Portal de Periódicos da CAPES

Deep learning classification and regression models for temperature values on a simulated fibre specklegram sensor

2021; IOP Publishing; Volume: 2139; Issue: 1 Linguagem: Inglês

10.1088/1742-6596/2139/1/012001

1742-6596

Juan Diego Arango, Víctor H. Aristizábal, Juan Carrasquilla, Jorge Alberto Gómez, Jairo Quijano, Francisco J. Vélez, Jorge Herrera-Ramírez,

Industrial Vision Systems and Defect Detection

Abstract Fiber optic specklegram sensors use the modal interference pattern (or specklegram) to determine the magnitude of a disturbance. The most used interrogation methods for these sensors have focused on point measurements of intensity or correlations between specklegrams, with limitations in sensitivity and useful measurement range. To investigate alternative methods of specklegram interrogation that improve the performance of the fiber specklegram sensors, we implemented and compared two deep learning models: a classification model and a regression model. To test and train the models, we use physical-optical models and simulations by the finite element method to create a database of specklegram images, covering the temperature range between 0 °C and 100 °C. With the prediction tests, we showed that both models can cover the entire proposed temperature range and achieve an accuracy of 99.5%, for the classification model, and a mean absolute error of 2.3 °C, in the regression model. We believe that these results show that the strategies implemented can improve the metrological capabilities of this type of sensor.