Scholarlink

<p>The heterogeneity of macerals represents a key challenge to accurately evaluating the hydrocarbon generation potential of coal. Conventional methods often overlook these differences, leading to biased understanding of its hydrocarbon generation characteristics. Therefore, this study integrates maceral identification, thermal simulation experiments, and machine learning algorithms to develop the extreme gradient boosting (XGBoost) prediction models for the yields of gaseous and liquid hydrocarbons. This approach enables enabling quantitative characterization of the hydrocarbon generation behavior of different macerals and identification of their primary controlling factors of coal in Xishanyao (<i>J</i><sub>2</sub><i>x</i>) Formation of Taibei Sag, China. The results indicate that the correlation coefficients of the prediction models for gaseous and liquid hydrocarbon yields are 0.98 and 0.78, respectively, and the difference in prediction accuracy between the two productions arises from differences in the primary controlling factors of hydrocarbon generation. SHAP and ANOVA analyses indicate that temperature is the primary controlling factor for gaseous hydrocarbon generation, whereas liquid hydrocarbon yields are synergistically controlled by temperature and macerals type. Among the macerals, sporinite is the favorable oil-prone component, while cutinite is characterized by “early oil and late gas.” Collotelinite is the principal gas-prone component, whereas collodetrinite and corpogelinite display relatively balanced potential for oil and gas. The differentiated hydrocarbon generation characteristics of the various macerals is essentially governed by differences in their molecular structures. The aliphatic chain structures primarily control oil generation, aromaticity governs gas generation, and bond types determine the distribution of the hydrocarbon generation window. Based on the above results, the study further delineates three types of favorable hydrocarbon-generating zones, namely Class I and Class II oil-gas co-generation zones and Class II oil-generating zones.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Data-driven intelligent analysis of hydrocarbon generation kinetics and differential characteristics during pyrolysis of coal macerals

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月15日

查看全文
  • Yijie Wen,
  • Zongsen Yao,
  • Fan Yang,
  • Yi Cui,
  • Shouqing Yan,
  • Bin Yu,
  • Zijian Zhang,
  • Shu Tao

摘要

The heterogeneity of macerals represents a key challenge to accurately evaluating the hydrocarbon generation potential of coal. Conventional methods often overlook these differences, leading to biased understanding of its hydrocarbon generation characteristics. Therefore, this study integrates maceral identification, thermal simulation experiments, and machine learning algorithms to develop the extreme gradient boosting (XGBoost) prediction models for the yields of gaseous and liquid hydrocarbons. This approach enables enabling quantitative characterization of the hydrocarbon generation behavior of different macerals and identification of their primary controlling factors of coal in Xishanyao (J2x) Formation of Taibei Sag, China. The results indicate that the correlation coefficients of the prediction models for gaseous and liquid hydrocarbon yields are 0.98 and 0.78, respectively, and the difference in prediction accuracy between the two productions arises from differences in the primary controlling factors of hydrocarbon generation. SHAP and ANOVA analyses indicate that temperature is the primary controlling factor for gaseous hydrocarbon generation, whereas liquid hydrocarbon yields are synergistically controlled by temperature and macerals type. Among the macerals, sporinite is the favorable oil-prone component, while cutinite is characterized by “early oil and late gas.” Collotelinite is the principal gas-prone component, whereas collodetrinite and corpogelinite display relatively balanced potential for oil and gas. The differentiated hydrocarbon generation characteristics of the various macerals is essentially governed by differences in their molecular structures. The aliphatic chain structures primarily control oil generation, aromaticity governs gas generation, and bond types determine the distribution of the hydrocarbon generation window. Based on the above results, the study further delineates three types of favorable hydrocarbon-generating zones, namely Class I and Class II oil-gas co-generation zones and Class II oil-generating zones.