CN112504983A - Nitrate concentration prediction method based on turbidity chromaticity compensation - Google Patents
Nitrate concentration prediction method based on turbidity chromaticity compensation Download PDFInfo
- Publication number
- CN112504983A CN112504983A CN202011464423.0A CN202011464423A CN112504983A CN 112504983 A CN112504983 A CN 112504983A CN 202011464423 A CN202011464423 A CN 202011464423A CN 112504983 A CN112504983 A CN 112504983A
- Authority
- CN
- China
- Prior art keywords
- nitrate concentration
- turbidity
- sample
- concentration prediction
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 229910002651 NO3 Inorganic materials 0.000 title claims abstract description 83
- NHNBFGGVMKEFGY-UHFFFAOYSA-N Nitrate Chemical compound [O-][N+]([O-])=O NHNBFGGVMKEFGY-UHFFFAOYSA-N 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000002371 ultraviolet--visible spectrum Methods 0.000 claims abstract description 33
- 230000003595 spectral effect Effects 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000010801 machine learning Methods 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims abstract description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 67
- 238000001228 spectrum Methods 0.000 claims description 17
- 238000002835 absorbance Methods 0.000 claims description 14
- 239000000243 solution Substances 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 11
- 239000012088 reference solution Substances 0.000 claims description 6
- 238000000411 transmission spectrum Methods 0.000 claims description 6
- 238000000862 absorption spectrum Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 235000013405 beer Nutrition 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000002834 transmittance Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 4
- 238000002211 ultraviolet spectrum Methods 0.000 abstract description 4
- 238000010521 absorption reaction Methods 0.000 description 7
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 description 6
- CLBRCZAHAHECKY-UHFFFAOYSA-N [Co].[Pt] Chemical compound [Co].[Pt] CLBRCZAHAHECKY-UHFFFAOYSA-N 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 239000011259 mixed solution Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 239000003153 chemical reaction reagent Substances 0.000 description 3
- 239000008367 deionised water Substances 0.000 description 2
- 229910021641 deionized water Inorganic materials 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052793 cadmium Inorganic materials 0.000 description 1
- BDOSMKKIYDKNTQ-UHFFFAOYSA-N cadmium atom Chemical compound [Cd] BDOSMKKIYDKNTQ-UHFFFAOYSA-N 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012851 eutrophication Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000004255 ion exchange chromatography Methods 0.000 description 1
- 150000002500 ions Chemical class 0.000 description 1
- 239000008239 natural water Substances 0.000 description 1
- 239000002244 precipitate Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 239000012086 standard solution Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000001429 visible spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/33—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using ultraviolet light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/59—Transmissivity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Abstract
The invention relates to a nitrate concentration prediction method based on turbidity chromaticity compensation. The method solves the problem of low measurement precision of the method for realizing the nitrate concentration prediction by using the existing nitrate concentration prediction model. The method comprises the steps of firstly preprocessing original ultraviolet spectrum data of a measured sample, then extracting spectral features, using the extracted features and turbidity chromaticity information of the measured sample as input of a machine learning model, using nitrate concentration information of the sample as output of the machine learning model, and training a concentration prediction model based on machine learning. And (3) bringing the spectral data and the turbidity chrominance information after the characteristic extraction of the sample to be tested into a trained concentration prediction model, outputting a prediction result, and obtaining the nitrate concentration of a new sample. Higher nitrate concentration prediction accuracy can be obtained by compensating the influence of turbidity and chromaticity on the ultraviolet-visible spectrum curve.
Description
Technical Field
The invention relates to a nitrate concentration prediction method based on turbidity chromaticity compensation.
Background
The over-high concentration of nitrate in the water body can cause the problems of water body eutrophication, harm to human health and the like. The traditional nitrate determination method comprises an ion chromatography method, a cadmium column reduction method, an ion electrode method and the like, but has the defects of high price, complex operation, long analysis time, reagent consumption, secondary pollution to water and the like.
