Hydraulic turbine set fault diagnosis method based on SDAE-IELM

A fault diagnosis and unit technology, applied in neural learning methods, computer components, pattern recognition in signals, etc., can solve problems affecting normal operation of equipment, increased production costs, economic losses, etc., and achieve strong decomposition adaptability, Adding the effect of suppressing the number of times and simplifying the cumbersome process

Pending Publication Date: 2020-10-16
福建亿华源能源管理有限公司
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Small hydropower stations are usually arranged in remote areas, and hydropower units often operate in harsh environments and are prone to failure
The abnormal vibration of the hydroelectric unit is one of the reasons for the decrease of the generation efficiency of the unit and the increase of production cost
Abnormal vibration will affect the normal operation of the equipment if it is light, and cause the power output to drop below the optimal level, resulting in economic losses; if it is severe, it may cause damage to the equipment and the unit will stop

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
  • Hydraulic turbine set fault diagnosis method based on SDAE-IELM
  • Hydraulic turbine set fault diagnosis method based on SDAE-IELM
  • Hydraulic turbine set fault diagnosis method based on SDAE-IELM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] Such as figure 1 As shown, the present invention proposes a new type of diagnosis method for hydraulic turbine fault diagnosis method. Specifically include:

[0060] Step 1: collect the vibration signal of the turbine unit, and decompose the signal through CEEMDAN;

[0061] Empirical Mode Decomposition (EMD) is an adaptive decomposition method that decomposes complex signals into a series of IMF components ranging from high frequency to low frequency and having practical physical meaning based on the local characteristic time scale of the signal. Each order IMF must meet two conditions: in the entire sequence, the number of zero points and extreme points is equal or differs by at most one; at any point, the envelope composed of local maximum and local minimum, the sum of the two The mean is zero.

[0062] Signal extreme points will affect the IMF, and if the distribution is not uniform, mode aliasing will occur. In order to solve this problem, Ensemble Empirical Mod...

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 hydraulic turbine set fault diagnosis method based on SDAE-IELM. The method comprises the following steps: employing a complete set empirical mode decomposition algorithm CEEMDAN with adaptive noise addition to decompose a hydraulic turbine set vibration signal, and obtaining an intrinsic mode function (IMF) part reflecting the local time scale features of the signal; dividing a time-frequency matrix formed by the IMF parts according to time periods and calculating energy values of all segments, thereby converting the time-frequency matrix into an energy matrix; performing feature extraction on the energy matrix by adopting SDAE; iELM is adopted to realize classification of known fault types and detection of unknown fault types. After the unit breaks down, judgment can be made quickly and accurately, the shutdown maintenance time can be shortened, the working intensity of operation and maintenance personnel is relieved, and the working efficiency is improved.

Description

【Technical field】 [0001] The invention belongs to the technical field of diagnosis of hydraulic turbines, and specifically refers to a fault diagnosis method for hydraulic turbines based on SDAE-IELM. 【Background technique】 [0002] In recent years, with the continuous growth of energy demand, the scale of hydropower development has been increasing, and the number of small and medium-sized hydropower units has also gradually increased. Small hydropower stations are usually arranged in remote areas, and hydropower units often operate in harsh environments and are prone to failure. The abnormal vibration of the hydroelectric unit is one of the reasons for the decrease of the generation efficiency of the unit and the increase of the production cost. Abnormal vibration will affect the normal operation of the equipment if it is light, and cause the power output to drop below the optimal level, resulting in economic losses; if it is severe, it may cause damage to the equipment an...

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): G06K9/00G06K9/62G06N3/04G06N3/08G01M99/00
CPCG06N3/08G01M99/00G06N3/045G06F2218/04G06F2218/08G06F2218/12G06F18/241G06F18/214
Inventor 高伟郭谋发乔苏朋蒋文林泽峰阮文华梁勇
Owner 福建亿华源能源管理有限公司
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