An automated detection method for afternoon tea products

Abstract

The present invention relates to the technical field of automated detection of noon tea products, and in particular to an automated detection method for noon tea products. The present invention takes samples and equally divides the finished products after encapsulation in a storage area as detection samples, comprehensively evaluates the drug content state, apparent state and encapsulation degree state of the detection samples, and obtains an encapsulation effect evaluation value of the detection samples. This process is continuously performed to obtain an encapsulation effect evaluation value of a group of detection samples, and then analyzes the encapsulation compliance rate of a group of detection samples. Based on the encapsulation compliance rate, the encapsulation compliance state of the remaining finished products is predicted, and a qualified or unqualified signal is output in real time, thereby realizing rapid and accurate detection of the encapsulation effect of noon tea, significantly improving the detection efficiency and quality control level, and injecting strong impetus into enterprise production optimization and market competition.

Description

Technical Field

[0001] The invention relates to the technical field of automatic detection of afternoon tea products, and in particular to an automatic detection method for afternoon tea products. Background Art

[0002] Wushicha is a traditional Chinese medicine granule with multiple functions. It is used to dispel wind and relieve exterior symptoms, eliminate dampness and harmonize the stomach. It is favored by consumers for its unique medicinal ingredients. However, with the continuous growth of market demand and the expansion of production scale, how to achieve efficient, unified and accurate detection of the quality of Wushicha products has become a key issue to be solved.

[0003] The traditional quality inspection process of afternoon tea products often relies on cumbersome manual sampling and visual inspection. This method is not only time-consuming, labor-intensive and inefficient, but also easily affected by the subjective judgment of operators, resulting in great instability and variability in the inspection results. In addition, with the advancement of the modern manufacturing industry's transformation towards automation and intelligence, the limitations of traditional inspection methods in coping with large-scale production and high-standard quality control are becoming increasingly obvious, and it is difficult to meet the market's higher requirements for product quality control.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] The purpose of the present invention is to solve the limitations of traditional detection methods in dealing with large-scale production and high-standard quality control, and to propose an automated detection method for afternoon tea products.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An automated detection method for afternoon tea products, comprising:

[0008] A1. Sampling and analyzing the finished tea bags at noon in the storage area to obtain test samples, including a1 test sample, a2 test sample and a3 test sample;

[0009] A2, analyzing the drug content status of the a1 test sample to obtain the drug content evaluation index of the a1 test sample;

[0010] A3, analyzing the apparent state of the a2 test sample to obtain the apparent evaluation index of the a2 test sample;

[0011] A4, analyzing the inclusion degree state of the a3 test sample to obtain the inclusion degree evaluation index of the a3 test sample;

[0012] A5. Comprehensively analyze the inclusion effect of the test samples. Specifically, the following analysis is performed: extract the drug content evaluation index of the a1 test sample, the apparent evaluation index of the a2 test sample, and the inclusion degree evaluation index of the a3 test sample, and mark them as δ1, δ2, and δ3, respectively. Take the values ​​of the three for normalization, and according to the formula: BXZ = δ1 × β1 + δ2 × β2 + δ3 × β3, obtain the inclusion effect evaluation value BXZ of the test sample, where β1, β2, and β3 represent the weight coefficients of the drug content evaluation index, the apparent evaluation index, and the inclusion degree evaluation index, respectively;

[0013] By continuously performing steps A1-A5, a group of inclusion effect evaluation values ​​of the test samples are obtained;

[0014] A6. Analyze the inclusion compliance status of a group of test samples to obtain the inclusion compliance rate of a group of test samples;

[0015] A7. Based on the compliance rate of the inclusion of a group of test samples, the compliance status of the inclusion of the finished products of the remaining afternoon tea in the storage area is predicted and analyzed to obtain a qualified test signal or a failed test signal.

