CN112326619A - Micro-fluidic pesticide residue detection method based on double-spectrum technology - Google Patents
Micro-fluidic pesticide residue detection method based on double-spectrum technology Download PDFInfo
- Publication number
- CN112326619A CN112326619A CN202011258098.2A CN202011258098A CN112326619A CN 112326619 A CN112326619 A CN 112326619A CN 202011258098 A CN202011258098 A CN 202011258098A CN 112326619 A CN112326619 A CN 112326619A
- Authority
- CN
- China
- Prior art keywords
- microfluidic
- module
- spectrum
- pesticide residue
- raman
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 239000000447 pesticide residue Substances 0.000 title claims abstract description 38
- 238000001228 spectrum Methods 0.000 title claims abstract description 25
- 238000005516 engineering process Methods 0.000 title claims abstract description 15
- 238000002189 fluorescence spectrum Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 21
- 230000005540 biological transmission Effects 0.000 claims abstract description 20
- 238000001069 Raman spectroscopy Methods 0.000 claims abstract description 19
- 238000001237 Raman spectrum Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 11
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 abstract description 6
- 238000004445 quantitative analysis Methods 0.000 abstract description 6
- 230000003595 spectral effect Effects 0.000 description 8
- 230000008901 benefit Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000000126 substance Substances 0.000 description 6
- 238000012937 correction Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000001506 fluorescence spectroscopy Methods 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 238000004451 qualitative analysis Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 235000012055 fruits and vegetables Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000004817 gas chromatography Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004811 liquid chromatography Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 235000013311 vegetables Nutrition 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
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
-
- 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
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/65—Raman scattering
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- 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
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
- G01N2021/6417—Spectrofluorimetric devices
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention discloses a micro-fluidic pesticide residue detection method based on a double-spectrum technology, which comprises the following steps: the system comprises a microfluidic Raman spectrum module, a microfluidic fluorescence spectrum module, a data transmission module and a data processing module; the microfluidic Raman spectrum module comprises a Raman spectrometer, a first microfluidic chip and a microfluidic chip clamp; the microfluidic fluorescence spectrum module comprises a fluorescence spectrometer, a microfluidic chip placing table and a second microfluidic chip; the data transmission module transmits the spectrum signal of the spectrum module to the data processing module; the data processing module comprises a PIN array and an upper computer, the PIN array converts received spectrum signals into electric signals and then transmits the electric signals to the upper computer through the data transmission module, and the upper computer accurately obtains the type and content of an object to be detected after preprocessing, band selection, qualitative judgment and quantitative analysis of the obtained signals, so that the reliability of a pesticide residue detection result is improved, and high-precision pesticide residue rapid qualitative and quantitative detection is realized.
Description
Technical Field
The invention belongs to the field of pesticide residue detection, and particularly relates to a micro-fluidic pesticide residue detection method based on a double-spectrum technology.
Background
China is a big agricultural country, agriculture is always the life line of national economy, pesticide residue in agricultural products is more serious with the wide application of pesticides, and meanwhile, with the improvement of living standard of people, people pay more and more attention to the edible safety problem of agricultural products, particularly fruits and vegetables. The pesticide residue on the surfaces of fruits and vegetables can not only harm the physical health of consumers, but also influence the economic benefit.
