中心硕士生邹秀婷的工作——Optimization of Brillouin instantaneous frequency measurement using convolutional neural networks 的相关成果近期发表在Optics Letter期刊上，该工作得到了国家自然科学基金的部分资助（批准号61822508、61571292、61535006），解决了布里渊瞬时频率测量系统测频精度不高的问题。此方案采用卷积神经网络构建实验测得的瞬时频率和理论瞬时频率之间的映射，得到误差较小的优化瞬时频率，因此也提高了系统的敏感度和动态范围。
摘要: Brillouin instantaneous frequency measurement (B-IFM) is used to measure instantaneous frequencies of an arbitrary signal with high frequency and broad bandwidth. However, the instantaneous frequencies measured using the B-IFM system always suffer from errors due to system defects. To address this, we adopt a convolutional neural network (CNN), which establishes a function mapping between the measured and nominal instantaneous frequencies to obtain more accurate instantaneous frequency, thus, improving the frequency resolution, system sensitivity and dynamic range of the B-IFM. Using the proposed CNN-optimized B-IFM system, the average maximum and root mean square (RMS) errors between the optimized and nominal instantaneous frequencies are less than 26.3 MHz and 15.5 MHz, which is reduced from up to 105.8 MHz and 57.0 MHz. The system sensitivity is increased from 12.1dBm to 7.8 dBm for the 100-MHz frequency error and the dynamic range is larger.