[0016] As a further improvement of the present invention, the finished tea bags in the storage area at noon were sampled and analyzed, and the specific analysis was as follows:

[0017] By real-time monitoring and recording the amount of finished tea bags in the storage area at noon during the current monitoring period on the production line, and automatically comparing and analyzing the amount of finished tea bags in the storage area at noon during the current monitoring period on the production line with the preset reference amount of finished products, when the amount of finished tea bags in the storage area at noon during the current monitoring period on the production line reaches or exceeds the preset reference amount of finished products, the sampling instruction is triggered, and according to the triggered sampling instruction, the set amount of finished tea bags are extracted from the storage area by the sampling device, and the extracted finished tea bags are transported to the sample processing area, and divided into equal amounts by the filling machine, thereby obtaining the test samples.

[0018] As a further improvement of the present invention, the drug content status of the a1 test sample is analyzed, and the specific analysis is as follows:

[0019] The solution of the A1 test sample is analyzed by high performance liquid chromatography to obtain the chromatogram of the A1 test sample, the characteristic peak of the drug in the chromatogram of the A1 test sample is identified, and the peak area is extracted therefrom to obtain the peak area of ​​the A1 test sample, and the peak area of ​​the A1 test sample is substituted into the regression equation of the reference standard curve to obtain the real-time drug content of the A1 test sample, which is marked as SFD. According to the formula: δ1 = (sfdsfd *)×100%, and obtain the drug content evaluation index δ1 of the a1 test sample, where sfd * Indicates reference drug content.

[0020] As a further improvement of the present invention, the apparent state of the a2 test sample is analyzed, and the specific analysis is as follows:

[0021] The apparent image of the a2 detection sample is acquired by collecting the apparent image of the a2 detection sample, and the detection points are arranged on the apparent image of the a2 detection sample to obtain each detection point in the apparent image of the a2 detection sample, and the chromaticity value of each detection point in the apparent image of the a2 detection sample is extracted, and the chromaticity value of each detection point in the apparent image of the a2 detection sample is compared and analyzed with a preset reference interval. If the chromaticity value of a detection point in the apparent image of the a2 detection sample is outside the preset reference interval, the detection point in the apparent image of the a2 detection sample is marked as an abnormal point, and the abnormal points in the apparent image of the a2 detection sample are integrated to obtain the abnormal area in the apparent image of the a2 detection sample, which is used as the color surface value of the a2 detection sample and marked as smz;

[0022] The apparent image of the a2 detection sample is evenly divided to obtain each sub-apparent image of the a2 detection sample, and each sub-apparent image of the a2 detection sample is matched with the apparent image of each set foreign-shaped object. If a sub-apparent image of the a2 detection sample successfully matches the apparent image of a set foreign-shaped object, the sub-apparent image is marked as a foreign-shaped object image, and the foreign-shaped object images of the a2 detection sample are counted, and the foreign-shaped object area is extracted from each foreign-shaped object image of the a2 detection sample to obtain each foreign-shaped object area of ​​the a2 detection sample, and the sum is calculated to obtain the total foreign-shaped object area of ​​the a2 detection sample, which is used as the foreign-object face value of the a2 detection sample and marked as ymz;

[0023] Extract the color value smz and foreign body value ymz of the a2 test sample for normalization according to the formula: The apparent evaluation index δ2 of the a2 test sample is obtained, where smz * and ymz * They represent the reference color value and the reference foreign body value respectively, and η1 and η2 represent the weight coefficients of the color value and the foreign body value respectively.

[0024] As a further improvement of the present invention, the inclusion degree state of the a3 test sample is analyzed, and the specific analysis is as follows:

[0025] By acquiring the odor intensity of the a3 detection sample, the odor intensity of the a3 detection sample is obtained, which is used as the odor intensity value of the a3 detection sample and marked as qwz;

[0026] By placing the a3 test sample and the reference sample in the same volume of solvent, respectively, the experimental group and the control group are obtained, the solute concentrations of the experimental group and the control group corresponding to each test time point in the set time period are obtained, and the solute concentrations of the experimental group and the control group corresponding to adjacent test time points in the set time period are calculated to obtain the difference of each solute concentration of the experimental group and the control group in the set time period. At the same time, the difference of each solute concentration of the experimental group and the control group in the set time period is calculated to obtain the mean concentration of the experimental group and the control group in the set time period, and they are marked as sjz and djz respectively; according to the formula: The dissolution rate value ndp of the a3 test sample is obtained, where u1 and u2 represent natural constants, and λ1 and λ2 represent set correction factors;

