CN109507144B - Embedded water organic phosphorus pesticide residue detection device and method - Google Patents
Embedded water organic phosphorus pesticide residue detection device and method Download PDFInfo
- Publication number
- CN109507144B CN109507144B CN201811579556.5A CN201811579556A CN109507144B CN 109507144 B CN109507144 B CN 109507144B CN 201811579556 A CN201811579556 A CN 201811579556A CN 109507144 B CN109507144 B CN 109507144B
- Authority
- CN
- China
- Prior art keywords
- optical fiber
- water body
- organophosphorus
- spectrum
- organophosphorus pesticide
- 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.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 61
- 238000001514 detection method Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 14
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 title claims description 8
- 229910052698 phosphorus Inorganic materials 0.000 title claims description 8
- 239000011574 phosphorus Substances 0.000 title claims description 8
- 239000000447 pesticide residue Substances 0.000 title description 2
- 239000013307 optical fiber Substances 0.000 claims abstract description 46
- 239000003987 organophosphate pesticide Substances 0.000 claims abstract description 46
- 238000001228 spectrum Methods 0.000 claims abstract description 43
- 239000000523 sample Substances 0.000 claims abstract description 42
- 241000544061 Cuculus canorus Species 0.000 claims abstract description 22
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 230000010365 information processing Effects 0.000 claims abstract description 20
- 238000007654 immersion Methods 0.000 claims abstract description 14
- 230000003595 spectral effect Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 11
- 230000003287 optical effect Effects 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 9
- 239000000126 substance Substances 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000002093 peripheral effect Effects 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims 2
- 238000005516 engineering process Methods 0.000 abstract description 11
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000002329 infrared spectrum Methods 0.000 abstract description 5
- 238000011897 real-time detection Methods 0.000 abstract description 5
- 239000000575 pesticide Substances 0.000 description 13
- 230000000694 effects Effects 0.000 description 4
- 239000012298 atmosphere Substances 0.000 description 3
- 230000006378 damage Effects 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000012488 sample solution Substances 0.000 description 2
- 241000238631 Hexapoda Species 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 229910052736 halogen Inorganic materials 0.000 description 1
- 150000002367 halogens Chemical class 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 150000002894 organic compounds Chemical class 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001988 toxicity Effects 0.000 description 1
- 231100000419 toxicity Toxicity 0.000 description 1
- WFKWXMTUELFFGS-UHFFFAOYSA-N tungsten Chemical compound [W] WFKWXMTUELFFGS-UHFFFAOYSA-N 0.000 description 1
- 229910052721 tungsten Inorganic materials 0.000 description 1
- 239000010937 tungsten Substances 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
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3577—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing liquids, e.g. polluted water
-
- 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
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Theoretical Computer Science (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention particularly relates to an embedded water body organophosphorus pesticide residue detection device which comprises an immersion type optical fiber probe detection module, a spectrometer and a spectrum information processing module, wherein the immersion type optical fiber probe detection module is used for collecting transmitted light and backscattered light of an organophosphorus pesticide sample to be detected and outputting the acquired transmitted light and backscattered light to the spectrometer; detection methods are also disclosed. The method adopts a near infrared spectrum detection technology, and the water body is directly put into the water body to be detected, so that the real-time detection of the content of the organophosphorus pesticide in the water body is realized; by an embedded system technology and by constructing a prediction model for the concentration of the organophosphorus pesticide in the water body by optimizing a neural network through a cuckoo algorithm, the rapid, sensitive, accurate and simple analysis of the concentration data of the organophosphorus pesticide in the water body is realized.
Description
Technical Field
The invention relates to the technical field of pesticide detection, in particular to an embedded device and a method for detecting organophosphorus pesticide residues in a water body.
