Research on the Pressure Fluctuation in Draft Tube Based on the Sparse Bayesian

Li Ying Wang; Wei Guo Zhao; Ji Gao Zhang

doi:10.4028/www.scientific.net/AMR.108-111.696

Paper Titles

The Research of Two-Dimension Micromachined Level Posture Sensor
p.676

The Research of Micromachined Airflow Tilt Sensor
p.682

A Sensitive Technique of Airflow Omnibearing Level Posture
p.686

Application of ANN Trained with GA in Energy Characteristics of Hydraulic Turbine
p.692

Research on the Pressure Fluctuation in Draft Tube Based on the Sparse Bayesian
p.696

Online Power Measurement and Prediction of PCs
p.700

A Measurement Approach for Critical Voids in Mineral Aggregate Based on AC-20
p.708

On-Line Measuring System for Urban Highway Traffic Flow Based on Video Detection Technique
p.713

Research and Implementation of Smart Banknote Counter Self-Learning System
p.718

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 108-111Research on the Pressure Fluctuation in Draft Tube...

Research on the Pressure Fluctuation in Draft Tube Based on the Sparse Bayesian

Abstract:

Relevance Vector Machine (RVM) is a novel kernel method based on Sparse Bayesian, which has many advantages such as its kernel functions without the restriction of Mercer’s conditions, the relevance vectors automatically determined and fewer parameters. In view of the actual situation that the corresponding space curved surface which expressed the characteristics of pressure fluctuation is too complex to be analyzed, the RVM regression model for describing the characteristics which is nonlinear relationship among pressure fluctuation value，unit rotation and unit discharge is established，and it is applied to hydropower station. Comparing with Support Vector Machine (SVM), the experimental results show the final RVM model achieved is sparser, the prediction precision is higher and the prediction values are in better agreement with the real values.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 108-111)

Pages:

696-699

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.108-111.696

Citation:

Cite this paper

Online since:

May 2010

Authors:

Li Ying Wang, Wei Guo Zhao, Ji Gao Zhang

Keywords:

Draft Tube, Pressure Fluctuation, Relevance Vector Machine, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] HE cheng-lian, WANG zheng-wei.; Journal of Machinery Industry, 2007, 38(11): 62-65.

Google Scholar

[2] Mural Yuichi, Yamamoto Fujio: Journal of Hydrodynamics, 2009, 21(1): 91-96.

Google Scholar

[3] YUAN Shou-qi: Chinese journal of mechanical engineering, 2009, 22(1): 64-69.

Google Scholar

[4] JIAN hua, YAN Zhong-min: Journal of Hydrodynamics, 2008, 20(6): 65-73.

Google Scholar

[5] WANG Xiao-ping，ZHEN Ling，HUANG Hai: Chinese Journal of Scientific Instrument, 2007, 23(6): 596-599.

Google Scholar

[6] JI Shun-wen, ZHU Yue-ming.: Journal of Hydrodynamics, 2008, 20(4): 15-21.

Google Scholar

[7] Tipping ME.: Advances in Information Processing System, 2000, (2): 652-658.

Google Scholar

[8] Tipping ME: Journal of machine learning research, 2001, 1(3): 211-244.

Google Scholar

[9] LU Jian-kui, WANG Ya-lin: Sichuan water power, 2004, 23(2): 19-21.

Google Scholar

[10] Tamura Y, Matsumoto Y.: Journal of Hydrodynamics, 2009, 21(1): 41-46.

Google Scholar

[11] LI Gang, WU Hui-xin, XUE Hui-feng: Computer simulation 2008, 25(12): 122-125.

Google Scholar

[12] CHEN Li, PAN Feng: Automation and Instrumentation, 2009, 24(1): 5-8. vector machine number of vector percent of training set MSE of training set MSE of test set SVM 37 56. 9% 3. 975% 4. 396% RVM 16 24. 6% 2. 217% 2. 581.

Google Scholar