[0027] By obtaining the initial time point and the end time point of the dissolution of the a3 test sample, and performing a difference calculation, that is, subtracting the initial time point from the end time point, the dissolution time of the a3 test sample is obtained and marked as rjs;

[0028] The values ​​of the odor intensity value qwz, dissolution rate value ndp and dissolution time rjs of the a3 test sample are extracted and normalized according to the formula: The inclusion degree evaluation index δ3 of the a3 test sample is obtained, where rjs * represents the reference dissolution time, and θ1, θ2 and θ3 represent the weight coefficients of odor intensity value, dissolution rate value and dissolution time, respectively.

[0029] As a further improvement of the present invention, the inclusion compliance status of a group of test samples is analyzed, and the specific analysis is as follows:

[0030] By extracting the inclusion effect evaluation values ​​of a group of test samples, comparing and analyzing the inclusion effect evaluation values ​​of a group of test samples with the preset inclusion effect evaluation threshold, the primary inclusion effect, the secondary inclusion effect and the tertiary inclusion effect are obtained;

[0031] The number of times a group of test samples are judged to be the primary inclusion effect and the number of times the secondary inclusion effect is judged to be the secondary inclusion effect is counted, and they are marked as Sbnm1 and Sbnm2 respectively, according to the formula: Get the inclusion compliance rate P of a group of test samples sample , where Sbnm 总 represents the total number of judgments, and q1 and q2 represent correction factors.

[0032] As a further improvement of the present invention, a prediction analysis is performed on the encapsulation compliance status of the finished products of the remaining afternoon tea in the storage area, and the specific analysis is as follows:

[0033] By obtaining the remaining amount of afternoon tea bags in the storage area on the production line, and recording it as Q reningAt the same time, obtain the finished product quantity of a group of test samples and record it as P rening , according to the formula: Q sample =K×P sample , and obtain the encapsulation compliance rate Q corresponding to the finished products of the remaining afternoon tea in the storage area sample , where K is solved as:

[0034] The encapsulation compliance rate Q of the finished products of the remaining afternoon tea in the storage area sample Compared with the preset reference interval, if the remaining afternoon tea packaged finished products in the storage area have a package compliance rate Q sample If the test result is within the preset reference range, a qualified signal is generated. If the qualified rate Q of the finished product of the remaining afternoon tea in the storage area is sample When it is outside the preset reference interval, a detection failure signal is generated.

[0035] Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects:

[0036] 1. The present invention takes samples from the finished products of the noon tea packaged in the storage area and divides them into equal parts to obtain test samples, so as to ensure that the test of the finished products of the noon tea packaged is more accurate and scientific, which can greatly improve the reliability of the test results and further provide strong data support for the subsequent analysis and evaluation of the package effect of the noon tea;

[0037] 2. The present invention comprehensively evaluates the inclusion effect of Wu Shi Tea by taking into account the evaluation indexes of drug content, apparent state and inclusion degree. By continuously executing this process, a group of inclusion effect evaluation values ​​of the test samples are obtained, which provides rich data support for the subsequent in-depth analysis of the compliance rate of the inclusion effect of Wu Shi Tea.

