Method and system for predicting quality and performance of natural rubber by using particle sizes of rubber particles

Abstract

The invention discloses a method and system for predicting the quality and performance of natural rubber by using the particle size of rubber particles, and belongs to the technical field of data prediction.The method comprises the steps that fresh latex of a rubber tree is obtained; determining the particle size value of rubber particles of the fresh latex; selecting a target quality performance item from the candidate quality performance items according to a first selection operation of a user; determining one or more target prediction models from prediction models corresponding to the quality performance items according to the selected target quality performance items; importing the rubber particle size value into each target prediction model to obtain a prediction value output by the target prediction model; and determining a target quality performance parameter value according to the prediction value output by each target prediction model. According to the method, the quality and performance indexes of the natural rubber can be simply, conveniently, rapidly, economically and effectively obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data prediction, and particularly to a method and system for predicting quality and performance of natural rubber by using rubber particle size. BACKGROUND

[0002] Natural rubber is derived from latex produced by tapping rubber trees, and is an important industrial raw material with cis-1,4-polyisoprene as the main component, which is widely used in the fields of medical and health, transportation, aerospace, national defense equipment, and special equipment manufacturing.

[0003] Tensile strength is one of the important indicators for evaluating the mechanical properties of natural rubber, and is closely related to the rubber molecular weight and the content of non-rubber components such as protein. The value has an important influence on the physical and mechanical properties of natural rubber and product production.

[0004] Therefore, the determination of the tensile strength of natural rubber has become an important part of evaluating the quality and performance of natural rubber. At present, the determination of the tensile strength index of natural rubber needs to go through many links such as latex coagulation and drying, vulcanization of raw rubber samples, rubber mixing, detection by a vulcanization analyzer, and tensile strength determination of vulcanized rubber. The testing process is complicated, the equipment is multiple, the time is long, the cost is high, the environment is polluted, and professional technical personnel are needed to support.

[0005] The information disclosed in this BACKGROUND section is only intended to increase an understanding of the general context in which the present application can be practiced. It is not admitted that any of the information provided in this section constitutes prior art. SUMMARY

[0006] The present application aims to provide a method and system for predicting the quality and performance of natural rubber by using rubber particle size.

[0007] To achieve the above-mentioned purpose, in a first aspect, the present application provides a method for predicting the quality and performance of natural rubber by using rubber particle size, comprising: obtaining fresh latex of rubber trees; determining the rubber particle size value of the latex; according to the first selection operation of a user, selecting a target quality performance item from candidate quality performance items; according to the selected target quality performance item, determining one or more target prediction models from the prediction models corresponding to the quality performance items; inputting the rubber particle size value into each target prediction model to obtain the prediction value output by the target prediction model; determining the target quality performance parameter value according to the prediction value output by each target prediction model; wherein the target quality performance parameter prediction value indicates the quality or performance of natural rubber.

[0008] In an embodiment of the present application, the candidate quality performance item comprises one or more of the following: rubber weight average molecular weight, rubber viscosity average molecular weight, plasticity index, acetone extract, tensile strength, 500% modulus, tear strength.

[0009] In an embodiment of the present application, the method further comprises: setting a plurality of quality performance items; determining the plurality of quality performance items from the test latex sample; determining the rubber particle size value of the latex from the same batch of test latex sample; constructing a regression equation of the rubber particle size value and the quality performance item for the rubber particle size value; evaluating each regression equation, and determining the candidate quality performance item according to the evaluation result of the regression equation.

[0010] In an embodiment of the present application, the regression equation of the rubber particle size and the rubber weight average molecular weight is Y = 2614561 - 824703x, wherein x represents the rubber particle size and Y represents the weight average molecular weight; the regression equation of the rubber particle size and the rubber viscosity average molecular weight is Y = 2132640 - 702682x, wherein x represents the rubber particle size and Y represents the viscosity average molecular weight; the regression equation of the rubber particle size and the plasticity index is Y = 54.106 - 17.151x, wherein x represents the rubber particle size and Y represents the plasticity index; the regression equation of the rubber particle size and the acetone extract is Y = 1.4921 + 1.6494x, wherein x represents the rubber particle size and Y represents the acetone extract; the regression equation of the rubber particle size and the tensile strength is Y = 30.77 - 13.03x, wherein x represents the rubber particle size and Y represents the tensile strength; the regression equation of the rubber particle size and the 500% modulus is Y = 4.2981 - 1.5602x, wherein x represents the rubber particle size and Y represents the 500% modulus; the regression equation of the rubber particle size and the vulcanized rubber tear strength is Y = 32.356 - 6.829x, wherein x represents the rubber particle size and Y represents the vulcanized rubber tear strength.

[0011] In an embodiment of the present application, the generating of the target quality performance parameter value according to the prediction value output by each target prediction model comprises: obtaining a preset weight corresponding to the target quality performance item; determining a weight corresponding to the prediction value output by each prediction model according to the weight corresponding to the target quality performance item; and determining the target quality performance parameter value based on each prediction value and the corresponding weight.

[0012] In an embodiment of the present application, the method further comprises: collecting latex samples of rubber trees; determining the rubber particle size of the first group of latex samples; determining the quality performance item of the rubber prepared from the second group of latex samples as the determination of the quality performance parameter value; and constructing a prediction model corresponding to the quality performance item for the determination of the rubber particle size and the determination of the quality performance parameter value.

[0013] In an embodiment of the present application, the method for determining the rubber particle size of the first group of latex samples comprises: taking 10-15 μL of each latex sample into a test tube containing 100 mmol / L Tris-HCl buffer; taking 100-150 μL of the latex with buffer from the test tube; using a laser scattering particle size distribution analyzer to determine the average volume particle size of the rubber particles by using a number basis.

[0014] In an embodiment of the present application, the method for determining the quality performance parameters of the rubber prepared from the second group of latex samples comprises: coagulating fresh latex with acid in a container and placing for 24 hours; using a crepe sheet machine to make a sheet, drying, and then drying in an oven at 70°C for 24 hours to obtain a raw rubber sample; using a gel permeation chromatograph to determine the weight average molecular weight and viscosity average molecular weight of the rubber; using a rapid plasticometer to determine the plasticity initial value; using a thermal desorption-gas chromatography-mass spectrometry method to determine the raw rubber ketone solubles; using a tensile testing machine to determine the tensile strength and 500% modulus of the vulcanized rubber; and using a tear test method to determine the tear strength of the vulcanized rubber.

