这是indexloc提供的服务，不要输入任何密码
Skip to main content
Springer Nature Link
Log in

Gas concentration prediction based on ED-SLSTM model under the framework of Trend Prediction-Time Point Prediction

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

In order to solve the problems of low prediction accuracy and inability to achieve long-term prediction in traditional coal mine gas concentration prediction, this paper proposes a new gas concentration prediction framework based on the problem of independent gate units of traditional Long Short Time Memory (LSTM) neural network—“Trend Prediction-Time Point Prediction” (TP-TPP) structure, and it is the first time to add a selection gate mechanism to the LSTM model to construct the Select LSTM (SLSTM) model, which is in line with the actual production pattern of coal mines. Firstly, the data of gas multi-parameter time series are processed, and then the input data features under the framework of trend prediction are reconstructed. Then the modified Snake Optimizer (SO) algorithm is used to simplify the parameter adjustment process of neural network. Here the Encoder–Decoder–SLSTM (ED-SLSTM) model is compared with LightGBM, LSTM, Bi-LSTM, LSTM-Attention and CEEMDAN-LSTM models under the framework of TP-TPP, respectively. The performance of each evaluation index in ED-SLSTM is closer to the real value than them of other models. The results show that ED-SLSTM has higher prediction accuracy and better prediction effect.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+
from $39.99 /Month
  • Starting from 10 chapters or articles per month
  • Access and download chapters and articles from more than 300k books and 2,500 journals
  • Cancel anytime
View plans

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, books and news in related subjects, suggested using machine learning.

Data availability

Since we signed a confidentiality agreement when using the data in the manuscript, we are very sorry that we cannot provide the complete data used in the paper.

References

  1. Cheng L, Li L (2022) Prediction of gas concentration evolution with evolutionary attention-based temporal graph convolutional network. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2022.116944

    Article  Google Scholar 

  2. Liu F, Guo L, Zhao L (2022) Double carbon under the background of coal safety interval and green low carbon technology path. J Coal 47(01):1–15. https://doi.org/10.13225/j.carolcarrollnkiJCCS.Yg22.0016

    Article  Google Scholar 

  3. Zhang Z, Zhu Q, Li Q, Liu Y, Zhang E, Zhao Q, Qin X (2021) Based on Keras length when the memory network of the mine gas concentration prediction research. J Saf Environ Eng 28(01):61–67. https://doi.org/10.1357/j.carolcarrollnki.issn1671-1556.2021.01.010

    Article  Google Scholar 

  4. Jia P, Zhang Z, Liang R, Liu H, Miao Y (2021) Based on PSO–CNN–aBiGRU gas concentration prediction method. J Res Dev Min 9(12):76–81. https://doi.org/10.13827/j.carolcarrollnkikyyk.2021.12.002

    Article  Google Scholar 

  5. Liu F (2021) Study on coal mine gas concentration prediction based on PCA-RVM. Inner Mong Coal Econ 23:70–72. https://doi.org/10.13487/j.carolcarrollnkiimce.021434

    Article  Google Scholar 

  6. Wang Y, Wang S, Wang Z, Ren R (2021) Multi-parameter gas concentration prediction model based on improved locust algorithm optimized long term memory neural network. Chin J Sens Technol 34(09):1196–1203

    Google Scholar 

  7. Lai X, Xia Y, Zheng W, Cui J, Yanqing Wu, Shi Y (2021) Improved grey gas concentration sequence prediction based on ensemble learning. China Saf Prod Sci Technol 17(07):16–21

    Google Scholar 

  8. Ran Q, Wu H, Ding L, Li X, Lai Y, Yang Y, Yang L, Lai X (2022) Study on gas concentration sequence prediction based on A-GRU. Softw Guide 21(05):38–42

    Google Scholar 

  9. Wen T, Chen S (2023) Time series gas concentration prediction model based on IAPSO-Holt-TCN. China Saf Prod Sci Technol 19(07):57–62

    Google Scholar 

  10. Fan J, Huang Y, Yan Z et al (2022) ARIMA-driven by a combination of SVM model of gas concentration prediction research. J Ind Autom 13(9):134–139

    Google Scholar 

  11. Qin J, Ge S, Long F et al (2023) Spatial and temporal distribution prediction of gas concentration based on GCN-GRU. Ind Mine Autom 49(05):82–89+111

    Google Scholar 

  12. Xu Y, Bai J, Wang Y et al (2023) Gas emission prediction model based on CEEMDAN-DA-GRU. J Sens Technol 36(03):441–448

    Google Scholar 

  13. Lyu P, Chen N (2020) LSTM based encoder-decoder for short-term predictions of gas concentration using multi-sensor fusion. Process Saf Environ Prot 137:93–105. https://doi.org/10.1016/j.psep.2020.02.021

    Article  Google Scholar 

  14. Xun X, Su C, Li W, Pang M (2020) Coal mine gas concentration prediction based on CNN-LSTM. J Modern Inf Technol 4(20):149–152. https://doi.org/10.19850/j.carolcarrollnki.2096-4706.2020.20.040

