Effect of self-absorption correction on LIBS measurements by calibration curve and artificial neural network

Abstract

In this paper, laser-induced breakdown spectroscopy (LIBS) technique is used for concentration prediction of six elements of Mn, Si, Cu, Fe, Zn, and Mg in seven Al samples by two approaches of artificial neural network (ANN) and standard calibration curve. ANN is utilized as a new technique for determination and classification of various materials and elements in LIBS method. In this study, a few spectra of six aluminum standards with known concentrations are used for training of ANN. It should be noted that the mentioned network is not on trial and error basis, but it is a self-organized network. Calibration curve method, which is implemented in represented paper, determines certain relation between concentration and intensity. Then, the calibration curve and ANN methods obtained by six samples are used for prediction of the elements of the seventh standard sample in order to check the accuracy of these methods and make a comparison. In both approaches, a self-absorption correction is applied for high concentrations species and an improvement in prediction of two methods is seen. Results illustrate that at high concentrations except for Si, ANN shows a better prediction with a lower relative error compared to calibration curve approach after self-absorption correction. Primitive study without any self-absorption correction shows that ANN and calibration curve predictions with the best result are related to Fe with R 2 = 0.99 % having the minimum errors.