Rapid detection system and method for pesticide residues based on fluorescence immunochromatography

By combining fluorescent immunochromatography and the LSTM model, the problems of slow detection speed and difficult concentration detection of traditional pesticide residue detection were solved, and fast and accurate pesticide residue detection was achieved to ensure food safety.

CN119985957BActive Publication Date: 2025-09-23SUZHOU HUIYUAN ANSHI TESTING TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411995187.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-12-31
Publication Date
2025-09-23
Estimated Expiration
2044-12-31

Smart Images

  • Figure CN119985957B_ABST
    Figure CN119985957B_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of pesticide residue detection, and discloses a rapid pesticide residue detection system and method based on fluorescence immunochromatography. The system and method comprise the following steps: collecting p_v samples to be detected, performing deep extraction on the samples to be detected, and obtaining p_v portions of sample extracts to be detected; extracting p_f portions of the sample extracts to be detected and recording them as sample test solutions to be detected, performing a primary pesticide residue detection on the sample test solutions to be detected, obtaining environmental data within a time period of the primary pesticide residue detection, and judging whether to perform a secondary pesticide residue detection according to the environmental data; obtaining the pesticide concentration in the sample test solutions to be detected according to the result of the primary pesticide residue detection and the judgment result; extracting the remaining sample extracts to be detected and recording them as sample prediction solutions to be detected, and obtaining the pesticide concentration in the sample prediction solutions to be detected according to the pesticide concentration in the sample test solutions to be detected; and rapidly and accurately performing pesticide residue detection on the samples to be detected.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of pesticide residue detection, and more particularly to a system and method for rapid detection of pesticide residues based on fluorescence immunochromatography. Background Art

[0002] Patent application publication number CN112946105A discloses a rapid pesticide residue detection system and method. The system includes a sample collection module, a sample processing module, a sample detection module, a test result acquisition module, a test result recognition module, a central processing and control module, a data transmission module, a network server module, a voice broadcast module, and a human-computer interaction module. The system utilizes the sample collection and processing modules to quantitatively collect and process samples, reducing the burden of harvesting and processing on staff. Furthermore, the network server module integrates the detection and network terminals, shortening the release time of test data and improving the timeliness and effectiveness of the data. This system generates vegetable safety big data, enabling large-scale transformation of research results, thereby ensuring the quality and safety of food products, enhancing the domestic and international competitiveness of food products, and promoting sustainable development.

[0003] However, in the process of detecting pesticide residues, traditional pesticide residue detection is slow and cannot detect the concentration of pesticides, which poses a threat to food safety. External environmental factors will also affect the results of pesticide residue detection. For a large number of samples to be tested, if they are tested one by one, it will take a lot of time and cause unnecessary waste of manpower and material resources.

[0004] In view of this, the present invention proposes a rapid detection system and method for pesticide residues based on fluorescence immunochromatography to solve the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a rapid detection method for pesticide residues based on fluorescent immunochromatography, comprising:

[0006] Step S1: Collect p_v samples to be tested, perform deep extraction on the samples to be tested, and obtain p_v extracts of the samples to be tested;

[0007] Step S2: extracting p_f portions of the sample extract to be tested and recording them as the sample test solution to be tested, performing a primary test for pesticide residues on the sample test solution to be tested, and obtaining environmental data within the time period of the primary test for pesticide residues, and determining whether to perform a secondary test for pesticide residues based on the environmental data;

[0008] Step S3: Obtaining the pesticide concentration in the test solution of the sample to be tested based on the result of the first pesticide residue test and the judgment result;

[0009] Step S4: extract the remaining sample extract to be tested and record it as the predicted sample extract to be tested, and obtain the pesticide concentration in the predicted sample extract according to the pesticide concentration in the test sample extract to be tested.

[0010] Furthermore, the method of performing deep extraction on the sample to be tested to obtain p_v portions of sample extract to be tested includes:

[0011] chopping and grinding p_v parts of the sample to be tested, adding a solvent to the ground sample to be tested to obtain p_v parts of a preliminary extract;

[0012] Stir and filter p_v parts of the preliminary extract to obtain p_v parts of the sample extract to be tested.

[0013] Furthermore, the method for performing a single detection of pesticide residues on a sample test solution to be tested includes:

[0014] Use a pipette to draw d (uL) of the sample test solution to be tested, where d is the volume of the sample test solution to be tested drawn by the pipette, and uL is the volume unit in microliters, and add d (uL) of the sample test solution to be tested to the sample area of ​​the fluorescent immunochromatographic reagent test card;

[0015] The fluorescent immunochromatographic reagent detection card comprises a sample area, a binding area, a fluorescent area and a detection area, wherein the binding area is provided with a binding antibody, the fluorescent area is provided with a fluorescent marker, and the detection area is provided with a capture antibody;

[0016] The test liquid of the sample to be tested flows from the sample area to the binding area. If there are pesticide molecules in the test liquid of the sample to be tested, they will bind to the binding antibodies in the binding area to form an antigen-antibody complex. Otherwise, no antigen-antibody complex will be formed.

[0017] The test fluid of the sample to be tested flows from the binding area to the fluorescent area. If there is an antigen-antibody complex in the test fluid of the sample to be tested, it will combine with the fluorescent marker in the fluorescent area to form a fluorescent-antigen-antibody complex. Otherwise, no fluorescent-antigen-antibody complex will be formed.

[0018] The test liquid of the sample to be tested flows from the fluorescence area to the detection area. If there is a fluorescent-antigen-antibody complex in the test liquid of the sample to be tested, it will combine with the capture antibody in the detection area to form a fluorescent signal. Otherwise, no fluorescent signal will be formed.

