Wavelength variable optimization method in spectrum analysis

Abstract

The invention discloses a method for optimizing wavelength variable in spectral analysis. The method comprises the steps as follows: obtained original spectrum is pretreated to obtain a spectral array with useless information eliminated; the purity value of each wavelength variable is calculated in the obtained spectral array to select the wavelength variable with maximum purity value as a first wavelength variable; the relative weighting function of no. j wavelength variable and selected (j-1) wavelength variables is calculated, and the purity value of each wavelength variable after the relative weighting function is added is calculated; the wavelength variable with the maximum purity value is selected as no. j wavelength variable, wherein, j is the integral more than or equal to 2; partial least square regression modeling is carried out by optimized different quantities of the wavelength variables, and predicted root mean square error is calculated; when the predicted root mean square error is minimum, the wavelength variable combination selected for modeling is the optimized wavelength variable combination. The quantity of the wavelength variables selected by the method is small, and the method can minimize redundant information and can improve modeling speed and efficiency obviously.

Description

technical field [0001] The invention relates to spectral analysis technology, in particular to a wavelength variable optimization method in spectral analysis. Background technique [0002] The spectral analysis technology combined with the multivariate calibration model is a new technology for rapid and non-destructive detection of the content or properties of components in samples. Since the content or properties of the measured sample components change, the absorption spectrum will change, so firstly by correlating the sample spectrum with its concentration or properties, a multivariate calibration model is established, and then through the multivariate calibration model and the spectral information of the measured sample. Predict unknown component concentrations or component properties in the tested sample. However, due to the existence of various interferences, the spectral information is complex and easy to overlap. Therefore, it is necessary to remove redundant inform...

AI Technical Summary

Problems solved by technology

Although the search algorithms such as simulated annealing method and genetic algorithm have quite strong search ability, the parameter settings of these methods are complicated, which affects the ability to search for the global optimal solution and local optimal solution, and the setting of these parameters also depends on the research Due to the experience of the researcher and his grasp of the research problem, it has a certain degree of subjectivity and randomness

In addition, when the genetic algorithm is used for wavelength variable optimization, although the predictive ability of the multivariate correction model is very high in a single experiment, due to its randomness, the adaptability of the multivariate correction model is very low, so the genetic algorithm optimized Wavelength does not improve the robustness and adaptability of multivariate correction models

Images