SCI和EI收录∣中国化工学会会刊

中国化学工程学报 ›› 2020, Vol. 28 ›› Issue (7): 1832-1839.DOI: 10.1016/j.cjche.2020.01.017

• Catalysis, Kinetics and Reaction Engineering • 上一篇    下一篇

Application of machine learning to process simulation of n-pentane cracking to produce ethylene and propene

Weijun Zhu1, Xingwang Liu1, Xu Hou1, Jiayao Hu2, Zhenheng Diao1   

  1. 1 School of Chemical Engineering, Changchun University of Technology, Changchun 130012, China;
    2 School of Mathematics and Statistics, Changchun University of Technology, Changchun 130012, China
  • 收稿日期:2019-11-28 修回日期:2020-01-16 出版日期:2020-07-28 发布日期:2020-08-31
  • 通讯作者: Xu Hou
  • 基金资助:
    The authors gratefully acknowledged for the financial support from the National Natural Science Foundation of China (Grant No. 21908010), the Education Department of Jilin Province (Grant No. JJKH20191314KJ), and Changchun University of Technology.

Application of machine learning to process simulation of n-pentane cracking to produce ethylene and propene

Weijun Zhu1, Xingwang Liu1, Xu Hou1, Jiayao Hu2, Zhenheng Diao1   

  1. 1 School of Chemical Engineering, Changchun University of Technology, Changchun 130012, China;
    2 School of Mathematics and Statistics, Changchun University of Technology, Changchun 130012, China
  • Received:2019-11-28 Revised:2020-01-16 Online:2020-07-28 Published:2020-08-31
  • Contact: Xu Hou
  • Supported by:
    The authors gratefully acknowledged for the financial support from the National Natural Science Foundation of China (Grant No. 21908010), the Education Department of Jilin Province (Grant No. JJKH20191314KJ), and Changchun University of Technology.

摘要: Modeling light olefin production was one of the main concerns in chemical engineering field. In this paper, machine learning model based on artificial neural networks (ANN) was established to describe the effects of temperature and catalyst on ethylene and propene formation in n-pentane cracking. The establishment procedure included data pretreatment, model design, training process and testing process, and the mean square error (MSE) and regression coefficient (R2) indexes were employed to evaluate model performance. It was found that the learning algorithm and ANN topology affected the calculation accuracy. GD24223, CGB2423, and LM24223 models were established by optimally matching the learning algorithm with ANN topology, and achieved excellent calculation accuracy. Furthermore, the stability of GD24223, CGB2423 and LM24223 models was investigated by gradually decreasing training data and simultaneously transforming data distribution. Compared with GD24223 and LM24223 models, CGB2423 model was more stable against the variations of training data, and the MSE values were always maintained at the magnitude of 10-3-10-4, confirming its applicability for simulating light olefin production in n-pentane cracking.

关键词: Machine learning, ANN, Calculation accuracy, Light olefins, n-Pentane cracking

Abstract: Modeling light olefin production was one of the main concerns in chemical engineering field. In this paper, machine learning model based on artificial neural networks (ANN) was established to describe the effects of temperature and catalyst on ethylene and propene formation in n-pentane cracking. The establishment procedure included data pretreatment, model design, training process and testing process, and the mean square error (MSE) and regression coefficient (R2) indexes were employed to evaluate model performance. It was found that the learning algorithm and ANN topology affected the calculation accuracy. GD24223, CGB2423, and LM24223 models were established by optimally matching the learning algorithm with ANN topology, and achieved excellent calculation accuracy. Furthermore, the stability of GD24223, CGB2423 and LM24223 models was investigated by gradually decreasing training data and simultaneously transforming data distribution. Compared with GD24223 and LM24223 models, CGB2423 model was more stable against the variations of training data, and the MSE values were always maintained at the magnitude of 10-3-10-4, confirming its applicability for simulating light olefin production in n-pentane cracking.

Key words: Machine learning, ANN, Calculation accuracy, Light olefins, n-Pentane cracking