Prediction of burn‐up nucleus density based on machine learning

Summary Machine learning models were built by using four different algorithms using Linear Regression, Regression Tree, Multi‐Layer Perceptron, and Random Forest by 10‐fold Cross‐Validation method using the training set. The validity of the four different machine learning algorithms was verified by...

Full description

Saved in:
Bibliographic Details
Published in:International journal of energy research 2021-07, Vol.45 (9), p.14052-14061
Main Authors: Lei, Ji‐Chong, Zhou, Jian‐Dong, Zhao, Ya‐Nan, Chen, Zhen‐Ping, Zhao, Peng‐Cheng, Xie, Chao, Ni, Zi‐Ning, Yu, Tao, Xie, Jin‐Sen
Format: Article
Language:English
Subjects:
Algorithms
burn‐up
Caesium 137
Cesium 137
Cesium isotopes
Cesium radioisotopes
Coefficients
Correlation coefficient
Correlation coefficients
Deviation
DRAGON
Learning algorithms
Machine learning
Mathematical models
multi‐layer perceptron
nuclide density
Regression analysis
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Summary Machine learning models were built by using four different algorithms using Linear Regression, Regression Tree, Multi‐Layer Perceptron, and Random Forest by 10‐fold Cross‐Validation method using the training set. The validity of the four different machine learning algorithms was verified by predicting the nuclide densities of 235U, 238U, 239Pu, 241Pu, 137Cs, 244Cm, and 254Nd at different burn‐up depths by enrichment and burn‐up depth. The experimental results show that the Pearson Correlation Coefficients of the training sets of the four algorithms based on the 10‐fold Cross‐Validation method are all greater than 0.72, among which the evaluation coefficients of the models of Regression Tree and Random Forest are better than those of the Multi‐Layer Perceptron and Linear Regression; however, the prediction based on the test set is found that the model of the Multi‐Layer Perceptron predicts better than the other three models, and the average deviation is less than 1% and the average deviation is less than 3% for the Regression Tree and Random Forest algorithm model.
ISSN:0363-907X
1099-114X
DOI:10.1002/er.6660