Three-dimensional Fluorescence Spectroscopy Benzene Series Identification Method Based on Spectral Line Fitting and Total Variation Denoising

Abstract

The present invention discloses a method for identifying benzene series compounds in three-dimensional fluorescence spectra by combining spectral line fitting and total variation denoising, belonging to the field of analytical detection, which includes the following steps: collecting and preprocessing the three-dimensional fluorescence spectral data of pure water background sample solutions with different concentrations of single benzene series pollutants, pollution-free normal river water samples, and river water samples to be detected with unknown target benzene series pollutants; using a spectral peak search method to extract pollutant fluorescence peak information from the preprocessed data and establishing a pollutant spectral peak information library; using principal component analysis to extract feature vectors and constructing a support vector machine classification model; for the preprocessed spectral data of the river water samples to be detected, Doppler-Gaussian spectral line fitting is combined with total variation denoising and feature extraction, and then the classification model is used for target discrimination. This method can effectively extract the three-dimensional fluorescence spectral characteristics of target pollutants, solve the problem of spectral peak overlap, and improve the accuracy and rapidity of identification.

Description

Technical Field

[0001] The present invention belongs to the field of analytical detection, and relates to a method for identifying benzene series compounds in three-dimensional fluorescence spectra by combining spectral line fitting and total variation denoising. Background Art

[0002] Water quality safety is closely related to people's livelihood. As a river that serves as the water source for many civil uses, there are various types of pollution occurring in it. Industrial organic pollution represented by benzene series pollutants is particularly prominent among many pollution incidents due to its high occurrence frequency and great pollution harm. Therefore, how to accurately and efficiently identify benzene series pollutants in rivers has become an urgent problem to be solved.

[0003] Since benzene series compounds generally have obvious and specific three-dimensional fluorescence signals, the three-dimensional fluorescence method can effectively identify benzene series pollutants and has been applied in the detection of benzene series pollutants. The commonly used three-dimensional fluorescence field detection method usually extracts the fluorescence characteristics in the water sample and compares them with the fluorescence library of pollutants established in the laboratory and other environments to determine the types of pollutants. However, in actual polluted rivers, in addition to the target pollutants, there are other substances that can produce fluorescence reactions, such as organic acids with less harm and amino acids in aqueous solutions. The measured three-dimensional fluorescence spectrum is a linear superposition of the spectral peaks of the target pollutants, the spectral peaks of other substances, and non-spectral peak interference information, that is, the spectral peaks of the target pollutants will overlap with those of other substances, thus affecting the accuracy of detection. In previous studies, the parallel factor method was often used to deal with the problem of spectral peak overlap between the substances to be measured and the water quality background and other substances in three-dimensional fluorescence detection. In other optical detection fields, spectral peak overlap is also an urgent problem to be solved, and there are also some solutions in detection methods such as infrared and terahertz. For example, Du Zhiheng et al. proposed a sharpened error wavelet method in the research on a sharpened error wavelet EDXRF spectral analysis method, which successfully separated the relatively highly overlapping spectral peaks of manganese, iron, and aluminum metals; Chen Jiwen et al. proposed a spectral peak overlap resolution method based on the particle swarm optimization algorithm (PSO) in the rapid spectral peak overlap resolution algorithm based on multi-peak cooperation and normalization of the characteristic peak areas of pure elements, which can achieve the separation of the spectral peaks of toluene, o-xylene, and m-xylene; MICHAEL A et al. proposed using the evolution factor method for spectral peak overlap resolution, which achieved the separation of the spectral peaks of nickel and titanium; XIONG J Y et al. proposed a spectral peak overlap resolution method based on the multi-order difference method and the genetic algorithm (GA), which can effectively separate the infrared absorption overlapping peaks of methane, ethane, and propane in alkanes.

