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

M310 nuclear power unit equipment label position number image identification method

A nuclear power unit and image recognition technology, applied in the field of image recognition, can solve problems such as the inability to identify the M310 nuclear power equipment label number, and achieve the effect of reducing operating costs and reducing the probability of human error

Active Publication Date: 2019-08-30
CNNC FUJIAN FUQING NUCLEAR POWER
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In other fields such as power grids and chemical petroleum fields, there are similar methods of identifying equipment label numbers through images, but the identification of M310 nuclear power equipment label numbers cannot be performed.

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
  • M310 nuclear power unit equipment label position number image identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0035] Such as figure 1 As shown, the M310 nuclear power unit equipment tag number image recognition method of the present invention includes the following steps:

[0036] S1: call opencv (open source computer vision library);

[0037] S2: Collect the image of the M310 nuclear power site including the BGR color mode of the equipment signage;

[0038] S3: save the image collected in S2 as .jpg or .png format;

[0039] S4: the BGR color mode among the S3 is converted into the HSV color mode;

[0040] S5: By reading all the pixels of the HSV color mode picture in the HSV color space, the maximum number of yellow, green, red, blue, and white distributions in the hue (H) is used to judge the color of the shading of the signboard;

[0041] S6: scan the picture of the HSV color mode in S4 again by the equipment label shading color obtained in S5...

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 image recognition, and particularly relates to an M310 nuclear power unit equipment label position number image recognition method. The method comprisesthe following steps of calling an open source computer vision library; collecting an image containing the BGR color mode of the equipment label on the M310 nuclear power site; storing the acquired image in a. Jpg or. png format; converting the BGR color mode into an HSV color mode; reading a maximum number of distribution conditions of all pixels of an HSV color mode picture in an HSV color spaceand yellow, green, red, blue and white tones, and judging the shading color of the sign; scanning the image in the HSV color mode in the S4 again to obtain a coordinate area where the color shading is located; carrying out pixel point interception and cutting on the obtained coordinate area to obtain an image of a BGR color mode of the equipment label; and analyzing the relative positions of thefour coordinates of the left upper corner, the right upper corner, the left lower corner and the right lower corner. The method can reduce the human factor fault probability of the nuclear power fieldworkers, and reduces the operation cost of the nuclear power plant.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to an image recognition method for an M310 nuclear power unit equipment tag number image. Background technique [0002] Every piece of equipment in a nuclear power unit has a unique equipment tag corresponding to it. The complete M310 nuclear power unit equipment tag includes 1 unit identification number + 3 system identification numbers + 3 equipment serial numbers + 2 equipment type numbers. For example, 1CRF001PO represents the No. 1 pump of the circulating water system of Unit 1. The maintenance, operation, and management activities of the nuclear power site are all carried out around the equipment tag. Effective identification of equipment tag numbers can improve the efficiency of nuclear power production activities, and improving the accuracy of equipment tag identification can effectively prevent personnel errors from causing unpredictable personnel in...

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): G06K9/32G06K9/34G06F16/33
CPCG06F16/334G06V20/63G06V30/153G06V30/10Y02D10/00
Inventor 王五妹姚伟黄宇航黄鸿刘建忠魏祖荣刘政薛广彬张琼瑶郑孝珠季诚肖付伟潘文静
Owner CNNC FUJIAN FUQING NUCLEAR POWER