An experimental method and system for detecting residual amount of cleaning agent

Abstract

The present invention discloses an experimental method and system for detecting the residual amount of detergent used, and specifically relates to the field of residual detection technology, including diluting a known standard solution according to a set of dilution multiples to obtain a set of concentration standard solutions; the known standard solution is a detergent residue of a reference concentration; the concentration standard solution set includes M concentration standard solutions and a known concentration value corresponding to each concentration standard solution; the M concentration standard solutions in the concentration standard solution set are detected and analyzed to obtain absorbance values, and a standard curve is generated based on the absorbance values ​​and the known concentration values ​​corresponding to each concentration standard solution; the present invention detects an abnormality mechanism, performs abnormal analysis on detergent samples, improves the speed of analyzing the residual amount of detergent used and the data accuracy, further judges the safety level of the residual amount of detergent used based on the sample concentration coefficient, and is conducive to preventing high-concentration detergent residues from causing potential damage to the environment.

Description

Technical Field

[0001] The present invention relates to the technical field of residual detection, and more specifically, to an experimental method and system for detecting the residual amount of detergent used. Background Art

[0002] In various industries and fields, detergents are widely used and common. The residual problem of detergents has always been the focus of attention, especially in the fields of food processing and medical device manufacturing, where residual detergents may have a potential impact on the quality and safety of products. Therefore, it is particularly important to accurately detect and analyze the residual amount of detergents used. At present, the residual amount of detergents is mainly detected by a large number of experiments conducted by staff. Due to different work experience, the test results have large errors and it is difficult to further improve the detection efficiency. In order to improve the detection efficiency, similar residual experimental methods are used in the prior art. For example, the Chinese patent with authorization announcement number CN214749703U discloses a rapid detection box for agricultural residues with high detection accuracy, and the Chinese patent with authorization announcement number CN206725412U discloses a portable detection device for trace plant growth regulator residues in fruits and vegetables. Although the above method can realize the detection of the residual amount, the inventor has studied and applied the above method and the prior art and found that the above method and the prior art have at least the following partial defects:

[0003] (1) No abnormal detection mechanism was added, so the detection results still have large errors;

[0004] (2) The traditional manual experimental method increases a lot of experimental preparation and operation time, and also increases the demand for manual operation.

[0005] To this end, the present invention provides an experimental method and system for detecting the residual amount of detergent used. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides an experimental method and system for detecting the residual amount of detergent used, so as to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: an experimental method for detecting the residual amount of detergent used, comprising:

[0008] Step 1: diluting a known standard solution according to a set of dilution multiples to obtain a set of concentration standard solutions; the known standard solution is a detergent residue of a reference concentration; the set of concentration standard solutions includes M concentration standard solutions and a known concentration value corresponding to each concentration standard solution;

[0009] Step 2: Detect and analyze the M concentration standard solutions in the concentration standard solution set to obtain absorbance values, and generate a standard curve graph based on the absorbance values ​​and the known concentration values ​​corresponding to each concentration standard solution;

[0010] Step 3: obtaining concentration characteristic data of the nth detergent sample in the detergent sample set, inputting the concentration characteristic data into a pre-built machine learning model, and predicting a concentration value corresponding to the concentration characteristic data; the detergent sample set includes N detergent samples, N is an integer greater than zero, n∈N;

[0011] Step 4: Obtain a sample curve graph of the nth cleaning agent sample, and compare the sample curve graph with the standard curve graph to obtain the sample abnormal concentration coefficient of the nth cleaning agent;

[0012] Step 5: Compare and analyze the abnormal concentration coefficient of the nth detergent sample with the abnormal concentration coefficient threshold to determine whether to generate a concentration analysis instruction; if a concentration analysis instruction is generated, obtain sample characteristic data, and generate a sample concentration coefficient of the nth detergent sample based on the sample characteristic data; classify the nth detergent sample into safety levels according to the sample concentration coefficient; the sample characteristic data includes the wavelength value, absorbance value, concentration value and temperature value of the nth detergent sample.

[0013] Furthermore, the method for obtaining a concentration standard solution set is as follows:

[0014] a1: Divide the known standard solution equally into M sub-bottles, and obtain a dilution multiple set; the dilution multiple set consists of M dilution multiples that are equally spaced from each other; each dilution multiple in the dilution multiple set has a one-to-one correspondence with the number of sub-bottles;

[0015] a2: According to the relationship between the dilution factor and the solvent volume, determine the volume of solvent required to be added for each dilution of the known standard solution;

[0016] a3: add the corresponding volume of solvent to the mth sub-bottle, set m=m+1, and jump back to step a2;

[0017] a4: Repeat steps a2 to a3 above until the cycle ends when m=M, and obtain a concentration standard solution set of known standard solutions. The known concentration value corresponding to each concentration standard solution in the concentration standard solution set is divided according to the gradient concentration interval.

