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

doi:10.1016/j.cjche.2025.05.012

Chinese Journal of Chemical Engineering ›› 2025, Vol. 84 ›› Issue (8): 133-145.DOI: 10.1016/j.cjche.2025.05.012

Previous Articles Next Articles

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

Zheyuan Pang¹, Siying Liu², Yiting Lin^2,3, Xiangchen Fang⁴, Honglai Liu^1,2, Chong Peng⁵, Cheng Lian^1,2

1. State Key Laboratory of Chemical Engineering, Shanghai Engineering Research Center of Hierarchical Nanomaterials, and School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China;
2. School of Chemistry and Molecular Engineering, East China University of Science and Technology, Shanghai 200237, China;
3. Key Laboratory of Pressure Systems and Safety (MOE), School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai 200237, China;
4. Dalian Research Institute of Petroleum and Petrochemicals, SINOPEC, Dalian 116024, China;
5. State Key Laboratory of Fine Chemicals, School of Chemical Engineering, Dalian University of Technology, Dalian 116024, China

Received:2025-02-20 Revised:2025-05-15 Accepted:2025-05-15 Online:2025-06-04 Published:2025-08-28
Contact: Chong Peng,E-mail:pengchong@dlut.edu.cn;Cheng Lian,E-mail:liancheng@ecust.edu.cn
Supported by:
This work was supported by the National Key Research and Development Program of China (2023YFA1507601), the National Natural Science Foundation of China (22278127, 22378038), the Fundamental Research Funds for the Central Universities (2022ZFJH004), the Shanghai Pilot Program for Basic Research (22T01400100-18), and the Natural Science Foundation of Liaoning Province, China (2024-MSBA-15).

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

Zheyuan Pang¹, Siying Liu², Yiting Lin^2,3, Xiangchen Fang⁴, Honglai Liu^1,2, Chong Peng⁵, Cheng Lian^1,2

1. State Key Laboratory of Chemical Engineering, Shanghai Engineering Research Center of Hierarchical Nanomaterials, and School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China;
2. School of Chemistry and Molecular Engineering, East China University of Science and Technology, Shanghai 200237, China;
3. Key Laboratory of Pressure Systems and Safety (MOE), School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai 200237, China;
4. Dalian Research Institute of Petroleum and Petrochemicals, SINOPEC, Dalian 116024, China;
5. State Key Laboratory of Fine Chemicals, School of Chemical Engineering, Dalian University of Technology, Dalian 116024, China

通讯作者: Chong Peng,E-mail:pengchong@dlut.edu.cn;Cheng Lian,E-mail:liancheng@ecust.edu.cn
基金资助:
This work was supported by the National Key Research and Development Program of China (2023YFA1507601), the National Natural Science Foundation of China (22278127, 22378038), the Fundamental Research Funds for the Central Universities (2022ZFJH004), the Shanghai Pilot Program for Basic Research (22T01400100-18), and the Natural Science Foundation of Liaoning Province, China (2024-MSBA-15).

Abstract

Abstract: Data-driven approaches are extensively employed to model complex chemical engineering processes, such as hydrotreating, to address the challenges of mechanism-based methods demanding deep process understanding. However, the development of such models requires specialized expertise in data science, limiting their broader application. Large language models (LLMs), such as GPT-4, have demonstrated potential in supporting and guiding research efforts. This work presents a novel AI-assisted framework where GPT-4, through well-engineered prompts, facilitates the construction and explanation of multi-objective neural networks. These models predict hydrotreating products properties (such as distillation range), including refined diesel and refined gas oil, using feedstock properties, operating conditions, and recycle hydrogen composition. Gradient-weighted class activation mapping was employed to identify key features influencing the output variables. This work illustrates an innovative AI-guided paradigm for chemical engineering applications, and the designed prompts hold promise for adaptation to other complex processes.

Key words: Hydrogenation, Prompt engineering, Large language model, Neural networks, Prediction

摘要： Data-driven approaches are extensively employed to model complex chemical engineering processes, such as hydrotreating, to address the challenges of mechanism-based methods demanding deep process understanding. However, the development of such models requires specialized expertise in data science, limiting their broader application. Large language models (LLMs), such as GPT-4, have demonstrated potential in supporting and guiding research efforts. This work presents a novel AI-assisted framework where GPT-4, through well-engineered prompts, facilitates the construction and explanation of multi-objective neural networks. These models predict hydrotreating products properties (such as distillation range), including refined diesel and refined gas oil, using feedstock properties, operating conditions, and recycle hydrogen composition. Gradient-weighted class activation mapping was employed to identify key features influencing the output variables. This work illustrates an innovative AI-guided paradigm for chemical engineering applications, and the designed prompts hold promise for adaptation to other complex processes.

