OrdinalEncoder based DNN for Natural Gas Leak Prediction

다국어 초록 (Multilingual 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.

참고문헌 (Reference)

1 구진희, "사물인터넷 환경에서 제품 불량 예측을 위한 기계 학습 모델에 관한 연구" 중소기업융합학회 7 (7): 55-60, 2017

2 Zachary D. Weller, "Vehicle-Based Methane Surveys for Finding Natural Gas Leaks and Estimating Their Size: Validation and Uncertainty" American Chemical Society (ACS) 52 (52): 11922-11930, 2018

3 Joseph C. von Fischer, "Rapid, Vehicle-Based Identification of Location and Magnitude of Urban Natural Gas Pipeline Leaks" American Chemical Society (ACS) 51 (51): 4091-4099, 2017

4 Matthew Barriault, "Quantitative Natural Gas Discrimination For Pipeline Leak Detection Through Time-Series Analysis of an MOS Sensor Respons" CSME 2018

5 Joanne H. Shorter, "Methane emission measurements in urban areas in Eastern Germany" Springer Science and Business Media LLC 24 (24): 121-140, 1996

6 Jeremy Wilkinson, "Measuring CO2 and CH4 with a portable gas analyzer: Closed-loop operation, optimization and assessment" Public Library of Science (PLoS) 13 (13): e0193973-, 2018

7 J. Wanga, "Machine Vision for Natural Gas Methane Emissions Detection Using an Infrared Camera"

8 Xiaojun Zhai, "MLP Neural Network Based Gas Classification System on Zynq SoC" Institute of Electrical and Electronics Engineers (IEEE) 4 : 8138-8146, 2016

9 F. H. Margaret, "Fugitive methane emissions from leak-prone natural gas distribution infrastructure in urban environments" 213 : 710-716, 2016

10 P. Kaur, "Early detection of SF6 gas in gas insulated switchgear" IICPE 1-6, 2016

11 L. Salhi, "Early Detection System for Gas Leakage and Fire in Smart Home Using Machine Learning" IEEE 1-6, 2019

12 Brian K. Lamb, "Direct Measurements Show Decreasing Methane Emissions from Natural Gas Local Distribution Systems in the United States" American Chemical Society (ACS) 49 (49): 5161-5169, 2015

13 Chandler E. Kemp, "Comparing Natural Gas Leakage Detection Technologies Using an Open-Source “Virtual Gas Field” Simulator" American Chemical Society (ACS) 50 (50): 4546-4553, 2016

14 D. Khongorzul, "Classification using the Multilayer Perceptron prediction for Natural Gas leak" ICCT 553-554, 2019

15 이용배, "Classification Accuracy by Deviation-based Classification Method with the Number of Training Documents" 한국디지털정책학회 12 (12): 323-332, 2014

16 Zachary D. Weller, "An open source algorithm to detect natural gas leaks from mobile methane survey data" Public Library of Science (PLoS) 14 (14): e0212287-, 2019