Search

Considering that vehicle exhaust contributes to the majority of nitrogen oxides (NOx), which is harmful to environment and climate, it is important to measure NOx concentrations in sustainable developments. This article proposes to apply spectroscopic gas sensing methods and an innovative deep learning network algorithm for obtaining high-precision NOx data. The adopted mid-infrared sensor technology is based on mid-infrared spectroscopy combined with an advanced substrate-integrated hollow waveguide (iHWG) sensing interface. Using extreme learning machine (ELM) algorithms with an exceptionally fast learning speed when dealing with big data problems next to excellent generalization abilities, a deep learning network for regressing NOx concentrations was implemented. Moreover, to further improve the regression performance the proposed deep ELM was provided with features derived from supervised learning improving its ability to address target constituents. Finally, experiments with gas mixtures containing three species relevant in exhaust emission monitoring have confirmed the utility of the developed approach. [ABSTRACT FROM AUTHOR]

Advanced chemometric analysis is required for rapid and reliable determination of physical and/or chemical components in complex gas mixtures. Based on infrared (IR) spectroscopic/sensing techniques, we propose an advanced regression model based on the extreme learning machine (ELM) algorithm for quantitative chemometric analysis. The proposed model makes two contributions to the field of advanced chemometrics. First, an ELM-based autoencoder (AE) was developed for reducing the dimensionality of spectral signals and learning important features for regression. Second, the fast regression ability of ELM architecture was directly used for constructing the regression model. In this contribution, nitrogen oxide mixtures (i.e., N2O/NO2/NO) found in vehicle exhaust were selected as a relevant example of a real-world gas mixture. Both simulated data and experimental data acquired using Fourier transform infrared spectroscopy (FTIR) were analyzed by the proposed chemometrics model. By comparing the numerical results with those obtained using conventional principle components regression (PCR) and partial least square regression (PLSR) models, the proposed model was verified to offer superior robustness and performance in quantitative IR spectral analysis. [ABSTRACT FROM AUTHOR]