At present, although there are many mature detection technologies for detecting pesticide residues, such as CN201910577263.1, a vegetable pesticide residue detection method, which uses gas chromatography and liquid chromatography to detect pesticide residues. However, these detection techniques require pretreatment of the sample, have long time for analyzing the sample, are not favorable for on-site and on-line detection, and require professional technical personnel to complete detection of pesticide residues, are not suitable for production practice, and are more suitable for accurate analysis in laboratories. The spectrum detection technology is a novel rapid and nondestructive detection technology, and is rapidly developed in the fields of pesticide residue detection and the like, wherein the Raman spectrum detection technology can realize rapid, simple, repeatable and nondestructive qualitative and quantitative analysis on a substance to be detected, and meanwhile, due to the fact that the Raman spectrum sensitivity is too high, the advantage of stable qualitative and quantitative detection by utilizing the fluorescence spectrum detection technology is compared with a Raman detection result. Meanwhile, a micro-fluidic chip technology is introduced, so that the complex sample pretreatment process required by the conventional pesticide residue detection is simplified, and a stable and low-noise environment is provided for each detection. The micro-fluidic chip technology can integrate basic operation units of sample preparation, reaction, separation, detection and the like in the processes of biological, chemical and medical analysis on a micron-scale chip, and has the advantages of integration, high analysis and detection speed, low energy consumption, low material consumption, small pollution and low cost. In addition, the total amount of the detected substances can be accurately controlled by the micro-fluidic chip technology, and the whole detection system is a closed environment, so that the interference of the external environment can be greatly reduced, the detection precision and the interference of stray signals are improved, and the accuracy and the reliability of pesticide residue detection are further improved.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a micro-fluidic pesticide residue detection method based on a double-spectrum technology, which has the advantages that the method can accurately and effectively carry out quick qualitative and quantitative detection on pesticide residues
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a micro-fluidic pesticide residue detection method based on a double-spectrum technology, which comprises the following steps: the system comprises a microfluidic Raman spectrum module (1), a microfluidic fluorescence spectrum module (2), a data transmission module (3) and a data processing module (4);
the microfluidic Raman spectrum module (1) comprises a Raman spectrometer (101), a first microfluidic chip (102) and a microfluidic chip clamp (103);
the microfluidic fluorescence spectrum module (2) comprises a fluorescence spectrometer (201), a microfluidic chip placing table (202) and a second microfluidic chip (203);
the data transmission module (3) transmits the spectrum signals of the microfluidic Raman spectrum module (1) and the microfluidic fluorescence spectrum module (2) to the data processing module (4) in a wired, wireless and mobile storage mode such as a serial port, a USB (universal serial bus), a Bluetooth mode, a mobile hard disk and the like;
the data processing module (4) comprises a PIN array (401) and an upper computer (402);
the PIN array (401) converts received spectrum signals of the microfluidic Raman spectrum module (1) and the microfluidic fluorescence spectrum module (2) into electric signals through the data transmission module (3), and then transmits the electric signals into the upper computer (402) through the data transmission module (3);
the upper computer (402) comprehensively analyzes the Raman electric signals and the fluorescence electric signals through a built-in intelligent algorithm, and the algorithm specifically comprises but is not limited to data processing modes of a Raman baseline, denoising, wave band selection, peak searching, fitting, suspicious peak identification, qualitative judgment, parameter evolution optimization, deep learning and the like.
The invention provides a pesticide residue detection method based on double spectra and microfluidics, which comprehensively analyzes and uses Raman spectrum signals and fluorescence spectrum signals of a microfluidic chip through an intelligent algorithm, can improve the detection precision and the reliability of results on the premise of quick qualitative and quantitative determination, and realizes high-precision quick qualitative and quantitative detection of pesticide residues.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a method structure diagram of a pesticide residue detection method based on dual spectrum and microfluidics provided by an embodiment of the invention;
FIG. 2 is a flow chart of a dual-spectrum and micro-fluidic based pesticide residue detection method provided by the invention;
in the drawings:
1-microfluidic raman spectroscopy module; 2-microfluidic fluorescence spectroscopy module; 3-a data transmission module; 4-a data processing module; 101-raman spectrometer; 102-a first microfluidic chip; 103-microfluidic chip clamp; 201-fluorescence spectrometer; 202-microfluidic chip placing table; 203-a second microfluidic chip; 401-PIN array; 402-an upper computer; .
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The invention provides a pesticide residue detection method based on double spectrums and microfluidics, which is shown in figure 1 and comprises the following steps: the system comprises a microfluidic Raman spectrum module 1, a microfluidic fluorescence spectrum module 2, a data transmission module 3 and a data processing module 4;
as shown in fig. 1, a raman spectrometer 101 is arranged on the microfluidic raman spectroscopy module 1, a microfluidic chip clamp 103 is arranged on the left side, and a first microfluidic chip 102 is clamped on the microfluidic chip clamp; the microfluidic chip clamp 103 fixes the first microfluidic chip 102, and the first microfluidic chip 102 is aligned to the detection port of the raman spectrometer 101, and the raman spectrometer 101 transmits the raman spectrum signal obtained from the first microfluidic chip 102 to the data processing module 4 through the data transmission module 3.
