Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

OrdinalEncoder based DNN for Natural Gas Leak Prediction

천연가스 누출 예측을 위한 OrdinalEncoder 기반 DNN

  • Received : 2019.08.19
  • Accepted : 2019.10.20
  • Published : 2019.10.28
Download PDF
⟨ Previous Next ⟩

Abstract

The natural gas (NG), mostly methane leaks into the air, it is a big problem for the climate. detected NG leaks under U.S. city streets and collected data. In this paper, we introduced a Deep Neural Network (DNN) classification of prediction for a level of NS leak. The proposed method is OrdinalEncoder(OE) based K-means clustering and Multilayer Perceptron(MLP) for predicting NG leak. The 15 features are the input neurons and the using backpropagation. In this paper, we propose the OE method for labeling target data using k-means clustering and compared normalization methods performance for NG leak prediction. There five normalization methods used. We have shown that our proposed OE based MLP method is accuracy 97.7%, F1-score 96.4%, which is relatively higher than the other methods. The system has implemented SPSS and Python, including its performance, is tested on real open data.

대부분의 천연가스(NG)는 공기 중으로 누출 되며 그중에서도 메탄가스의 누출은 기후에 많은 영향을 준다. 미국 도시의 거리에서 메탄가스 누출 데이터를 수집하였다. 본 논문은 메탄가스누출 정도를 예측하는 딥러닝(Deep Neural Network)방법을 제안하였으며 제안된 방법은 OrdinalEncoder(OE) 기반 K-means clustering과 Multilayer Perceptron(MLP)을 활용하였다. 15개의 특징을 입력뉴런과 오류역전파 알고리즘을 적용하였다. 데이터는 실제 미국의 거리에서 누출되는 메탄가스농도 오픈데이터를 활용하여 진행하였다. 우리는 OE 기반 K-means알고리즘을 적용하여 데이터를 레이블링 하였고 NG누출 예측을 위한 정규화 방법 OE, MinMax, Standard, MaxAbs. Quantile 5가지 방법을 실험하였다. 그 결과 OE 기반 MLP의 인식률이 97.7%, F1-score 96.4%이며 다른 방법보다 상대적으로 높은 인식률을 보였다. 실험은 SPSS 및 Python으로 구현하였으며 실제오픈 데이터를 활용하여 실험하였다.

Keywords

References

  1. Z. D. Weller, D. K. Yang & J. C. von Fischer. (2019). An open source algorithm to detect natural gas leaks from mobile methane survey data. PLOS ONE, 14(2), e0212287. DOI:10.1371/journal.pone.0212287
  2. J. Wanga et al. (2019). Machine Vision for Natural Gas Methane Emissions Detection Using an Infrared Camera. arXiv preprint, arXiv:1904.08500v1
  3. L. Salhi et al. (2019). Early Detection System for Gas Leakage and Fire in Smart Home Using Machine Learning. 2019 IEEE International Conference on Consumer Electronics (ICCE). (pp. 1-6). Las Vegas : IEEE. DOI: 10.1109/ICCE.2019.8661990
  4. J. H. Mcmanus et al. (1996). Methane emission measurements in urban areas in Eastern Germany, Journal of Atmos Chem, 24, pp. 121-140. DOI: 10.1007/BF00162407
  5. J. Wilkinson et al. (2018). Measuring CO2 and CH4 with a portable gas analyzer: Closed-loop operation, optimization and assessment, PLOS ONE, 13(4), e0193973. DOI: 10.1371/journal.pone.0193973.
  6. D. W. Zachary et al. (2018). Vehicle-Based Methane Surveys for Finding Natural Gas Leaks and Estimating Their Size: Validation and Uncertainty, Environmental Science & Technology, 52(20), pp. 11922-11930. DOI: 10.1021/acs.est.8b03135
  7. F. H. Margaret et al. (2016). Fugitive methane emissions from leak-prone natural gas distribution infrastructure in urban environments, Environmental Pollution, 213, 710-716. https://doi.org/10.1016/j.envpol.2016.01.094
  8. Joseph C et al. (2017). Rapid, Vehicle-Based Identification of Location and Magnitude of Urban Natural Gas Pipeline Leaks, Environmental Science & Technology, 51(7), 4091-4099 DOI: 10.1021/acs.est.6b06095
  9. E. K. Chandler, P. R. Arvind & R. B. Adam. (2016). Comparing Natural Gas Leakage Detection Technologies Using an Open-Source "Virtual Gas Field" Simulator. Environ. Sci. Technol. 50(8), 4546-4553. DOI: 10.1021/acs.est.5b06068
  10. Brian K. Lamb et al. (2015). Direct Measurements Show Decreasing Methane Emissions from Natural Gas Local Distribution Systems in the United States, Environ. Sci. Technol. 49(8), 5161-5169. DOI: 10.1021/es505116p
  11. P. Kaur & T. Choudhury. (2016). Early detection of SF6 gas in gas insulated switchgear, 7th India Int. Conf. on Power Electronics (IICPE). (pp. 1-6). Patiala: IICPE.
  12. D. Khongorzul, M. H. Kim & S. M. Lee, (2019m July). Classification using the Multilayer Perceptron prediction for Natural Gas leak. The 9th Int. Conf. on Conv. Techn.. (pp. 553-554). Jeju : ICCT.
  13. Matthew Barriault et al. (2018, May). Quantitative Natural Gas Discrimination For Pipeline Leak Detection Through Time-Series Analysis of an MOS Sensor Respons, Proc. of The Canadian Society for Mechanical Engineering Int. Congress, Toronto : CSME.
  14. Z. Xiaojun et al. (2016). MLP Neural Network Based Gas Classification System on Zynq SoC, IEEE Access, (4), 8138-8146. DOI: 10.1109/ACCESS.2016.2619181
  15. Jin-Hee Ku. (2017). A Study on the Machine Learning Model for Product Faulty Prediction in Internet of Things Environment. Journal of Convergence for Information Technology, 7(1), 55-60. DOI: 10.22156/CS4SMB.2017.7.1.055
  16. Yong-Bae Lee. (2014). Classification Accuracy by Deviation-based Classification Method with the Number of Training Documents. Journal of Digital Convergence, 12(6), 323-332. DOI: 10.14400/JDC.2014.12.6.325