关键词: Hydrogenation, Prompt engineering, Large language model, Neural networks, Prediction

Zheyuan Pang, Siying Liu, Yiting Lin, Xiangchen Fang, Honglai Liu, Chong Peng, Cheng Lian. Large language model-based multi-objective modeling framework for vacuum gas oil hydrotreating[J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 133-145.

References

[1] D. Chehadeh, X.L. Ma, H. Al Bazzaz, Recent progress in hydrotreating kinetics and modeling of heavy oil and residue: a review, Fuel 334 (2023) 126404.
[2] X.L. Qin, L. Ye, J.C. Liu, Y.H. Xu, A. Murad, Q. Ying, H.T. Shen, X. Wang, L.X. Hou, X. Pu, X. Han, J.B. Li, R.J. Wang, N. Liu, A molecular-level coupling model of fluid catalytic cracking and hydrotreating processes to improve gasoline quality, Chem. Eng. J. 451 (2023) 138778.
[3] Z. Liu, J.C. Yuan, Z.Z. Sun, X. Feng, Y.B. Liu, H.H. Zhu, C. Peng, C.H. Yang, Morphology effect on catalytic performance of ebullated-bed residue hydrotreating over Ni-Mo/Al₂O₃ catalyst: a kinetic modeling study, Green Chem. Eng. 5 (1) (2024) 60-67.
[4] Z.Y. Pang, P. Huang, C. Lian, C. Peng, X.C. Fang, H.L. Liu, Data-driven prediction of product yields and control framework of hydrocracking unit, Chem. Eng. Sci. 283 (2024) 119386.
[5] D. Haolan Tao, S.J. Wang, P. . Honglai Liu, P. Cheng Lian, Deep neural network enhanced mesoscopic thermodynamic model for unlocking the electrode/electrolyte interface, Angew. Chem. Int. Ed. 64 (6) (2025) e202418447.
[6] Y. Lin, C. Lian, M.U. Berrueta, H. Liu, R. van Roij, Microscopic model for cyclic voltammetry of porous electrodes, Phys. Rev. Lett. 128 (20) (2022) 206001.
[7] W.Q. Yang, Y.T. Lin, J.L. Du, C. Lian, H.L. Liu, Integrating electrochemical and thermal models for improved lithium-lon battery energy storage system heat dissipation, Chin. J. Chem. Eng., (2025)(in press).
[8] S.C.D. Eswaran, M.V. Olarte, R. Rallo, L. Marrlett, J. Harper, M. Anderson, E. Shapiro, P. Kozyra, A. Starks, HT model: using the molecular transformer for predicting hydrotreating reactions, Energy Fuels 37 (19) (2023) 14922-14935.
[9] D. Ghosh, J. Moreira, P. Mhaskar, Application of data-driven modeling approaches to industrial hydroprocessing units, Chem. Eng. Res. Des. 177 (2022) 123-135.
[10] D.A. Boiko, R. MacKnight, B. Kline, G. Gomes, Autonomous chemical research with large language models, Nature 624 (7992) (2023) 570-578.
[11] N.J. Szymanski, B. Rendy, Y. Fei, R.E. Kumar, T. He, D. Milsted, M.J. McDermott, M. Gallant, E.D. Cubuk, A. Merchant, H. Kim, A. Jain, C.J. Bartel, K. Persson, Y. Zeng, G. Ceder, An autonomous laboratory for the accelerated synthesis of novel materials, Nature 624 (7990) (2023) 86-91.
[12] A.J. Thirunavukarasu, D.S.J. Ting, K. Elangovan, L. Gutierrez, T.F. Tan, D.S.W. Ting, Large language models in medicine, Nat. Med. 29 (2023) 1930-1940.
[13] Z.L. Zheng, Z.C. Rong, D. Nakul Rampal, P. . Christian Borgs, P. .J.T. Chayes, P. .O.M. Yaghi, A GPT-4 reticular chemist for guiding MOF discovery, Angew. Chem. Int. Ed. 62 (46) (2023) e202311983.
[14] J. Dagdelen, A. Dunn, S. Lee, N. Walker, A.S. Rosen, G. Ceder, K.A. Persson, A. Jain, Structured information extraction from scientific text with large language models, Nat. Commun. 15 (1) (2024) 1418.
[15] Feng Y, Hu G, Zhang Z. Gpt4battery: An Llm-Driven Framework for Adaptive State of Health Estimation of Raw Li-Ion Batteries. arXiv preprint arXiv:240200068, 2024.
[16] Z.P. Gu, B.K. Zhu, G.B. Zhu, Y.Y. Chen, M. Tang, J.Q. Wang, AnomalyGPT: detecting industrial anomalies using large vision-language models, Proc. AAAI Conf. Artif. Intell. 38 (3) (2024) 1932-1940.
[17] Y.Q. Pan, Q.F. Xiao, F.Y. Zhao, Z.H. Li, J.Y. Liu, S. Ullah, K.H. Lim, T.Y. Huang, Z.Y. Yu, C. Li, D.Y. Zhang, Q.Q. Xue, Q. Chen, S. Kawi, Y.J. Wang, G.S. Luo, Chat-microreactor: a large-language-model-based assistant for designing continuous flow systems, Chem. Eng. Sci. 311 (2025) 121567.
