Young Hwan Choi

Water pipe systems, which are a type of social infrastructure, provide essential services for human life. However, as they are buried underground, access is limited, causing considerable difficulty in internal exploration for maintenance. Previous defect detection in sewer pipes is relatively straightforward due to stable camera positioning and clear image geometry under water shutdown conditions. However, in water distribution pipes, where inspection must be performed using nondisruptive (non‐shutdown) endoscopic cameras, varying camera orientation and image distortion make defect detection and quantification significantly more challenging. To address this, this study proposes a method for estimating the vanishing point from monocular endoscopic images to geometrically align the view and reduce perspective distortion, enabling more accurate defect analysis. The proposed monocular vanishing point detection (Cs‐MVP) technique utilizes brightness channel extraction, binarization, Canny edge detection, and the Hough circles method to detect circular cross‐sections and estimate the vanishing point. The proposed method is capable of detecting reliable vanishing points with an average measurement accuracy exceeding 96% in refined environments. Although results indicate that area errors of up to 1.5 times may occur under intense noise conditions, this approach minimizes human error typically associated with conventional secondary manual evaluations. By providing essential geometric cues for defect assessment, the method is expected to support more objective and scientific maintenance decision‐making.

Leakage events occurring at multiple locations simultaneously generate overlapping and topology-dependent pressure signatures, making reliable detection and subsequent restoration planning a persistent challenge in water distribution systems (WDSs). While recent data-driven techniques have improved the ability to identify anomalous hydraulic behavior, most approaches remain limited to the detection stage and offer little guidance on how utilities should prioritize repairs once multiple failures are identified. To bridge this gap, this study proposes an integrated framework that links topology-aware leakage detection with quantitative restoration prioritization. First, a multi-task learning framework based on Graph Attention Networks (GAT) is employed to jointly detect both the location and magnitude of multiple leakages by explicitly incorporating hydraulic responses and network topology into the learning process. The model’s detection robustness is evaluated across networks with contrasting looped, branched, and hybrid topologies to examine how structural characteristics influence detection accuracy under multi-event conditions. Second, the study develops a restoration-planning module that constructs a two-objective decision space combining restoration cost and segment vulnerability, where the latter accounts for disruption potential arising from hydraulic importance and local service connectivity. Non-dominated sorting is used to derive Pareto-optimal restoration sequences, enabling explicit quantification of the trade-offs between operational cost and service disruption. This provides decision-makers with a ranked set of restoration orders that reflect both hydraulic impact and functional risk, rather than relying on heuristics or cost-only criteria. Notably, the proposed framework separates offline training from online inference, requiring only a single forward pass for real-time decision-making without the need for iterative hydraulic simulations. Results demonstrate that topology strongly governs both detection performance and the structure of optimal repair sequences, underscoring the importance of integrating network-aware learning with multi-criteria restoration evaluation.

Aging water pipelines are increasingly prone to structural failure, leakage, and ground subsidence, creating critical risks to urban infrastructure. Closed-circuit television endoscopy is widely used for internal assessment, but it depends on manual interpretation and lacks reliable quantitative defect information. Traditional vanishing point detection techniques, such as the Hough Transform, often fail under practical conditions due to irregular lighting, debris, and deformed pipe surfaces, especially when pipes are water-filled. To overcome these challenges, this study introduces a deep learning-based method that estimates inverse projection parameters from monocular endoscopic images. The proposed approach reconstructs a spatially accurate two-dimensional projection of the pipe interior from a single frame, enabling defect quantification for cracks, scaling, and delamination. This eliminates the need for stereo cameras or additional sensors, providing a robust and cost-effective solution compatible with existing inspection systems. By integrating convolutional neural networks with geometric projection estimation, the framework advances computational intelligence applications in pipeline condition monitoring. Experimental validation demonstrates high accuracy in pose estimation and defect size recovery, confirming the potential of the system for automated, non-disruptive pipeline health evaluation.