[0038] 3. The present invention obtains the inclusion standard rate of a group of test samples by analyzing the inclusion standard status of a group of test samples, and predicts and analyzes the inclusion standard status of the remaining afternoon tea finished products in the storage area on the production line based on the inclusion standard rate of a group of test samples, thereby obtaining a qualified test signal or a failed test signal, thereby realizing rapid and accurate detection of the inclusion effect of afternoon tea, significantly improving the detection efficiency and quality control level, and injecting strong impetus into enterprise production optimization and market competition. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 It is a block diagram of the overall method of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0042] like Figure 1 As shown, an automated detection method for afternoon tea products comprises:

[0043] A1. Sample processing: Sampling and analysis of finished tea bags in the storage area at noon. The specific analysis is as follows:

[0044] By real-time monitoring and recording the amount of finished products of noon tea bags in the storage area during the current monitoring time period on the production line (such as every hour, every minute, etc., set according to actual needs), and automatically comparing and analyzing the amount of finished products of noon tea bags in the storage area during the current monitoring time period on the production line with the preset reference finished product amount, when the amount of finished products of noon tea bags in the storage area during the current monitoring time period on the production line reaches or exceeds the preset reference finished product amount, a sampling instruction is triggered, and according to the triggered sampling instruction, a set amount of finished products of noon tea bags are extracted from the storage area by a sampling device, and the extracted finished products of noon tea bags are transported to a sample processing area, and divided equally by a packaging machine, thereby obtaining test samples, the test samples include a1 test samples, a2 test samples and a3 test samples, and the a1 test sample is executed as A2, the a2 test sample is executed as A3, and the a3 test sample is executed as A4;

[0045] In a specific embodiment, the present invention samples the finished product of the noon tea packaged in the storage area and divides it into equal parts to obtain the test samples, so as to ensure that the test of the finished product of the noon tea packaged is more accurate and scientific, which can greatly improve the reliability of the test results and further provide strong data support for the subsequent analysis and evaluation of the package effect of the noon tea;

[0046] A2. Analysis of the first inclusion effect: Analyze the drug content of the sample tested in a1. The specific analysis is as follows:

[0047] The a1 test sample is dissolved in an appropriate solvent and diluted when necessary to ensure that the concentration of the a1 test sample is within the detection range. The solution is filtered using a filter membrane to remove insoluble impurities and particulate matter, thereby obtaining a solution of the a1 test sample. The solution of the a1 test sample is analyzed by high performance liquid chromatography (HPLC) to obtain a chromatogram of the a1 test sample. The characteristic peak of the drug in the chromatogram of the a1 test sample is identified, and the peak area is extracted therefrom to obtain the peak area of ​​the a1 test sample. The peak area of ​​the a1 test sample is substituted into the regression equation of the reference standard curve to obtain the real-time drug content of the a1 test sample, which is marked as sfd, according to the formula: δ1=(sfdsfd * )×100%, and obtain the drug content evaluation index δ1 of the a1 test sample, where sfd * Indicates reference drug content;

[0048] It should be noted that the regression equation of the reference standard curve is solved as follows: a set of standard solutions of different concentrations are prepared by using the reference substance, and then the set of standard solutions is measured and analyzed by high performance liquid chromatography (HPLC), and the peak area at each concentration is recorded, and then the reference standard curve is drawn with the concentration as the abscissa and the peak area as the ordinate, thereby obtaining the regression equation of the reference standard curve;

[0049] A3. Second inclusion effect analysis: Analyze the apparent state of the a2 test sample. The specific analysis is as follows:

[0050] The apparent image of the a2 detection sample is collected by a high-definition camera to obtain the apparent image of the a2 detection sample, and the detection points are arranged on the apparent image of the a2 detection sample to obtain each detection point in the apparent image of the a2 detection sample, and the chromaticity value of each detection point in the apparent image of the a2 detection sample is extracted, and the chromaticity value of each detection point in the apparent image of the a2 detection sample is compared and analyzed with a preset reference interval. If the chromaticity value of a detection point in the apparent image of the a2 detection sample is outside the preset reference interval, then the detection point in the apparent image of the a2 detection sample is marked as an abnormal point, otherwise, then the detection point in the apparent image of the a2 detection sample is marked as a normal point, and the abnormal points in the apparent image of the a2 detection sample are integrated and processed to obtain the abnormal area in the apparent image of the a2 detection sample, which is used as the color surface value of the a2 detection sample and marked as smz;