[0015] In an embodiment of the present application, the method further comprises: inputting the determined rubber particle size of the first group of samples into the constructed prediction model to obtain an evaluated prediction value; performing T-test on the evaluated prediction value and the determined quality performance parameter value of the second group of samples; and judging the significant difference between the evaluated prediction value and the determined quality performance parameter value according to the result of the T-test.

[0016] In a second aspect, the present application provides a system for predicting the quality and performance of natural rubber using rubber particle size, comprising: an acquisition unit configured to acquire latex from rubber trees; a determination unit configured to determine the rubber particle size of the latex; a selection unit configured to select a target quality performance item from candidate quality performance items according to a first selection operation of a user; a first determination unit configured to determine one or more target prediction models from prediction models corresponding to the target quality performance item; a prediction unit configured to input the rubber particle size into each target prediction model to obtain a prediction value output by each target prediction model; and a second determination unit configured to determine a target quality performance parameter value according to the prediction value output by each target prediction model; wherein the target quality performance parameter prediction value indicates the quality or performance of the natural rubber.

[0017] Compared with the prior art, the application has the advantages that the method for predicting the quality and performance of natural rubber by using the particle size of rubber particles is provided, and the method can obtain the quality and performance indexes of natural rubber simply, quickly, economically and effectively after tapping, and can solve the problems of high cost, long cycle, quality fluctuation between batches and the need of professional technical support in conventional testing, and can select the specific quality or performance item to be predicted flexibly, and determine the target quality and performance parameter value according to the selected quality or performance item, so as to more accurately represent the quality and performance of natural rubber and improve the prediction accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 Comparison of the function model for predicting the weight average molecular weight of rubber by using the particle size and the simulation value and the observation value;

[0019] Figure 2 Comparison of the function model for predicting the viscosity average molecular weight of rubber by using the particle size and the simulation value and the observation value;

[0020] Figure 3 Comparison of the function model for predicting the plastic initial value by using the particle size and the simulation value and the observation value;

[0021] Figure 4 Comparison of the function model for predicting the acetone soluble matter by using the particle size and the simulation value and the observation value;

[0022] Figure 5 Comparison of the function model for predicting the tensile elongation by using the particle size and the simulation value and the observation value;

[0023] Figure 6 Comparison of the function model for predicting the 500% tensile modulus by using the particle size and the simulation value and the observation value;

[0024] Figure 7 Comparison of the function model for predicting the tear strength by using the particle size and the simulation value and the observation value;

[0025] Figure 8 A step flowchart of the method for predicting the quality and performance of natural rubber by using the particle size of rubber particles provided by the embodiment of the application;

[0026] Figure 9 A module block diagram of the system for predicting the quality and performance of natural rubber by using the particle size of rubber particles provided by the embodiment of the application. DETAILED DESCRIPTION

[0027] The specific embodiments of the application are described in detail below with reference to the accompanying drawings, but it should be understood that the protection scope of the application is not limited by the specific embodiments.

[0028] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, technologies, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0029] It is to be understood that the terminology "includes", "has", "holds", "contains" and / or "comprising", "including", "having" and / or "fronts" when used in this specification and in the following claims, specifies the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0030] It is also to be understood that the terminology "and / or" where used in this specification and in the following claims is used to describe one or more of the associated listed items, in any combination with one another, and all possible combinations.

[0031] As used in this specification and in the claims, the term "if" can be construed to mean "when" or "upon" or "in response to determining" or "in response to detecting," that a stated condition precedes.

[0032] In addition, the terms "first", "second", "third", etc. in the description of the present application and the following claims are only used to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0033] Reference in the specification to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrases "in one embodiment", "in some embodiments", "in other embodiments", "in additional embodiments", etc. in various places in the specification are not necessarily all referring to the same embodiment, although they can. The terms "comprising", "including", "having" and their variants, mean "including but not limited to", unless otherwise expressly specified and / or limited by the context.

[0034] Reference in the specification to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrases "in one embodiment", "in some embodiments", "in other embodiments", "in additional embodiments", etc. in various places in the specification are not necessarily all referring to the same embodiment, although they can. The terms "comprising", "including", "having" and their variants, mean "including but not limited to", unless otherwise expressly specified and / or limited by the context. Figure 8 The embodiments of the present application provide a method for predicting the quality and performance of natural rubber by using rubber particle size, which specifically comprises steps 101-106.

[0035] Step 101: Obtain fresh latex of rubber trees.

[0036] Step 102: Measure the rubber particle size value of the fresh latex.

[0037] Step 103: selecting a target quality performance item from the candidate quality performance items according to the first selection operation of the user.

[0038] Step 104: determining one or more target prediction models from the prediction models corresponding to the quality performance items according to the selected target quality performance item.

[0039] Step 105: inputting the rubber particle size value into each target prediction model to obtain a predicted value output by the target prediction model.

[0040] Step 106: determining a target quality performance parameter value according to the predicted value output by each target prediction model.

[0041] The target quality performance parameter predicted value indicates the quality or performance of the natural rubber.

[0042] Optionally, the above step 101 can include sampling the fresh latex of the rubber tree, and placing the sample in an ice bath and a refrigerator to bring back to the laboratory.

[0043] Optionally, step 102 can include collecting the fresh latex of the rubber tree, and measuring the rubber particle size in the latex by using a particle size analyzer.

[0044] Optionally, the above pre-constructed prediction model can adopt various forms or structures. For example, the above pre-constructed prediction model can be expressed in the form of a regression equation, or can be trained by using a neural network as a basic model.

[0045] In some embodiments, the candidate quality performance items include one or more of the following: rubber weight average molecular weight, rubber viscosity average molecular weight, plastic initial value, acetone solubles, tensile strength, 500% modulus, and tear strength of vulcanized rubber.

[0046] As an example, candidate quality performance items can be displayed, and the user can select a target quality performance item from the candidate quality performance items. The target quality performance item can be an item used to determine a target quality performance parameter value.

[0047] In this embodiment, a prediction model can be pre-constructed for each quality performance item. For example, for the rubber weight average molecular weight, a prediction model is constructed, the input of which is the rubber particle size, and the output is the predicted weight average molecular weight.

[0048] The user can select one or more prediction models to participate in prediction.