The safety of aging dam infrastructure has emerged as a critical issue as many social infrastructure systems experience functional degradation over time. While numerous monitoring devices have been deployed to evaluate dam conditions, the reliability of measurement data is often compromised due to harsh environmental factors, missing values, and abnormal fluctuations. These challenges highlight the necessity of ensuring data quality through both accurate point-level validation and comprehensive pattern analysis. Existing approaches often fail to systematically distinguish between environmental conditions such as rainfall and non-rainfall events, limiting the predictive reliability of artificial intelligence (AI) models in dam safety applications. To address this limitation, this study proposes a robust prediction framework that combines targeted data preprocessing with an eXtreme Gradient Boosting (XGBoost) model to enhance the reliability of dam measurement forecasts. Measurement data from infiltration turbidity and leakage meters were categorized based on rainfall occurrence to reflect environmental variability. The preprocessing method emphasizes structured training data reconstruction rather than the simple removal of outliers by identifying and separating time segments influenced by rainfall events. The proposed approach allows the model to better capture complex nonlinear patterns in dam behavior and improves prediction accuracy across various dam conditions. This study offers a practical contribution to the development of high-reliability forecasting systems for dam monitoring and lays the groundwork for future adaptive dam safety management strategies.

This study proposes an integrated performance evaluation system to prioritize the repair and reinforcement of water distribution systems (WDSs). Recognizing that aging infrastructure poses risks such as pipe failures and water quality degradation, the integrated performance evaluation system offers a comprehensive assessment approach, addressing the limitations of traditional evaluation methods that are constrained by time and cost. The system integrates both direct and indirect performance evaluations, focusing on factors such as pipeline aging, hydraulic stability, and water quality safety. The system also evaluates hydraulic stability by simulating pressure fluctuations and water quality through the analysis of water residence times under varying demand conditions. To systematically determine repair and reinforcement priorities, the analytic hierarchy process is applied, assigning weights to each evaluation factor based on its relative importance. By simulating hypothetical abnormal scenarios, such as pipeline failures, the system estimates potential damage and the risk to water supply blocks. These evaluations provide valuable insights into the vulnerability of different sections of the WDSs, supporting informed decision-making for maintenance planning. The integrated approach of the integrated performance evaluation system not only ensures a more reliable and data-driven prioritization process but also enhances preparedness for abnormal system conditions. The framework is validated through applications in real-world water distribution networks, demonstrating its effectiveness in guiding resource allocation and maintenance efforts for long-term system stability.

In the water supply system, for stable operation and management, pressure control, and energy consumption are important factors. However, gravity flow water supply systems can cause leaks and pipe damage when high pressure from upstream moves downstream. Therefore, the only popular way to control pressure within an acceptable range is to use a pressure reduction valve to control pressure within an appropriate range. However, using only the pressure reduction valve causes indiscriminate energy waste in operating and managing the water supply system. Accordingly, a micro-hydro turbine was proposed to replace the pressure reduction valve to provide appropriate pressure control and energy recovery. In addition, existing micro-hydro turbine designs were designed with only energy recovery in mind, but for sustainable operation, various design factors must be considered for optimal design. However, in design, EPANET2.2, the model simulation program in this study, does not have a model that can calculate the size of the turbine, so it is replaced with the pressure reduction valve and designed using the corresponding pressure and flow rate. Therefore, in this study, the range that satisfies the appropriate pressure condition is determined by using the pressure reduction valve (if a micro-hydro turbine is used with a surplus pressure head considering appropriate pressure control, the potential energy recovery amount can be determined). Therefore, a multi-objective optimal design technique was proposed that can optimize objective functions such as energy recovery and installation cost. The optimization technique is a multi-objective harmony search, and benchmark networks were applied to verify the proposed methodology. Through this study, it is expected that it can be effectively used in the sustainable operation of the water supply system by considering various design factors through adjustment of the set pressure.

Recent statistics indicate that the national water supply coverage is approximately 99%, reflecting a high level of service. However, the aging infrastructure continues to cause issues such as pipe failures and water quality concerns, creating operational difficulties. To solve these issues, performance assessments are used to quantitatively evaluate the system conditions and ensure effective maintenance. In Korea, these assessments are based on a scoring system that combines direct and indirect assessments. However, direct assessment of all pipes is limited by cost and time constraints. To address this issue, a deep neural network is used to assess the aging of water distribution systems. This study develops a framework to estimate direct results from indirect data by analyzing the correlation between indirect and direct assessments. Additionally, data augmentation is considered to compensate for the lack of training data in direct assessments, improve the reliability of performance assessments, and support better prioritization in system maintenance.