[0018] Furthermore, the method of detecting and analyzing the M concentration standard solutions in the concentration standard solution set to obtain absorbance includes:

[0019] Preset the wavelength value, temperature value and transmittance value of the optical detection device, batch test the M concentration standard solutions in the concentration standard solution set, and record the absorbance value measured by the optical detection device; the optical detection device is a spectrophotometer, a gas chromatograph or a liquid chromatograph;

[0020] Methods for generating a standard curve graph based on absorbance values ​​and known concentration values ​​corresponding to each concentration standard solution include:

[0021] Obtain the known concentration value corresponding to each concentration standard solution, and use each known concentration value as the horizontal axis data of the standard curve graph;

[0022] Obtain the absorbance value of each concentration of the standard solution, and use the absorbance value as the vertical axis data of the standard curve graph;

[0023] Use the drawing tool to mark the coordinate points of each concentration standard solution on the chart, and connect the coordinate points of each concentration standard solution to draw a standard curve chart.

[0024] Furthermore, the concentration characteristic data includes a wavelength value, a transmittance value, an absorbance value and a temperature value, and each group of the concentration characteristic data corresponds to a concentration value;

[0025] The wavelength value and transmittance value are parameters set by the optical detection device, the absorbance value is the value obtained by the optical detection device for detecting the nth detergent sample; the temperature value is measured and obtained by the temperature sensor on the optical detection device;

[0026] The concentration value is the average concentration value of the nth detergent sample;

[0027] The method for constructing the machine learning model includes:

[0028] Convert a set of concentration characteristic data and concentration values ​​into a corresponding set of characteristic vectors;

[0029] Each group of feature vectors is used as the input of the machine learning model. The machine learning model uses the concentration value corresponding to a group of concentration feature data as the output, and the concentration value actually corresponding to a group of concentration feature data as the prediction target. Minimizing the loss function value of the machine learning model is used as the training target; training is stopped when the loss function value of the machine learning model is less than or equal to a preset target loss value. The machine learning model is one of the models such as SVM regression, random forest regression or neural network regression.

[0030] Furthermore, the method for obtaining the sample curve graph of the nth detergent sample includes:

[0031] Obtain the predicted concentration value and absorbance value of the nth detergent sample;

[0032] Dividing the predicted concentration value and absorbance value of the nth detergent sample according to the gradient concentration interval to obtain a predicted concentration set and absorbance set of the nth detergent sample;

[0033] The concentration value in the concentration set of the nth detergent sample is used as the horizontal axis data, and the absorbance value in the absorbance set corresponding to the concentration set is used as the vertical axis data. Use the drawing tool to plot the horizontal axis data and the vertical axis data on the chart to obtain the sample curve chart of the nth detergent sample.

[0034] Further, the method of comparing the sample curve graph with the standard curve graph to obtain the abnormal concentration coefficient of the nth detergent sample includes:

[0035] The sample curve and the standard curve are divided into H regions according to the gradient concentration interval;

[0036] Compare the pixels in the same position area of ​​the sample curve graph and the standard curve graph one by one, and record the difference area between the sample curve graph and the standard curve graph;

[0037] The number of difference regions with differences is counted to obtain the total number of difference regions, and the total number of difference regions is used as the abnormal concentration coefficient of the nth detergent sample.

[0038] Further, the method for determining whether to generate a concentration analysis instruction includes:

[0039] Preset an abnormal concentration coefficient threshold, and compare and analyze the abnormal concentration coefficient of each detergent sample with the abnormal concentration coefficient threshold;

[0040] If the abnormal concentration coefficient is less than or equal to the abnormal concentration coefficient threshold, a concentration analysis instruction is generated;

[0041] If the abnormal concentration coefficient is greater than the abnormal concentration coefficient threshold, a sample abnormal instruction is generated;

[0042] According to the concentration analysis instruction, a sample concentration coefficient of the nth cleaning agent sample is generated;

[0043] Further, the method of generating the sample concentration coefficient of the nth detergent sample based on the sample characteristic data includes:

[0044] Get the wavelength value, absorbance value, concentration value and temperature value of the nth detergent sample, marked as Xg n , Bc n 、Nd n and Wd n , and perform formula calculation to obtain the sample concentration coefficient, the calculation formula of the sample concentration coefficient is:

[0045]

[0046] In the formula, YP n represents the sample concentration factor of the nth detergent sample, Xg n Indicates the absorbance value of the nth detergent sample, Bc n Represents the wavelength value of the nth detergent sample, Nd n Indicates the concentration value of the nth detergent sample, Wd n represents the temperature value of the nth detergent sample, p represents a natural constant, β1 represents the weight factor of the absorbance value of the nth detergent sample; β2 represents the weight factor of the wavelength value of the nth detergent sample; β3 represents the weight factor of the concentration value of the nth detergent sample; β4 represents the weight factor of the temperature value of the nth detergent sample.