Background
The use of the pesticide has important significance for preventing plant diseases and insect pests, improving the crop yield and guaranteeing national food safety, and soil, water and atmosphere are polluted to different degrees due to illegal and non-control use of the pesticide. The persistent organophosphorus pesticide remained in the environment migrates to high-rise or other areas through the atmosphere and water, so that the pollution range of the pesticide to the environment is continuously expanded. China is a big agricultural country, the used varieties and the use amount of pesticides are large, the pesticide yield reaches 40 ten thousand tons, and the pesticide occupies the top of the world. The organophosphorus pesticide is a phosphorus-containing organic compound, belongs to a broad-spectrum pesticide, has strong toxicity and is slowly decomposed in water and soil, so that the wide application of the organophosphorus pesticide causes serious direct or indirect pollution to soil, water, atmosphere and the like, and the damage to the ecological environment is increasingly serious. Pesticides can also migrate and accumulate through the food chain, creating hazards to environmental organisms and even humans. The organophosphorus pesticide has wide residual range and great harm effect, and brings great negative effects to food safety, human life health and agricultural product trade. Therefore, a more complete and perfect detection technology system is established, and the method has long-term significance for standardizing the use of organophosphorus pesticides and ensuring the safety of food.
Disclosure of Invention
The invention aims to provide a quick, sensitive and accurate embedded device for detecting organophosphorus pesticide residues in a water body.
In order to realize the purpose, the invention adopts the technical scheme that: the utility model provides an embedded water organophosphorus pesticide residue detection device, includes immersion optical fiber probe detection module, spectrum appearance and spectral information processing module, immersion optical fiber probe detection module be arranged in gathering the penetrating light and the back scattering light of organophosphorus pesticide sample that awaits measuring and export to the spectrum appearance in, the spectrum appearance decomposes the light signal and exports to spectral information processing module after for spectral signal, spectral information processing module substitutes the spectral signal in its storage the cuckoo algorithm optimize neural network in calculate organophosphorus pesticide concentration in the solution that awaits measuring and export.
Compared with the prior art, the invention has the following technical effects: the near infrared spectrum detection technology is adopted, a water sample is not required to be manually collected and processed, and the water sample is directly put into a water body to be detected, so that the real-time detection of the content of the organophosphorus pesticide in the water body is realized; by the embedded system technology and the prediction model for the concentration of the organophosphorus pesticide in the water body, which optimizes the neural network by the cuckoo algorithm, the water body organophosphorus concentration data is analyzed quickly, sensitively, accurately, simply and conveniently, and the requirements and regulations for quick analysis of the organophosphorus in the water body can be met.
The invention also aims to provide a rapid, sensitive and accurate method for detecting organophosphorus pesticide residues in the embedded water body.
In order to realize the purpose, the invention adopts the technical scheme that: an embedded water body organophosphorus pesticide residue detection method comprises the following steps: (A) the immersion type optical fiber probe detection module collects transmitted light and backscattered light of an organophosphorus pesticide sample to be detected and outputs the transmitted light and the backscattered light to the spectrometer, and the spectrometer decomposes an optical signal into a spectrum signal and outputs the spectrum signal to the spectrum information processing module; (B) carrying out baseline background subtraction or manual subtraction of baseline background by adopting an adaptive penalty least square method or wavelet change-based processing or frequency change-based processing or polynomial fitting-based processing; (C) selecting a full-range spectrum or a spectrum at a characteristic peak position to sequentially perform first derivative absolute value, multivariate scattering correction and standard normal transformation processing; (D) and substituting the preprocessed spectral data into the cuckoo algorithm optimization neural network stored in the spectral information processing module to calculate and output the concentration of the organophosphorus pesticide in the solution to be detected.
Compared with the prior art, the invention has the following technical effects: the near infrared spectrum detection technology is adopted, a water sample is not required to be manually collected and processed, and the water sample is directly put into a water body to be detected, so that the real-time detection of the content of the organophosphorus pesticide in the water body is realized; by the embedded system technology and the prediction model for the concentration of the organophosphorus pesticide in the water body, which optimizes the neural network by the cuckoo algorithm, the water body organophosphorus concentration data is analyzed quickly, sensitively, accurately, simply and conveniently, and the requirements and regulations for quick analysis of the organophosphorus in the water body can be met.
