Health status assessment of pump station units based on spatio-temporal fusion and uncertainty information DOI Creative Commons

Panpan Qiu,

Jianzhuo Yan,

Hongxia Xu

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 15, 2024

An effective health status assessment (HSA) for pump station units (PSUs) is crucial accurately determining their real and providing technical support safe operational decisions. Due to the limitations of existing data-driven HSA methods, which primarily focus on temporal dependencies monitoring signals fail explore complex interconnections among comprehensively. Moreover, when constructing performance degradation indices based linear differences, these methods do not effectively integrate heterogeneous signals, resulting in an incomplete inaccurate overall system degradation. This paper proposes a real-time comprehensive method PSUs multi-source uncertainty information. Initially, benchmark model (HBM) built using CrossGNN, possesses cross-scale cross-variable interaction capabilities, precisely capture dynamic relationships variables signals. Subsequently, key measurement points that reflect are identified through correlation analysis establish evaluation indices. Then, considering signal changes, novel index (HDI) developed Mahalanobis distance (MD) Gaussian Cloud Model (GCM) analyze changes unit status. Furthermore, weighting calculation non-dominated sorting genetic algorithm (NSGA-II) proposed (RCHDI) thorough Finally, effectiveness validated case study data from South-to-North Water Diversion Project China. The results show that, compared other studies, significantly improves stability smoothness state curve, with increases 21.5% 47.1% respectively, new perspective comprehensively assessing PSUs.V.

Language: Английский

Heterogeneous graph contrastive learning-based transductive health condition assessment of Francis turbine unit DOI
Fengyuan Zhang, Jie Liu, Yujie Liu

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 145, P. 110240 - 110240

Published: Feb. 13, 2025

Language: Английский

Citations

2
An intelligent lithology recognition system for continental shale by using digital coring images and convolutional neural networks DOI
Zhuo Zhang, Jizhou Tang, Bo Fan

et al.

Geoenergy Science and Engineering, Journal Year: 2024, Volume and Issue: 239, P. 212909 - 212909

Published: May 10, 2024

Language: Английский

Citations

7
Machine learning-driven high-fidelity ensemble surrogate modeling of Francis turbine unit based on data-model interactive simulation DOI
Jian Wang, Jie Liu, Yanglong Lu

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 133, P. 108385 - 108385

Published: April 11, 2024

Language: Английский

Citations

5
Research on the Health Evaluation of a Pump Turbine in Smoothing Output Volatility of the Hybrid System Under a High Proportion of Wind and Photovoltaic Power Connection DOI Creative Commons
Yan Ren, Haonan Zhang, Lile Wu

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(5), P. 1306 - 1306

Published: March 6, 2025

With the high proportion of wind and photovoltaic (PV) power connection in new electricity system, system output volatility is enhanced. When fluctuation suppressed, pumped storage condition changed frequently, which leads to vibration enhancement unit a decrease safety. This paper proposes pump turbine health evaluation model based on combination weighting method cloud PV scenario. The wind–PV characteristics complementary year (8760 h) typical week four seasons (168 are analyzed, frequent working transitions units studied against this background. A five-level classification including multi-dimensional indicators established, multi-level membership quantification realized by combining method. case analysis station within shows that as whole presents (Ex = 76.411, En 12.071, He 4.014), degree “good” state reaches 0.772. However, draft tube index 62.476) water guide 50.333) have shown deterioration trend. results verify applicability reliability model. study provides strong support for safe stable operation context high-proportion connection, great significance smooth system.

Language: Английский

Citations

0
Data-model interaction-driven transferable graph learning method for weak-shot onsite FTU health condition assessment DOI
Fengyuan Zhang, Jie Liu, Haoliang Li

et al.

Advanced Engineering Informatics, Journal Year: 2025, Volume and Issue: 65, P. 103364 - 103364

Published: May 1, 2025

Language: Английский

Citations

0
Hierarchical cavitation intensity recognition using Sub-Master Transition Network-based acoustic signals in pipeline systems DOI
Shuiping Gou, Yu Sha, Bo Liu

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 258, P. 125155 - 125155

Published: Aug. 23, 2024

Language: Английский

Citations

0
Health status assessment of pump station units based on spatio-temporal fusion and uncertainty information DOI Creative Commons

Panpan Qiu,

Jianzhuo Yan,

Hongxia Xu

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 15, 2024

An effective health status assessment (HSA) for pump station units (PSUs) is crucial accurately determining their real and providing technical support safe operational decisions. Due to the limitations of existing data-driven HSA methods, which primarily focus on temporal dependencies monitoring signals fail explore complex interconnections among comprehensively. Moreover, when constructing performance degradation indices based linear differences, these methods do not effectively integrate heterogeneous signals, resulting in an incomplete inaccurate overall system degradation. This paper proposes a real-time comprehensive method PSUs multi-source uncertainty information. Initially, benchmark model (HBM) built using CrossGNN, possesses cross-scale cross-variable interaction capabilities, precisely capture dynamic relationships variables signals. Subsequently, key measurement points that reflect are identified through correlation analysis establish evaluation indices. Then, considering signal changes, novel index (HDI) developed Mahalanobis distance (MD) Gaussian Cloud Model (GCM) analyze changes unit status. Furthermore, weighting calculation non-dominated sorting genetic algorithm (NSGA-II) proposed (RCHDI) thorough Finally, effectiveness validated case study data from South-to-North Water Diversion Project China. The results show that, compared other studies, significantly improves stability smoothness state curve, with increases 21.5% 47.1% respectively, new perspective comprehensively assessing PSUs.V.

Language: Английский

Citations

0