Machine-learning-assisted high-throughput computational screening of the n-hexane cracking initiator

doi:10.1016/j.cjche.2025.07.002

中国化学工程学报 ›› 2025, Vol. 84 ›› Issue (8): 190-200.DOI: 10.1016/j.cjche.2025.07.002

• Full Length Article • 上一篇下一篇

Machine-learning-assisted high-throughput computational screening of the n-hexane cracking initiator

Xiaodong Hong^1,2, Yudong Shen¹, Zuwei Liao¹, Yongrong Yang¹

1. State Key Laboratory of Chemical Engineering, College of Chemical and Biological Engineering, Zhejiang University, Hangzhou 310027, China;
2. Engineering Research Center of Functional Materials Intelligent Manufacturing of Zhejiang Province, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 311215, China

收稿日期:2025-01-27 修回日期:2025-07-13 接受日期:2025-07-17 出版日期:2025-08-28 发布日期:2025-07-25
通讯作者: Zuwei Liao,E-mail:liaozw@zju.edu.cn
基金资助:
The financial support provided by the Project of the National Natural Science Foundation of China (22308314, U22A20415), the Natural Science Foundation of Zhejiang Province (LQ24B060001), the "Pioneer" and "Leading Goose" Research & Development Program of Zhejiang (2022C01SA442617), and the SINOPEC Technology Development Project (224244) is gratefully acknowledged. The authors would also like to thank the AI + High Performance Computing Center of ZJU-ICI.

Machine-learning-assisted high-throughput computational screening of the n-hexane cracking initiator

Xiaodong Hong^1,2, Yudong Shen¹, Zuwei Liao¹, Yongrong Yang¹

1. State Key Laboratory of Chemical Engineering, College of Chemical and Biological Engineering, Zhejiang University, Hangzhou 310027, China;
2. Engineering Research Center of Functional Materials Intelligent Manufacturing of Zhejiang Province, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 311215, China

Received:2025-01-27 Revised:2025-07-13 Accepted:2025-07-17 Online:2025-08-28 Published:2025-07-25
Contact: Zuwei Liao,E-mail:liaozw@zju.edu.cn
Supported by:
The financial support provided by the Project of the National Natural Science Foundation of China (22308314, U22A20415), the Natural Science Foundation of Zhejiang Province (LQ24B060001), the "Pioneer" and "Leading Goose" Research & Development Program of Zhejiang (2022C01SA442617), and the SINOPEC Technology Development Project (224244) is gratefully acknowledged. The authors would also like to thank the AI + High Performance Computing Center of ZJU-ICI.

摘要/Abstract

摘要： This study leverages machine learning to perform high-throughput computational screening of n-hexane cracking initiators. Artificial neural networks are applied to predict the chemical performance of initiators, using simulated pyrolysis data as the training dataset. Various feature extraction methods are utilized, and five neural network architectures are developed to predict the co-cracking product distribution based on molecular structures. High-throughput screening of 12946 molecules outside the training dataset identifies the top 10 initiators for each target product—ethylene, propylene, and butadiene. The relative error between predicted and simulated values is less than 7%. Additionally, reaction pathway analysis elucidates the mechanisms by which initiators influence the distribution of cracking products. The proposed framework provides a practical and efficient approach for the rapid identification and evaluation of high-performance cracking initiators.

关键词: Cracking initiator, Properties prediction, Neural network, High-throughput, Computer simulation, Radical

Abstract: This study leverages machine learning to perform high-throughput computational screening of n-hexane cracking initiators. Artificial neural networks are applied to predict the chemical performance of initiators, using simulated pyrolysis data as the training dataset. Various feature extraction methods are utilized, and five neural network architectures are developed to predict the co-cracking product distribution based on molecular structures. High-throughput screening of 12946 molecules outside the training dataset identifies the top 10 initiators for each target product—ethylene, propylene, and butadiene. The relative error between predicted and simulated values is less than 7%. Additionally, reaction pathway analysis elucidates the mechanisms by which initiators influence the distribution of cracking products. The proposed framework provides a practical and efficient approach for the rapid identification and evaluation of high-performance cracking initiators.

Key words: Cracking initiator, Properties prediction, Neural network, High-throughput, Computer simulation, Radical

Xiaodong Hong, Yudong Shen, Zuwei Liao, Yongrong Yang. Machine-learning-assisted high-throughput computational screening of the n-hexane cracking initiator[J]. 中国化学工程学报, 2025, 84(8): 190-200.

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.

参考文献

[1] N.E. Jackson, M.A. Webb, J.J. de Pablo, Recent advances in machine learning towards multiscale soft materials design, Curr. Opin. Chem. Eng. 23 (2019) 106-114.
[2] Y. Liu, T.L. Zhao, W.W. Ju, S.Q. Shi, Materials discovery and design using machine learning, J. Materiomics 3 (3) (2017) 159-177.
[3] K. Hansen, F. Biegler, R. Ramakrishnan, W. Pronobis, O.A. von Lilienfeld, K.R. Muller, A. Tkatchenko, Machine learning predictions of molecular properties: accurate many-body potentials and nonlocality in chemical space, J. Phys. Chem. Lett. 6 (12) (2015) 2326-2331.
[4] Z. Zhang, K. Friedrich, Artificial neural networks applied to polymer composites: a review, Compos. Sci. Technol. 63 (14) (2003) 2029-2044.
[5] W.Q. Liu, C.Z. Cao, Artificial neural network prediction of glass transition temperature of polymers, Colloid Polym. Sci. 287 (7) (2009) 811-818.
[6] F. Hou, Z.Y. Wu, Z. Hu, Z.R. Xiao, L. Wang, X.W. Zhang, G.Z. Li, Comparison study on the prediction of multiple molecular properties by various neural networks, J. Phys. Chem. A 122 (46) (2018) 9128-9134.
[7] G.A. Schwartz, Prediction of rheometric properties of compounds by using artificial neural networks, Rubber Chem. Technol. 74 (1) (2001) 116-123.
[8] Y.F. Li, H.L. Minh, M.S. Cao, X.D. Qian, M. Abdel Wahab, An integrated surrogate model-driven and improved termite life cycle optimizer for damage identification in dams, Mech. Syst. Signal Process. 208 (2024) 110986.
[9] L. Nguyen-Ngoc, Q. Nguyen-Huu, G. De Roeck, T. Bui-Tien, M. Abdel-Wahab, Deep neural network and evolved optimization algorithm for damage assessment in a truss bridge, Mathematics 12 (15) (2024) 2300.
[10] Y.J. Guo, C. Wang, S.T. Han, G. Kosec, Y.L. Zhou, L.H. Wang, M. Abdel Wahab, A deep neural network model for parameter identification in deep drawing metal forming process, J. Manuf. Process. 133 (2025) 380-394.
[11] D.Q. Nguyen, K.Q. Tran, T.D. Le, M. Abdel Wahab, H. Nguyen-Xuan, A data-driven uncertainty quantification framework in probabilistic bio-inspired porous materials (Material-UQ): an investigation for RotTMPS plates, Comput. Meth. Appl. Mech. Eng. 435 (2025) 117603.
[12] M. Monai, M. Gambino, S. Wannakao, B.M. Weckhuysen, Propane to olefins tandem catalysis: a selective route towards light olefins production, Chem. Soc. Rev. 50 (20) (2021) 11503-11529.
[13] Z. Gholami, F. Gholami, Z. Tisler, M. Vakili, A review on the production of light olefins using steam cracking of hydrocarbons, Energies 14 (23) (2021) 1-24.
[14] G.S. Guo, Y. Ren, Y.B. Yu, Z.W. Liao, B.B. Jiang, Y. Yang, G.J. He, W.J. Fang, J.D. Wang, Y.R. Yang, Hyperbranched poly(amidoamine) as an efficient macroinitiator for steam cracking of naphtha, Fuel 299 (2021) 120907.
[15] J. Chang, Y. Fu, Y. Shibata, M. Yoshimoto, K. Fujimoto, N. Tsubaki, Promotional effect of oxidation pretreatment on hydro-thermal cracking of Canadian oil sand bitumen, Fuel 84 (12-13) (2005) 1661-1663.
[16] J. Chang, L. Fan, K. Fujimoto, Enhancement effect of free radical initiator on hydro-thermal cracking of heavy oil and model compound, Energy Fuels 13 (5) (1999) 1107-1108.
[17] D.T. Wickham, J.R. Engel, S. Rooney, B.D. Hitch, Additives to improve fuel heat sink capacity in air/fuel heat exchangers, J. Propuls. Power 24 (1) (2008) 55-63.
