ANN-Assisted High-Resolution and Large Dynamic Range Temperature Sensor Based on Simultaneous Microwave Photonic and Optical Measurements

Abstract

We proposed and demonstrated a temperature sensor with both high resolution and large dynamic range based on simultaneous microwave photonic and optical measurements. To simultaneously increase the sensitivity and dynamic range of optical measurement, two cascaded ring resonators (CRRs) with different temperature sensitivities and free spectral ranges (FSRs) are designed as the sensing probe and fabricated based on silicon-on-insulator (SOI) wafer. Based on the ultrahigh-Q-factor microring in the CRR, a microwave photonic notch filter (MPNF) is obtained and used to achieve a high temperature resolution. Meanwhile, the optical transmission spectrum of the CRR is used to achieve a large dynamic range. Combining the two measurements, a temperature sensor with both high resolution and large dynamic range is realized. To improve the response speed and robustness of the sensing system, the artificial neural network (ANN) is used to directly extract the temperature from the CRR spectrum, which is particularly helpful at low signal-to-noise ratio (SNR). The sensing resolution and dynamic range achieved by our scheme are <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$7.02 \times 10^{-3}$ </tex-math></inline-formula> °C and 106.94 °C, respectively.