[0047] Furthermore, the method for classifying the safety level of the nth detergent sample according to the sample concentration coefficient includes:

[0048] b1: Get the sample concentration coefficient of the nth detergent sample;

[0049] b2: Set G concentration coefficient gradient intervals, and set K sample levels corresponding to the G concentration coefficient gradient intervals;

[0050] Each of the concentration coefficient gradient intervals has one and only one sample level associated and bound thereto;

[0051] b3: comparing the sample concentration coefficient of the nth detergent sample with each concentration coefficient gradient interval to obtain the concentration coefficient gradient interval into which the sample concentration coefficient of the nth detergent sample falls;

[0052] b4: Classify the nth detergent sample into a corresponding sample level according to the concentration coefficient gradient interval into which the sample concentration coefficient of the nth detergent sample falls; and set n=n+1, and jump back to step b1;

[0053] b5: Repeat the above steps b1 to b4 until the cycle ends when n=N, so that each of the cleaning agent samples is divided into K sample levels in turn.

[0054] In a second aspect, the present invention provides an experimental system for detecting the residual amount of detergent used, which is used to implement the above-mentioned experimental method for detecting the residual amount of detergent used, comprising:

[0055] A dilution module, used to dilute a known standard solution according to a set of dilution multiples to obtain a set of concentration standard solutions; the known standard solution is a detergent residue of a reference concentration; the set of concentration standard solutions includes M concentration standard solutions and a known concentration value corresponding to each concentration standard solution;

[0056] The acquisition and analysis module is used to detect and analyze the M concentration standard solutions in the concentration standard solution set to obtain absorbance values, and generate a standard curve graph based on the absorbance values ​​and the known concentration values ​​corresponding to each concentration standard solution;

[0057] A prediction module, used to obtain concentration characteristic data of an nth detergent sample in a detergent sample set, input the concentration characteristic data into a pre-built machine learning model, and predict a concentration value corresponding to the concentration characteristic data; the detergent sample set includes N detergent samples, N is an integer greater than zero, n∈N;

[0058] A comparative analysis module, used for obtaining a sample curve graph of the nth detergent sample, and comparing the sample curve graph with the standard curve graph to obtain an abnormal concentration coefficient of the sample of the nth detergent;

[0059] The instruction generation module is used to compare and analyze the abnormal concentration coefficient of the nth detergent sample with the abnormal concentration coefficient threshold to determine whether to generate a concentration analysis instruction; if the concentration analysis instruction is generated, the sample concentration coefficient of the nth detergent sample is obtained, and the nth detergent sample is classified into a safety level according to the sample concentration coefficient.

[0060] Technical effects and advantages of the present invention:

[0061] 1. The present invention dilutes a known standard solution according to a set of dilution multiples to obtain a concentration standard solution set; the known standard solution is a detergent residue of a reference concentration; the concentration standard solution set includes M concentration standard solutions and a known concentration value corresponding to each concentration standard solution; the M concentration standard solutions in the concentration standard solution set are detected and analyzed to obtain absorbance values, and a standard curve graph is generated based on the absorbance values ​​and the known concentration values ​​corresponding to each concentration standard solution; the concentration characteristic data of the nth detergent sample in the detergent sample set is obtained, the concentration characteristic data is input into a pre-built machine learning model, and a concentration value corresponding to the concentration characteristic data is predicted; the detergent sample set includes N detergent samples, a sample curve graph of the nth detergent sample is obtained, and the sample curve graph is compared with the standard curve graph to obtain abnormal concentration coefficient of the nth detergent sample; comparing and analyzing the abnormal concentration coefficient of the nth detergent sample with the abnormal concentration coefficient threshold to determine whether to generate a concentration analysis instruction; if a concentration analysis instruction is generated, obtaining sample characteristic data, and generating a sample concentration coefficient of the nth detergent sample based on the sample characteristic data; classifying the nth detergent sample into safety levels according to the sample concentration coefficient; in this embodiment, by obtaining data such as wavelength values, transmittance values, absorbance values, and temperature values, a machine learning model is used to quickly predict the concentration value, and at the same time, an abnormality detection mechanism is added to perform abnormal analysis on the detergent sample, thereby improving the speed and data accuracy of analyzing the residual amount of detergent used, and further determining the safety level of the residual amount of detergent used based on the sample concentration coefficient, which is beneficial to preventing high concentrations of detergent residues from causing potential damage to the environment.

[0062] 2. When testing a large number of detergent samples, compared with traditional manual experimental methods, the present invention can automatically process data and make predictions through machine learning models, which reduces a lot of experimental preparation and operation time, and reduces the need for manual operation, thereby improving work efficiency and accuracy, increasing the speed of analyzing the residual amount of detergent used, and reducing time and labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A flow chart of an experimental method for detecting the residual amount of cleaning agent used in Example 1;

[0064] Figure 2 A schematic diagram of an experimental system for detecting the residual amount of cleaning agent used in Example 2;

[0065] Figure 3 This is a schematic diagram of an electronic device according to Embodiment 3;

[0066] Figure 4 A schematic diagram of a computer-readable storage medium of Example 4. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0068] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0069] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0070] Example 1

[0071] See also Figure 1 As shown, this embodiment discloses an experimental method for detecting the residual amount of detergent used, comprising:

[0072] Step 1: diluting a known standard solution according to a set of dilution multiples to obtain a set of concentration standard solutions; the known standard solution is a detergent residue of a reference concentration; the set of concentration standard solutions includes M concentration standard solutions and a known concentration value corresponding to each concentration standard solution;

[0073] It should be noted that the reference concentration of detergent residue refers to a standard solution prepared with a predetermined concentration during an experiment or production process, which is used to simulate and measure the residual amount of a detergent sample.