[18] D. Wickham, J. Engel, B. Hitch, Additives to Increase Fuel Heat Sink Capacity38th AIAA/ASME/SAE/ASEE Joint Propulsion Conference & Exhibit. 07 July 2002 - 10 July 2002, Indianapolis, Indiana. Reston, Virginia: AIAA, 2002: 3872.
[19] D.T. Wickham, J.R. Engel, B.D. Hitch, M.E. Karpuk, Initiators for endothermic fuels, J. Propuls. Power 17 (6) (2001) 1253-1257.
[20] Z. Wang, R.S. Lin, W.J. Fang, G. Li, Y.S. Guo, Z.W. Qin, Triethylamine as an initiator for cracking of heptane, Energy 31 (14) (2006) 2773-2790.
[21] A. Niaei, J. Towfighi, A.R. Khataee, K. Rostamizadeh, The use of ANN and the mathematical model for prediction of the main product yields in the thermal cracking of naphtha, Petrol. Sci. Technol. 25 (8) (2007) 967-982.
[22] M. Sedighi, K. Keyvanloo, J. Towfighi, Modeling of thermal cracking of heavy liquid hydrocarbon: application of kinetic modeling, artificial neural network, and neuro-fuzzy models, Ind. Eng. Chem. Res. 50 (3) (2011) 1536-1547.
[23] Y.K. Jin, J.L. Li, W.L. Du, F. Qian, Multi-objective optimization of pseudo-dynamic operation of naphtha pyrolysis by a surrogate model, Chem. Eng. Technol. 38 (5) (2015) 900-906.
[24] Y.K. Jin, J.L. Li, W.L. Du, F. Qian, Adaptive sampling for surrogate modelling with artificial neural network and its application in an industrial cracking furnace, Can. J. Chem. Eng. 94 (2) (2016) 262-272.
[25] F. Hua, Z. Fang, T. Qiu, Application of convolutional neural networks to large-scale naphtha pyrolysis kinetic modeling, Chin. J. Chem. Eng. 26 (12) (2018) 2562-2572.
[26] F. Hua, Z. Fang, T. Qiu, Modeling ethylene cracking process by learning convolutional neural networks, . 13th International Symposium on Process Systems Engineering (PSE 2018). Elsevier, (2018), pp 41-846.
[27] D. Rogers, M. Hahn, Extended-connectivity fingerprints, J. Chem. Inf. Model. 50 (5) (2010) 742-754.
[28] M. Rupp, A. Tkatchenko, K.R. Muller, O.A. von Lilienfeld, Fast and accurate modeling of molecular atomization energies with machine learning, Phys. Rev. Lett. 108 (5) (2012) 058301.
[29] D.G. Bonchev, Chemical graph theory: introduction and fundamentals, Gordon and Breach Science Publishers, Basel, Switzerland,1994.
[30] A.M. Schweidtmann, J.G. Rittig, A. Konig, M. Grohe, A. Mitsos, M. Dahmen, Graph neural networks for prediction of fuel ignition quality, Energy Fuels 34 (9) (2020) 11395-11407.
[31] G.B. Goh, C. Siegel, A. Vishnu, N. Hodas, N. Baker, How much chemistry does a deep neural network need to know to make accurate predictions? 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). Lake Tahoe, NV, USA. IEEE, (2018) 1340-1349.
[32] G.B. Goh, C. Siegel, A. Vishnu, N.O. Hodas, N. Baker, Chemception: a deep neural network with minimal chemistry knowledge matches the performance of expert-developed QSAR/QSPR models, arXiv E Prints (2017) arXiv1706.06689.
[33] K.T. Schutt, F. Arbabzadah, S. Chmiela, K.R. Muller, A. Tkatchenko, Quantum-chemical insights from deep tensor neural networks, Nat. Commun. 8 (2017) 13890.
[34] J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, G. E. Dahl, Neural message passing for quantum chemistry, [accessed 2024-October-7], https://arxiv.org/abs/1704.01212v2.
[35] Y.D. Shen, Y.L. Mao, X.D. Hong, Y. Yang, Y. Ren, J.D. Wang, Y.R. Yang, A.N. Kay Lup, Z.W. Liao, Time-integrated species flux analysis: a novel method for kinetic reduction and pathway analysis in pyrolysis process, AlChE. J. 70 (10) (2024) e18532.
[36] L. van der Maaten, G. Hinton, Visualizing Data Using T-SNE. Journal of Machine Learning Research 9(2008) 2579-2605.
[37] J. Bergstra, R. Bardenet, Y. Bengio, B. Kegl, Algorithms for hyper-parameter optimization, Proceedings of the 25th International Conference on Neural Information Processing Systems. Granada, Spain. ACM, (2011) 2546-2554.

