Research on running state recognition method of hydro-turbine based on FOA-PNN

被引：17

作者：

Lan, Chaofeng ^{[1
]}

Li, Shuijing ^{[2
]}

Chen, Huan ^{[3
]}

Zhang, Wu ^{[4
]}

Li, Hui ^{[5
]}

机构：

[1] Harbin Univ Sci & Technol, Coll Elect & Elect Engn, Harbin 150000, Peoples R China

[2] Mediatek Shenzhen Inc, Intelligent Multimedia BU Syst Software Div 6, Shenzhen 518000, Peoples R China

[3] China Ship Design & Dev Ctr, Wuhan 430000, Peoples R China

[4] Guangzhou Univ, Sch Phys & Mat Sci, Guangzhou 510006, Peoples R China

[5] Harbin Inst Large Elect Machinery, Stace Key Lab Hydropower Equipment, Hrbin 150040, Peoples R China

来源：

MEASUREMENT | 2021年 / 169卷

基金：

中国国家自然科学基金;

关键词：

Hydro-turbine; Pressure fluctuations; Probabilistic neural network; Fault diagnosis; Fruit fly optimization algorithm; PRESSURE FLUCTUATION; DRAFT TUBE; DIAGNOSIS; FLOW;

D O I：

10.1016/j.measurement.2020.108498

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

To effectively monitor the operating state of hydro-turbine, a diagnosis strategy based on the operating conditions and pressure pulsation of the turbine is proposed. The improved Hilbert-Huang Transform (HHT) method is used to study the characteristics of pressure pulsation under different operating conditions. The physical parameters of pressure pulsation are extracted through the mutual information theory. Procedures include optimizing the smoothing factor sigma of the Probabilistic neural network (PNN) network through the Fruit fly optimization algorithm (FOA), constructing the FOA-PNN network model, classifying the unit operating status. The result shows that when sigma = 0.23, the prediction accuracy of the FOA-PNN network is 100%, and the training time is 0.336372 s. It is proven that the FOA-PNN can predict the running state of the turbine in a short time and monitor the running malfunction in real time.

引用

页数：12

共 24 条

[1]

[Anonymous], 2018, HYDROPOWER PUMPED ST, V4, P38

[2]

[Anonymous], 2015, Investigation to approaches of online condition assessment and short-term reliability prediction of wind turbines

[3] Suppression of unsteady swirl flow in the draft tube of a Francis hydro turbine model using J-Groove [J].

Chen, Zhenmu ;

Singh, Patrick Mark ;

Choi, Young-Do .

JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY, 2017, 31 (12) :5813-5820

[4]

Fan Xue-li, 2013, Control and Decision, V28, P915

[5] Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings [J].

Gan, Meng ;

Wang, Cong ;

Zhu, Chang'an .

MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2016, 72-73 :92-104

[6] Multifeatures Fusion and Nonlinear Dimension Reduction for Intelligent Bearing Condition Monitoring [J].

Guo, Liang ;

Gao, Hongli ;

Huang, Haifeng ;

He, Xiang ;

Li, ShiChao .

SHOCK AND VIBRATION, 2016, 2016

[7] Impeller fault detection under variable flow conditions based on three feature extraction methods and artificial neural networks [J].

Jami, A. ;

Heyns, P. S. .

JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY, 2018, 32 (09) :4079-4087

[8]

[金成学 Jin Chengxue], 2014, [清华大学学报. 自然科学版, Journal of Tsinghua University. Science and Technology], V54, P1453

[9]

[雷亚国 Lei Yaguo], 2015, [机械工程学报, Journal of Mechanical Engineering], V51, P49

[10]

[李琪飞 Li Qifei], 2015, [水利学报, Journal of Hydraulic Engineering], V46, P350

← 1 2 3 →