Nuclear Science and Techniques ›› 2019, Vol. 42 ›› Issue (3): 30202-030202.doi: 10.11889/j.0253-3219.2019.hjs.42.030202

Previous Articles     Next Articles

Research on digital radiography classification learning method based on simulation data

Xuerui CHEN1,2,Zhongwei ZHAO1,2,Yuewen SUN1,2,Guangchao LI1,2(),Peng CONG1,2()   

  1. 1. Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, China
    2. Key Laboratory of Nuclear Detection Technology, Beijing 100084, China
  • Received:2018-12-20 Revised:2019-01-22 Online:2019-03-10 Published:2019-03-14
  • Contact: Guangchao LI,Peng CONG E-mail:congp@tsinghua.edu.cn LI Guangchao;liguangchao@tsinghua.edu.cn;congp@tsinghua.edu.cn LI Guangchao;congp@tsinghua.edu.cn
  • About author:<named-content content-type="corresp-name">CHEN Xuerui</named-content>, male, born in 1993, graduated from Tsinghua University in 2016, master student, focusing on nuclear detection technology|<named-content content-type="corresp-name">CHEN Xuerui</named-content>, male, born in 1993, graduated from Tsinghua University in 2016, master student, focusing on nuclear detection technology|CONG Peng, E-mail:<email>congp@tsinghua.edu.cn LI Guangchao</email>, E-mail:<email>liguangchao@tsinghua.edu.cn</email>|CONG Peng, E-mail:<email>congp@tsinghua.edu.cn LI Guangchao</email>, E-mail:<email>liguangchao@tsinghua.edu.cn</email>
  • Supported by:
    Supported by National Nuclear Industry Science Foundation-funded Projects(No.20154602098);Supported by National Nuclear Industry Science Foundation-funded Projects (No.20154602098)

Abstract: Background

As one of the important directions of machine learning, classification learning has great potential in industrial digital radiography, which can fully exploit different types of data features. Classification learning requires a large amount of labeled training data to train the prediction models. In view of the complex conditions of industrial digital radiography, obtaining complete training set samples by practical experiments is expensive and inefficient.

Purpose

This study aims to obtain complete training set data accurately and quickly by using simulation data.

Methods

First of all, numerical method was used to generate simulation data in corresponding scene. Then the training set for classification learning was established to be trained by using prediction model based on the Bagging Trees method and the KNN method. Finally, some of simulation data were assigned as test data set, and real industrial digital radiography data were used as verification data set to evaluate prediction models.

Results

The prediction accuracy of bagging trees method for the test set and verification set data is 99.6% and 81.25% respectively whilst KNN method for the test set and verification set data is 89.1% and 50% respectively.

Conclusion

The results show that the bagging trees method has a good effect on classification learning of radiography imaging based on simulation data.

Key words: Digital radiography, Simulation data, Machine learning

CLC Number: 

  • TL99