[18] M.L. Tsai, C.W. Ong, C.L. Chen, Exploring the use of large language models (LLMs) in chemical engineering education: Building core course problem models with Chat-GPT, Educ. Chem. Eng. 44 (2023) 71-95.
[19] F. Caccavale, C.L. Gargalo, K.V. Gernaey, U. Kruhne, Towards Education 4.0: The role of Large Language Models as virtual tutors in chemical engineering, Educ. Chem. Eng. 49 (2024) 1-11.
[20] M. Keith, E. Keiller, C. Windows-Yule, I. Kings, P. Robbins, Harnessing generative AI in chemical engineering education: Implementation and evaluation of the large language model ChatGPT v3.5, Educ. Chem. Eng. 51 (2025) 20-33.
[21] M.P. Polak, D. Morgan, Extracting accurate materials data from research papers with conversational language models and prompt engineering, Nat. Commun. 15 (1) (2024) 1569.
[22] Z. Zheng, O. Zhang, C. Borgs, J.T. Chayes, O.M. Yaghi, ChatGPT chemistry assistant for text mining and the prediction of MOF synthesis, J Am Chem Soc 145 (32) (2023) 18048-18062.
[23] Z.L. Zheng, Z.G. He, O. Khattab, N. Rampal, M.A. Zaharia, C. Borgs, J.T. Chayes, O.M. Yaghi, Image and data mining in reticular chemistry powered by GPT-4V, Digit. Discov. 3 (3) (2024) 491-501.
[24] J. Maharjan, A. Garikipati, N.P. Singh, L. Cyrus, M. Sharma, M. Ciobanu, G. Barnes, R. Thapa, Q. Mao, R. Das, OpenMedLM: prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models, Sci. Rep. 14 (1) (2024) 14156.
[25] L. Wang, X. Chen, X.W. Deng, H. Wen, M.K. You, W.Z. Liu, Q. Li, J. Li, Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs, NPJ Digit. Med. 7 (1) (2024) 41.
[26] Y. Kang, J. Kim, ChatMOF: an artificial intelligence system for predicting and generating metal-organic frameworks using large language models, Nat. Commun. 15 (1) (2024) 4705.
[27] D. Peng, L.B. Zheng, D. Liu, C. Han, X. Wang, Y. Yang, L. Song, M.Y. Zhao, Y.F. Wei, J.Y. Li, X.X. Ye, Y.X. Wei, Z.H. Feng, X.H. Huang, M.M. Chen, Y.J. Gou, Y. Xue, L.Y. Zhang, Large-language models facilitate discovery of the molecular signatures regulating sleep and activity, Nat. Commun. 15 (1) (2024) 3685.
[28] N.S. Lai, Y.S. Tew, X.L. Zhong, J. Yin, J.L. Li, B.H. Yan, X.N. Wang, Artificial intelligence (AI) workflow for catalyst design and optimization, Ind. Eng. Chem. Res. 62 (43) (2023) 17835-17848.
[29] J.C. Jiang, T.Y. Li, C. Chang, C. Yang, L. Liao, Fault diagnosis method for lithium-ion batteries in electric vehicles based on isolated forest algorithm, J. Energy Storage 50 (2022) 104177.
[30] F.T. Liu, K.M. Ting, Z.H. Zhou, Isolation forest, 2008 Eighth IEEE International Conference on Data Mining. December 15-19, 2008, Pisa, Italy. IEEE, (2008) 413-422.
[31] X.L. Tao, Y. Peng, F. Zhao, P.C. Zhao, Y. Wang, A parallel algorithm for network traffic anomaly detection based on Isolation Forest, Int. J. Distrib. Sens. Netw. 14 (11) (2018) 155014771881447.
[32] Y.B. Wang, D.G. Chang, S.R. Qin, Y.H. Fan, H.B. Mu, G.J. Zhang, Separating multi-source partial discharge signals using linear prediction analysis and isolation forest algorithm, IEEE Trans. Instrum. Meas. 69 (6) (2020) 2734-2742.
[33] D.E. Rumelhart, G.E. Hinton, R.J. Williams, Learning representations by back-propagating errors, Nature 323 (1986) 533-536.
[34] S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Comput. 9 (8) (1997) 1735-1780.
[35] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proc. IEEE 86 (11) (1998) 2278-2324.
[36] R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-CAM: visual explanations from deep networks via gradient-based localization, In:2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy. IEEE, 2017.
[37] Z.Y. Xu, S.Z. Wang, X.L. Zhang, G.W. He, Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping, J. Comput. Phys. 514 (2024) 113224.
[38] H.F. Kaiser, A second generation little jiffy, Psychometrika 35 (4) (1970) 401-415.

