Method and device for determining the composition of a lightweight gypsum-based self-leveling mortar

Abstract

The application relates to a method and device for determining the proportion of lightweight gypsum-based self-leveling mortar. The method comprises the following steps: obtaining first reference mortar data, the first reference mortar data comprising a plurality of first reference mortar formulations and corresponding first reference performance parameters; generating a mortar analysis model based on a preset initial model and the first reference mortar data; obtaining target performance parameters corresponding to user requirements; and inputting the target performance parameters into the mortar analysis model to determine a target mortar formulation corresponding to the target performance parameters, thereby efficiently and accurately determining the proportion of lightweight gypsum-based self-leveling mortar, and solving the problem that the traditional method for determining the proportion of lightweight gypsum-based self-leveling mortar is inefficient and difficult to accurately meet target performance requirements.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of building materials, in particular to a method and device for determining the proportion of light gypsum-based self-leveling mortar. BACKGROUND

[0002] With the continuous development of modern building technology, the requirements for building materials are also getting higher and higher. Light gypsum-based self-leveling mortar, as a kind of high-performance ground leveling material, has been widely used in the construction industry due to its light weight, environmental protection, and convenient construction.

[0003] The traditional method for determining the proportion of light gypsum-based self-leveling mortar mostly uses trial-and-error method, which finds the best solution by constantly testing and adjusting the proportion of raw materials. However, the gypsum-based self-leveling mortar prepared by the traditional trial-and-error method generally needs more than 10 tests, which not only has low efficiency, but also is difficult to accurately meet the target performance requirements. SUMMARY

[0004] Therefore, it is necessary to provide a method and device for determining the proportion of light gypsum-based self-leveling mortar, which can efficiently and accurately determine the proportion.

[0005] In a first aspect, the present application provides a method for determining the proportion of light gypsum-based self-leveling mortar, which comprises: obtaining first reference mortar data, the first reference mortar data comprising a plurality of first reference mortar formulations and a first reference performance parameter corresponding to each first reference mortar formulation; generating a mortar analysis model based on a preset initial model according to the first reference mortar data; obtaining a target performance parameter corresponding to a user requirement; inputting the target performance parameter into the mortar analysis model to determine a target mortar formulation corresponding to the target performance parameter.

[0006] In one embodiment, the preset initial model comprises at least one of a mathematical model, a linear regression model, a multivariate nonlinear regression model, a neural network model, a decision tree model, and a support vector machine model.

[0007] In one of the embodiments, the preset initial model comprises a mathematical fitting model, the first reference performance parameters comprise density, compressive strength and flexural strength; and generating the mortar analysis model based on the preset initial model and the first reference mortar data comprises: constructing a first function based on density based on the preset initial model and the plurality of first reference mortar formulations and the density corresponding to each of the first reference mortar formulations; constructing a second function based on compressive strength based on the preset initial model and the plurality of first reference mortar formulations and the compressive strength corresponding to each of the first reference mortar formulations; constructing a third function based on flexural strength based on the preset initial model and the plurality of first reference mortar formulations and the flexural strength corresponding to each of the first reference mortar formulations; and taking the first function, the second function and the third function as the mortar analysis model.

[0008] In one of the embodiments, inputting the target performance parameters into the mortar analysis model to determine the target mortar formulation corresponding to the target performance parameters comprises: obtaining boundary conditions of a plurality of components corresponding to the target performance parameters; substituting the density corresponding to the target performance parameters into the first function, substituting the compressive strength corresponding to the target performance parameters into the second function, and substituting the flexural strength corresponding to the target performance parameters into the third function, to obtain the target mortar formulation corresponding to the target performance parameters with the boundary conditions of the plurality of components as constraint conditions.

[0009] In one of the embodiments, the method further comprises: determining actual performance parameters corresponding to the target mortar formulation according to the target mortar formulation; and determining whether the target mortar formulation meets the user demand based on the actual performance parameters and the target performance parameters.

[0010] In one of the embodiments, the method for determining the proportion of the lightweight gypsum-based self-leveling mortar further comprises: obtaining second reference mortar data, the second reference mortar data comprising a plurality of second reference mortar formulations and second reference performance parameters corresponding to the plurality of second reference mortar formulations; determining predicted performance parameters corresponding to the plurality of second reference mortar formulations based on the mortar analysis model and the plurality of second reference mortar formulations; verifying the mortar analysis model based on the plurality of predicted performance parameters and the plurality of second reference performance parameters; and replacing the preset initial model if the verification fails.

[0011] In one of the embodiments, the verifying the mortar analysis model based on the plurality of predicted performance parameters and the plurality of second reference performance parameters comprises: calculating a performance parameter mean value based on the plurality of second reference performance parameters; calculating a determination coefficient according to the performance parameter mean value and the predicted performance parameter and the second reference performance parameter corresponding to each second reference mortar formula; calculating a relative error corresponding to each second reference mortar formula according to the predicted performance parameter and the second reference performance parameter corresponding to each second reference mortar formula; determining an error mean value according to the relative error corresponding to each second reference mortar formula; if the determination coefficient meets a first preset requirement and the error mean value meets a second preset requirement, the mortar analysis model is verified to be passed.

