Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Physics-informed machine learning modeling for predictive control using noisy data

Journal Article · · Chemical Engineering Research and Design
 [1];  [2];  [3];  [2]
  1. University of California, Los Angeles, CA (United States); Kuwait University (Kuwait)
  2. University of California, Los Angeles, CA (United States)
  3. National University of Singapore (Singapore)
+ Show Author Affiliations
Due to the occurrence of over-fitting at the learning phase, the modeling of chemical processes via artificial neural networks (ANN) by using corrupted data (i.e., noisy data) is an ongoing challenge. Therefore, this work investigates the effect of both Gaussian and non-Gaussian noise on the performance of process-structure based recurrent neural networks (RNN) models, which take the form of partially-connected RNN models in this work, that are used to approximate a class of multi-input-multi-outputs nonlinear systems. Furthermore, two different techniques, specifically Monte Carlo dropout and co-teaching, are utilized in the development of partially-connected RNN models. Here, these two techniques are employed to reduce the over-fitting in ANNs when noisy data is used in the training process and, hence, to improve the open-loop accuracy as well as the closed-loop performance under a Lyapunov-based model predictive controller (MPC). Aspen Plus Dynamics, a well-known high-fidelity process simulator, is used to simulate a large-scale chemical process application in order to demonstrate the anticipated improvements in both open-loop approximation and closed-loop controller performance in the presence of Gaussian and non-Gaussian noise in the data set using physics-informed RNNs.
Research Organization:
University of California, Los Angeles, CA (United States)
Sponsoring Organization:
USDOE
OSTI ID:
2424561
Journal Information:
Chemical Engineering Research and Design, Journal Name: Chemical Engineering Research and Design Journal Issue: C Vol. 186; ISSN 0263-8762
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (22)

Nonlinear stochastic modeling to improve state estimation in process monitoring and control journal May 2010
Machine learning‐based distributed model predictive control of nonlinear processes journal September 2020
Machine learning modeling and predictive control of nonlinear processes using noisy data journal January 2021
Statistical machine‐learning– based predictive control of uncertain nonlinear processes journal March 2022
Modeling chemical processes using prior knowledge and neural networks journal August 1994
Intelligent systems in process engineering: a review journal June 1996
A universal formula for stabilization with bounded controls journal June 1991
Approximate model predictive building control via machine learning journal May 2018
The validity domain of hybrid models and its application in process optimization journal November 2007
Machine-learning-based state estimation and predictive control of nonlinear processes journal March 2021
Process structure-based recurrent neural network modeling for predictive control: A comparative study journal March 2022
Deep convolutional neural network model based chemical process fault diagnosis journal July 2018
Feature engineering in big data analytics for IoT-enabled smart manufacturing – Comparison between deep learning and statistical learning journal October 2020
Machine-learning-based simulation and fed-batch control of cyanobacterial-phycocyanin production in Plectonema by artificial neural network and deep reinforcement learning journal November 2020
Handling noisy data in sparse model identification using subsampling and co-teaching journal January 2022
Nonlinear Bayesian state estimation: A review of recent developments journal October 2012
Modelling and control of chaotic processes through their Bifurcation Diagrams generated with the help of Recurrent Neural Network models: Part 1—simulation studies journal January 2006
A Wiener-type recurrent neural network and its control strategy for nonlinear dynamic applications journal June 2009
Process structure-based recurrent neural network modeling for model predictive control of nonlinear processes journal May 2020
110th Anniversary: Ensemble-Based Machine Learning for Industrial Fermenter Classification and Foaming Control journal August 2019
Uncertainty-aware prediction of chemical reaction yields with graph neural networks journal January 2022
Real-Time Optimization and Control of Nonlinear Processes Using Machine Learning journal September 2019

Similar Records

B-PINNs: Bayesian Physics-informal Neural Networks for Forward and Inverse PDE Problems with Noisy Data
Journal Article · Thu Jan 14 23:00:00 EST 2021 · Journal of Computational Physics · OSTI ID:1763962
B-PINNs: Bayesian physics-informed neural networks for forward and inverse PDE problems with noisy data
Journal Article · Wed Oct 14 20:00:00 EDT 2020 · Journal of Computational Physics · OSTI ID:2282008
Quantification of neural networks uncertainties with applications to SAFARI-1 axial neutron flux profiles
Conference · Fri Jul 01 00:00:00 EDT 2022 · OSTI ID:23203868

Related Subjects

97 MATHEMATICS AND COMPUTING
Aspen Plus Dynamics
Engineering
Machine Learning
Model predictive control
Nonlinear processes
Process control
Recurrent neural networks