Machine Learning-Driven Compensation for Non-Ideal Channels in AWG-Based FBG Interrogator

TL;DR

This study compares analytical and machine learning calibration methods for fiber Bragg grating interrogators based on AWG, demonstrating that ML offers superior accuracy, generalization, and reduced manual effort in handling non-ideal spectral responses.

Contribution

The paper introduces a machine learning calibration approach for AWG-based FBG interrogators, outperforming traditional analytical methods in accuracy and scalability.

Findings

ML calibration achieves 3.17 pm RMSE, better than 7.11 pm of analytical method.

ML model generalizes across a 2.9 nm span with sub-5 pm accuracy.

ML reduces manual calibration and enhances robustness for diverse sensors.

Abstract

We present an experimental study of a fiber Bragg grating (FBG) interrogator based on a silicon oxynitride (SiON) photonic integrated arrayed waveguide grating (AWG). While AWG-based interrogators are compact and scalable, their practical performance is limited by non-ideal spectral responses. To address this, two calibration strategies within a 2.4 nm spectral region were compared: (1) a segmented analytical model based on a sigmoid fitting function, and (2) a machine learning (ML)-based regression model. The analytical method achieves a root mean square error (RMSE) of 7.11 pm within the calibrated range, while the ML approach based on exponential regression achieves 3.17 pm. Moreover, the ML model demonstrates generalization across an extended 2.9 nm wavelength span, maintaining sub-5 pm accuracy without re-fitting. Residual and error distribution analyses further illustrate the trade-offs between the two approaches. ML-based calibration provides a robust, data-driven alternative to analytical methods, delivering enhanced accuracy for non-ideal channel responses, reduced manual calibration effort, and improved scalability across diverse FBG sensor configurations.