LIBS Info: Element Analysis

Title Authors Material Detector Spectrometer Software
A comparative study of laser induced breakdown spectroscopy analysis for element concentrations in aluminum alloy using artificial neural networks and calibration methods Prasanthi Inakollu, Thomas Philip, Fang Y. Yueh, Jagdish P. Singh Aluminium Alloy Princeton Instruments ICCD Max Jobin Yvon HR460
Laser: Nd:YAG
532.0000nm
20.0000mJ
10.000Hz
Gate Delay: Noneus
Gate Width: Noneus
As the title describes, an Artificial Neural Network (ANN) is used to calculate concentrations of minor metals in Aluminium Alloys. Input vector to the model includes +/-20 channels from the element peaks, laser power, neutral density filter settings etc. Peak intensities were ratioed to the maximum intensity in the spectra (to give an input data set in the range -1 to 1, which is favoured by ANNs).
Element Detection Limit (ppm) Wavelength (nm) Other Wavelengths (nm) Calibration Method Calibration Range (ppm) Notes


Element RMSE (ppm) Wavelength (nm) Calibration Method Notes
Cr 52.3211 ppm 359.3500 Artificial Neural Network Input vector uses +/- pixels around element peak (359.59nm) as well as data on laser power, neutral density filter pos.
Mn 883.2812 ppm 404.1600 Artificial Neural Network [Values estimated from Figure in paper]
Mg 348.8075 ppm 383.8290 Artificial Neural Network [Values measured from chart in paper]
Cu 1879.9668 ppm 324.7500 Artificial Neural Network Values estimated from Figure in Paper