[0049] As an example, the user can select three prediction models to participate in the prediction. The three models output prediction values respectively, i.e. three prediction values (e.g. rubber average molecular weight, plasticity initial value, acetone solubles) are obtained. According to the three prediction values, the target quality performance parameter value can be generated, for example, the three prediction values can be weighted and averaged to obtain the target quality performance parameter value.

[0050] Therefore, the method of the present application not only does not require various special equipment and instruments, solves the problems of high cost, long cycle, quality fluctuation between batches and the need for professional technical personnel to support in conventional testing, and can obtain the quality and performance indicators of natural rubber simply, quickly and economically and effectively after tapping; moreover, the specific quality performance items that need to be predicted can be flexibly selected, and the target quality performance parameter value is determined according to the selected quality performance items, so as to more accurately represent the quality and performance of natural rubber and improve the accuracy of prediction.

[0051] In some embodiments, the method further comprises: setting a plurality of quality performance items; determining the plurality of quality performance items from the test latex sample; determining the rubber particle size value of the latex from the same batch of test latex sample; constructing a regression equation of the rubber particle size value and the quality performance item for the rubber particle size value; evaluating each regression equation, and determining the candidate quality performance item according to the evaluation result of the regression equation.

[0052] As an example, evaluating the regression equation means a series of checks on the regression equation to see if the regression equation is suitable for the data and if the model assumption is correct. By checking the residual plot, normality test, homoscedasticity test, etc., it is determined whether the model has problems such as bias, heteroscedasticity, nonlinearity, etc. If problems are found in the inspection, the model may need to be adjusted or the data may need to be transformed. Therefore, the prediction ability and goodness of fit of the model can be measured by statistical indicators.

[0053] The evaluation indicators include R 2 (determination coefficient, indicating the proportion of variation explained by the model), mean square error (MSE), root mean square error (RMSE), accuracy, recall rate, etc.

[0054] Therefore, from a plurality of quality performance of natural rubber, the quality performance parameter that has a greater correlation with the quality of natural rubber and has a greater impact can be determined, and a prediction model between the quality performance parameter and the rubber particle size is constructed, thereby improving the rationality and accuracy of the prediction model.

[0055] In some embodiments, the generating the target quality performance parameter value according to the predicted values output by the respective target prediction model comprises: obtaining a preset weight corresponding to the target quality performance item; determining a weight corresponding to the predicted value output by each prediction model according to the weight corresponding to the target quality performance item; and determining the target quality performance parameter value based on the respective predicted value and the corresponding weight.

[0056] Thus, the weighting of various quality performance parameter items can be realized, an accurate target quality performance parameter value can be determined, and data accuracy can be improved.

[0057] In some embodiments, the regression equation of the rubber particle size and the rubber weight average molecular weight is Y=2614561-824703x, where x represents the rubber particle size and Y represents the rubber weight average molecular weight.

[0058] In some embodiments, the regression equation of the rubber particle size and the rubber viscosity average molecular weight is Y=2132640-702682x, where x represents the rubber particle size and Y represents the rubber viscosity average molecular weight.

[0059] In some embodiments, the regression equation of the rubber particle size and the plasticity initial value is Y=54.106-17.151x, where x represents the rubber particle size and Y represents the plasticity initial value.

[0060] In some embodiments, the regression equation of the rubber particle size and the acetone soluble is Y=1.4921+1.6494x, where x represents the rubber particle size and Y represents the acetone soluble.

[0061] In some embodiments, the regression equation of the rubber particle size and the tensile strength is Y=30.77-13.03x, where x represents the rubber particle size and Y represents the tensile strength.

[0062] In some embodiments, the regression equation of the rubber particle size and the 500% modulus is Y=4.2981-1.5602x, where x represents the rubber particle size and Y represents the 500% modulus.

[0063] In some embodiments, the regression equation of the rubber particle size and the tear strength of the vulcanized rubber is Y=32.356-6.829x, where x represents the rubber particle size and Y represents the tear strength of the vulcanized rubber.

[0064] In some embodiments, the method further comprises: collecting latex samples of rubber trees; determining the rubber particle size of a first group of latex samples; determining the quality performance items of rubber prepared from a second group of latex samples as the determination of the quality performance parameter value; and constructing a prediction model corresponding to the quality performance item for the determination of the rubber particle size and the determination of the quality performance parameter value.

[0065] In some embodiments, the method for determining the rubber particle size of the first group of latex samples comprises: taking 10-15 μL of each latex sample into a test tube containing 100 mmol / L Tris-HCl buffer; taking 100-150 μL of the latex with buffer from the test tube; using a laser scattering particle size distribution analyzer to determine the average volume particle size of the rubber particles.

[0066] In some embodiments, the method for determining the quality and performance of the rubber prepared from the second group of latex samples as the quality and performance parameter values comprises: coagulating fresh latex in a container with acid and placing it for 24 hours; using a crepe machine to press the sample into a sheet, drying it, and then drying it in an oven at 70°C for 24 hours to obtain a raw rubber sample; using a gel permeation chromatograph to determine the weight average molecular weight and viscosity average molecular weight of the rubber; using a rapid plastometer to determine the initial plasticity; using a thermal desorption-gas chromatography-mass spectrometry method to determine the raw rubber ketone solubles; using a tensile testing machine to determine the tensile strength and 500% modulus of the vulcanized rubber; and using a tear test method to determine the tear strength of the vulcanized rubber.

[0067] As an example, the model construction step includes:

[0068] First step, the method for determining the rubber particle size of the fresh rubber latex of rubber trees. First, the fresh rubber latex of rubber trees is sampled and placed in an ice bath and a refrigerator for transportation to the laboratory. 10-15 μL of each latex sample is taken into a test tube containing 100 mmol / L Tris-HCl buffer. Then, 100-150 μL of the latex with buffer is taken from the test tube, and a laser scattering particle size distribution analyzer is used to determine the average volume particle size of the rubber particles.

[0069] Second step, in the same batch of samples as in the first step, fresh latex is coagulated in a container with acid and placed for about 24 hours. A crepe machine is used to press the sample into a sheet, which is dried and then dried in an oven at 70°C for about 24 hours to obtain a raw rubber sample. A gel permeation chromatograph (GPC) is used to determine the weight average molecular weight and viscosity average molecular weight of the rubber. A rapid plastometer is used to determine the initial plasticity. A thermal desorption-gas chromatography-mass spectrometry method is used to determine the raw rubber ketone solubles. A tensile testing machine is used to determine the tensile strength and 500% modulus of the vulcanized rubber. A tear test method is used to determine the tear strength of the vulcanized rubber.

