EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HPO-Optimized Bidirectional LSTM for Gas Concentration Prediction in Coal Mine Working Faces

Xiaoliang Zheng, Shilong Liu, Lei Zhang

Eng · 01.03.2026 · 7 (3) · 112

DOI: 10.3390/eng7030112 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Eng, online erschienen am 01.03.2026. Verfasst von Xiaoliang Zheng und 2 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China during the 14th Five-Year Plan Period, Joint National-Local Engineering Research Center for Safety and Precise Coal Mining.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

An HPO (Hunter–Prey Optimizer)-optimized Bidirectional LSTM (HPO-BiLSTM) model is introduced to address the challenges in predicting gas concentration within coal mining working faces. This study aims to adaptively adjust the key hyperparameters (such as learning rate and number of hidden layer units) of the BiLSTM network through intelligent optimization algorithms. While the BiLSTM architecture inherently mitigates gradient vanishing and exploding problems through its gating mechanisms, the proposed HPO method focuses on addressing the inefficiency of manual parameter tuning and the risk of trapping in local optima that traditional methods encounter when dealing with nonlinear and non-stationary gas concentration time series. The experiment utilized the actual methane monitoring data from the 15117 working face of Jishazhuang Coal Mine in Jinzhong City, Shanxi Province (with a sampling interval of 2 min). The proposed HPO-BiLSTM model was compared with baseline models such as LSTM, BiLSTM, GA-BiLSTM, and PSO-BiLSTM in terms of performance. This study systematically compares the performance of LSTM, BiLSTM, and BiLSTM models optimized with GA, PSO, and HPO. Results demonstrate that all optimized models outperform the baselines, with HPO-BiLSTM achieving the best overall performance. It attained the lowest RMSE and highest R2 across the training, validation, and test sets, showcasing superior fitting and generalization capabilities. Furthermore, HPO-BiLSTM converged to the lowest loss value (0.00062) in only 15 iterations, demonstrating significantly greater efficiency and stability than both GA-BiLSTM (loss 0.00072, 25 iterations) and PSO-BiLSTM (loss 0.00071, 30 iterations). The experiments confirm that the HPO algorithm effectively configures BiLSTM hyperparameters, mitigates overfitting, and provides a more accurate and robust solution for gas concentration prediction in coal mines.

Förderung

  • National Key R&D Program of China during the 14th Five-Year Plan Period
  • Joint National-Local Engineering Research Center for Safety and Precise Coal Mining

Zitieren

APA

Zheng, X., Liu, S., & Zhang, L. (2026). HPO-Optimized Bidirectional LSTM for Gas Concentration Prediction in Coal Mine Working Faces. Eng, 7(3), 112. https://doi.org/10.3390/eng7030112

Vancouver

Zheng X, Liu S, Zhang L. HPO-Optimized Bidirectional LSTM for Gas Concentration Prediction in Coal Mine Working Faces. Eng. 2026;7(3):112. doi:10.3390/eng7030112

BibTeX
@article{Zheng2026,
  author = {Zheng, Xiaoliang and Liu, Shilong and Zhang, Lei},
  title = {HPO-Optimized Bidirectional LSTM for Gas Concentration Prediction in Coal Mine Working Faces},
  journal = {Eng},
  year = {2026},
  volume = {7},
  number = {3},
  pages = {112},
  doi = {10.3390/eng7030112}
}
Kostenlos starten →