Nuclear Science and Techniques

《核技术》(英文版) ISSN 1001-8042 CN 31-1559/TL     2019 Impact factor 1.556

Nuclear Science and Techniques ›› 2019, Vol. 30 ›› Issue (11): 171 doi: 10.1007/s41365-019-0691-2

• NUCLEAR ELECTRONICS AND INSTRUMENTATION • Previous Articles     Next Articles

Estimation of Gaussian Overlapping Nuclear Pulses Parameters Based on Deep Learning LSTM Model

Xing-Ke Ma, Hong-Quan Huang, Qian-Cheng Wang, Jing Zhao, Fei Yang, Kai-Ming Jiang, Wei-Cheng Ding, Wei Zhou   

  1. College of Nuclear Technology and Automation Engineering,Chengdu University of Technology, Dongsanlu, Erxianqiao, Chengdu , China chengdu, 610059 , Chengdu 610059, China
  • Received:2019-05-22 Revised:2019-06-29 Accepted:2019-07-03
  • Contact: Hong-Quan Huang E-mail:huanghongquan@cdut.cn
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (Nos. 41774140 and 11675028), the Scientific Research Fund of Sichuan Provincial Education Department (No. 18ZA0050), and the Scientific Research Innovation Team of Chengdu University of Technology (No. 10912-KYTD201701).
PDF ShareIt Export Citation
Xing-Ke Ma, Hong-Quan Huang, Qian-Cheng Wang, Jing Zhao, Fei Yang, Kai-Ming Jiang, Wei-Cheng Ding, Wei Zhou. Estimation of Gaussian Overlapping Nuclear Pulses Parameters Based on Deep Learning LSTM Model.Nuclear Science and Techniques, 2019, 30(11): 171     doi: 10.1007/s41365-019-0691-2

Abstract: A long short-term memory (LSTM) neural network has excellent learning ability applicable to time series of nuclear pulse signals. It can accurately estimate parameters associated with amplitude, time, and so on, in digitally shaped nuclear pulse signals—especially signals from overlapping pulses. By learning the mapping relationship between Gaussian overlapping pulses after digital shaping and exponential pulses before shaping, the shaping parameters of the overlapping exponential nuclear pulses can be estimated using the LSTM model. Firstly, the Gaussian overlapping nuclear pulse (ONP) parameters which need to be estimated received Gaussian digital shaping treatment, after superposition by multiple exponential nuclear pulses. Secondly, a dataset containing multiple samples was produced, each containing a sequence of sample values from Gaussian ONP, after digital shaping, and a set of shaping parameters from exponential pulses before digital shaping. Thirdly, the Training Set in the dataset was used to train the LSTM model. From these datasets, the values sampled from the Gaussian ONP were used as the input data for the LSTM model, and the pulse parameters estimated by the current LSTM model were calculated by forward propagation. Next, the loss function was used to calculate the loss value between the network-estimated pulse parameters and the actual pulse parameters. Then, a gradient-based optimization algorithm was applied, to feedback the loss value and the gradient of the loss function to the neural network, to update the weight of the LSTM model, thereby achieving the purpose of training the network. Finally, the sampled value of the Gaussian ONP for which the shaping parameters needed to be estimated was used as the input data for the LSTM model. After this, the LSTM model produced the required nuclear pulse parameter set. In summary, experimental results showed that the proposed method overcame the defect of local convergence encountered in traditional methods and could accurately extract parameters from multiple, severely overlapping Gaussian pulses, to achieve optimal estimation of nuclear pulse parameters in the global sense. These results support the conclusion that this is a good method for estimating nuclear pulse parameters.

Key words: Nuclear pulses, S–K digital shaping, Deep learning, LSTM