Neural Network Based Aliasing Spectral Decoupling Algorithm for Precise Mid-Infrared Multicomponent Gases Sensing.

Owing to the overlapping and cross-interference of absorption lines in multicomponent gases, the simultaneous measurement of such gases via laser absorption spectroscopy frequently necessitates the use of supplementary pressure sensors to distinguish the spectral lines. Alternatively, it requires multiple lasers combined with time-division multiplexing to independently scan the absorption peaks of each gas, thereby preventing interference from other gases. This inevitably escalates both the cost of the system and the complexity of the gas pathway. In response to these challenges, a mid-infrared sensor employing a neural network-based decoupling algorithm for aliasing spectral is developed, enabling the simultaneous detection of methane(CH), water vapor(HO), and ethane(CH). The sensor system underwent evaluation in a controlled laboratory environment. Allan deviation analysis revealed that the minimum detection limits for CH,HO, and CH were 6.04, 118.44, and 1 ppb, respectively, with an averaging time of 3 s. The performance of the proposed sensor demonstrates that the aliasing spectral decoupling algorithm based on neural network combined with wavelength-modulated spectroscopy technology has the advantages of high sensitivity, low cost and low complexity, showing its potential for simultaneous detection of multicomponent trace gases in various fields.