EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Coal and gas outburst prediction based on data augmentation and neuroevolution

Wenbing Shi iD, Ji Huang, Gaoming Yang iD, Shuzhi Su, Shexiang Jiang

PLOS ONE · 2025

DOI: 10.1371/journal.pone.0317461 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2025. Verfasst von Wenbing Shi und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, Anhui, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Coal Mining, Coal. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Research Project of Colleges and Universities in Anhui Province, Anhui Provincial Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Coal and gas outburst (CGO) is a complicated natural disaster in underground coal mine production. In constructing smart mines, predicting CGO risks efficiently and accurately is necessary. This paper proposes a CGO risk prediction method based on data augmentation and a neuroevolution algorithm, denoted as ANEAT. First, sample features are applied to the transfer function using a pointwise intensity transformation to obtain new feature samples. It solves the problems of imbalanced data samples and insufficient diversity. Second, the feature importance score sorting and Sparse PCA dimensionality reduction are performed on the data-augmented samples. It provides the initial genome code for the evolutionary neural network. Finally, an evolutionary neural network for CGO prediction is constructed through population initialization, fitness evaluation, species differentiation, genome mutation, and recombination. The optimal phenotype is obtained in the evolutionary generations. In the experiment, we verify the effectiveness of ANEAT from multiple aspects such as data augmentation effectiveness analysis, deep learning model comparison, swarm intelligence optimization algorithm comparison, and other method comparisons. The results show that the MAE , RMSE , and EVAR indexes of ANEAT on the test set are 0.0816, 0.1322, and 0.8972, respectively. It has the optimal CGO prediction effect. ANEAT realizes the high-precision mapping of feature parameters and outburst risk with a lightweight network architecture, which can be well applied to CGO prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerCoal MiningCoalAlgorithmsHumans

Substanzen

Coal

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, Anhui, China.
  • Fujian Provincial Key Laboratory of Medical Big Data Engineering, Fujian Provincial Hospital, Fuzhou, Fujian, China.
  • Anhui Key Laboratory of Mine Intelligent Equipment and Technology, Anhui University of Science and Technology, Huainan, Anhui, China.

ORCID-Profile: Wenbing Shi, Gaoming Yang

Förderung

  • National Natural Science Foundation of China
  • Natural Science Research Project of Colleges and Universities in Anhui Province
  • Anhui Provincial Natural Science Foundation
  • The Open Fund of Fujian Provincial Key Laboratory of Medical Big Data Engineering
  • The Open Fund of Anhui Key Laboratory of Mine Intelligent Equipment and Technology

Zitieren

APA

Shi, W., Huang, J., Yang, G., Su, S., & Jiang, S. (2025). Coal and gas outburst prediction based on data augmentation and neuroevolution. PLOS ONE. https://doi.org/10.1371/journal.pone.0317461

Vancouver

Shi W, Huang J, Yang G, Su S, Jiang S. Coal and gas outburst prediction based on data augmentation and neuroevolution. PLOS ONE. 2025. doi:10.1371/journal.pone.0317461

BibTeX
@article{Shi2025,
  author = {Shi, Wenbing and Huang, Ji and Yang, Gaoming and Su, Shuzhi and Jiang, Shexiang},
  title = {Coal and gas outburst prediction based on data augmentation and neuroevolution},
  journal = {PLOS ONE},
  year = {2025},
  doi = {10.1371/journal.pone.0317461}
}
Kostenlos starten →