Drawings
FIG. 1 is a schematic diagram of the system architecture of the present invention;
FIG. 2 is a flow chart of construction of a CS-BP-based water body organophosphorus pesticide content prediction model.
Detailed Description
The present invention will be described in further detail with reference to fig. 1 to 2.
Referring to fig. 1, an embedded device for detecting organophosphorus pesticide residues in a water body comprises an immersion type optical fiber probe detection module 10, a spectrometer 20 and a spectrum information processing module 30, wherein the immersion type optical fiber probe detection module 10 is used for collecting transmitted light and backscattered light of an organophosphorus pesticide sample to be detected and outputting the collected transmitted light and backscattered light to the spectrometer 20, the spectrometer 20 decomposes an optical signal into a spectrum signal and outputs the spectrum signal to the spectrum information processing module 30, and the spectrum signal is substituted into a stored cuckoo algorithm optimization neural network by the spectrum information processing module 30 to calculate and output the concentration of organophosphorus pesticide in a solution to be detected. The near infrared spectrum detection technology is adopted, a water sample is not required to be manually collected and processed, and the water sample is directly put into a water body to be detected, so that the real-time detection of the content of the organophosphorus pesticide in the water body is realized; by the embedded system technology and the prediction model for the concentration of the organophosphorus pesticide in the water body, which optimizes the neural network by the cuckoo algorithm, the water body organophosphorus concentration data is analyzed quickly, sensitively, accurately, simply and conveniently, and the requirements and regulations for quick analysis of the organophosphorus in the water body can be met.
As a preferred embodiment of the present invention, the immersion type optical fiber probe detection module 10 includes a light source 11, a collimating mirror 12, a Y-shaped optical fiber 13, and an optical fiber probe 14, wherein light emitted from the light source 10 is collimated by the collimating mirror 12 and then output to an input end of the Y-shaped optical fiber 13, light entering from the input end of the Y-shaped optical fiber 13 is output to the optical fiber probe 14 from a common end of the Y-shaped optical fiber 13, the optical fiber probe 14 is immersed in the organic phosphorus pesticide sample solution to be detected, and light reflected from the optical fiber probe 14 is input from the common end of the Y-shaped optical fiber 13 and output to the spectrometer 20 from an output end of the Y-shaped optical fiber 13. The Y-shaped optical fiber 13 is used, so that the whole optical path is more simplified, and the optical path has a simple structure and is convenient to use.
The structure of the optical fiber probe 14 is many, and in the present invention, preferably, the optical fiber probe 14 includes a cylindrical housing 141 and a filter 142, a flat convex mirror 143, and a plane mirror 144 sequentially disposed in the housing 141, where one end of the housing 141 close to the filter 142 is connected to a common end of the Y-shaped optical fiber 13, where the filter 142 is used for filtering stray light in light, the flat convex mirror 143 is used for focusing light, the plane mirror 144 is used for reflecting light, the outlines of the filter 142, the flat convex mirror 143, and the plane mirror 144 are all circular, and the axial cores of the three lenses are coincident with the axial core of the housing 141; the area between the planoconvex mirror 143 and the planoconvex mirror 144 constitutes a measuring cell 145, and the peripheral wall of the outer shell of the measuring cell 145 is provided with a through hole 146 for allowing the organophosphorus pesticide sample solution to be measured to flow into the measuring cell 145. After the arrangement, all the lenses and the shell 141 are packaged together, so that collision and damage during use can be avoided, and the service life is prolonged; meanwhile, the structure is compact, the transmitted light and the backscattered light from the organophosphorus pesticide sample to be measured can be measured, and the internal reflected light within the dynamic range of the measurement is limited.