[0004] These methods can, to a certain extent, reduce the impact of spectral peak overlap on the accuracy of final pollutant detection. However, due to the lack of support from fluorescence mechanisms in mathematical statistics and the lack of interpretability in the intermediate process, a large number of sample pre-training and prior knowledge are often required. For example, the parallel factor method needs to determine the number of factors in advance, manually judge the quality of the emission spectra and fluorescence spectra obtained by decomposing different numbers of factors, and select the optimal number of components. In a new environment, as the positions of overlapping fluorescence peaks change, the detection accuracy will be greatly affected. Therefore, it is difficult for such methods and models to meet the requirements of migration between different rivers and on-site detection. Summary of the Invention

[0005] The object of the present invention is to address the problems that the fluorescence spectral peaks of other substances in the river background overlap with those of the target pollutants, affecting the detection accuracy, requiring a large amount of sample pre-training, and the model is difficult to migrate in different river backgrounds. A three-dimensional fluorescence spectroscopy benzene series compound recognition method combining spectral line fitting and total variation denoising is proposed.

[0006] To achieve the object of the present invention, the technical solution adopted by the present invention is: to provide a three-dimensional fluorescence spectroscopy benzene series compound recognition method combining spectral line fitting and total variation denoising, including the following steps:

[0007] Collect the three-dimensional fluorescence spectra of the pure water background sample solution of the target benzene series pollutant and the non-polluted normal river water sample, which are used as the target benzene series pollutant spectrum and the background spectrum respectively;

[0008] Adopt a spectral peak search method to extract the fluorescence spectral peak position information of the target benzene series pollutant spectrum; extract the feature vectors of the target benzene series pollutant spectrum and the background spectrum through principal component analysis, establish a data set, use the presence or absence of pollution as a label, and construct a classification model based on machine learning;

[0009] Collect the three-dimensional fluorescence spectrum of the sample to be tested, adopt a spectral peak search method to extract the fluorescence spectral peak position information of the three-dimensional fluorescence spectrum of the sample to be tested, and remove the fluorescence spectral peaks whose distances from the fluorescence spectral peak positions of the target benzene series pollutant spectrum are less than the threshold; use the collision broadening formula to fit the excitation spectrum and remove the fluorescence spectral peaks with a fitting degree lower than the threshold to obtain the interfering substance spectral peaks; take the excitation wavelength or emission wavelength of the interfering substance spectral peaks as the boundary, use the Doppler broadening formula for the part where the excitation wavelength or emission wavelength is lower than the boundary, and use the collision broadening formula for the part higher than the boundary to fit the excitation spectra at each emission wavelength and the emission spectra at each excitation wavelength respectively to obtain the three-dimensional fluorescence spectrum of the interfering substance; based on total variation denoising, strip the three-dimensional fluorescence spectrum of the interfering substance from the three-dimensional fluorescence spectrum of the sample to be tested to obtain the characteristic spectrum; extract the feature vectors of the characteristic spectrum through principal component analysis and input them into the classification model to determine whether the target benzene series pollutant exists.

[0010] Further, the specific process for processing the collected samples is as follows: After the river water sample is collected, it is filtered, stored at 4°C and shielded from light, and the three-dimensional fluorescence spectrum data of the river water sample is recorded within one hour.

[0011] Preferably, after obtaining the three-dimensional fluorescence spectrum, preprocessing is further included; the preprocessing includes: removing Raman scattering, removing Rayleigh scattering, and smoothing.

[0012] Further, the specific spectral peak search method is as follows: Search for local maxima in the three-dimensional fluorescence spectrum, and calculate the average fluorescence intensity and variance within a 15nm×15nm region near the local maximum; if the local maximum is greater than the sum of the average value and three times the variance, extract the fluorescence spectral peak position corresponding to the local maximum, and the fluorescence spectral peak position is represented by the excitation wavelength and emission wavelength corresponding to the fluorescence spectral peak.

[0013] Preferably, the support vector machine is used for constructing the classification model based on machine learning.

[0014] Further, the fluorescence spectral peaks with a distance less than the threshold from the fluorescence spectral peak position of the target benzene series pollutant spectrum are removed using the Euclidean distance formula.

[0015] Further, the collected pure water background sample solution of the target benzene series pollutant contains multiple concentrations. In the step of extracting the fluorescence spectral peak position information of the sample to be measured and removing the fluorescence spectral peaks with a distance less than the threshold from the fluorescence spectral peak position of the target benzene series pollutant spectrum, the fluorescence spectral peaks with a distance less than the threshold from the fluorescence spectral peak position of the target benzene series pollutant spectrum at any concentration are removed.

[0016] Further, taking the excitation wavelength of the interference spectral peak as the boundary, the following Doppler broadening formula is used for the part where the excitation wavelength is lower than the boundary:

[0017] ;

[0018] The following collision broadening formula is used for the part where the excitation wavelength is higher than the boundary:

[0019] ;

[0020] Among them, is the fluorescence intensity, is the excitation spectrum peak value corresponding to the emission wavelength, is the spectral peak excitation wavelength, is the spectral peak emission wavelength, is the spectral half-line width, is the independent variable excitation wavelength, is the independent variable emission wavelength.

[0021] Further, based on total variation denoising, the three-dimensional fluorescence spectrum of the interfering substances is removed from the three-dimensional fluorescence spectrum of the sample to be measured to obtain the characteristic spectrum, specifically as follows:

[0022] The following total variation model is adopted, and Bregman iteration is used for denoising:

[0023] ;

[0024] ;

[0025] wherein, is the energy functional, is a non-negative parameter, is the characteristic spectrum to be obtained, is the spectrum of the external interfering substances, is the spectrum directly measured by the instrument, is the regularization term for maintaining the smoothness of the spectrum;

[0026] At this time, the functional to be minimized is:

[0027] .

[0028] The beneficial effects of the present invention are as follows:

[0029] Aiming at the problems that the detection accuracy of the existing technology is easily affected by the overlapping of the fluorescence peaks of interfering substances and the poor transferability of the model among different rivers, by using the spectral line broadening theory of natural optics, a Doppler-Gaussian spectral line fitting combined with total variation denoising method is proposed to strip the fluorescence peaks of interfering substances in the river background, improving the anti-interference ability of the detection method; the technical solution based on the spectral line broadening theory can have high transfer applicability in different river scenarios. Aiming at the problems that the current benzene series pollutant recognition method lacks the support of fluorescence mechanism and requires a large number of samples for preliminary training, the present invention uses the three-dimensional fluorescence spectra of different concentration samples of target pollutants and the three-dimensional fluorescence spectra of river background for preliminary model training, reducing the requirements for preliminary training samples. The spectral interference signal of the sample to be measured is stripped by using the Doppler-Gaussian spectral line fitting combined with total variation denoising algorithm, and then the principal component analysis and the existing support vector machine classifier are used to realize the efficient and accurate recognition of benzene series pollutants under different complex river backgrounds, while making the establishment of the model simpler and more efficient. Description of the Drawings

[0030] Figure 1 is the flow chart of the method of the present invention;

[0031] Figure 2 is the three-dimensional fluorescence spectrogram of four typical benzene series pollutants; wherein, Figure 2 in (a) is the three-dimensional fluorescence spectrogram of ethylbenzene, Figure 2Among them, (b) is the three-dimensional fluorescence spectrum of styrene, Figure 2 Among them, (c) is the three-dimensional fluorescence spectrum of phenanthrene, Figure 2 Among them, (d) is the three-dimensional fluorescence spectrum of phenol;

[0032] Figure 3 is the flowchart of spectral peak search;

[0033] Figure 4 is the schematic diagram of the spectral peak extraction result taking styrene as an example;

[0034] Figure 5 are the three-dimensional fluorescence spectra of two background water samples; among them, Figure 5 Among them, (a) is the three-dimensional fluorescence spectrum of normal river water, Figure 5 Among them, (b) is the three-dimensional fluorescence spectrum of river water with high-concentration dissolved organic matter;

[0035] Figure 6 is the flowchart of the method for spectral line fitting combined with total variation denoising (DCF-TV) for feature extraction of Doppler-Gaussian spectral lines;

[0036] Figure 7 is the schematic diagram of the effect of excitation spectrum fitting taking phenol as an example;

[0037] Figure 8 is the comparison diagram of the three-dimensional fluorescence spectral peak fitting effect taking styrene as an example; among them, Figure 8 Among them, (a) is the original three-dimensional fluorescence spectrum, Figure 8 Among them, (b) is the three-dimensional fluorescence spectrum after fitting. Specific implementation manner

[0038] The present invention proposes a classification model for rapid discrimination of benzene series pollutants. The fluorescence peak information of pollutants is extracted from the collected three-dimensional fluorescence spectrum by the local maximum method, the average value and variance of the spectral intensity are calculated, a fluorescence spectral peak information library is established, the principal component analysis (PCA) is used to extract feature vectors, and combined with pollution and non-pollution labels, a support vector machine (SVM) classification model is constructed. At the same time, a method for spectral line fitting combined with total variation denoising to solve the problem of fluorescence spectral peak overlap is proposed: the Doppler broadening and collision broadening models are used to fit the excitation spectrum and emission spectrum of the spectral peak, and it is extended to the three-dimensional spectrum by interpolation. The total variation model is used to denoise and strip the interference spectral peak, obtain a pure characteristic spectrum, and use the SVM classification model to judge the presence of pollutants. The core technology is to use the Doppler-Gaussian spectral line fitting combined with the total variation denoising algorithm to strip the interference spectral peak in the river background, obtain a relatively pure characteristic spectrum, and perform principal component analysis on it together with the pollutant spectrum of the pure water solvent and the pollution-free river background spectrum to extract feature vectors, and use the established support vector machine to identify the presence of the target benzene series pollutants.

[0039] The present invention proposes a method for identifying benzene series compounds in three-dimensional fluorescence spectra by combining spectral line fitting and total variation denoising. The step process is as follows Figure 1 shown, and the specific steps are as follows:

[0040] S1: Obtain pure water background sample solutions of different concentrations of single benzene series pollutants (ethylbenzene, styrene, phenanthrene, and phenol), and collect three-dimensional fluorescence spectral data of each sample; obtain non-polluted normal river water samples, and after sample treatment, collect three-dimensional fluorescence spectral data of the river water samples. The pollutant concentration in the pure water background solutions of the four benzene series pollutants is as follows: the concentration range of ethylbenzene is 0.2 - 1 mg / L, and the concentration ranges of phenol, styrene, and phenanthrene are all 10 - 50 μg / L. The specific sample treatment is as follows: after the river water sample is collected, it is filtered, stored at 4°C and shielded from light, and the three-dimensional fluorescence spectral data of the river water sample is recorded within one hour.

[0041] In this embodiment, normal river water samples are taken at seven sampling points, and the specific locations are shown in Table 1. The normal river water sample collection points are not limited to the locations shown in Table 1.

[0042] Table 1: Latitude and longitude coordinate table of river water sampling points

[0043]

[0044] S2: Data preprocessing: Perform spectral preprocessing on the three-dimensional fluorescence spectra and background spectra of each benzene series pollutant under pure water background to make a data set. The specific operation is as follows: perform Raman scattering removal, Rayleigh scattering removal, and smoothing on the three-dimensional fluorescence spectra and background spectra of the benzene series pollutants.

[0045] As Figure 2 shown is the three-dimensional fluorescence spectral diagram of four typical benzene series pollutants. Figure 2 Among them, (a) is the three-dimensional fluorescence spectral diagram of ethylbenzene. Figure 2 Among them, (b) is the three-dimensional fluorescence spectral diagram of styrene. Figure 2 Among them, (c) is the three-dimensional fluorescence spectral diagram of phenanthrene. Figure 2 Among them, (d) is the three-dimensional fluorescence spectral diagram of phenol.

[0046] S3: Use the spectral peak search method to extract pollutant fluorescence peak information from the preprocessed three-dimensional fluorescence spectra of benzene series pollutant samples, and obtain the fluorescence peak position information (l is an integer, 1 ≤ l ≤ K), establish a pollutant spectral peak information database, K is the total number of fluorescence peaks searched, is the excitation wavelength of the l-th fluorescence peak, is the emission wavelength of the l-th fluorescence peak.

[0047] The specific spectral peak search method is as follows: First, search for local maxima in the three-dimensional fluorescence spectrum ; Calculate the local maximum value The average fluorescence intensity within a 15 nm × 15 nm area near , and the variance ; Determine whether to search for the local maximum value is satisfied to obtain the fluorescence spectrum peak position information.

[0048] Figure 3 Figure 4 is the flowchart of spectral peak search, whose purpose is to screen out the fluorescence peak information of all possible target pollutants in the three-dimensional fluorescence spectrum, including the peak position and its peak fluorescence intensity, providing prior information for subsequent spectral peak stripping.

[0049] Figure 4 Figure 5 is a schematic diagram of the spectral peak extraction result taking styrene as an example, where the positions marked by the red circles in the figure are the fluorescence spectrum peak positions searched by the spectral peak search method.

[0050] S4: Use principal component analysis to extract the eigenvectors of the three-dimensional fluorescence spectrum and the background spectrum of benzene series pollutants, and construct a support vector machine classification model using the eigenvectors and their corresponding pollution labels (presence or absence).

[0051] S5: Obtain a sample of the river water to be tested for the presence of unknown target benzene series pollutants, perform sample processing according to the sample processing method in step S1, collect its three-dimensional fluorescence spectrum data, and perform spectral preprocessing according to step S2 to obtain the spectral data of the preprocessed sample to be tested.

[0052] The unknown sample in this embodiment is composed of a single mixture of two backgrounds and four benzene series pollutants. The specific sample situation is shown in Table 2. Among them, background Ⅰ is normal river water, and background Ⅱ is the background of river water with high-concentration dissolved organic matter (fulvic acid with a final concentration of 20 mg / L and tryptophan with a final concentration of 2 mg / L were added to normal river water).

[0053] Figure 5 Figure 6 is the three-dimensional fluorescence spectrum diagram of the two background water samples; Figure 5 In (a) of Figure 6 is the three-dimensional fluorescence spectrum diagram of normal river water, Figure 5 In (b) of Figure 6 is the three-dimensional fluorescence spectrum diagram of river water with high-concentration dissolved organic matter.

[0054] Table 2: Composition table of unknown samples

[0055]

[0056] S6: Apply the Doppler - Gaussian spectral line fitting combined with total variation denoising (DCF - TV) algorithm to the pre - processed spectral data in step S5 to obtain the characteristic spectra for the target benzene - series pollutants, eliminating the interference of background spectral information. Then, perform principal component analysis on the characteristic spectra together with the three - dimensional fluorescence spectral data of the target pollutants and normal river water in step S2 to extract the eigenvectors, and use the support vector machine classification model established in step S4 to determine whether the target benzene - series pollutants exist in the eigenvectors of the test samples.

[0057] Figure 6 It is the flowchart of the characteristic extraction method combining Doppler - Gaussian spectral line fitting with total variation denoising, including the following sub - steps:

[0058] S6.1: Perform peak search based on local maximum discrimination on the three - dimensional fluorescence spectrum of the pre - processed test sample according to the peak search method in step S3 to obtain the positions of fluorescence peaks that meet the requirements. , represents the excitation wavelength corresponding to the fluorescence peak, represents the emission wavelength corresponding to the fluorescence peak.

[0059] S6.2: Compare the positions of the fluorescence peaks extracted in step S6.1 with the positions of the fluorescence peaks of the target benzene - series pollutants extracted in step S3.

[0060] The specific operation is as follows: Calculate the minimum distance between the positions of the fluorescence peaks extracted in step S6.1 and the positions of the fluorescence peaks of the target benzene - series pollutants extracted in step S3. The calculation process is as follows:

[0061] ;

[0062] and are the excitation and emission wavelengths corresponding to the fluorescence peak of the test sample extracted in step S6.1, and are the position information of the fluorescence peaks of the target benzene - series pollutants, corresponding to the excitation wavelength and emission wavelength respectively, is the threshold for peak screening. If the distance is less than the threshold, it is considered to be the peak of the target benzene - series pollutants, and the threshold value is set according to the actual situation.

[0063] Among them, the target benzene - series pollutants for comparison include all concentrations used in step S1. If the calculation result of any concentration is lower than the threshold, it can be considered that the fluorescence peak position information belongs to the target benzene - series pollutants.

[0064] S6.3: For the spectral peaks screened in step S6.2, use the collision broadening formula for spectral line broadening to fit the excitation spectra of each spectral peak. For spectral peaks with a fitting degree lower than the threshold ( ), identify them as non-material interference peaks such as instrument noise, and conduct a secondary screening of spectral peaks; the remaining spectral peaks after removing the spectral peaks of the target benzene series pollutants and non-material interference peaks through the two screenings are identified as the fluorescence spectra of other substances other than benzene series pollutants.

[0065] The specific operation is as follows: For the spectral peaks screened in step S6.2 (removing the spectral peaks of the target benzene series pollutants), after obtaining the position information of its fluorescence spectral peaks and fluorescence intensity , conduct spectral line fitting on its excitation spectrum, calculate the fitting degree , and for spectral peaks with a fitting degree lower than the threshold (

[0066] ), identify them as non-material interference peaks such as instrument noise and ignore them; the remaining spectral peaks after screening are identified as the fluorescence spectra of other substances other than benzene series pollutants (i.e., interference spectral peaks).

[0067] ;

[0068] where, is the excitation wavelength of the spectral peak, is the spectral half-line width, is the independent variable excitation wavelength of the fitting curve.

[0069] S6.4: For the fluorescence spectra of other substances screened in step S6.3, use the spectral line fitting method to fit the excitation spectrum and emission spectrum of each spectral peak, and then interpolate and expand them to a three-dimensional fluorescence spectrum to realize the mathematical characterization of interference spectral peaks; use total variation denoising to strip the spectral peaks of other substances to obtain a relatively pure characteristic spectrum of the sample to be measured for subsequent classification and discrimination.

[0070] The specific spectral line fitting method for the excitation spectrum and emission spectrum in step S6.4 is as follows:

[0071] Taking the excitation spectrum as an example, its spectral line shape expression for Doppler broadening is:

[0072] .

[0073] Its spectral line shape expression for collision broadening is:

[0074] .

[0075] Its spectral line shape expression for Voigt broadening is:

[0076] 。

[0077] Among them, is the spectral peak excitation wavelength, is the spectral half-width, is the wavelength broadening amount, and its calculation formula is:

[0078] ;

[0079] Among them is the spectral line width, is the speed of light in vacuum, is the Boltzmann constant, is the absolute temperature, is the gas molecular mass.

[0080] Figure 7 is a schematic diagram of the fitting effect of the excitation spectrum with phenol as an example. Among them, the unit of the excitation wavelength is nm. In the actual fitting process, for the case of a single fluorescence spectral peak, taking the excitation wavelength of the spectral peak as the boundary, the Doppler broadening fitting effect is better at low excitation wavelengths, while the collision broadening fitting effect is better at high wavelengths.

[0081] The interpolation expansion method of the three-dimensional fluorescence spectrum in step S6.4 is specifically as follows:

[0082] Assume that the excitation spectrum curve at any emission wavelength conforms to the spectral line broadening theory. Take the fluorescence intensity value on the emission spectrum corresponding to the spectral peak as the peak value of the excitation spectrum at the corresponding emission wavelength, and use the segmented Doppler-collision broadening model to fit the excitation spectrum at each emission wavelength. Taking the excitation wavelength of the spectral peak as the boundary, use Doppler broadening fitting at low excitation wavelengths and collision broadening fitting at high wavelengths, that is, it is fitted by the following formula:

[0083] When is adopted:

[0084] ;

[0085] When is adopted: ;

[0086] Among them, is the fluorescence intensity, is the peak value of the excitation spectrum at the corresponding emission wavelength, is the spectral peak excitation wavelength, is the spectral peak emission wavelength, is the spectral half-width, is the independent variable excitation wavelength, is the independent variable emission wavelength.

[0087] Similarly, a segmented Doppler-collision broadening model is adopted. Taking the emission wavelength of the interference spectrum peak as the boundary, the Doppler broadening formula is used for wavelengths below the boundary, and the collision broadening formula is used for wavelengths above the boundary to fit the emission spectra at each excitation wavelength. Finally, a three-dimensional fluorescence spectrum is extended to obtain the spectrum of the external interference object.

[0088] Figure 8 Figure 5 shows a comparison chart of the fitting effects of the three-dimensional fluorescence spectrum peaks with styrene as an example; Figure 8 In (a) of Figure 5, it is the original three-dimensional fluorescence spectrum, Figure 8 In (b) of Figure 5, it is the three-dimensional fluorescence spectrum after fitting. According to the image comparison, the similarity of the spectral peak fitting is relatively high, and there are fitting differences at the spectral peak edges.

[0089] The specific method of spectral peak stripping by total variation denoising in step S6.4 is as follows:

[0090] The following total variation model is adopted, and Bregman iteration is used for denoising.

[0091] ;

[0092] ;

[0093] Among them, is the energy functional, is a non-negative parameter, is the target characteristic spectrum to be obtained, is the spectrum of the external interference object, is the spectrum directly measured by the instrument (i.e., the three-dimensional fluorescence spectrum data collected in step S5), is the regularization term used to maintain the smoothness of the spectrum.

[0094] At this time, the functional to be minimized is:

[0095] .

[0096] Among them, the spectrum of the interference object has been characterized as a mathematical function by the spectral line broadening fitting method:

[0097] ;

[0098] Among them, is the central wavelength of the excitation spectrum, is the central wavelength of the emission spectrum, is the standard deviation, which is used to describe the broadening degree of the spectral line, is the excitation wavelength of and the emission wavelength of under the fluorescence intensity.

[0099] In this specific embodiment, Accuracy, Precision, Recall, and F1-score are selected as evaluation indicators.

[0100] For the four benzene series pollutants under Background I, the detection effects of the present invention are shown in Table 3.

[0101] Table 3: Table of various evaluation indicators for four benzene series pollutants under Background I

[0102]

[0103] For the four benzene series pollutants under Background II, the detection effects of the present invention are shown in Table 4.

[0104] Table 4: Table of various evaluation indicators for four benzene series pollutants under Background II

[0105]

[0106] The detection effects of the present invention under the two backgrounds demonstrate the high mobility of the method of the present invention under different river detection backgrounds. In the face of Background II that was not involved in training, the detection effect of the method of the present invention changes little and still remains at a relatively high level, showing the anti-interference performance in the detection of complex water sample backgrounds.

[0107] The above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions, or substitutions made by those skilled in the art within the substantial scope of the present invention should also fall within the protection scope of the present invention.

Claims

1. A method for identifying benzene series compounds in three-dimensional fluorescence spectra by combining spectral line fitting and total variation denoising, characterized in that Including the following steps: Collect the three-dimensional fluorescence spectra of the pure water background sample solution of the target benzene series pollutants and the non-polluted normal river water sample, which are used as the spectra of the target benzene series pollutants and the background spectrum respectively; Adopt the spectral peak search method to extract the fluorescence spectral peak position information of the target benzene series pollutants spectrum; extract the eigenvectors of the target benzene series pollutants spectrum and the background spectrum through principal component analysis, establish a data set, use pollution or non-pollution as the label, and construct a classification model based on machine learning; Collect the three-dimensional fluorescence spectrum of the sample to be measured, adopt the spectral peak search method to extract the fluorescence spectral peak position information of the three-dimensional fluorescence spectrum of the sample to be measured, and remove the fluorescence spectral peaks whose distance from the fluorescence spectral peak position of the target benzene series pollutants spectrum is less than the threshold; fit the excitation spectrum with the collision broadening formula, and remove the fluorescence spectral peaks with a fitting degree lower than the threshold to obtain the interfering spectral peaks; Taking the excitation wavelength or emission wavelength of the interfering spectral peak as the boundary, use the Doppler broadening formula for the excitation wavelength or emission wavelength lower than the boundary, and use the collision broadening formula for the excitation wavelength or emission wavelength higher than the boundary to fit the excitation spectra at each emission wavelength and the emission spectra at each excitation wavelength respectively to obtain the three-dimensional fluorescence spectrum of the interfering substance; Based on total variation denoising, strip the three-dimensional fluorescence spectrum of the interfering substance from the three-dimensional fluorescence spectrum of the sample to be measured to obtain the characteristic spectrum; Extract the eigenvector of the characteristic spectrum through principal component analysis, input it into the classification model, and judge whether the target benzene series pollutants exist.

2. The three-dimensional fluorescence spectrum benzene series compound recognition method based on spectral line fitting combined with total variation denoising according to claim 1, wherein After collecting the three-dimensional fluorescence spectrum, preprocessing is also included; the preprocessing includes: performing Raman scattering removal, Rayleigh scattering removal and smoothing.

3. The three-dimensional fluorescence spectrum benzene series compound recognition method based on spectral line fitting combined with total variation denoising according to claim 1, characterized in that, The specific spectral peak search method is: search for the local maximum value in the three-dimensional fluorescence spectrum, and calculate the average value and variance of the fluorescence intensity in the 15nm×15nm area near the local maximum value; if the local maximum value is greater than the sum of the average value and three times the variance, extract the fluorescence spectral peak position corresponding to the local maximum value, and the fluorescence spectral peak position is represented by the excitation wavelength and emission wavelength corresponding to the fluorescence spectral peak.

4. The three-dimensional fluorescence spectrum benzene series compound recognition method based on spectral line fitting combined with total variation denoising according to claim 1, characterized in that The support vector machine is used for constructing the classification model based on machine learning.

5. The three-dimensional fluorescence spectrum benzene series identification method based on spectral line fitting combined with total variation denoising according to claim 1, characterized in that The Euclidean distance formula is used to remove the fluorescence spectral peaks whose distance from the fluorescence spectral peak position of the target benzene series pollutants spectrum is less than the threshold.

6. The three-dimensional fluorescence spectrum benzene series compound recognition method based on spectral line fitting combined with total variation denoising according to claim 1, characterized in that The pure water background sample solution of the target benzene series pollutants contains multiple concentrations. After extracting the fluorescence spectral peak position information of the three-dimensional fluorescence spectrum of the sample to be measured, remove the fluorescence spectral peaks whose distance from the fluorescence spectral peak position of the target benzene series pollutants spectrum at any concentration is less than the threshold.

7. The method for identifying benzene series compounds in three-dimensional fluorescence spectra by spectral line fitting combined with total variation denoising according to claim 1, characterized in that, Taking the excitation wavelength of the interfering spectral peak as the boundary, the following Doppler broadening formula is used for the excitation wavelength lower than the boundary: ； The following collision broadening formula is used for the excitation wavelength higher than the boundary: ； Among them, is the fluorescence intensity, is the peak value of the excitation spectrum corresponding to the emission wavelength, is the excitation wavelength of the spectral peak, is the emission wavelength of the spectral peak, is the spectral half-width, is the wavelength broadening amount, is the independent variable excitation wavelength, is the independent variable emission wavelength.

8. The three-dimensional fluorescence spectrum benzene series compound recognition method based on spectral line fitting combined with total variation denoising according to claim 1, characterized in that, Based on total variation denoising, stripping the three-dimensional fluorescence spectrum of the interfering substance from the three-dimensional fluorescence spectrum of the sample to be measured to obtain the characteristic spectrum, specifically: Adopt the following total variation model and use Bregman iteration for denoising: ； ； wherein, is the energy functional, is a non - negative parameter, is the target characteristic spectrum to be obtained, is the spectrum of external interferents, is the spectrum directly measured by the instrument, is the regularization term used to maintain the spectral smoothness; The functional to be minimized at this time is: 。

Images