Unlock instant, AI-driven research and patent intelligence for your innovation.

Fan blade fault monitoring method based on feedback optimization

A technology for wind turbine blade and fault monitoring, applied in nuclear methods, wind power generation, computer components, etc., can solve the problems of many algorithm iterations, large amount of calculation, and can not well meet the fault monitoring of wind turbine blades.

Active Publication Date: 2021-05-14
CHINA THREE GORGES CORPORATION
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to solve the existing fan blade fault monitoring method that considers a single factor, and the single factor does not necessarily have an absolute correlation with the fault of the fan blade, which causes the technical problem that the fault of the fan blade cannot be effectively and accurately monitored. Moreover, the problem of fan blade failure is complex. The existing algorithm has many iterations and a large amount of calculation, and the algorithm is easy to fall into a local optimal solution, which cannot well meet the needs of fan blade failure monitoring.

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
  • Fan blade fault monitoring method based on feedback optimization
  • Fan blade fault monitoring method based on feedback optimization
  • Fan blade fault monitoring method based on feedback optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Such as figure 1 As shown, a feedback optimization support vector machine fan blade fault monitoring method includes the following steps:

[0054] Step 1: Construct a data set for fan blade condition monitoring;

[0055] Step 2: Build a support vector machine model to segment the feature space of fan blade data;

[0056] Step 3: optimize and solve the parameters of the support vector machine model;

[0057] Step 4: Evaluate the support vector machine model.

[0058] In step 1, the data set consists of D samples (X i ,Y i ) is sufficient, where X i ∈ R n , Y i ∈{-1,+1}, where the operating data of the fan blades is collected as the feature vector X i , at the same time collect fan running status label Y (normal is +1, fault is -1)), and each feature is standardized.

[0059] The standardization process is:

[0060] where μ is X i The sample mean of the feature, σ is X t The sample standard deviation of the feature.

[0061] Among them, the operating data i...

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 fan blade fault monitoring method based on feedback optimization. The method comprises the following steps of: step 1, constructing a data set of fan blade state monitoring; 2, constructing a support vector machine model to segment a feature space of fan blade data; 3, optimizing and solving parameters of the support vector machine model; and 4, evaluating the support vector machine model. According to an existing fan blade fault monitoring method, a single factor is considered, the single factor does not have absolute correlation with a fan blade fault, and as a result, the fan blade fault cannot be effectively and accurately monitored, and a fan blade fault problem is complex; an existing algorithm is large in number of iterations, large in calculation amount, prone to falling into a local optimal solution and incapable of well meeting the requirement for fan blade fault monitoring. The invention just aims to solve the above problems.

Description

technical field [0001] The invention belongs to the technical field of wind power generation, and in particular relates to a method for fault monitoring of fan blades which integrates technologies such as support vector machine and particle swarm algorithm. Background technique [0002] Under the background of speeding up the adjustment and optimization of industrial structure, energy structure and vigorous development of new energy, the installed capacity of wind power in my country is increasing steadily. Wind power will not produce greenhouse gases during operation and will not cause damage to the ecological environment. It is a new energy industry that our country is vigorously developing. At present, timely and reliable detection of fan blade failures is an important task for power plant operation and maintenance personnel. [0003] Support vector machine SVM (Support Vector Machine) can solve nonlinear segmentation problems in high-dimensional feature space. Particle ...

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
IPC IPC(8): G06F30/27G06K9/62G06N3/00G06N20/10
CPCG06F30/27G06N3/006G06N20/10G06F18/2411Y02E10/72
Inventor 于傲张亚平王方政汤鹏邹祖冰朱小毅
Owner CHINA THREE GORGES CORPORATION