Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Parameter Identification Method for Linear Model of Pump Turbine

A pump-turbine, linear model technology, applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve problems such as unsatisfactory data accuracy, difficulty in determining linear model parameters, and operating condition operating boundary migration, etc. Achieve the effect of easy determination of linear model parameters, stable network training results, and low acquisition difficulty

Active Publication Date: 2022-05-31
STATE GRID CORP OF CHINA +2
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The determination of the parameters of the linear model has always been a difficult problem in the engineering field. The traditional method is to calculate the six coefficients of the linear model based on the comprehensive characteristic curve of the water turbine or the full characteristic curve of the pump turbine at a certain stable point. Linear model parameters are difficult to determine
However, with the long-term operation of the unit or after a major overhaul, the operating boundary of its working conditions will migrate, and the linear model parameters calculated based on the characteristic curve have certain limitations on the accurate description of the real-time operating state of the unit, and the accuracy of the data is not high. ideal
Therefore, in the existing identification methods for the control system parameters of pumped storage units, there are problems that the parameters of the linear model are difficult to determine and the accuracy of the data is not ideal.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Parameter Identification Method for Linear Model of Pump Turbine
  • A Parameter Identification Method for Linear Model of Pump Turbine
  • A Parameter Identification Method for Linear Model of Pump Turbine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051]

[0054]

[0058]

[0061]

[0064]

[0067]

[0070]

Embodiment 2

[0082] 2) The unit is started with no load, and the PID parameters are Kp=0.6, Ki=0.09, and Kd=0.5.

[0084] The parameter boundary is calculated from the measured data of the unit operation as shown in Table 1.

[0086]

[0088] In order to ensure the diversity and randomness of the samples, in the boundary domain of the determined parameters [ex, eqx, ey, eqy, eh, eqh]

[0093]

[0095]

[0098]

[0102]

[0105]

[0108]

[0111]

[0114]

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for identifying parameters of a linear model of a pump-turbine, which comprises the following steps: obtaining a power generation working condition by coupling an approximate elastic water hammer model of a water diversion system, an IEEE six-parameter model of a water pump-turbine, a system model of a generator motor, and a model of a PID governor The linear model of the speed regulation system of the pumped storage unit is constructed below, and the linear mapping model of the speed regulation system of the pumped storage unit is constructed; the upper and lower boundaries of the parameters to be identified in the speed regulation system of the pumped storage unit are determined, and the parameter identification sample data are obtained; The network method trains the parameter identification sample data, and establishes the BP neural network parameter identification model; takes the actual measurement data of the pumped storage unit speed control system as the input of the BP neural network parameter identification model, and obtains the parameter identification of the pumped storage unit speed control system result. The invention not only makes it easier to determine the parameters of the linear model and has ideal data accuracy, but also has the advantages of less difficulty in obtaining samples and better flexibility in selecting samples.

Description

A Parameter Identification Method of Linear Model of Pump Turbine technical field The invention belongs to the field of accurate modeling of pumped storage units, be specifically related to a kind of pump-turbine linear model parameter identification method. Background technique The pump turbine is the core equipment of the pumped storage unit, and is the control object in the unit speed regulation system. The basis of the related researches on the dynamic response mechanism, control optimization and fault diagnosis of the speed control system of the water storage unit is the system model. precise description of the type. Model parameter identification is an effective way to solve the accurate expression of the unit speed control system model, and it is also a related field. Research hotspots in the field, and method research is gradually becoming mature. Domestic and foreign academic and engineering circles on the control system of pumped storage units Parameter...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/17G06F30/27G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06F30/17G06F30/20G06N3/044G06F18/24G06F18/214Y02E60/16
Inventor 彭绪意杨文聂赛杨雄洪云来常国庆莫旭晶刘泽胥千鑫汤凯秦程章志平温锦红
Owner STATE GRID CORP OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products