Capillary-based optical fiber sensor for turbidity measurement

Abstract

This work introduces an innovative capillary or hollow core-based sensor designed to measure turbidity by using the reflection of light in its cladding. The structure consists of two different capillary sections and has been optimized to maximise the interaction of light with the external liquid. Experimentation includes data collection from different turbidity levels using the reflected spectrum. To improve the measuring results, machine learning is implemented, exploring the effectiveness of various algorithms and neural network architectures to achieve a good root mean square error.