{"title":"基于倾斜光栅串联Sagnac干涉仪和ResNet网络的高精度盐度和温度测量","authors":"Weihao Lin;Yibin Liu;Yuhui Liu;Xiasen Yang;Renan Xu;Xuming Zhang;Li-Yang Shao;Perry Ping Shum","doi":"10.1109/JSEN.2024.3484590","DOIUrl":null,"url":null,"abstract":"The measurement of salinity and temperature is vital for ocean observation. However, due to the cross-sensitivity phenomenon of fiber sensors, traditional fiber-based demodulation algorithms are difficult to measure the dual-parameter accurately and simultaneously. In this research, a cascaded structure of a tilted fiber Bragg grating (TFBG) and a Sagnac interferometer (SI) is employed to monitor salinity and temperature simultaneously. The transfer learning-based ResNet networks (TFRes) is proposed to demodulate two variables at the same time. A total of 1680 spectral samples were collected for training and testing when the sensor was immersed in sodium chloride solution with different salinities ranging from 0% to 25% with 5% intervals and temperatures ranging from 20 °C to 32 °C with 3 °C intervals. The SI exhibits a temperature sensitivity of −1.458 nm/°C, accompanied by a mean absolute error (MAE) of 0.28 °C. The sensitivity of the TFBG core mode to temperature is 0.009 nm/°C, and the sensitivity of one of the cladding modes to salinity is 0.004 nm/%. After training through the TFRes, we successfully achieved precise demodulation of salinity and temperature variations by analyzing the composite reflection spectra of SI and TFBG. The MAE amounted to 0.07304 °C for temperature and 0.07285% for salinity, outperforming traditional analyzer demodulation methods by a factor of four. The monitoring experiment of dual parameter simultaneous changes is conducted, with a temperature error of 0.18 °C and a salinity error of 0.1%. The designed sensing system is poised to play a significant role in marine physical quantity monitoring.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"24 24","pages":"40912-40920"},"PeriodicalIF":4.3000,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"High Accuracy Measurement of Salinity and Temperature Based on Tilted Grating Concatenated Sagnac Interferometer and ResNet Network\",\"authors\":\"Weihao Lin;Yibin Liu;Yuhui Liu;Xiasen Yang;Renan Xu;Xuming Zhang;Li-Yang Shao;Perry Ping Shum\",\"doi\":\"10.1109/JSEN.2024.3484590\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The measurement of salinity and temperature is vital for ocean observation. However, due to the cross-sensitivity phenomenon of fiber sensors, traditional fiber-based demodulation algorithms are difficult to measure the dual-parameter accurately and simultaneously. In this research, a cascaded structure of a tilted fiber Bragg grating (TFBG) and a Sagnac interferometer (SI) is employed to monitor salinity and temperature simultaneously. The transfer learning-based ResNet networks (TFRes) is proposed to demodulate two variables at the same time. A total of 1680 spectral samples were collected for training and testing when the sensor was immersed in sodium chloride solution with different salinities ranging from 0% to 25% with 5% intervals and temperatures ranging from 20 °C to 32 °C with 3 °C intervals. The SI exhibits a temperature sensitivity of −1.458 nm/°C, accompanied by a mean absolute error (MAE) of 0.28 °C. The sensitivity of the TFBG core mode to temperature is 0.009 nm/°C, and the sensitivity of one of the cladding modes to salinity is 0.004 nm/%. After training through the TFRes, we successfully achieved precise demodulation of salinity and temperature variations by analyzing the composite reflection spectra of SI and TFBG. The MAE amounted to 0.07304 °C for temperature and 0.07285% for salinity, outperforming traditional analyzer demodulation methods by a factor of four. The monitoring experiment of dual parameter simultaneous changes is conducted, with a temperature error of 0.18 °C and a salinity error of 0.1%. The designed sensing system is poised to play a significant role in marine physical quantity monitoring.\",\"PeriodicalId\":447,\"journal\":{\"name\":\"IEEE Sensors Journal\",\"volume\":\"24 24\",\"pages\":\"40912-40920\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-10-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Sensors Journal\",\"FirstCategoryId\":\"103\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10736952/\",\"RegionNum\":2,\"RegionCategory\":\"综合性期刊\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Sensors Journal","FirstCategoryId":"103","ListUrlMain":"https://ieeexplore.ieee.org/document/10736952/","RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
High Accuracy Measurement of Salinity and Temperature Based on Tilted Grating Concatenated Sagnac Interferometer and ResNet Network
The measurement of salinity and temperature is vital for ocean observation. However, due to the cross-sensitivity phenomenon of fiber sensors, traditional fiber-based demodulation algorithms are difficult to measure the dual-parameter accurately and simultaneously. In this research, a cascaded structure of a tilted fiber Bragg grating (TFBG) and a Sagnac interferometer (SI) is employed to monitor salinity and temperature simultaneously. The transfer learning-based ResNet networks (TFRes) is proposed to demodulate two variables at the same time. A total of 1680 spectral samples were collected for training and testing when the sensor was immersed in sodium chloride solution with different salinities ranging from 0% to 25% with 5% intervals and temperatures ranging from 20 °C to 32 °C with 3 °C intervals. The SI exhibits a temperature sensitivity of −1.458 nm/°C, accompanied by a mean absolute error (MAE) of 0.28 °C. The sensitivity of the TFBG core mode to temperature is 0.009 nm/°C, and the sensitivity of one of the cladding modes to salinity is 0.004 nm/%. After training through the TFRes, we successfully achieved precise demodulation of salinity and temperature variations by analyzing the composite reflection spectra of SI and TFBG. The MAE amounted to 0.07304 °C for temperature and 0.07285% for salinity, outperforming traditional analyzer demodulation methods by a factor of four. The monitoring experiment of dual parameter simultaneous changes is conducted, with a temperature error of 0.18 °C and a salinity error of 0.1%. The designed sensing system is poised to play a significant role in marine physical quantity monitoring.
期刊介绍:
The fields of interest of the IEEE Sensors Journal are the theory, design , fabrication, manufacturing and applications of devices for sensing and transducing physical, chemical and biological phenomena, with emphasis on the electronics and physics aspect of sensors and integrated sensors-actuators. IEEE Sensors Journal deals with the following:
-Sensor Phenomenology, Modelling, and Evaluation
-Sensor Materials, Processing, and Fabrication
-Chemical and Gas Sensors
-Microfluidics and Biosensors
-Optical Sensors
-Physical Sensors: Temperature, Mechanical, Magnetic, and others
-Acoustic and Ultrasonic Sensors
-Sensor Packaging
-Sensor Networks
-Sensor Applications
-Sensor Systems: Signals, Processing, and Interfaces
-Actuators and Sensor Power Systems
-Sensor Signal Processing for high precision and stability (amplification, filtering, linearization, modulation/demodulation) and under harsh conditions (EMC, radiation, humidity, temperature); energy consumption/harvesting
-Sensor Data Processing (soft computing with sensor data, e.g., pattern recognition, machine learning, evolutionary computation; sensor data fusion, processing of wave e.g., electromagnetic and acoustic; and non-wave, e.g., chemical, gravity, particle, thermal, radiative and non-radiative sensor data, detection, estimation and classification based on sensor data)
-Sensors in Industrial Practice