Machine learning-based ethylene concentration estimation, real-time optimization and feedback control of an experimental electrochemical reactor
Abstract
With the increase in electricity supply from clean energy sources, electrochemical reduction of carbon dioxide (CO2) has received increasing attention as an alternative source of carbon-based fuels. As CO2 reduction is becoming a stronger alternative for the clean production of chemicals, the need to model, optimize and control the electrochemical reduction of the CO2 process becomes inevitable. However, on one hand, a first-principles model to represent the electrochemical CO2 reduction has not been fully developed yet because of the complexity of its reaction mechanism, which makes it challenging to define a precise state-space model for the control system. On the other hand, the unavailability of efficient concentration measurement sensors continues to challenge our ability to develop feedback control systems. Gas chromatography (GC) is the most common equipment for monitoring the gas product composition, but it requires a period of time to analyze the sample, which means that GC can provide only delayed measurements during the operation. Moreover, the electrochemical CO2 reduction process is catalyzed by a fast-deactivating copper catalyst and undergoes a selectivity shift from the product-of-interest at the later stages of experiments, which can pose a challenge for conventional control methods. To this end, machine learning (ML) techniques providemore »
- Authors:
-
- University of California, Los Angeles, CA (United States)
- Publication Date:
- Research Org.:
- Univ. of California, Los Angeles, CA (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE)
- OSTI Identifier:
- 1976960
- Alternate Identifier(s):
- OSTI ID: 1961079
- Grant/Contract Number:
- EE0007613
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Chemical Engineering Research and Design
- Additional Journal Information:
- Journal Volume: 185; Journal Issue: C; Journal ID: ISSN 0263-8762
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 42 ENGINEERING; electrochemical reactor; CO2 reduction; support vector regression; data-driven modeling; gas chromatography; real-time optimization; feedback control
Citation Formats
Çıtmacı, Berkay, Luo, Junwei, Jang, Joon Baek, Canuso, Vito, Richard, Derek, Ren, Yi Ming, Morales-Guio, Carlos G., and Christofides, Panagiotis D. Machine learning-based ethylene concentration estimation, real-time optimization and feedback control of an experimental electrochemical reactor. United States: N. p., 2022.
Web. doi:10.1016/j.cherd.2022.06.044.
Çıtmacı, Berkay, Luo, Junwei, Jang, Joon Baek, Canuso, Vito, Richard, Derek, Ren, Yi Ming, Morales-Guio, Carlos G., & Christofides, Panagiotis D. Machine learning-based ethylene concentration estimation, real-time optimization and feedback control of an experimental electrochemical reactor. United States. https://doi.org/10.1016/j.cherd.2022.06.044
Çıtmacı, Berkay, Luo, Junwei, Jang, Joon Baek, Canuso, Vito, Richard, Derek, Ren, Yi Ming, Morales-Guio, Carlos G., and Christofides, Panagiotis D. Fri .
"Machine learning-based ethylene concentration estimation, real-time optimization and feedback control of an experimental electrochemical reactor". United States. https://doi.org/10.1016/j.cherd.2022.06.044. https://www.osti.gov/servlets/purl/1976960.