[0074] The method for obtaining the concentration standard solution set is as follows:

[0075] a1: Divide the known standard solution into M sub-bottles and obtain a set of dilution multiples;

[0076] It should be understood that: the dilution multiple set consists of M dilution multiples that are equally spaced from each other; each dilution multiple in the dilution multiple set corresponds to the number of sub-filling bottles in a one-to-one relationship; the dilution multiple refers to the ratio of mixing a known standard solution with a solvent, and the solvent is preferably pure water;

[0077] a2: According to the relationship between the dilution factor and the solvent volume, determine the volume of solvent required to be added for each dilution of the known standard solution;

[0078] It should be noted that the relationship between the dilution multiple and the solvent volume is expressed by the formula:

[0079] For example, if 100 mL of a known standard solution is diluted to a 1:10 dilution, 100 mL of the known standard solution needs to be mixed with 900 mL of a solvent, then the dilution factor is 1:10;

[0080] a3: add the corresponding volume of solvent to the mth sub-bottle, set m=m+1, and jump back to step a2; the volume of solvent added to the mth sub-bottle is added at one time according to the dilution multiple.

[0081] a4: repeating the above steps a2 to a3 until the cycle ends when m=M, and obtaining a concentration standard solution set of known standard solutions, wherein the known concentration value corresponding to each concentration standard solution in the concentration standard solution set is divided according to a gradient concentration interval;

[0082] In this step, the known standard solution is diluted by a dilution multiple equal to each other at each interval, thereby forming a concentration standard solution set of the known standard solution, so that the known concentration value corresponding to each concentration standard solution in the concentration standard solution set is divided according to the gradient concentration interval.

[0083] Step 2: Detect and analyze the M concentration standard solutions in the concentration standard solution set to obtain absorbance values, and generate a standard curve graph based on the absorbance values ​​and the known concentration values ​​corresponding to each concentration standard solution;

[0084] In implementation, the method of detecting and analyzing the M concentration standard solutions in the concentration standard solution set to obtain absorbance includes:

[0085] Preset the wavelength value, temperature value and transmittance value of the optical detection device, batch test the M concentration standard solutions in the concentration standard solution set, and record the absorbance value measured by the optical detection device; the optical detection device includes but is not limited to a spectrophotometer, a gas chromatograph or a liquid chromatograph;

[0086] It should be noted that before the M concentration standard solutions are tested and analyzed, the optical detection equipment needs to be calibrated in advance to ensure the accuracy of the absorbance values ​​of the M concentration standard solutions;

[0087] Methods for generating a standard curve graph based on absorbance values ​​and known concentration values ​​corresponding to each concentration standard solution include:

[0088] Obtain the known concentration value corresponding to each concentration standard solution, and use each known concentration value as the horizontal axis data of the standard curve graph;

[0089] Obtain the absorbance value of each concentration of the standard solution, and use the absorbance value as the vertical axis data of the standard curve graph;

[0090] Using a drawing tool to mark the coordinate point of each concentration standard solution on a graph, and connect the coordinate points of each concentration standard solution to draw a standard curve graph; the drawing tool includes but is not limited to Excel, Matplotlib, etc.;

[0091] In this step, each concentration standard solution is detected and analyzed by an optical detection device to obtain the absorbance, and a standard curve is generated based on the absorbance and the known concentration value corresponding to each concentration standard solution, and a sample curve is drawn for the subsequent N detergent samples, and preparation is made for the analysis of the sample curve.

[0092] Step 3: obtaining concentration characteristic data of the nth detergent sample in the detergent sample set, inputting the concentration characteristic data into a pre-built machine learning model, and predicting a concentration value corresponding to the concentration characteristic data; the detergent sample set includes N detergent samples, N is an integer greater than zero, n∈N;

[0093] The concentration characteristic data includes wavelength value, transmittance value, absorbance value and temperature value, and each set of concentration characteristic data corresponds to a concentration value.

[0094] It should be noted that the wavelength value and transmittance value are parameters set by the optical detection device, and the absorbance value is the value obtained by the optical detection device for detecting the nth detergent sample; wherein, the larger the wavelength value, the larger the concentration value, and similarly, the larger the transmittance value or the absorbance value, the larger the concentration value; the temperature value is measured and obtained by the temperature sensor on the optical detection device;

[0095] The concentration value is the average concentration value of the nth detergent sample. In an experimental environment, the concentration values ​​of the detergent samples are measured multiple times by an optical detection device, and the average value is calculated to obtain the concentration value.

[0096] It should be noted that, as described in the background technology, the concentration value measurement method requires staff to continuously experiment with detergent samples to measure and obtain. Since a large number of detergent samples need to be tested, the time cost and labor cost of the test are increased. Therefore, this embodiment provides a prediction method for obtaining the concentration value in real time.

