波谱学杂志 ›› 2026, Vol. 43 ›› Issue (2): 115-124.doi: 10.11938/cjmr20253166cstr: 32225.14.cjmr20253166

• 研究论文 • 上一篇    下一篇

基于多通道Transformer重构的NMR环境噪声抑制方法

赵静1, 鲍庆嘉2,3, 张志2,3, 陈罡2,3, 吴肇博1, 黄臻1,*(), 刘朝阳2,3,#()   

  1. 1 武汉轻工大学 电气与电子工程学院湖北 武汉 430023
    2 中国科学院精密测量科学与技术创新研究院磁共振波谱与成像全国重点实验室,武汉磁共振中心湖北 武汉 430071
    3 中国科学院大学北京 100049
  • 收稿日期:2025-05-19 出版日期:2026-06-05 在线发表日期:2025-06-04
  • 通讯作者: 黄臻,刘朝阳 E-mail:zhenhuang@whpu.edu.cn;chyliu@apm.ac.cn
  • 基金资助:
    国家重点研发计划(2023YFE0113300);国家重点研发计划(2022YFF0707000);中国科学院磁共振技术联盟科研仪器设备研制项目(2021GZL001);中国科学院基础与交叉前沿科研先导专项(XDB0540300);国家自然科学基金项目(22327901);国家自然科学基金项目(81627901);国家自然科学基金项目(22374158);国家自然科学基金项目(22127801);国家自然科学基金项目(21927801);国家自然科学基金项目(12205352);国家自然科学基金项目(22204168);中国科学院精密测量科学与技术创新研究院交叉培育项目(S21S4101);中国科学院科研仪器研制项目(YJKYYQ20190032)

NMR Environmental Noise Suppression Method Based on Multi-channel Transformer Reconstruction

ZHAO Jing1, BAO Qingjia2,3, ZHANG Zhi2,3, CHEN Gang2,3, WU Zhaobo1, HUANG Zhen1,*(), LIU Chaoyang2,3,#()   

  1. 1 School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan 430023, China
    2 State Key Laboratory of Magnetic Resonance Spectroscopy and Imaging, National Center for Magnetic Resonance in Wuhan, Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences, Wuhan 430071, China
    3 University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2025-05-19 Published:2026-06-05 Online:2025-06-04
  • Contact: HUANG Zhen, LIU Chaoyang E-mail:zhenhuang@whpu.edu.cn;chyliu@apm.ac.cn

摘要:

便携式核磁共振(NMR)波谱仪易受外部电磁干扰(EMI),导致信噪比低、分析准确性下降.本文提出一种基于多参考线圈和深度学习的方法:利用多通道线圈并行采集环境电磁噪声,输入多通道Transformer重构(MCTR)网络,该网络通过捕捉环境电磁信号的长程依赖关系,实时预测并去除主线圈中的环境噪声.实验表明,该方法在仿真和实际NMR数据中均可有效抑制噪声,提升检测性能,且优于传统方法,信号质量高、鲁棒性强,为便携式NMR在复杂电磁环境中的应用提供了有效支持,有望推动现场检测发展.

关键词: 便携式NMR, 多通道并行接收, 参考线圈, 噪声抑制, Transformer

Abstract:

Portable nuclear magnetic resonance (NMR) spectrometers are susceptible to external electromagnetic interference (EMI), leading to low signal-to-noise ratio and reduced analytical accuracy. This paper proposes a method based on multiple reference coils and deep learning: multi-channel coils are used to acquire ambient electromagnetic noise in parallel, which is fed into a multi-channel Transformer reconstruction (MCTR) network. The network captures long-range dependencies of ambient electromagnetic signals, predicts and removes the environmental noise in the main receiving coil in real time. Experiments show that this method effectively suppresses noise in both simulated and actual NMR data, improves detection performance, outperforms traditional methods, maintains high signal quality, and has strong robustness. It provides effective support for the application of portable NMR in complex electromagnetic environments, and is expected to promote the development of on-site detection.

Key words: portable NMR, multi-channel parallel reception, reference coils, noise suppression, Transformer

中图分类号: