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

Fan blade fault prediction method and system and storage medium

A technology for wind turbine blades and fault prediction, applied to wind turbines in the same direction as the wind, wind turbines, neural learning methods, etc., can solve problems such as large manpower input, complex working environment, and failure to reflect blade damage, and achieve enhanced operation The effect of maintenance and avoiding breakage

Active Publication Date: 2021-11-30
BEIJING NAVROOM TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing wind turbines generally do not have sensors on the blades to collect the performance of the blades. The later installation of sensors is economical and requires a lot of manpower, and the fan blades work in an outdoor environment, the working environment is complicated, and the data collected by the sensors is noisy. It is relatively large and cannot accurately reflect the real condition of the blade; in addition, since the blade is always in a state of vibration during normal operation, occasional vibration abnormalities often cannot reflect the damage of the blade

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 prediction method and system and storage medium
  • Fan blade fault prediction method and system and storage medium
  • Fan blade fault prediction method and system and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] This application provides a deep learning-based fault prediction method for wind turbine blades on the basis of existing wind farms without adding new structural elements. The general structure of wind power generator (referred to as fan in this application) is as attached figure 2 As shown, including blade 1, nacelle 2 and tower 3, in nacelle 2, a data collection element (not shown) for collecting various data in the wind turbine operation process is provided, the blade failure prediction method in the present application The probability of wind turbine blade failure is predicted from existing operational data collected by these data collection elements.

[0033] See attached figure 1 , the prediction method in this application includes the following steps:

[0034] Step S01: establish a deep learning model, the input of the deep learning model includes the vibration of the x-axis of the cabin, the vibration of the y-axis of the cabin (such as figure 2 As shown in...

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 relates to the technical field of wind power generation, in particular to a fan blade fault prediction method and system based on deep learning and a storage medium. The method comprises the steps that a deep learning model is established, and the deep learning model is trained by using historical operation data of a fan blade; a blade operation normal judgment range is determined according to the historical operation data of the fan blade; data is collected from a fan SCADA system, and the collected data is input into the deep learning model to obtain a blade vibration equivalent; whether the blade vibration equivalent is within the blade operation normal judgment range or not is judged, and if the blade vibration equivalent is within the blade operation normal judgment range, it is judged that the blade operates normally; and if the blade vibration equivalent is beyond the blade operation normal judgment range, it is judged that the blade is in a pre-fault state, and the blade is maintained before faults occur so that the faults such as blade breakage can be avoided. According to the fan blade fault prediction method based on deep learning, the vibration condition of the existing fan blade can be accurately monitored without arranging additional structures, so that the blade faults are predicted, the operation maintenance of the fan blade is enhanced, and severe consequences such as fan blade breakage can be avoided.

Description

technical field [0001] The present invention relates to the technical field of wind power generation, and in particular to a method, system and storage medium for fault prediction of fan blades based on deep learning. Background technique [0002] The working principle of a wind turbine is that the wind rotor rotates under the action of the wind, converting the kinetic energy of the wind into the mechanical energy of the wind rotor shaft, and the generator rotates to generate electricity under the drive of the wind rotor shaft. Fan blades are the key components of wind turbines, but their working environment is complicated. If the fan blades vibrate abnormally, cracks may be formed on the blades. If the continuous vibration is abnormal, the blades may break, resulting in huge economic losses. Usually, the monitoring of blade vibration is to install sensors on the blades to collect vibration data, and then analyze the data collected by the sensors to monitor the vibration of ...

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 Applications(China)
IPC IPC(8): F03D17/00F03D1/06G06N3/04G06N3/08
CPCF03D17/00F03D1/0633F03D1/0675G06N3/08G06N3/044Y02E10/72Y04S10/50
Inventor 庞涛马征刘翀秦大林白颖伟吕楠楠
Owner BEIJING NAVROOM TECH CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com