Machine-learning-assisted high-throughput computational screening of the n-hexane cracking initiator

Machine-learning-assisted high-throughput computational screening of the n-hexane cracking initiator

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[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]. 中国化学工程学报, 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]. 中国化学工程学报, 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]. 中国化学工程学报, 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]. 中国化学工程学报, 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]. 中国化学工程学报, 2025, 84(8): 96-106.
[6]	Xin Wang, Shengxu Jin, Chengwei Cai, Junran Luo, Xiangshuai Tan, Yunfei Guo, Zhao Li, Jinghui Gao, Xinlin He, Litao Niu, Yicun Lin, Wei Zhao, Guangjin Chen, Chun Deng. Two-layer model for the early warning and analysis of condensate water quality abnormalities based on autoencoder and expert knowledge[J]. 中国化学工程学报, 2025, 84(8): 107-116.
[7]	Zhi Ma, Peng Cui, Xu Wang, Lanyu Li, Haoxiang Xu, Adrian Fisher, Daojian Cheng. The integration of artificial intelligence and high-throughput experiments: An innovative driving force in catalyst design[J]. 中国化学工程学报, 2025, 84(8): 117-132.
[8]	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]. 中国化学工程学报, 2025, 84(8): 133-145.
[9]	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]. 中国化学工程学报, 2025, 84(8): 146-157.
[10]	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]. 中国化学工程学报, 2025, 84(8): 254-265.
[11]	Haowei Li, Bingzhu Min, Yaling Gong, Linsheng Li, Xingbao Wang, Yimeng Zhu, Wenying Li. Molecular design of high energy density fuels from coal-to-liquids[J]. 中国化学工程学报, 2025, 84(8): 266-273.
[12]	Daiwen Li, Shoutian Qiu, Gan Liu, Ming Liu, Mingjie Wei, Shipeng Sun, Weihong Xing, Xiaohua Lu, Yong Wang. Coarse-grained molecular dynamics simulations on self-assembly of polystyrene-block-poly(2-vinylpyridine)[J]. 中国化学工程学报, 2025, 83(7): 15-25.
[13]	Zenan Tian, Zhiyu Zhang, Xiang Li, Xinxin Gao, Ziru Ren, Xiaobin Zhang. Evaluation of live Cryo-ECT system for liquid nitrogen-vapor nitrogen flow[J]. 中国化学工程学报, 2025, 82(6): 246-255.
[14]	Meixian Liu, Shuyun Xue, Yajun Zhang, Linjuan Pei, Zhanfeng Zheng. Screening suitable metal ion bridges for the construction of unimpeded dual carrier-transfer channels in carbon nitride photocatalyst[J]. 中国化学工程学报, 2025, 80(4): 70-78.
[15]	Xiaoyu Zhou, Erwei Song, Mingmei Wang, Erqiang Wang. Dynamic temperature control of dividing wall batch distillation with middle vessel based on neural network soft-sensor and fuzzy control[J]. 中国化学工程学报, 2025, 79(3): 200-211.