[0097] Furthermore, the method for constructing the machine learning model includes:

[0098] Convert a set of concentration characteristic data and concentration values ​​into a corresponding set of characteristic vectors;

[0099] Each set of feature vectors is used as input of a machine learning model, wherein the machine learning model uses a concentration value corresponding to a set of concentration feature data as output, uses a concentration value actually corresponding to a set of concentration feature data as a prediction target, and uses minimizing the loss function value of the machine learning model as a training target; training is stopped when the loss function value of the machine learning model is less than or equal to a preset target loss value, and the machine learning model is one of SVM regression, random forest regression, neural network regression, and the like;

[0100] The loss function value of the machine learning model is the mean square error; the loss function formula is: The model is trained with minimization as the goal. In the loss function, MSE is the loss function value of the machine learning model, e is the feature vector group number; E is the number of feature vector groups; K e is the concentration value corresponding to the e-th group of eigenvectors, is the actual concentration value corresponding to the e-th group of eigenvectors.

[0101] Step 4: Obtain a sample curve graph of the nth cleaning agent sample, and compare the sample curve graph with the standard curve graph to obtain the sample abnormal concentration coefficient of the nth cleaning agent;

[0102] It should be noted that the method for obtaining the sample curve graph of the nth detergent sample includes:

[0103] Obtain the predicted concentration value and absorbance value of the nth detergent sample;

[0104] Dividing the predicted concentration value and absorbance value of the nth detergent sample according to the gradient concentration interval to obtain a predicted concentration set and absorbance set of the nth detergent sample;

[0105] Using the concentration value in the concentration set of the nth detergent sample as the horizontal axis data, using the absorbance value in the absorbance set corresponding to the concentration set as the vertical axis data, using a drawing tool to plot the horizontal axis data and the vertical axis data on a chart, to obtain a sample curve chart of the nth detergent sample;

[0106] It should be noted that the drawing tool is the same as the drawing tool in step 2;

[0107] Further, the method of comparing the sample curve graph with the standard curve graph to obtain the abnormal concentration coefficient of the nth detergent sample includes:

[0108] The sample curve and the standard curve are divided into H regions according to the gradient concentration interval;

[0109] Compare the pixels in the same position area of ​​the sample curve graph and the standard curve graph one by one, and record the difference area between the sample curve graph and the standard curve graph;

[0110] The number of difference regions with differences is counted to obtain the total number of difference regions, and the total number of difference regions is used as the abnormal concentration coefficient of the nth detergent sample.

[0111] Step 5: Compare and analyze the abnormal concentration coefficient of the nth detergent sample with the abnormal concentration coefficient threshold to determine whether to generate a concentration analysis instruction; if the concentration analysis instruction is generated, generate a sample concentration coefficient of the nth detergent sample, and classify the nth detergent sample into safety levels according to the sample concentration coefficient;

[0112] In implementation, the method for determining whether to generate a concentration analysis instruction includes:

[0113] Preset an abnormal concentration coefficient threshold, and compare and analyze the abnormal concentration coefficient of each detergent sample with the abnormal concentration coefficient threshold;

[0114] If the abnormal concentration coefficient is less than or equal to the abnormal concentration coefficient threshold, a concentration analysis instruction is generated, sample characteristic data is acquired, and a sample concentration coefficient of the nth detergent sample is generated based on the sample characteristic data;

[0115] It should be noted that the sample characteristic data includes the wavelength value, absorbance value, concentration value and temperature value of the nth detergent sample;

[0116] In implementation, a method for generating a sample concentration coefficient of an nth cleaning agent sample based on sample characteristic data includes:

[0117] Get the wavelength value, absorbance value, concentration value and temperature value of the nth detergent sample, marked as Xg n , Bc n 、Nd n and Wd n ; and perform a formula calculation to obtain a sample concentration coefficient, the calculation formula of the sample concentration coefficient is:

[0118]

[0119] In the formula, YP n represents the sample concentration factor of the nth detergent sample, Xg n Indicates the absorbance value of the nth detergent sample, Bc n Represents the wavelength value of the nth detergent sample, Nd n Indicates the concentration value of the nth detergent sample, Wd n represents the temperature value of the nth detergent sample, p represents a natural constant, β1 represents a weighting factor of the absorbance value of the nth detergent sample; β2 represents a weighting factor of the wavelength value of the nth detergent sample; β3 represents a weighting factor of the concentration value of the nth detergent sample; β4 represents a weighting factor of the temperature value of the nth detergent sample;

[0120] If the abnormal concentration coefficient is greater than the abnormal concentration coefficient threshold, a sample abnormality instruction is generated; upon receiving the sample abnormality instruction, the management personnel analyzes the abnormal detergent sample to make the predicted concentration value conform to the detectable value range of the optical detection equipment.