[0070] Third step, using R 4.5.0 software to construct a regression equation for the rubber particle size and the quality and performance indicators of the rubber, such as the weight average molecular weight, the viscosity average molecular weight, the initial plasticity, the ketone solubles, the tensile strength, the 500% modulus, and the tear strength, to carry out model prediction.

[0071] As an example, lm function can be used for analysis, confint function for calculating confidence interval, performance package for model diagnosis, statistical values based on the prediction model for evaluating model performance, and prediction model function establishment.

[0072] lm is the abbreviation of Linear Model, which is a function in R language for fitting linear regression models; function: estimate the parameters of linear models by least squares method, used to analyze the linear relationship between dependent variable and one or more independent variables.

[0073] confint is the abbreviation of "confidence interval", which is the confidence interval; function: used to calculate the confidence interval of model parameters. The confidence interval represents the range in which the true value of the model parameter may be within a certain confidence level (such as 95%).

[0074] performance is a R language package, which is used for model diagnosis and performance evaluation; function: provides a series of functions to evaluate the goodness of fit, accuracy and reliability of statistical models. For example, it can calculate the R 2 value (determination coefficient), AIC (Akaike information criterion), BIC (Bayesian information criterion) and other statistical indicators of the model, and check whether the assumptions of the model are met (such as normality, homoscedasticity, etc.).

[0075] The method provided by the present application does not require a variety of special equipment and instruments, and solves the problems of high cost, long cycle, quality fluctuation between batches and the need for professional technical personnel to support the conventional test of natural rubber quality and performance; the present application can obtain the quality and performance indicators of natural rubber from the fresh latex of rubber trees after tapping, which is simple, fast, economical and effective.

[0076] In some embodiments, the method further comprises: inputting the rubber particle size measurement value of the first group of samples into the constructed prediction model to obtain the to-be-evaluated prediction value; performing T test on the to-be-evaluated prediction value and the measured quality performance parameter value of the second group of samples; and judging the significant difference between the to-be-evaluated prediction value and the measured quality performance parameter value according to the T test result.

[0077] T test is a statistical hypothesis testing method used to compare whether the means of two groups of data have significant differences.

[0078] As an example, input the measured values and predicted values as two sets of data, respectively; use the correlation function (such as ggboxplot or ggbarplot) in the ggpubr package to draw a graph, and automatically add the results of the T-test (such as the significance mark) on the graph; according to the p-value of the T-test, judge whether there is a significant difference between the means of the two sets of data (usually, a p-value less than 0.05 indicates a significant difference).

[0079] In this way, the accuracy of the model prediction can be verified.

[0080] Test Example 1

[0081] In 2024, samples were taken from a rubber plantation test site in a certain test farm, and the method of the present application was used to predict the quality and performance indicators of natural rubber.

[0082] The method of predicting the quality and performance indicators of natural rubber using fresh latex rubber particle size is carried out according to the following steps:

[0083] I. Collect fresh latex from rubber trees and measure the particle size of the rubber particles;

[0084] II. According to the following prediction model function, the prediction of the quality and performance indicators of natural rubber is completed, that is:

[0085] 1. The regression equation of particle size and rubber weight average molecular weight is:

[0086] Y = 2614561 - 824703x (p = 0.006512 < 0.001)

[0087] 2. The regression equation of particle size and rubber viscosity average molecular weight is:

[0088] Y = 2132640 - 702682x (p = 0.01125 < 0.05)

[0089] 3. The regression equation of particle size and plastic initial value is:

[0090] Y = 54.106 - 17.151x (p = 0.004251 < 0.01)

[0091] 4. The regression equation of particle size and acetone solubles is:

[0092] Y = 1.4921 + 1.6494x (p = 0.003024 < 0.01)

[0093] 5. The regression equation of particle size and tensile strength is:

[0094] Y = 30.77 - 13.03x (p = 6.686e-06 < 0.001)

[0095] 6. The regression equation between particle size and 500% constant tensile stress is:

[0096] Y=4.2981-1.5602x(p=3.346e-05<0.001)

[0097] 7. The regression equation for particle size and tear strength is:

[0098] Y=32.356-6.829x(p=0.003377<0.01)

[0099] The method for determining the particle size of rubber particles in rubber tree latex in step one of this embodiment is as follows: First, fresh latex samples are taken from rubber trees and brought back to the laboratory in an ice bath and refrigerator. 10-15 μL of each latex sample is added to a test tube containing 100 mmol / L Tris-HCl buffer. Then, 100-150 μL of latex with buffer is drawn from the test tube and measured using a laser scattering particle size analyzer with a quantitative standard. Finally, the average volumetric particle size of the rubber particles is calculated.

[0100] The method for establishing the prediction model function in step two above:

[0101] 1. In step one of the batches of samples, fresh latex was coagulated with acid in a container and left for about 24 hours. It was then pressed into sheets using a crepe machine, air-dried, and finally dried in an oven at 70°C for about 24 hours to obtain raw rubber samples. The weight-average molecular weight and viscosity-average molecular weight of the rubber were determined using gel permeation chromatography. The initial plasticity value was determined using a rapid plasticity tester. The acetone-soluble content of the raw rubber was determined using thermal desorption-gas chromatography-mass spectrometry. The tensile strength and 500% elongation stress of the vulcanized rubber were determined using a tensile testing machine. The tear strength of the vulcanized rubber was determined using a tear test.

[0102] 2. Using R4.5.0 software, regression equations were constructed for quality and performance indicators such as rubber particle size, rubber weight-average molecular weight, rubber viscosity-average molecular weight, initial plasticity, acetone solubility, tensile strength, 500% tensile stress, and tear strength, and model prediction was carried out.

[0103] Third, the established prediction model equations are analyzed using the lm function, the performance toolkit is used for model diagnosis, the model performance is evaluated based on the statistical values ​​of the prediction model, and the prediction model function is established.

[0104] The above-mentioned fresh latex samples need to be measured to obtain the predicted natural rubber quality and performance index values ​​through the corresponding prediction model function of this embodiment.

