Operable adaptive sparse identification of systems: Application to chemical processes

被引:69
作者
Bhadriraju, Bhavana [1 ]
Bangi, Mohammed Saad Faizan [1 ]
Narasingam, Abhinav [1 ]
Kwon, Joseph Sang-Il [1 ]
机构
[1] Texas A&M Univ, Artie McFerrin Dept Chem Engn, College Stn, TX 77840 USA
基金
美国国家科学基金会;
关键词
data-driven system identification; deep neural networks; model predictive control; online model identification; sparse regression; KALMAN FILTER; MODEL IDENTIFICATION; NEURAL-NETWORKS; REGRESSION; ALGORITHM; DECOMPOSITION; SIMULATION;
D O I
10.1002/aic.16980
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Over the past few decades, several data-driven methods have been developed for identifying a model that accurately describes the process dynamics. Lately, sparse identification of nonlinear dynamics (SINDy) has delivered promising results for various nonlinear processes. However, at any instance of plant-model mismatch or process upset, retraining the model using SINDy is computationally expensive and cannot guarantee to catch up with rapidly changing dynamics. Hence, we propose operable adaptive sparse identification of systems (OASIS) framework that extends the capabilities of SINDy for accurate, automatic, and adaptive approximation of process models. First, we use SINDy to obtain multiple models from historical data for varying input settings. Next, using these models and their training data, we build a deep neural network that is incorporated in a model predictive control framework for closed-loop operation. We demonstrate the OASIS methodology on the identification and control of a continuous stirred tank reactor.
引用
收藏
页数:15
相关论文
共 67 条
[1]   Machine learning for neuroirnaging with scikit-learn [J].
Abraham, Alexandre ;
Pedregosa, Fabian ;
Eickenberg, Michael ;
Gervais, Philippe ;
Mueller, Andreas ;
Kossaifi, Jean ;
Gramfort, Alexandre ;
Thirion, Bertrand ;
Varoquaux, Gael .
FRONTIERS IN NEUROINFORMATICS, 2014, 8
[2]   Error-triggered on-line model identification for model-based feedback control [J].
Alanqar, Anas ;
Durand, Helen ;
Christofides, Panagiotis D. .
AICHE JOURNAL, 2017, 63 (03) :949-966
[3]   Deep hybrid modeling of chemical process: Application to hydraulic fracturing [J].
Bangi, Mohammed Saad Faizan ;
Kwon, Joseph Sang-Il .
COMPUTERS & CHEMICAL ENGINEERING, 2020, 134
[4]   1ST-ORDER AND 2ND-ORDER METHODS FOR LEARNING - BETWEEN STEEPEST DESCENT AND NEWTON METHOD [J].
BATTITI, R .
NEURAL COMPUTATION, 1992, 4 (02) :141-166
[5]  
Bergstra J, 2012, J MACH LEARN RES, V13, P281
[6]   Machine learning-based adaptive model identification of systems: Application to a chemical process [J].
Bhadriraju, Bhavana ;
Narasingam, Abhinav ;
Kwon, Joseph Sang-Il .
CHEMICAL ENGINEERING RESEARCH & DESIGN, 2019, 152 :372-383
[7]   Surrogate-Model Accelerated Random Search algorithm for global optimization with applications to inverse material identification [J].
Brigham, John C. ;
Aquino, Wilkins .
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2007, 196 (45-48) :4561-4576
[8]   p-Curve and p-Hacking in Observational Research [J].
Bruns, Stephan B. ;
Ioannidis, John P. A. .
PLOS ONE, 2016, 11 (02)
[9]   Discovering governing equations from data by sparse identification of nonlinear dynamical systems [J].
Brunton, Steven L. ;
Proctor, Joshua L. ;
Kutz, J. Nathan .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2016, 113 (15) :3932-3937
[10]   Discovery of Nonlinear Multiscale Systems: Sampling Strategies and Embeddings [J].
Champion, Kathleen P. ;
Brunton, Steven L. ;
Kutz, J. Nathan .
SIAM JOURNAL ON APPLIED DYNAMICAL SYSTEMS, 2019, 18 (01) :312-333