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

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

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Qingyu Wang, Duiping Liu, Yong Lu, Jibin Zhou, Xiangang Ma, Mao Ye. Deep learning approach for morphology classification and particle sizing of industrial methanol-to-olefins (MTO) catalyst [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 1-10.
[2]	Nan Liu, Chunmeng Zhu, Zeng Li, Yunpeng Zhao, Xiaogang Shi, Xingying Lan. Hierarchical framework for predictive maintenance of coking risk in fluid catalytic cracking units: A data and knowledge-driven method [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 35-46.
[3]	Ali Tarik Karagoz, Omar Alqusair, Chao Liu, Jie Li. Advances in conceptual process design: From conventional strategies to AI-assisted methods [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 60-76.
[4]	Tiantong Zhang, Haolin Cheng, Yao Nian, Jinli Zhang, Qingbiao Li, You Han. Application of generative artificial intelligence in catalysis [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 86-95.
[5]	Zhenhua Yu, Guan Wang, Qingchao Jiang, Xuefeng Yan. Process fault root cause diagnosis through state evolution mapping based on temporal unit shapelets [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 96-106.
[6]	Zhenhua Yu, Zongyu Yao, Weijun Wang, Qingchao Jiang, Zhixing Cao. SmdaNet: A hierarchical hard sample mining and domain adaptation neural network for fault diagnosis in industrial process [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 146-157.
[7]	Raúl Díaz, Hongliang Xin. Knowledge graphs in heterogeneous catalysis: Recent advances and future opportunities [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 179-189.
[8]	Xiaodong Hong, Yudong Shen, Zuwei Liao, Yongrong Yang. Machine-learning-assisted high-throughput computational screening of the n-hexane cracking initiator [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 190-200.
[9]	Haijun Feng, Li Jiajia, Zhou Jian. Prediction of ionic liquid toxicity by interpretable machine learning [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 201-210.
[10]	Yuan Tian, Honghua Zhang, Yueyang Qiao, Han Yang, Yanrong Liu, Xiaoyan Ji. Intelligent prediction of ionic liquids and deep eutectic solvents by machine learning [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 227-243.
[11]	Yuan Wang, Mengyue Chen, Jingwei Tian, Weidong Zhang, Dahuan Liu. A data-driven predictive model for solubility: A case study of the NaCl-Na₂SO₄-H₂O system [J]. Chinese Journal of Chemical Engineering, 2025, 84(8): 254-265.
[12]	Mengting Chen, Minjie Zhu, Tingyu Zhou, Qifeng Zhong, Meihua Zhang, Yingxin Liu, Zuojun Wei. Enhanced activity and stability of SAPO-5 zeolite supported RuMn catalyst for aqueous-phase selective hydrodeoxygenation of guaiacol to cyclohexanol [J]. Chinese Journal of Chemical Engineering, 2025, 81(5): 200-207.
[13]	Zhenhui Lv, Jianan Li, Tao Yang, Yibao Li, Chong Peng. Effect of carbon modifications on the performance of hydrogenation catalysts [J]. Chinese Journal of Chemical Engineering, 2025, 81(5): 270-276.
[14]	Xiangli Liu, Yiqing Zeng, Jiahao Chen, Zhaoxiang Zhong, Weihong Xing. Research progress on the monolithic catalyst for hydrogenation of CO₂ to methane [J]. Chinese Journal of Chemical Engineering, 2025, 80(4): 184-197.
[15]	Wenbo Li, Xinyao Fu, Weiming Zhai, Xingyang Huang, Wenbin Chen, Chen Zhang, Wei Zhang, Cuiqing Li, Yong Luo, Feng Liu, Mingfeng Li. Hydrogenation kinetic of alkenes and aromatics over NiMo hydrotreatment catalysts [J]. Chinese Journal of Chemical Engineering, 2025, 79(3): 11-22.