Fourier spectral resolution enhancement algorithm based on linear prediction

Abstract

Fourier transform infrared spectroscopy (FTIR) has been widely used for real-time monitoring of ambient gases, but for quantitative analysis of certain gases, higher spectral resolution is required to quantify more accurately. In this paper, a Fourier spectral resolution enhancement algorithm based on linear prediction is proposed. Firstly, the linear prediction model for interference signals is studied, utilizing the forward and backward linear prediction total least squares method for parameter estimation, minimum error criterion for determining the autoregressive (AR) model order, and sliding window technique for multi-step prediction. Then, the impact of the signal-to-noise ratio, enhancement factor, and initial resolution of the FTIR spectrum on the accuracy of the algorithm was studied through simulations. Finally, the algorithm is applied to spectral resolution enhancement and quantitative analysis of ammonia (NH3). The experimental results show that when the spectral resolution of NH3 is enhanced from 4 cm−1 to 2 cm−1 and 1 cm−1, the spectral error of the characteristic band is 0.16% and 0.26%, respectively. Additionally, the accuracy of concentration inversion is improved by 2.13% and 4.06%, respectively. The relative error of concentration inversion is 0.69% and 2.15%, respectively, when compared to the measured spectrum at corresponding resolutions. The algorithm proves effective in enhancing spectral resolution and improving the accuracy of quantitative analysis.