As shown in fig. 1, a fluorescence spectrometer 201 is disposed on the microfluidic fluorescence spectrum module 2, a microfluidic chip placing table 202 is disposed on the left side, a second microfluidic chip 203 is disposed on the fluorescence spectrum module, the second microfluidic chip 203 is aligned with a detection port of the fluorescence spectrometer 201, and the fluorescence spectrum spectrometer 201 transmits a fluorescence spectrum signal obtained from the second microfluidic chip 203 to the data processing module 4 through the data transmission module 3.
As shown in fig. 1, a PIN array 401 in a data processing module 4 is on the left of an upper computer 402, the PIN array 401 and the micro-fluidic fluorescence spectrum module 2 are connected through a data transmission module 3, the PIN array 401 receives spectral data from the micro-fluidic raman spectrum module 1 and the micro-fluidic fluorescence spectrum module 2 through the data transmission module 3 and converts the spectral data into corresponding spectral electrical signals, the upper computer 402 receives the spectral electrical signals from the PIN array 401 through the data transmission module 3, and then the upper computer 402 processes the obtained fluorescence data and raman data through an intelligent algorithm to establish a qualitative and quantitative detection model of the spectral signals and concentration information of a substance to be detected. After the upper computer 402 processes the spectrum signals, the upper computer 402 displays the obtained pesticide residue types and concentrations.
The general idea of the intelligent algorithm is as follows, the upper computer 402 can obtain fluorescence data and Raman dataAnd combining a deep learning algorithm, and accurately obtaining the variety and the content of the object to be detected after four steps of preprocessing, band selection, qualitative judgment and quantitative analysis. And in the preprocessing stage, a Raman-CNN convolutional neural network is constructed to realize denoising and baseline correction. In the wave band selection stage, an improved genetic algorithm is used, self-adaptive training is carried out to obtain wave band data with most useful information and least useless information, the overlapping degree of peaks is judged according to four parameters of peak height, center position of the peaks, half width of the peaks and Lorentz coefficient, and if the overlapping degree of the peaks is lower than the overlapping degree of the peaks, the overlapping degree of the peaks is judged according to the four parameters
The characteristic peak is valid. In the qualitative and quantitative analysis stage, the obtained characteristic peak data is utilized, and a qualitative and quantitative detection model of the spectral signal and the concentration information of the substance to be detected is established by combining a deep learning network, so that the type and the content of the pesticide residue are accurately detected.
In the preprocessing stage, the characteristic that convolution can not only realize denoising of the Raman spectrum, but also perform baseline correction is utilized, a convolution neural network Raman-CNN combining convolution (denoising and baseline correction) and a prediction target is constructed, and parameters of a convolution kernel can be learned in a self-adaptive mode. The constructed convolutional neural network is divided into three parts of convolutional denoising, convolutional baseline correction and full-link correction, and the convolutional layer and the full-link layer are jointly modeled. Meanwhile, in order to reduce the loss of the self characteristics of the spectrum in the preprocessing process, the pooling layer is deleted and the convolution layer is simplified. For the C1 layer, the weight is initialized randomly, and for the C2 layer, the weight is initialized by adopting a genetic algorithm, and the local optimal solution of the coefficient is found more quickly.
In the wave band selection stage, in order to reduce interference, reduce operation speed and improve prediction accuracy, the preprocessed signals are subjected to wave band selection based on an improved genetic algorithm. The method comprises the following specific steps: (1) adopting binary coding and utilizing subspace division method, setting wave band to be divided into D subspaces, and the wave band number of each subspace is DjAnd if the coding length is k, the front m bits represent the number of the regions of the band, and the rear n bits represent the position of the band in the region. (2) The derived decoding formula:
wherein,
and k is m + n. (3) Calculating the joint entropy and the Papanicolaou distance, constructing a fitness equation (4), and naturally selecting the population by adopting a roulette method to obtain an individual with the maximum fitness, namely the required wave band combination. Through the four steps, spectrum wave bands which are subjected to preprocessing, interference is eliminated as much as possible, useful information is reserved, and Voigt peak fitting is carried out on spectrum data. The Voigt peak function is defined by convolution of a Lorentz function and a Gaussian function, the calculation process is time-consuming, in order to reduce the dimension of the optimization problem, an improved spectral modeling algorithm is provided by judging the overlapped peaks, the operation time is shortened, and the model precision is improved. Each Voigt function has four free parameters, which are respectively the peak height, the center position of the peak, the half width of the peak and the Lorentz coefficient. Judging the overlapping degree of the peaks by four parameters, if the overlapping degree of the peaks is lower than that of the peaks
If the peak is a useful characteristic peak, otherwise, a useless overlapped peak is removed, and the data of the first eight characteristic peaks are taken to enter a qualitative discrimination and quantitative analysis stage.