[0019] Furthermore, the environmental data includes ambient temperature, ambient humidity and concentration of particulate matter in the air;

[0020] The method for determining whether to perform a secondary detection of pesticide residues based on environmental data includes:

[0021] Step D1: Establish a temperature blank coordinate system, divide the time period equally into n time points, fill the n time points into the abscissa of the temperature blank coordinate system in sequence, set the ordinate of the temperature blank coordinate system to the ambient temperature, and fill the ambient temperature at the time point into the temperature blank coordinate system to obtain ambient temperature data sample points, connect the ambient temperature data sample points in sequence with straight lines in chronological order, and obtain an ambient temperature change line graph;

[0022] Determine whether the ambient temperature change is abnormal based on the ambient temperature change line graph. If the ambient temperature change is abnormal, conduct a secondary test for pesticide residues.

[0023] Step D2: Repeat step D1 to obtain a line graph of environmental humidity changes and a line graph of particulate matter concentration changes. Based on the line graphs, determine whether the environmental humidity changes and particulate matter concentration changes are abnormal. If the environmental humidity changes or particulate matter concentration changes are abnormal, perform a secondary test for pesticide residues.

[0024] Step D3: Setting an ambient temperature threshold range, an ambient humidity threshold range, and a particle concentration threshold range. When the ambient temperature within the primary pesticide residue detection period exceeds the ambient temperature threshold range, or the ambient humidity exceeds the ambient humidity threshold range, or the particle concentration is greater than or equal to the particle concentration threshold, a secondary pesticide residue detection is performed.

[0025] Step D4: When the ambient temperature is within the ambient temperature threshold range, the ambient humidity is within the ambient humidity threshold range, the particulate matter concentration is less than the particulate matter concentration threshold, and the changes in ambient temperature, ambient humidity, and particulate matter concentration are all normal, no secondary detection of pesticide residues is performed.

[0026] Furthermore, the method for determining whether the ambient temperature change is abnormal based on the ambient temperature change line graph includes:

[0027] Starting from the second ambient temperature data sample point, the length of the straight line between the ambient temperature data sample point and the previous ambient temperature data sample point is obtained and recorded as the first straight line length, and the first straight line length threshold is set. When the first straight line length is greater than or equal to the first straight line length threshold, the ambient temperature change is abnormal, otherwise, the ambient temperature change is normal.

[0028] Furthermore, the method for obtaining the pesticide concentration in the test solution of the sample to be tested based on the result of the first pesticide residue test and the judgment result includes:

[0029] If a secondary pesticide residue test is not performed, the pesticide concentration in the test solution of the sample to be tested is obtained based on the results of the primary pesticide residue test, specifically including:

[0030] Prepare a pesticide standard stock solution with a pesticide concentration of e (mg / mL), where mg is the mass unit in milligrams and mL is the volume unit in milliliters. Dilute the pesticide standard stock solution into f portions of pesticide standard solutions with different pesticide concentrations. Label the pesticide standard solutions as i, where i = 1, 2, 3, ..., f. Perform a single pesticide residue test on the pesticide standard solutions and obtain the fluorescence signal intensity after the test.

[0031] A two-dimensional rectangular coordinate system is established, and the labels of the pesticide standard solutions are filled in the abscissa of the two-dimensional rectangular coordinate system in order from small to large. The ordinate of the two-dimensional rectangular coordinate system is set to the fluorescence signal intensity, and the fluorescence signal intensity corresponding to the pesticide standard solution with the corresponding label is filled in the two-dimensional rectangular coordinate system, and the fluorescence signal data sample points are obtained, and the fitting parameters are obtained. The fluorescence signal data sample points are fitted according to the fitting parameters to obtain the pesticide concentration-fluorescence signal intensity correlation function: y = a0 + a1x + a2x 2 +……+a m x m ;

[0032] Among them, y is the fluorescence signal intensity, x is the pesticide concentration, a0, a1, a2, ..., a m is the fitting parameter;

[0033] Obtaining the fluorescence signal intensity corresponding to the test solution of the sample to be tested. If the fluorescence signal intensity corresponding to the test solution of the sample to be tested is zero, then there is no pesticide residue in the test solution of the sample to be tested. Otherwise, the fluorescence signal intensity corresponding to the test solution of the sample to be tested is input into the pesticide concentration-fluorescence signal intensity correlation function to obtain the pesticide concentration in the test solution of the sample to be tested;

[0034] If a secondary test for pesticide residues is performed, the pesticide concentration in the test solution of the sample to be tested is obtained based on the result of the secondary test for pesticide residues.

[0035] Furthermore, the method for obtaining fitting parameters includes:

[0036] Find the fitting parameters a0, a1, a2, ..., a m , so that the sum of squared errors S is minimized, specifically including:

[0037] in,

[0038] Among them, y i is the fluorescence signal intensity corresponding to the pesticide standard solution labeled i, x i is the pesticide concentration of the pesticide standard solution labeled i;

[0039] The pesticide concentration-fluorescence signal intensity correlation function was converted into a matrix form: Y = XA;

[0040] Where Y is the column vector of fluorescence signal intensity y, y1 is the fluorescence signal intensity corresponding to the pesticide standard solution labeled 1, y2 is the fluorescence signal intensity corresponding to the pesticide standard solution labeled 2, and y f is the fluorescence signal intensity corresponding to the pesticide standard solution labeled f, X is the design matrix of the pesticide concentration x, x1 is the pesticide concentration of the pesticide standard solution with the label 1, x2 is the pesticide concentration of the pesticide standard solution with the label 2, and x f is the pesticide concentration of the pesticide standard solution labeled f, and A is the column vector of fitting parameters;

[0041] The fitting parameters a0, a1, a2, ..., a are obtained according to the matrix form of the pesticide concentration-fluorescence signal intensity correlation function. m ;

[0042] in, X T is the transpose of the design matrix of pesticide concentration x, (X T X) -1 Represents X T The inverse matrix of X.

[0043] Furthermore, the method for obtaining the pesticide concentration in the predicted solution of the sample to be detected based on the pesticide concentration in the test solution of the sample to be detected includes:

[0044] Obtaining the time interval between the collection time of the sample to be tested and the time of spraying the pesticide, the pesticide dosage, and the rainfall from the time of spraying the pesticide to the collection time corresponding to the test solution of the sample to be tested;

[0045] Construct a pesticide concentration recursive model, including:

[0046] Based on the LSTM basic framework, the input layer, LSTM layer, fully connected layer, and output layer were set. The input of the input layer was set to the time interval, pesticide dosage, and rainfall. The activation function of the fully connected layer was ReLU. The output of the output layer was the pesticide concentration.

[0047] Using the Adam algorithm, the loss function is: F(k) represents the model output pesticide concentration of the kth sample, F'(k) represents the actual pesticide concentration of the kth sample, N is the number of samples, δ is the weight coefficient, and k is the index of the number of samples;

[0048] Training and using pesticide concentration recursive models, including:

[0049] Step B1: Collect p_f samples to form a sample set, and divide it into a training set and a validation set in a ratio of 8:2. Input the training set into batches in sequence into the pesticide concentration recursive model for forward propagation;

[0050] Step B2: Obtain the pesticide concentration output by the pesticide concentration recursive model, calculate the loss value using the loss function, calculate each parameter in the model using the backpropagation algorithm, and update the parameters using the gradient descent algorithm;

[0051] Step B3: Repeat steps B1 and B2 until the loss function value of the pesticide concentration recursive model no longer changes. Then, import the validation set for verification. If the verification is successful, the trained pesticide concentration recursive model is obtained. If the verification is unsuccessful, repeat step B3.

[0052] Step B4: Obtain the time interval between the collection time of the sample to be tested and the pesticide spraying time, the pesticide spraying dosage, and the rainfall from the pesticide spraying time to the collection time corresponding to the predicted liquid of the sample to be tested, and input them into the trained pesticide concentration recursive model to obtain the pesticide concentration in the predicted liquid of the sample to be tested.

[0053] Furthermore, the method of collecting p_f samples to form a sample set includes:

[0054] The time interval between the collection time of the sample to be tested and the pesticide spraying time, the pesticide spraying dosage, the rainfall from the pesticide spraying time to the collection time, and the pesticide concentration of a sample to be tested are taken as a sample, and p_f samples are collected to form a sample set.

[0055] The rapid detection system for pesticide residues based on fluorescence immunochromatography includes:

[0056] Data acquisition module, used to collect p_v samples to be tested;

[0057] The residue detection module is used to perform a deep extraction of the sample to be tested, obtain p_v parts of the sample extract to be tested, extract p_f parts of the sample extract to be tested and record them as the sample test solution to be tested, perform a primary pesticide residue test on the sample test solution to be tested, and obtain environmental data within the time period of the primary pesticide residue test, and determine whether to perform a secondary pesticide residue test based on the environmental data;

[0058] The concentration acquisition module obtains the pesticide concentration in the test solution of the sample to be tested based on the result of the first pesticide residue test and the judgment result, extracts the remaining extract of the sample to be tested and records it as the predicted solution of the sample to be tested, and obtains the pesticide concentration in the predicted solution of the sample to be tested based on the pesticide concentration in the test solution of the sample to be tested.

[0059] The technical effects and advantages of the fluorescent immunochromatography-based rapid detection system and method of pesticide residues of the present invention are as follows:

[0060] Collect p_v samples to be tested, perform deep extraction on the samples to be tested, and obtain p_v extracts of the samples to be tested, so that the pesticide components can be released from the samples more efficiently, the pesticides can be extracted to the maximum extent, undissolved solid particles can be removed, and the interference with pesticide detection can be reduced. Extract p_f extracts of the samples to be tested and record them as the test solutions of the samples to be tested. Perform a pesticide residue test on the test solution of the samples to be tested, and obtain the environmental data within the time period of the pesticide residue test. Determine whether to conduct a secondary test for pesticide residue based on the environmental data. Environmental factors will interfere with the pesticide detection results. When environmental factors interfere with the pesticide detection results, When interference occurs in the results, a secondary test for pesticide residues is performed, which greatly improves the accuracy of the pesticide test results. The pesticide concentration in the test liquid of the sample to be tested is obtained based on the results of the first test of pesticide residues and the judgment result. The pesticide concentration is specifically obtained, which makes the grasp of the pesticide residues in the sample to be tested clearer and ensures food safety. The remaining extract of the sample to be tested is extracted and recorded as the predicted liquid of the sample to be tested. The pesticide concentration in the predicted liquid of the sample to be tested is obtained based on the pesticide concentration in the test liquid of the sample to be tested. The pesticide concentration in the predicted liquid of the sample to be tested does not need to be tested, but is directly predicted, which greatly improves the rate of pesticide residue detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 Schematic diagram of the rapid detection method for pesticide residues based on fluorescence immunochromatography of the present invention;

[0062] Figure 2 Schematic diagram of the rapid detection system for pesticide residues based on fluorescence immunochromatography of the present invention. DETAILED DESCRIPTION

[0063] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0064] Example 1

[0065] See also Figure 1 As shown, the rapid detection method of pesticide residues based on fluorescence immunochromatography described in this embodiment includes:

[0066] Step S1: Collect p_v samples to be tested, perform deep extraction on the samples to be tested, and obtain p_v extracts of the samples to be tested;

[0067] Step S2: extracting p_f portions of the sample extract to be tested and recording them as the sample test solution to be tested, performing a primary test for pesticide residues on the sample test solution to be tested, and obtaining environmental data within the time period of the primary test for pesticide residues, and determining whether to perform a secondary test for pesticide residues based on the environmental data;

[0068] Step S3: Obtaining the pesticide concentration in the test solution of the sample to be tested based on the result of the first pesticide residue test and the judgment result;

[0069] Step S4: extract the remaining sample extract to be tested and record it as the predicted sample extract to be tested, and obtain the pesticide concentration in the predicted sample extract according to the pesticide concentration in the test sample extract to be tested.

[0070] The process of collecting p_v samples to be tested includes:

[0071] Samples to be tested include fruits on fruit trees that have been sprayed with pesticides, farmland that has been sprayed with pesticides, and water sources;

[0072] If the sample to be tested is fruit from fruit trees that have been sprayed with pesticides, then obtain j (mg) peels from p_v pieces of fruit as the sample to be tested, where j is the weight of the peels obtained, and mg is the mass unit in milligrams. If the sample to be tested is farmland that has been sprayed with pesticides, then obtain b (mg) soil from p_v pieces of farmland as the sample to be tested, where b is the weight of the obtained soil. If the sample to be tested is a water source, then obtain c (mL) water from p_v water sources as the sample to be tested, where c is the volume of the obtained water, and mL is the volume unit in milliliters.

[0073] It needs to be explained that the samples collected for testing are distributed in different regions.

[0074] The process of performing deep extraction on the sample to be tested and obtaining p_v portions of the sample extract to be tested includes:

[0075] chopping and grinding p_v parts of the sample to be tested, adding a solvent to the ground sample to obtain p_v parts of a preliminary extract;

[0076] Stirring and filtering p_v parts of the preliminary extract to obtain p_v parts of the sample extract to be tested;

[0077] It needs to be explained that chopping and grinding the sample to be tested can increase the surface area in contact with the solvent, so that the pesticide components can be released from the sample more efficiently. The purpose of stirring is to enable the solvent to evenly penetrate the sample to be tested and maximize the extraction of pesticides. The purpose of filtration is to remove undissolved solid particles and reduce interference with pesticide detection.

[0078] The process of conducting a single pesticide residue test on the sample solution to be tested includes:

[0079] Use a pipette to draw d (uL) of the sample test solution to be tested, where d is the volume of the sample test solution to be tested drawn by the pipette, and uL is the volume unit in microliters, and add d (uL) of the sample test solution to be tested to the sample area of ​​the fluorescent immunochromatographic reagent test card;

[0080] The fluorescent immunochromatographic reagent detection card includes a sample area, a binding area, a fluorescent area, and a detection area. The binding area is provided with a binding antibody, which can bind to the pesticide molecules in the sample test liquid to be detected to form an antigen-antibody complex. The fluorescent area is provided with a fluorescent marker, which can bind to the antigen-antibody complex to form a fluorescent-antigen-antibody complex. The detection area is provided with a capture antibody, which can capture the fluorescent-antigen-antibody complex to form a fluorescent signal.

[0081] The test liquid of the sample to be tested flows from the sample area to the binding area. If there are pesticide molecules in the test liquid of the sample to be tested, they will bind to the binding antibodies in the binding area to form an antigen-antibody complex. If there are no pesticide molecules in the test liquid of the sample to be tested, no antigen-antibody complex will be formed.

[0082] The test solution of the sample to be tested flows from the binding area to the fluorescent area. If there is an antigen-antibody complex in the test solution of the sample to be tested, it combines with the fluorescent marker in the fluorescent area to form a fluorescent-antigen-antibody complex. If there is no antigen-antibody complex in the test solution of the sample to be tested, no fluorescent-antigen-antibody complex is formed.

[0083] The test liquid of the sample to be tested flows from the fluorescence area to the detection area. If there is a fluorescent-antigen-antibody complex in the test liquid of the sample to be tested, it will combine with the capture antibody in the detection area to form a fluorescent signal. If there is no fluorescent-antigen-antibody complex in the test liquid of the sample to be tested, no fluorescent signal will be formed.

[0084] The process of obtaining environmental data within the time period of the first pesticide residue test and determining whether to conduct a second pesticide residue test based on the environmental data includes:

[0085] The environmental data includes ambient temperature, ambient humidity and concentration of particulate matter in the air;

[0086] The ambient temperature is obtained through the temperature sensor, the ambient humidity is obtained through the humidity sensor, and the concentration of particulate matter in the air is obtained through the particulate matter detection equipment;

[0087] Establish a temperature blank coordinate system, divide the time period equally into n time points, fill the n time points into the abscissa of the temperature blank coordinate system in sequence, set the ordinate of the temperature blank coordinate system to the ambient temperature, and fill the ambient temperature at the time point into the temperature blank coordinate system to obtain ambient temperature data sample points, connect the ambient temperature data sample points in sequence with straight lines in chronological order, and obtain an ambient temperature change line graph;

[0088] Set the ambient temperature threshold range. When the ambient temperature during the first pesticide residue detection period exceeds the ambient temperature threshold range, a second pesticide residue detection will be performed.

[0089] Starting from the second ambient temperature data sample point, obtain the straight line length between the ambient temperature data sample point and the ambient temperature data sample point before the ambient temperature data sample point, and record it as the first straight line length, and set the first straight line length threshold. When the first straight line length is greater than or equal to the first straight line length threshold, the ambient temperature change is abnormal and a secondary detection of pesticide residues is performed. Otherwise, the ambient temperature change is normal;

[0090] Establish a humidity blank coordinate system, fill n time points into the horizontal coordinate of the humidity blank coordinate system in sequence, set the vertical coordinate of the humidity blank coordinate system to the ambient humidity, and fill the ambient humidity at the time point into the humidity blank coordinate system to obtain ambient humidity data sample points, connect the ambient humidity data sample points in chronological order with straight lines, and obtain an ambient humidity change line graph;

[0091] Set the environmental humidity threshold range. When the environmental humidity during the first pesticide residue detection period exceeds the environmental humidity threshold range, a second pesticide residue detection will be performed.

[0092] Starting from the second environmental humidity data sample point, obtain the straight line length between the environmental humidity data sample point and the environmental humidity data sample point before the environmental humidity data sample point, and record it as the second straight line length, and set the second straight line length threshold. When the second straight line length is greater than or equal to the second straight line length threshold, the environmental humidity change is abnormal and a secondary detection of pesticide residues is performed. Otherwise, the environmental humidity change is normal.

[0093] Establish a particle concentration blank coordinate system, sequentially fill n time points into the abscissa of the particle concentration blank coordinate system, set the ordinate of the particle concentration blank coordinate system to the particle concentration, and fill the particle concentration at the time point into the particle concentration blank coordinate system to obtain particle concentration data sample points, and sequentially connect the particle concentration data sample points with straight lines in chronological order to obtain a particle concentration change line graph;

[0094] Set a particle concentration threshold. When the particle concentration within the first pesticide residue detection period is greater than or equal to the particle concentration threshold, conduct a second pesticide residue detection.

[0095] Starting from the second particle concentration data sample point, obtain the straight line length between the particle concentration data sample point and the particle concentration data sample point before the particle concentration data sample point, and record it as the third straight line length, and set the third straight line length threshold. When the third straight line length is greater than or equal to the third straight line length threshold, the particle concentration change is abnormal and a secondary pesticide residue test is performed. Otherwise, the particle concentration change is normal;

[0096] When the ambient temperature is within the ambient temperature threshold range, the ambient humidity is within the ambient humidity threshold range, the particulate matter concentration is less than the particulate matter concentration threshold, and the changes in ambient temperature, ambient humidity, and particulate matter concentration are normal, no secondary detection of pesticide residues is performed;

[0097] It should be explained that the process of secondary pesticide residue testing is the same as that of primary pesticide residue testing.

[0098] The process of obtaining the pesticide concentration in the test solution of the sample to be tested based on the results of the first pesticide residue test and the judgment results includes:

[0099] If the secondary pesticide residue test is not performed, the pesticide concentration in the test solution of the sample to be tested is obtained based on the result of the primary pesticide residue test;

[0100] Prepare a pesticide standard stock solution with a pesticide concentration of e (mg / mL), dilute the pesticide standard stock solution into f portions of pesticide standard solutions with different pesticide concentrations, and label the pesticide standard solutions as i, where i = 1, 2, 3, ..., f. Perform a single pesticide residue test on the pesticide standard solutions and obtain the fluorescence signal intensity after the test.

[0101] It should be explained that the smaller the label number of the pesticide standard solution, the lower the pesticide concentration of the pesticide standard solution, and the larger the label number of the pesticide standard solution, the higher the pesticide concentration of the pesticide standard solution;

[0102] A two-dimensional rectangular coordinate system was established, and the numbers of the pesticide standard solutions were filled into the abscissa of the two-dimensional rectangular coordinate system in order from small to large. The ordinate of the two-dimensional rectangular coordinate system was set to the fluorescence signal intensity, and the fluorescence signal intensity corresponding to the pesticide standard solution with the corresponding number was filled into the two-dimensional rectangular coordinate system to obtain the fluorescence signal data sample points. The fluorescence signal data sample points were fitted to obtain the pesticide concentration-fluorescence signal intensity correlation function: y = a0 + a1x + a2x 2 +……+a m x m ;

[0103] Among them, y is the fluorescence signal intensity, x is the pesticide concentration, a0, a1, a2, ..., a m is the fitting parameter to be obtained;

[0104] The process of obtaining fitting parameters includes:

[0105] Find the fitting parameters a0, a1, a2, ..., a m , so that the sum of squared errors S is minimized;

[0106] in,

[0107] Among them, y i is the fluorescence signal intensity corresponding to the pesticide standard solution labeled i, x i is the pesticide concentration of the pesticide standard solution labeled i;

[0108] Find the fitting parameters a0, a1, a2, ..., a m , the process of minimizing the sum of squared errors S includes:

[0109] The pesticide concentration-fluorescence signal intensity correlation function was converted into a matrix form: Y = XA;

[0110] Where Y is the column vector of fluorescence signal intensity y, y1 is the fluorescence signal intensity corresponding to the pesticide standard solution labeled 1, y2 is the fluorescence signal intensity corresponding to the pesticide standard solution labeled 2, and y f is the fluorescence signal intensity corresponding to the pesticide standard solution labeled f, X is the design matrix of the pesticide concentration x, x1 is the pesticide concentration of the pesticide standard solution with the label 1, x2 is the pesticide concentration of the pesticide standard solution with the label 2, and x f is the pesticide concentration of the pesticide standard solution labeled f, A is the column vector of fitting parameters,

[0111] The fitting parameters were obtained based on the matrix form of the pesticide concentration-fluorescence signal intensity correlation function;

[0112] in, X T is the transpose of the design matrix of pesticide concentration x, (X T X) -1 Represents X T The inverse matrix of X;

[0113] Obtaining the fluorescence signal intensity corresponding to the test solution of the sample to be detected; if the fluorescence signal intensity corresponding to the test solution of the sample to be detected is zero, then there is no pesticide residue in the test solution of the sample to be detected; if the fluorescence signal intensity corresponding to the test solution of the sample to be detected is not zero, inputting the fluorescence signal intensity corresponding to the test solution of the sample to be detected into a pesticide concentration-fluorescence signal intensity correlation function to obtain the pesticide concentration in the test solution of the sample to be detected;

[0114] If a secondary test for pesticide residues is performed, the pesticide concentration in the test solution of the sample to be tested is obtained based on the result of the secondary test for pesticide residues;

[0115] It should be explained that the process of obtaining the pesticide concentration in the test solution of the sample to be tested based on the results of the secondary test for pesticide residues is the same as the process of obtaining the pesticide concentration in the test solution of the sample to be tested based on the results of the primary test for pesticide residues.

[0116] The process of obtaining the pesticide concentration in the predicted solution of the sample to be tested based on the pesticide concentration in the test solution of the sample to be tested includes:

[0117] Obtaining the time interval between the collection time of the sample to be tested and the time of spraying the pesticide, the pesticide dosage, and the rainfall from the time of spraying the pesticide to the collection time corresponding to the test solution of the sample to be tested;

[0118] Construct a pesticide concentration recursive model, including:

[0119] Based on the LSTM basic framework, the input layer, LSTM layer, fully connected layer, and output layer were set. The input of the input layer was set to the time interval, pesticide dosage, and rainfall. The activation function of the fully connected layer was ReLU. The output of the output layer was the pesticide concentration.

[0120] Using the Adam algorithm, the loss function is: F(k) represents the model output pesticide concentration of the kth sample, F′(k) represents the actual pesticide concentration of the kth sample, N is the number of samples, δ is the weight coefficient, and k is the index of the number of samples;

[0121] Training and using pesticide concentration recursive models, including:

[0122] Step B1: Collect p_f samples to form a sample set, and divide it into a training set and a validation set in a ratio of 8:2. Input the training set into batches in sequence into the pesticide concentration recursive model for forward propagation;

[0123] Step B2: Obtain the pesticide concentration output by the pesticide concentration recursive model, calculate the loss value using the loss function, calculate each parameter in the model using the backpropagation algorithm, and update the parameters using the gradient descent algorithm;

[0124] Step B3: Repeat steps B1 and B2 until the loss function value of the pesticide concentration recursive model no longer changes. Then, import the validation set for verification. If the verification is successful, the trained pesticide concentration recursive model is obtained. If the verification is unsuccessful, repeat step B3.

[0125] Step B4: Obtain the time interval between the collection time of the sample to be tested and the time of pesticide spraying, the pesticide dosage, and the rainfall from the time of pesticide spraying to the collection time corresponding to the predicted solution of the sample to be tested, and input them into the trained pesticide concentration recursive model to obtain the pesticide concentration in the predicted solution of the sample to be tested;

[0126] The process of collecting p_f samples to form a sample set includes:

[0127] The time interval between the collection time of the sample to be tested and the pesticide spraying time, the pesticide spraying dosage, the rainfall from the pesticide spraying time to the collection time, and the pesticide concentration of a sample to be tested are taken as a sample, and p_f samples are collected to form a sample set.

[0128] In this embodiment, p_v samples to be tested are collected, and deep extraction is performed on the samples to be tested to obtain p_v extracts of the samples to be tested, so that the pesticide components can be released from the samples more efficiently, the pesticide is extracted to the maximum extent, undissolved solid particles are removed, and interference with pesticide detection is reduced. P_f extracts of the samples to be tested are extracted and recorded as test solutions of the samples to be tested. The test solutions of the samples to be tested are tested for pesticide residues once, and environmental data within the time period of the first pesticide residue test is obtained. It is determined whether to perform a second pesticide residue test based on the environmental data. Environmental factors will interfere with the pesticide detection results. When environmental factors interfere with the pesticide residue detection results, When the pesticide detection results are interfered with, a secondary detection of pesticide residues is carried out, which greatly improves the accuracy of the pesticide detection results. The pesticide concentration in the detection liquid of the sample to be detected is obtained according to the result and judgment result of the first detection of pesticide residues. The specific pesticide concentration is obtained, which makes the grasp of the pesticide residues in the sample to be detected clearer and ensures food safety. The remaining sample to be detected extract is extracted and recorded as the predicted sample to be detected liquid. The pesticide concentration in the predicted sample to be detected liquid is obtained according to the pesticide concentration in the detection liquid of the sample to be detected. The pesticide concentration in the predicted sample to be detected liquid does not need to be tested, but is directly predicted, which greatly improves the rate of pesticide residue detection.

[0129] Example 2

[0130] See also Figure 2 As shown, for the parts not described in detail in this embodiment, please refer to the description of Example 1. A rapid detection system for pesticide residues based on fluorescent immunochromatography is provided, comprising:

[0131] Data acquisition module, used to collect p_v samples to be tested;

[0132] The residue detection module is used to perform a deep extraction of the sample to be tested, obtain p_v parts of the sample extract to be tested, extract p_f parts of the sample extract to be tested and record them as the sample test solution to be tested, perform a primary pesticide residue test on the sample test solution to be tested, and obtain environmental data within the time period of the primary pesticide residue test, and determine whether to perform a secondary pesticide residue test based on the environmental data;

[0133] The concentration acquisition module obtains the pesticide concentration in the test solution of the sample to be tested based on the result of the first pesticide residue test and the judgment result, extracts the remaining extract of the sample to be tested and records it as the predicted solution of the sample to be tested, and obtains the pesticide concentration in the predicted solution of the sample to be tested based on the pesticide concentration in the test solution of the sample to be tested.

[0134] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0135] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0136] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

[0137] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A rapid detection method for pesticide residues based on fluorescence immunochromatography, characterized in that: The rapid detection method for pesticide residues based on fluorescence immunochromatography includes: Step S1: Collect p_v samples to be tested, perform deep extraction on the samples to be tested, and obtain p_v extracts of the samples to be tested; Step S2: extracting p_f portions of the sample extract to be tested and recording them as the sample test solution to be tested, performing a primary test for pesticide residues on the sample test solution to be tested, and obtaining environmental data within the time period of the primary test for pesticide residues, and determining whether to perform a secondary test for pesticide residues based on the environmental data; The environmental data includes ambient temperature, ambient humidity, and concentration of particulate matter in the air; the method for determining whether to perform a secondary detection of pesticide residues based on the environmental data includes: Set the ambient temperature threshold range, ambient humidity threshold range, and particulate matter concentration threshold range. When the ambient temperature within the time period of the first pesticide residue detection exceeds the ambient temperature threshold range, the ambient humidity exceeds the ambient humidity threshold range, or the particulate matter concentration is greater than or equal to the particulate matter concentration threshold, a second pesticide residue detection is performed. When the ambient temperature is within the ambient temperature threshold range, the ambient humidity is within the ambient humidity threshold range, the particulate matter concentration is less than the particulate matter concentration threshold, and the changes in ambient temperature, ambient humidity, and particulate matter concentration are normal, no secondary detection of pesticide residues is performed; Step S3: Obtaining the pesticide concentration in the test solution of the sample to be tested based on the result of the first pesticide residue test and the judgment result; which includes: If the secondary pesticide residue test is not performed, the pesticide concentration in the test solution of the sample to be tested is obtained based on the result of the primary pesticide residue test. If the secondary pesticide residue test is performed, the pesticide concentration in the test solution of the sample to be tested is obtained based on the result of the secondary pesticide residue test. Step S4: extracting the remaining sample extract to be tested and recording it as the predicted sample extract to be tested, and obtaining the pesticide concentration in the predicted sample extract based on the pesticide concentration in the test sample extract to be tested; this includes obtaining the time interval between the collection time of the sample to be tested and the pesticide spraying time, the pesticide spraying dosage, and the rainfall from the pesticide spraying time to the collection time corresponding to the test sample extract to be tested; Construct a pesticide concentration recursive model, including: Based on the LSTM basic framework, the input layer, LSTM layer, fully connected layer, and output layer were set. The input of the input layer was set to the time interval, pesticide dosage, and rainfall. The activation function of the fully connected layer was ReLU. The output of the output layer was the pesticide concentration. Using the Adam algorithm, the loss function is: ; Indicates the The model outputs the pesticide concentration of samples, Indicates the The actual pesticide concentration of each sample, is the sample size, is the weight coefficient, is the index of the sample number; Train and use the pesticide concentration recursive model to obtain the pesticide concentration in the predicted solution of the sample to be tested.