Further, an inner screw head 147 is arranged on one side of the outer shell 141 of the optical fiber probe 14 far away from the Y-shaped optical fiber 13, a plane mirror 144 is fixedly arranged on the inner screw head 147, a thread matched with the inner screw head 147 is arranged on the inner side of the outer shell 141 from the planoconvex mirror 143 to the end part of one side far away from the Y-shaped optical fiber 13, and a through hole 146 of a measuring cell 145 is arranged on the thread section. After the inner screw head 147 is arranged, the position of the plane mirror 144 can be adjusted, the measuring cell 145 is formed between the planoconvex mirror 143 and the plane mirror 144, the adjustment of the measuring cell 145 is realized through the adjustment of the plane mirror 144, the adjustable optical path of the probe measuring with the length of 2mm to 20mm can be realized in the embodiment, and the measurement of organophosphorus pesticide samples with different concentrations is realized through the flexible control of the optical path.
The light source 11, the spectrometer 20 and the spectrum information processing module 30 may select appropriate electrical components according to actual needs, and in this embodiment, preferably, the light source 11 is a high power halogen tungsten lamp with a model number of HL-2000-HP, and the spectrometer 20 is a NIRQUEST 512; the spectrum information processing module 30 comprises an S3C6410 microprocessor based on an ARM11 kernel, analytical models of different concentrations of different types of organophosphorus pesticides and different feature peak positions and peak values of corresponding spectrum information are stored in the microprocessor, and the microprocessor inputs the received spectrum information into the models to calculate and output the concentration of the organophosphorus pesticides in the solution to be detected.
The invention also discloses a method for detecting the organophosphorus pesticide residue in the embedded water body, which comprises the following steps: (A) the immersion type optical fiber probe detection module 10 collects transmitted light and backscattered light of an organophosphorus pesticide sample to be detected and outputs the transmitted light and the backscattered light to the spectrometer 20, and the spectrometer 20 decomposes an optical signal into a spectrum signal and outputs the spectrum signal to the spectrum information processing module 30; (B) carrying out baseline background subtraction or manual subtraction of baseline background by adopting an adaptive penalty least square method or wavelet change-based processing or frequency change-based processing or polynomial fitting-based processing; (C) selecting a full-range spectrum or a spectrum at a characteristic peak position to sequentially perform first derivative absolute value, multivariate scattering correction and standard normal transformation processing; (D) and substituting the preprocessed spectral data into the cuckoo algorithm optimization neural network stored in the spectral information processing module 30 to calculate and output the concentration of the organophosphorus pesticide in the solution to be detected. The near infrared spectrum detection technology is adopted, a water sample is not required to be manually collected and processed, and the water sample is directly put into a water body to be detected, so that the real-time detection of the content of the organophosphorus pesticide in the water body is realized; by the embedded system technology and the prediction model for the concentration of the organophosphorus pesticide in the water body, which optimizes the neural network by the cuckoo algorithm, the water body organophosphorus concentration data is analyzed quickly, sensitively, accurately, simply and conveniently, and the requirements and regulations for quick analysis of the organophosphorus in the water body can be met.
In the present invention, preferably, in step D, the model for predicting the concentration of the organophosphorus pesticide in the water body based on the cuckoo algorithm-optimized neural network stored in the spectral information processing module 30 is constructed according to the following steps: (D1) establishing a water body organophosphorus pesticide concentration prediction model based on a cuckoo algorithm optimization neural network on a PC (personal computer); (D2) selecting different types and concentrations of organic phosphorus standard products, collecting transmitted light and backscattered light of the organic phosphorus standard products by an immersion type optical fiber probe detection module 10, outputting the collected transmitted light and backscattered light to a spectrometer 20, decomposing an optical signal into a spectrum signal by the spectrometer 20, and outputting the spectrum signal to a PC (personal computer); (D3) preprocessing the spectrum signal according to the steps B and C; (D4) respectively taking the spectral data and the concentration of the organophosphorus standard substance after treatment as the input and the output of the cuckoo algorithm optimized neural network in the step D1, training the cuckoo algorithm optimized neural network until the network is converged, and calculating to obtain network parameters; (D5) and completing construction of a prediction model for the content of the organophosphorus pesticide residues in the water body based on the cuckoo algorithm optimized artificial neural network according to the calculated network parameters, storing the prediction model into a spectral information processing module 30 in an embedded system platform, compiling a network parameter file which is trained on a PC and is based on the cuckoo algorithm optimized neural network (CS-BP) to generate executable codes which are operated on the S3C6410 after an embedded Linux operating system is transplanted in an S3C6410 processor during actual use, and then downloading the executable codes to the embedded system platform for operation, thereby completing construction of the prediction model for the content of the organophosphorus pesticide residues in the water body based on the cuckoo algorithm optimized artificial neural network on the device.
In order to reduce the error of the spectrum signal, in the present invention, preferably, the step D2 includes the following steps: (D21) selecting organophosphorus standard substances with the concentrations of 0mg/L, 0.25mg/L, 0.5mg/L, 0.75mg/L, 1.0mg/L, 5.0mg/L, 7.5mg/L and 10.0mg/L for each organophosphorus standard substance; (D22) performing step D23 for each organophosphorus standard at each concentration; (D23) measuring the organophosphorus standard substance with the same concentration for multiple times to obtain a plurality of spectrum signals, randomly selecting M strips to be added, averaging the M strips into one strip, and randomly extracting N times to obtain N spectrum signals; (D24) and outputting all the obtained spectrum signals to a PC for processing. More preferably, in step D23, M is 10 and N is 50. In the step B, baseline background subtraction is carried out by adopting a self-adaptive punishment least square method, so that the operation is more convenient.
Claims (1)
1. A method for detecting organophosphorus pesticide residues in a water body is characterized by comprising the following steps:
the method adopts an embedded device for detecting organophosphorus pesticide residues in the water body, and the device comprises an immersion type optical fiber probe detection module (10), a spectrometer (20) and a spectrum information processing module (30);
the immersion type optical fiber probe detection module (10) comprises a light source (11), a collimating mirror (12), a Y-shaped optical fiber (13) and an optical fiber probe (14), light rays emitted by the light source (11) are output to the input end of the Y-shaped optical fiber (13) after being collimated by the collimating mirror (12), light rays entering from the input end of the Y-shaped optical fiber (13) are output to the optical fiber probe (14) from the common end of the Y-shaped optical fiber (13), the optical fiber probe (14) is immersed in a water body to be detected, and light rays reflected back from the optical fiber probe (14) are input from the common end of the Y-shaped optical fiber (13) and output to a spectrometer (20) from the output end of the Y-shaped optical fiber (13);
the optical fiber probe (14) comprises a cylindrical shell (141) and a filter mirror (142), a plano-convex mirror (143) and a plane mirror (144) which are sequentially arranged in the shell (141), one end of the shell (141) close to the filter mirror (142) is connected with the common end of the Y-shaped optical fiber (13), the outlines of the filter mirror (142), the plano-convex mirror (143) and the plane mirror (144) are circular, and the axial cores of the three lenses are superposed with the axial core of the shell (141); a measuring pool (145) is formed in the area between the planoconvex mirror (143) and the plane mirror (144), and through holes (146) are formed in the peripheral wall of the outer shell of the measuring pool (145) for the water body to be measured to flow into the measuring pool (145);
an inner screw head (147) is arranged on one side, away from the Y-shaped optical fiber (13), of a shell (141) of the optical fiber probe (14), a plane mirror (144) is fixedly installed on the inner screw head (147), a threaded section matched with the inner screw head (147) is arranged on the inner side of the shell (141) between a flat convex mirror (143) and the end part, away from one side of the Y-shaped optical fiber (13), of the shell, and a through hole (146) of a measuring cell (145) is arranged on the threaded section;
the detection method comprises the following steps:
(A) the immersion type optical fiber probe detection module (10) collects transmitted light and backscattered light of a water body to be detected and outputs the transmitted light and the backscattered light to the spectrometer (20), and the spectrometer (20) decomposes an optical signal into a spectrum signal and outputs the spectrum signal to the spectrum information processing module (30);
(B) deducting a baseline background by adopting a self-adaptive punishment least square method;
(C) selecting a full-range spectrum or a spectrum at a characteristic peak position to sequentially perform first derivative absolute value, multivariate scattering correction and standard normal transformation processing;
