A fault diagnosis method for a hydroelectric unit

A hydroelectric unit and fault diagnosis technology, applied in neural learning methods, machine/structural component testing, instruments, etc., can solve problems such as deterioration of optimization performance and complex processing process, and achieve overcoming unstable processing, clear diagnostic results, widely used effect

Inactive Publication Date: 2020-01-31
HONGHE COLLEGE
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a fault diagnosis method for hydroelectric units, which solves the problem that the control parameters of the existing cuckoo search algorithm need to be continuously adjusted, which causes the processing process to be complicated and even the optimization performance to deteriorate

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 fault diagnosis method for a hydroelectric unit
  • A fault diagnosis method for a hydroelectric unit
  • A fault diagnosis method for a hydroelectric unit

Examples

Experimental program
Comparison scheme
Effect test

example

[0087] According to the collected sample data of vibration faults of hydropower units, the adaptive cuckoo search neural network (abbreviated as ACSBP) is used for fault diagnosis. In the experiment, the population size is set to 30, the maximum number of iterations is set to 200, the system parameter is 110, the conversion parameter is equal to 0.15, p amax = 1,p amin = 0.05. For comparative analysis, BP neural network and cuckoo search neural network model (CSBP) are also used in the fault diagnosis system of hydropower units. Among them, the training error curves of CSBP and ACSBP models are as follows figure 2 shown. In addition, for the convenience of drawing, the four coded failure modes correspond to 1, 2, 3 and 4, respectively. For the selected 28 groups of test samples, the distribution of the diagnostic results of the three models is as follows image 3 shown.

[0088] From figure 2 It can be seen that the CSBP model has lower convergence accuracy and slower...

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 fault diagnosis method of a water power set. Characteristic parameters of different fault vibration signals of the water power set are extracted to establish a fault set; a step factor and the discovery probability of Cuckoo search are embedded into an optimal solution searching process, a proper control parameter value is selected adaptively according to the quality of the solution, and the method is suitable for different optimization problems. A non-uniform variation operator is used to adjust the searching step of the present optimal solution adaptively, and the convergence precision of the algorithm is improved further. The adaptive Cuckoo search is used to find an optimal weight threshold parameter of the BP neural network, and a fault diagnosis model of thewater power set is established; and compared with a neural network model and a Cuckoo search neural network model, the method of the invention can be used to improve the fault positioning efficiencyand accuracy of the water power set substantially.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of a hydroelectric power generation system, and in particular relates to a fault diagnosis method of a hydroelectric unit. Background technique [0002] The hydroelectric unit is a key equipment in the hydroelectric power generation system, and its health directly affects the operation status of the hydropower plant. According to statistics, about 80% of failures or accidents are closely related to the vibration of hydroelectric units. Therefore, starting from the vibration signal of the hydroelectric unit, and then establishing a corresponding model has become an important means of diagnosing the unit failure. However, in view of the complex and diverse causes of unit vibration failures, involving mechanical, electromagnetic and hydraulic factors, the failure mode recognition and classification methods have become a hot and difficult research point. [0003] In fact, the problem of vibr...

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): G01M99/00G06N3/00G06N3/08
CPCG01M99/00G06N3/006G06N3/084
Inventor 程加堂熊燕任志刚
Owner HONGHE COLLEGE
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