Laser Induced Breakdown Spectroscopy algorithm using weights iteration artificial neural network

摘要

Laser-induced breakdown spectroscopy (LIBS) was applied to quantitative analysis of heavy metal pollution elements in soil. The artificial neural network (ANN) algorithm is used to the processing of the complicated spectrum lines of soil. In this paper we developed a new algorithm using weight iteration in the artificial neural network, so as to decrease the training epochs remarkably. The spectrum line intensity of some elements, such as Cu, Cd, Al, Fe and Si, were obtained. The limits of detection for trace elements Cu and Cd in soil were determined to be 42 and 5ppm, respectively.