@article{osti_1976960,
title = {Machine learning-based ethylene concentration estimation, real-time optimization and feedback control of an experimental electrochemical reactor},
author = {Çıtmacı, Berkay and Luo, Junwei and Jang, Joon Baek and Canuso, Vito and Richard, Derek and Ren, Yi Ming and Morales-Guio, Carlos G. and Christofides, Panagiotis D.},
abstractNote = {With the increase in electricity supply from clean energy sources, electrochemical reduction of carbon dioxide (CO2) has received increasing attention as an alternative source of carbon-based fuels. As CO2 reduction is becoming a stronger alternative for the clean production of chemicals, the need to model, optimize and control the electrochemical reduction of the CO2 process becomes inevitable. However, on one hand, a first-principles model to represent the electrochemical CO2 reduction has not been fully developed yet because of the complexity of its reaction mechanism, which makes it challenging to define a precise state-space model for the control system. On the other hand, the unavailability of efficient concentration measurement sensors continues to challenge our ability to develop feedback control systems. Gas chromatography (GC) is the most common equipment for monitoring the gas product composition, but it requires a period of time to analyze the sample, which means that GC can provide only delayed measurements during the operation. Moreover, the electrochemical CO2 reduction process is catalyzed by a fast-deactivating copper catalyst and undergoes a selectivity shift from the product-of-interest at the later stages of experiments, which can pose a challenge for conventional control methods. To this end, machine learning (ML) techniques provide a potential approach to overcome those difficulties due to their demonstrated ability to capture the dynamic behavior of a chemical process from data. Motivated by the above considerations, we propose a machine learning-based modeling methodology that integrates support vector regression and first-principles modeling to capture the dynamic behavior of an experimental electrochemical reactor; this model, together with limited gas chromatography measurements, is employed to predict the evolution of gas-phase ethylene concentration. The model prediction is directly used in a proportional-integral (PI) controller that manipulates the applied potential to regulate the gas-phase ethylene concentration at energy-optimal set-point values computed by a real-time process optimizer (RTO). Specifically, the RTO calculates the operation set-point by solving an optimization problem to maximize the economic benefit of the reactor. Finally, suitable compensation methods are introduced to further account for the experimental uncertainties and handle catalyst deactivation. The proposed modeling, optimization, and control approaches are the first demonstration of active control for a CO2 electrolyzer and contribute to the automation and scale-up efforts for electrified manufacturing of fuels and chemicals starting from CO2.},
doi = {10.1016/j.cherd.2022.06.044},
journal = {Chemical Engineering Research and Design},
number = C,
volume = 185,
place = {United States},
year = {Fri Jul 01 00:00:00 EDT 2022},
month = {Fri Jul 01 00:00:00 EDT 2022}
}
Works referenced in this record:
A Data-Driven Framework for the Accelerated Discovery of CO2 Reduction Electrocatalysts
journal, April 2021
- Malek, Ali; Wang, Qianpu; Baumann, Stefan
- Frontiers in Energy Research, Vol. 9
What would it take for renewably powered electrosynthesis to displace petrochemical processes?
journal, April 2019
- De Luna, Phil; Hahn, Christopher; Higgins, Drew
- Science, Vol. 364, Issue 6438
An empirical analysis of feature engineering for predictive modeling
conference, March 2016
- Heaton, Jeff
- SoutheastCon 2016
Electrochemical Reduction of CO at a Copper Electrode
journal, September 1997
- Hori, Yoshio; Takahashi, Ryutaro; Yoshinami, Yuzuru
- The Journal of Physical Chemistry B, Vol. 101, Issue 36
Self-Optimization of Continuous Flow Electrochemical Synthesis Using Fourier Transform Infrared Spectroscopy and Gas Chromatography
journal, December 2021
- Ke, Jie; Gao, Chuang; Folgueiras-Amador, Ana A.
- Applied Spectroscopy, Vol. 76, Issue 1
Pulsed Electroreduction of CO[sub 2] on Copper Electrodes
journal, January 1993
- Shiratsuchi, Ryuichi
- Journal of The Electrochemical Society, Vol. 140, Issue 12
Manipulating the Hydrocarbon Selectivity of Copper Nanoparticles in CO 2 Electroreduction by Process Conditions
journal, December 2014
- Kas, Recep; Kortlever, Ruud; Yılmaz, Hasan
- ChemElectroChem, Vol. 2, Issue 3
Surface Reconstruction of Polycrystalline Cu Electrodes in Aqueous KHCO3 Electrolyte at Potentials in the Early Stages of CO2 Reduction
journal, April 2018
- Kim, Youn-Geun; Baricuatro, Jack H.; Soriaga, Manuel P.
- Electrocatalysis, Vol. 9, Issue 4
An introduction to decision tree modeling
journal, June 2004
- Myles, Anthony J.; Feudale, Robert N.; Liu, Yang
- Journal of Chemometrics, Vol. 18, Issue 6
On the Electrochemical CO 2 Reduction at Copper Sheet Electrodes with Enhanced Long-Term Stability by Pulsed Electrolysis
journal, January 2018
- Engelbrecht, Andreas; Uhlig, Conrad; Stark, Oliver
- Journal of The Electrochemical Society, Vol. 165, Issue 15
High Selectivity for Ethylene from Carbon Dioxide Reduction over Copper Nanocube Electrocatalysts
journal, February 2015
- Roberts, F. Sloan; Kuhl, Kendra P.; Nilsson, Anders
- Angewandte Chemie, Vol. 127, Issue 17
Gradient boosting trees for auto insurance loss cost modeling and prediction
journal, February 2012
- Guelman, Leo
- Expert Systems with Applications, Vol. 39, Issue 3
The Evolution of the Polycrystalline Copper Surface, First to Cu(111) and Then to Cu(100), at a Fixed CO 2 RR Potential: A Study by Operando EC-STM
journal, December 2014
- Kim, Youn-Geun; Baricuatro, Jack Hess; Javier, Alnald
- Langmuir, Vol. 30, Issue 50
A method for PID controller tuning using nonlinear control techniques
conference, January 2004
- Mhaskar, P.; El-Farra, N. H.; Christofides, P. D.
