Article
Engineering, Environmental
Ziyuan Liao, Hexiang Yan, Zhenheng Tang, Xiaowen Chu, Tao Tao
Summary: This study introduces deep learning into the pipeline leak identification method using transient frequency response (TFR) and develops an extended framework for leak identification. The proposed framework demonstrates robustness against uncertainties and shows significant advantages over existing methods when applied to larger networks.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Chemistry, Analytical
Suan Lee, Byeonghak Kim
Summary: In this study, a machine learning-based method for water leakage detection was proposed and achieved a high accuracy of 99.79% using data collected from leak detection sensors. This method effectively reduces the time for leak detection and response, minimizing water waste and economic losses.
Article
Engineering, Mechanical
Bin Pan, Caterina Capponi, Silvia Meniconi, Bruno Brunone, Huan-Feng Duan
Summary: The paper introduces an efficient single-step frequency domain inverse transient analysis method for simultaneous identification of viscoelastic parameters and leaks in plastic pipes to enhance the applicability and accuracy of leak detection methods. Experimental validations and numerical applications demonstrate the high efficiency and accuracy of the method in detecting leaks in different viscoelastic pipe systems. The mechanism of transient wave-leak-viscoelasticity is analyzed based on application results and theoretical evidence, and a sensitivity analysis is performed to discuss the advantages and limitations of the method.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Engineering, Mechanical
Sanghyun Kim
Summary: An alternative approach for modeling the hydraulic transient response and leakage detection in reservoir pipeline valve systems has been proposed, introducing the Time-Domain Impedance Function (TIF) to address specific pipeline system transient responses and substantially improve leakage detection ability. The integration of the particle swarm optimization scheme has provided a robust evaluation capability, showing potential for leak location prediction and water hammer simulation in pipeline systems.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Engineering, Environmental
Nauman Aziz, Shujaat Ali Khan Tanoli, Faiza Nawaz
Summary: Pipelines are crucial for long-distance transportation, but leakages can lead to significant waste of natural resources. This research focuses on designing a novel leak detection system with improved sensitivity and accuracy. The proposed system demonstrates real-time leak detection sensitivity of 5 L/min and leak localization accuracy of ?8.5%.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Thermodynamics
Xuejing Zheng, Fangshu Hu, Yaran Wang, Lijun Zheng, Xinyong Gao, Huan Zhang, Shijun You, Boxiao Xu
Summary: Long-distance district heating pipelines are crucial infrastructures in large scale district heating systems, and accurate leak detection techniques are essential for maintenance and preventing heating failures. A proposed method using hydraulic transient models and PSO algorithm showed promising results in simulation tests, with high frequency and precise measurement instruments being key to effective leak detection.
Article
Engineering, Mechanical
Alireza Keramat, Huan-Feng Duan
Summary: This study focuses on using transient waves and system responses to identify leaks in water supply pipelines, proposing a new method that can accurately locate leaks with a single spatial measurement, and comparing and improving upon traditional methods.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Environmental Sciences
Jingrong Lin, Xun Wang, Mohamed S. Ghidaoui
Summary: This study introduces a leakage localization scheme that enhances leak detection accuracy by fusing multiple sensor measurements, demonstrating its success in detecting leaks in noisy environments through evidence.
WATER RESOURCES RESEARCH
(2021)
Article
Construction & Building Technology
Vahid Asghari, Mohammad Hossein Kazemi, Huan-Feng Duan, Shu-Chien Hsu, Alireza Keramat
Summary: This paper proposes a Machine Learning-based framework to detect pipe leaks using transient waves. By training an ensemble of models, the ML approach achieves high accuracy in leak detection and prediction of leak sizes, showing significant superiority over traditional methods.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Engineering, Multidisciplinary
Sang Hyun Kim
Summary: The dimensionless impedance method (DIM) provides an efficient simulation and calibration method for solving water hammer problems in pipeline systems, enabling effective comparison and analysis of hydraulic transients between different systems.
ENGINEERING APPLICATIONS OF COMPUTATIONAL FLUID MECHANICS
(2022)
Article
Environmental Sciences
Yongxin Shen, Weiping Cheng
Summary: This study develops and compares three machine learning models for assisting leak detection operations in water distribution systems. By conducting numerous on-site tests and analyzing signal features, it was found that certain features can effectively distinguish leakage signals from non-leakage signals.
