• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.19-27
• /
• 2020

In this paper, we propose a machine learning method for diagnosing the failure of a gas pressure regulator. Originally, when implementing a machine learning model for detecting abnormal operation of a facility, it is common to install sensors to collect data. However, failure of a gas pressure regulator can lead to fatal safety problems, so that installing an additional sensor on a gas pressure regulator is not simple. In this paper, we propose various machine learning approach for diagnosing the abnormal operation of a gas pressure regulator with only the flow rate and gas pressure data collected from a gas pressure regulator itself. Since the fault data of a gas pressure regulator is not enough, the model is trained in all classes by applying the over-sampling method. The classification model was implemented using Gradient boosting, 1D Convolutional Neural Networks, and LSTM algorithm, and gradient boosting model showed the best performance among classification models with 99.975% accuracy.

• Journal of Wetlands Research
• /
• v.18 no.4
• /
• pp.394-403
• /
• 2016

This study was carried out to verify change and relationship between the concentration of chlorophyll-a and environmental factors including weather, water quality and discharge at before & after Gangcheon and Ipoh weir construction at Namhan river, based on the weather and water quality data provided by the measuring network. We classified the period of before & after weir construction by the cluster analysis with Ward's method, and also through the correlation analysis between the concentration of chlorophyll-a and environmental factors, the influence factors related with algae occurrence(Chlorophyll-a) were analyzed. The result by cluster analysis based on data of the total 12 factors (water temperature, rainfall, daylight, pH, DO, BOD, COD, T-N, $NH_3-N$, $NO_3-N$, T-P, $PO_4-P$) from 2005 to 2015 indicated a clear classification into two periods, before(2006-2007) & after (2012-2013) weir construction. After weir construction, class of BOD at Gangcheon weir was better than before, changed from II class to Ia class, and likewise class of BOD at Ipoh weir was improved from II-III class to Ia-IIclass. Also T-P and T-N concentration also were to be improved in general after weir construction. Concentraion of Chlorophyll-a afterGangcheon and Ipoh weir construction was to be decreased. However, frequency of algae warning was increased from 9 to 15 after Ipoh weir construction due to increasing of HRT and water temperature. After weirs construction, the result of correlation analysis between weather, water quality and discharge and concentration of chlorophyll-a indicated a positive correlation, order of BOD(0.579) > COD(0.413) > temperature(0.237), and a negative correlation, order of $NO_3-N$(-0.344) > T-N(-0.293) at Gangcheon weir. And there were likewise positive correlation, order of BOD(0.795) > pH(0.581) > Water temperature(0.422), and negative correlation, order of $NO_3-N$(-0.457) > T-N(-0.371) > $NH_3-N$(-0.326) > $PO_4-P$(-0.288) > Discharge(-0.213) after Ipoh weir construction. Although water quality after Ipoh weir construction was generally improved, increase of frequency of algae warning occurrence was influenced by change of water conditions such as reduction of the velocity, increase of HRT and water temperature, etc impacted strongly by change of the stream flow more than change of water environments after weir construction.

• Clinical and Experimental Pediatrics
• /
• v.51 no.3
• /
• pp.323-328
• /
• 2008

Purpose : Asthma is defined as chronic inflammation of the lower small airways, and bronchial hyperreactivity (BHR) is a pathophysiologic feature of asthma. It has been proposed that although there is no direct variable capable of assessing the small airways, a forced expiratory flow of between 25 and 75 percent ($FEF_{25-75}$) might be considered a more sensitive early marker of small airway obstruction than the forced expiratory volume in 1 second ($FEV_1$). Thus, we proposed that the presence and degree of positive responses to bronchial methacholine testing were related to the difference (DFF) and ratio (RFF) between $FEV_1$ and $FEF_{25-75}$ in asthmatic children. Methods : The subjects were 583 symptomatic children, including 324 children with BHR and 259 controls. Pulmonary function tests, methacholine challenge tests, and skin prick tests were performed, and the total eosinophil count, total serum IgE, and serum eosinophil cationic protein level were measured in all subjects. From a concentration-response curve, the methacholine concentration required to produce a decrease of 20% from post-saline $FEV_1$ was calculated ($PC_{20}$). Results : The median DFF and RFF values decreased in controls compared to subjects with bronchial hyperresponsiveness, and this trend was found in groups ranked by its severity. $PC_{20}$ had a negative correlation with DFF and RFF. Cutoff values of 0.5 for DFF and 1.042 for RFF were identified, and sensitivity and specificity were calculated. Conclusion : This study revealed that DFF and RFF might be predictive of bronchial hyperresponsiveness in the context of normal $FEV_1$ in children.