The ultraviolet visible spectrum technology has the advantages of convenient and fast measurement, no need of introducing other reagents and the like, so that the method can be used for measuring the concentration of nitrate in water. The method utilizes the principle that a measuring substance absorbs ultraviolet visible spectrum radiation, substitutes the spectrum information of the water sample to be measured into a nitrate concentration prediction model to predict the concentration of the water sample, and has high sensitivity but low measurement precision.
Disclosure of Invention
The invention aims to provide a nitrate concentration prediction method based on a turbidity chromaticity compensation algorithm, and solves the problem of low measurement precision of the nitrate concentration prediction method realized by using the existing nitrate concentration prediction model.
The basic idea of the prediction method of the invention is as follows: through analyzing the modeling of the existing nitrate concentration prediction model, the reason that the prediction precision is low is found to be that the turbidity and the chroma of the water sample to be detected are too high, and the prediction of the nitrate concentration is interfered. Therefore, the method comprises the steps of firstly preprocessing the original ultraviolet spectrum data of the measured sample, then extracting the spectrum characteristics, using the extracted characteristics and the turbidity chromaticity information of the measured sample as the input of a machine learning model, using the nitrate concentration information of the sample as the output of the machine learning model, and training the concentration prediction model based on machine learning. And (3) bringing the spectral data and the turbidity chrominance information after the characteristic extraction of the sample to be tested into a trained concentration prediction model, outputting a prediction result, and obtaining the nitrate concentration of a new sample.
The technical scheme of the invention is to provide a nitrate concentration prediction method for turbidity chromaticity compensation, which is characterized by comprising the following steps:
step 1.1, establishing a training sample set and a verification sample set;
step 1.11, collecting turbidity and chromaticity information of n groups of water samples; wherein n is a natural number greater than 1;
step 1.12, obtaining ultraviolet-visible spectrum curves of the n groups of water samples;
step 1.13, preprocessing the ultraviolet-visible spectrum curves of the n groups of water samples to obtain absorbance curves of the n groups of water samples;
step 1.14, extracting the absorbance curve spectral characteristics of the n groups of water samples;
step 1.15, constructing sample information by using the spectral characteristic data and the turbidity chrominance information of the n groups of water samples; one part of the sample information is used as a training sample set, and the other part of the sample information is used as a verification sample set;
step 1.2, using a Back Propagation Neural Network (BPNN) in machine learning as a modeling method, using spectral characteristic data and turbidity chrominance information of each group of water samples in a training sample set as input of a nitrate concentration prediction model, using nitrate concentration information of each group of water samples as output of the nitrate concentration prediction model, and training to obtain the nitrate concentration prediction model;
step 1.3, inputting spectral characteristic data and turbidity chrominance information of each group of water samples in the verification sample set into a trained nitrate concentration prediction model, and verifying the nitrate concentration prediction model;
step 2.1, collecting turbidity and chromaticity information of a water sample to be detected;
step 2.2, obtaining an ultraviolet-visible spectrum curve of the water sample to be detected;
step 2.3, preprocessing the ultraviolet-visible spectrum curve of the water sample to be detected to obtain the absorbance curve of the water sample to be detected;
2.4, extracting the spectral characteristics of the absorbance curve of the water sample to be detected;
and 2.5, inputting the spectral characteristics and turbidity chromaticity information of the water sample to be detected into the nitrate concentration prediction model verified in the first step, and outputting a prediction result to obtain the nitrate concentration of the water sample to be detected.
Further, the pretreatment processes in step 1.13 and step 2.3 are specifically:
firstly, extracting the characteristics to be detected of an ultraviolet-visible spectrum curve:
wherein, XiIs the spectrum of the i-th group of water samples, XDark backgroundSpectrum against dark background, XReference solutionAs spectrum of the base solution, TiDeducting a dark background for the ith group of water samples, and using a reference solution as a transmission spectrum value after baseline correction;
the transmission spectrum is then converted to an absorbance spectrum according to lambert beer's law:
wherein a (λ) and T (λ) represent absorbance and transmittance at a wavelength λ, respectively;
and finally, denoising by adopting an MSC and SNV preprocessing algorithm.
