Signal processing for real-time identification of similar metals by laser-induced breakdown spectroscopy

Abstract

Laser-induced breakdown spectroscopy (LIBS) is regarded as a promising technique for realtime sorting of scrap metals due to its capability of fast multi-elemental and in-air analysis. This work reports a method for signal processing which ensures high accuracy and high speed during similar metal sorting by LIBS. Similar metals such as aluminum alloys or stainless steel are characterized by nearly the same constituent elements with slight variations in elemental concentration depending on metal type. In the proposed method, the original data matrix is substantially reduced for fast processing by selecting new input variables (spectral lines) using the information for the constituent elements of similar metals. Specifically, principal component analysis (PCA) of full-spectra LIBS data was performed and then, based on the loading plots, the input variables of greater significance were selected in the order of higher weights for each constituent element. The results for the classification test with aluminum alloy, copper alloy, stainless steel and cast steel showed that the classification accuracy of the proposed method was nearly the same as that of full-spectra PCA, but the computation time was reduced by a factor of 20 or more. The results demonstrated that incorporating the information for constituent elements can significantly accelerate classification speed without loss of accuracy.

A feature selection method combined with ridge regression and recursive feature elimination in quantitative analysis of laser induced breakdown spectroscopy

“…Ridge regression was first proposed by Hoerl [18] to solve the problem of multicollinearity among independent variables, and the standard deviation of parameters obtained by ridge regression was relatively small. The ridge regression is to introduce the diagonal matrix of rI in equation (7) when calculating the solution of parameter w, that is, to introduce the L2 regular term into the loss function…”

“…By contrast, the multivariable analysis method can make full use of the information of spectroscopy to obtain a better analysis [4,5], but too much feature data as model inputs will significantly increase the model complexity and easily lead to over-fitting. Hence, it is important to carry out the feature selection of high dimension spectral data to reduce the dimension of the input data [6,7].…”

Improvement in classification accuracy of stainless steel alloys by laser-induced breakdown spectroscopy based on elemental intensity ratio analysis

“…The performance of the proposed method for stainless steel classification was evaluated by comparing with the results based on full-spectra principal component analysis (PCA) and on the intensities of the 17 selected lines in table 2. For the performance test, the 360 LIBS spectra (40 spectra/sam-ple×9 samples) obtained from all the stainless steel CRMs were used and 10-fold cross-validation by linear discriminant analysis was carried out [23].…”

Review of In-Situ Online LIBS Detection in the Atmospheric Environment

“…Over the past several decades, much scientific work covering a wide range of subjects has been carried out by research groups worldwide, 7 and the basic theory of LIBS has gradually matured. Now, it has a wide variety of applications in many fields, such as in material sorting, [8][9][10][11][12] coal analysis, [13][14][15][16] food testing, [17][18][19] medical testing, [20][21][22] environmental monitoring, [23][24][25][26] ocean exploration, [27][28][29][30] and space exploration. [31][32][33] Unlike current chemical analytical methods, LIBS is a novel optical analytical method with many distinguishing features, such as rapid and precise response, high sensitivity, small sample loss, and simultaneous multi-element analysis, and it is pollutionfree.…”