• Journal of Korea Water Resources Association
• /
• v.49 no.2
• /
• pp.95-106
• /
• 2016

Water Management Resilience Index (WMRI) was developed as a policy measure of adaptability to withstand water stresses and to set up water management strategies mainly in mid-small scale tributaries, and then evaluated on 117 sub-basins in South Korea. The index consists of 3 sub-indices such as vulnerability, robustness and redundancy sub-indices, each including indicators of 3 sectors: water use, flood mitigation, and river environment. Total number of indicators selected for the index was 31. Taking into account the stream order and control capability of river flow discharge, sub-basins were categorized into 3: 1 for mainstreams of lower large dams, 2 and 3 for tributaries, respectively without and with flow discharge regulation. As a result of the evaluation, resilience index scores in Category 2 and 3 are much lower than that of Category 1, especially with very poor score of redundancy. Although there was no significant difference between mainstream and tributaries in vulnerability and robustness sub-indices, results of redundancy sub-index in tributaries were lower than those in mainstream. Thus, it is conceived that the variety of water management schemes should be considered to improve their resilience in the face of future uncertainty. Addressing comprehensive stability of river basin against internal and external impacts, WMRI in this study can also be used for the prioritization of water management plans.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.146-146
• /
• 2020

최근 하천의 유사 중 소류사량을 계측하기 위해 사용된 기존의 물리적 소류사 샘플러를 이용한 직접계측방법은 홍수 시에 깊은 수위와 빠른 유속, 계측 절차상의 위험성 때문에 현장관측이 매우 어려운 한계를 극복하기 위해 현업에서는 소류사량을 간접적으로 추정하는 이론식에 의한 방법이 광범위하게 활용되고 있으나 이 방법 또한 추정이론식의 적용지역, 적용방법에 따라 결과가 수십배 이상 큰 차이를 나타나 실제 활용성에 대한 문제점이 있다. 이러한 기존의 소류사량 측정 방법의 문제점을 보완하기 위해 소류사량을 간접계측하는 방법이 활발히 제안되고 있다. 대표적인 방법으로 하상 이동 시 소류사의 충돌음을 음향센서로 계측하여 신호처리를 통해 소류사량을 추정하는 계측기기인 하이드로폰이 있다. 그러나 국외의 소류사량 간접계측 장치는 소류사량의 운송량이 많을 경우 음향신호 중접으로 인해 펄스 수의 감소, 감지 가능한 입경크기의 제한 등의 문제가 있다. 또한 국내의 백무평(2018)이 제안한 소류사 분석 방법인 대역통과방법(B-P Method)는 소류사량 추정에 있어서 기존의 방법과는 달리 주파수 특성을 반영하여 이전 연구들에 비하여 펄스 검출률을 향상시겼지만 이 방법은 극히 낮은 저유속과 작은 입경이라는 실험조건에서 이루어졌다는 제한사항이 있다. 따라서 본 연구는 다양한 입경과 고유속에 대하여 소류사량을 정량화할 수 있는 방법을 제시하기 위해 소류사 입경이 하이드로폰에 충돌할 때 발생하는 단독입자의 충돌음을 계측하기 위한 실외 수로실험장치를 구축하여 계측을 수행하였다. 실험은 현장에서 대표 시료로 분류된 몇 가지 입경에 대해서 유량 변화에 따른 충돌음향과 소류사량 그리고 소류사 입경크기에 따른 하이드로폰에서 인지되는 음향 특성을 계측 및 분석하였다. 연구결과 입경 크기 및 수리조건 변화에 따른 하이드로폰의 충돌음향 특성을 파악하여 단일 입경별 소류사량 추정관계식을 산출하였다. 또한 산출된 추정 관계식의 특성치와 공급 소류사량 간의 관계를 유도해 보았다. 향후 혼합입경에 대한 실험과 추정 관계식 신뢰성 검토 후 추가적으로 다양한 실험조건을 고려하여 실제 하천에 운송되는 소류사량과의 교정관계 확립을 진행한다면 국내 소류사량 데이터 수집을 위한 현장 설치까지 가능할 것으로 사료된다.

• Journal of Korea Water Resources Association
• /
• v.47 no.6
• /
• pp.501-511
• /
• 2014

The effects of initial conditions and input values of the rainfall-runoff model were studied in the applications of a lumped concept model for flood event data extension. For the initial conditions of the rainfall-runoff model, baseflow effects and spatial distributions of saturation points ($R_{sa}$) for the storage function methods (SFM) were analyzed. In addition, researches on the effects of rainfall data conditions as input values for the rainfall-runoff model were performed. The Chungju Dam watershed was selected and divided into 3 catchments including smaller size of 22 sub-catchments. The observed discharge and inflow amounts at Yeongwol 1, Chungju Dam, and Yeongwol 2 water level stations were individually operated as criteria for flood data extension in 30 flood events from 1993 to 2009. Direct and base flow were distinguished from a stream flow. In order to test capability of flood data extension, obtained base flow was applied to the rainfall-runoff model for three water level stations. When base flow was adopted in the model, the Nash-Sutcliffe Efficiency(NSE) was increased. The numbers of over satisfaction for model performance (>0.5) were increased over 10%. Saturation points ($R_{sa}$) which strongly influence the runoff amount when rainfall starts were optimized based on the runoff amount at three water level stations. The sizes of saturation points for three locations were similar which means saturation point size is not depending on the runoff amount. The effects of rainfall information for flood runoff were tested at 2002ev1 and 2008ev1. When increased the amount of rainfall information, the runoff simulations were closer to the simulations with full of rainfall information. However, the size of improvement was not substantial on rainfall-runoff simulations in terms of the size of total amount of rainfall.