2. The method for rapid detection of pesticide residues based on fluorescent immunochromatography according to claim 1, characterized in that: The method for performing deep extraction on the sample to be detected to obtain p_v portions of the sample extract to be detected comprises: chopping and grinding p_v parts of the sample to be tested, adding a solvent to the ground sample to be tested to obtain p_v parts of a preliminary extract; Stir and filter p_v parts of the preliminary extract to obtain p_v parts of the sample extract to be tested.

3. The method for rapid detection of pesticide residues based on fluorescent immunochromatography according to claim 2, characterized in that: The method for performing a single detection of pesticide residues on a sample test solution to be tested comprises: Use a pipette to draw d uL of the sample test solution to be tested, where d is the volume of the sample test solution to be tested drawn by the pipette, and uL is the volume unit in microliters, and add d uL of the sample test solution to be tested to the sample area of ​​the fluorescent immunochromatographic reagent test card; The fluorescent immunochromatographic reagent detection card comprises a sample area, a binding area, a fluorescent area and a detection area, wherein the binding area is provided with a binding antibody, the fluorescent area is provided with a fluorescent marker, and the detection area is provided with a capture antibody; The test liquid of the sample to be tested flows from the sample area to the binding area. If there are pesticide molecules in the test liquid of the sample to be tested, they will bind to the binding antibodies in the binding area to form an antigen-antibody complex. Otherwise, no antigen-antibody complex will be formed. The test fluid of the sample to be tested flows from the binding area to the fluorescent area. If there is an antigen-antibody complex in the test fluid of the sample to be tested, it will combine with the fluorescent marker in the fluorescent area to form a fluorescent-antigen-antibody complex. Otherwise, no fluorescent-antigen-antibody complex will be formed. The test liquid of the sample to be tested flows from the fluorescence area to the detection area. If there is a fluorescent-antigen-antibody complex in the test liquid of the sample to be tested, it will combine with the capture antibody in the detection area to form a fluorescent signal. Otherwise, no fluorescent signal will be formed.

4. The method for rapid detection of pesticide residues based on fluorescent immunochromatography according to claim 3, characterized in that: The method for determining whether to perform a secondary detection of pesticide residues based on environmental data further includes: Step D1: Establish a temperature blank coordinate system and divide the time period into At a point in time, Fill in the horizontal coordinate of the temperature blank coordinate system at each time point in sequence, set the vertical coordinate of the temperature blank coordinate system to the ambient temperature, and fill in the ambient temperature at the time point in the temperature blank coordinate system to obtain the ambient temperature data sample points, and connect the ambient temperature data sample points in sequence with straight lines in chronological order to obtain the ambient temperature change line graph; Determine whether the ambient temperature change is abnormal based on the ambient temperature change line graph. If the ambient temperature change is abnormal, conduct a secondary test for pesticide residues. Step D2: Repeat step D1 to obtain a line graph of the ambient humidity change and a line graph of the particulate matter concentration change. Based on the line graphs of the ambient humidity change and the particulate matter concentration change, determine whether the ambient humidity change and the particulate matter concentration change are abnormal. If the ambient humidity change or the particulate matter concentration change is abnormal, perform a secondary test for pesticide residues.

5. The method for rapid detection of pesticide residues based on fluorescent immunochromatography according to claim 4, characterized in that: The method for determining whether the ambient temperature change is abnormal based on the ambient temperature change line graph includes: Starting from the second ambient temperature data sample point, the length of the straight line between the ambient temperature data sample point and the previous ambient temperature data sample point is obtained and recorded as the first straight line length, and the first straight line length threshold is set. When the first straight line length is greater than or equal to the first straight line length threshold, the ambient temperature change is abnormal, otherwise, the ambient temperature change is normal.

6. The method for rapid detection of pesticide residues based on fluorescent immunochromatography according to claim 5, characterized in that: If the secondary pesticide residue test is not performed, the pesticide concentration in the test solution of the sample to be tested is obtained based on the result of the primary pesticide residue test, specifically including: Prepare a pesticide standard stock solution with a pesticide concentration of e mg / mL, where mg is the mass unit in milligrams and mL is the volume unit in milliliters. Dilute the pesticide standard stock solution to Prepare pesticide standard solutions with different pesticide concentrations and label the pesticide standard solutions as , , perform a pesticide residue test on the pesticide standard solution once, and obtain the fluorescence signal intensity after the test; A two-dimensional rectangular coordinate system is established, and the labels of the pesticide standard solutions are filled in the abscissa of the two-dimensional rectangular coordinate system in order from small to large. The ordinate of the two-dimensional rectangular coordinate system is set to the fluorescence signal intensity, and the fluorescence signal intensity corresponding to the pesticide standard solution with the corresponding label is filled in the two-dimensional rectangular coordinate system. The fluorescence signal data sample points are obtained, and the fitting parameters are obtained. The fluorescence signal data sample points are fitted according to the fitting parameters to obtain the pesticide concentration-fluorescence signal intensity correlation function: ; in, is the fluorescence signal intensity, is the pesticide concentration, is the fitting parameter; The fluorescence signal intensity corresponding to the test solution of the sample to be tested is obtained. If the fluorescence signal intensity corresponding to the test solution of the sample to be tested is zero, there is no pesticide residue in the test solution of the sample to be tested. Otherwise, the fluorescence signal intensity corresponding to the test solution of the sample to be tested is input into the pesticide concentration-fluorescence signal intensity correlation function to obtain the pesticide concentration in the test solution of the sample to be tested.

