Combining multiscale decomposition with time-series modeling: An approach for petrochemical processes

Luo Mengjie; Zhang Mengxuan; Shi Xiaogang; Lan Xingying; Liu Yongdong; Li Wei

doi:null

Your Location：

Home >

Browse articles >

Combining multiscale decomposition with time-series modeling: An approach for petrochemical processes

Updated：2026-09-17

- Combining multiscale decomposition with time-series modeling: An approach for petrochemical processes
- Combining multiscale decomposition with time-series modeling: An approach for petrochemical processes
- 中国化学工程学报（英文） 2026年95卷第7期页码：313-327
- Affiliations：
  
  State Key Laboratory of Heavy Oil Processing, China University of Petroleum-Beijing, Beijing 102249, China
  China Industrial Control Systems Cyber Emergency Response Team, Beijing 100040, China
- Author bio：
  
  *Corresponding authors. E-mail addresses:lanxy@cup.edu.cn(X. Lan)
  *Corresponding authors. E-mail addresses:liuyongdong@cics-cert.org.cn(Y. Liu).
- Funds：
  
  the National Natural Science Foundation of China(22021004)
- DOI：
  中图分类号：
- 收稿：2025-04-15，
  
  修回：2026-03-01，
  
  录用：2026-03-03，
  
  网络首发：2026-04-01，
  
  纸质出版：2026-07
- Accepted：
Scan QR Code
Luo Mengjie, Zhang Mengxuan, Shi Xiaogang, 等. Combining multiscale decomposition with time-series modeling: An approach for petrochemical processes[J]. 中国化学工程学报（英文）, 2026,95(7):313-327.

Luo Mengjie, Zhang Mengxuan, Shi Xiaogang, et al. Combining multiscale decomposition with time-series modeling: An approach for petrochemical processes[J]. Chinese Journal of Chemical Engineering, 2026, 95(7): 313-327.
Luo Mengjie, Zhang Mengxuan, Shi Xiaogang, 等. Combining multiscale decomposition with time-series modeling: An approach for petrochemical processes[J]. 中国化学工程学报（英文）, 2026,95(7):313-327. DOI：

Luo Mengjie, Zhang Mengxuan, Shi Xiaogang, et al. Combining multiscale decomposition with time-series modeling: An approach for petrochemical processes[J]. Chinese Journal of Chemical Engineering, 2026, 95(7): 313-327. DOI：

摘要

Abstract

Accurately predicting key pr

oduct features is essential for process optimization and safety in petrochemical processes. However

conventional data-driven AI models often struggle to adequately capture the strong nonlinearity and multi-scale characteristics of these systems. To address this challenge

this paper proposes a multi-scale prediction framework that integrates variational mode decomposition (VMD)

attention mechanisms

and temporal convolutional networks (TCN)

referred to as DATCN. This framework facilitates the extraction of multi-scale features across temporal

spatial

and frequency domains

enabling cross-scale interaction modeling in complex processes. Comparative experiments on the Tennessee Eastman (TE) benchmark and industrial fluid catalytic cracking (FCC) long-term time-series datasets demonstrate that the proposed model achieves superior prediction accuracy (RMSE reduced by 24.75% to 37.26%

versus

other deep-learning models). The results demonstrate the framework's capability to address both nonlinear dynamics and spatiotemporal heterogeneity

offering a promising solution for intelligent optimization in petrochemical production.

关键词

Keywords

references

Y.J. Wang, C. Qian, S.J. Qin, Attention-mechanism based DiPLS-LSTM and its application in indust rial process time series big data prediction, Comput. Chem. Eng. 176 (2023) 108296.

Y.F. Chen, A.L. Li, X.Y. Li, D. Xue, J. Long, Efficient JITL framework for nonlinear industrial chemical engineering soft sensing based on adaptive multi-branch variable scale integrated convolutional neural networks, Adv. Eng. Inform. 58 (2023) 102199.

S.B. Yang, J. Moreira, Z.K. Li, Bioinspired encoder—decoder recurrent neural network with attention for hydroprocessing unit modeling, Ind. Eng. Chem. Res. 62 (44) (2023) 18526—18540.

J.M. Lu, Y.F. Wang, Z.Y. Zhou, J.X. Wu, Y.H. Zhang, L.Z. Zhang, Q. Shi, S.B. He, C. M. Xu, Molecular transformation of heavy oil during slurry phase hydrocracking process: influences of operational conditions, Pet. Sci. 22 (2) (2025) 884—893.

Z. Li, Y.H. Ying, M.L. Yang, L. Zhao, L. Zhao, W.L. Du, Monitoring and path optimization of catalytic reformer in a refinery: principal component analysis and A*algorithm application, Expert Syst. Appl. 209 (2022) 118358.

M.X. Zhang, Z. Yang, Y.P. Zhao, M.Z. Lv, X.Y. Lan, X.G. Shi, J.S. Gao, C.K. Li, Z. Yuan, Y. Lin, A hybrid safety monitoring framework for industrial FCC disengager coking rate based onFPM, CFD, and ML, Process. Saf. Environ. Prot. 175 (2023) 17—33.

T. Dias, R. Oliveira, P. Saraiva, M.S. Reis, Predictive analytics in the petrochemical industry: research Octane Number (RON) forecasting and analysis in an industrial catalytic reforming unit, Comput. Chem. Eng. 139 (2020) 106912.

C.W. Tang, J.L. Huang, M. Xu, X. Liu, F. Yang, W.T. Feng, Z.N. He, J.C. Lv, Attention-based early warning framework for abnormal operating conditions in fluid catalytic cracking units, Appl. Soft Comput. 153 (2024) 111275.

J. Abdi, G. Mazloom, F. Hadavimoghaddam, A. Hemmati-Sarapardeh, S.H. Esmaeili-Faraj, A. Bolhasani, S. Karamian, S. Hosseini, Estimation of the flow rate of pyrolysis gasoline, ethylene, and propylene in an industrial olefin plant using machine learning approaches, Sci. Rep. 13 (2023) 14081.

C.S. He, C.W. Zhang, T.F. Bian, K.X. Jiao, W.K. Su, K.J. Wu, A. Su, A review on artificial intelligence enabled design, synthesis, and process optimization of chemical products for industry 4.0, Processes 11 (2) (2023) 330.

M. Misra, H.H. Yue, S.J. Qin, C. Ling, Multivariate process monitoring and fault diagnosis by multi-scale PCA, Comput. Chem. Eng. 26 (9) (2002) 1281—1293.

J.H. Cho, J.M. Lee, S. Wook Choi, D. Lee, I.B. Lee, Fault identification for process monitoring using kernel principal component analysis, Chem. Eng. Sci. 60 (1) (2005) 279—288.

Q.M. Zhao, K.X. Bi, T. Qiu, Data-driven intelligent modeling framework for the steam cracking process, Chin. J. Chem. Eng. 61 (2023) 237—247.

Y.M. Bai, S.Y. Xiang, F.F. Cheng, J.S. Zhao, A dynamic-inner LSTM prediction method for key alarm variables forecasting in chemical process, Chin. J. Chem. Eng. 55 (2023) 266—276.

M.K. Lim, J.S. Yun, K.H. Cho, J.W. Yoon, U.H. Lee, A. Ferreira, A. Mafalda Ribeiro, I.B.R. Nogueira, J. Park, J.K. Kim, K. Kim, Multi-objective optimization of ANN-based vacuum pressure swing adsorption process for ethane and ethylene separation, J. Ind. Eng. Chem. 143 (2025) 221—239.

I. Alhajree, G. Zahedi, Z.A. Manan, S.M. Zadeh, Modeling and optimization of an industrial hydrocracker plant, J. Petrol. Sci. Eng. 78 (3—4) (2011) 627—636.

W.J. Zhu, X.W. Liu, X. Hou, J.Y. Hu, Z.H. Diao, Application of machine learning to process simulation of n-pentane cracking to produce ethylene and propene, Chin. J. Chem. Eng. 28 (7) (2020) 1832—1839.

L. Iapteff, J. Jacques, M. Rolland, B. Celse, Reducing the number of experiments required for modelling the hydrocracking process with Kriging through Bayesian transfer learning, J. R. Stat. Soc. Ser. C 70 (5) (2021) 1344—1364.

Y.J. Wang, Y.C. Zhang, Z. Wu, H.G. Li, P.D. Christofides, Operational trend prediction and classification for chemical processes: a novel convolutional neural network method based on symbolic hierarchical clustering, Chem. Eng. Sci. 225 (2020) 115796.

Y.M. Han, C.Y. Fan, M. Xu, Z.Q. Geng, Y.H. Zhong, Production capacity analysis and energy saving of complex chemical processes using LSTM based on attention mechanism, Appl. Therm. Eng. 160 (2019) 114072.

F. Yang, Y.S. Sang, J.C. Lv, J. Cao, Prediction of gasoline yield in fluid catalytic cracking based on multiple level LSTM, Chem. Eng. Res. Des. 185 (20 22) 119—129.

T.W. Zhang, F.F. Shen, Z. Li, X. Peng, W.M. Zhong, Synergizing low-carbon planning and operation for sustainable integrated refinery-petrochemical processes under arrival time uncertainty: a large-scale hierarchical energyefficiency optimization perspective, Appl. Energy 377 (2025) 124497.

J. Long, C. Huang, K. Deng, L. Wan, G.H. Hu, F. Zhang, Novel hybrid data-driven modeling integrating variational modal decomposition and dual-stage self-attention model: applied to industrial petrochemical process, Energy 304 (2024) 131895.

M.K. Khaldi, M. Al-Dhaifallah, O. Taha, Artificial intelligence perspectives: a systematic literature review on modeling, control, and optimization of fluid catalytic cracking, Alex. Eng. J. 80 (2023) 294—314.

G. He, C.L. Zhou, T. Luo, L. Zhou, Y.Y. Dai, Y.G. Dang, X. Ji, Online optimization of fluid catalytic cracking process via a hybrid model based on simplified structure-oriented lumping and case-based reasoning, Ind. Eng. Chem. Res. 60 (1) (2021) 412—424.

S. Santhakumaran, Y.A.W. Shardt, Data-driven nonlinear system identification and SIR particle filtering for chemical process monitoring and prediction, IFAC-PapersOnLine 58 (14) (2024) 434—439.

S.W. Xiong, L. Zhou, Y.Y. Dai, X. Ji, Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis, Chin. J. Chem. Eng. 56 (2023) 1—14.

J. Huang, X.Y. Sun, X. Yang, K.X. Peng, Fa ult detection for chemical processes based on non-stationarity sensitive cointegration analysis, ISA Trans. 129 (Pt B) (2022) 321—333.

J. Long, L. Ye, H.F. Peng, Z. Tian, Efficient prediction framework for large-scale nonlinear petrochemical process based on feature selection and temporal-attention LSTM: applied to fluid catalytic cracking, Chem. Eng. Sci. 301 (2025) 120733.

S.Z. Liu, Q.L. Liu, S. Ahmed, J.J. Wang, F.Y. Lei, D.F. Zhao, A method for the early prediction of abnormal conditions in chemical processes combined with physical knowledge and the data-driven model, J. Loss Prev. Process. Ind. 86 (2023) 105185.

Q. Li, M.X. Zhang, X.G. Shi, X.Y. Lan, X.Q. Guo, Y.L. Guan, An intelligent hybrid feature subset selection and production pattern recognition method for modeling ethylene plant, J. Anal. Appl. Pyrolysis 160 (2021) 105352.

