Operable adaptive sparse identification of systems: Application to chemical processes
- 15 July 2020
- journal article
- research article
- Published by Wiley in AIChE Journal
- Vol. 66 (11) , e16980
Abstract
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.Keywords
Funding Information
- Division of Chemical, Bioengineering, Environmental and Transport Systems (CBET‐1804407)
- U.S. Department of Energy (DE‐EE0007888‐10‐8)
- Artie McFerrin Department of Chemical Engineering, Texas A and M University
- Energy Institute, Texas A and M University
This publication has 54 references indexed in Scilit:
- How To NOT Make the Extended Kalman Filter FailIndustrial & Engineering Chemistry Research, 2013
- State-of-charge estimation of lead-acid batteries using an adaptive extended Kalman filterJournal of Power Sources, 2009
- Equation-free modelling of evolving diseases: coarse-grained computations with individual-based modelsProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2004
- The unscented filter as an alternative to the EKF for nonlinear state estimation: a simulation case studyComputers & Chemical Engineering, 2004
- Neural network architecture for process control based on the RTRL algorithmAIChE Journal, 1996
- Nonlinear model-based control using second-order Volterra modelsAutomatica, 1995
- Extended Kalman Filter Based Nonlinear Model Predictive ControlIndustrial & Engineering Chemistry Research, 1994
- N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systemsAutomatica, 1994
- First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's MethodNeural Computation, 1992
- Conjugate gradient algorithm for efficient training of artificial neural networksIEE Proceedings G Circuits, Devices and Systems, 1992