Further, in step 1.14 and step 2.4, the spectral feature extraction is performed by a manifold learning method.
Further, in step 1.3, the nitrate concentration prediction model is validated based on the Root Mean Square Error (RMSEP) and the coefficient of determination (R) of the validation parameters2) The lower the RMSEP, the lower R2The higher the prediction accuracy of the model, the higher the prediction accuracy.
The invention has the beneficial effects that:
1. according to the invention, through analyzing the modeling of the existing nitrate concentration prediction model, the prediction accuracy of the water sample is found to be influenced by overhigh turbidity and chromaticity, so that the higher nitrate concentration prediction accuracy can be obtained by performing cross validation modeling by using the spectral information and turbidity chromaticity of the water sample and the corresponding nitrate concentration and compensating the influence of the turbidity and chromaticity on an ultraviolet-visible spectrum curve.
2. The method is used for measuring the nitrate concentration based on the ultraviolet-visible spectrum technology, is convenient and quick, does not need to introduce other reagents, and does not produce secondary pollution to water.
Drawings
FIG. 1 is a graph of UV-visible spectra of platinum-cobalt solutions of different chromaticities;
FIG. 2 is a graph of ultraviolet-visible spectra of formalin suspension at different turbidity;
FIG. 3 is a graph of UV-Vis spectra of mixed solutions of the same nitrate concentration, different chromaticities, and turbidity;
FIG. 4 is a flowchart of the modeling and verification of the chroma turbidity compensation algorithm of the present invention;
FIG. 5 is an original UV-Vis spectrum curve of a collected water sample;
FIG. 6 is a schematic diagram of a turbidity chromaticity compensated nitrate concentration prediction method according to the present invention;
fig. 7 is an absorbance curve of 94 water samples.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments.
The invention passes through the cash registerThe modeling of a nitrate concentration prediction model is used for analysis, and the fact that the turbidity and the chroma in a water sample to be detected are too high is found to interfere with the prediction of the nitrate concentration in the water sample to be detected. The interference of chromaticity is shown in that it generates a new absorption peak in the ultraviolet-visible spectrum curve, and the absorption peak may overlap with the characteristic peak of nitrate, thereby causing the shift of the nitrate absorption peak. In chemistry, the change in substituent or solvent often results in the absorption band maximum wavelength λ of the solutemaxThe shift is called red shift in the long wavelength direction and blue shift in the short wavelength direction. In the ultraviolet spectrum section, because the particles causing turbidity generate adsorption on organic matters, the influence of the turbidity on the ultraviolet spectrum of the water sample is complex; in the visible spectrum, the effect of turbidity on the spectrum diminishes with increasing wavelength.
Because the platinum-cobalt solution has similar color tone to natural water yellow, the platinum-cobalt standard solution is diluted into different chroma solutions by adding deionized water, and the measured ultraviolet-visible spectrum curve is shown in figure 1, and an obvious absorption peak appears between 200 and 300 nm. This absorption peak overlaps with the characteristic peak of nitrate, resulting in a shift in the nitrate absorption peak, thereby affecting the nitrate concentration prediction accuracy.
Different turbidity solutions are diluted by formalin standard suspension and deionized water, and measured ultraviolet-visible spectrum curves are shown in fig. 2, so that the measured ultraviolet-visible spectrum curves show that when the turbidity in the water body is too high, on one hand, the solution can block the transmission of light, on the other hand, the formalin turbidity solution can absorb light between 200 and 300nm, and the characteristic peak position and the ultraviolet-visible spectrum curve of nitrate can be affected, so that the modeling prediction of the nitrate concentration is interfered.
