• 비파괴검사학회지
• /
• 제35권1호
• /
• pp.31-38
• /
• 2015

스마트 워터 그리드와 같은 지하매설 상수도 배관망을 구성할 때 누수 지점에 대한 지능적 탐지는 중요한 요소이다. 이런 지능형 배관망의 구성에는 많은 수의 누수탐지센서를 일정한 간격으로 설치하는 것이 필요하며 이들 센서에서 계측되는 신호를 분석해서 누수 유무 및 누수발생시 그 지점의 추정을 신속히 할 수 있어야 한다. 그래서 본 연구에서는 특히 두 지점에서 동시에 누수가 발생하는 경우에 대해 그 센서가 측정한 신호가 가지는 특성 및 두 누수지점 동시 추정 가능성을 심도있게 분석하였다. 즉, 센서간 거리가 315.6 m 인 100A 사이즈의 주철관 상수도 배관에 대해 두 지점 동시 누수시 각각의 개별 센서신호를 계측하였으며, 그 신호를 기반으로 주파수 특성 및 상호상관함수 등의 분석을 통해 두 지점의 누수탐지에 대해 기술하였다.

• 상하수도학회지
• /
• 제19권3호
• /
• pp.279-287
• /
• 2005

In this study, I suggest an effective operation of waterwork facilities in large cities and a scientific method for utilizing water in water distribution systems. To achieve this goal, my simulation were carried out on data from Kwangju City using Pipenet '98, a pipe-network program. From this simulation, I examine the possibilities of application the system in large cities, comparing data measured at 33 hydraulic pressure monitoring places from waterwork enterprises. The result is coincident with that of waterwork enterprises, with about a 12.5% average error rate and $0.32kg/cm^2$ average deviation. The method and program I use here can be helpful in cities where there is a need to extend the waterwork facilities, or where there is a need to suspend the water supply, and/or there is an accident. The simulation shows how to expand waterwork facilities effectively, how to prevent accidents, and how to estimate the hydraulic pressure even in the areas without monitoring places.

• 농촌계획
• /
• 제28권4호
• /
• pp.105-117
• /
• 2022

This study tested SVM(support vector machine), RF(random forest), and ANN(artificial neural network) machine-learning models that can predict net irrigation water requirements in paddy fields. For the Jeonju and Jeongeup meteorological stations, the net irrigation water requirement was calculated using K-HAS from 1981 to 2021 and set as the label. For each algorithm, twelve models were constructed based on cumulative precipitation, precipitation, crop evapotranspiration, and month. Compared to the CE model, the R² of the CEP model was higher, and MAE, RMSE, and MSE were lower. Comprehensively considering learning performance and learning time, it is judged that the RF algorithm has the best usability and predictive power of five-days is better than three-days. The results of this study are expected to provide the scientific information necessary for the decision-making of on-site water managers is expected to be possible through the connection with weather forecast data. In the future, if the actual amount of irrigation and supply are measured, it is necessary to develop a learning model that reflects this.

• 한국습지학회지
• /
• 제25권4호
• /
• pp.284-290
• /
• 2023

국내 상하수도 시설들은 운전과 관리 인력의 노후화와 같은 유지관리의 어려움이 가속화되고 있으므로 디지털트윈 기술이 유력한 관리 기술로 부각되고 있다. 국내 정수장의 디지털트윈 기술은 환경부의 지능형 하수처리, 일부 지자체에서 독자적으로 진행되는 사업 및 K-water 주관의 디지털 트윈 과제 등이 포함되지만, 적용 범위가 각 기관별로 상이하다. 이에 따라 정수공정에서는 시행착오를 줄이고, 미래 사업 활성화를 위해서는 기술표준화와 순차적 도입과정이 필요하다. 본 연구의 목적은 환경부 스마트하수처리사업, K-water 지능형정수공정 구현사업, 지자체 사업 등 각 기관별로 추진되고 있는 디지털트윈 관련 기술에 대한 효율적인 추진 전략을 제공하는데 있다.

• 상하수도학회지
• /
• 제12권1호
• /
• pp.70-80
• /
• 1998

Many algorithms to find a minimum cost design of water distribution network (WDN) have been developed during the last decades. Most of them have tried to optimize cost only while satisfying other constraining conditions. For this, a certain degree of simplification is required in their calculation process which inevitably limits the real application of the algorithms, especially, to large networks. In this paper, an optimum design method using the Genetic Algorithms (GA) is developed which is designed to increase the applicability, especially for the real world large WDN. The increased to applicability is due to the inherent characteristics of GA consisting of selection, reproduction, crossover and mutation. Just for illustration, the GA method is applied to find an optimal solution of the New York City water supply tunnel. For the calculation, the parameter of population size and generation number is fixed to 100 and the probability of crossover is 0.7, the probability of mutation is 0.01. The yielded optimal design is found to be superior to the least cost design obtained from the Linear Program method by $4.276 million.