[0051] The surface image of the a2 detection sample is evenly divided to obtain each sub-surface image of the a2 detection sample, and each sub-surface image of the a2 detection sample is matched with the surface image of each set foreign-shaped object. If a sub-surface image of the a2 detection sample successfully matches the surface image of a set foreign-shaped object, the sub-surface image is marked as a foreign-shaped object image, and the foreign-shaped object images of the a2 detection sample are counted, wherein the foreign-shaped objects include lumps, fragments, oversized particles, etc. The area of ​​the foreign-shaped objects is extracted from each foreign-shaped object image of the a2 detection sample to obtain each foreign-shaped object area of ​​the a2 detection sample, and the sum is calculated to obtain the total foreign-shaped object area of ​​the a2 detection sample, which is used as the foreign-object face value of the a2 detection sample and marked as ymz;

[0052] Extract the color value smz and foreign body value ymz of the a2 test sample for normalization according to the formula: The apparent evaluation index δ2 of the a2 test sample is obtained, where smz * and ymz * They represent the reference color value and the reference foreign body value respectively, η1 and η2 represent the weight coefficients of the color value and the foreign body value respectively, and η1>η2;

[0053] A4. Analysis of the third inclusion effect: Analyze the inclusion degree of the a3 test sample. The specific analysis is as follows:

[0054] The odor intensity of the a3 test sample is obtained by using an odor meter to obtain the odor intensity of the a3 test sample, which is used as the odor intensity value of the a3 test sample and marked as qwz;

[0055] By placing the a3 test sample and the reference sample in the same volume of solvent, respectively, the experimental group and the control group are obtained, the solute concentration of the experimental group corresponding to each test time point in the set time period is obtained, and the solute concentration of the experimental group corresponding to adjacent test time points in the set time period is calculated to obtain the difference of each solute concentration of the experimental group in the set time period, and the mean of each solute concentration difference of the experimental group in the set time period is calculated to obtain the mean concentration of the experimental group in the set time period, which is marked as sjz;

[0056] Obtain the solute concentration of the control group corresponding to each detection time point within the set time period, and perform difference calculation on the solute concentrations of the control group corresponding to adjacent detection time points within the set time period, thereby obtaining the difference of each solute concentration of the control group within the set time period, and at the same time perform mean calculation on the difference of each solute concentration of the control group within the set time period, obtain the mean concentration of the control group within the set time period, and mark it as djz;

[0057] According to the formula: The dissolution rate value ndp of the a3 test sample is obtained, where u1 and u2 represent natural constants, and λ1 and λ2 represent set correction factors;

[0058] Set an initial time point, that is, the moment when the a3 test sample is placed in the solvent, and then closely monitor the dissolution process of the a3 test sample in the solvent until the a3 test sample reaches a completely dissolved state. At this time, record this time point as the end time point, extract the initial time point and the end time point for difference calculation, that is, subtract the initial time point from the end time point, thereby obtaining the dissolution time of the a3 test sample and marking it as rjs;

[0059] The odor intensity value qwz, dissolution rate value ndp and dissolution time rjs of the a3 test sample are extracted and normalized according to the formula: The inclusion degree evaluation index δ3 of the a3 test sample is obtained, where rjs * represents the reference dissolution time, θ1, θ2 and θ3 represent the weight coefficients of the odor intensity value, the dissolution rate value and the dissolution time, respectively, and θ1>θ2>θ3;

[0060] A5. Comprehensive inclusion effect analysis: Comprehensive analysis of the inclusion effect of the test samples, specifically:

[0061] By extracting the values ​​of the drug content evaluation index δ1 of the a1 test sample, the apparent evaluation index δ2 of the a2 test sample, and the inclusion degree evaluation index δ3 of the a3 test sample, and performing normalization processing, the inclusion effect evaluation value BXZ of the test sample is obtained according to the formula: BXZ=δ1×β1+δ2×β2+δ3×β3, wherein β1, β2 and β3 represent the weight coefficients of the drug content evaluation index, the apparent evaluation index and the inclusion degree evaluation index, respectively, and β1>β2>β3;

[0062] By continuously performing steps A1-A5, a group of inclusion effect evaluation values ​​of the test samples are obtained;

[0063] In a specific embodiment, the present invention comprehensively evaluates the inclusion effect of Wu Shi Tea by comprehensively considering the evaluation indexes of multiple aspects such as drug content, apparent state and inclusion degree, and then continuously performs steps A1-A5 to collect a complete set of data sets, which provides rich data support for the subsequent in-depth analysis of the compliance rate of the inclusion effect of Wu Shi Tea.

