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

Predication system and predication method for after-stretching performance of nuclear material radiation based on extreme learning machine

An extreme learning machine and performance prediction technology, which is applied in prediction, data processing applications, calculations, etc., can solve problems such as the decline of prediction accuracy and the decline of neural network training speed, so as to reduce overhead, reduce the impact of human intervention, and improve objectivity Effect

Inactive Publication Date: 2017-01-25
HEFEI INSTITUTES OF PHYSICAL SCIENCE - CHINESE ACAD OF SCI
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In recent years, some people have begun to use the neural network method to predict the performance of nuclear materials. The prediction accuracy of this method is high, but it largely depends on the degree of human mastery of the neural network, and many parameters need to be set. has a large impact, and when the amount of data continues to increase, the training speed of the neural network will drop rapidly
Some people also use the support vector machine method to predict the performance of nuclear materials. When this method is used for performance prediction, the speed is faster than that of neural networks, but its prediction accuracy will be reduced.

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
  • Predication system and predication method for after-stretching performance of nuclear material radiation based on extreme learning machine
  • Predication system and predication method for after-stretching performance of nuclear material radiation based on extreme learning machine
  • Predication system and predication method for after-stretching performance of nuclear material radiation based on extreme learning machine

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0039] Example 1: Prediction of yield strength of nuclear materials after irradiation

[0040] The general picture of the system is as follows figure 1 shown. The user uses this system to input the data accumulated in the yield strength experiment to the data preprocessing module of this system. The experimental data input in the example is shown in Table 1. The data preprocessing module will automatically obtain the maximum and minimum values ​​of the two condition columns of radiation dose and radiation temperature, and preprocess the radiation dose and radiation temperature according to formula 1), and the yield strength does not need preprocessing. The data obtained after preprocessing are shown in Table 2.

[0041] After the data preprocessing module completes the preprocessing operation, it transmits the data as shown in Table 2 to the training and testing modules. The training and testing module randomly divides the received data set Table 2 into 80% and 20%, respect...

example 2

[0043] Example 2: Prediction of tensile strength of nuclear materials after irradiation

[0044] The general picture of the system is as follows figure 1 shown. The user uses this system to input the data accumulated in the tensile strength experiment to the data preprocessing module of this system. The experimental data input in the example is shown in Table 7. The data preprocessing module will automatically obtain the maximum and minimum values ​​of the two condition columns of radiation dose and radiation temperature, and preprocess the radiation dose and radiation temperature according to formula 1), and the tensile strength does not need preprocessing. The data obtained after preprocessing are shown in Table 8.

[0045] After the data preprocessing module completes the preprocessing operation, it transmits the data as shown in Table 8 to the training and testing modules. The training and testing module randomly divides the received data set Table 8 into 80% and 20%, r...

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

A system and method on prediction after-irradiation tensile property of nuclear material based on extreme learning machine, mainly comprising three modules: data pre-processing module, training and testing module, and performance prediction module. The system has procedure comprising three steps: first, inputting experimental data into pre-processing module, and reflecting irradiation temperature and irradiation dose within the [ 1,1] scope; second, inputting the data after pre-processing into training and testing module, which then is randomly divided into training set and testing set, after that, building model with training set and verifying the predicted precision with testing set, and saving the model if the precision is high enough; third, submitting to users the tensile property under new irradiation temperature and irradiation dose for prediction.

Description

technical field [0001] The invention relates to a system and a prediction method that can be used to predict the tensile properties of nuclear materials after irradiation. It predicts the tensile properties according to the experimental conditions newly input by users, and belongs to the field of nuclear material performance optimization. Background technique [0002] The issue of nuclear materials is one of the key issues in realizing the commercial operation of fusion power plants. Fusion materials work under special conditions such as high radiation and high temperature. The existing technology is to optimize the material properties by cooking, that is, to adjust the material composition percentage, and to test the changes in material properties after irradiation. Or adjust the experimental conditions to test the changes in material properties after irradiation. The development of performance optimization of nuclear materials is hindered by the high time and economic cos...

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): G06Q10/04
CPCG06Q10/04
Inventor 邹俊吴宜灿胡丽琴尚雷明王芳
Owner HEFEI INSTITUTES OF PHYSICAL SCIENCE - CHINESE ACAD OF SCI
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com