Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

High Power Laser and Particle Beams, Volume. 37, Issue 5, 059001(2025)

Lightweight neural network model for nuclide recognition based on nuclear pulse peak sequence and its FPGA acceleration method

Chao Li1, Rui Shi1,2、*, Shuxin Zeng2, Xinhua Xu2, Yuhong Wei2, and Xianguo Tuo1
Author Affiliations
  • 1College of Physics and Electronic Engineering, Sichuan University of Science and Engineering , Yibin 644000, China
  • 2School of Computer Science and Engineering, Sichuan University of Science and Engineering , Yibin 644000, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (15)
    Equations (10)
    References (20)
    Tools
    Paper Information
    Topics
    Figures & Tables(15)
    Detector modeling and simulation energy spectrum

    Fig. 1. Detector modeling and simulation energy spectrum

    Download full size
    View in Article
    DT5800D analog signal flow

    Fig. 2. DT5800D analog signal flow

    Download full size
    View in Article
    Convolution contrast and residual module contrast

    Fig. 3. Convolution contrast and residual module contrast

    Download full size
    View in Article
    Diagram of neural network structure

    Fig. 4. Diagram of neural network structure

    Download full size
    View in Article
    Model training process

    Fig. 5. Model training process

    Download full size
    View in Article
    Test set confusion matrix

    Fig. 6. Test set confusion matrix

    Download full size
    View in Article
    Pipeline diagram

    Fig. 7. Pipeline diagram

    Download full size
    View in Article
    Partition type

    Fig. 8. Partition type

    Download full size
    View in Article
    HLS partially optimized pseudocode

    Fig. 9. HLS partially optimized pseudocode

    Download full size
    View in Article
    Block diagram of nuclide recognition system

    Fig. 10. Block diagram of nuclide recognition system

    Download full size
    View in Article

    • Table 1. Model comparison

      View table
      View in Article

      Table 1. Model comparison

      modelrecognition accuracy/%model parametermodel size/kbit
      my model98.3212825.9
      LSTM85.327536111
      GhostNet96.917100966711
      MobileNet-V194.123966889430
      ResNet-1893.8385691215151
      VGGNet-1693.034341200134156

    • Table 2. Quantifying resource consumption and delay

      View table
      View in Article

      Table 2. Quantifying resource consumption and delay

      resource32 bit float (utilization rate)16 bit fixed-point number (utilization rate)
      BRAM_18K240(85%)79(28%)
      DSP162(73%)114(51%)
      FF46 657(43%)12 968(12%)
      LUT51 846(97%)21 483(40%)
      latency(cycles)38 10134 792

    • Table 3. Resource consumption and latency before and after fusion

      View table
      View in Article

      Table 3. Resource consumption and latency before and after fusion

      resourcebefore fusion(utilization rate)after fusion(utilization rate)
      BRAM_18K252(90%)240(85%)
      DSP169(76%)162(73%)
      FF51006(47%)46657(43%)
      LUT54753(102%)51846(97%)
      latency(cycles)4701338101

    • Table 4. Resource consumption and delay before and after partial optimization

      View table
      View in Article

      Table 4. Resource consumption and delay before and after partial optimization

      resourcebefore optimization (utilization rate)after optimization (utilization rate)
      BRAM_18K0(0%)0(0%)
      DSP4(1%)32(14%)
      FF328(～0%)1 808(1%)
      LUT427(～0%)802(1%)
      latency(cycles)3 208811

    • Table 5. Resource consumption and delay before and after optimization

      View table
      View in Article

      Table 5. Resource consumption and delay before and after optimization

      resource16 bit fixed-point number (utilization rate)after-optimization (utilization rate)VIVADO (utilization rate)
      BRAM_18K79(28%)109(38%)95(68%)
      DSP114(51%)136(61%)154(70%)
      FF12968(12%)21099(19%)15372(14%)
      LUT21483(40%)39204(73%)12452(23%)
      latency(cycles)3479227334\
    Tools

    Get Citation

    Copy Citation Text

    Chao Li, Rui Shi, Shuxin Zeng, Xinhua Xu, Yuhong Wei, Xianguo Tuo. Lightweight neural network model for nuclide recognition based on nuclear pulse peak sequence and its FPGA acceleration method[J]. High Power Laser and Particle Beams, 2025, 37(5): 059001

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Advanced Interdisciplinary Science

    Received: Nov. 17, 2024

    Accepted: Feb. 24, 2025

    Published Online: May. 22, 2025

    The Author Email: Rui Shi (shirui@suse.edu.cn)

    DOI:10.11884/HPLPB202537.240398

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology