A spectral wavelength selection method based on pls-vip-aco algorithm

Abstract

The invention belongs to the field of spectrum analysis, and particularly relates to a spectrum wavelength selection method based on a PLS-VIP-ACO algorithm. The method combines an ant colony algorithm (ACO algorithm), a variable important in projection coefficient (VIP coefficient) and partial least squares (PLS), and comprises the steps of establishing a PLS model in a whole wavelength section, calculating the VIP coefficient of each wavelength variable, and taking the obtained VIP coefficients as initial values of ACO pheromones; in each ACO iteration, recording a wavelength point corresponding to an optimal model obtained by each iteration, and a PLS coefficient absolute value of the wavelength point, accumulating with results of last iteration, and updating the ACO pheromones by considering the VIP coefficients, thus entering next ACO iteration; after all iterations are ended, counting accumulated PLS coefficients of all the wavelength points, sorting in a descending order, recording a corresponding wavelength ordering sequence, and then adopting a strategy of reversely removing weak correlation wavelengths to obtain a final optimal wavelength combination. The method can be used to remarkably improve the robustness and accuracy of spectrum modeling.

Description

technical field [0001] The invention relates to the field of spectral analysis, in particular to a spectral wavelength selection method based on the PLS-VIP-ACO algorithm. Background technique [0002] As a fast and non-destructive quantitative analysis method, spectral analysis technology has been successfully applied in petrochemical, food, agriculture, environmental protection and other fields. However, the original spectrum obtained in spectral detection often has thousands of wavelength points, and the overlap is serious, the spectral information is redundant, and the characteristic absorption area is not obvious, which reduces the accuracy of the subsequent analysis model. In order to improve the prediction accuracy of the model and reduce the complexity and calculation speed of the model, it is necessary to optimize the wavelength and select the characteristic wavelength point most relevant to the sample information to be used for the establishment of the model. [0...

AI Technical Summary

Problems solved by technology

The limitation of the correlation coefficient method is that it is only suitable for the case where the correlation between the spectrum and the sample attributes is high. If the correlation is low, it is easy to eliminate useful information or retain noise information and reduce the stability of the model; the wavelength selection strategy based on interval , the selection of the size of the wavelength range is difficult to determine, and the characteristic wavelength point may be only a single point, and the selected wavelength range may contain irrelevant wavelengths, which cannot eliminate irrelevant wavelengths to the greatest extent; the non-informative variable elimination algorithm adopts the correction spectrum The matrix artificially generates a noise matrix, and eliminates the method of eliminating wavelengths whose information is smaller than the noise variable to extract the characteristic wavelength points, but this method also has a certain degree of subjectivity, and the selection of the noise matrix affects the results of wavelength selection. The final wavelength selection results are usually There is a lot of redundancy; the ant colony algorithm lacks effective information in the process of pheromone initialization, random optimization leads to model instability, and as an iterative algorithm, it has defects such as slow convergence. The limitations of the above-mentioned existing methods affect the robustness of the model sex and precision

Images