Data-Driven Condition-Aware Adaptive Model Predictive Control for Industrial Ethylene Cracking Furnaces

Mengjie Luo; Mengxuan Zhang; Yunpeng Zhao; Xiaogang Shi; Xingying Lan

doi:10.53941/sce.2026.100005

Abstract

During long-term operation of ethylene cracking furnaces, coke deposition and operating condition variations continuously alter process dynamics, resulting in strong non-stationarity and reduced control performance of conventional model predictive control (MPC). To address this issue, a condition-aware adaptive MPC (CA-AMPC) framework is proposed, in which operating conditions are incorporated into the control loop to enable adaptive prediction and control adjustment. A segment-wise operating condition identification method combining change point detection and clustering is developed to capture both abrupt transitions and gradual process evolution. Based on the identified conditions, condition-dependent prediction models and optimized control parameters are dynamically activated to improve control adaptability under varying operating regimes. Industrial case studies demonstrate that the proposed framework achieves yield improvements of approximately 1.0%, 1.5%, and 0.3% under normal-load early-coking, normal-load severe-coking, and post-decoking high-load conditions, respectively. The total online computation time remains well below the 120 s DCS sampling interval. The proposed framework provides an effective solution for adaptive control of non-stationary industrial processes.

References

1.
Fakhroleslam, M.; Sadrameli, S.M. Thermal/catalytic cracking of hydrocarbons for the production of olefins; a state-of-the-art review III: Process modeling and simulation. Fuel 2019, 252, 553–566.
2.
Sadrameli, S.M. Thermal/catalytic cracking of hydrocarbons for the production of olefins: A state-of-the-art review I: Thermal cracking review. Fuel 2015, 140, 102–115.
3.
Yuan, B.F.; Zhang, Y.; Du, W.L.; et al. Assessment of energy saving potential of an industrial ethylene cracking furnace using advanced exergy analysis. Appl. Energy 2019, 254, 113583.
4.
Hu, G.H.; Zhang, Y.; Du, W.L.; et al. Zone method based coupled simulation of industrial steam cracking furnaces. Energy 2019, 172, 1098–1116.
5.
Shen, W.H.; Tian, Z.; Zhao, L.; et al. Life Cycle Assessment and Multiobjective Optimization for Steam Cracking Process in Ethylene Plant. ACS Omega 2022, 7, 15507–15517.
6.
Shi, H.Y.; Wang, W.Z.; Peng, B.; et al. Multi-step compensated robust predictive cascade control for ethylene cracking furnaces with time delay. Chem. Eng. Sci. 2026, 320, 122412.
7.
Zheng, S.; Zhang, X.Y.; Qi, C.B.; et al. Modeling of heat transfer and pyrolysis reactions in ethylene cracking furnace based on 3-D combustion monitoring. Int. J. Therm. Sci. 2015, 94, 28–36.
8.
Dormido, S. Advanced PID control. IEEE Control Syst. Mag. 2006, 26, 98–101.
9.
Martineau, S.; Burnham, K.J.; Minihan, J.A.; et al. Application of a Bilinear Pid Compensator to an Industrial Furnace. IFAC Proc. Vols. 2002, 35, 25–30.
10.
Ben-Mansour, R.; Badr, H.M.; Araoye, A.A.; et al. Computational analysis of water-submerged jet erosion. Energies 2021, 14, 3074.
11.
Meri, Y.; Siddiqui, O.; Toor, I.U.H.; et al. A detailed review of numerical modeling of flow accelerated corrosion: Challenges and opportunities for the future. Mater. Corros. 2024, 76, 368–385.
12.
Zhang, C.H.; Wang, Z.L. A data-driven strategy for industrial cracking furnace system scheduling under uncertainty. Chem. Eng. Sci. 2023, 277, 118865.
13.
Zhang, R.D.; Xue, A.K.; Wang, S.Q. Dynamic Modeling and nonlinear predictive control based on partitioned model and nonlinear optimization. Ind. Eng. Chem. Res. 2011, 50, 8110–8121.
14.
Zhang, R.D.; Wang, S.Q. Support vector machine based predictive functional control design for output temperature of coking furnace. J. Process Control 2008, 18, 439–448.
15.
Qin, S.J.; Badgwell, T.A. A survey of industrial model predictive control technology. Control Eng. Pract. 2003, 11, 733–764.