[0121] In implementation, the method of classifying the safety level of the nth detergent sample according to the sample concentration coefficient includes:

[0122] b1: Get the sample concentration coefficient of the nth detergent sample;

[0123] b2: Set G concentration coefficient gradient intervals, and set K sample levels corresponding to the G concentration coefficient gradient intervals;

[0124] It should be understood that each concentration coefficient gradient interval has one and only one sample level associated with it;

[0125] b3: comparing the sample concentration coefficient of the nth detergent sample with each concentration coefficient gradient interval to obtain the concentration coefficient gradient interval into which the sample concentration coefficient of the nth detergent sample falls;

[0126] b4: Classify the nth detergent sample into a corresponding sample level according to the concentration coefficient gradient interval into which the sample concentration coefficient of the nth detergent sample falls; and set n=n+1, and jump back to step b1;

[0127] b5: repeating the above steps b1 to b4 until n=N, and the cycle ends, so that each of the cleaning agent samples is divided into K sample levels in turn;

[0128] In this step, the abnormal concentration coefficient of the nth detergent sample is compared with the abnormal concentration coefficient threshold to determine whether to generate a concentration analysis instruction; if a concentration analysis instruction is generated, the sample concentration coefficient of the nth detergent sample is obtained, and the nth detergent sample is divided into safety levels according to the sample concentration coefficient to determine the safety level of the residual amount of detergent used.

[0129] In this embodiment, a known standard solution is diluted according to a set of dilution multiples to obtain a concentration standard solution set; the known standard solution is a cleaning agent residue of a reference concentration; the concentration standard solution set includes M concentration standard solutions and a known concentration value corresponding to each concentration standard solution; the M concentration standard solutions in the concentration standard solution set are detected and analyzed to obtain absorbance values, and a standard curve graph is generated based on the absorbance values ​​and the known concentration values ​​corresponding to each concentration standard solution; the concentration characteristic data of the nth cleaning agent sample in the cleaning agent sample set is obtained, the concentration characteristic data is input into a pre-built machine learning model, and a concentration value corresponding to the concentration characteristic data is predicted; the cleaning agent sample set includes N cleaning agent samples, a sample curve graph of the nth cleaning agent sample is obtained, and the sample curve graph is compared with the standard curve graph to obtain abnormal concentration coefficient of the nth detergent sample; comparing and analyzing the abnormal concentration coefficient of the nth detergent sample with the abnormal concentration coefficient threshold to determine whether to generate a concentration analysis instruction; if a concentration analysis instruction is generated, obtaining sample characteristic data, and generating a sample concentration coefficient of the nth detergent sample based on the sample characteristic data; classifying the nth detergent sample into safety levels according to the sample concentration coefficient; in this embodiment, by obtaining data such as wavelength values, transmittance values, absorbance values, and temperature values, a machine learning model is used to quickly predict the concentration value, and at the same time, an abnormality detection mechanism is added to perform abnormal analysis on the detergent sample, thereby improving the speed and data accuracy of analyzing the residual amount of detergent used, and further determining the safety level of the residual amount of detergent used based on the sample concentration coefficient, which is beneficial to preventing high concentrations of detergent residues from causing potential damage to the environment.

[0130] When a large number of cleaning agent samples are tested in this embodiment, compared with the traditional manual experimental method, the machine learning model can automatically process the data and make predictions, which reduces a lot of experimental preparation and operation time, and reduces the need for manual operation, thereby improving work efficiency and accuracy, increasing the speed of analyzing the residual amount of cleaning agent, and reducing time and labor costs.

[0131] The formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weight factors in the formula and the preset thresholds in the analysis process are set by technicians in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the weight factor depends on the amount of sample data and the corresponding processing coefficient initially set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0132] Example 2

[0133] See also Figure 2 As shown, this embodiment provides an experimental system for detecting the residual amount of detergent used, including:

[0134] A dilution module, used to dilute a known standard solution according to a set of dilution multiples to obtain a set of concentration standard solutions; the known standard solution is a detergent residue of a reference concentration; the set of concentration standard solutions includes M concentration standard solutions and a known concentration value corresponding to each concentration standard solution;

[0135] The acquisition and analysis module is used to detect and analyze the M concentration standard solutions in the concentration standard solution set to obtain absorbance values, and generate a standard curve graph based on the absorbance values ​​and the known concentration values ​​corresponding to each concentration standard solution;

[0136] A prediction module, used to obtain concentration characteristic data of an nth detergent sample in a detergent sample set, input the concentration characteristic data into a pre-built machine learning model, and predict a concentration value corresponding to the concentration characteristic data; the detergent sample set includes N detergent samples, N is an integer greater than zero, n∈N;

[0137] A comparative analysis module, used for obtaining a sample curve graph of the nth detergent sample, and comparing the sample curve graph with the standard curve graph to obtain an abnormal concentration coefficient of the sample of the nth detergent;

[0138] The instruction generation module is used to compare and analyze the abnormal concentration coefficient of the nth detergent sample with the abnormal concentration coefficient threshold to determine whether to generate a concentration analysis instruction; if the concentration analysis instruction is generated, the sample concentration coefficient of the nth detergent sample is obtained, and the nth detergent sample is classified into a safety level according to the sample concentration coefficient.

[0139] Example 3

[0140] See also Figure 3As shown, this embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0141] The processor executes an experimental method for detecting the residual amount of detergent used in Example 1 by calling the computer program stored in the memory.

[0142] Example 4

[0143] See also Figure 4 As shown, this embodiment provides a computer-readable storage medium storing instructions. When the instructions are executed on a computer, the computer executes an experimental method for detecting the residual amount of detergent used in embodiment 1.