(D) substituting the preprocessed spectral data into a cuckoo algorithm optimization neural network model stored in a spectral information processing module (30) to calculate and output the concentration of the organophosphorus pesticide in the water body to be detected;
in the step (D), the cuckoo algorithm optimization neural network model stored in the spectral information processing module (30) is constructed according to the following steps: (D1) establishing a water body organophosphorus pesticide concentration prediction model based on a cuckoo algorithm optimization neural network on a PC (personal computer);
(D2) the method comprises the following steps of selecting different types of organic phosphorus standard products with different concentrations, collecting transmitted light and backscattered light of the organic phosphorus standard products by an immersion type optical fiber probe detection module (10) and outputting the transmitted light and the backscattered light to a spectrometer (20), and decomposing an optical signal into a spectrum signal by the spectrometer (20) and outputting the spectrum signal to a PC (personal computer); (D3) preprocessing the spectrum signal according to the steps (B) and (C);
(D4) respectively taking the spectral data and the concentration of the organophosphorus standard substance after treatment as the input and the output of the cuckoo algorithm optimization neural network in the step (D1), training the cuckoo algorithm optimization neural network until the network is converged, and calculating to obtain network parameters;
(D5) the construction of a prediction model of the organophosphorus pesticide residue content in the water body based on the cuckoo algorithm optimized neural network is completed according to the calculated network parameters, and the prediction model is stored in a spectral information processing module (30) of the embedded organophosphorus pesticide residue detection device in the water body;
the step (D2) comprises the following steps:
(D21) selecting organophosphorus standard substances with the concentrations of 0mg/L, 0.25mg/L, 0.5mg/L, 0.75mg/L, 1.0mg/L, 5.0mg/L, 7.5mg/L and 10.0mg/L for each organophosphorus standard substance;
(D22) performing step (D23) for each organophosphorus standard at each concentration;
(D23) measuring an organophosphorus standard substance under a certain similar concentration for multiple times to obtain a plurality of spectrum signals, randomly selecting M strips to be added, averaging the M strips into one strip, and randomly extracting N times to obtain N spectrum signals; m is 10, N is 50;
(D24) and outputting all the obtained spectrum signals to a PC for processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811579556.5A CN109507144B (en) | 2018-12-24 | 2018-12-24 | Embedded water organic phosphorus pesticide residue detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811579556.5A CN109507144B (en) | 2018-12-24 | 2018-12-24 | Embedded water organic phosphorus pesticide residue detection device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109507144A CN109507144A (en) | 2019-03-22 |
| CN109507144B true CN109507144B (en) | 2021-11-26 |
Family
ID=65754280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811579556.5A Active CN109507144B (en) | 2018-12-24 | 2018-12-24 | Embedded water organic phosphorus pesticide residue detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109507144B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114414520B (en) * | 2021-12-28 | 2023-10-24 | 中国科学院南京土壤研究所 | Water phosphorus in-situ monitoring sensor and monitoring method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203287313U (en) * | 2013-05-29 | 2013-11-13 | 江西农业大学 | Rapid pesticide residue detection device |
| CN104483287A (en) * | 2014-12-05 | 2015-04-01 | 南京工业大学 | Detection device and detection method based on near infrared spectrum for biological parameters in on-line fermentation process |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103323418A (en) * | 2013-06-04 | 2013-09-25 | 上海物联网有限公司 | Chemical oxygen demand online monitoring sensor and method |
| CN104880429A (en) * | 2015-04-23 | 2015-09-02 | 能讯传感技术（上海）有限公司 | Online simultaneous monitoring sensor and online simultaneous monitoring method for COD (Chemical Oxygen Demand) and nitrogen content of nitrate |
| CN107576635B (en) * | 2017-08-30 | 2024-04-12 | 南京航空航天大学 | Transparent liquid concentration measuring method and system based on reflection type optical fiber system |
