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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/13/4568 |
| _version_ | 1797527846749470720 |
|---|---|
| author | Katiuski Pereira Wagner Coimbra Renan Lazaro Anselmo Frizera-Neto Carlos Marques Arnaldo Gomes Leal-Junior |
| author_facet | Katiuski Pereira Wagner Coimbra Renan Lazaro Anselmo Frizera-Neto Carlos Marques Arnaldo Gomes Leal-Junior |
| author_sort | Katiuski Pereira |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T09:49:37Z |
| format | Article |
| id | doaj.art-302b3ba5ab0b4a069dccc8a0bfa9b86c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:49:37Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-302b3ba5ab0b4a069dccc8a0bfa9b86c2023-11-22T02:51:19ZengMDPI AGSensors1424-82202021-07-012113456810.3390/s21134568FBG-Based Temperature Sensors for Liquid Identification and Liquid Level Estimation via Random ForestKatiuski Pereira0Wagner Coimbra1Renan Lazaro2Anselmo Frizera-Neto3Carlos Marques4Arnaldo Gomes Leal-Junior5Graduate Program in Electrical Engineering, Federal University of Espirito Santo (UFES), Vitória 29075-910, ES, BrazilGraduate Program in Electrical Engineering, Federal University of Espirito Santo (UFES), Vitória 29075-910, ES, BrazilGraduate Program in Electrical Engineering, Federal University of Espirito Santo (UFES), Vitória 29075-910, ES, BrazilGraduate Program in Electrical Engineering, Federal University of Espirito Santo (UFES), Vitória 29075-910, ES, BrazilPhysics Department & I3N, University of Aveiro, 3810-193 Aveiro, PortugalGraduate Program in Electrical Engineering, Federal University of Espirito Santo (UFES), Vitória 29075-910, ES, BrazilThis 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.https://www.mdpi.com/1424-8220/21/13/4568fiber Bragg gratingstemperature sensorrandom forestoil classificationfluid identificationliquid level estimation |
| spellingShingle | Katiuski Pereira Wagner Coimbra Renan Lazaro Anselmo Frizera-Neto Carlos Marques Arnaldo Gomes Leal-Junior FBG-Based Temperature Sensors for Liquid Identification and Liquid Level Estimation via Random Forest Sensors fiber Bragg gratings temperature sensor random forest oil classification fluid identification liquid level estimation |
| title | FBG-Based Temperature Sensors for Liquid Identification and Liquid Level Estimation via Random Forest |
| title_full | FBG-Based Temperature Sensors for Liquid Identification and Liquid Level Estimation via Random Forest |
| title_fullStr | FBG-Based Temperature Sensors for Liquid Identification and Liquid Level Estimation via Random Forest |
| title_full_unstemmed | FBG-Based Temperature Sensors for Liquid Identification and Liquid Level Estimation via Random Forest |
| title_short | FBG-Based Temperature Sensors for Liquid Identification and Liquid Level Estimation via Random Forest |
| title_sort | fbg based temperature sensors for liquid identification and liquid level estimation via random forest |
| topic | fiber Bragg gratings temperature sensor random forest oil classification fluid identification liquid level estimation |
| url | https://www.mdpi.com/1424-8220/21/13/4568 |
| work_keys_str_mv | AT katiuskipereira fbgbasedtemperaturesensorsforliquididentificationandliquidlevelestimationviarandomforest AT wagnercoimbra fbgbasedtemperaturesensorsforliquididentificationandliquidlevelestimationviarandomforest AT renanlazaro fbgbasedtemperaturesensorsforliquididentificationandliquidlevelestimationviarandomforest AT anselmofrizeraneto fbgbasedtemperaturesensorsforliquididentificationandliquidlevelestimationviarandomforest AT carlosmarques fbgbasedtemperaturesensorsforliquididentificationandliquidlevelestimationviarandomforest AT arnaldogomeslealjunior fbgbasedtemperaturesensorsforliquididentificationandliquidlevelestimationviarandomforest |