Article
Management
Victor Blanco, Miguel Martinez-Anton
Summary: In this paper, a mathematical optimization-based framework is proposed to determine the location of leak detection devices along a network. Two different models are analyzed, aiming to minimize the number of devices or maximize the coverage volume. Unlike other approaches, the models in this paper allow for flexible coverage by assuming devices are located in the whole space. Experimental results on real-world water supply pipeline networks support the validity of the proposed models.
OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE
(2024)
Article
Engineering, Electrical & Electronic
Lei Yang, Qing Zhao
Summary: This paper proposes a deep learning-based method for pipeline leak detection and disturbance-assisted localization, which improves the accuracy of leak detection and localization by using pressure sequence classification and non-leak disturbance exploitation.
IEEE SENSORS JOURNAL
(2022)
Article
Engineering, Mechanical
Zahoor Ahmad, Tuan-Khai Nguyen, Akhand Rai, Jong-Myon Kim
Summary: This paper proposes a novel technique for leak detection and localization in industrial fluid pipelines. The method utilizes acoustic emission signals and a multiscale Mann-Whitney test for leak detection, and a newly developed method called acoustic emission event tracking for leak localization. The results demonstrate that this method outperforms reference methods in terms of accuracy for leak detection and localization under variable pressure and leak conditions.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Environmental Sciences
Elias Tasca, Bryan Karney, Vicente S. Fuertes-Miquel, Jose Gilberto Dalfre Filho, Edevar Luvizotto Jr
Summary: The paper evaluates the consistency of air valve characteristic curves with basic air flow principles, and finds that using inaccurate air valve characteristics in transient simulations can result in significant errors. A case study is conducted to examine the significance of these representation issues on system behavior.
Article
Engineering, Multidisciplinary
Hang Yin, Feifei Zheng, Huan-Feng Duan, Dragan Savic, Zoran Kapelan
Summary: Urban flooding is a global issue that causes significant economic losses and serious threats to public safety. Building a real-time flood risk management system is a promising approach to mitigate its impacts; however, the lack of high spatiotemporal rainfall data poses challenges. This paper proposes an image-based deep learning model to estimate urban rainfall intensity with high spatial and temporal resolution.
Article
Engineering, Multidisciplinary
Bin Pan, Alireza Keramat, Yuntong She, Huan-Feng Duan
Summary: A novel leak localization method based on forward and backward transient analysis is proposed, which utilizes discrepancies between simulation results to locate potential leaks along a pipeline. This method does not require inverse calibration and demonstrates high localization efficiency. The performance of the method is validated in a simulated oil conveyance pipeline system in a noisy environment, revealing that the accuracy may be affected by the amplification of noise in viscoelastic pipes.
Article
Engineering, Mechanical
Alireza Keramat, Huan-Feng Duan, Bin Pan, Qingzhi Hou
Summary: This study customizes an efficient optimization procedure for identifying multiple leaks in the frequency domain. The use of maximum likelihood estimation and closed-form formulations for the objective function and its gradient enables a deeper understanding of the complex optimization process required. The proposed technique shows versatility in finding leaks with a single spatial measurement vector and demonstrates efficiency and accuracy through the use of closed-form formulations.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Engineering, Mechanical
Ying Zhang, Huan-Feng Duan, Alireza Keramat, Tong-Chuan Che
Summary: The study derives the leak-induced reflection coefficient at the measurement point by incorporating additional damping effects and conducts systematic analysis of different factors using dimensional analysis and numerical simulations. Results show that the leak factor has the largest influence on the wave reflection coefficient in the pipeline system, followed by transient intensity, initial system and flow conditions, and measurement distance from the leak location. The findings aim to explain the applicability and effectiveness of the transient reflection method under varying conditions for leakage management.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Correction
Environmental Sciences
Liu Tong-Huan, Wang Yi-Kui, Wang Xie-Kang, Duan Huan-Feng, Yan Xu-Feng
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Ecology
Xu-Feng Yan, Yuan-Yuan Jia, Yu Zhang, Li-Bin Fang, Huan-Feng Duan, Xie-Kang Wang
Summary: This study experimentally evaluated the flow adjustment performance and vertical flow structure adaptive to a submerged partially distributed canopy. The canopy interior velocity adjustment distance for submerged partially distributed canopies was comparable with that for emergent ones. The vertical mixing-layer flow behaviour characterised by pronounced vertical Reynolds shear stress transversely extended into the nonobstructed region, suggesting that the canopy-side waters significantly impacted the neighbouring open flow.
Article
Engineering, Multidisciplinary
Wenke Song, Hexiang Yan, Fei Li, Tao Tao, Huanfeng Duan, Kunlun Xin, Shuping Li
Summary: This study develops a complete SPH-based Water Hammer model for Water Distribution System (SPH-WHWDS) to solve water hammer problems in practical water distribution systems. The proposed model can accurately simulate transient flows in pipeline systems by designing complex boundary condition treatment models and using the method of characteristics. It provides a new tool to study water hammer phenomena in complex water distribution systems.
ENGINEERING APPLICATIONS OF COMPUTATIONAL FLUID MECHANICS
(2023)
Article
Mechanics
Yuan-Heng Zhang, Huan-Feng Duan, Xu-Feng Yan, Alessandro Stocchino
Summary: This paper presents an experimental study on the impact of variable solid volume fractions and aspect ratios on the flow behavior and wake structure of a centre-channel rectangular porous patch. The study establishes the importance of aspect ratio in wake vortex generation. By elongating the patch, a vortex street can be generated due to the promotion of transverse velocity gradient in the wake region. The paper also proposes non-dimensional threshold maps to express the combined effects of solid volume fraction and aspect ratio on the initiation of the wake vortex street.
JOURNAL OF FLUID MECHANICS
(2023)
Article
Engineering, Civil
Husnain Tansar, Huan-Feng Duan, Ole Mark
Summary: This paper proposes a multi-objective decision-making framework for optimizing green-grey infrastructures to understand the trade-off between benefits and retrofit costs. The results show that optimal designs of grey infrastructure are more cost-effective and can significantly reduce flood damages, while green infrastructure improves the functionality of urban drainage systems better than grey infrastructure.
JOURNAL OF HYDROLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Alireza Keramat, Iman Ahmadianfar, Huan-Feng Duan, Qingzhi Hou
Summary: This study aims to combine metaheuristic and gradient-based optimization techniques to find the optimal solution of the novel objective function and locate the leak positions.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Civil
Bin Pan, Alireza Keramat, Huan-Feng Duan
Summary: This paper investigates the impacts of leaks on pipeline systems by analyzing the energy exchanges and revealing the variations in transient internal and kinetic energy intensity. The results are supported by numerical analysis and provide insight for developing transient-based leak detection methods. The limitations of this study are also summarized.
JOURNAL OF HYDRAULIC ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Husnain Tansar, H. F. Duan, Ole Mark
Summary: This study conducts a comprehensive sensitivity analysis of bioretention cell (BC) design parameters using the Stormwater Management Model (SWMM). The results show that different design parameters have unique characteristics under different storm scenarios, and their impacts on model responses dynamically change within their factor spaces. At the catchment scale, design parameters of vegetation and soil layers have significant effects on controlling stormwater, thus optimal selection of these parameters is crucial for improving the effectiveness of BC.
JOURNAL OF HYDROINFORMATICS
(2023)
Article
Engineering, Civil
Xu-Feng Yan, Huan-Feng Duan, Yuan-Heng Zhang, Xie-Kang Wang
Summary: This paper focuses on the flow characteristics of partially-distributed submerged canopy flows (PSCFs) with multiple mixing interfaces. It finds that both secondary circulations (SCs) and large-scale vortices (LSVs) contribute significantly to momentum flux. The results also show that the flow behavior in PSCFs is influenced by canopy geometric and hydraulic factors.
JOURNAL OF HYDROLOGY
(2023)
Review
Mechanics
Vincent Tjuatja, Alireza Keramat, Bin Pan, Huan-Feng Duan, Bruno Brunone, Silvia Meniconi
Summary: This paper reviews the research progress on transient waves in viscoelastic pipes, emphasizing the importance of mathematical modeling, experimental setups, and parameter calibration. Despite significant progress in the past two decades, a reliable transient wave model in viscoelastic pipes is yet to be fully confirmed.
Article
Environmental Sciences
Feifei Zheng, Hang Yin, Yiyi Ma, Huan-Feng Duan, Hoshin Gupta, Dragan Savic, Zoran Kapelan
Summary: Under global climate change, urban flooding occurs frequently, causing significant economic losses and human casualties. Estimating rainfall intensities accurately and at a high spatiotemporal resolution is crucial for real-time urban flood forecasting. A novel approach using machine learning algorithms and surveillance camera imagery shows promise in estimating rainfall intensities.
WATER RESOURCES RESEARCH
(2023)