• 한국수자원학회논문집
• /
• 제53권11호
• /
• pp.1015-1024
• /
• 2020

최근 인천, 서울 적수 사고와 같은 관로 내 수질오염 사고가 지속적으로 발생되고 있다. 이러한 수질문제를 인지하기 위해서는 적절한 위치에 수질계측기를 설치하고 미리 계측하여 수용가의 수도꼭지까지 물 공급이 되기 이전에 발견 혹은 차단할 필요가 있다. 그러나 모든 관로에 수질계측기를 다수 설치하는 것에는 유지비용증대와 같은 한계점이 존재한다. 따라서 본 연구에서는 관로 내 수질문제 인지를 위한 유속기반의 수질계측기 설치위치를 결정하고 우선순위를 선정하는 방법론을 제안하였다. 제안된 절차를 관 파괴 시나리오와 국내에서 실제 운영 중인 비상연계관로가 포함된 관망운영 시나리오에 적용해 수질계측기 위치를 결정하고 결과를 분석하였다. 결정 결과 개별적인 관로의 파괴와 비상연계에 의한 비정상상황 발생시 대수용가와 탱크 주변, 그리고 비상연계관로 인근에 위치한 관로의 유속이 급격히 변하여 탁수발생에 의한 수질사고가 나타날 수 있을것으로 나타났다. 제안된 유속기반의 수질계측기 위치 결정 절차는 향후 관 청소를 위한 차단 및 비상관로 운영 계획 수립 등 수질모니터링 지점 선정 기법으로 활용 가능할 것으로 기대된다.

• 상하수도학회지
• /
• 제35권1호
• /
• pp.83-91
• /
• 2021

The increased turbidity in rivers during flood events has various effects on water environmental management, including drinking water supply systems. Thus, prediction of turbid water is essential for water environmental management. Recently, various advanced machine learning algorithms have been increasingly used in water environmental management. Ensemble machine learning algorithms such as random forest (RF) and gradient boosting decision tree (GBDT) are some of the most popular machine learning algorithms used for water environmental management, along with deep learning algorithms such as recurrent neural networks. In this study GBDT, an ensemble machine learning algorithm, and gated recurrent unit (GRU), a recurrent neural networks algorithm, are used for model development to predict turbidity in a river. The observation frequencies of input data used for the model were 2, 4, 8, 24, 48, 120 and 168 h. The root-mean-square error-observations standard deviation ratio (RSR) of GRU and GBDT ranges between 0.182~0.766 and 0.400~0.683, respectively. Both models show similar prediction accuracy with RSR of 0.682 for GRU and 0.683 for GBDT. The GRU shows better prediction accuracy when the observation frequency is relatively short (i.e., 2, 4, and 8 h) where GBDT shows better prediction accuracy when the observation frequency is relatively long (i.e. 48, 120, 160 h). The results suggest that the characteristics of input data should be considered to develop an appropriate model to predict turbidity.

• 한국농공학회논문집
• /
• 제65권1호
• /
• pp.15-26
• /
• 2023

This study aimed to evaluate the performance of water level classification from CCTV images in agricultural facilities such as reservoirs. Recently, the CCTV system, widely used for facility monitor or disaster detection, can automatically detect and identify people and objects from the images by developing new technologies such as a deep learning system. Accordingly, we applied the ResNet-50 deep learning system based on Convolutional Neural Network and analyzed the water level of the agricultural reservoir from CCTV images obtained from TOMS (Total Operation Management System) of the Korea Rural Community Corporation. As a result, the accuracy of water level detection was improved by excluding night and rainfall CCTV images and applying measures. For example, the error rate significantly decreased from 24.39 % to 1.43 % in the Bakseok reservoir. We believe that the utilization of CCTVs should be further improved when calculating the amount of water supply and establishing a supply plan according to the integrated water management policy.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2008년도 춘계학술대회논문집
• /
• pp.626-629
• /
• 2008

Numerical predictions on flow phenomena in pipe network systems have been considered as playing an important role in both designing and operating various facilities of piping or duct systems, such as water supply, tunnel or mine ventilation, hydraulic systems of automobile or aircraft, and etc. Traditionally, coupling conditions between junction and connected branches are assumed to satisfy conservation law of mass and to share an equal pressure at junction node. However, the conventional methodology cannot reflect momentum interactions between pipes sufficiently. Thus, a new finite volume junction treatment is proposed both to reflect the interchanges of linear momentums between neighbor branches at junction and to include the effect of wall at junction in present work.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.65.6-65
• /
• 2001

The satellite communication has been widely applied in the various fields included the remote monitoring and control system through the technical progress. In the star network that is a type of the satellite communication network, users can easily use an earth station because of the large scale and high power of the hub station. This type has many profits which are flexible of network configuration, and can conveniently and inexpensively supply various services which is used in the data acquisition and distribution by important communication means for construction of information society. Using these profits, the satellite communication system is applied to the unmaned remote operation field for the remote control and monitor of the water treatment plants But, ...