16.
Khimani, D.; Mate, S.; Bhartiya, S. Model Predictive Control: Trade-offs between performance and computation time. IFAC-Pap. 2024, 57, 77–82.
17.
Chen, P.; Xu, B.C.; He, W.; et al. Transformer-based model predictive control with feedforward prediction for ammonia injection optimization in SCR denitrification systems. Process Saf. Environ. 2025, 202, 107804.
18.
Jin, Y.K.; Li, J.L.; Du, W.L.; et al. Integrated operation and cyclic scheduling optimization for an ethylene cracking furnaces system. Ind. Eng. Chem. Res. 2015, 54, 3844–3854.
19.
Zhang, Y.; Sha, P.; Wang, M.H.; et al. Toward intelligent and green ethylene manufacturing: An AI-based multi-objective dynamic optimization framework for the steam thermal cracking process. Engineering 2025, 52, 160–171.
20.
Zhao, S.J.; Zhang, J.; Xu, Y.M. Performance monitoring of processes with multiple operating modes through multiple PLS models. J. Process Control 2006, 16, 763–772.
21.
Pipino, H.A.; Adam, E.J. Adaptive model-based predictive control with changing operation points. Comput. Chem. Eng. 2025, 200, 109188.
22.
Hou, Z.S.; Wang, Z. From model-based control to data-driven control: Survey, classification and perspective. Inf. Sci. 2013, 235, 3–35.
23.
Bakhtyari, A.; Seo, J.G. AI-assisted modeling and optimization of large-scale ethylene production by catalytic oxidative dehydrogenation of ethane in a shell-and-tube multi-tubular reactor. Chem. Eng. J. 2026, 529, 172969.
24.
Berreni, M.; Wang, M.H. Modelling and dynamic optimization of thermal cracking of propane for ethylene manufacturing. Comput. Chem. Eng. 2011, 35, 2876–2885.
25.
Nian, X.Y.; Wang, Z.L.; Qian, F. Strategy of changing cracking furnace feedstock based on improved group search optimization. Chin. J. Chem. Eng. 2015, 23, 181–191.
26.
Geng, Z.Q.; Kong, W.K.; Wang, X.T.; et al. Adaptive search based Grey Wolf optimization algorithm for multi-objective optimization of ethylene cracking furnace. Swarm Evol. Comput. 2025, 92, 101810.
27.
Allah, M. AA.; Toor, I.U.H.; Shams, A.; et al. Application of machine learning and deep learning techniques for corrosion and cracks detection in nuclear power plants: A review. Arab. J. Sci. Eng. 2024, 50, 3017–3045.
28.
Li, Q.; Zhang, M.X.; Shi, X.G.; et al. An intelligent hybrid feature subset selection and production pattern recognition method for modeling ethylene plant. J. Anal Appl. Pyrol. 2021, 160, 105352.
29.
Camperos, J.A.; Diaz, C.M.; Cely, M.M.; et al. Dense-gas/liquid two-phase flow pattern recognition using convolutional neural networks and transfer learning. Int. J. Multiph. Flow 2026, 194, 105479.
30.
Wang, C.Y.; Du, M.J.; Jiang, X.; et al. Fuzzy cluster-aware contrastive clustering for time series. Pattern Recognit. 2026, 173, 112899.
31.
Lin, X.W.; Zhao, L.; Shang, C.; et al. Data-driven robust optimization for cyclic scheduling of ethylene cracking furnace system under uncertainty based on kernel learning. Chem. Eng. Sci. 2022, 260, 117919.
32.
Li, H.R.; Wei, Y.X.; Qiu, T. Dynamic Scheduling of ethylene cracking furnaces system leveraging deep reinforcement learning. In Computer Aided Chemical Engineering; Manenti, F., Reklaitis, G.V., Eds.; Elsevier: Amsterdam, The Netherlands, 2024; Volume 53, pp. 2989–2994.
33.
Cong, D.; Shi, C.J.; Cui, Y.F.; et al. Novel competing evolutionary membrane algorithm based on multiple reference points for multi-objective optimization of ethylene cracking processes. Chemom. Intell. Lab. Syst. 2021, 217, 104389.
34.
Yu, K.J.; While, L.; Reynolds, M.; et al. Cyclic scheduling for an ethylene cracking furnace system using diversity learning teaching-learning-based optimization. Comput. Chem. Eng. 2017, 99, 314–324.
35.
Chiu, J.E.; Fu, S.Z. On-line recognition of mixture control chart patterns using hybrid CNN and LSTM for auto-correlated processes. Comput. Ind. Eng. 2024, 198, 110674.
36.
