• 상하수도학회지
• /
• 제14권3호
• /
• pp.281-290
• /
• 2000

This study investigates the prediction of daily water supply, which is a necessary for the efficient management of water distribution system. ANFIS, namely artificial intelligence, is a neural network into which fuzzy information is inputted and then processed. In this study, daily water supply was predicted through an application of network-based fuzzy inference system(ANFIS) for daily water supply prediction. This study was investigated methods for predicting water supply based on data about the amount of water which supplied in Kwangju city. For variables choice, four analyses of input data were conducted: correlation analysis, autocorrelation analysis, partial autocorrelation analysis, and cross-correlation analysis. Input variables were (a) the amount of water supply, (b) the mean temperature, and (c) the population of the area supplied with water. Variables were combined in an integrated model. Data of the amount of daily water supply only was modelled and its validity was verified in the case that the meteorological office of weather forecast is not always reliable. Proposed models include accidental cases such as a suspension of water supply. The maximum error rate between the estimation of the model and the actual measurement was 18.46% and the average error was lower than 2.36%. The model is expected to be a real-time estimation of the operational control of water works and water/drain pipes.

• 상하수도학회지
• /
• 제31권5호
• /
• pp.421-430
• /
• 2017

In this study, a model was developed to predict for Disinfection By-Products (DBPs) generated in water supply networks and consumer premises, before and after the introduction of advanced water purification facilities. Based on two-way ANOVA, which was carried out to statistically verify the water quality difference in the water supply network according to introduce the advanced water treatment process. The water quality before and after advanced water purification was shown to have a statistically significant difference. A multiple regression model was developed to predict the concentration of DBPs in consumer premises before and after the introduction of advanced water purification facilities. The prediction model developed for the concentration of DBPs accurately simulated the actual measurements, as its coefficients of correlation with the actual measurements were all 0.88 or higher. In addition, the prediction for the period not used in the model development to verify the developed model also showed coefficients of correlation with the actual measurements of 0.96 or higher. As the prediction model developed in this study has an advantage in that the variables that compose the model are relatively simple when compared with those of models developed in previous studies, it is considered highly usable for further study and field application. The methodology proposed in this study and the study findings can be used to meet the level of consumer requirement related to DBPs and to analyze and set the service level when establishing a master plan for development of water supply, and a water supply facility asset management plan.

• 상하수도학회지
• /
• 제19권4호
• /
• pp.395-403
• /
• 2005

It is very important to forecast water supply for reasonal operation and management of water utilities. In this paper, water supply forecasting models using artificial intelligence are developed. Artificial intelligence models shows better results by using Temperature(t), water supply discharge (t-1) and water supply discharge (t-2), which are expressed by neural network(LMNNWS; Levenberg-Marquardt Neural Network for Water Supply, MDNNWS; MoDular Neural Network for Water Supply) and neuro fuzzy(ANASWS; Adaptive Neuro-Fuzzy Inference Systems for Water Supply). ANFISWS model which is applied for water supply forecasting shows stable application to the variable water supply data. As results, MDNNWS model shows the highest overall accuracy among proposed water supply forecasting models and the lowest estimation error with the order of ANFISWS, LMNNWS model.

• 한국물환경학회지
• /
• 제37권5호
• /
• pp.335-343
• /
• 2021

Water quality prediction is essential for the proper management of water supply systems. Increased suspended sediment concentration (SSC) has various effects on water supply systems such as increased treatment cost and consequently, there have been various efforts to develop a model for predicting SSC. However, SSC is affected by both the natural and anthropogenic environment, making it challenging to predict SSC. Recently, advanced machine learning models have increasingly been used for water quality prediction. This study developed an ensemble machine learning model to predict SSC using the XGBoost (XGB) algorithm. The observed discharge (Q) and SSC in two fields monitoring stations were used to develop the model. The input variables were clustered in two groups with low and high ranges of Q using the k-means clustering algorithm. Then each group of data was separately used to optimize XGB (Model 1). The model performance was compared with that of the XGB model using the entire data (Model 2). The models were evaluated by mean squared error-ob servation standard deviation ratio (RSR) and root mean squared error. The RSR were 0.51 and 0.57 in the two monitoring stations for Model 2, respectively, while the model performance improved to RSR 0.46 and 0.55, respectively, for Model 1.

• 설비공학논문집
• /
• 제28권9호
• /
• pp.355-360
• /
• 2016

Continuing to the modeling of heating load, this paper, as the second part of consecutive works, presents LS-SVM (least square support vector machine) based model of winter time apartment hot water supply load in a district heating system, so as to be used in prediction of heating energy usage. Similar, but more severely, to heating load, hot water supply load varies in highly nonlinear manner. Such nonlinearity makes analytical model of it hardly exist in the literatures. LS-SVM is known as a good modeling tool for the system, especially for the nonlinear system depended by many independent factors. We collect 26,208 data of hot water supply load over a 13-week period in winter time, from 12 heat exchangers in seven different apartments. Then part of the collected data were used to construct LS-SVM based model and the rest of those were used to test the formed model accuracy. In modeling, we first constructed the model of district heating system's hot water supply load, using the unit heating area's hot water supply load of seven apartments. Such model will be used to estimate the total hot water supply load of which the district heating system needs to provide. Then the individual apartment hot water supply load model is also formed, which can be used to predict and to control the energy consumption of the individual apartment. The results obtained show that the total hot water supply load, which will be provided by the district heating system in winter time, can be predicted within 10% in MAPE (mean absolute percentage error). Also the individual apartment models can predict the individual apartment energy consumption for hot water supply load within 10% ~ 20% in MAPE.

