Method for on-line measurement of coal quality characteristics based on partial least squares method

Abstract

The invention provides a method for on-line measurement of coal quality characteristics based on partial least squares method. Firstly, the coal calibration samples containing known components are detected by use of an laser-induced breakdown spectroscopy (LIBS) system, the calibration samples are classified by the principal component analysis (PCA) or partial least squares-discriminant analysis (PLS-DA) method according to the obtained spectral line intensity matrix, and PLS regression equations of the individual classes of the calibration samples are established respectively; and then a sample to be tested is detected on line to obtain an LIBS spectrum, the type of the sample to be tested is judged by the PCA or PLS-DA method, and the spectral line intensity matrix of the LIBS spectrum is put into the PLS regression equation of the corresponding type to calculate the mass concentrations of individual elements in the sample to be tested. The method fully utilizes the effective information of the LIBS spectrum, eliminates the multiple correlation of spectral line intensity caused by the mutual interference of the elements, reduces the influence of the matrix effect, and is characterized by high goodness of fit, strong reproducibility and high prediction accuracy in comparison with the single-variable calibration method in the prior art.

Description

technical field [0001] The invention relates to a method for measuring coal quality characteristics. Specifically, the basic principle of the method is laser-induced plasma spectroscopy (LIBS for short). On the basis of using principal component analysis (PCA) or partial least squares regression analysis (PLS-DA) to classify coal types, the application Partial least squares (PLS) method was used to quantitatively analyze coal components. Background technique [0002] In coal mines, coal plants and power plants and other coal-consuming units, real-time adjustment of working parameters according to different coal quality components is conducive to improving combustion efficiency, saving energy and reducing pollutant emissions. However, the traditional coal quality analysis methods mostly use off-line analysis, which has the disadvantages of poor sampling and sample preparation, slow analysis speed, and cumbersome procedures. Therefore, coal users are in urgent need of a coal...

AI Technical Summary

Problems solved by technology

Therefore, the PLS method has greater advantages in the LIBS spectral analysis of coal, but there are still shortcomings such as poor nonlinear fitting ability, poor fault tolerance, and insufficient robustness.

Images