[0105] The present embodiment takes the rubber particle size, rubber weight average molecular weight, rubber viscosity average molecular weight, plasticity initial value, acetone solubles, tensile strength, 500% modulus, tear strength and other eight kinds of measured natural rubber quality and performance indexes of rubber tree fresh latex samples as the basis, through regression analysis, it is determined that the rubber particle size and the above seven kinds of natural rubber quality and performance indexes present significant relationship (p<0.05), and the present application can predict the natural rubber quality and performance indexes based on the rubber particle size of the latex through the prediction model function equation.

[0106] Test example 2

[0107] In 2024, the rubber weight average molecular weight index of rubber trees in a test farm is predicted.

[0108] Fresh rubber latex of rubber trees is obtained from a test farm, and the sample is placed in an ice bath and taken back to the laboratory in a refrigerator. 10-15 μL of fresh latex is taken from each sample and added to a test tube containing 100 mmol / L Tris-HCl buffer to prepare the sample to be tested. The average particle size of the rubber particles is measured and calculated using a laser scattering particle size distribution analyzer. At the same time, in the same batch of samples, fresh latex is added to a container and coagulated with acid, and placed for about 24 hours. A sheet machine is used to press the sample, and after drying, the temperature of the oven is set to 70°C for about 24 hours to obtain a raw rubber test sample. The rubber weight average molecular weight index value is measured using a gel permeation chromatograph (GPC).

[0109] The prediction model function equation Y=2614561-824703x based on the rubber particle size and the rubber weight average molecular weight is used to predict the rubber weight average molecular weight index value. For example, the rubber particle sizes are 0.8831400, 0.9814267, 1.0194600, 0.9892433, 1.0335300, 1.0728967, 1.1093400, 1.0758400, 1.0226133, 1.0083667, 1.0430833, 1.1395933 and 1.0278667, respectively. According to the prediction model function, the simulated values of the rubber weight average molecular weight are 1886233, 1805175, 1773809, 1798729, 1762206, 1729740, 1699685, 1727313, 1771209, 1782958, 1754327, 1674735 and 1766876, respectively. Further, the T test (T-test) is performed on the rubber weight average molecular weight test value and the weight average molecular weight simulated value using the R software ggpubr toolkit. Figure 1 The T test result shows that p=0.26>0.05, i.e. the difference between the simulated value and the observed value of the rubber weight average molecular weight is not significant, which indicates that the prediction model has statistical significance, and the method of the present application realizes the prediction of the rubber weight average molecular weight index value.

[0110] Test Example 3

[0111] Predicting the rubber average molecular weight of rubber trees in a test farm in 2024.

[0112] Fresh rubber latex was obtained from a test farm, and the sample was placed in an ice bath and taken back to the laboratory in a cooler. 10-15 μL of fresh latex was taken from each sample and added to a test tube containing 100 mmol / L Tris-HCl buffer to prepare the sample to be tested. The average particle size of the rubber particles in the latex was measured and calculated using a laser scattering particle size distribution analyzer. At the same time, in the same batch of samples, fresh latex was added to a container and coagulated with acid, and left to stand for about 24 hours. A sheeting machine was used to press the sample, and after drying, the sample was dried in an oven at a temperature of 70°C for about 24 hours to obtain a raw rubber test sample. The rubber average molecular weight index value was measured using a gel permeation chromatograph.

[0113] The rubber average molecular weight index value was predicted using the prediction model function equation Y=2132640-702682x based on the rubber particle size and the rubber average molecular weight. For example, the rubber particle sizes were 0.8831400, 0.9814267, 1.0194600, 0.9892433, 1.0335300, 1.0728967, 1.1093400, 1.0758400, 1.0226133, 1.0083667, 1.0430833, 1.1395933 and 1.0278667, respectively. According to the prediction model function, the simulated values of the rubber average molecular weight were 1512073, 1443009, 1416284, 1437517, 1406397, 1378735, 1353127, 1376667, 1414068, 1424079, 1399684, 1331868 and 1410377, respectively. The rubber average molecular weight test values and the rubber average molecular weight simulated values were subjected to T-test using the R software ggpubr toolkit Figure 2 ), and the T-test result showed that p=0.12>0.05, i.e. the difference between the simulated value and the observed value of the rubber average molecular weight was not significant, indicating that the prediction model had statistical significance, and the method of the present application realized the prediction of the rubber average molecular weight index value.

[0114] Test Example 4

[0115] Predicting the raw rubber plasticity initial value of rubber trees in a test farm in 2024

[0116] Fresh latex of rubber tree was obtained from a test field, and the sample was placed in an ice bath and taken back to the laboratory in a refrigerator. 10-15 μL of fresh latex was taken from each sample and added to a test tube containing 100 mmol / L Tris-HCl buffer to prepare the sample to be tested. The average particle size of the rubber particles in the latex was determined and calculated using a laser scattering particle size distribution analyzer. At the same time, in the same batch of samples, fresh latex was taken and acid coagulation was performed in a container, and the sample was placed for about 24 hours. A crepe sheet machine was used to press the sample, and after drying, the temperature of the oven was set to 70°C and the sample was dried for about 24 hours to obtain a raw rubber test sample. A rapid plasticity tester was used to determine the initial plasticity of the raw rubber.

[0117] The initial plasticity was predicted using a prediction model function equation Y = 54.106-17.151x based on the particle size of the rubber particles and the initial plasticity of the raw rubber. For example, when the particle size of the rubber particles was 1.02699, 0.97578, 1.01346, 0.88314, 1.02306, 1.00483, 0.94343, 1.07384, 1.12068, 1.00865, 1.03882, 1.01691, 1.02920 and 1.07833, the simulated values of the initial plasticity were 36.49209, 37.37045, 36.72420, 38.95927, 36.55956, 36.87222, 37.92517, 35.68851, 34.88516, 36.80664, 36.28920, 36.66503, 36.45425 and 35.61156, respectively, according to the prediction model function. The T test of the initial plasticity test value and the initial plasticity simulation value was further applied using the R software ggpubr toolkit ( Figure 3 ), and the T test result showed that p = 0.79 > 0.05, i.e. the difference between the simulated value and the observed value of the initial plasticity was not significant, indicating that the prediction model had statistical significance, and the method of the present application realized the prediction of the initial plasticity of natural rubber.