The uv-vis spectra of the mixed solution with the same nitrate concentration and different color and turbidity are shown in fig. 3, and it can be seen from table 1 that each uv-vis spectrum is different due to the interference of color and turbidity.
TABLE 1 turbidity and color data for turbidity mixed solutions of the same nitrate concentration and different colors.
Based on the analysis, the influence of chromaticity and turbidity is considered when the nitrate concentration prediction model is established, and the accuracy of nitrate concentration prediction is improved.
The basic idea of the method of the invention is as follows: firstly, preprocessing the original ultraviolet-visible spectrum data of a measured training sample, then extracting the spectrum characteristics by a manifold learning method, using the extracted spectrum characteristics and the turbidity chromaticity information of the measured training sample as the input of a nitrate concentration prediction model, using the nitrate concentration information of the training sample as the output of the model, and training the nitrate concentration prediction model based on machine learning. And verifying the prediction accuracy of the model by using the test sample. The accuracy evaluation is based mainly on the Root Mean Square Error (RMSEP) and the coefficient of determination (R) of the verification parameters2) To ensure a comprehensive description of the model. And then, bringing the spectral characteristics and the turbidity chromaticity information of the sample to be tested into a prediction model, outputting a prediction result, and obtaining the nitrate concentration of the sample to be tested.
The specific method is shown in fig. 4, and comprises the following steps:
1) respectively collecting turbidity and chromaticity information of 94 groups of water samples by using a turbidity meter and a chromaticity meter; the chromaticity range of 94 groups of water samples is 7-15 platinum cobalt, and the turbidity range is 7-15 NTU;
2) and obtaining the original ultraviolet-visible spectrum curve of the water sample, wherein fig. 5 is the original ultraviolet-visible spectrum curve of 1 group of water samples, which contains light source spectrum, dark background noise and the like, so that the spectrum information of the object to be detected (namely nitrate) is not prominent and is inconvenient for modeling calculation.
3) Preprocessing an original ultraviolet-visible spectrum curve;
preprocessing the original ultraviolet-visible spectrum curves of the 94 groups of water samples obtained in the step 2), and removing noise generated by an instrument and influence of solid precipitate particles in the water samples on the ultraviolet-visible spectrum curves;
the pretreatment is divided into two parts, firstly, the characteristic to be measured of the original ultraviolet-visible spectrum curve is extracted (background dark noise is removed when a sample is collected, and the spectrum information of the solution except the substance to be measured is weakened), and the following formula is used:
wherein, XiIs the spectrum of the i-th group of water samples, XDark backgroundSpectrum against dark background, XReference solutionAs spectrum of the base solution, TiAnd (4) subtracting a dark background for the ith water sample, and taking a reference solution as a transmission spectrum value after baseline correction.
And then converting the transmission spectrum into an absorbance spectrum according to the Lambert beer law, wherein the calculation formula is as follows:
where a (λ) and T (λ) represent absorbance and transmittance at a wavelength λ, respectively. The absorbance spectrum obtained by calculation.
And finally, denoising by adopting mature preprocessing algorithms such as MSC and SNV. For 94 groups of samples of the modeling method provided by the invention, fig. 7 is an absorbance curve of the sample after the pretreatment is completed.
4) Extracting spectral characteristics of the pretreated 94 groups of water sample absorbance curves by a manifold learning method; constructing sample information by using spectral characteristic data and turbidity chrominance information of each group of water samples; one part of the sample information is used as a training sample set, and the other part of the sample information is used as a verification sample set;
5) obtaining a nitrate concentration prediction model;
adopting a Back Propagation Neural Network (BPNN) in machine learning as a modeling method, as shown in FIG. 6, inputting spectral characteristic data and turbidity chromaticity information (a training sample set) into a model, and training nitrate concentration information of each group of water samples as output of the model to obtain a nitrate concentration prediction model;
6) verifying a nitrate concentration prediction model;
will be examinedInputting a sample set, namely a nitrate concentration prediction model obtained in the step 5), adjusting manifold learning algorithm parameters and BPNN input parameters in a training process, and verifying the Root Mean Square Error (RMSEP) and the coefficient of determination (R) of a prediction result of the sample set by calculation2) And obtaining a nitrate concentration prediction model which enables the best prediction effect of the verification sample set. The above parameters may be different for different samples to be tested.
