Leakage separation in multi-leaks pipe networks based on improved Independent Component Analysis with Reference (ICA-R) algorithm

Yuanzhe Li; Jinliang Gao; Wenyan Wu; Cai Jian; Shiyuan Hu; Jianyu Li; Jianwei Ding; Ming Cui; Shuhe Zou

Leakage separation in multi-leaks pipe networks based on improved Independent Component Analysis with Reference (ICA-R) algorithm

Yuanzhe Li^*
, Jinliang Gao
, Wenyan Wu
, Cai Jian
, Shiyuan Hu
, Jianyu Li
, Jianwei Ding
, Ming Cui
, Shuhe Zou

^*Corresponding author for this work

School of Environment

Harbin Institute of Technology
Birmingham City University
Ji Xi Chenergy Water Co.Ltd. Jixi
Harbin Gongda Water and Waste Water Technology Co. Ltd

Research output: Contribution to conference › Paper › peer-review

Abstract

The existing leakage assessment methods are not accurate and timely, making it difficult to meet the needs of water companies. In this paper, a methodology based on Independent Component Analysis with Reference (ICA-R) algorithm was proposed to give a more accurate estimation of leakage discharge in multi-leaks water distribution network without considering the specific individual single leak. The proposed algorithm has been improved to prevent error convergence in multi-leak pipe networks. Then an EPANET model and a physical experimental platform were built to simulate the flow in multi-leak WDNs, and the leakage flow rate is calculated by improved ICA-R algorithm and FastICA algorithm. The simulation results are shown the improved ICA-R algorithm has better performance.

Original language	English
State	Published - 2018
Event	1st International Joint Conference in Water Distribution Systems Analysis and Computing and Control in the Water Industry, WDSA/CCWI 2018 - Kingston, Canada Duration: 23 Jul 2018 → 25 Jul 2018

Conference

Conference	1st International Joint Conference in Water Distribution Systems Analysis and Computing and Control in the Water Industry, WDSA/CCWI 2018
Country/Territory	Canada
City	Kingston
Period	23/07/18 → 25/07/18

Keywords

Blind source separation
Improved Independent Component Correlation algorithm with reference(ICA-R)
Physical leakage flow

Cite this

Li, Y., Gao, J., Wu, W., Jian, C., Hu, S., Li, J., Ding, J., Cui, M., & Zou, S. (2018). Leakage separation in multi-leaks pipe networks based on improved Independent Component Analysis with Reference (ICA-R) algorithm. Paper presented at 1st International Joint Conference in Water Distribution Systems Analysis and Computing and Control in the Water Industry, WDSA/CCWI 2018, Kingston, Canada.

@conference{74b25ad32ffd45f88028854fd1d85d34,

title = "Leakage separation in multi-leaks pipe networks based on improved Independent Component Analysis with Reference (ICA-R) algorithm",

abstract = "The existing leakage assessment methods are not accurate and timely, making it difficult to meet the needs of water companies. In this paper, a methodology based on Independent Component Analysis with Reference (ICA-R) algorithm was proposed to give a more accurate estimation of leakage discharge in multi-leaks water distribution network without considering the specific individual single leak. The proposed algorithm has been improved to prevent error convergence in multi-leak pipe networks. Then an EPANET model and a physical experimental platform were built to simulate the flow in multi-leak WDNs, and the leakage flow rate is calculated by improved ICA-R algorithm and FastICA algorithm. The simulation results are shown the improved ICA-R algorithm has better performance.",

keywords = "Blind source separation, Improved Independent Component Correlation algorithm with reference(ICA-R), Physical leakage flow",

author = "Yuanzhe Li and Jinliang Gao and Wenyan Wu and Cai Jian and Shiyuan Hu and Jianyu Li and Jianwei Ding and Ming Cui and Shuhe Zou",

note = "Publisher Copyright: {\textcopyright} 2018 1st International WDSA / CCWI 2018 Joint Conference. All rights reserved.; 1st International Joint Conference in Water Distribution Systems Analysis and Computing and Control in the Water Industry, WDSA/CCWI 2018 ; Conference date: 23-07-2018 Through 25-07-2018",

year = "2018",

language = "英语",

}

Li, Y, Gao, J, Wu, W, Jian, C, Hu, S, Li, J, Ding, J, Cui, M & Zou, S 2018, 'Leakage separation in multi-leaks pipe networks based on improved Independent Component Analysis with Reference (ICA-R) algorithm', Paper presented at 1st International Joint Conference in Water Distribution Systems Analysis and Computing and Control in the Water Industry, WDSA/CCWI 2018, Kingston, Canada, 23/07/18 - 25/07/18.

Leakage separation in multi-leaks pipe networks based on improved Independent Component Analysis with Reference (ICA-R) algorithm. / Li, Yuanzhe; Gao, Jinliang; Wu, Wenyan et al.
2018. Paper presented at 1st International Joint Conference in Water Distribution Systems Analysis and Computing and Control in the Water Industry, WDSA/CCWI 2018, Kingston, Canada.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Leakage separation in multi-leaks pipe networks based on improved Independent Component Analysis with Reference (ICA-R) algorithm

AU - Li, Yuanzhe

AU - Gao, Jinliang

AU - Wu, Wenyan

AU - Jian, Cai

AU - Hu, Shiyuan

AU - Li, Jianyu

AU - Ding, Jianwei

AU - Cui, Ming

AU - Zou, Shuhe

PY - 2018

Y1 - 2018

N2 - The existing leakage assessment methods are not accurate and timely, making it difficult to meet the needs of water companies. In this paper, a methodology based on Independent Component Analysis with Reference (ICA-R) algorithm was proposed to give a more accurate estimation of leakage discharge in multi-leaks water distribution network without considering the specific individual single leak. The proposed algorithm has been improved to prevent error convergence in multi-leak pipe networks. Then an EPANET model and a physical experimental platform were built to simulate the flow in multi-leak WDNs, and the leakage flow rate is calculated by improved ICA-R algorithm and FastICA algorithm. The simulation results are shown the improved ICA-R algorithm has better performance.

AB - The existing leakage assessment methods are not accurate and timely, making it difficult to meet the needs of water companies. In this paper, a methodology based on Independent Component Analysis with Reference (ICA-R) algorithm was proposed to give a more accurate estimation of leakage discharge in multi-leaks water distribution network without considering the specific individual single leak. The proposed algorithm has been improved to prevent error convergence in multi-leak pipe networks. Then an EPANET model and a physical experimental platform were built to simulate the flow in multi-leak WDNs, and the leakage flow rate is calculated by improved ICA-R algorithm and FastICA algorithm. The simulation results are shown the improved ICA-R algorithm has better performance.

KW - Blind source separation

KW - Improved Independent Component Correlation algorithm with reference(ICA-R)

KW - Physical leakage flow

UR - https://www.scopus.com/pages/publications/85093890964

M3 - 论文

AN - SCOPUS:85093890964

T2 - 1st International Joint Conference in Water Distribution Systems Analysis and Computing and Control in the Water Industry, WDSA/CCWI 2018

Y2 - 23 July 2018 through 25 July 2018

ER -

Leakage separation in multi-leaks pipe networks based on improved Independent Component Analysis with Reference (ICA-R) algorithm

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this