SCI和EI收录∣中国化工学会会刊

Chinese Journal of Chemical Engineering ›› 2020, Vol. 28 ›› Issue (9): 2343-2357.DOI: 10.1016/j.cjche.2020.06.014

• Process Systems Engineering and Process Safety • Previous Articles     Next Articles

Gas leakage recognition for CO2 geological sequestration based on the time series neural network

Denglong Ma1, Jianmin Gao1, Zhiyong Gao1, Hongquan Jiang1, Zaoxiao Zhang2, Juntai Xie1   

  1. 1 School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China;
    2 School of Chemical Engineering and Technology, Xi'an Jiaotong University, Xi'an 710049, China
  • Received:2020-01-16 Revised:2020-05-06 Online:2020-10-21 Published:2020-09-28
  • Contact: Denglong Ma
  • Supported by:
    Financial support was provided by the National Natural Science Foundation of China (21808181), China Postdoctoral Science Foundation (2019M653651), Shaanxi Provincial Science and Technology Department (2017ZDXM-GY-115), Basic Research Project of Natural Science in Shaanxi Province (2020JM-021).

Gas leakage recognition for CO2 geological sequestration based on the time series neural network

Denglong Ma1, Jianmin Gao1, Zhiyong Gao1, Hongquan Jiang1, Zaoxiao Zhang2, Juntai Xie1   

  1. 1 School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China;
    2 School of Chemical Engineering and Technology, Xi'an Jiaotong University, Xi'an 710049, China
  • 通讯作者: Denglong Ma
  • 基金资助:
    Financial support was provided by the National Natural Science Foundation of China (21808181), China Postdoctoral Science Foundation (2019M653651), Shaanxi Provincial Science and Technology Department (2017ZDXM-GY-115), Basic Research Project of Natural Science in Shaanxi Province (2020JM-021).

Abstract: The leakage of stored and transported CO2 is a risk for geological sequestration technology. One of the most challenging problems is to recognize and determine CO2 leakage signal in the complex atmosphere background. In this work, a time series model was proposed to forecast the atmospheric CO2 variation and the approximation error of the model was utilized to recognize the leakage. First, the fitting neural network trained with recently past CO2 data was applied to predict the daily atmospheric CO2. Further, the recurrent nonlinear autoregressive with exogenous input (NARX) model was adopted to get more accurate prediction. Compared with fitting neural network, the approximation errors of NARX have a clearer baseline, and the abnormal leakage signal can be seized more easily even in small release cases. Hence, the fitting approximation of time series prediction model is a potential excellent method to capture atmospheric abnormal signal for CO2 storage and transportation technologies.

Key words: Leakage identification, Process safety, Gas leakage, Monitoring carbon sequestration, CO2 storage

摘要: The leakage of stored and transported CO2 is a risk for geological sequestration technology. One of the most challenging problems is to recognize and determine CO2 leakage signal in the complex atmosphere background. In this work, a time series model was proposed to forecast the atmospheric CO2 variation and the approximation error of the model was utilized to recognize the leakage. First, the fitting neural network trained with recently past CO2 data was applied to predict the daily atmospheric CO2. Further, the recurrent nonlinear autoregressive with exogenous input (NARX) model was adopted to get more accurate prediction. Compared with fitting neural network, the approximation errors of NARX have a clearer baseline, and the abnormal leakage signal can be seized more easily even in small release cases. Hence, the fitting approximation of time series prediction model is a potential excellent method to capture atmospheric abnormal signal for CO2 storage and transportation technologies.

关键词: Leakage identification, Process safety, Gas leakage, Monitoring carbon sequestration, CO2 storage