EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transient Thermal Response and Simulation-Driven Machine Learning Prediction for Temperature in a Petroleum Coke Vertical Shaft Calciner

Longxin Lai, Jinlong Zhong, Jing Li iD, Jindi Huang iD

Materials · 29.10.2026 · 19 (21) · 4569

DOI: 10.3390/ma19214569 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 29.10.2026. Verfasst von Longxin Lai und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Metallurgical Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangxi Provincial Natural Science Foundation of China, National Natural Science Foundation of China, Jiangxi University of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transient temperature evolution in a petroleum coke vertical shaft calciner (VSC) helps assess responses to operating disturbances, but transient multiphysics simulations are costly. A transient two-dimensional multiphysics model representing one pot and the flues on one side of a 24-pot, eight-layer co-current VSC, with prescribed flue temperatures, was developed to investigate step changes in flue temperature and per-pot discharge rate. Raising the upper-flue temperature by 200 K extended the high-temperature calcination zone from 1.3 to 1.9 m and shifted it upward. Increasing the discharge rate from 95 to 115 kg/h shortened this zone from 1.3 to 0.3 m and shifted it downward. The furnace wall approached a quasi-steady state within 10 h, whereas the coke bed required up to 40 h. Using 4.59 × 105 numerically generated temperature values from 510 pot-centerline locations under nine flue-temperature disturbance conditions, a Temporal Convolutional Network–Bidirectional Long Short-Term Memory–Convolutional Neural Network–Attention (TCLCA) surrogate model was developed. TCLCA achieved an R2 of 0.997 in recursive prediction while reducing computational time by approximately 94%. The framework enables rapid prediction of simulated centerline temperature evolution.

Schlagwörter

Stichwörter der Autor:innen

machine learningpetroleum cokesimulationtransient temperaturevertical shaft calciner

Autor:innen und Institutionen

  • School of Metallurgical Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China.
  • Jiangxi Provincial Key Laboratory of High-Performance Steel and Iron Alloy Materials, Jiangxi University of Science and Technology, Ganzhou 341000, China.
  • Jiangxi Provincial Center for Interdisciplinary Studies in Future-oriented Materials, Jiangxi University of Science and Technology, Ganzhou 341000, China.

ORCID-Profile: Jing Li, Jindi Huang

Förderung

  • Jiangxi Provincial Natural Science Foundation of China
  • National Natural Science Foundation of China
  • Jiangxi University of Science and Technology
  • the Jiangxi Provincial Key Laboratory of High-Performance Steel and Iron Alloy Materials
  • Jiangxi Provincial Key Laboratory of High-Performance Steel and Iron Alloy Materials
  • Pioneer Research Program of Jiangxi Provincial Center

Zitieren

APA

Lai, L., Zhong, J., Li, J., & Huang, J. (2026). Transient Thermal Response and Simulation-Driven Machine Learning Prediction for Temperature in a Petroleum Coke Vertical Shaft Calciner. Materials, 19(21), 4569. https://doi.org/10.3390/ma19214569

Vancouver

Lai L, Zhong J, Li J, Huang J. Transient Thermal Response and Simulation-Driven Machine Learning Prediction for Temperature in a Petroleum Coke Vertical Shaft Calciner. Materials. 2026;19(21):4569. doi:10.3390/ma19214569

BibTeX
@article{Lai2026,
  author = {Lai, Longxin and Zhong, Jinlong and Li, Jing and Huang, Jindi},
  title = {Transient Thermal Response and Simulation-Driven Machine Learning Prediction for Temperature in a Petroleum Coke Vertical Shaft Calciner},
  journal = {Materials},
  year = {2026},
  volume = {19},
  number = {21},
  pages = {4569},
  doi = {10.3390/ma19214569}
}
Kostenlos starten →