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

Static stacking CO60 radioactive source early warning method based on artificial intelligence

A technology of artificial intelligence and radioactive sources, applied in neural learning methods, image data processing, instruments, etc., can solve problems such as cargo fires, enterprise losses, and card source incidents

Pending Publication Date: 2021-09-10
HARBIN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, while bringing huge profits, due to the complexity of the nuclear radiation environment, operators cannot directly enter the working environment. Therefore, image processing in the radiation environment has become a prerequisite for identification. If the goods in the radiation environment cannot be correctly identified location information, and issuing an early warning when it deviates from the normal position will lead to the occurrence of a card source event. If no staff enters for many days, the goods will be irradiated for a long time and cause a fire because the radiation source cannot be lowered smoothly. Bring huge and irreparable losses to the enterprise

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
  • Static stacking CO60 radioactive source early warning method based on artificial intelligence
  • Static stacking CO60 radioactive source early warning method based on artificial intelligence
  • Static stacking CO60 radioactive source early warning method based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] An artificial intelligence-based static stacking CO60 radioactive source early warning method is characterized by:

[0039] The method comprises the steps of:

[0040] Step 1: Adopt 60 Co-γ radiation source simulates the working environment, applies bias voltage at both ends of the CMOS, tests the radiation resistance of the CMOS chip, and arranges four CMOS cameras in the four corners of the radiation room to collect images;

[0041] Step 2: Artificially add different concentrations of salt and pepper noise to simulate the noise of the collected image in the radiation room in the real environment, and then use the median filter and the improved adaptive median filter to denoise the image with salt and pepper noise Denoising processing, and verify the effect of the two methods, choose the method with good image denoising performance to remove the noise;

[0042] Step 3: Divide the denoised image obtained after the above operation into training set, test set and verifi...

Embodiment 2

[0048] According to the artificial intelligence-based static stacking CO60 radioactive source early warning method described in embodiment 1, it is characterized in that: the specific process of described step one is: the maximum tolerated dose is tested, using 60 Co-γ radiation source simulates the working environment simulation, the dose rate is 1Gy / h, and the cumulative dose is 1000Gy. When irradiating, a bias voltage is applied to both ends of the CMOS to test the radiation resistance of the CMOS chip. Four CMOS cameras are arranged in the corners for image collection.

Embodiment 3

[0050] According to the artificial intelligence-based static stacking CO60 radioactive source early warning method described in embodiment 1 or 2, it is characterized in that: the specific process of the second step is: most of the noise generated in the image collected in the radiation room is Salt and pepper noise, artificially adding different concentrations of salt and pepper noise to simulate the noise of the collected images in the radiation room in the real environment, and then use the median filter and the improved adaptive median filter to denoise the image added with salt and pepper noise Denoising processing, and verify the effect of the two methods through MSE, PSNR, SSIM and other indicators, and select the method with good image denoising performance to remove the noise;

[0051] Use the 7x7 median filter as the comparison object and the improved adaptive median filter to verify the effect

[0052] Such as Figure 4 As shown, according to the following data (0....

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 static stacking CO60 radioactive source early warning method based on artificial intelligence. Due to the complexity of a nuclear radiation environment, an operator cannot directly enter a working environment, so that image processing in the radiation environment becomes a precondition for recognition. The condition that, if position information of goods in the radiation environment cannot be correctly recognized and an early warning is given when the goods deviate from a normal position so as to cause a source jamming event, can be avoided. According to the invention, a 60Co-gamma radiation source is adopted to simulate a working environment; the simulation of collected image noise in a real environment in a radiation room is carried out by manually adding salt and pepper noise with different concentrations, an improved MoilNetV3-SSD algorithm network is constructed, and model training is carried out by using an improved algorithm. The invention is used for the static stacking CO60 radioactive source early warning method based on artificial intelligence.

Description

technical field [0001] The invention relates to the fields of radiation technology, computer vision and automatic detection. Background technique [0002] With the rapid development of nuclear technology, people are also applying nuclear energy to more and more fields. The application of nuclear technology is also called non-power nuclear technology application. It is the physical, chemical and The technology of applied research and development based on biological effects is called "light industry of nuclear industry". At present, more than 200 units in 28 provinces, municipalities and autonomous regions have carried out research on irradiating and preserving more than 200 kinds of food, killing insects and sterilizing them, and improving product quality. More than 60 countries in the world have approved the application of more than 300 kinds of food irradiation technology. In addition to food processing, isotope and radiation technology (application of nuclear technology)...

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): G06T7/00G06T7/73G06T5/00G06T5/20G06N3/04G06N3/08
CPCG06T7/0002G06T7/73G06T5/20G06N3/082G06T2207/20081G06T2207/20084G06T2207/20032G06N3/048G06T5/70
Inventor 李东洁任子宸姚钢
Owner HARBIN UNIV OF SCI & TECH