[0118] Test Example 5

[0119] Prediction of raw rubber acetone solubles of rubber trees in a test field in 2024

[0120] Fresh latex was obtained from a test field, and the sample was placed in an ice bath and taken back to the laboratory in a cooler. 10-15 μL of fresh latex was taken from each sample and added to a test tube containing 100 mmol / L Tris-HCl buffer to prepare the sample to be tested. The average particle size of the rubber particles in the latex was determined and calculated using a laser scattering particle size distribution analyzer. At the same time, in the same batch of samples, fresh latex was coagulated by adding acid to the container and left to stand for about 24 hours. A sheeting machine was used to press the sample, and after drying, the sample was dried in an oven set at 70°C for about 24 hours to obtain a raw rubber test sample. Soxhlet extraction and thermal desorption-gas chromatography-mass spectrometry were used to determine the raw rubber acetone extract.

[0121] The acetone extract was predicted using a prediction model function equation Y = 1.4921 + 1.6494x based on the particle size of the rubber particles and the raw rubber acetone extract. For example, when the particle size of the rubber particles was 1.02699, 0.97578, 1.01346, 0.88314, 1.02306, 1.00483, 0.94343, 1.07384, 1.12068, 1.00865, 1.03882, 1.01691, 1.02920 and 1.07833, respectively, the simulated values of the raw rubber acetone extract were 3.186017, 3.101546, 3.163695, 2.948751, 3.179530, 3.149461, 3.048199, 3.263297, 3.340555, 3.155767, 3.205530, 3.169386, 3.189657 and 3.270698, respectively, according to the prediction model function. The T test of the acetone extract test value and the acetone extract simulated value was further carried out using the R software ggpubr toolkit ( Figure 4 ). The T test result showed that p = 0.97 > 0.05, i.e. the difference between the simulated value and the observed value of the acetone extract was not significant, indicating that the prediction model had statistical significance, and the method of the present application realized the prediction of the acetone extract of natural rubber.

[0122] Test Example 6

[0123] Prediction of the rubber tensile strength of rubber trees in a test field in 2024

[0124] Fresh latex of rubber tree was obtained from a test field, and the sample was placed in an ice bath and taken back to the laboratory in a refrigerator. 10-15 μL of fresh latex was taken from each sample and added to a test tube containing 100 mmol / L Tris-HCl buffer to prepare the sample to be tested. The average particle size of the rubber particles in the latex was determined and calculated using a laser scattering particle size distribution analyzer. At the same time, in the same batch of samples, fresh latex was coagulated by adding acid to the container and left to stand for about 24 hours. A sheeting machine was used to press the sheet, and after drying, the temperature of the oven was set to 70°C and dried for about 24 hours to obtain the raw rubber test sample. The vulcanized rubber sample was prepared according to the conventional formula, and the tensile strength of the vulcanized rubber was measured using a tensile strength tester.

[0125] The tensile strength was predicted using the prediction model function equation Y = 30.77-13.03x based on the particle size of the rubber particles and the tensile strength. For example, the particle sizes of the rubber particles were 1.02699, 0.97578, 1.01346, 0.88314, 1.02306, 1.00483, 0.94343, 1.07384, 1.12068, 1.00865, 1.03882, 1.01691, 1.02920 and 1.07833, respectively. According to the prediction model function, the simulated values of the tensile strength were 17.38832, 18.05563, 17.56466, 19.26269, 17.43957, 17.67711, 18.47706, 16.77782, 16.16750, 17.62729, 17.23418, 17.51971, 17.35957 and 16.71936, respectively. Further application of the R software ggpubr toolkit for T test of the tensile strength test value and the tensile strength simulation value Figure 5 ), the T test result showed that p = 0.75 > 0.05, i.e. the difference between the simulated value and the observed value of the tensile strength was not significant, indicating that the prediction model had statistical significance, and the method of the present application realized the prediction of the tensile strength and other performance indicators of natural rubber using the particle size of the rubber particles.

[0126] Test Example 7

[0127] Prediction of the 500% modulus of rubber of rubber trees in a test field in 2024

[0128] Fresh latex of rubber tree was obtained from a test field, and the sample was placed in an ice bath and taken back to the laboratory in a refrigerator. 10-15 μL of fresh latex was taken from each sample and added to a test tube containing 100 mmol / L Tris-HCl buffer to prepare the sample to be tested. The average particle size of the rubber particles in the latex was determined and calculated using a laser scattering particle size distribution analyzer. At the same time, in the same batch of samples, fresh latex was coagulated by adding acid to the container and left to stand for about 24 hours. A sheeting machine was used to press the sheet, which was dried in an oven set at 70°C for about 24 hours to obtain a raw rubber test sample. The vulcanized rubber sample was prepared according to the conventional formula, and the 500% modulus of the vulcanized rubber was determined using a tensile stress tester.

[0129] The tensile strength was predicted using the prediction model function equation Y = 4.2981-1.5602x based on the particle size of the rubber particles and the 500% modulus. For example, the particle sizes of the rubber particles were 1.02699, 0.97578, 1.01346, 0.88314, 1.02306, 1.00483, 0.94343, 1.07384, 1.12068, 1.00865, 1.03882, 1.01691, 1.02920 and 1.07833, respectively. According to the prediction model function, the simulated values of the 500% modulus were 2.695790, 2.775693, 2.716905, 2.920225, 2.701927, 2.730369, 2.826155, 2.622690, 2.549610, 2.724404, 2.677333, 2.711522, 2.692347 and 2.615690, respectively. The T test was performed on the test values of the 500% modulus and the simulated values of the 500% modulus using the R software ggpubr toolkit. Figure 6 The T test result showed that p = 0.35 > 0.05, i.e. the difference between the simulated values and the observed values of the 500% modulus was not significant, indicating that the prediction model had statistical significance, and the method of the present application realized the prediction of the 500% modulus of natural rubber using the particle size of the rubber particles.

[0130] Test Example 8

[0131] Prediction of the rubber tear strength of rubber trees in a test field in 2024

[0132] Fresh latex of rubber tree was obtained from a test field, and the sample was placed in an ice bath and taken back to the laboratory in a refrigerator. 10-15 μL of fresh latex was taken from each sample and added to a test tube containing 100 mmol / L Tris-HCl buffer to prepare the sample to be tested. The average particle size of the rubber particles in the latex was determined and calculated using a laser scattering particle size distribution analyzer. At the same time, in the same batch of samples, fresh latex was coagulated by adding acid in a container and left to stand for about 24 hours. A sheeting machine was used to press the sheet, and after drying, the temperature of the oven was set to 70°C for about 24 hours to obtain the raw rubber test sample. The vulcanized rubber sample was obtained by vulcanization according to the conventional formula, and the tear strength was determined by the tear test method.

