• Journal of Korean Society of Water and Wastewater
• /
• v.27 no.6
• /
• pp.679-687
• /
• 2013

Although stable and safe drinking water supply to the customers is a basic function of multi-regional water supply systems in Korea, most systems have their vulnerabilities in emergency time due to the branch-type. Application of connections from the other water supply system can provide a solutions for these tentative problems. This paper describes reduction planning of water supply accidents that can minimize a service interruption to customers in multi-regional water supply system by connecting pipe lines between local water supply systems in Mokpo city areas. The result of this study shows that Juam dam multi-regional water supply systems can cover all of the water shortage in southern parts of Jeonnam multi-regional water supply systems by transmitting water through connected pipes between local networks. This can be effective to supply water interactively in various contingencies, when a pipe line accident occurs in southern area of Jeonnam multi-regional water supply systems. On the contrary, southern area of Jeonnam multi-regional water supply systems can cover 99.5 %($62,500m^3/day$) of the water shortage of Juam dam multi-regional water supply systems when service interruptions caused by various pipe accidents occur in the system.

• Nuclear Engineering and Technology
• /
• v.52 no.11
• /
• pp.2678-2685
• /
• 2020

The pipe bends and elbows in nuclear power plants (NPPs) are vulnerable to degradation mechanisms and can cause wall-thinning defects. As it is difficult to detect both the defects generated inside the wall-thinned pipes and the preliminary signs, the wall-thinning defects should be accurately estimated to maintain the integrity of NPPs. This paper proposes a deep fuzzy neural network (DFNN) method and estimates the collapse moment of wall-thinned pipe bends and elbows. The proposed model has a simplified structure in which the fuzzy neural network module is repeatedly connected, and it is optimized using the least squares method and genetic algorithm. Numerical data obtained through simulations on the pipe bends and elbows with extrados, intrados, and crown defects were applied to the DFNN model to estimate the collapse moment. The acquired databases were divided into training, optimization, and test datasets and used to train and verify the estimation model. Consequently, the relative root mean square (RMS) errors of the estimated collapse moment at all the defect locations were within 0.25% for the test data. Such a low RMS error indicates that the DFNN model is accurate in estimating the collapse moment for wall-thinned pipe bends and elbows.

• Journal of Korea Water Resources Association
• /
• v.51 no.2
• /
• pp.121-129
• /
• 2018

Rainfall falling in the impervious area of the cities flows over the surface and into the stormwater pipe networks to be discharged from the catchment. Therefore, it is very important to determine the size of stormwater pipes based on the peak discharge to mitigate urban flood. Climate change causes the severe rainfall in the small area, then the peak rainfall can not be discharged due to the capacity of the stormwater pipes and causes the urban flood for the short time periods. To mitigate these type of flood, the large stormwater pipes have to be constructed. However, the economic factor is also very important to design the stormwater pipe networks. In this study, 4 urban catchments were selected from the frequently flooded cities. Rainfall data from Seoul and Busan weather stations were applied to calculate runoff from the catchments using SWMM model. The characteristics of the peak runoff were analyzed using linear regression model and the 95% confidence interval and the coefficient of variation was calculated. The drainage density was calculated and the runoff characteristics were analyzed. As a result, the drainage density were depended on the structure of stormwater pipe network whether the structures are dendritic or looped. As the drainage density become higher, the runoff could be predicted more accurately. it is because the possibility of flooding caused by the capacity of stormwater pipes is decreased when the drainage density is high. It would be very efficient if the structure of stormwater pipe network is considered when the network is designed.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.589-597
• /
• 2021

In this study, corrosion depth equation was suggested according to real measured corrosion data, and then management indexes of pipe network which can determine the deterioration rate and safety rate has been established and applied to real pipe networks. Furthermore, reliability analysis and management index analysis have been conducted to estimate and compare the deterioration rate. From the results of reliability analysis, it was found that probability of failure of 200 mm steel pipe can be increased from 4.36% at present time to 8.23% after 20years at Gaduk and from 7.35% to 12.99% at Nami. From the results of management index analysis, it was found that deterioration rates of Gaduk and Nami are 1.009 and 1.174, respectively. Priority of improvement and replacement of water pipe can be determined by results of reliability analysis and management index analysis.

