Nuclear power starting water pump rolling bearing fault detection method and system

A rolling bearing and fault detection technology, which is applied in the field of intelligent operation and maintenance, can solve the problems of unreported fault diagnosis methods, unguaranteed algorithm versatility, and low efficiency of operation and maintenance management, so as to improve the operating efficiency and economic benefits of enterprises, and improve Reliability and stability, calculation of simple and fast results

Pending Publication Date: 2021-04-23
XI AN JIAOTONG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] ①Under different environments, the generality of the algorithm cannot be guaranteed, and the fault diagnosis method for rolling bearings of nuclear power start-up pumps has not been reported yet
[0008] ② Existing traditional bearing fault diagnosis technology needs to analyze the internal mechanism of the fault first, and then extract key characteristic signals, which has a high technical threshold and is difficult
[0009] ③ Existing data-driven feature extraction methods need

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
  • Nuclear power starting water pump rolling bearing fault detection method and system
  • Nuclear power starting water pump rolling bearing fault detection method and system
  • Nuclear power starting water pump rolling bearing fault detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0069]Embodiment:

[0070]S1: Get the original operation of the rolling bearing through field experiments and its working labels, and divided into training and test data sets 3: 1.

[0071]S1.1, the field experiments include:

[0072]Bearing Type: The support shaft to be detected is a rotating shaft of the nuclear power activation pump motor, the sampling frequency is 12kHz and 48kHz.。

[0073]Fault setting: The damage of the bearing is a single point of injury of electric spark processing. The fault diameter is 0.007, 0.014, 0.021, 0.028 and 0.040 mm, respectively. The damage point is provided on the bearing inner ring, the rolling bodies, and the outer ring.

[0074]Signal Sampling: The motor wind sector and the drive end are placed over the bearing seat of the drive to collect the vibration acceleration signal and power of the faulty bearing, using a 16-channel data recorder collecting the vibration acceleration signal data of the test stage, data acquisition frequency It is 12kHz, the shaft sp...

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 nuclear power starting water pump rolling bearing fault detection method and system, and the method comprises the steps: building a bearing fault diagnosis model based on a convolutional neural network, determining model parameters through employing a simulation experiment based on a control variable method, and obtaining a fault diagnosis result based on the determined model parameters. And training the bearing fault diagnosis model by using the original operation data of the nuclear power starting water pump rolling bearing and the working condition label corresponding to the original operation data to obtain a bearing fault diagnosis model. The convolutional neural network parameters are optimized by using a method based on experimental research, so that the model training efficiency is further improved; according to the method, the end-to-end characteristic of the convolutional neural network is utilized, internal mechanism analysis, Fourier transform and other links are skipped, the method directly acts on original data, original information is prevented from being lost, experiments and theories are combined, a fault diagnosis model is optimized, accurate maintenance of the nuclear power starting water pump rolling bearing is achieved according to fault diagnosis, and the maintenance efficiency of the nuclear power starting water pump rolling bearing is improved. And the operation efficiency of nuclear power enterprises is further improved.

Description

technical field [0001] The invention relates to the technical field of intelligent operation and maintenance, in particular to a method and system for detecting faults of rolling bearings of nuclear power starting water pumps. Background technique [0002] Nuclear power is one of the energy guarantees for my country's economic and social development. The nuclear power start-up water pump is mainly used to provide start-up feed water for steam generators under normal operating conditions, and backup feed water when the booster pump / main feed water pump fails. Its health status is related to nuclear power plants. Safety and economics during start-up and shutdown. The rolling bearing is an important supporting part of the starting water pump of the nuclear power unit, and its health directly affects the performance, power, and life of the starting water pump equipment. [0003] At present, nuclear power enterprises mainly adopt regular maintenance strategies to maintain the rel...

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): G06F30/27G06N3/04G06N3/08G01M13/04G01M13/045G06F119/02
CPCG06F30/27G06N3/04G06N3/084G01M13/04G01M13/045G06F2119/02
Inventor 成玮刘雪陈雪峰海金斌周光辉高琳邢继堵树宏孙涛徐钊于方小稚
Owner XI AN JIAOTONG UNIV
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