[0133] The prediction model function equation Y = 32.356-6.829x based on the particle size of the rubber particles and the tear strength was used to predict the tear strength. For example, the particle sizes of the rubber particles were 1.02699, 0.97578, 1.01346, 0.88314, 1.02306, 1.00483, 0.94343, 1.07384, 1.12068, 1.00865, 1.03882, 1.01691, 1.02920 and 1.07833, and according to the prediction model function, the simulated values of the tear strength were 25.34269, 25.69242, 25.43510, 26.32504, 25.36955, 25.49404, 25.91329, 25.02272, 24.70285, 25.46793, 25.26190, 25.41154, 25.32762 and 24.99208. Further, the T test of the tear strength test value and the tear strength simulation value was performed by using the R software ggpubr toolkit Figure 7 ), and the T test result showed that p = 0.57 > 0.05, that is, the difference between the simulated value and the observed value of the tear strength was not significant, indicating that the prediction model had statistical significance, and the method of the application realized the prediction of the tear strength index of natural rubber by using the particle size of the rubber particles.

[0134] Please refer to Figure 9 , based on the same inventive concept, the application also provides a method for predicting the quality and performance of natural rubber by using the particle size of rubber particles, comprising:

[0135] The acquisition unit 901 is configured to acquire fresh latex of a rubber tree;

[0136] The determination unit 902 is configured to determine the particle size value of the rubber particles in the latex;

[0137] The selection unit 903 is configured to select a target quality performance item from the candidate quality performance items according to a first selection operation of a user;

[0138] The first determining unit 904 is configured to determine one or more target prediction models from the prediction models corresponding to the quality performance items according to the selected target quality performance item;

[0139] The prediction unit 905 is configured to input the rubber particle size value into each target prediction model to obtain a predicted value output by the target prediction model;

[0140] The second determining unit 906 is configured to determine a target quality performance parameter value according to the predicted value output by each target prediction model;

[0141] The target quality performance parameter predicted value indicates the quality or performance of the natural rubber.

[0142] Optionally, the candidate quality performance item includes one or more of the following: rubber weight average molecular weight, rubber viscosity average molecular weight, plasticity initial value, acetone solubles, tensile strength, 500% modulus, and vulcanizate tear strength.

[0143] Optionally, the system is further configured to: set a plurality of quality performance items; measure the plurality of quality performance items from a test latex sample; measure the rubber particle size value of the latex from the same batch of test latex sample; construct a regression equation of the rubber particle size value and the quality performance item according to the rubber particle size value; evaluate each regression equation; and determine the candidate quality performance item according to the evaluation result of the regression equation.

[0144] Optionally, the regression equation of the rubber particle size and the rubber weight average molecular weight is Y=2614561-824703x, where x represents the rubber particle size and Y represents the weight average molecular weight; the regression equation of the rubber particle size and the rubber viscosity average molecular weight is Y=2132640-702682x, where x represents the rubber particle size and Y represents the viscosity average molecular weight; the regression equation of the rubber particle size and the plasticity initial value is Y=54.106-17.151x, where x represents the rubber particle size and Y represents the plasticity initial value; the regression equation of the rubber particle size and the acetone solubles is Y=1.4921+1.6494x, where x represents the rubber particle size and Y represents the acetone solubles; the regression equation of the rubber particle size and the tensile strength is Y=30.77-13.03x, where x represents the rubber particle size and Y represents the tensile strength; the regression equation of the rubber particle size and the 500% modulus is Y=4.2981-1.5602x, where x represents the rubber particle size and Y represents the 500% modulus; and the regression equation of the rubber particle size and the vulcanizate tear strength is Y=32.356-6.829x, where x represents the rubber particle size and Y represents the vulcanizate tear strength.

[0145] Optionally, the generating the target quality performance parameter value according to the predicted values output by the respective target prediction model comprises: obtaining a preset weight corresponding to the target quality performance item; determining a weight corresponding to the predicted value output by each prediction model according to the weight corresponding to the target quality performance item; and determining the target quality performance parameter value based on the respective predicted value and the corresponding weight.

[0146] Optionally, the system is further configured to: collect latex samples of rubber trees; measure rubber particle sizes of the first group of latex samples; measure quality performance items of rubber prepared from the second group of latex samples as the measured quality performance parameter values; and construct the prediction model corresponding to the quality performance item based on the measurement of the rubber particle sizes and the measurement of the quality performance parameter values.

[0147] Optionally, the measurement of the rubber particle sizes of the first group of latex samples comprises: extracting 10-15 μL of each latex sample into a test tube containing 100 mmol / L Tris-HCl buffer; extracting 100-150 μL of the latex with the buffer from the test tube; measuring the rubber particle sizes using a laser scattering particle size distribution analyzer based on a quantity reference; and finally calculating the average volume particle size of the rubber particles.

[0148] Optionally, the measurement of the quality performance items of rubber prepared from the second group of latex samples as the measured quality performance parameter values comprises: coagulating fresh latex with acid in a container and placing for 24 hours; pressing the latex into a sheet using a sheeting machine, drying the sheet, and drying the sheet in an oven at a temperature of 70°C for 24 hours to obtain a raw rubber sample; measuring the weight average molecular weight and viscosity average molecular weight of the rubber using a gel permeation chromatograph; measuring the plasticity initial value using a rapid plastometer method; measuring the raw rubber ketone solubles using a thermal desorption-gas chromatography-mass spectrometry method; measuring the tensile strength and 500% modulus of the vulcanized rubber using a tensile testing machine; and measuring the tear strength of the vulcanized rubber using a tear test method.

[0149] Optionally, the system is further configured to: input the measured rubber particle size of the first group of samples into the constructed prediction model to obtain an evaluated predicted value; perform T-test on the evaluated predicted value and the measured quality performance parameter value of the second group of samples; and determine the significant difference between the evaluated predicted value and the measured quality performance parameter value based on the T-test result.

[0150] It should be noted that the information interaction and execution process between the above systems / units are based on the same concept as the method embodiments of the present application, and the specific functions and technical effects brought by the same can be found in the method embodiments, which will not be described here in detail.