• Journal of Korea Water Resources Association
• /
• v.42 no.7
• /
• pp.525-535
• /
• 2009

In this paper a heuristic method for identifying individual pipes in water pipe networks to determine specific sections of the pipes that need to be replaced due to deterioration. An appropriate minimum pipe length is determined by selecting the pipe length that has the greatest variance of the average cumulative break number slopes among the various pipe lengths used. As a result, the minimum pipe length for the case study water network is determined as 4 m and a total of 39 individual pipe IDs are obtained. The economically optimal replacement times of the individual pipe IDs are estimated by using the threshold break rate of an individual pipe ID and the pipe break trends models for which the General Pipe Break Prediction Model(Park and Loganathan, 2002) that can incorporate the linear, exponential, and in-between of the linear and exponetial failure trends and the ROCOFs based on the modified time scale(Park et al., 2007) are used. The maximum log-likelihoods of the log-linear ROCOF and Weibull ROCOF estimated for the break data of a pipe are compared and the ROCOF that has a greater likelihood is selected for the pipe of interest. The effects of the social costs of a pipe break on the optimal replacement time are also discussed.

• Nuclear Engineering and Technology
• /
• v.53 no.12
• /
• pp.4060-4066
• /
• 2021

Flow-accelerated corrosion (FAC) of carbon steel piping is a significant problem in nuclear power plants. The basic process of FAC is currently understood relatively well; however, the accuracy of prediction models of the wall-thinning rate under an FAC environment is not reliable. Herein, we propose a methodology to construct pipe wall-thinning rate prediction models using artificial neural networks and a convolutional neural network, which is confined to a straight pipe without geometric changes. Furthermore, a methodology to generate training data is proposed to efficiently train the neural network for the development of a machine learning-based FAC prediction model. Consequently, it is concluded that machine learning can be used to construct pipe wall thinning rate prediction models and optimize the number of training datasets for training the machine learning algorithm. The proposed methodology can be applied to efficiently generate a large dataset from an FAC test to develop a wall thinning rate prediction model for a real situation.

• Fire Science and Engineering
• /
• v.21 no.4
• /
• pp.1-11
• /
• 2007

This study aims to investigate, review, and summarize the definition, development, and applications of "percent agent in pipe", "percent of agent in pipe" which is used as a key factor in testing and evaluating the performance of gaseous fire extinguishing agents, including Halon 1301 and $CO_2$. This study also analyzes and compares the local and international standards on testing and evaluating the performance of gaseous fire extinguishing systems, as well as the results of system performance tests conducted as a part of performance evaluation and approval programs for gaseous fire extinguishing systems, especially, Korean Gaseous Fire Extinguishing System Performance Approval Program called KFI Approval. Percent agent in pipe was defined first in NFPA 12A, Standard on Halon 1301 Fire Extinguishing Systems, dating back to the 1970's. After the phaseout of Halon 1301 systems in 1994 in the developed countries, the percent agent in pipe has been widely used in Halon 1301 alternative clean agent fire extinguishing systems, both halocarbon clean agent systems and inert gas clean agent systems, as an essential criterion to assure the system design accuracy, determine the limitations and performance of a system, and to predict the system performance results accurately, especially, in association with their system flow calculations. Underwriters Laboratories has their own standards such as UL 2127 and 2166 applying percent agent in pipe in testing and evaluating the performance of clean agent fire extinguishing systems. As a part of a system performance test and approval program called KFI Approval System, Korea also has started to apply the percent agent in pipe as a key factor to test, evaluate, and approve the performance of gaseous fire extinguishing systems, including both high and low pressure $CO_2$ systems, from the early 2000's. This study outlines and summarizes the relevant UL and KFI standards and also describes the actual test resultant data, including the maximum percents of agent in pipe for gaseous fire extinguishing systems. As evidenced in lots of tests conducted as a part of the system performance test and approval programs like KFI Approval System, it has been proven that the percent agent in pipe may work as a key factor in testing, evaluating, and determining the limitations and performance of gaseous fire extinguishing systems, especially compared with the hydraulic flow calculations of computer design programs of gaseous fire extinguishing systems, and will remain as such in the future. As one thing to note, however, there are some difficulties in using the unified percent agent in pipe to determine the maximum lengths of pipe networks for gaseous fire extinguishing systems, because the varying definitions used by some of the flow calculations (not in accordance with NFPA 12A definition) make it impossible to do any direct comparison of pipe lengths based on percent agent in pipe.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.2
• /
• pp.27-37
• /
• 2021

In this paper, we propose Automatic detection system of underground pipe which automatically detects underground pipe to help experts. Actual location of underground pipe does not match with blueprint due to various factors such as ground changes over time, construction discrepancies, etc. So, various accidents occur during excavation or just by ageing. Locating underground utilities is done through GPR exploration to prevent these accidents but there are shortage of experts, because GPR data is enormous and takes long time to analyze. In this paper, To analyze 3D GPR data automatically, we use 3D image segmentation, one of deep learning technique, and propose proper data generation algorithm. We also propose data augmentation technique and pre-processing module that are adequate to GPR data. In experiment results, we found the possibility for pipe analysis using image segmentation through our system recorded the performance of F1 score 40.4%.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.09a
• /
• pp.221-222
• /
• 2005

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.09a
• /
• pp.285-286
• /
• 2005