Development of a Surrogate-model Based Energy Efficiency Estimator for a Multi-step Chemical Process
DOI:
https://doi.org/10.3384/ecp211851Keywords:
chemical process engineering, Tennessee Eastman, energy efficiency, PLSR models, model adaptationAbstract
Energy efficiency is increasingly being considered as a critical measure of process performance due to its importance both in production costs and in environmental footprint. In this work, an indirect energy efficiency estimator was developed for the Tennessee Eastman (TE) benchmark process for the first time. The TE model was first modified to provide the reference values of energy efficiency. A sophisticated model selection scheme was then applied to build the surrogate-model. The results indicate reasonable model performance with mean absolute prediction error around 1.7%. The results also highlight the limitations present in the training set, which are, together with other practical implementation issues, discussed in this work.References
A. Bakdi and A. Kouadri. An improved plant‐wide fault detection scheme based on PCA and adaptive threshold for reliable process monitoring: Application on the new revised model of Tennessee Eastman process. Journal of Chemometrics, 32(5), 2018. doi: 10.1002/cem.2978
A. Bathelt, N. Ricker and M. Jelali. Revision of the Tennessee Eastman Process Model. IFAC-PapersOnLine, 48(8):309–314, 2015. doi: 10.1016/j.ifacol.2015.08.199S.
S. de Jong. SIMPLS: An Alternative Approach to Partial Least Squares Regression. Chemometrics and Intelligent Laboratory Systems, 18(3):251–263, 1993. doi: 10.1016/0169-7439(93)85002-X
J. Downs, E. Vogel. A plant-wide industrial process control problem. Computers & Chemical Engineering, 17(3):245-255, 1993. doi: 10.1016/0098-1354(93)80018-I
C. Drumm, J. Busch, W. Dietrich, J. Eickmans and A. Jupke. STRUCTese® – Energy efficiency management for the process industry. Chemical Engineering and Processing – Process Intensification, 67:99–110. doi: 10.1016/j.cep.2012.09.009
T. Hastie, R. Tibshirani and J. Friedman. The elements of statistical learning: data mining, inference, and prediction. 2009. Springer Science & Business Media.
T. Jockenhövel, L. Biegler and A. Wächter. Dynamic optimization of the Tennessee Eastman process using the OptControlCentre. Computers & Chemical Engineering. 27:1513–1531, 2003. doi: 10.1016/S0098-1354(03)00113-3
N. Jämsä. Model predictive control for the Tennessee Eastman process, M.Sc. Thesis, Aalto University, 2018.
U. Konge, A. Baikadi, J. Mondi and S. Subramanian. Data-Driven Model Based Computation and Analysis of Operability Sets Using High-Dimensional Continuation: A Plant-Wide Case Study. Industrial & Engineering Chemistry Research, 59(21):10043—10060, 2020. doi: 10.1021/acs.iecr.9b07087
A. Kulkarni, V. Jayaraman and B. Kulkarni. Knowledge incorporated support vector machines to detect faults in Tennessee Eastman Process. Computers & Chemical Engineering, 29(10):2128-2133, 2005. doi: 10.1016/j.compchemeng.2005.06.006
T. Larsson, K. Hestetun, E. Hovland and S. Skogestad. Self-Optimizing Control of a Large-Scale Plant: The Tennessee Eastman Process. Industrial & Engineering Chemistry Research, 40:4889–4901, 2001. doi: 10.1021/ie000586y
Y. Ma, X. Gu and Y. Wang. Histogram similarity measure using variable bin size distance. Computer Vision and Image Understanding, 114(8):981–989, 2010. doi: 10.1016/j.cviu.2010.03.006
J. Mathiassen, A. Skavhaug and K. Bø. Texture similarity measure using Kullback-Leibler divergence between gamma distributions. In Proceedings – 7th European Conference on Computer Vision, ECCV 2002, 28-31 May, 2002, Copenhagen, Denmark, pages 133–147, 2002. doi: 10.1007/3-540-47977-5_9
J. Moreno-Torres, T. Raeder, R. Alaiz-Rodríguez, N. Chawla and F. Herrera. A unifying view on dataset shift in classification. Pattern Recognition, 45(1):521-530, 2012. doi: 10.1016/j.patcog.2011.06.019
R. Nikula, M. Ruusunen and K. Leiviskä. Data-driven framework for boiler performance monitoring. Applied Energy, 183:1374-1388, 2016. doi: 10.1016/j.apenergy.2016.09.072
N. Ricker. Tennessee Eastman Challenge Archive, 2015, https://depts.washington.edu/control/LARRY/TE/download.html#Basic_TE_Code.
D. Saygin, M. Patel, E. Worrell, C. Tam and D. Gielen. Potential of best practice technology to improve energy efficiency in the global chemical and petrochemical sector. Energy, 36(9):5779-5790, 2011. doi: 10.1016/j.energy.2011.05.019
A. Sheta, M. Braik and H. Al-Hiary. Modeling the Tennessee Eastman chemical process reactor using bio-inspired feedforward neural network (BI-FF-NN). The International Journal of Advanced Manufacturing Technology, 103:1359–1380, 2019. doi: 10.1007/s00170-019-03621-5
M. Swain and H. Ballard. Color indexing. International Journal of Computer Vision, 7(1):11-32, 1991. doi: 10.1007/BF00130487
A. Tran and C. Georgakis. On the estimation of high-dimensional surrogate models of steady-state of plant-wide processes characteristics. Computers & Chemical Engineering, 116:56–68, 2018. doi: 10.1016/j.compchemeng.2018.02.014
D. Xie and L. Bai. A hierarchical deep neural network for fault diagnosis on Tennessee-Eastman process. In Proceedings -2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), 9-11 December, 2015, Miami, FL, USA, pages 745–748, 2015. doi: 10.1109/ICMLA.2015.208
W. Zou, Y. Xia and H. Li. Fault diagnosis of Tennessee-Eastman process using orthogonal incremental extreme learning machine based on driving amount. IEEE Transactions on Cybernetics, 48(12):3403–3410, 2018. doi: 10.1109/TCYB.2018.28
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Markku Ohenoja, Tero Vuolio, Teemu Pätsi, Petri Österberg, Mika Ruusunen
This work is licensed under a Creative Commons Attribution 4.0 International License.
