Phased Long Short-Term Memory-Based Predictive Control of Chemical Processes With Asynchronous and Delayed Measurements
Open accessAbstract
This work develops novel machine learning modeling and predictive control techniques for nonlinear chemical systems that experience asynchronous and delayed measurements that result in missingness in both offline and online data collections. Specifically, a phased long short-term memory (PLSTM) network is used to learn the process dynamics amidst the missingness in the data measurements, during the offline training process. The generalization performance of PLSTM is theoretically studied on the basis of statistical machine learning theory to better understand the capabilities of PLSTM models. The PLSTM model is subsequently employed to forecast the evolution of states for a Lyapunov-based model predictive control (LMPC). The proposed PLSTM-based LMPC is designed to account for data loss and delays in real-time implementation, and guarantees the closed-loop stability of nonlinear systems subjected to missing real-time data, provided that there is an upper bound on the number of consecutively missing real-time data. Finally, two chemical processes including an extractive dividing wall column (EDWC) and a continuous stirred tank reactor (CSTR) are used to demonstrate the effectiveness of PLSTM modeling and predictive control methods.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Wächter, A., & Biegler, L. T. (2006) · Mathematical Programming · doi:10.1007/s10107-004-0559-y · Cited by 9,483 · see citing works
Stability of networked control systems
Zhang, W., Branicky, M. S., & Phillips, S. M. (2001) · IEEE Control Systems · doi:10.1109/37.898794 · Cited by 3,459 · see citing works
Recurrent Neural Networks for Multivariate Time Series with Missing Values
Che, Z., Purushotham, S., Cho, K., Sontag, D., & Liu, Y. (2018) · Scientific Reports · doi:10.1038/s41598-018-24271-9 · Cited by 2,370 · see citing works
A ‘universal’ construction of Artstein's theorem on nonlinear stabilization
Sontag, E. D. (1989) · Systems & Control Letters · doi:10.1016/0167-6911(89)90028-5 · Cited by 1,448 · see citing works
Foundations of Machine Learning
Mohri, M., Rostamizadeh, A., & Talwalkar, A. (2018) · doi:10.7551/mitpress/10290.001.0001 · Cited by 1,122 · see citing works
A new method for stabilization of networked control systems with random delays
Zhang, L., Shi, Y., Chen, T., et al. (2005) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2005.852550 · Cited by 857 · see citing works
Patient Subtyping via Time-Aware LSTM Networks
Baytaş, İ. M., Xiao, C., Zhang, X., Wang, F., Jain, A. K., & Zhou, J. (2017) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3097983.3097997 · Cited by 646 · see citing works
A review of irregular time series data handling with gated recurrent neural networks
Weerakody, P. B., Wong, K. W., Wang, G., & Ela, W. P. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.02.046 · Cited by 453 · see citing works
Reliability in wireless sensor networks: A survey and challenges ahead
Mahmood, M. A., Seah, W. K. G., & Welch, I. S. (2015) · Computer Networks · doi:10.1016/j.comnet.2014.12.016 · Cited by 345 · see citing works
Lyapunov-Based Model Predictive Control of Nonlinear Systems Subject to Data Losses
de la Peña, D. M., & Christofides, P. D. (2008) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2008.929401 · Cited by 307 · see citing works
Machine learning‐based predictive control of nonlinear processes. Part I: Theory
Wu, Z., Tran, A. T., Rincón, D., et al. (2019) · AIChE Journal · doi:10.1002/aic.16729 · Cited by 248 · see citing works
Self-citationSize-independent sample complexity of neural networks
Golowich, N., Rakhlin, A., & Shamir, O. (2019) · Information and Inference A Journal of the IMA · doi:10.1093/imaiai/iaz007 · Cited by 183 · see citing works
A Vector-Contraction Inequality for Rademacher Complexities
Maurer, A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46379-7_1 · Cited by 168 · see citing works
Nonlinear model validation using correlation tests
Billings, S. A., & Zhu, Q. (1994) · International Journal of Control · doi:10.1080/00207179408921513 · Cited by 165 · see citing works
Tipsuwan, Y., & Chow, M. (2004) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2004.837866 · Cited by 157 · see citing works
Critical Assessment of the Energy-Saving Potential of an Extractive Dividing-Wall Column
Wu, Y. C., Hsu, P. H.-C., & Chien, I. (2013) · Industrial & Engineering Chemistry Research · doi:10.1021/ie3035898 · Cited by 138 · see citing works
Wu, Z., Tran, A. T., Rincón, D., et al. (2019) · AIChE Journal · doi:10.1002/aic.16734 · Cited by 137 · see citing works
Self-citationNeural Network-Based Model Predictive Control: Fault Tolerance and Stability