Zhang, L.X.; Xiang, W.M. Mode-identifying time estimation and switching-delay tolerant control for switched systems: An elementary time unit approach. Automatica 2016, 64, 174–181.
37.
Zhao, S.J.; Zhang, J.; Xu, Y.M. Monitoring of processes with multiple operating modes through multiple principle component analysis models. Ind. Eng. Chem. Res. 2004, 43, 7025–7035.
38.
Zheng, C.; Zhang, Y.; Sha, P.; et al. Optimal scheduling of low-carbon ethylene production system based on deep reinforcement learning: Considering flexible operation under furnace coking and renewable energy fluctuations. Energy 2026, 342, 139780.
39.
Deng, Z.Y.; Han, T.; Cheng, Z.H.; et al. Fault detection of petrochemical process based on space-time compressed matrix and Naive Bayes. Process Saf. Environ. 2022, 160, 327–340.
40.
Han, X.Y.; Tian, S.W.; Romagnoli, J.A.; et al. The real-time multiple operational condition monitoring of ethylene cracking furnace based on the principal component analysis. Chem. Eng. Trans. 2017, 61, 517–522.
41.
Maestri, M.; Farall, A.; Groisman, P.; et al. A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes. Comput. Chem. Eng. 2010, 34, 223–231.
42.
Bao, X.Y.; Chen, L.; Zhong, J.S.; et al. A self-supervised contrastive change point detection method for industrial time series. Eng. Appl. Artif. Intell. 2024, 133, 108217.
43.
Zhang, M.X.; Cao, D.F.; Lan, X.Y.; et al. An Ensemble-learning approach to predict the coke yield of commercial FCC unit. Ind. Eng. Chem. Res. 2022, 61, 8422–8431.
44.
Zhang, M.X.; Yang, Z.; Zhao, Y.P.; et al. A hybrid safety monitoring framework for industrial FCC disengager coking rate based on FPM, CFD, and ML. Process Saf. Environ. 2023, 175, 17–33.
45.
He, G.; Luo, L.; Zhou, L.; et al. Deep learning prediction of yields of fluid catalytic cracking via differential evolutionary dual-stage attention-based LSTM. Fuel 2024, 370, 131826.
46.
Yue, Z.H.; Wang, Y.J.; Duan, J.Y.; et al. TS2Vec: Towards universal representation of time series. In Proceedings of the the Thirty-Sixth AAAI Conference on Artificial Intelligence, Virtual, 22 February–1 March 2022; pp 8980–8988.
47.
Xu, R.Y.; Song, Z.R.; Wu, J.G.; et al. Change-point detection with deep learning: A review. Front. Eng. Manag. 2025, 12, 154–176.
48.
Keshavarz, M.; Huang, B. Bayesian and expectation maximization methods for multivariate change point detection. Comput. Chem. Eng. 2014, 60, 339–353.
49.
Liu, R.; Wang, H.; Yu, X.M. Shared-nearest-neighbor-based clustering by fast search and find of density peaks. Inf. Sci. 2018, 450, 200–226.
50.
Zhang, X.; Qu, J.H. Density peaks clustering based on shared nearest neighbors and dense degree. In Proceedings of the 8th International Conference on Intelligent Computing and Signal Processing (ICSP), Xi’an, China, 21–23 April 2023; pp. 1088–1091.
51.
Zou, T.G.; Zhou, M.W.; Wang, C.; et al. Pre-Shift fill control of wet clutches in heavy tracked vehicles using velocity prediction and a model predictive control framework. Control Eng. Pract. 2026, 173, 106950.
52.
Yuan, X.F.; Huang, L.F.; Ye, L.J.; et al. Quality prediction modeling for industrial processes using multiscale attention-based convolutional neural network. IEEE Trans. Cybern. 2024, 54, 2696–2707.
53.
Cui, D.S.; Qin, J.W.; He, F.; et al. MP3Net: Multi-scale patch parallel prediction networks for multivariate time series forecasting. In Proceedings of the International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan, 30 June–5 July 2024; pp. 1–7.
54.
Fang, Z.Y.; Gao, S.W.; Dang, X.C.; et al. Transformer enhanced by local perception self-attention for dynamic soft sensor modeling of industrial processes. Meas. Sci. Technol. 2024, 35, 055123.
55.
Masoumi, M.; Sadrameli, S.; Towfighi, J.; et al. Simulation, optimization and control of a thermal cracking furnace. Energy 2006, 31, 516–527.

Scilight Press

Author Information

Abstract

Keywords

References

About Scilight

Journals

Publishing Policies

Contact Us