华侨大学学报（自然科学版）2026，Vol.47Issue(1)：76-82,7.DOI:10.11830/ISSN.1000-5013.202507012
基于深度学习测量水温的多模光纤传感器
Deep Learning-Based Multimode Fiber Sensor for Water Temperature Measurement
摘要
Abstract
By utilizing the characteristic that the speckle image generated by a laser beam transmitting through a multimode optical fiber vary with temperature,the multimode fiber is immersed in water to enable water tem-perature monitoring.A convolutional neural network(CNN)model is designed,and a speckle image dataset corresponding to water temperatures ranging from 1.6 to 60.0℃is constructed to train the system for monito-ring the temperature of water level in multimode fiber.The results show that within a deviation range of±1.0℃,the proposed method provides an average temperature monitoring accuracy of 98.66%,which offers a high-accuracy,wide-range solution for underwater temperature sensing and monitoring.关键词
散斑图像/卷积神经网络/高精度温度监测/多模光纤Key words
speckle image/convolutional neural network/high precision temperature monitoring/multimode fiber分类
数理科学引用本文复制引用
王孝艳,杨璐璇,吕蓬,刘永欣..基于深度学习测量水温的多模光纤传感器[J].华侨大学学报（自然科学版）,2026,47(1):76-82,7.基金项目
国家自然科学基金资助项目(62375092) （62375092）
