them difficult to model strongly nonlinear and time-varying DPSs. To overcome this, a novel modeling method that integrates the advantages of both manifold-learning-based spatial basis functions learning and temporal dynamic online modeling is proposed. In this method, the original spatiotemporal data are first mapped into high dimensional space using nonlinear mapping function, from which manifold learning is developed to obtain spatial basis functions. This allows the strongly nonlinear relationship on space able to be constructed due to nonlinear mapping, and maintaining the intrinsic data structure due to manifold learning. In addition, the online least squares support vector machine (LS-SVM) is developed to construct the temporal dynamics model. This may make time-varying dynamics of DPSs able to be captured. By integrating spatial basis functions and the online LS-SVM temporal model, a spatiotemporal model is constructed, which allows for the reconstruction of time-varying and nonlinear dynamics of DPSs. The catalytic rod simulation and heating experiments not only demonstrate the effectiveness of the proposed method, but also the better modeling ability as compared to several common modeling methods.

[1]  P. Christofides,et al.  Nonlinear and Robust Control of PDE Systems: Methods and Applications to Transport-Reaction Processes , 2002 .

[2]  Chenkun Qi,et al.  A Karhunen-Loève Decomposition-Based Wiener Modeling Approach for Nonlinear Distributed Parameter Processes , 2008 .

[3]  H. Deng,et al.  Improved Empirical Eigenfunctions Based Model Reduction for Nonlinear Distributed Parameter Systems , 2013 .

[4]  J. F. Forbes,et al.  Model predictive control for quasilinear hyperbolic distributed parameter systems , 2004 .

[5]  Xiaogang Wang,et al.  Neural network based boundary control of a vibrating string system with input deadzone , 2018, Neurocomputing.

[6]  Hao Zhang,et al.  Numerical Methods of Karhunen–Loève Expansion for Spatial Data , 2015 .

[7]  Zhen Liu,et al.  A Spatiotemporal Estimation Method for Temperature Distribution in Lithium-Ion Batteries , 2014, IEEE Transactions on Industrial Informatics.

[8]  Chang Liu,et al.  Online Spatiotemporal Extreme Learning Machine for Complex Time-Varying Distributed Parameter Systems , 2017, IEEE Transactions on Industrial Informatics.

[9]  Changyin Sun,et al.  Vibration Control of an Industrial Moving Strip in the Presence of Input Deadzone , 2017, IEEE Transactions on Industrial Electronics.

[10]  Shaoyuan Li,et al.  Embedded Interval Type-2 T-S Fuzzy Time/Space Separation Modeling Approach for Nonlinear Distributed Parameter System , 2011 .

[11]  Huai-Ning Wu,et al.  Exponential Pointwise Stabilization of Semilinear Parabolic Distributed Parameter Systems via the Takagi–Sugeno Fuzzy PDE Model , 2018, IEEE Transactions on Fuzzy Systems.

[12]  Ning Wang,et al.  Control design for a vibrating flexible marine riser system , 2017, J. Frankl. Inst..

[13]  Dong Liang,et al.  A facial expression recognition system based on supervised locally linear embedding , 2005, Pattern Recognit. Lett..

[14]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[15]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[16]  Chenkun Qi,et al.  A LS-SVM modeling approach for nonlinear distributed parameter processes , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[17]  L. Sirovich.  TURBULENCE AND THE DYNAMICS OF COHERENT STRUCTURES PART I : COHERENT STRUCTURES , 2016 .

[18]  Stephen A. Billings,et al.  Direct parameter identification of distributed parameter systems , 2000, Int. J. Syst. Sci..

[19]  Minghui Huang,et al.  A Novel Spatiotemporal LS-SVM Method for Complex Distributed Parameter Systems With Applications to Curing Thermal Process , 2016, IEEE Transactions on Industrial Informatics.

[20]  Han-Xiong Li,et al.  Local-Properties-Embedding-Based Nonlinear Spatiotemporal Modeling for Lithium-Ion Battery Thermal Process , 2018, IEEE Transactions on Industrial Electronics.

[21]  Jun Shi,et al.  Adaptive neural network control of a flexible string system with non-symmetric dead-zone and output constraint , 2017, Neurocomputing.

[22]  Chang Liu,et al.  Online Probabilistic Extreme Learning Machine for Distribution Modeling of Complex Batch Forging Processes , 2015, IEEE Transactions on Industrial Informatics.

[23]  Minghui Huang,et al.  Robust Spatiotemporal LS-SVM Modeling for Nonlinear Distributed Parameter System With Disturbance , 2017, IEEE Transactions on Industrial Electronics.

[24]  Omar Aguilar-Leal,et al.  Distributed parameter system identification using finite element differential neural networks , 2016, Appl. Soft Comput..

[25]  Minghui Huang,et al.  Online Spatiotemporal Least-Squares Support Vector Machine Modeling Approach for Time-Varying Distributed Parameter Processes , 2017 .

[26]  K. Hoo,et al.  Low-Order Model Identification of Distributed Parameter Systems by a Combination of Singular Value Decomposition and the Karhunen−Loève Expansion , 2002 .

[27]  Ge Zhaoqiang.  Stability of the time varying singular distributed parameter systems in Hilbert spaces , 2015, 2015 34th Chinese Control Conference (CCC).

[28]  L. Sirovich.  Turbulence and the dynamics of coherent structures. I. Coherent structures , 1987 .

[29]  Dan Givoli,et al.  Towards automating the finite element method: a test-bed for soft computing , 2003, Appl. Soft Comput..

[30]  H. Park,et al.  The use of the Karhunen-Loève decomposition for the modeling of distributed parameter systems , 1996 .

[31]  Yao Yu,et al.  Mixed H2/H∞ fuzzy proportional-spatial integral control design for a class of nonlinear distributed parameter systems , 2017, Fuzzy Sets Syst..

[32]  Sandip Mazumder,et al.  The Finite Difference Method , 2016 .

[33]  Han-Xiong Li,et al.  A Membership-Function-Dependent Approach to Design Fuzzy Pointwise State Feedback Controller for Nonlinear Parabolic Distributed Parameter Systems With Spatially Discrete Actuators , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[34]  Chenkun Qi,et al.  Modeling of distributed parameter systems for applications—A synthesized review from time–space separation , 2010 .

[35]  Stephen A. Billings,et al.  Identification of finite dimensional models of infinite dimensional dynamical systems , 2002, Autom..

[36]  Yinlai Jiang,et al.  Knowledge Acquisition Method Based on Singular Value Decomposition for Human Motion Analysis , 2014, IEEE Transactions on Knowledge and Data Engineering.

[37]  Kaixiang Peng,et al.  Data-Driven Quality Monitoring Techniques for Distributed Parameter Systems With Application to Hot-Rolled Strip Laminar Cooling Process , 2018, IEEE Access.

[38]  C. Canuto.  Spectral methods in fluid dynamics , 1991 .

[39]  A. R. Mitchell,et al.  The Finite Difference Method in Partial Differential Equations , 1980 .

[40]  Han-Xiong Li,et al.  Evolutionary Design of Spatio–Temporal Learning Model for Thermal Distribution in Lithium-Ion Batteries , 2019, IEEE Transactions on Industrial Informatics.

[41]  Shaoyuan Li,et al.  A fuzzy-based spatio-temporal multi-modeling for nonlinear distributed parameter processes , 2014, Appl. Soft Comput..

[42]  Shuzhi Sam Ge,et al.  Hand Gesture Recognition and Tracking based on Distributed Locally Linear Embedding , 2006 .

[43]  Guanrong Chen,et al.  Spectral-approximation-based intelligent modeling for distributed thermal processes , 2005, IEEE Transactions on Control Systems Technology.