In the qualitative judgment stage, an SVM (support vector machine) support vector machine model is established by utilizing the wave numbers of the eight characteristic peaks and the four free coefficients, wherein the dimensionality of the data is 8 multiplied by 4, and the object to be detected is qualitatively judged. The specific steps are as follows (1), the obtained characteristic peak data is X ═ X1,x2,...,xn) The category label Y ═ Y1,y2,...,yn). (2) And selecting a proper kernel function K and a penalty parameter C based on the prior knowledge. (3) Constructing and solving an optimization problem:
get the optimal solution
(4) Selection of alpha*A positive component of
And calculates therefrom a threshold value:
(5) constructing a decision function:
the hyperplane is divided as follows: w is aTx + b is 0, where w determines the direction of the hyperplane and b determines the distance between the hyperplane and the origin. (6) And (5) training the hyperplane by using the training set, recording the classification accuracy, returning to the step (2), and traversing to obtain the parameter combination with the highest classification accuracy. (7) And carrying out qualitative analysis on the object to be detected by using the divided hyperplane.
In the quantitative analysis stage, a deep neural network is constructed for prediction, and the specific steps are as follows: (1) initializing the topological layer structure of the BP neural network and setting a correlation coefficient. According to the dimensionality of the training set, the number of input nodes of the network is determined to be n-8, the number of hidden nodes is determined to be l-8, the number of output nodes is determined to be m-1, the initial learning rate is set to be 0.035, a hidden layer threshold value a and an output layer threshold value b are initialized, and connection weights among neurons of the input layer, the hidden layer and the output layer are determined. (2) Selecting a sigmoid function as an excitation function, calculating an output layer, evaluating the output of the output layer by using a Softmax loss function, calculating an error, updating a weight value by using a reverse error propagation algorithm, and self-learning 50000 times. (3) And after the network training is finished, storing the trained network structure. (4) And predicting and outputting by using the trained network structure.
Based on the four parts, a qualitative and quantitative detection model of the spectral signal and the concentration information of the substance to be detected is established, so that the pesticide residue and the pesticide residue variety are accurately detected.
The previous description of the disclosure is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A micro-fluidic pesticide residue detection method based on a double-spectrum technology is characterized by comprising the following steps: the method comprises the following steps: the system comprises a microfluidic Raman spectrum module (1), a microfluidic fluorescence spectrum module (2), a data transmission module (3) and a data processing module (4);
the microfluidic Raman spectrum module (1) comprises a Raman spectrometer (101), a first microfluidic chip (102) and a microfluidic chip clamp (103);
the microfluidic fluorescence spectrum module (2) comprises a fluorescence spectrometer (201), a microfluidic chip placing table (202) and a second microfluidic chip (203);
the data transmission module (3) transmits the spectrum signals of the microfluidic Raman spectrum module (1) and the microfluidic fluorescence spectrum module (2) to the data processing module (4) in a wired, wireless and mobile storage mode such as a serial port, a USB (universal serial bus), a Bluetooth mode, a mobile hard disk and the like;
the data processing module (4) comprises a PIN array (401) and an upper computer (402); the PIN array (401) converts received spectrum signals of the microfluidic Raman spectrum module (1) and the microfluidic fluorescence spectrum module (2) into electric signals through the data transmission module (3), and then transmits the electric signals into the upper computer (402) through the data transmission module (3); the upper computer (402) comprehensively analyzes the Raman electric signals and the fluorescence electric signals through a built-in intelligent algorithm, and the algorithm specifically comprises but is not limited to data processing modes of a Raman baseline, denoising, wave band selection, peak searching, fitting, suspicious peak identification, qualitative judgment, parameter evolution optimization, deep learning and the like.
2. The microfluidic pesticide residue detection method according to claim 1, wherein the raman spectrometer (101) is a general-type raman spectrometer, and the microfluidic chip holder (103) is an object capable of fixing the first microfluidic chip (102) and aligning the first microfluidic chip with a detection port of the raman spectrometer (101).