7) Obtaining the concentration of nitrate;
and substituting the spectral data and the turbidity chrominance information after the characteristic extraction of the sample to be detected into the nitrate concentration prediction model, and outputting a prediction result to obtain the nitrate concentration of the sample to be detected.
Experiments were performed using the prediction method of the present invention and the conventional nitrate prediction method on 94 sets of samples of nitrate solutions with different turbidity shades. The results of the predictions of the presence or absence of colorimetric turbidity compensation after using the two preprocessing algorithms of multivariate scatter correction MSC and standard normal transform SNV are compared, respectively, as shown in Table 2.
TABLE 2 comparison of results of predicting nitrate concentration in mixed solution samples by different methods
As can be seen from Table 2, no matter SNV or MSC is adopted as the spectral data preprocessing method, the prediction accuracy can be improved after the chroma turbidity compensation, and the prediction accuracy is expressed as R2Elevated, while RMSEP is reduced.
Claims (4)
1. A turbidity chromaticity compensation nitrate concentration prediction method is characterized by comprising the following steps:
step 1, establishing, training and verifying a nitrate concentration prediction model;
step 1.1, establishing a training sample set and a verification sample set;
step 1.11, collecting turbidity and chromaticity information of n groups of water samples; wherein n is a natural number greater than 1;
step 1.12, obtaining ultraviolet-visible spectrum curves of the n groups of water samples;
step 1.13, preprocessing the ultraviolet-visible spectrum curves of the n groups of water samples to obtain absorbance curves of the n groups of water samples;
step 1.14, extracting the absorbance curve spectral characteristics of the n groups of water samples;
step 1.15, constructing sample information by using the spectral characteristic data and the turbidity chrominance information of the n groups of water samples; one part of the sample information is used as a training sample set, and the other part of the sample information is used as a verification sample set;
step 1.2, using a Back Propagation Neural Network (BPNN) in machine learning as a modeling method, using spectral characteristic data and turbidity chrominance information of each group of water samples in a training sample set as input of a nitrate concentration prediction model, using nitrate concentration information of each group of water samples as output of the nitrate concentration prediction model, and training to obtain the nitrate concentration prediction model;
step 1.3, inputting spectral characteristic data and turbidity chrominance information of each group of water samples in the verification sample set into a trained nitrate concentration prediction model, and verifying the nitrate concentration prediction model;
step 2, obtaining the nitrate concentration of the water sample to be detected;
step 2.1, collecting turbidity and chromaticity information of a water sample to be detected;
step 2.2, obtaining an ultraviolet-visible spectrum curve of the water sample to be detected;
step 2.3, preprocessing the ultraviolet-visible spectrum curve of the water sample to be detected to obtain the absorbance curve of the water sample to be detected;
2.4, extracting the spectral characteristics of the absorbance curve of the water sample to be detected;
and 2.5, inputting the spectral characteristics and turbidity chromaticity information of the water sample to be detected into the nitrate concentration prediction model verified in the first step, and outputting a prediction result to obtain the nitrate concentration of the water sample to be detected.