[0144] The formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weight factors in the formula and the preset thresholds in the analysis process are set by technicians in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the weight factor depends on the amount of sample data and the corresponding processing coefficient initially set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0145] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center via a wired network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0146] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein 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. Professional and technical personnel 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 this application.

[0147] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0148] In the several embodiments provided in the present application, 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 only schematic. For example, the division of the units is only one. There may be other division methods in actual implementation. For example, 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.

[0149] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0151] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0152] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0153] 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 protection scope of the present invention.

Claims

1. An experimental method for detecting the residual amount of cleaning agent used, It is characterized in that include: Step 1: diluting a known standard solution according to a dilution multiple set to obtain a concentration standard solution set; the known standard solution is a detergent residue of a reference concentration; the concentration standard solution set includes M concentration standard solutions and a known concentration value corresponding to each concentration standard solution; the dilution multiple set consists of M dilution multiples that are equally spaced from each other; Step 2: Detect and analyze the M concentration standard solutions in the concentration standard solution set to obtain absorbance values, and generate a standard curve graph based on the absorbance values ​​and the known concentration values ​​corresponding to each concentration standard solution; Step 3: obtaining concentration characteristic data of the nth detergent sample in the detergent sample set, inputting the concentration characteristic data into a pre-built machine learning model, and predicting a concentration value corresponding to the concentration characteristic data; the detergent sample set includes N detergent samples, N is an integer greater than zero, n∈N; Step 4: Obtain a sample curve graph of the nth detergent sample, and compare the sample curve graph with the standard curve graph to obtain an abnormal concentration coefficient of the nth detergent sample; Methods for obtaining the abnormal concentration coefficient of the nth detergent sample include: The sample curve and the standard curve are divided into H regions according to the gradient concentration interval; Compare the pixels in the same position area of ​​the sample curve graph and the standard curve graph one by one, and record the difference area between the sample curve graph and the standard curve graph; Counting the number of difference regions with differences to obtain the total number of difference regions, and using the total number of difference regions as the abnormal concentration coefficient of the nth detergent sample; Step 5: Compare and analyze the abnormal concentration coefficient of the nth detergent sample with the abnormal concentration coefficient threshold value to determine whether to generate a concentration analysis instruction; if a concentration analysis instruction is generated, obtain sample characteristic data, and generate a sample concentration coefficient of the nth detergent sample based on the sample characteristic data; classify the nth detergent sample into safety levels according to the sample concentration coefficient; the sample characteristic data includes a wavelength value, an absorbance value, a concentration value, and a temperature value of the nth detergent sample; The method of generating a sample concentration coefficient for the nth detergent sample based on the sample characteristic data includes: Get the wavelength value, absorbance value, concentration value and temperature value of the nth detergent sample, marked as Xg n , Bc n 、Nd n and Wd n , and perform formula calculation to obtain the sample concentration coefficient; the calculation formula of the sample concentration coefficient is: In the formula, YP n represents the sample concentration factor of the nth detergent sample, Xg n Indicates the absorbance value of the nth detergent sample, Bc n Represents the wavelength value of the nth detergent sample, Nd n Indicates the concentration value of the nth detergent sample, Wd n represents the temperature value of the nth detergent sample, p represents the natural constant, β 1 represents the weight factor of the absorbance value of the nth detergent sample; β 2 represents the weight factor of the wavelength value of the nth detergent sample; β 3 The weight factor representing the concentration value of the nth detergent sample; β 4 represents the temperature numerical weight factor of the nth detergent sample; Methods for determining whether to generate a concentration analysis instruction include: Preset an abnormal concentration coefficient threshold, and compare and analyze the abnormal concentration coefficient of each detergent sample with the abnormal concentration coefficient threshold; If the abnormal concentration coefficient is less than or equal to the abnormal concentration coefficient threshold, a concentration analysis instruction is generated; If the abnormal concentration coefficient is greater than the abnormal concentration coefficient threshold, a sample abnormal instruction is generated; According to the concentration analysis instruction, a sample concentration coefficient of the nth detergent sample is generated.

2. An experimental method for detecting the residual amount of cleaning agent according to claim 1, It is characterized in that The method to obtain the concentration standard solution set is as follows: a1: Divide the known standard solution equally into M sub-bottles, and obtain a dilution multiple set; each dilution multiple in the dilution multiple set is in one-to-one correspondence with the number of sub-bottles; a2: According to the relationship between the dilution factor and the solvent volume, determine the volume of solvent required to be added for each dilution of the known standard solution; a3: add the corresponding volume of solvent to the mth sub-bottle, set m=m+1, and jump back to step a2; a4: Repeat steps a2 to a3 above until the cycle ends when m=M, and obtain a concentration standard solution set of known standard solutions. The known concentration value corresponding to each concentration standard solution in the concentration standard solution set is divided according to the gradient concentration interval.