[0064] A6. Compliance rate analysis: Analyze the compliance status of a group of test samples. The specific analysis is as follows:

[0065] By extracting the inclusion effect evaluation value of a group of test samples, comparing and analyzing the inclusion effect evaluation value of a group of test samples with the preset inclusion effect evaluation threshold, if the inclusion effect evaluation value is greater than the preset inclusion effect evaluation threshold, the test sample is determined to be a first-level inclusion effect, if the inclusion effect evaluation value is equal to the preset inclusion effect evaluation threshold, the test sample is determined to be a second-level inclusion effect, if the inclusion effect evaluation value is less than the preset inclusion effect evaluation threshold, the test sample is determined to be a third-level inclusion effect;

[0066] The number of times a group of test samples are judged to be the primary inclusion effect and the number of times the secondary inclusion effect is judged to be the secondary inclusion effect is counted, and they are marked as Sbnm1 and Sbnm2 respectively, according to the formula: Get the inclusion compliance rate P of a group of test samples sample , where Sbnm 总 represents the total number of judgments, q1 and q2 represent correction factors;

[0067] A7. Remaining prediction analysis: Based on the inclusion compliance rate of a group of test samples, the inclusion compliance status of the remaining afternoon tea products in the storage area is predicted and analyzed. The specific analysis is as follows:

[0068] By obtaining the remaining amount of afternoon tea bags in the storage area on the production line, and recording it as Q rening At the same time, obtain the finished product quantity of a group of test samples and record it as P rening , according to the formula: Q sample =K×P sample , and obtain the encapsulation compliance rate Q corresponding to the finished products of the remaining afternoon tea in the storage area sample , where K is solved as:

[0069] The encapsulation compliance rate Q of the finished products of the remaining afternoon tea in the storage area sample Compared with the preset reference interval, if the remaining afternoon tea packaged finished products in the storage area have a package compliance rate Q sample If the test result is within the preset reference range, a qualified signal is generated. If the qualified rate Q of the finished product of the remaining afternoon tea in the storage area is sample When it is outside the preset reference interval, a detection failure signal is generated;

[0070] Sending the generated qualified detection signal or unqualified detection signal to the display terminal for display notification;

[0071] In a specific embodiment, the present invention analyzes the inclusion compliance status of a group of test samples to obtain the inclusion compliance rate of a group of test samples, and based on the inclusion compliance rate of a group of test samples, predicts and analyzes the inclusion compliance status of the remaining noon tea finished products in the storage area on the production line, thereby obtaining a qualified test signal or a failed test signal, thereby achieving effective monitoring and prediction of the inclusion compliance status of the noon tea finished products in the storage area on the production line, providing enterprises with timely and accurate quality information, which not only improves production efficiency and product quality, but also reduces the risks and costs caused by quality problems, thereby achieving refined management and control of the production process.

[0072] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An automated detection method for afternoon tea products, characterized in that: include: A1. Sampling and analyzing the finished tea bags at noon in the storage area to obtain test samples, including a1 test sample, a2 test sample and a3 test sample; A2, analyzing the drug content status of the a1 test sample to obtain the drug content evaluation index of the a1 test sample; A3, analyzing the apparent state of the a2 test sample to obtain the apparent evaluation index of the a2 test sample; A4, analyzing the inclusion degree state of the a3 test sample to obtain the inclusion degree evaluation index of the a3 test sample; A5. Comprehensively analyze the inclusion effect of the test samples. Specifically, the following analysis is performed: extract the drug content evaluation index of the a1 test sample, the apparent evaluation index of the a2 test sample, and the inclusion degree evaluation index of the a3 test sample, and mark them as δ1, δ2, and δ3, respectively. Take the values ​​of the three for normalization, and according to the formula: BXZ = δ1 × β1 + δ2 × β2 + δ3 × β3, obtain the inclusion effect evaluation value BXZ of the test sample, where β1, β2, and β3 represent the weight coefficients of the drug content evaluation index, the apparent evaluation index, and the inclusion degree evaluation index, respectively; By continuously performing steps A1-A5, a group of inclusion effect evaluation values ​​of the test samples are obtained; A6. Analyze the inclusion compliance status of a group of test samples to obtain the inclusion compliance rate of a group of test samples; A7. Based on the compliance rate of the inclusion of a group of test samples, the compliance status of the inclusion of the finished products of the remaining afternoon tea in the storage area is predicted and analyzed to obtain a qualified test signal or a failed test signal.

2. The automated detection method for afternoon tea products according to claim 1, characterized in that: The finished tea bags in the storage area at noon were sampled and analyzed. The specific analysis was as follows: By real-time monitoring and recording the amount of finished tea bags in the storage area at noon during the current monitoring time period on the production line, and automatically comparing and analyzing the amount of finished tea bags in the storage area at noon during the current monitoring time period on the production line with the preset reference amount of finished products, when the amount of finished tea bags in the storage area at noon during the current monitoring time period on the production line reaches or exceeds the preset reference amount of finished products, the sampling instruction is triggered, and the set amount of finished tea bags in the storage area is extracted according to the triggered sampling instruction, and the extracted finished tea bags are transported to the sample processing area for equal division, thereby obtaining the test samples.

3. The automated detection method for afternoon tea products according to claim 1, characterized in that: The drug content status of the a1 test sample was analyzed, and the specific analysis was as follows: The solution of the a1 test sample is analyzed by high performance liquid chromatography, thereby obtaining the chromatogram of the a1 test sample, identifying the characteristic peak of the drug in the chromatogram of the a1 test sample, and extracting the peak area therefrom, thereby obtaining the peak area of ​​the a1 test sample, substituting the peak area of ​​the a1 test sample into the regression equation of the reference standard curve, thereby obtaining the real-time drug content of the a1 test sample, and marking it as sfd, according to the formula: δ1 = (sfd / sfd * )×100%, and obtain the drug content evaluation index δ1 of the a1 test sample, where sfd * Indicates reference drug content.

4. The automated detection method for afternoon tea products according to claim 1, characterized in that: The apparent state of the a2 test sample was analyzed, and the specific analysis was as follows: The apparent image of the a2 detection sample is acquired by collecting the apparent image of the a2 detection sample, and the detection points are arranged on the apparent image of the a2 detection sample to obtain each detection point in the apparent image of the a2 detection sample, and the chromaticity value of each detection point in the apparent image of the a2 detection sample is extracted, and the chromaticity value of each detection point in the apparent image of the a2 detection sample is compared and analyzed with a preset reference interval. If the chromaticity value of a detection point in the apparent image of the a2 detection sample is outside the preset reference interval, the detection point in the apparent image of the a2 detection sample is marked as an abnormal point, and the abnormal points in the apparent image of the a2 detection sample are integrated to obtain the abnormal area in the apparent image of the a2 detection sample, which is used as the color surface value of the a2 detection sample and marked as smz; The apparent image of the a2 detection sample is evenly divided to obtain each sub-apparent image of the a2 detection sample, and each sub-apparent image of the a2 detection sample is matched with the apparent image of each set foreign-shaped object. If a sub-apparent image of the a2 detection sample successfully matches the apparent image of a set foreign-shaped object, the sub-apparent image is marked as a foreign-shaped object image, and the foreign-shaped object images of the a2 detection sample are counted, and the foreign-shaped object area is extracted from each foreign-shaped object image of the a2 detection sample to obtain each foreign-shaped object area of ​​the a2 detection sample, and the sum is calculated to obtain the total foreign-shaped object area of ​​the a2 detection sample, which is used as the foreign-object face value of the a2 detection sample and marked as ymz; Extract the color value smz and foreign body value ymz of the a2 test sample for normalization according to the formula: The apparent evaluation index δ2 of the a2 test sample is obtained, where smz * and ymz * They represent the reference color value and the reference foreign body value respectively, and η1 and η2 represent the weight coefficients of the color value and the foreign body value respectively.

5. The automated detection method for afternoon tea products according to claim 1, characterized in that: The inclusion degree of the a3 test sample is analyzed, and the specific analysis is as follows: By acquiring the odor intensity of the a3 detection sample, the odor intensity of the a3 detection sample is obtained, which is used as the odor intensity value of the a3 detection sample and marked as qwz; By placing the a3 test sample and the reference sample in the same volume of solvent, respectively, the experimental group and the control group are obtained, the solute concentrations of the experimental group and the control group corresponding to each test time point in the set time period are obtained, and the solute concentrations of the experimental group and the control group corresponding to adjacent test time points in the set time period are calculated to obtain the difference of each solute concentration of the experimental group and the control group in the set time period. At the same time, the difference of each solute concentration of the experimental group and the control group in the set time period is calculated to obtain the mean concentration of the experimental group and the control group in the set time period, and they are marked as sjz and djz respectively; according to the formula: The dissolution rate value ndp of the a3 test sample is obtained, where u1 and u2 represent natural constants, and λ1 and λ2 represent set correction factors; By obtaining the initial time point and the end time point of the dissolution of the a3 test sample, and performing a difference calculation, that is, subtracting the initial time point from the end time point, the dissolution time of the a3 test sample is obtained and marked as rjs; The values ​​of the odor intensity value qwz, dissolution rate value ndp and dissolution time rjs of the a3 test sample are extracted and normalized according to the formula: The inclusion degree evaluation index δ3 of the a3 test sample is obtained, where rjs * represents the reference dissolution time, and θ1, θ2 and θ3 represent the weight coefficients of odor intensity value, dissolution rate value and dissolution time, respectively.

6. The automated detection method for afternoon tea products according to claim 1, characterized in that: The inclusion compliance status of a group of test samples was analyzed, and the specific analysis was as follows: By extracting the inclusion effect evaluation values ​​of a group of test samples, comparing and analyzing the inclusion effect evaluation values ​​of a group of test samples with the preset inclusion effect evaluation threshold, the primary inclusion effect, the secondary inclusion effect and the tertiary inclusion effect are obtained; The number of times a group of test samples are judged to be the primary inclusion effect and the number of times the secondary inclusion effect is judged to be the secondary inclusion effect is counted, and they are marked as Sbnm1 and Sbnm2 respectively, according to the formula: Get the inclusion compliance rate P of a group of test samples sample , where Sbnm 总 represents the total number of judgments, and q1 and q2 represent correction factors.

7. The automated detection method for afternoon tea products according to claim 1, characterized in that: The prediction and analysis of the package compliance status of the remaining afternoon tea packaged finished products in the storage area are as follows: By obtaining the remaining amount of afternoon tea bags in the storage area on the production line, and recording it as Q rening At the same time, obtain the finished product quantity of a group of test samples and record it as P rening , according to the formula: Q sample =K×P sample , and obtain the encapsulation compliance rate Q corresponding to the finished products of the remaining afternoon tea in the storage area sample , where K is solved as: The encapsulation compliance rate Q of the finished products of the remaining afternoon tea in the storage area sample Compared with the preset reference interval, if the remaining afternoon tea packaged finished products in the storage area have a package compliance rate Q sample If the test result is within the preset reference range, a qualified signal is generated. If the qualified rate Q of the finished product of the remaining afternoon tea in the storage area is sample When it is outside the preset reference interval, a detection failure signal is generated.

Images