FBG-Based Temperature Sensors for Liquid Identification and Liquid Level Estimation via Random Forest

This paper proposed a liquid level measurement and classification system based on a fiber Bragg grating (FBG) temperature sensor array. For the oil classification, the fluids were dichotomized into oil and nonoil, i.e., water and emulsion. Due to the low variability of the classes, the random forest (RF) algorithm was chosen for the classification. Three different fluids, namely water, mineral oil, and silicone oil (Kryo 51), were identified by three FBGs located at 21.5 cm, 10.5 cm, and 3 cm from the bottom. The fluids were heated by a Peltier device placed at the bottom of the beaker and maintained at a temperature of 318.15 K during the entire experiment. The fluid identification by the RF algorithm achieved an accuracy of 100%. An average root mean squared error (RMSE) of 0.2603 cm, with a maximum RMSE lower than 0.4 cm, was obtained in the fluid level measurement also using the RF algorithm. Thus, the proposed method is a feasible tool for fluid identification and level estimation under temperature variation conditions and provides important benefits in practical applications due to its easy assembly and straightforward operation.

[1]  Arnaldo G. Leal-Junior,et al.  Liquid Level Measurement Based on FBG-Embedded Diaphragms With Temperature Compensation , 2018, IEEE Sensors Journal.

[2]  Joseph John,et al.  Fabry–Perot Interferometer-Based Absolute Pressure Sensor With Stainless Steel Diaphragm , 2019, IEEE Sensors Journal.

[3]  Moisés R. N. Ribeiro,et al.  Optical Fiber Sensing for Sub-Millimeter Liquid-Level Monitoring: A Review , 2019, IEEE Sensors Journal.

[4]  A. Leal-Junior,et al.  FBG-Based Measurement Systems for Density, Specific Heat Capacity and Thermal Conductivity Assessment for Liquids , 2021, IEEE Sensors Journal.

[5]  Colin Bradley,et al.  Tapered Fiber-Optic Mach-Zehnder Interferometer for Ultra-High Sensitivity Measurement of Refractive Index , 2019, Sensors.

[6]  A. Cutolo,et al.  A Fiber Bragg Grating Liquid Level Sensor Based on the Archimedes' Law of Buoyancy , 2018, Journal of Lightwave Technology.

[7]  Qi Zhang,et al.  Glass 3D Printing of Microfluidic Pressure Sensor Interrogated by Fiber-Optic Refractometry , 2020, IEEE Photonics Technology Letters.

[8]  Kyriacos Kalli,et al.  FPI-POFBG Angular Movement Sensor Inscribed in CYTOP Fibers With Dynamic Angle Compensator , 2020, IEEE Sensors Journal.

[9]  Jianping He,et al.  Multi-scale load identification system based on distributed optical fiber and local FBG-based vibration sensors , 2020 .

[10]  Shilpi Saha,et al.  Automated interface detection in liquid-liquid systems using self-calibrating ultrasonic sensor , 2021 .

[11]  Chenglin Wen,et al.  An Acoustic Resonance-Based Liquid Level Detector With Error Compensation , 2019, IEEE Transactions on Instrumentation and Measurement.

[12]  Artur J. Jaworski,et al.  On-line measurement of separation dynamics in primary gas/oil/water separators: Challenges and technical solutions-A review , 2009 .

[13]  C. Brodley,et al.  Decision tree classification of land cover from remotely sensed data , 1997 .

[14]  Forrest R. Stevens,et al.  Assessing the spatial sensitivity of a random forest model: Application in gridded population modeling , 2019, Comput. Environ. Urban Syst..

[15]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[16]  A. Leal-Junior,et al.  Diaphragm-Embedded Optical Fiber Sensors: A Review and Tutorial , 2021, IEEE Sensors Journal.

[17]  Maurice Beck,et al.  A multi-interface level measurement system using a segmented capacitance sensor for oil separators , 1994 .

[18]  Mary Ann Schroeder,et al.  Diagnosing and Dealing with Multicollinearity , 1990, Western journal of nursing research.

[19]  K. Hill,et al.  Fiber Bragg grating technology fundamentals and overview , 1997 .

[20]  Arnaldo G. Leal-Junior,et al.  Multi-interface level in oil tanks and applications of optical fiber sensors , 2018 .

[21]  Ran Wang,et al.  Bootstrap Aggregating and Random Forest , 2019, Macroeconomic Forecasting in the Era of Big Data.

[22]  Eftichios Koutroulis,et al.  Water level sensing: State of the art review and performance evaluation of a low-cost measurement system , 2016 .

[23]  Yi Jiang,et al.  A Dual-Cavity Fabry–Perot Interferometric Fiber-Optic Sensor for the Simultaneous Measurement of High-Temperature and High-Gas-Pressure , 2020, IEEE Access.

[24]  Yibeltal Chanie Manie,et al.  Intensity and Wavelength Division Multiplexing FBG Sensor System Using a Raman Amplifier and Extreme Learning Machine , 2018, J. Sensors.

[25]  A. Leal-Junior,et al.  Thermal and Mechanical Analyses of Fiber Bragg Gratings-Embedded Polymer Diaphragms , 2020, IEEE Photonics Technology Letters.

[26]  Wuqiang Yang,et al.  Multi-interface Level Sensors and New Development in Monitoring and Control of Oil Separators , 2006, Sensors (Basel, Switzerland).

[27]  Beatriz Ortega,et al.  Inscription of Bragg gratings in undoped PMMA mPOF with Nd:YAG laser at 266 nm wavelength. , 2019, Optics express.

[28]  Maria José Pontes,et al.  Material features based compensation technique for the temperature effects in a polymer diaphragm-based FBG pressure sensor. , 2018, Optics express.

[29]  Lingxin Kong,et al.  Ultra-high sensitivity and temperature-compensated Fabry–Perot strain sensor based on tapered FBG , 2020 .

[30]  Wenhua Wang,et al.  Large-range liquid level sensor based on an optical fibre extrinsic Fabry–Perot interferometer , 2014 .

[31]  Hong-Nan Li,et al.  Pipeline leakage identification and localization based on the fiber Bragg grating hoop strain measurements and particle swarm optimization and support vector machine , 2018, Structural Control and Health Monitoring.

[32]  D. Zibar,et al.  Machine Learning Assisted Fiber Bragg Grating-Based Temperature Sensing , 2019, IEEE Photonics Technology Letters.