HKHyunjun Kim

Hyunjun Kim

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hyunjun Kim has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Assessment and Variation of Water Quality in Urban Distribution Networks: From Reservoir to Faucet

    by Eunhye Jeong, Kyung-Yup Hwang, Sumin Lee, Kwangjun Jung, Hyunjun Kim

    This study focuses on evaluating the spatiotemporal variations in water quality across a potable water distribution network in D City, South Korea, spanning from a reservoir to a large consumer’s tap. Utilizing water quality sensors installed at strategic points (the reservoir, District Metered Area inlet, consumer inlet, tank outlet, and tap), this research observes real-time changes in parameters such as chlorine concentration, turbidity, temperature, pH, and electrical conductivity. The investigation, conducted from 25 January 2024 to 4 February 2024, identifies significant trends such as the gradual decrease in chlorine concentration with distance and time, an increase in turbidity and temperature towards the consumer end, and variations in electrical conductivity. These observations suggest that there is an influence of pipe material interactions, water stagnation, and usage patterns on water quality. This study contributes to understanding the dynamic nature of tap water’s quality, highlighting the need for continuous monitoring and research to manage water quality effectively in urban distribution networks.

  • Open Access

    Rapid response to pressure variations in water distribution networks through machine learning-enhanced data acquisition

    by Hyunjun Kim, K. J. Jung, S. Lee, E. H. Jeong

    This study investigates rapid dynamic pressure variations in water distribution networks due to critical incidents such as pipe bursts and valve operations. We developed and implemented a machine learning (ML)-based methodology that surpasses traditional slow cycles of pressure data acquisition, facilitating the efficient capture of transient phenomena. Employing the Orion ML library, which features advanced algorithms including long short-term memory dynamic threshold, autoencoder with regression, and time series anomaly detection using generative adversarial networks, we engineered a system that dynamically adjusts data acquisition frequencies to enhance the detection and analysis of anomalies indicative of system failures. The system's performance was extensively tested using a pilot-scale water distribution network across diverse operational conditions, yielding significant enhancements in detecting leaks, blockages, and other anomalies. The effectiveness of this approach was further confirmed in real-world settings, demonstrating its operational feasibility and potential for integration into existing water distribution infrastructures. By optimizing data acquisition based on learned data patterns and detected anomalies, our approach introduces a novel solution to the conventionally resource-intensive practice of high-frequency monitoring. This study underscores the critical role of advanced ML techniques in water network management and explores future possibilities for adaptive monitoring systems across various infrastructural applications.


  • Open Access

    Enhanced gate-valve failure detection in water distribution networks using ML and pressure data

    by Hyunjun Kim, Kwangjun Jung, Sumin Lee, Eunhye Jeong

    This study introduces an innovative diagnostic approach for identifying gate-valve failures in water distribution systems. By implementing high-frequency pressure sensors upstream and downstream of the gate valves, we obtained detailed pressure data that are pivotal for fault diagnosis. We explored three distinct machine-learning algorithms and two data-handling techniques to ensure optimal performance in real-world applications. In our methodology, supervised learning algorithms are used to analyze pressure differentials and predict valve behavior. We rigorously tested these algorithms using both raw and feature-engineered data, and the results indicated the effectiveness of the Gaussian-naïve Bayes model with six extracted features. This approach enhances the precision and reliability of diagnostics in water distribution networks.


  • Experimental and Numerical Study of Air Vessel in Quasi-Two-Dimensional Transient Flow Analysis

    by Hyunjun Kim, Lakwon Choi, Sanghyun Kim

    An air vessel is a simple and effective device for protecting a pipeline system from abnormal pressure events. In order to design and select a suitable air vessel, analysis of the pipeline system is necessary. A quasi-2D approach can overcome some of the limitations of the conventional one-dimensional transient flow analysis method. However, only a few hydraulic components can be implemented in the quasi-2D approach. In this study, we propose a methodology for applying an air vessel in the quasi-2D model. An experimental study is performed for validating the proposed model. Although an identical approach involving an accumulator model is used to model the air vessel as in the 1D model, the quasi-2D model shows improved performance for the experimental system.


  • A Generalized Procedure for Pipeline Hydraulic Components in Quasi-Two-Dimensional Unsteady Flow Analysis

    by Hyunjun Kim, Sanghyun Kim

    Quasi-two-dimensional (2D) modeling of unsteady flow is important for the accurate prediction of flow and pressure in pipeline systems. In this study, a generalized method is developed to consider various inline components such as junctions and inline valves for quasi-2D method of characteristic (MOC). The occurrence of vaporous cavitation is incorporated into the developed scheme under transient conditions. To address the discharge and pressure profile at the generalized component, a procedure is proposed to obtain the convergence satisfying the characteristic equations and hydraulic structure function. The validity of the developed method is tested for two different pipeline systems. Good agreements of transient pressure between simulations and experimental results are obtained, thus demonstrating the predictability of the developed method for junctions and inline valves with vaporous cavitation.


  • Two dimensional cavitation waterhammer model for a reservoir-pipeline-valve system

    by Hyunjun Kim, Sanghyun Kim

    A waterhammer model was proposed to simulate a transient event with cavitation in a simple pipeline system. The governing equations for a quasi-two-dimensional model were solved through a hybrid scheme of the method of characteristics and the finite difference method considering the relationship between pressure head reduction and cavitation. An alternative method to address the boundary condition for the two-dimensional model was proposed, which improved the stability of the existing approaches. The comparison of longitudinal and radial velocity profiles between the proposed and existing models exhibited significant differences, which can be explained by the sequential generation and collapse of the cavity. The time series of the pressure head obtained through experimental transient events with vapour cavitation showed good agreement with that of the proposed model. The investigation of energy under a waterhammer showed that the pattern of transition between internal energy and kinetic energy is also substantially affected by the fate of cavitation during transient events.


  • Optimization of Operation Parameters for Direct Spring Loaded Pressure Relief Valve in a Pipeline System

    by Hyunjun Kim, Sanghyun Kim, Youngman Kim, Jonghwan Kim

    A direct spring loaded pressure relief valve (DSLPRV) is an efficient hydraulic structure used to control a potential water hammer in pipeline systems. The optimization of a DSLPRV was explored to consider the instability issue of a valve disk and the surge control for a pipeline system. A surge analysis scheme, named the method of characteristics, was implemented into a multiple-objective genetic algorithm to determine the adjustable factors in the operation of the DSLPRV. The forward transient analysis and multi-objective optimization of adjustable factors, such as the spring constant, degree of precompression, and disk mass, showed substantial relaxation in the surge pressure and oscillation of valve disk in a hypothetical pipeline system. The results of the regression analysis of surge were compared with the optimization results to demonstrate the potential of the developed method to substantially reduce computational costs.