3. An experimental method for detecting the residual amount of cleaning agent according to claim 2, It is characterized in that The method of detecting and analyzing M concentration standard solutions in the concentration standard solution set to obtain absorbance includes: Preset the wavelength value, temperature value and transmittance value of the optical detection device, batch test the M concentration standard solutions in the concentration standard solution set, and record the absorbance value measured by the optical detection device; the optical detection device is a spectrophotometer, a gas chromatograph or a liquid chromatograph; Methods for generating a standard curve graph based on absorbance values ​​and known concentration values ​​corresponding to each concentration standard solution include: Obtain the known concentration value corresponding to each concentration standard solution, and use each known concentration value as the horizontal axis data of the standard curve graph; Obtain the absorbance value of each concentration of the standard solution, and use the absorbance value as the vertical axis data of the standard curve graph; Use the drawing tool to mark the coordinate points of each concentration standard solution on the chart, and connect the coordinate points of each concentration standard solution to draw a standard curve chart.

4. An experimental method for detecting the residual amount of cleaning agent according to claim 3, It is characterized in that The concentration characteristic data includes a wavelength value, a transmittance value, an absorbance value and a temperature value, and each group of the concentration characteristic data corresponds to a concentration value; The wavelength value and transmittance value are parameters set by the optical detection device, the absorbance value is the value obtained by the optical detection device for detecting the nth detergent sample; the temperature value is measured and obtained by the temperature sensor on the optical detection device; The concentration value is the average concentration value of the nth detergent sample; The method for constructing the machine learning model includes: Convert a set of concentration characteristic data and concentration values ​​into a corresponding set of characteristic vectors; Each group of feature vectors is used as the input of the machine learning model. The machine learning model uses the concentration value corresponding to a group of concentration feature data as the output, and the concentration value actually corresponding to a group of concentration feature data as the prediction target. Minimizing the loss function value of the machine learning model is used as the training target; training is stopped when the loss function value of the machine learning model is less than or equal to a preset target loss value. The machine learning model is one of the models such as SVM regression, random forest regression or neural network regression.

5. An experimental method for detecting the residual amount of cleaning agent according to claim 4, It is characterized in that The method of obtaining a sample curve graph of the nth detergent sample includes: Obtain the predicted concentration value and absorbance value of the nth detergent sample; Dividing the predicted concentration value and absorbance value of the nth detergent sample according to the gradient concentration interval to obtain a predicted concentration set and absorbance set of the nth detergent sample; The concentration value in the concentration set of the nth detergent sample is used as the horizontal axis data, and the absorbance value in the absorbance set corresponding to the concentration set is used as the vertical axis data. Use the drawing tool to plot the horizontal axis data and the vertical axis data on the chart to obtain the sample curve chart of the nth detergent sample.

6. An experimental method for detecting the residual amount of cleaning agent according to claim 5, It is characterized in that Methods for classifying the safety level of the nth cleaning agent sample according to the sample concentration coefficient include: b1: Get the sample concentration coefficient of the nth detergent sample; b2: Set G concentration coefficient gradient intervals, and set K sample levels corresponding to the G concentration coefficient gradient intervals; Each of the concentration coefficient gradient intervals has one and only one sample level associated and bound thereto; b3: comparing the sample concentration coefficient of the nth detergent sample with each concentration coefficient gradient interval to obtain the concentration coefficient gradient interval into which the sample concentration coefficient of the nth detergent sample falls; b4: Classify the nth detergent sample into a corresponding sample level according to the concentration coefficient gradient interval into which the sample concentration coefficient of the nth detergent sample falls; and set n=n+1, and jump back to step b1; b5: Repeat the above steps b1 to b4 until the cycle ends when n=N, so that each of the detergent samples is divided into K sample levels in turn.

7. An experimental system for detecting the residual amount of detergent used, used for implementing the experimental method for detecting the residual amount of detergent used according to any one of claims 1 to 6, It is characterized in that include: A dilution module, used to dilute a known standard solution according to a set of dilution multiples to obtain a set of concentration standard solutions; the known standard solution is a detergent residue of a reference concentration; the set of concentration standard solutions includes M concentration standard solutions and a known concentration value corresponding to each concentration standard solution; The acquisition and analysis module is used to detect and analyze the M concentration standard solutions in the concentration standard solution set to obtain absorbance values, and generate a standard curve graph based on the absorbance values ​​and the known concentration values ​​corresponding to each concentration standard solution; A prediction module, used to obtain concentration characteristic data of an nth detergent sample in a detergent sample set, input the concentration characteristic data into a pre-built machine learning model, and predict a concentration value corresponding to the concentration characteristic data; the detergent sample set includes N detergent samples, N is an integer greater than zero, n∈N; A comparative analysis module, used for obtaining a sample curve graph of the nth detergent sample, and comparing the sample curve graph with the standard curve graph to obtain an abnormal concentration coefficient of the nth detergent sample; The instruction generation module is used to compare and analyze the abnormal concentration coefficient of the nth detergent sample with the abnormal concentration coefficient threshold to determine whether to generate a concentration analysis instruction; if the concentration analysis instruction is generated, the sample concentration coefficient of the nth detergent sample is obtained, and the nth detergent sample is classified into a safety level according to the sample concentration coefficient.

Images