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

Alarming method of nuclear power station loose part based on support vector machine

A technology of support vector machine and loose parts, which is used in measuring devices, measuring ultrasonic/sonic/infrasonic waves, instruments, etc., can solve the problems of inability to filter out signal noise, false alarm rate, high false alarm rate, effective signal submersion, etc. Achieve the effect of low false alarm rate, lower false alarm rate, and lower false alarm rate

Inactive Publication Date: 2011-06-08
ZHEJIANG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] However, the existing filtering methods cannot completely filter out the noise in the signal. When the amplitude of the noise exceeds the preset value, a false alarm is generated, or the effective signal is submerged in the noise, and the alarm is missed. The accuracy of the alarm is low, and the false alarm Disadvantages of high rate and false negative rate

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
  • Alarming method of nuclear power station loose part based on support vector machine
  • Alarming method of nuclear power station loose part based on support vector machine
  • Alarming method of nuclear power station loose part based on support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] With reference to accompanying drawing, further illustrate the present invention:

[0046] A support vector machine-based alarm method for loose parts in nuclear power plants includes the following steps:

[0047] 1. Install multiple acceleration sensors in the primary circuit of the nuclear reactor to obtain the environmental noise in the nuclear reactor and the impact signal mixed with environmental noise generated when the loose parts fall;

[0048] 2. Hit the steel plate with a hammer with different strengths to simulate the impact signal generated when the loose parts in the nuclear reactor fall, and obtain the percussion signal generated by the hammer hitting the steel plate, and these percussion signals form a vibration signal library;

[0049] 3, extract the feature of knocking signal, construct Support Vector Machine (SVM) recognition model with knocking signal feature;

[0050] 4. Perform AR modeling on the shock signal obtained in step 1), whiten the shock sig...

Embodiment 2

[0115] In conjunction with concrete test, illustrate the present invention:

[0116] 1. Simulation conditions

[0117] The simulation experiment is carried out on a steel plate of 3200mm×2000mm×20mm, and an anti-shock damping device is placed on each of the four corners of the steel plate. Steel balls of 6 different masses, 720g, 185g, 110g, 55g, 30g, and 10g, were used for the impact test. The position and height of each drop are not limited, and the steel balls hit different parts of the steel plate to simulate different drops of loose parts. Location. The distribution of sensors in the test is triangular. The background noise adopts the actual measured noise of Qinshan Nuclear Power Plant (including the thermal noise of the pressure vessel, the thermal noise of the steam generator, the thermal noise of the lower head of the main pump, the cold noise of the pressure vessel, the cold noise of the steam generator, and the lower seal of the main pump. Head cold state noise),...

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 an alarming method of a nuclear power station loose part based on a support vector machine. The alarming method comprises the following steps of: installing a plurality of acceleration sensors on a circuit of a nuclear reactor to acquire environmental noises and impact signals; forming a vibration signal band by knocking signals which are generated by forcibly hammering a steel plate with different forces; extracting characteristics of the knocking signals and constructing an identification module of the support vector module (SVM) by the knocking signals; carrying outan AR modeling on an impact signal, whitening the impact signal and acquiring a root mean square of the whitened signal, wherein the root mean square is used for representing the amplitude of the whitened signal; judging whether to a primary alarm is generated, and recording the whitened signal; acquiring the whitened signal triggering the primary alarm, extracting target characteristic of the whitened signal, inputting the target characteristic to the SVM, and judging whether the target characteristic is an interference signal or not by the SVM according to computation. The invention has theadvantages of high data processing speed, high alarming accuracy rate, and low false alarming rate and missed alarming rate.

Description

technical field [0001] The invention relates to a method for sending an alarm when a loose part of a nuclear power plant is detected to fall. technical background [0002] Loose parts monitoring system (LPMS) is one of the most basic safety tools in the primary circuit of nuclear power plants, and plays an important role in the operation safety of nuclear power plants. The main function of LPMS is to monitor whether there are loose or dropped parts in the reactor cooling system (RCS), and to issue an alarm if there is any. The existing loose parts alarm related documents include: [0003] [1] BECHTOLD B, KUNZ U.KUES'95-The modern diagnostic system for loose parts monitoring[J].Progress in Nuclear Energy, 1999, 34(3):221-230. (BECHTOLD B, KUNZ U.KUES'95 -Advanced monitoring and diagnosis system for loose parts [J]. Nuclear Energy Progress, 1999, 34(3): 221-230.) [0004] [2] SZAPPANOS G, POR G. Basics ideas and realization of completely digitized loose part detection syste...

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): G01H17/00
Inventor 杨将新郑华文何元峰程实
Owner ZHEJIANG UNIV