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

A Fault Diagnosis Method of Steam Turbine Rotor Based on LSTM

A technology for steam turbine rotor and fault diagnosis, which is applied in mechanical equipment, engine components, engine functions, etc., and can solve problems such as low diagnostic efficiency, unfavorable industrial promotion, and poor diagnostic accuracy.

Active Publication Date: 2021-04-20
XI AN JIAOTONG UNIV
View PDF5 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 detect and identify steam turbine rotor faults and ensure the safe operation of steam turbine generator sets. A LSTM-based steam turbine rotor fault diagnosis method is provided to solve the need for steam turbine rotor diagnosis in traditional methods with the help of experience and extremely high signals. Handling skills lead to low diagnostic efficiency, poor diagnostic accuracy, and are not conducive to industrial promotion and other issues

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 of Steam Turbine Rotor Based on LSTM
  • A Fault Diagnosis Method of Steam Turbine Rotor Based on LSTM
  • A Fault Diagnosis Method of Steam Turbine Rotor Based on LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0160]Such asFigure 4 As shown, according to the method of the present invention, a vibration data of a typical failure of four steam turbine rotors is first given. A total of two sets of different simulation vibration data, the signal-to-noise ratio is -3. The simulation vibration data sampling frequency is 12000. The rotor speed is 3000 rpm. The window length of the split vibration data is 2048. Each fault vibration data can be divided into 685 samples of training sets. One of the sets of simulations passed the pre-processing set, and the other set of simulated vibration data periods as the test set.

[0161]A LSTM neural network containing a full-connection layer is set, setting an initial learning rate of 0.001, reducing a magnitude of learning rate every 30, and the final learning rate is 0.00001.

[0162]Table 1 is a confusion matrix of the model of the present invention in the test set, from the result of the confusion matrix, the diagnostic element value is much larger than the el...

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 steam turbine rotor fault diagnosis method based on LSTM, which belongs to the technical field of mechanical fault diagnosis. Firstly, multi-measuring point acquisition sensors are deployed to collect vibration signals of various typical steam turbine rotor faults as training sets and verification sets. Secondly, the vibration signal of the steam turbine rotor is extracted from the DCS system of the power plant as a test set. Then, the training set, test set and verification set are divided and stacked to realize the fusion and data enhancement of multi-point signal data. Then build a neural network based on LSTM, use the training set and verification set to complete the training of the network, and finally combine the actual diagnosis task to maintain the diagnosis model, and finally realize the turbine rotor fault diagnosis on the test set.

Description

Technical field[0001]This is a mechanical fault diagnosis technology, and it is specifically involved in an LSTM-based steam turbine rotor fault diagnosis method.Background technique[0002]Turbo generator is a key device for electricity production. It has the complicated structure, poor working conditions (high temperature, high pressure, high speed), continuous operation requirements, and failure. In the unit operation, the rotor acts as an important part, and once the failure cannot be investigated in time, it will cause non-planning downtime due to the amount of vibration, which will cause damage to the unit damage and personnel casualties. Therefore, the fault diagnosis method and experimental study of turbine generator set rotors, which is of great significance for ensuring safe operation of steam turbine generator sets, reducing significant economic losses and avoiding disastrous accidents.[0003]Steam turbine rotor faults include composite faults such as rotor cracks, imbalance...

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): F01D21/00G06K9/62
CPCF01D21/00F01D21/003F05D2260/80G06F2218/12G06F18/214
Inventor 张荻王崇宇谢永慧刘天源
Owner XI AN JIAOTONG UNIV
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