- Proceedings of the 2004 American Control Conference
Electrochemical and Surface Studies of Carbon Dioxide Reduction to Methane and Ethylene at Copper Electrodes in Aqueous Solutions
journal, January 1989
- DeWulf, David W.
- Journal of The Electrochemical Society, Vol. 136, Issue 6, p. 1686-1691
The Bayesian Lasso
journal, June 2008
- Park, Trevor; Casella, George
- Journal of the American Statistical Association, Vol. 103, Issue 482
“Deactivation of copper electrode” in electrochemical reduction of CO2
journal, September 2005
- Hori, Y.; Konishi, H.; Futamura, T.
- Electrochimica Acta, Vol. 50, Issue 27
A Quick Review of Machine Learning Algorithms
conference, February 2019
- Ray, Susmita
- 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon)
Data-driven models of steady state and transient operations of spiral-wound RO plant
journal, May 2013
- Pascual, Xavier; Gu, Han; Bartman, Alex R.
- Desalination, Vol. 316
NOX Emission Model for Coal-Fired Boilers Using Principle Component Analysis and Support Vector Regression
journal, January 2016
- Tan, Peng; Zhang, Cheng; Xia, Ji
- Journal of Chemical Engineering of Japan, Vol. 49, Issue 2
Directing Selectivity of Electrochemical Carbon Dioxide Reduction Using Plasmonics
journal, April 2019
- Creel, Erin B.; Corson, Elizabeth R.; Eichhorn, Johanna
- ACS Energy Letters, Vol. 4, Issue 5
Scalable Gas Diffusion Electrode Fabrication for Electrochemical CO2 Reduction Using Physical Vapor Deposition Methods
journal, February 2022
- Jeng, Emily; Qi, Zhen; Kashi, Ajay R.
- ACS Applied Materials & Interfaces, Vol. 14, Issue 6
Advances and Challenges for the Electrochemical Reduction of CO 2 to CO: From Fundamentals to Industrialization
journal, May 2021
- Jin, Song; Hao, Zhimeng; Zhang, Kai
- Angewandte Chemie International Edition, Vol. 60, Issue 38
Cost Competitiveness of Electrolytic Hydrogen
journal, October 2019
- Guerra, Omar J.; Eichman, Joshua; Kurtz, Jennifer
- Joule, Vol. 3, Issue 10
Machine Learning Investigation of Supplementary Adsorbate Influence on Copper for Enhanced Electrochemical CO 2 Reduction Performance
journal, July 2021
- Wu, Donghuan; Zhang, Jiayi; Cheng, Mu-Jeng
- The Journal of Physical Chemistry C, Vol. 125, Issue 28
Progress and Perspectives of Electrochemical CO 2 Reduction on Copper in Aqueous Electrolyte
journal, April 2019
- Nitopi, Stephanie; Bertheussen, Erlend; Scott, Soren B.
- Chemical Reviews, Vol. 119, Issue 12
On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming
journal, April 2005
- Wächter, Andreas; Biegler, Lorenz T.
- Mathematical Programming, Vol. 106, Issue 1
Efficient electrochemical CO2 reduction on a unique chrysanthemum-like Cu nanoflower electrode and direct observation of carbon deposite
journal, September 2014
- Xie, Jia-Fang; Huang, Yu-Xi; Li, Wen-Wei
- Electrochimica Acta, Vol. 139
Effect on electrochemical reduction of nitrogen to ammonia under ambient conditions: Challenges and opportunities for chemical fuels
journal, October 2021
- Niu, Lijuan; An, Li; Wang, Xiayan
- Journal of Energy Chemistry, Vol. 61