Method for tracing, classifying and identifying polluted water body by utilizing three-dimensional fluorescence spectrum characteristic information

Abstract

The invention discloses a method for tracing, classifying and identifying a polluted water body by utilizing fluorescence spectrum features. The classification and identification method comprises thefollowing steps: extracting features according to three-dimensional fluorescence spectrum data, constructing a basic fluorescence spectrum database and a feature fluorescence spectrum database, constructing a basic model of fluorescence spectrum clustering by using a K-means algorithm, and taking a K-means clustering result as a mode layer and a summation layer of a PNN probabilistic neural network for training to obtain a category to which an input sample belongs. On the basis, the PNN neural network is utilized to predict an unknown sewage sample to judge the affiliation category of the unknown sewage sample. In order to obtain unknown sample matching information, basic fluorescence spectrum data of all known samples in the same category of the unknown sample and feature spectral data are brought into a comparison recognition library, the similarity matching degrees of the unknown sample and all known samples in the same category are obtained through similarity comparison calculation, the matching with a highest matching item score is optimal matching of the two samples, and the suspected traceability information of the unknown sample is obtained.

Description

technical field [0001] The invention belongs to the field of environmental science, and in particular relates to a method for tracing, classifying and identifying polluted water bodies by utilizing fluorescence spectrum characteristics in the field. Background technique [0002] Environmental protection departments usually rely on the installation of on-line monitoring equipment at the discharge outlets of pollution sources for the supervision of sewage enterprises. Regulatory departments sometimes use manual investigation to gradually investigate along the water flow direction or upstream of the drainage pipe network after the pollution accident occurs, and detect and compare abnormal water samples and sewage water samples to realize traceability and accountability for illegal discharge. There are some deficiencies in the above-mentioned supervision methods. Some unscrupulous enterprises adopt various methods and methods by artificially altering and destroying online monito...

AI Technical Summary

Problems solved by technology

However, in practice, it is found that in the case of relatively sparse data, such as a sparse matrix, especially when the fluorescence peak is a single peak and the fluorescence intensity value is much greater than a large number of background noise values, these similarity calculation methods are due to the absolute value of the specific value. Insensitive, there are certain problems, resulting in errors in similarity recognition and comparison results

Images