2. The turbidity chromaticity compensated nitrate concentration prediction method according to claim 1, wherein the pretreatment processes in step 1.13 and step 2.3 are specifically:
firstly, extracting the characteristics to be detected of an ultraviolet-visible spectrum curve:
wherein, XiIs the spectrum of the i-th group of water samples, XDark backgroundSpectrum against dark background, XReference solutionAs spectrum of the base solution, TiDeducting a dark background for the ith group of water samples, and using a reference solution as a transmission spectrum value after baseline correction;
the transmission spectrum is then converted to an absorbance spectrum according to lambert beer's law:
wherein a (λ) and T (λ) represent absorbance and transmittance at a wavelength λ, respectively;
and finally, denoising by adopting an MSC and SNV preprocessing algorithm.
3. The turbidity chromaticity compensated nitrate concentration prediction method according to claim 2, wherein: the spectral feature extraction is performed in step 1.14 and step 2.4 by a manifold learning method.
4. The turbidity chromaticity compensated nitrate concentration prediction method according to claim 3, wherein: in step 1.3, the Root Mean Square Error (RMSEP) and the coefficient of determination (R) are determined based on the verification parameters2) And (5) verifying a nitrate concentration prediction model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011464423.0A CN112504983A (en) | 2020-12-11 | 2020-12-11 | Nitrate concentration prediction method based on turbidity chromaticity compensation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011464423.0A CN112504983A (en) | 2020-12-11 | 2020-12-11 | Nitrate concentration prediction method based on turbidity chromaticity compensation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112504983A true CN112504983A (en) | 2021-03-16 |
Family
ID=74972596
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011464423.0A Pending CN112504983A (en) | 2020-12-11 | 2020-12-11 | Nitrate concentration prediction method based on turbidity chromaticity compensation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112504983A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112924404A (en) * | 2021-05-11 | 2021-06-08 | 南京智谱科技有限公司 | Full-spectrum water quality monitoring system and method |
CN112986161A (en) * | 2021-05-11 | 2021-06-18 | 南京智谱科技有限公司 | Online wavelength calibration method and device for water quality monitoring spectrometer |
CN116183535A (en) * | 2023-04-23 | 2023-05-30 | 中国科学技术大学 | Method, system, equipment and medium for analyzing spectrum of macromolecular solution aging process |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104034684A (en) * | 2014-06-05 | 2014-09-10 | 北京金达清创环境科技有限公司 | Water quality multi-index detection method on basis of ultraviolet-visible absorption spectrum |
CN108647831A (en) * | 2018-05-16 | 2018-10-12 | 华南农业大学 | Ammonia nitrogen/content of nitrite forecasting system and method in a kind of culture environment of aquatic products of Multi-source Information Fusion |
CN109073457A (en) * | 2016-03-09 | 2018-12-21 | Ysi公司 | Optics nitrate sensor compensation algorithm for multi-parameter water quality measurement |
CN110887800A (en) * | 2019-11-27 | 2020-03-17 | 中国科学院西安光学精密机械研究所 | Data calibration method for online water quality monitoring system by using spectroscopy |
CN110987846A (en) * | 2019-11-27 | 2020-04-10 | 中国科学院西安光学精密机械研究所 | Nitrate concentration prediction method based on iPLS-PA algorithm |
-
2020
- 2020-12-11 CN CN202011464423.0A patent/CN112504983A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104034684A (en) * | 2014-06-05 | 2014-09-10 | 北京金达清创环境科技有限公司 | Water quality multi-index detection method on basis of ultraviolet-visible absorption spectrum |
CN109073457A (en) * | 2016-03-09 | 2018-12-21 | Ysi公司 | Optics nitrate sensor compensation algorithm for multi-parameter water quality measurement |
CN108647831A (en) * | 2018-05-16 | 2018-10-12 | 华南农业大学 | Ammonia nitrogen/content of nitrite forecasting system and method in a kind of culture environment of aquatic products of Multi-source Information Fusion |