N. Liu, C.M. Zhu, M.X. Zhang, X.Y. Lan, A multiscale adaptive framework based on convolutional neural network: application to fluid catalytic cracking product yield prediction, Pet. Sci. 21 (4) (2024) 2849—2869.

M.X. Zhang, D.F. Cao, X.Y. Lan, X.G. Shi, J.S. Gao, An ensemble-learning approach to predict the coke yield of commercial FCC unit, Ind. Eng. Chem. Res. 61 (24) (2022) 8422—8431.

W.J. Song, V. Mahalec, J. Long, M.L. Yang, F. Qian, Modeling the hydrocracking process with deep neural networks, Ind. Eng. Chem. Res. 59 (7) (2020) 3077—3090.

K. Dragomiretskiy, D. Zosso , Variational mode decomposition, IEEE Trans. Signal Process. 62 (3) (2014) 531—544.

H.Y. Chen, H. Huang, Y. Zheng, B. Yang, A load forecasting approach for integrated energy systems based on aggregation hybrid modal decomposition and combined model, Appl. Energy 375 (2024) 124166.

N.E. Huang, Z. Shen, S.R. Long, M.C. Wu, H.H. Shih, Q.A. Zheng, N.C. Yen, C.C. Tung, H.H. Liu, The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proc. Math. Phys. Eng. Sci. 454 (1971) (1998) 903—995.

Z.H. Wu, N.E. Huang, Ensemble empirical mode decomposition: a noise-assisted data analysis method, Adv. Adapt. Data Anal. 1 (1) (2009) 1—41.

J.R. Yeh, J.S. Shieh, N.E. Huang, Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method, Adv. Adapt. Data Anal. 2 (2) (2010) 135—156.

Y.H. Zhang, K.Z. Zhong, X.P. Xie, Y.Z. Huang, S. Han, G.Z. Liu, Z.Y. Chen, VMD-ConvTSMixer: spatiotemporal channel mixing model for non-stationary time series forecasting, Expert Syst. Appl. 271 (2025) 126535.

H.Y. Zhang, W.S. Wu, X.Y. Song, Z.X. Chen, Improving density logging resolution byVMD-CEEMDAN-ICWTmethod and its application in thin layer identification, Geoenergy Sci. Eng. 239 (2024) 212993.

Q.H. Wang, L.H. Li, Research on semi-supervised soft sensor modeling method for sulfur recovery unit based onISSA-VMD-ESN, Chem. Eng. Sci. 2 98 (2024) 120397.

X.L. Li, X.F. Zou, J.F. Cheng, M. Tang, P.F. Hu, FMM-VMD-Transformer: a hybrid deep learning model for predicting natural gas consumption, Digit. Eng. 2 (2024) 100005.

S.J. Bai, J.Z. Kolter, V. Koltun, An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, arXiv: 1803.01271 (2018), https://doi.org/10.48550/arXiv.1803.01271.

Q. Li, X.Y. Ren, F. Zhang, L. Gao, B. Hao, A novel ultra-short-term wind power forecasting method based on TCN and Informer models, Comput. Electr. Eng. 120 (2024) 109632.

L.S. Ke, L.L. Fang, J.H. Meng, J.C. Peng, J. Wu, M.Q. Lin, D.I. Stroe, Identification of the aging state of lithium-ion batteries via temporal convolution network and self-attention mechanism, J. Energy Storage 84 (2024) 110999.

J.J. Zhu, L.C. Su, Y.W. Li, Wind power forecasting based on new hybrid model with TCN residual modification, Energy AI 10 (2022) 100199.

S.J. Qian, T. Peng, Z.H. Tao, X. Li, M.S. Nazir, C. Zhang, An evolutionary deep learning model based on XGBoost feature selection and Gaussian data augmentation for AQI prediction, Process. Saf. Environ. Prot. 191 (2024) 836—851.

Y.H. Zhao, X.H. Peng, T. Tu, Z. Li, P.Y. Yan, C. Li, WOA-VMD-SCINet:hybrid model for accurate prediction of ultra-short-term Photovoltaic generation power considering seasonal variations, Energy Rep. 12 (2024) 3470—3487.

M.K. Fang, F.F. Zhang, Y. Yang, R. Tao, R.F. Xiao, D. Zhu, The influence of optimization algorithm on the signal prediction accuracy ofVMD-LSTMfor the pumped storage hydropower unit, J. Energy Storage 78 (2024) 110187.

K. Zhang, H.N. Ting, Y.M. Choo, Baby cry recognition based on WOA-VMD and an improved Dempster—Shafer evidence theory, Comput. Methods Progr. Biomed. 245 (2024) 108043.

N. Saleem, H. Elmannai, S. Bourouis, A. Trigui, Squeeze-and-excitation 3D convolutional attention recurrent network for end-to-end speech emotion recognition, Appl. Soft Comput. 161 (2024) 111735.

C.Q. Xu, J.L. Wang, J. Zhang, Forecasting the power consumption of a rotor spinning machine by using an adaptive squeeze and excitation convolutional neural network with imbalanced data, J. Clean. Prod. 275 (2020) 122864.

B.L. Li, J. Li, X.S. Wu, H.Q. Tang, Gated recurrent unit and temporal convolutional network with soft thresholding and attention mechanism for tool wear prediction, Measurement 240 (2025) 115546.

Y.M. Li, T. Peng, W. Sun, C.L. Ji, Y.H. Wang, Z.H. Tao, C. Zhang, M. Shahzad Nazir, A soft sensor model based on CNN-BiLSTM and IHHO algorithm for Tennessee Eastman process, Measurement 218 (2023) 113195.

M. Huang, Y. Zheng, S.Y. Li, Distributed economic model predictive control for an industrial fluid catalytic cracking unit ensuring safe operation, Control Eng. Pract. 126 (2022) 105263.

Q. Yang , A.S. Berrouk, Y.P. Du, H. Zhao, C.H. Yang, M.A. Rakib, A. Mohamed, A. Taher, CFD investigation of hydrodynamics, heat transfer and cracking reactions in a large-scale fluidized catalytic cracking riser, Appl. Math. Model. 40 (21—22) (2016) 9378—9397.

I. Al Aslani, G. Lezcano, J.M. Colom, A. Alahmadi, T. Shoinkhorova, A. Dikhtiarenko, M.M. Cui, L. Alfilfil, I. Morales Osorio, K. Almajnouni, P. Castanõ, J. Gascon, Reaction network and kinetic modeling for the direct catalytic cracking of Arabian light crude oil to chemicals, Chem. Eng. J. 498 (2024) 154981.

Y.M. John, R. Patel, I.M. Mujtaba, Modelling and simulation of an industrial riser in fluid catalytic cracking process, Comput. Chem. Eng. 106 (2017) 730—743.

A. Gupta, D. Subba Rao, Effect of feed atomization on FCC performance:simulation of entire unit, Chem. Eng. Sci. 58 (20) (2003) 4567—4579.

J. Chang, F.D. Meng, L.Y. Wang, K. Zhang, H.G. Chen, Y.P. Yang, CFD investigation of hydrodynamics, heat transfer and cracking reaction in a heavy oil riser with bottom airlift loop mixer, Chem. Eng. Sci. 78 (2012) 128—143.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Real-time risk prediction of chemical processes based on attention-based Bi-LSTM

Adaptive multiscale convolutional neural network model for chemical process fault diagnosis

From data to insight: Building a knowledge graph for risk analysis of hazardous chemical accidents

Large language model-based multi-objective modeling framework for vacuum gas oil hydrotreating

Distributed process monitoring based on Kantorovich distance-multiblock variational autoencoder and Bayesian inference