Time-Efficient Convolutional Neural Network-Assisted Brillouin Optical Frequency Domain Analysis

Sensors

卷:21

Christos Karapanagiotis¹  Aleksander Wosniok¹  Konstantin Hicke¹  Katerina Krebber¹ 

[1] Bundesanstalt für Materialforschung und-Prüfung, Unter den Eichen 87, 12205 Berlin, Germany;

关键词: distributed Brillouin sensing;    convolutional neural networks;    Brillouin optical frequency domain analysis;    distributed fiber-optic sensors;    temperature and strain sensing;   

DOI  :  10.3390/s21082724

来源: DOAJ

【 摘 要 】

To our knowledge, this is the first report on a machine-learning-assisted Brillouin optical frequency domain analysis (BOFDA) for time-efficient temperature measurements. We propose a convolutional neural network (CNN)-based signal post-processing method that, compared to the conventional Lorentzian curve fitting approach, facilitates temperature extraction. Due to its robustness against noise, it can enhance the performance of the system. The CNN-assisted BOFDA is expected to shorten the measurement time by more than nine times and open the way for applications, where faster monitoring is essential.

【 授权许可】

Unknown