SCI和EI收录∣中国化工学会会刊

Chinese Journal of Chemical Engineering ›› 2018, Vol. 26 ›› Issue (12): 2562-2572.DOI: 10.1016/j.cjche.2018.09.021

• Process Systems Engineering and Process Safety • 上一篇    下一篇

Application of convolutional neural networks to large-scale naphtha pyrolysis kinetic modeling

Feng Hua1,2, Zhou Fang1, Tong Qiu1,2   

  1. 1 Department of Chemical Engineering, Tsinghua University, Beijing 100084, China;
    2 Beijing Key Laboratory of Industrial Big Data System and Application, Beijing 100084, China
  • 收稿日期:2018-05-31 修回日期:2018-09-18 出版日期:2018-12-28 发布日期:2019-01-09
  • 通讯作者: Tong Qiu
  • 基金资助:

    Supported by the National Natural Science Foundation of China (U1462206).

Application of convolutional neural networks to large-scale naphtha pyrolysis kinetic modeling

Feng Hua1,2, Zhou Fang1, Tong Qiu1,2   

  1. 1 Department of Chemical Engineering, Tsinghua University, Beijing 100084, China;
    2 Beijing Key Laboratory of Industrial Big Data System and Application, Beijing 100084, China
  • Received:2018-05-31 Revised:2018-09-18 Online:2018-12-28 Published:2019-01-09
  • Contact: Tong Qiu
  • Supported by:

    Supported by the National Natural Science Foundation of China (U1462206).

摘要: System design and optimization problems require large-scale chemical kinetic models. Pure kinetic models of naphtha pyrolysis need to solve a complete set of stiff ODEs and is therefore too computational expensive. On the other hand, artificial neural networks that completely neglect the topology of the reaction networks often have poor generalization. In this paper, a framework is proposed for learning local representations from largescale chemical reaction networks. At first, the features of naphtha pyrolysis reactions are extracted by applying complex network characterization methods. The selected features are then used as inputs in convolutional architectures. Different CNN models are established and compared to optimize the neural network structure. After the pre-training and fine-tuning step, the ultimate CNN model reduces the computational cost of the previous kinetic model by over 300 times and predicts the yields of main products with the average error of less than 3%. The obtained results demonstrate the high efficiency of the proposed framework.

关键词: Convolutional neural network, Network motif, Naphtha pyrolysis, Kinetic modeling

Abstract: System design and optimization problems require large-scale chemical kinetic models. Pure kinetic models of naphtha pyrolysis need to solve a complete set of stiff ODEs and is therefore too computational expensive. On the other hand, artificial neural networks that completely neglect the topology of the reaction networks often have poor generalization. In this paper, a framework is proposed for learning local representations from largescale chemical reaction networks. At first, the features of naphtha pyrolysis reactions are extracted by applying complex network characterization methods. The selected features are then used as inputs in convolutional architectures. Different CNN models are established and compared to optimize the neural network structure. After the pre-training and fine-tuning step, the ultimate CNN model reduces the computational cost of the previous kinetic model by over 300 times and predicts the yields of main products with the average error of less than 3%. The obtained results demonstrate the high efficiency of the proposed framework.

Key words: Convolutional neural network, Network motif, Naphtha pyrolysis, Kinetic modeling