Unlock instant, AI-driven research and patent intelligence for your innovation.

Electric reactor mechanical fault joint detection model, method and device based on vibration and sound

A technology of joint detection and reactor, which is applied in the direction of measuring device, testing of mechanical parts, character and pattern recognition, etc., can solve the problems of poor detection accuracy and achieve the effect of improving accuracy and eliminating influence

Active Publication Date: 2020-03-27
国网吉林省电力有限公司超高压公司 +1
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention proposes a combined detection model, method and device for reactor mechanical faults based on vibration and sound, which solves the problem of reactor mechanical fault detection in the prior art The problem of poor accuracy

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
  • Electric reactor mechanical fault joint detection model, method and device based on vibration and sound
  • Electric reactor mechanical fault joint detection model, method and device based on vibration and sound
  • Electric reactor mechanical fault joint detection model, method and device based on vibration and sound

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as Figure 1-Figure 4 As shown, this embodiment proposes a joint detection model for reactor mechanical faults based on vibration and sound, including

[0057] S10: collecting temperature signals, sound signals and vibration signals from the reactor 4, the vibration signals are at least four channels from different positions of the reactor 4;

[0058] S11: According to the temperature signal, the sound signal and each vibration signal are calculated separately to calculate the temperature-related high-frequency relative quantity r, specifically:

[0059]

[0060] Denote the temperature-correlated high-frequency relative amount of the sound signal as r vo , the de-temperature-correlated high-frequency relative quantities of each vibration signal are r vi1 , r vi2 ... r vin , n≥4, when calculating the relative quantity of the temperature-correlated high-frequency of the sound signal, the current signal is the sound signal; when calculating the relative quantit...

Embodiment 2

[0074] Such as Figure 5 As shown, based on the same inventive concept as the first embodiment above, this embodiment proposes a combined detection device for reactor mechanical faults based on vibration and sound, including

[0075] S20: According to steps S10-S15, train the combined detection model of reactor mechanical faults based on vibration and sound;

[0076] S21: collect the temperature signal, sound signal and vibration signal from the reactor 4, and input it to the reactor mechanical fault joint detection model based on vibration and sound, and the vibration signals are at least four paths from different positions of the reactor 4;

[0077] S22: The output of the combined detection model for reactor mechanical faults based on vibration and sound is a fault code, and the fault type is obtained by analyzing the fault code.

[0078] By training the joint detection model of reactor mechanical faults based on vibration and sound, and then input the collected temperature...

Embodiment 3

[0080] Such as Figure 6-Figure 7 As shown, based on the same inventive concept as the first and second embodiments above, this embodiment also proposes a joint detection device for reactor mechanical faults based on vibration and sound, including

[0081] The temperature sensor 31 is used to collect the temperature signal of the reactor 4;

[0082] Acoustic signal sensor 32, for collecting the acoustic signal of reactor 4;

[0083] Vibration sensors 33, there are at least four vibration sensors 33, and they are located at different positions of the reactor 4,

[0084]The central processing unit 35 is used to receive the temperature signal from the temperature sensor 31 and the signal from the signal processing unit 34, train the reactor mechanical fault joint detection model based on vibration and sound, and utilize the reactor mechanical fault based on vibration and sound The fault joint detection model judges the fault type.

[0085] Wherein, the temperature sensor 31 is...

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 belongs to the technical field of reactors, and provides a reactor mechanical fault joint detection model, method and device based on vibration and sound, and the method comprises the steps: collecting a temperature signal, a sound signal and a vibration signal from a reactor; according to the temperature signal, respectively calculating the temperature-dependent high-frequency relative quantity r of the sound signal and each path of vibration signal; finding out a vibration signal closest to the sound signal; respectively inputting the sound signal and the closest vibration signal into a GRU deep neural network for calculation; splicing output layers of the GRU deep neural network, and inputting the output layers into a DNN deep neural network for training; and adjusting related parameter values to obtain a trained reactor mechanical fault joint detection model based on vibration and sound. By means of the technical scheme, the problem that in the prior art, the accuracyof reactor mechanical fault detection is poor is solved.

Description

technical field [0001] The invention belongs to the technical field of reactors, and relates to a joint detection model, method and device for reactor mechanical faults based on vibration and sound. Background technique [0002] The existing reactor fault detection methods are mainly detected by electrical characteristic quantities, chemical characteristic quantities, and optical characteristic quantities. However, reactor fault detection methods based on these three characteristic quantities have the characteristics of difficult installation and high cost, and are difficult to operate. The reactor in the state is equipped with detection equipment, and it cannot respond in time to mechanical defects such as winding deformation, which is not conducive to the online monitoring and non-stop detection of the reactor. [0003] Both the vibration volume and the sound volume contain a large amount of equipment status information. Since the vibration signal of the reactor has a stro...

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): G06K9/62G01M13/00G06N3/04
CPCG01M13/00G06N3/045G06F18/24Y02E30/30
Inventor 韩科张轶珠王建龙祝晓宏赵雪松谢蓓敏陶善宏王博闻
Owner 国网吉林省电力有限公司超高压公司