Study on the off situ reconstruction of the core neutron field based on dual-task hybrid network architecture

被引:0
|
作者
Pei Cao [1 ]
Hui Ding [1 ]
ChengLong Cao [2 ]
ZiHui Yang [3 ]
GuoMin Sun [3 ]
机构
[1] School of Artificial Intelligence and Big Data, Hefei University
[2] College of Electronic Engineering, National University of Defense Technology
[3] Institute of Nuclear Energy Safety Technology, HFIPS, Chinese Academy of
关键词
D O I
暂无
中图分类号
TL364 [反应堆安全];
学科分类号
1402 ;
摘要
The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to cases wherein a single region changes at a specified location of the core. However, when the neutron field changes are complex, the accurate identification of the individual changed regions becomes challenging, which seriously affects the accuracy and stability of the neutron field reconstruction. Therefore, this study proposed a dual-task hybrid network architecture(DTHNet) for off situ reconstruction of the core neutron field, which trained the outermost assembly reconstruction task and the core reconstruction task jointly such that the former could assist the latter in the reconstruction of the core neutron field under core complex changes. Furthermore,to exploit the characteristics of the ex-core detection signals, this study designed a global-local feature upsampling module that efficiently distributed the ex-core detection signals to each reconstruction unit to improve the accuracy and stability of reconstruction. Reconstruction experiments were performed on the simulation datasets of the CLEAR-I reactor to verify the accuracy and stability of the proposed method. The results showed that when the location uncertainty of a single region did not exceed nine and the number of multiple changed regions did not exceed five. Further, the reconstructed ARD was within 2%, RDmax was maintained within 17.5%, and the number of RD≥10% was maintained within 10. Furthermore, when the noise interference of the ex-core detection signals was within ±2%, although the average number of RD≥10% increased to 16, the average ARD was still within in 2%, and the average RDmax was within 22%. Collectively, these results show that,theoretically, the DTHNet can accurately and stably reconstruct most of the neutron field under certain complex core changes.
引用
收藏
页码:61 / 77
页数:17
相关论文
共 43 条
  • [1] Study on the off situ reconstruction of the core neutron field based on dual-task hybrid network architecture
    Cao, Pei
    Ding, Hui
    Cao, Cheng-Long
    Yang, Zi-Hui
    Sun, Guo-Min
    NUCLEAR SCIENCE AND TECHNIQUES, 2025, 36 (01)
  • [2] Multi-zone cooperative reconstruction network for off-situ monitoring of the core neutron field
    Cao, Pei
    Li, Donghao
    Ren, Mengfang
    ANNALS OF NUCLEAR ENERGY, 2025, 211
  • [3] Wavelet-Based Dual-Task Network
    Wu, Fuzhi
    Wu, Jiasong
    Zhang, Chen
    Kong, Youyong
    Yang, Chunfeng
    Yang, Guanyu
    Shu, Huazhong
    Carrault, Guy
    Senhadji, Lotfi
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024,
  • [4] Dual-task guided network: hybrid supervised learning for surface defect detection
    Zou, Juncheng
    Lv, Junjie
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2025, 36 (03)
  • [5] Brain Image Segmentation for Ultrascale Neuron Reconstruction via an Adaptive Dual-Task Learning Network
    Liu, Min
    Wu, Shuhan
    Chen, Runze
    Lin, Zhuangdian
    Wang, Yaonan
    Meijering, Erik
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2024, 43 (07) : 2574 - 2586
  • [6] Fusion-Based Dual-Task Architecture for Predicting the Remaining Useful Life of an Aeroengine
    Du, Xiao
    Chen, Jiajie
    Wang, Jiqiang
    Zhang, Haibo
    Wen, Junhao
    JOURNAL OF AEROSPACE ENGINEERING, 2025, 38 (03)
  • [7] Fast recognition system forTree images based on dual-task Gabor convolutional neural network
    Li, Mingxuan
    Zhou, Guoxiong
    Li, Zongchen
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (20) : 28607 - 28631
  • [8] Fast recognition system forTree images based on dual-task Gabor convolutional neural network
    Mingxuan Li
    Guoxiong Zhou
    Zongchen Li
    Multimedia Tools and Applications, 2022, 81 : 28607 - 28631
  • [9] Dual-task and movement: a bibliometric study based on high-impact search engines
    Mas-Mas, Delfina
    Molla, Antonio Francisco Arnau
    Naranjo, Francisco Javier Romero
    RETOS-NUEVAS TENDENCIAS EN EDUCACION FISICA DEPORTE Y RECREACION, 2023, (50): : 995 - 1009
  • [10] An artificial neural network based neutron field reconstruction method for reactor
    Cao Pei
    Gan Quan
    Song Jing
    Long Pengcheng
    Wang Fang
    Hu Liqin
    Wu Yican
    ANNALS OF NUCLEAR ENERGY, 2020, 138