Phase advance capability modeling method of synchronous generator based on forward propagation NN (Neural Network)

A technology of synchronous generators and neural networks, applied in biological neural network models, neural learning methods, electrical digital data processing, etc., can solve the problems of poor generalization ability and low precision

Active Publication Date: 2012-10-03
JIANGSU FRONTIER ELECTRIC TECH +2
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a synchronous generator phase-advance capability modeling method to solve the problem of generator phase-advance capability modeling in view of the shortcomings of low precision and poor generalization ability existing in the current traditional modeling method for generator phase-advance operation. The generalization problem of phase test results

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
  • Phase advance capability modeling method of synchronous generator based on forward propagation NN (Neural Network)
  • Phase advance capability modeling method of synchronous generator based on forward propagation NN (Neural Network)
  • Phase advance capability modeling method of synchronous generator based on forward propagation NN (Neural Network)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0019] Embodiment 1: Modeling example of generator phase advance capability based on BP neural network

[0020] 1. Carry out the phase advance operation test of the generator, and obtain training samples and generalization test samples

[0021] According to the rated active power P of the generator N , for 50% P N \75%P N \100%P N Under typical working conditions, within the limit of the maximum allowable phase-advancing reactive power under the corresponding active working conditions calculated based on the limit of the power angle between the generator excitation potential and the main transformer high-voltage side voltage of 70 degrees, different phase-advancing depths are carried out Generator phase advance test to obtain typical test data that can fully reflect the generator phase advance characteristics, and use it as a training sample and a generalization test sample. For example, see attached table 1 for field test data of a 600MW generator in advanced phase operat...

Embodiment 2

[0026] Example 2: Modeling of Generator Phase Advance Capability Based on Radial Basis Neural Network

[0027] 1. Carry out the running test of the generator to obtain training samples and generalization test samples

[0028] According to the rated active power P of the generator N , for 50% P N \75%P N \100%P N Under typical working conditions, within the limit of the maximum allowable phase-advancing reactive power under the corresponding active working conditions calculated based on the limit of the power angle between the generator excitation potential and the main transformer high-voltage side voltage of 70 degrees, different phase-advancing depths are carried out Generator phase advance test to obtain typical test data that can fully reflect the generator phase advance characteristics, and use it as a training sample and a generalization test sample. For example, see attached table 1 for field test data of a 600MW generator in advanced phase operation.

[0029] 2. E...

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 modeling the phase advance capability of a synchronous generator based on a forward propagation NN (Neural Network). The method is characterized by comprising the following steps of: (1) carrying out a phase advance test on a generator to acquire a training sample and generalize a test sample; (2) establishing a network topological structure and training a network by adopting a steepest gradient descent method based on the forward propagation NN; and (3) authenticating the generalization capability of the network by adopting the test sample. The invention based on the multi-layer forward propagation NN has the capability of approximating any non-linear input / output relation, proposes a new method of training a BP (Back Propagation) NN and an RBF (Radial Basis Function) NN by applying a typical phase advance test result of the generator as a training sample to establish a phase advance operation capability model of the synchronous generator and solves the problem of generalizing the phase advance test result of the generator. The model can be used as a reference for monitoring parameters, adjusting a reactive load and formulating on-site operation regulations for the phase advance operation of the generator.

Description

technical field [0001] The invention relates to a synchronous generator phase-advancing operation to regulate grid voltage and an artificial neural network modeling method, belonging to the technical field of generator testing. Background technique [0002] It is impossible to exhaustively enumerate all working condition points in the on-site measurement test of generator phase advance, and the working conditions that require phase advance in power grid operation will definitely be different from those in the test, and the test results are poorly referable. The phase-advance capability analysis of the generator that does not include the operating point in the field test, that is, the generalization study of the phase-advance test results, is a key issue to be solved. [0003] The traditional modeling methods currently used to determine the phase advance capability of generators are mainly: mathematical model calculation method and test result fitting method. Among them, the...

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): G06F17/50G06N3/08
Inventor 王成亮王宏华黄磊徐钢
Owner JIANGSU FRONTIER ELECTRIC TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap