Laser Fluence Recognition Using Computationally Intelligent Pulsed Photoacoustics Within the Trace Gases Analysis

Abstract

In this paper, the possibilities of computational intelligence applications for trace gas monitoring are discussed. For this, pulsed infrared photoacoustics is used to investigate $$\hbox {SF}_{6}$$ –Ar mixtures in a multiphoton regime, assisted by artificial neural networks. Feedforward multilayer perceptron networks are applied in order to recognize both the spatial characteristics of the laser beam and the values of laser fluence $$\Phi $$ from the given photoacoustic signal and prevent changes. Neural networks are trained in an offline batch training regime to simultaneously estimate four parameters from theoretical or experimental photoacoustic signals: the laser beam spatial profile R(r), vibrational-to-translational relaxation time $$\tau _{V-T} $$ , distance from the laser beam to the absorption molecules in the photoacoustic cell r* and laser fluence $$\Phi $$ . The results presented in this paper show that neural networks can estimate an unknown laser beam spatial profile and the parameters of photoacoustic signals in real time and with high precision. Real-time operation, high accuracy and the possibility of application for higher intensities of radiation for a wide range of laser fluencies are factors that classify the computational intelligence approach as efficient and powerful for the in situ measurement of atmospheric pollutants.