• 한국정보통신학회논문지
• /
• 제26권7호
• /
• pp.963-971
• /
• 2022

상수도 관망은 국가 수도 시설의 주요한 구성 요소이지만 대부분이 지중에 매립되어 있어 배관의 노후화 정도 및 누수를 파악하기 어려우므로 유지관리 하기가 매우 어렵다. 본 연구에서는 관망에 설치된 다양한 센서 조합을 가정하여, 데이터 조합에 따른 관로 누수 판별 가능성을 검토하기 위하여 선형회귀분석, 뉴로퍼지 등의 인공지능 알고리즘을 통한 유량과 압력 예측을 실시하여 최적 알고리즘을 도출하였다. 공급압력 예측을 통한 누수판별의 경우 뉴로퍼지 알고리즘이 선형회귀분석에 비하여 우수하였다. 누수유량 예측에서는 뉴로퍼지를 이용한 유량예측이 우선 고려되어야 한다. 다만, 유량을 모사하기 힘든 경우에는 선형 알고리즘을 이용한 공급압력 예측이 이루어져야 할 것으로 사료 된다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2001년도 학술발표회 논문집(II)
• /
• pp.1189-1194
• /
• 2001

• 설비공학논문집
• /
• 제27권3호
• /
• pp.137-145
• /
• 2015

In this study, the actual energy consumption of the secondary side of District Heating System (DHS) with different hot water supply temperature control methods are compared. Three methods are Set-point Control, Outdoor Temperature Reset Control and Outdoor Temperature Prediction Control. While Outdoor Temperature Reset Control has been widely used for energy savings of the secondary side of the system, the results show that Outdoor Temperature Prediction Control method saves more energy. In general, Outdoor Temperature Prediction Control method lowers the supply temperature of hot water, and it reduces standby losses and increases overall heat transfer value of heated spaces due to more flow into the space. During actual energy consumption monitoring, Outdoor Temperature Prediction Control method saves about 7.1% in comparison to Outdoor Temperature Reset Control method and about 15.7% in comparison to Set-point Control method. Also, it is found that at when partial load condition, such as daytime, the fluctuation of hot water supply temperature with Set-point Control is more severe than Outdoor Temperature Prediction Control. Therefore, it proves that Outdoor Temperature Prediction Control is more stable even at the partial load conditions.

• 한국수자원학회논문집
• /
• 제31권6호
• /
• pp.821-832
• /
• 1998

본 논문에서는 상수도시설을 효율적으로 운영하는 데 필요한 1일 급수량 수요를 예측하는 방식에 대하여 인공지능(Artificial Inteligence)이라 불리는 퍼지 뉴론(fuzzy neuron)을 이용하여 연구하였다. 퍼지뉴론이란 퍼지정보(fuzzy information)를 입력으로 받아들이고 처리하는 퍼지 신경망을 일컫는 말이다. 본 연구에서는 소속함수와 퍼지규칙을 신경망으로 학습하는 기능인 적응식 학습방법을 통하여 1일 급수량을 예측하였으며 연구대상 지역으로는 광주광역시를 선정하였다. 또한 1일 급수량 예측에 있어서 필요한 변수 선택을 위해 입력자료를 상관분석, 자기상관, 부분자기상관, 교차상관 분석 등을 하였으며 동정된 입력변수는 급수량, 평균기온, 급수인구이다. 먼저 급수량, 평균기온, 급수인구로 모델을 구성하였고, 한편으론 기상청의 기후예보자료를 신뢰할 수 없는 경우에는 급수량을 예측할 수 있도록 급수량 자료만으로 모델을 구성하여 그 유효성을 검증하였다. 제안된 모형식은 사고 등의 인위적인 조작(단수 등)이 가해지는 시기를 포함하고도 실측치와 모형의 예측치와의 오차율이 최대 18.46%, 평균2.36% 이내로 나타나, 모형의 결과는 상수도 시설의 운용 및 급·배수관망의 실시간 제어에 많은 도움을 주리라 생각된다.

• 환경영향평가
• /
• 제14권4호
• /
• pp.157-164
• /
• 2005

Existing models that predict of Daily water supply include statistical models and neural network model. The neural network model was more effective than the statistical models. Only neural network model, which predict of Daily water supply, is focused on estimation of the operational control. Neural network model takes long learning time and gets into local minimum. This study proposes Neuro Genetic hybrid model which a combination of genetic algorithm and neural network. Hybrid model makes up for neural network's shortcomings. In this study, the amount of supply, the mean temperature and the population of the area supplied with water are use for neural network's learning patterns for prediction. RMSE(Root Mean Square Error) is used for a MOE(Measure Of Effectiveness). The comparison of the two models showed that the predicting capability of Hybrid model is more effective than that of neural network model. The proposed hybrid model is able to predict of Daily water, thus it can apply real time estimation of operational control of water works and water drain pipes. Proposed models include accidental cases such as a suspension of water supply. The maximum error rate between the estimation of the model and the actual measurement was 11.81% and the average error was lower than 1.76%. The model is expected to be a real-time estimation of the operational control of water works and water/drain pipes.