Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Automation and Machine Learning
  4. Vol 6, Issue 1, 2025

Over-warning of Coal Spontaneous Combustion Risk Based on the Transformer Model

Download as PDF

DOI: 10.23977/autml.2025.060104 | Downloads: 8 | Views: 202

Author(s)

Jidong Yao 1, Yilong Xiao 1, Ruiyuan Su 1, Wenhao Li 1, Jianxin Pang 1, Chao Jiang 1

Affiliation(s)

1 College of Artificial Intelligence, North China University of Science and Technology, Tangshan, China

Corresponding Author

Jidong Yao

ABSTRACT

In order to capture the information of different locations in the space more accurately, solve the problem of long-time prediction and parallel computation, and realise the over-warning of coal mine safety, we propose the over-warning method of coal spontaneous combustion risk based on the Transformer model. Firstly, the median filtering method and Lagrange interpolation method are used to detect the outliers, expand the data and fill the missing values. Then the unique self-attention mechanism of Transformer is used for feature extraction and trend prediction of the time series data; finally, the Transformer model is compared with LSTM and RNN by adjusting the size and step size of the sliding window. The experimental results show that, under certain circumstances, using the Transformer model to predict the CO and O2 concentrations can capture the gas changes very well, and the prediction accuracy of the Transformer is improved compared with the Long Short-Term Memory Neural Network (LSTM) and Recurrent Neural Network (RNN), which can be effectively applied to the coal mine safety early warning, reduce the occurrence of spontaneous combustion accidents, and protect the safety of miners and production stability, guaranteeing the safety of miners and production stability.

KEYWORDS

Transformer Model, Coal Spontaneous Combustion Risk Warning, Time Series Prediction, Coal Mine Safety, Data Preprocessing and Feature Extraction

CITE THIS PAPER

Jidong Yao, Yilong Xiao, Ruiyuan Su, Wenhao Li, Jianxin Pang, Chao Jiang, Over-warning of Coal Spontaneous Combustion Risk Based on the Transformer Model. Automation and Machine Learning (2025) Vol. 6: 31-39. DOI: http://dx.doi.org/10.23977/autml.2025.060104.

REFERENCES

[1] Luo Zhenmin, Zhang Lidong, Song Zeyang. Realisation of multi-step prediction of CO in mining area based on fully connected long and short-term memory network[J]. Journal of Tsinghua University (Natural Science Edition), 2024, 64(06):940-952.DOI:10.16511/j.cnki.qhdxxb.2024.22.011.
[2] Li Yiman. Research on time series prediction of multiple indicators of coal spontaneous combustion in the mining hollow area[D]. North China Institute of Science and Technology, 2023.DOI:10.27861/d.cnki.gnckj.2023.000002.
[3] Mao Yuanhong, Sun Chenchen, Xu Luyu, et al. A review of time series forecasting methods based on deep learning[J]. Microelectronics and Computers, 2023, 40(04):8-17. DOI:10.19304/J.ISSN1000-7180.2022.0725.
[4] Liang Hongtao, Liu Shuo, Du Junwei, et al. A review of research on deep learning applied to timing prediction[J]. Computer Science and Exploration, 2023, 17(06):1285-1300.
[5] Meng Xiangfu, Shi Haoyuan. A review of time-series data prediction methods based on Transformer model[J/OL]. Computer Science and Exploration, 1-24[2024-11-03].
[6] Ye Mi. Transformer-based multi-feature futures price trend prediction [D]. Nanjing: Nanjing University of Finance and Economics, 2023. 
[7] Zhang Shuai, Liu Wenxia, Tang Haoyang, et al. A short-term load forecasting method based on Transformer multi-feature fusion[J/OL][2023-06-07]. Journal of North China Electric Power University (Natural Science Edition):1-9 
[8] Zhou H Y, Zhang S H, Pen G J Q, et al. Informer: Beyond efficient transformerforlong sequencetime- seriesforecasting[C]//Proceedings of the AAAI conference on artificial intelligence. 2021, 35(12): 1 1 106-1 1 1 1 5.
[9] Geng Xinyue, Hu Changhua, Zheng Jianfei, et al. Transformer-based residual life prediction of lithium batteries in dual time scales[J]. Space Control Technology and Applications, 2023, 49(4): 119-126. 
[10] Wang Yiwen, Lai Jianjun, Qu Zaipeng. Research on short-term blood glucose prediction method based on Transformer[J]. Journal of China University of Weights and Measures, 2023, 34(3): 372-378. 
[11] Tian Sheng, Hu Xiao. Vehicle trajectory prediction based on Transformer model[J]. Journal of Guangxi Normal University (Natural Science Edition).2024 , 42 (03)
[12] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information pro-cessing systems, 2017, 30:5998-6008. 
[13] Li S Y, Jin X Y, Xuan Y, et al. Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting [C]. NeurIPS 2019: 5244-5254.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 3076
Visits: 127914

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.