EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Intelligent Partition-and-Prediction Framework for Ultra-Low-Phosphorus High-Purity Iron: Improved Interpretability and Accuracy

Didi Zhao, Baiqiao Chen, Zemin Chen, Yiliang Liu, Yun Feng, Jingyuan Li

Processes · 29.06.2026 · 14 (13) · 2122

DOI: 10.3390/pr14132122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 29.06.2026. Verfasst von Didi Zhao und 5 weiteren Autor:innen. Die Arbeit nennt 86 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key Research and Development Program of China, the 2024 Shanxi Provincial Major Science and Technology Special Project, the Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ultra-low-phosphorus high-purity iron (ULP-HPFe) is essential for advanced electromagnetic, aerospace, and defense systems, yet stabilizing basic-oxygen-furnace (BOF) dephosphorization remains challenging. To address this instability, we present an intelligent partition-and-prediction framework (iDePP) that first auto-classifies 5102 industrial data records into medium-phosphorus (iDePP-MP), low-phosphorus (iDePP-LP), and ultra-low-phosphorus (iDePP-ULP) subsets, and dedicated ensemble prediction models are then developed for each subset based on representative machine learning algorithms, including random forest (RF), extreme gradient boosting (XGBoost), and neural networks (NNs). Compared with a single global predictor, iDePP reduces the mean absolute error from 0.0018% to 0.0011%, 0.0007%, and 0.0004% for the three classes, respectively, and increases the iDePP-ULP hit rate (HR) to 82.7% within ±6 ppm. Shapley additive explanations (SHAP) and quantitative feature coupling analysis reveal two critical mechanisms governing extreme dephosphorization: limestone-induced thermal penalties and furnace-age effects. Guided by these insights, three consecutive 200-ton BOF industrial trials preliminarily verified the practical feasibility of producing ULP-HPFe, with model plant deviations of approximately 4 ppm, 1 ppm, and 1.5 ppm, respectively. Notably, this work demonstrates the value of automatic domain partitioning combined with subset-specific ensemble learning for complex BOF control, highlighting the potential applicability of iDePP to other data-sparse industrial processes.

Förderung

  • the National Key Research and Development Program of China
  • the 2024 Shanxi Provincial Major Science and Technology Special Project
  • the Fundamental Research Funds for the Central Universities

Zitieren

APA

Zhao, D., Chen, B., Chen, Z., Liu, Y., Feng, Y., & Li, J. (2026). An Intelligent Partition-and-Prediction Framework for Ultra-Low-Phosphorus High-Purity Iron: Improved Interpretability and Accuracy. Processes, 14(13), 2122. https://doi.org/10.3390/pr14132122

Vancouver

Zhao D, Chen B, Chen Z, Liu Y, Feng Y, Li J. An Intelligent Partition-and-Prediction Framework for Ultra-Low-Phosphorus High-Purity Iron: Improved Interpretability and Accuracy. Processes. 2026;14(13):2122. doi:10.3390/pr14132122

BibTeX
@article{Zhao2026,
  author = {Zhao, Didi and Chen, Baiqiao and Chen, Zemin and Liu, Yiliang and Feng, Yun and Li, Jingyuan},
  title = {An Intelligent Partition-and-Prediction Framework for Ultra-Low-Phosphorus High-Purity Iron: Improved Interpretability and Accuracy},
  journal = {Processes},
  year = {2026},
  volume = {14},
  number = {13},
  pages = {2122},
  doi = {10.3390/pr14132122}
}
Kostenlos starten →