    Article  Google Scholar 

  15. Ji Y, Zhang H (2021) CNN-based encoder-decoder networks for salient object detection: a comprehensive review and recent advances. Inf Sci 546:835–857. https://doi.org/10.1016/j.ins.2020.09.003

    Article  MathSciNet  Google Scholar 

  16. Zhang C, Wang E (2021) A new method for coal and gas outburst prediction and prevention based on the fragmentation of ejected coal. Fuel. https://doi.org/10.1016/j.fuel.2020.119493

    Article  Google Scholar 

  17. Zhang Y, Guo H (2020) Distributed gas concentration prediction with intelligent edge devices in coal mine. Eng Appl Artif Intell. https://doi.org/10.1016/j.engappai.2020.103643

    Article  Google Scholar 

  18. Fatma AH, Abdelazim G (2022) Snake optimizer: a novel meta-heuristic optimization algorithm. Knowl Based Syst. https://doi.org/10.1016/j.knosys.2022.108320

    Article  Google Scholar 

  19. Zhang D, Xia H, Zhang C, Ma G, Wang C (2022) Improved firefly algorithm and its convergence analysis. Syst Eng Electron 44(04):291–1300

    Google Scholar 

  20. Shi M, Xiao S, Fin X (2022) Random disturbance based on multiple populations of random disturbance of ant colony algorithm to solve the distributed constraint optimization problem. Comput Appl Res. https://doi.org/10.19734/j.issn.1001-3695.2022.03.0084

    Article  Google Scholar 

  21. Prashanth LA, Bhatnagar S, Bhavsar N, Fu M, Marcus SI (2020) Random directions stochastic approximation with deterministic perturbations. IEEE Trans Autom Control 65(6):2450–2465. https://doi.org/10.1109/TAC.2019.2930821

    Article  MathSciNet  Google Scholar 

  22. Xu J, Li Q, Guan Z, Wang X (2022) Nonlinear reconstruction of target density based on stochastic perturbation optimization and multi-model fusion. Acta Photon Sin. 51(03):1–14

    Google Scholar 

  23. Jian L, Li X (2013) Parameter estimation of chaotic systems based on hybrid biogeographic optimization. Acta Geograph Sin 62(03):74–80

    Google Scholar 

  24. Long W, Cai S, Jiao J, Tang M, Wu T (2017) Improved whale optimization algorithm for solving large-scale optimization problems. Syst Eng Theory Pract 37(11):2983–2994

    Google Scholar 

  25. Xu N, Wang X (2022) Gas concentration prediction based on IWOA-LSTM-CEEMDAN residual correction model. Sensors 22:4412. https://doi.org/10.3390/s22124412

    Article  Google Scholar 

  26. Fan D, Sun H (2021) Well production forecasting based on ARIMA-LSTM model considering manual operations. Energy. https://doi.org/10.1016/j.energy.2020.119708

    Article  Google Scholar 

  27. Shu X, Zhang L, Sun Y (2021) Host–parasite: graph LSTM-in-LSTM for group activity recognition. IEEE Trans Neural Netw Learn Syst 32(2):663–674. https://doi.org/10.1109/TNNLS.2020.2978942

    Article  Google Scholar 

  28. Zhang B, Zou G, Qin D (2021) A novel encoder–decoder model based on read-first LSTM for air pollutant prediction. Sci Total Environ. https://doi.org/10.1016/j.scitotenv.2020.144507

    Article  Google Scholar 

  29. Zhang P, Xue J, Lan C, Zeng W (2019) ELEATT-RNN: adding attentiveness to neurons in recurrent neural networks. IEEE Trans Image Process 29:1061–1073

    Article  MathSciNet  Google Scholar 

  30. Wang X, Xu N, Meng X, Chang H (2022) Prediction of gas concentration based on LSTM-LightGBM variable weight combination model. Energies 15(3):827. https://doi.org/10.3390/en15030827

    Article  Google Scholar 

  31. Kyusung K, Phuwadej P, Pil G (2022) Self-adaptive gas sensor system based on operating conditions using data prediction. ACS Sens 7(1):142–150. https://doi.org/10.1021/acssensors.1c01864

    Article  Google Scholar 

Download references

Acknowledgements

The authors gratefully appreciate the financial support provided by the National Natural Science Foundation of China(51874003),the Academic Funding Projects for Top Talents in Disciplines and Majors of Anhui (gxbjZD2021051).

Author information

Authors and Affiliations

  1. School of Economics and Management, Anhui University of Science and Technology, Huainan, 232000, Anhui, China

    Xiangqian Wang & Xiangrui Meng

  2. School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, 232000, Anhui, China

    Ningke Xu

Authors
  1. Xiangqian Wang
    View author publications

    Search author on:PubMed Google Scholar

  2. Ningke Xu
    View author publications

    Search author on:PubMed Google Scholar

  3. Xiangrui Meng
    View author publications

    Search author on:PubMed Google Scholar

Corresponding author

Correspondence to Ningke Xu.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, X., Xu, N. & Meng, X. Gas concentration prediction based on ED-SLSTM model under the framework of Trend Prediction-Time Point Prediction. Int. J. Mach. Learn. & Cyber. 15, 4695–4707 (2024). https://doi.org/10.1007/s13042-024-02183-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1007/s13042-024-02183-7

Keywords