Fan self-learning health monitoring system based on RRAM

A health monitoring system and self-learning technology, applied to wind turbines, wind turbine monitoring, engines, etc., can solve problems such as wind turbine management lag and inability to predict health status

Pending Publication Date: 2022-04-15
XIAN UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, large-scale wind turbines are equipped with a data acquisition and monitoring and control system (SCADA). SCADA can monitor and control wind turbines, and realize functions such as data collection, equipment control, measurement, parameter adjustment, and various signal alarms for power generation operations. However, these alarm signals can only locate and judge the fault area after the fault occurs, and cannot predict the health status of the future time period, resulting in lagging wind turbine management

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 self-learning health monitoring system based on RRAM
  • Fan self-learning health monitoring system based on RRAM
  • Fan self-learning health monitoring system based on RRAM

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0040] The neural network module U3 in the present invention uses the principle of support vector regression machine for machine learning, and obtains the regression curve of the normal operation of the wind turbine through the data of the normal operation of the wind turbine through the support vector regression machine, and the regression curve is stored in the wind turbine health management center U4. And set the threshold according to the actual operating environment. When the real-time data exceeds the threshold, it is judged that the operation status of the fan is abnormal, and a troubleshooting plan is formulated. The specific implementation is as follows:

[0041] Data of 200 sets of fans during normal operation: oil temperature T 11 , gear temperature T 12 , Sonic S 1 , mechanical vibration P 1 Input the neural network module U3 through the signal processing module U21, and perform machine learning through the support vector regression machine;

[0042] The data o...

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 self-learning health monitoring system based on an RRAM. The fan self-learning health monitoring system comprises a measurement module U1, a signal processing module U2, a neural network module U3 and a fan health management center U4 which are connected in sequence. According to the method, the fan can pre-judge the health condition of the fan according to the data condition of the fan during healthy operation in the past, and the health condition of the fan component can be quickly and accurately judged.

Description

technical field [0001] The invention belongs to the technical field of fan monitoring and monitoring, and relates to a fan self-learning health monitoring system based on RRAM. Background technique [0002] In recent years, with the expansion of wind power grid-connected scale, the reliability and operation and maintenance indicators of wind turbines have become a key part of ensuring the safe and stable operation of the power grid. A wind turbine is a nonlinear, strongly coupled mechanical device that integrates a variety of electrical, control and mechanical subsystems. The connections and couplings between the components of different subsystems are extremely close. If any component fails, if it is not timely Diagnosis and exclusion, through the cascading of components and the amplification effect of continuous coupling with each other, further serious failures will occur, which will lead to unplanned shutdown of wind turbines. Severe accidents such as large-scale power o...

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): F03D17/00
Inventor 张嘉伟魏晓飞
Owner XIAN UNIV OF 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