스마트 관망 관리를 위한 머신 러닝 기반 누수 감지 모델
Machine-learning based leakage detection model for smart management of water distribute network
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
기후 변화의 영향으로 물 스트레스를(Water stress) 받고 있는 지역에 전 세계 인구 10%가 거주하고 있지만 전 세계 상수도 공급의 30%가 여전히 누수(leakage)로 인해 낭비되고 있으며 누수를 탐지, 관리하기 위한 기존의 기술로는 이러한 문제를 제대로 해결하지 못하고 있다. 본 논문의 연구분야는 LTE-M 기반의 사물인터넷 (IoT, Internet of Things) 센서 네트워크와 클라우드 서버로 구성되어 있는 원격 누수 관리 시스템을 통해 2020년부터 2022년까지 대구지역 WDN에서 수집된 실제 현장 센서 데이터셋 5,000 샘플을 분석하고 머신 러닝 알고리즘을 적용하여 누수를 검출하고 예측하는 시스템에 대한 것이다. 본 연구에서 사용한 지도학습기반 머신 러닝 모델은 랜덤 포레스트(Random Forest), 그래디언트 부스팅(Gradient Boosting), 로지스틱 회귀(Logistic Regression), 서포트 벡터 머신(Support Vector Machine), 인공 신경망(Artificial Neural Network)이고 다양한 머신 러닝 알고리즘별 성능을 비교 분석하기 위해 AUROC (Area Under Rest of the Curve), F1 점수와 같은 이진분류 성능 척도를 사용하였다.
Abstract
Due to the climate change, 10% of the global population resides in the regions facing water stress. Meanwhile, 30% of the global water supply is wasted through leakage. The issue is that existing technologies fall short to detect and manage. This paper focuses on the leakage detection and prediction system, constructed from the data analysis of 5,000 real-world sensor samples, collected from the WDN in Daegu region from 2020 to 2022, and the application of machine learning (ML) algorithms. The research utilizes a remote leak management system consisting of LTE-M-based IoT sensor networks and cloud servers to compile the dataset. Various ML algorithms, including Random Forest (RF), Gradient Boosting (GB), Logistic Regression (LR), Support Vector Machine (SVM), and Artificial Neural Network (ANN), are employed as supervised learning models. Performance comparison and analysis of these ML algorithms applied to the field sensor data are done by binary classification performance metrics, such as AUROC (Area Under Rest of the Curve) and F1 score.
참고문헌 (27)
- 최준규, "누수 잡음 크기 스펙트럼을 이용한 SVM 기반의 상수관로 누수 감지 및 분류", 전자공학회논문지, 60(2), pp.6~14 (2023), 대한전자공학회
- A. Fabricoio et al., "On the Acoustic Filtering of the Pipe and Sensor in a Buried Plastic Water Pipe and its Effect on Leak Detection: An Experimental Investigation", Sensors, 14(3), pp.5595~5610 (2014)[DOI]
- S. Ivan et al., "PIPENET : A Wireless Sensor Network for Pipeline Monitoring", Paper presented at the 2007 6th International Symposium on Information Processing in Sensor Networks (2007)
- M. I. M. Ismail et al., "A Review of Vibration Detection Methods Using Accelerometer Sensors for Water Pipeline Leakage", IEEE Access, 7, pp.51965~51981 (2019)
- S. R. Mounce, "Burst detection using hydraulic data from water distribution systems with artificial neural networks", Urban Water Journal, 3(1), pp.21~31 (2006)
- X. Wan et al., "Literature Review of Data Analytics for Leak Detection in Water Distribution Networks : A Focus on Pressure and Flow Smart Sensors", Journal of Water Resources Planning and Management, 148(10) (2022)
- S. G. Vrachimis et al., "Battle of the Leakage Detection and Isolation Methods", Journal of Water Resources Hanrung & Management, 148(12), pp.1~20 (2022)
- Z. Li et al., "Fast Detection and Localization of Multiple Leaks in Water Distribution Network Jointly Driven by Simulation and Machine Learning", Journal of Water Resources Planning and Management, 148(9), pp.05022005~ (2022)
- X. Hu et al., "Novel detection and water loss management of urban water supply network using multiscale neural networks", Journal of Cleaner Production, 278, pp.9~ (2021)
- K. R. A. Britto et al., "Supervised Learning Algorithm for Water Leakage Detection through the Pipelines", 3rd International Conference on Smart Electronics and Communication (ICOSEC) (2022)
- M. Romano et al., "Automated detection of pipe bursts and other events in water distribution systems", Journal of Water Resources Planning and Management, 140(4), pp.457~467 (2014)
- X. Wang et al, "Burst Detection in District Metering Areas Using Deep Learning Method", Journal of Water Resources Planning and Management, 146(6), pp.04020031~ (2020)
- S. R. Mounce et al., "Cloud Based Machine Learning Approaches for Leakage Assessment and Management in Smart Water Networks", Procedia Engineering, 119, pp.43~52 (2015)[DOI]
- D. Garlisi, "Leakage Detection via Edge Processing in LoRaWAN-based Smart Water Distribution Networks", 18th International Conference on Mobility. Sensing and Networking (MSN), pp.223~230 (2022), IEEE
- C. Cortes., "Support vector networks", Machine Learning, 20(3), pp.273~ (1995)
- D. R. Cox, "The Regression Analysis of Binary Sequences", Journal of the Royal Statistical Society. Series B (Methodological), 20(2), pp.215~242 (1958)
- L. Mason, "Boosting Algorithms as Gradient Descent", Advances in Neural Information Processing Systems, 12 (1999), NIPS
- Y. Freund, "A Short Introduction to Boosting", Journal of Japanese Society for Artificial Intelligence, 14(5), pp.771~780 (1999)
- L. Rokach, "Top-Down Induction of Decision Trees Classifiers -A Survey", IEEE TRANSACTIONS ON SYSTEMS. MAN AND CYBERNETICS: PART C, 1(11) (2002)
- L Reiman, "Random Forests", Machine Learning, 45, pp.5~32 (2001)
- P. Geurts, "Extremely randomized trees" (2006), Springer Science Business Media. Inc
- N. S. Altman, "An introduction to kernel and nearest-neighbor nonparametric regression", The American Statistician, 46(3), pp.175~185 (1992)
- Z. DeVries, "Development of an unsupervised machine learning algorithm for the prognostication of walking ability in spinal cord injury patients", The Spine Journal, 20(2), pp.213~224 (2020)
- F. Rosenblatt, "The Perceptron : A Probabilistic Model for Information Storage and Organization in the Brain. Cornell Aeronautical Laboratory", Psychological Review, 65(6), pp.386~408 (1958)
- B. James, "Random Search for Hyper-Parameter Optimization", Journal of Machine Learning Research, 13, pp.281~305 (2012)
- Y.LeCun, "Deep learning", Nature, 521, pp.436~444 (2015)
- C. Spandonidis, "A Combined Semi-Supervised Deep Learning Method for Oil Leak Detection in Pipelines Using IIoT at the Edge", Sensors, 22(11), pp.4105~ (2022)[DOI]