[0151] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software functional unit. In addition, the specific names of the functional units and modules are only for easy distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0152] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0153] The embodiments of the present application provide a computer program product. When the computer program product is run on a mobile terminal, the mobile terminal is caused to implement the steps in the above method embodiments.

[0154] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above embodiment methods, which can be completed by a computer program instructing related hardware. The computer program can be stored in a computer readable storage medium. The computer program is executed by a processor to implement the steps in the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / electronic device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc.

[0155] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0156] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0157] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / network device and method can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division, and there can be another division in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or in other forms.

[0158] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. they can be located in one place, or distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0159] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent ones; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for predicting the quality and performance of natural rubber using the particle size of rubber particles, characterized by, The method comprises: obtaining fresh latex of rubber trees; determining the rubber particle size value of the fresh latex; selecting a target quality performance item from the candidate quality performance items according to a first selection operation of a user; determining one or more target prediction models from the prediction models corresponding to the quality performance items according to the selected target quality performance item; inputting the rubber particle size value into each target prediction model to obtain a prediction value output by the target prediction model; determining a target quality performance parameter value according to the prediction values output by each target prediction model; wherein the target quality performance parameter prediction value indicates the quality or performance of the natural rubber.

2. The method for predicting the quality performance of natural rubber using the particle diameter of rubber particles according to claim 1, characterized by, The candidate quality performance items include one or more of the following: rubber weight average molecular weight, rubber viscosity average molecular weight, plasticity initial value, acetone solubles, tensile strength, 500% modulus, and tear strength of vulcanized rubber.

3. The method for predicting the quality performance of natural rubber using rubber particle size according to claim 1, characterized by, The method further comprises: setting multiple quality performance items; determining the multiple quality performance items from the test latex samples; determining the rubber particle size value of the latex from the same batch of test latex samples; constructing a regression equation of the rubber particle size value and the quality performance items for the rubber particle size value; evaluating each regression equation, and determining the candidate quality performance items according to the evaluation results of the regression equations.

4. The method for predicting the quality performance of natural rubber using the rubber particle size according to claim 2, wherein: the regression equation of the rubber particle size and the rubber weight average molecular weight is Y = 2614561 - 824703x, wherein x represents the rubber particle size and Y represents the rubber weight average molecular weight; the regression equation of the rubber particle size and the rubber viscosity average molecular weight is Y = 2132640 - 702682x, wherein x represents the rubber particle size and Y represents the rubber viscosity average molecular weight; the regression equation of the rubber particle size and the plasticity initial value is Y = 54.106 - 17.151x, wherein x represents the rubber particle size and Y represents the plasticity initial value; the regression equation of the rubber particle size and the acetone solubles is Y = 1.4921 + 1.6494x, wherein x represents the rubber particle size and Y represents the acetone solubles; the regression equation of the rubber particle size and the tensile strength is Y = 30.77 - 13.03x, wherein x represents the rubber particle size and Y represents the tensile strength; the regression equation of the rubber particle size and the 500% modulus is Y = 4.2981 - 1.5602x, wherein x represents the rubber particle size and Y represents the 500% modulus; the regression equation of the rubber particle size and the tear strength of vulcanized rubber is Y = 32.356 - 6.829x, wherein x represents the rubber particle size and Y represents the tear strength of vulcanized rubber.

5. The method for predicting the quality performance of natural rubber using rubber particle size according to claim 1, characterized by, The method further comprises: acquiring a fresh latex sample of rubber trees; ​ ​ 6. The method of predicting the quality performance of natural rubber using rubber particle size according to claim 1, characterized by, ​ ​ Determine the rubber particle size of the first group of samples in the fresh latex sample; Determine the quality performance item of the rubber prepared by the second group of samples in the fresh latex sample as the determination of the quality performance parameter value; For determining the rubber particle size and determining the quality performance parameter value, a prediction model corresponding to the quality performance item is constructed.

7. The method for predicting the quality performance of natural rubber using rubber particle size according to claim 6, characterized by, The determination of the rubber particle size of the first group of samples in the latex sample comprises: 10-15 μL of each latex sample is taken into a test tube containing 100 mmol / L Tris-HCl buffer; 100-150 μL of latex with buffer is taken from the test tube; The average volume particle size of the rubber particles is finally calculated by using a laser scattering particle size distribution analyzer with a quantity reference.

8. The method for predicting the quality performance of natural rubber using rubber particle size according to claim 7, characterized by, The determination of the quality performance item of the rubber prepared by the second group of samples in the latex sample as the determination of the quality performance parameter value comprises: The fresh latex is coagulated with acid in a container and placed for 24 hours; A sheet machine is used to press the sheet, and after drying, the temperature is set to 70°C in the oven for 24 hours to obtain a raw rubber sample; The gel permeation chromatograph GPC is used to determine the weight average molecular weight and viscosity average molecular weight of the rubber; The rapid plastometer method is used to determine the plasticity initial value; The raw rubber ketone solute is determined by the thermal desorption-gas chromatography-mass spectrometry method; The tensile strength and 500% modulus of the vulcanized rubber are determined by using a tensile testing machine; The tear strength of the vulcanized rubber is determined by the tear test method.

9. The method for predicting the quality performance of natural rubber using rubber particle size according to claim 6, characterized by, The method further comprises: The rubber particle size determination value of the first group of samples is input into the constructed prediction model to obtain an evaluation prediction value; The evaluation prediction value and the determination of the quality performance parameter value of the second group of samples are subjected to T test; According to the T test result, the significant difference between the evaluation prediction value and the determination of the quality performance parameter value is judged.

10. A system for predicting quality and performance of natural rubber using rubber particle size, characterized by, Comprise: An acquisition unit is configured to acquire fresh latex of rubber trees; A determination unit is configured to determine the rubber particle size value of the latex; A selection unit is configured to select a target quality performance item from candidate quality performance items according to a first selection operation of a user; A first determination unit is configured to determine one or more target prediction models from the prediction models corresponding to the quality performance items according to the selected target quality performance item; A prediction unit is configured to input the rubber particle size value into each target prediction model to obtain a prediction value output by the target prediction model; A second determination unit is configured to determine a target quality performance parameter value according to the prediction value output by each target prediction model; The target quality performance parameter prediction value indicates the quality and / or performance of the natural rubber.

Images