3. The microfluidic pesticide residue detection method according to claim 1, wherein the fluorescence spectrometer (201) is a fluorescence spectrometer of a general type, and the microfluidic chip placement stage (202) is an object capable of fixing the second microfluidic chip (203) and aligning the second microfluidic chip with a detection port of the fluorescence spectrometer (201).
4. The microfluidic pesticide residue detection method according to claim 1, wherein the data transmission module (3) has a function of transmitting the spectrum signals of the microfluidic Raman spectrum module (1) and the microfluidic fluorescence spectrum module (2) to the data processing module (4), and the specific transmission method includes but is not limited to wired, wireless and mobile storage modes such as serial ports, USB, Bluetooth and mobile hard disks.
5. The microfluidic pesticide residue detection method according to claim 1, characterized in that the data processing module (4) comprises a PIN array (401), wherein the PIN array (401) functions to convert the corresponding optical signal into an electrical signal.
6. The microfluidic pesticide residue detection method according to claim 1, wherein the data processing module (4) comprises an upper computer (402), and the upper computer (402) comprehensively analyzes the Raman spectrum signal and the fluorescence spectrum signal through a built-in intelligent algorithm, so that the reliability of a pesticide residue detection result is improved, and high-precision pesticide residue rapid qualitative and quantitative detection is realized. The specific aspects of the algorithm include but are not limited to baseline pulling, denoising, band selection, peak searching, fitting, suspicious peak identification, qualitative discrimination, parameter evolution optimization, deep learning and other data processing modes. The upper computer (402) comprises a high-performance singlechip, a notebook computer, a desktop computer and other data processing equipment.
7. The microfluidic pesticide residue detection method according to claim 1, wherein after the spectrum signal is processed by the upper computer (402), the obtained pesticide residue type and concentration are displayed on the upper computer (402).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011258098.2A CN112326619A (en) | 2020-11-12 | 2020-11-12 | Micro-fluidic pesticide residue detection method based on double-spectrum technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011258098.2A CN112326619A (en) | 2020-11-12 | 2020-11-12 | Micro-fluidic pesticide residue detection method based on double-spectrum technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112326619A true CN112326619A (en) | 2021-02-05 |
Family
ID=74317932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011258098.2A Pending CN112326619A (en) | 2020-11-12 | 2020-11-12 | Micro-fluidic pesticide residue detection method based on double-spectrum technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112326619A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113624741A (en) * | 2021-08-17 | 2021-11-09 | 江苏大学 | Method and system for rapidly detecting benzimidazole pesticide residues in citrus based on Surface Enhanced Raman Spectroscopy (SERS) technology |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6197503B1 (en) * | 1997-11-26 | 2001-03-06 | Ut-Battelle, Llc | Integrated circuit biochip microsystem containing lens |
| CN205301175U (en) * | 2016-01-15 | 2016-06-08 | 公安部第一研究所 | Device with laser induced flourescense light path of optic fibre beam splitting |
| CN206262571U (en) * | 2016-12-02 | 2017-06-20 | 中国计量大学 | The micro fluidic device of magnetic metal oxide/noble metal composite nanometer particle enrichment |
| CN109493287A (en) * | 2018-10-10 | 2019-03-19 | 浙江大学 | A kind of quantitative spectra data analysis processing method based on deep learning |
| WO2020186026A1 (en) * | 2019-03-12 | 2020-09-17 | The Trustees Of Columbia University In The City Of New York | Stimulated raman coupled fluorescence spectroscopy and microscopy system and method |
-
2020
- 2020-11-12 CN CN202011258098.2A patent/CN112326619A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6197503B1 (en) * | 1997-11-26 | 2001-03-06 | Ut-Battelle, Llc | Integrated circuit biochip microsystem containing lens |
| CN205301175U (en) * | 2016-01-15 | 2016-06-08 | 公安部第一研究所 | Device with laser induced flourescense light path of optic fibre beam splitting |
| CN206262571U (en) * | 2016-12-02 | 2017-06-20 | 中国计量大学 | The micro fluidic device of magnetic metal oxide/noble metal composite nanometer particle enrichment |
| CN109493287A (en) * | 2018-10-10 | 2019-03-19 | 浙江大学 | A kind of quantitative spectra data analysis processing method based on deep learning |
| WO2020186026A1 (en) * | 2019-03-12 | 2020-09-17 | The Trustees Of Columbia University In The City Of New York | Stimulated raman coupled fluorescence spectroscopy and microscopy system and method |
Non-Patent Citations (4)
| Title |
|---|
| 吴海云;刘洋;左月明;: "近红外光谱数据分析方法的研究进展", 农产品加工(学刊), no. 03 * |
| 张恬: "表面增强拉曼和荧光用于微流控芯片中荧光素检测的研究", 中国优秀硕士学位论文全文数据库 信息科技辑, pages 15 - 42 * |
| 董家林: "基于深度学习的血液制品拉曼光谱分析方法研究及应用", 中国优秀硕士学位论文全文数据库 基础科学辑, vol. 2, pages 2 - 69 * |
| 赵勇;荣康;谈爱玲;: "基于一维卷积神经网络的雌激素粉末拉曼光谱定性分类", 光谱学与光谱分析, no. 12 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113624741A (en) * | 2021-08-17 | 2021-11-09 | 江苏大学 | Method and system for rapidly detecting benzimidazole pesticide residues in citrus based on Surface Enhanced Raman Spectroscopy (SERS) technology |
| CN113624741B (en) * | 2021-08-17 | 2022-11-18 | 江苏大学 | Method and system for rapidly detecting benzimidazole pesticide residues in citrus based on Surface Enhanced Raman Spectroscopy (SERS) technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110411957B (en) | Nondestructive rapid prediction method and device for shelf life and freshness of fruits | |
| CN103235095B (en) | Water-injected meat detection method and device | |
| CN109001180B (en) | Raman spectrum combined artificial intelligence high-throughput single cell analysis and identification method | |
| CN109540836A (en) | Near infrared spectrum pol detection method and system based on BP artificial neural network | |
| CN102982339A (en) | Hyperspectral characteristic variable selection method | |
| CN110378374A (en) | A kind of tealeaves near infrared light profile classification method that fuzzy authentication information extracts | |
| CN105548066A (en) | Method and system for distinguishing colloid types | |
| Bian et al. | Multiple kinds of pesticides detection based on back-propagation neural network analysis of fluorescence spectra | |
| CN111289489A (en) | Raman spectrum-based microbial unicell growth detection method | |
| Li et al. | Quantitative analysis of aflatoxin B1 of peanut by optimized support vector machine models based on near-infrared spectral features | |
| CN103278467A (en) | Rapid nondestructive high-accuracy method with for identifying abundance degree of nitrogen element in plant leaf | |
| Xu et al. | Nondestructive detection of total soluble solids in grapes using VMD‐RC and hyperspectral imaging | |
| Li et al. | Rapid detection of thiabendazole in food using SERS coupled with flower-like AgNPs and PSL-based variable selection algorithms | |
| CN112326619A (en) | Micro-fluidic pesticide residue detection method based on double-spectrum technology | |
| Ndung'u et al. | Optimization of diffuse reflectance spectroscopy measurements for direct and rapid screening of pesticides: A case study of spinach | |
| Yang et al. | A quality detection method of corn based on spectral technology and deep learning model | |
| Wang et al. | SVM classification method of waxy corn seeds with different vitality levels based on hyperspectral imaging | |
| CN113496218A (en) | Evaluation method and system for hyperspectral remote sensing sensitive band selection mode | |
| CN113408616A (en) | Spectrum classification method based on PCA-UVE-ELM | |
| CN105911000A (en) | Characteristic wave band based blood spot egg on-line detection method | |
| CN102854151A (en) | Chemometrics method for classifying sample sets in spectrum analysis | |
| CN110887798B (en) | Nonlinear full-spectrum water turbidity quantitative analysis method based on extreme random tree | |
| CN117169166A (en) | TOC rapid detection algorithm combining spectral technology and deep learning technology | |
| CN115931773A (en) | Wavelength selection method in near infrared spectrum quantitative analysis | |
| Li et al. | Non-destructive detection of specific enzyme activities in tomato plants using visible-near infrared spectroscopy |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210205 |
|
| WD01 | Invention patent application deemed withdrawn after publication |