A Double-layered Ultraviolet Flame Sensor Design for High-Resolution Spectral Discrimination Utilizing Machine Learning

Flame sensors are widely deployed in different fire monitoring scenarios. Identifying the origin of the flame, the fuel, often relies on the ultraviolet (UV) spectral signatures emitted by excited radicals during combustion. However, UV flame sensors capable of spectral discrimination typically require complex optical and material designs, resulting in high fabrication costs that hinder their application. To address this limitation, we proposed a multi-channel semiconductor UV flame sensor design based on an Al2O3-TiO2 double-layered nanostructure. This architecture was formed sequentially via anodization processes. By tuning the geometric parameters of the nanostructure, a seven-channel sensor array was designed to exhibit distinct wavelengthdependent responses within the spectral band of 280-320 nm, covering the • OH and NO• emissions. Simulations showed that the proposed structure achieved high responsivities and high internal quantum efficiencies in the target band. On this basis, a convolutional neural network (CNN) was trained to perform single-peak spectral discrimination, achieving a classification accuracy of 91% with a 0.1 nm label spacing, with a mean peak-position error of 0.32 nm. A U-Net-based network was further employed for dual-peak spectral reconstruction, yielding an average peak-intensity deviation ratio of 7.4% and high-fidelity recovery of the underlying spectra. These results demonstrate a compact UV flame sensing approach that combines Al2O3-TiO2 nanostructures with machine-learning-based spectral inference to enable high-resolution spectral discrimination for practical flame monitoring.