Patan, K. (2014) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2014.2354981 · Cited by 104 · see citing works
Learning model predictive control with long short‐term memory networks
Terzi, E., Bonassi, F., Farina, M., & Scattolini, R. (2021) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.5519 · Cited by 81 · see citing works
A two-tier architecture for networked process control
Liu, J., de la Peña, D. M., Ohran, B. J., et al. (2008) · Chemical Engineering Science · doi:10.1016/j.ces.2008.07.030 · Cited by 65 · see citing works
Overview of Networked Control Systems
Gupta, R. A., & Chow, M. (2008) · Springer eBooks · doi:10.1007/978-1-84800-215-9_1 · Cited by 58 · see citing works
Statistical Machine Learning in Model Predictive Control of Nonlinear Processes
Wu, Z., Rincón, D., Gu, Q., & Christofides, P. D. (2021) · Mathematics · doi:10.3390/math9161912 · Cited by 55 · see citing works
Self-citationLiu, J., de la Peña, D. M., Christofides, P. D., et al. (2008) · International Journal of Adaptive Control and Signal Processing · doi:10.1002/acs.1085 · Cited by 51 · see citing works
Challenging research for networked control systems: A survey
Li, M., & Chen, Y. (2018) · Transactions of the Institute of Measurement and Control · doi:10.1177/0142331218799818 · Cited by 35 · see citing works
Risk bounds for reservoir computing
Gonon, L., Grigoryeva, L., & Ortega, J. (2019) · Alexandria (UniSG) (University of St.Gallen) · doi:10.48550/arxiv.1910.13886 · Cited by 30
A bio-inspired bistable recurrent cell allows for long-lasting memory
Vecoven, N., Ernst, D., & Drion, G. (2021) · PLoS ONE · doi:10.1371/journal.pone.0252676 · Cited by 25 · see citing works
Alnajdi, A., Suryavanshi, A. V., Alhajeri, M. S., et al. (2023) · Digital Chemical Engineering · doi:10.1016/j.dche.2023.100084 · Cited by 25 · see citing works
Zhang, H., Chen, J., Hua, C., et al. (2023) · Chemical Engineering and Processing - Process Intensification · doi:10.1016/j.cep.2023.109643 · Cited by 14 · see citing works
Self-citationTime Series Prediction With Incomplete Dataset Based on Deep Bidirectional Echo State Network
Wang, Q., Wang, L., Liu, Y., Zhao, J., & Wang, W. (2019) · IEEE Access · doi:10.1109/access.2019.2948367 · Cited by 11 · see citing works
Recurrent Neural Network-Based MPC for Systems With Input and Incremental Input Constraints
Schimperna, I., Galuppini, G., & Magni, L. (2024) · IEEE Control Systems Letters · doi:10.1109/lcsys.2024.3404332 · Cited by 10 · see citing works
Park, J., Rho, M. J., Moon, H. W., & Lee, J. Y. (2020) · Applied Sciences · doi:10.3390/app10062000 · Cited by 7 · see citing works
Predictive Control of Nonlinear Chemical Processes under Asynchronous Measurements and Controls
Varutti, P., & Findeisen, R. (2009) · IFAC Proceedings Volumes · doi:10.3182/20090712-4-tr-2008.00022 · Cited by 5 · see citing works
Error bound characterization for reservoir computing-based OFDM symbol detection
Jere, S., Saad, H., & Liu, L. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9839095 · Cited by 4 · see citing works
Guinaldo, M., Rubio, F. R., Dormido, S., et al. (2015) · Springer eBooks · doi:10.1007/978-3-319-21299-9_1 · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- Seborg, 2016, Process Dynamics and Control
- Neil, Phased LSTM: Accelerating recurrent network training for long or event-based sequences, 3889
Cited by
Still being checked.
- Authors
- Wu, W., Wang, Y., Zhang, H., Zhang, M.-Q., Chiu, M.-S., & Wu, Z.
- Affiliations
- National University of Singapore (SG)
- Beijing University of Chemical Technology (CN)
- Venue
- IEEE Transactions on Control Systems Technology
- Published
- 2025-11
- Volume
- 33
- Issue
- 6
- Pages
- 2439-2454
- ISSN
- 1063-6536 (ISSN-L)
- 1558-0865
- 2374-0159
- OpenAlex
- W6940659363
- Cited by
- 3
- References
- 34
- Citations by year
- 2026: 3
- FWCI
- 1.17
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- IEEE Transactions on Control Systems Technology (publishedVersion, cc-by-nc-nd)
- Funders
- Ministry of Education Tier 1 (22-5367-A0001)
- ASTAR YIRG (M22K3c0093)
- National Research Foundation Competitive Research Programme (27-2021-0001)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Advanced Control Systems Optimization
- Physical Sciences › Engineering › Control and Systems Engineering › Control Systems and Identification
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Keywords
- missing data, delayed measurements, asynchronous measurements, model predictive control, Lyapunov-based model predictive control, nonlinear chemical processes, state forecasting, closed-loop stability, continuous stirred tank reactor, generalization bounds
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
