核脉冲峰值序列轻量化神经网络核素识别模型及其FPGA加速方法  

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

作　　者：李超[1] 石睿 曾树鑫 徐鑫华 魏雨鸿 庹先国 Li Chao;Shi Rui;Zeng Shuxin;Xu Xinhua;Wei Yuhong;Tuo Xianguo(College of Physics and Electronic Engineering,Sichuan University of Science and Engineering,Yibin 644000,China;School of Computer Science and Engineering,Sichuan University of Science and Engineering,Yibin 644000,China)

机构地区：[1]四川轻化工大学物理与电子工程学院,四川宜宾644000 [2]四川轻化工大学计算机科学与工程学院,四川宜宾644000

出　　处：《强激光与粒子束》2025年第5期139-149,共11页High Power Laser and Particle Beams

基　　金：国家自然科学基金项目(42074218,42374227);四川省高等教育人才培养质量和教学改革项目(JG2024-0907);四川轻化工大学研究生创新基金项目(Y2024251)。

摘　　要：放射性核素已在核医疗、核安保及无损检测等领域中广泛应用,而对其准确识别是放射性核素定性检测的基础。在便携式核素识别仪中,基于传统能谱分析方法存在延迟高、识别率低等不足。提出一种基于核脉冲峰值序列的核素识别轻量化神经网络模型及其FPGA硬件加速方法,通过引入深度可分离卷积和倒残差模块,并使用全局平均池化替代传统全连接层,构建了一种轻量化、高效的神经网络模型。针对网络训练数据集,通过蒙特卡罗工具包Geant4构建NaI(Tl)探测器模型,获取模拟能谱,再由核脉冲信号模拟仿真器根据能谱产生核脉冲信号序列,构建了16种核脉冲信号数据。最后,将训练好的模型通过量化、融合与并行计算等优化方法部署到PYNQ-Z2异构芯片,实现加速。实验结果表明,模型识别精度可达98.3%,相较传统卷积神经网络模型提高了13.2%,参数量仅为2 128。FPGA优化加速后单次识别耗时0.273 ms,功耗为1.94 W。Radionuclides have been widely used in the fields of nuclear medicine,nuclear security and non-destructive testing,and their accurate identification is the basis of qualitative detection of radionuclides.In the portable nuclide recognition instrument,the traditional energy spectrum analysis method has the shortcomings of high delay and low recognition rate.This paper proposes a lightweight neural network model for nuclide recognition based on kernel pulse peak sequence and its FPGA hardware acceleration method.A lightweight and efficient neural network model is constructed by introducing depth-separable convolution and reciprocal residual modules,and using global average pooling to replace the traditional fully connected layer.For the network training data set,NaI(Tl)detector model was constructed through Monte Carlo toolkit Geant4 to obtain the analog energy spectrum,and then a simulator generated nuclear pulse signal sequences according to the energy spectrum,and 16 kinds of nuclear pulse signal data were constructed.Finally,the trained model is deployed to PYNQ-Z2 heterogeneous chip through optimization methods such as quantization,fusion and parallel computing to achieve acceleration.Experimental results show that the recognition accuracy of the proposed model can reach 98.3%,which is 13.2%higher than that of the traditional convolutional neural network model,and the number of parameters is only 2128.After FPGA optimization and acceleration,the single recognition time is 0.273 ms,and the power consumption is 1.94 W.

关 键 词：核素识别 核信号 神经网络 FPGA 硬件加速 

分 类 号：TL81[核科学技术—核技术及应用]