Kibum Kim

Kibum Kim

Auto-generated profile, based on publicly available information

Kibum Kim

Purdue University, West Lafayette, IN, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 April 2023 in Urban Water Journal
Verified
Journal Article
Closed access
KKKibum Kim
Kibum Kim
HKHeechang Kang
Heechang Kang
TKTaehyeon Kim
Taehyeon Kim
DIDavid Thomas Iseley
David Thomas Iseley
JCJaeho Choi
Jaeho Choi
JKJayong Koo
Jayong Koo
Steel is a metal, and thus, it undergoes corrosion over time. The comprehensive analysis of the factors influencing corrosion can aid in developing strategies, such as new ways to avoid corrosive environments. This study explored the factors influencing pitting corrosion in steel water pipes in South Korea between 1988–2020, using artificial neural networks. Partial dependence plots and variable importance are used to identify the degree of influence of the 12 corrosion-influencing factors. Pipe age had the highest importance and strongest influence on corrosion among the corrosion-influencing factors. Soil resistivity strongly influenced external corrosion, especially at values less than 5,000 Ω-cm, and the influence of sulfide concentration on external corrosion was also relatively strong. Water alkalinity exhibited the strongest influence on internal corrosion. This study will serve as reference data for developing corrosion depth prediction models and will contribute to understanding corrosive environments when laying new pipelines and improving existing ones.

24 January 2023 in Water Supply
Verified
Journal Article
Open access
PDF file
HPHaeKeum Park
HaeKeum Park
KKKiBum Kim
KiBum Kim
JHJinseok Hyung
Jinseok Hyung
TKTaehyeon Kim
Taehyeon Kim
JKJaYong Koo
JaYong Koo
Owing to the consecutive occurrence of water quality incidents, such as the black and red water situation in Incheon, Mullae (Seoul), and Pohang, as well as the tap water larval events in Incheon and Jeju in 2020, South Korea's Ministry of Environment announced the new addition of Article 12-2 of the Enforcement Decree of the Water Supply and Waterworks Installation Act 2021. Additionally, the importance of intensive management for vulnerable areas where water quality incidents and complaints may occur repeatedly was specified. Therefore, this study suggests the hazard ranking of district-metered areas in the study area using the deterioration of the water distribution network, complaints (water quality, leakage), and modeling results (water pressure, residual chlorine concentration) to support the establishment of a reasonable water distribution network maintenance plan. The effective and sustainable maintenance of the water distribution network is possible if the hazard ranking is regularly determined using the suggested methodology proposed herein and the water distribution network intensive management area is managed.

31 May 2024 in Water Supply
Verified
Journal Article
Open access
PDF file
HPHaeKeum Park
HaeKeum Park
YOYooJin Oh
YooJin Oh
KKKibum Kim
Kibum Kim
TKTaehyeon Kim
Taehyeon Kim
JHJinseok Hyung
Jinseok Hyung
JKJayong Koo
Jayong Koo
Water distribution networks are operated to supply tap water stably, but they suffer from leakage due to various factors, resulting in poor performance. In Korea, IoT (Internet of Things)-based smart sensors are installed to reduce these leaks, and a large amount of data is collected. In this study, to solve the data uncertainty and verification of the model's field applicability, the eXtreme Gradient Boosting (XGBoost) model, which is based on boosting, was selected. This choice was made through hyperparameter optimization using leak detection data obtained from leak detection sensors, as well as data refined through on-site leak detection. The area under the curve_receiver operating characteristic value for each leak class using the XGB model was 0.9955 for class 0, 0.9956 for class 1, and 0.9985 for class 2. In addition, the partial dependence plot of 120 Hz, which has the highest variable importance, was derived from analyzing the influence of the leak detection and classification model on the amount of leak vibration change at 120 Hz. Therefore, it is expectged the suggested methods can be used to build a GIS-based monitoring system for real-time leak detection by linking the developed model and the location of the leak detection sensor.

15 May 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
DODahyun Oh
Dahyun Oh
KKKyubyung Kang
Kyubyung Kang
SSSungchul Seo
Sungchul Seo
JXJinwu Xiao
Jinwu Xiao
Kyochul JangKyochul Jang
Kyochul Jang
JWJeong-Hun Won
Jeong-Hun Won
Automated inspection systems utilizing computer vision technology are effective in managing traffic control devices (TCDs); however, they face challenges due to the limited availability of training datasets and the difficulty in generating new datasets. To address this, our study establishes a benchmark for cost-effective model training methods that achieve the desired accuracy using data from related domains and YOLOv5, a one-stage object detector known for its high accuracy and speed. In this study, three model cases were developed using distinct training approaches: (1) training with COCO-based pre-trained weights, (2) training with pre-trained weights from the source domain, and (3) training with a synthesized dataset mixed with source and target domains. Upon comparing these model cases, this study found that directly applying source domain data to the target domain is unfeasible, and a small amount of target domain data is necessary for optimal performance. A model trained with fine-tuning-based domain adaptation using pre-trained weights from the source domain and minimal target data, proved to be the most resource-efficient approach. These results contribute valuable guidance for practitioners aiming to develop TCD models with limited data, enabling them to build optimal models while conserving resources.

1 December 2024 in AQUA — Water Infrastructure, Ecosystems and Society
Verified
Journal Article
Open access
PDF file
KKKibum Kim
Kibum Kim
TKTaehyeon Kim
Taehyeon Kim
KKKyubyung Kang
Kyubyung Kang
JKJayong Koo
Jayong Koo
The increasing issue of aging water pipes highlights the need for a long-term renewal investment plan to respond effectively within constrained resources. This study proposes an optimization method designed to minimize life cycle costs while considering the structural safety of pipes and economic efficiency in pipe renewals. The method consists of two prediction models: artificial neural network (ANN)-based corrosion prediction models and ANN-based failure rate prediction models. This study uses these models to develop a dynamic programming (DP)-based optimization method that meets annual budget constraints. It applies successfully to a target area of conveyance pipe networks. Moreover, the findings demonstrate that adhering to annual budget constraints allows water utilities to allocate their budgets efficiently, facilitating strategic investments within set yearly limits. These findings offer substantial promise as foundational technologies for the asset management of water supply infrastructures, highlighting their potential for future applicability and value.

1 November 2023 in Journal of Pipeline Systems Engineering and Practice
Verified
Journal Article
Closed access
KKKibum Kim
Kibum Kim
JKJayong Koo
Jayong Koo
DIDavid Thomas Iseley
David Thomas Iseley
HPHaekeum Park
Haekeum Park
TKTaehyeon Kim
Taehyeon Kim
JHJinseok Hyung
Jinseok Hyung