| CN208255048U (en) * | 2018-05-29 | 2018-12-18 | 内蒙古民族大学 | Fibre-optical probe and water quality detecting device |
-
2018
- 2018-12-24 CN CN201811579556.5A patent/CN109507144B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203287313U (en) * | 2013-05-29 | 2013-11-13 | 江西农业大学 | Rapid pesticide residue detection device |
| CN104483287A (en) * | 2014-12-05 | 2015-04-01 | 南京工业大学 | Detection device and detection method based on near infrared spectrum for biological parameters in on-line fermentation process |
Non-Patent Citations (3)
| Title |
|---|
| Artificial Neural Network-Cuckoo Optimization Algorithm (ANN-COA) for Optimal Control of Khorramabad Wastewater Treatment Plant, Iran;Samaneh Khademikia et al.;《Civil Engineering Journal》;20161130;第2卷(第11期);557 * |
| Feasibility research on rapid detection of dimethoate in water by near-infrared spectroscopy;Yilong Su et al.;《Anal. Methods》;20120430;第4卷(第6期);1742-1743 * |
| 基于近红外光谱的番茄农药残留无损检测方法研究;吴泽鑫 等;《湖北农业科学》;20100430;第49卷(第4期);961 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109507144A (en) | 2019-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ravikanth et al. | Extraction of spectral information from hyperspectral data and application of hyperspectral imaging for food and agricultural products | |
| Bruning et al. | The development of hyperspectral distribution maps to predict the content and distribution of nitrogen and water in wheat (Triticum aestivum) | |
| Xue et al. | Application of particle swarm optimization (PSO) algorithm to determine dichlorvos residue on the surface of navel orange with Vis-NIR spectroscopy | |
| Shepherd et al. | Rapid characterization of organic resource quality for soil and livestock management in tropical agroecosystems using near‐infrared spectroscopy | |
| Diago et al. | Development and validation of a new methodology to assess the vineyard water status by on-the-go near infrared spectroscopy | |
| WO2014078862A1 (en) | Blending of agricultural products via hyperspectral imaging and analysis | |
| CN112634212A (en) | Hyperspectral unmanned aerial vehicle-based disease latent tree detection method and system | |
| Bendel et al. | Evaluating the suitability of hyper-and multispectral imaging to detect foliar symptoms of the grapevine trunk disease Esca in vineyards | |
| Xu et al. | Factors influencing near infrared spectroscopy analysis of agro-products: a review | |
| EP3117203B1 (en) | Substance or contamination detection | |
| CN102621118A (en) | Early warning method of greenhouse vegetable diseases and insect pests | |
| CN109374573A (en) | Cucumber epidermis pesticide residue recognition methods based on near-infrared spectrum analysis | |
| Cotrozzi | Spectroscopic detection of forest diseases: A review (1970–2020) | |
| CN108956584B (en) | The quick and precisely detection method of heavy metal element chromium in a kind of mulberry fruit | |
| CN104568824B (en) | Shrimps grade of freshness detection method and device based on Vis/NIR | |
| Tamburini et al. | Development of FT-NIR models for the simultaneous estimation of chlorophyll and nitrogen content in fresh apple (Malus domestica) leaves | |
| CN109507144B (en) | Embedded water organic phosphorus pesticide residue detection device and method | |
| CN108051410A (en) | A kind of tobacco root cadmium content rapid detection method based on laser induced breakdown spectroscopy | |
| CN102841063A (en) | Method for tracing and identifying charcoal based on spectrum technology | |
| Li et al. | Optical techniques in non-destructive detection of wheat quality: A review | |
| da Silva et al. | Near infrared spectroscopy to rapid assess the rubber tree clone and the influence of maturation and disease at the leaves | |
| Ning et al. | Study on apple damage detecting method based on relaxation single-wavelength laser and convolutional neural network | |
| Chen et al. | The spectral fusion of laser-induced breakdown spectroscopy (LIBS) and mid-infrared spectroscopy (MIR) coupled with random forest (RF) for the quantitative analysis of soil pH | |
| Qi et al. | Rapid and non-destructive determination of soluble solid content of crown pear by visible/near-infrared spectroscopy with deep learning regression | |
| CN115963066B (en) | Land-based fishpond culture water quality spectrum detection method and device and computer equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |