Real-Time Water Distribution System Hydraulic Modeling Using Prior Demand Information by Formal Bayesian Approach

Shao, Yu; Chu, Shipeng; Zhang, Tuqiao; Yang, Yue-Tzu; Yu, Tingchao

doi:10.1061/(asce)wr.1943-5452.0001137

Cited by 11 publications

(15 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent innovations in hydraulic modeling, namely the integration of both real-time measurements of water consumption in end users and valves and pump’s settings, are allowing water utilities to simulate the hydraulic behavior of the water distribution network under normal operation, with a relatively small uncertainty between computed and measured values [ 23 , 24 ]. During a pipe burst event, such models can be used to simulate distinct burst conditions in the network, thus generating training data.…”

Section: Methodsmentioning

confidence: 99%

Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks

et al. 2023

View full text Add to dashboard Cite

The current paper presents a hyper parameterization optimization process for a convolutional neural network (CNN) applied to pipe burst locations in water distribution networks (WDN). The hyper parameterization process of the CNN includes the early stopping termination criteria, dataset size, dataset normalization, training set batch size, optimizer learning rate regularization, and model structure. The study was applied using a case study of a real WDN. Obtained results indicate that the ideal model parameters consist of a CNN with a convolutional 1D layer (using 32 filters, a kernel size of 3 and strides equal to 1) for a maximum of 5000 epochs using a total of 250 datasets (using data normalization between 0 and 1 and tolerance equal to max noise) and a batch size of 500 samples per epoch step, optimized with Adam using learning rate regularization. This model was evaluated for distinct measurement noise levels and pipe burst locations. Results indicate that the parameterized model can provide a pipe burst search area with more or less dispersion depending on both the proximity of pressure sensors to the burst or the noise measurement level.

show abstract

Section: Methodsmentioning

confidence: 99%

Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks

et al. 2023

View full text Add to dashboard Cite

show abstract

“…However, this task can be challenging due to the large number of parameters involved and the limited availability of measured data. Consequently, parameter estimation often faces ill-conditioning issues, where the insufficient number of measurements leads to non-unique solutions within the search domain ( Shao et al 2019 ). In addition, uncertainties in both the measurement and model itself can significantly impact the parameter estimation accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…Kalman filter is the most well-known analytical method for state estimation in the linear system. For the non-linear system, the extended Kalman filter ( Singh et al 2022 ) and the iterative Kalman filter ( Huang et al 2022 ) have been developed, in which a linearized approximation of the system function is required ( Garcia-Fernandez et al 2012 ; Shao et al 2019 ). In the linearization of the system, the first-order gradient (Jacobian matrix) or second-order gradient (Hessian matrix) information is utilized to search for the optimal solution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling of truncated normal distribution for estimating hydraulic parameters in water distribution systems: taking nodal water demand as an example

Shao,

Li,

Zhang

et al. 2023

Journal of Hydroinformatics

Self Cite

View full text Add to dashboard Cite

The normal probability density function (PDF) is widely used in parameter estimation in the modeling of dynamic systems, assuming that the random variables are distributed at infinite intervals. However, in practice, these random variables are usually distributed in a finite region confined by the physical process and engineering practice. In this study, we address this issue through the application of truncated normal PDF. This method avoids a non-differentiable problem inherited in the truncated normal PDF at the truncation points, a limitation that can limit the use of analytical methods (e.g., Gaussian approximation). A data assimilation method with the derived formula is proposed to describe the probability of parameter and measurement noise in the truncated space. In application to a water distribution system (WDS), the proposed method leads to estimating nodal water demand and hydraulic pressure key to hydraulic and water quality model simulations. Application results to a hypothetical and a large field WDS clearly show the superiority of the proposed method in parameter estimation for WDS simulations. This improvement is essential for developing real-time hydraulic and water quality simulation and process control in field applications when the parameter and measurement noise are distributed in the finite region.

show abstract

“…Along with suitable time series databases and algorithms which are designed to analyze such time series in real-time, LPWAN technologies offer new possibilities in near real-time anomaly detection in WDS, e.g., to detect contamination events [ 14 , 15 ], cyber-attacks [ 16 ], as well as leaks and bursts [ 17 , 18 , 19 ].…”

Section: Introductionmentioning

confidence: 99%

Assessing the Potential of LPWAN Communication Technologies for Near Real-Time Leak Detection in Water Distribution Systems

Pointl

Fuchs-Hanusch

2021

Sensors

View full text Add to dashboard Cite

While low-power wide-area network (LPWAN) technologies have been studied extensively for a broad spectrum of smart city applications, their potential for water distribution system monitoring in high temporal resolution has not been studied in detail. However, due to their low power demand, these technologies offer new possibilities for operating pressure-monitoring devices for near real-time leak detection in water distribution systems (WDS). By combining long-distance wireless communication with low power consumption, LPWAN technologies promise long periods of maintenance-free device operation without having to rely on an external power source. This is of particular importance for pressure-based leak detection where optimal sensor positions are often located in the periphery of WDS without a suitable power source. To assess the potential of these technologies for replacing widely-used wireless communication technologies for leak detection, GPRS is compared with the LPWAN standards Narrowband IoT, long-range wide area network (LoRaWAN) and Sigfox. Based on sampling and transmission rates commonly applied in leak detection, the ability of these three technologies to replace GPRS is analyzed based on a self-developed low-power pressure-monitoring device and a simplified, linear energy-consumption model. The results indicate that even though some of the analyzed LPWAN technologies may suffer from contractual and technical limitations, all of them offer viable alternatives, meeting the requirements of leak detection in WDS. In accordance with existing research on data transmission with these technologies, the findings of this work show that even while retaining a compact design, which entails a limited battery capacity, pressure-monitoring devices can exceed runtimes of 5 years, as required for installation at water meters in Austria. Thus, LPWAN technologies have the potential to advance the wide application of near real-time, pressure-based leak detection in WDS, while simultaneously reducing the cost of device operation significantly.

show abstract

Real-Time Water Distribution System Hydraulic Modeling Using Prior Demand Information by Formal Bayesian Approach

Cited by 11 publications

References 43 publications

Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks

Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks

Modeling of truncated normal distribution for estimating hydraulic parameters in water distribution systems: taking nodal water demand as an example

Assessing the Potential of LPWAN Communication Technologies for Near Real-Time Leak Detection in Water Distribution Systems

Contact Info

Product

Resources

About