7. The method for rapid detection of pesticide residues based on fluorescent immunochromatography according to claim 6, characterized in that: The method for obtaining fitting parameters includes: Finding fitting parameters , so that the sum of squared errors Minimum, specifically including: in, ; in, For the label The fluorescence signal intensity corresponding to the pesticide standard solution, For the label Pesticide concentration of the pesticide standard solution; Convert the pesticide concentration-fluorescence signal intensity correlation function into a matrix form: ; in, is the fluorescence signal intensity Column vector of , ; For the label The fluorescence signal intensity corresponding to the pesticide standard solution, For the label The fluorescence signal intensity corresponding to the pesticide standard solution, For the label The fluorescence signal intensity corresponding to the pesticide standard solution, Pesticide concentration The design matrix, ; For the label The pesticide concentration of the pesticide standard solution, For the label The pesticide concentration of the pesticide standard solution, For the label The pesticide concentration of the pesticide standard solution, is the column vector of fitting parameters; The fitting parameters were obtained based on the matrix form of the pesticide concentration-fluorescence signal intensity correlation function. ; in, ; Pesticide concentration The transpose of the design matrix, express The inverse matrix of .

8. The method for rapid detection of pesticide residues based on fluorescent immunochromatography according to claim 7, characterized in that: The training and use of the pesticide concentration recursive model specifically includes: Step B1: Collect p_f samples to form a sample set, and divide it into a training set and a validation set in a ratio of 8:

2. Input the training set into batches in sequence into the pesticide concentration recursive model for forward propagation; Step B2: Obtain the pesticide concentration output by the pesticide concentration recursive model, calculate the loss value using the loss function, calculate each parameter in the model using the backpropagation algorithm, and update the parameters using the gradient descent algorithm; Step B3: Repeat steps B1 and B2 until the loss function value of the pesticide concentration recursive model no longer changes. Then, import the validation set for verification. If the verification is successful, the trained pesticide concentration recursive model is obtained. If the verification is unsuccessful, repeat step B3. Step B4: Obtain the time interval between the collection time of the sample to be tested and the pesticide spraying time, the pesticide spraying dosage, and the rainfall from the pesticide spraying time to the collection time corresponding to the predicted liquid of the sample to be tested, and input them into the trained pesticide concentration recursive model to obtain the pesticide concentration in the predicted liquid of the sample to be tested.

9. The method for rapid detection of pesticide residues based on fluorescent immunochromatography according to claim 8, characterized in that: The method of collecting p_f samples to form a sample set includes: The time interval between the collection time of the sample to be tested and the pesticide spraying time, the pesticide spraying dosage, the rainfall from the pesticide spraying time to the collection time, and the pesticide concentration of a sample to be tested are taken as a sample, and p_f samples are collected to form a sample set.

10. A rapid detection system for pesticide residues based on fluorescence immunochromatography, which is used to implement the rapid detection method for pesticide residues based on fluorescence immunochromatography according to any one of claims 1 to 9, characterized in that: include: Data acquisition module, used to collect p_v samples to be tested; The residue detection module is used to perform a deep extraction on the sample to be tested, obtain p_v parts of the sample extract to be tested, extract p_f parts of the sample extract to be tested and record them as the sample test liquid to be tested, perform a primary pesticide residue test on the sample test liquid to be tested, and obtain environmental data within the time period of the primary pesticide residue test, and determine whether to perform a secondary pesticide residue test based on the environmental data, wherein the environmental data includes ambient temperature, ambient humidity, and concentration of particulate matter in the air; the method for determining whether to perform a secondary pesticide residue test based on the environmental data includes: Set the ambient temperature threshold range, ambient humidity threshold range, and particulate matter concentration threshold range. When the ambient temperature within the time period of the first pesticide residue detection exceeds the ambient temperature threshold range, the ambient humidity exceeds the ambient humidity threshold range, or the particulate matter concentration is greater than or equal to the particulate matter concentration threshold, a second pesticide residue detection is performed. When the ambient temperature is within the ambient temperature threshold range, the ambient humidity is within the ambient humidity threshold range, the particulate matter concentration is less than the particulate matter concentration threshold, and the changes in ambient temperature, ambient humidity, and particulate matter concentration are normal, no secondary detection of pesticide residues is performed; The concentration acquisition module obtains the pesticide concentration in the test solution of the sample to be tested based on the result of the first pesticide residue test and the judgment result, extracts the remaining extract of the sample to be tested and records it as the predicted solution of the sample to be tested, and obtains the pesticide concentration in the predicted solution of the sample to be tested based on the pesticide concentration in the test solution of the sample to be tested. The module includes obtaining the time interval between the collection time of the sample to be tested and the pesticide spraying time, the pesticide spraying dosage, and the rainfall from the pesticide spraying time to the collection time corresponding to the test solution of the sample to be tested; Construct a pesticide concentration recursive model, including: Based on the LSTM basic framework, the input layer, LSTM layer, fully connected layer, and output layer were set. The input of the input layer was set to the time interval, pesticide dosage, and rainfall. The activation function of the fully connected layer was ReLU. The output of the output layer was the pesticide concentration. Using the Adam algorithm, the loss function is: ; Indicates the The model outputs the pesticide concentration of samples, Indicates the The actual pesticide concentration of each sample, is the sample size, is the weight coefficient, is the index of the sample number; Train and use the pesticide concentration recursive model to obtain the pesticide concentration in the predicted solution of the sample to be tested.

Citation Information

Patent Citations

  • Rapid pesticide residue detection system and detection method

    CN112946105A

  • Competitive fluorescence immunochromatography detection card for rapidly and quantitatively detecting carbendazim in tobacco sample as well as preparation method and application of competitive fluorescence immunochromatography detection card

    CN118330213A