CN110887800A (en) * | 2019-11-27 | 2020-03-17 | 中国科学院西安光学精密机械研究所 | Data calibration method for online water quality monitoring system by using spectroscopy |
CN110987846A (en) * | 2019-11-27 | 2020-04-10 | 中国科学院西安光学精密机械研究所 | Nitrate concentration prediction method based on iPLS-PA algorithm |
Non-Patent Citations (3)
Title |
---|
张维江: "《干旱地区水资源及其开发利用评价》", 31 October 2018, 黄河水利出版社 * |
王雪霁: "基于复杂水体的硝酸盐浓度精细光谱定量分析与预测方法研究", 《中国博士学位论文全文数据库 工程科技工程科技Ⅰ辑》 * |
陈颖等: "基于紫外光谱的水体硝酸盐氮浊度补偿研究", 《光谱学与光谱分析》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112924404A (en) * | 2021-05-11 | 2021-06-08 | 南京智谱科技有限公司 | Full-spectrum water quality monitoring system and method |
CN112986161A (en) * | 2021-05-11 | 2021-06-18 | 南京智谱科技有限公司 | Online wavelength calibration method and device for water quality monitoring spectrometer |
CN116183535A (en) * | 2023-04-23 | 2023-05-30 | 中国科学技术大学 | Method, system, equipment and medium for analyzing spectrum of macromolecular solution aging process |
CN116183535B (en) * | 2023-04-23 | 2023-08-29 | 中国科学技术大学 | Method, system, equipment and medium for analyzing spectrum of macromolecular solution aging process |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112504983A (en) | Nitrate concentration prediction method based on turbidity chromaticity compensation | |
CN103983595B (en) | A kind of water turbidity calculation method processed based on ultraviolet-visible spectrum | |
CN111239071B (en) | Method for detecting concentration of nitrate in seawater by spectrometry | |
CN109187392B (en) | Zinc liquid trace metal ion concentration prediction method based on partition modeling | |
CN104089911A (en) | Spectral model transmission method based on unary linear regression | |
CN106918567B (en) | A kind of method and apparatus measuring trace metal ion concentration | |
CN103175805B (en) | Method for determining indexes of COD and BOD5 in sewage through near infrared spectrometry | |
Wang et al. | High precision wide range online chemical oxygen demand measurement method based on ultraviolet absorption spectroscopy and full-spectrum data analysis | |
CN111855608B (en) | Near-infrared nondestructive detection method for apple acidity based on fusion characteristic wavelength selection algorithm | |
CN103543132B (en) | A kind of coal characteristic measuring method based on wavelet transformation | |
CN113484257B (en) | Water quality concentration calculating system and method based on neural network and full spectrum absorbance | |
CN111044503A (en) | Coal quality measurement method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy | |
CN113049512A (en) | Water quality on-line monitoring method based on full-wavelength ultraviolet-visible absorption spectrum | |
CN105486655A (en) | Rapid detection method for organic matters in soil based on infrared spectroscopic intelligent identification model | |
CN101943658B (en) | Method for continuously monitoring water quality by combining principal component analysis theory and spectrum analysis technology | |
CN111398233A (en) | Laser spectrum detection method for red wine quality | |
CN114894725A (en) | Water quality multi-parameter spectral data Stacking fusion model and water quality multi-parameter measuring method | |
CN105277531A (en) | Grading-based coal characteristic measurement method | |
CN107688007A (en) | A kind of detection method of the heat conduction oil quality based on near-infrared spectral analysis technology | |
Zhou et al. | Detection of chemical oxygen demand in water based on UV absorption spectroscopy and PSO-LSSVM algorithm | |
CN115728290A (en) | Method, system, equipment and storage medium for detecting chromium element in soil | |
CN101650306A (en) | Method for quickly testing and analyzing quality of sericite | |
Zhang et al. | Study on Nitrite Nitrogen Based on Ultraviolet Visible Absorption Spectrometry | |
CN109975275A (en) | The method for improving laser induced breakdown spectroscopy measurement nitrogen content of coal element precision | |
CN110907386A (en) | Multi-component gas analysis system and method for waste incineration power plant |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210316 |