[0012] In a second aspect, the present application further provides a proportioning device for a lightweight gypsum-based self-leveling mortar. The device comprises:

[0013] The obtaining module is configured to obtain first reference mortar data, the first reference mortar data comprising a plurality of first reference mortar formulas and a first reference performance parameter corresponding to each of the first reference mortar formulas;

[0014] The analysis module is configured to generate a mortar analysis model based on a preset initial model and the first reference mortar data.

[0015] The obtaining module is further configured to obtain a target performance parameter corresponding to a user demand.

[0016] The determining module is configured to input the target performance parameter into the mortar analysis model and determine a target mortar formula corresponding to the target performance parameter.

[0017] In a third aspect, the present application further provides a computer device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements any of the methods in the first aspect when executing the computer program.

[0018] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement any of the methods in the first aspect.

[0019] The method and device for determining the proportion of the lightweight gypsum-based self-leveling mortar according to the application first obtain first reference mortar data, wherein the first reference mortar data comprises a plurality of first reference mortar formulations and a first reference performance parameter corresponding to each first reference mortar formulation; then, based on a preset initial model, a mortar analysis model is generated according to the first reference mortar data; then, a target performance parameter corresponding to a user requirement is obtained; finally, the target performance parameter is input into the mortar analysis model, so as to determine a target mortar formulation corresponding to the target performance parameter, thereby realizing efficient and accurate determination of the proportion of the lightweight gypsum-based self-leveling mortar, and solving the problem that the traditional method for determining the proportion of the lightweight gypsum-based self-leveling mortar is inefficient and difficult to accurately meet the target performance requirement. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 An application environment diagram of the method for determining the proportion of the lightweight gypsum-based self-leveling mortar in one embodiment;

[0021] Figure 2 A flowchart of the method for determining the proportion of the lightweight gypsum-based self-leveling mortar in one embodiment;

[0022] Figure 3 A flowchart of the method for verifying the performance of the mortar analysis model in one embodiment;

[0023] Figure 4 A flowchart of the method for determining the proportion of the lightweight gypsum-based self-leveling mortar in another embodiment;

[0024] Figure 5 A structural block diagram of the device for determining the proportion of the lightweight gypsum-based self-leveling mortar in one embodiment;

[0025] Figure 6 An internal structure diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical scheme and advantages of the application clearer, the application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the application and do not limit the application.

[0027] With the continuous development of modern building technology, the requirements for building materials are also getting higher and higher. As a kind of high-performance ground leveling material, lightweight gypsum-based self-leveling mortar has been widely used in the construction industry due to its lightweight, environmental protection, and convenient construction. However, the lightweight gypsum-based self-leveling mortar on the current market still has some deficiencies in performance. For example, many lightweight gypsum-based self-leveling mortars sacrifice strength while pursuing lightweight, resulting in a decrease in the load-bearing capacity of the ground and affecting the safety of the building. At the same time, the self-leveling performance of some products is not good, and manual assistance is needed for leveling, increasing the difficulty and cost of construction. In addition, some lightweight gypsum-based self-leveling mortars are prone to cracking, falling off and other problems during long-term use, affecting the service life and aesthetics of the ground. The traditional method of determining the proportion of lightweight gypsum-based self-leveling mortar is mostly trial and error, which requires continuous testing and adjustment of raw material proportions to find the best solution. The lightweight gypsum-based self-leveling mortar prepared by the traditional trial and error method generally needs more than 10 tests. This method not only has low efficiency, but also is difficult to accurately meet the target performance requirements.

[0028] The method for determining the proportion of lightweight gypsum-based self-leveling mortar provided by the embodiments of the present application can be applied in the application environment as shown in Figure 1 The terminal 102 communicates with the server 104 through the network. The data storage system can store the data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The server 104 is used to execute the method for determining the proportion of lightweight gypsum-based self-leveling mortar. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be realized by an independent server or a server cluster composed of multiple servers.

[0029] In order to solve the above problems, in one embodiment of the present application, as shown in Figure 2 A method for determining the proportion of lightweight gypsum-based self-leveling mortar is provided, comprising the following steps:

[0030] Step 201, obtaining first reference mortar data.

[0031] The first reference mortar data includes a plurality of first reference mortar formulas and a first reference performance parameter corresponding to each of the first reference mortar formulas. The first reference mortar formula is a component formula of an actual lightweight gypsum-based self-leveling mortar, which includes the contents of gypsum powder, lightweight aggregate, water reducing agent, retarder, water retaining agent, and additive. The gypsum powder serves as a base material to provide the main strength and adhesion of the mortar. The lightweight aggregate is used to reduce the density of the mortar and improve the lightweight property of the material. The retarder is used to adjust the setting time of the mortar to ensure the operability during construction. The water retaining agent is used to maintain the moisture in the mortar to prevent it from drying too quickly, thereby ensuring the self-leveling performance. The additive is used to further improve the comprehensive performance of the mortar, such as toughness, antibacterial, fireproof, water resistance, etc. For example, the gypsum powder is 45 parts, the vermiculite is 25 parts, the tartaric acid is 1.5 parts, and the starch ether is 0.8 parts. The first reference performance parameter is an actual performance parameter of the first reference mortar formula, including density (p, kg / m3), compressive strength (f c, MPa), and flexural strength (f t, MPa). The first reference mortar data is obtained from historical data in the laboratory, related literature / patent data, and industry standards.

[0032] In step 202, a mortar analysis model is generated based on a preset initial model and according to the first reference mortar data.

[0033] The preset initial model includes at least one of a mathematical model, a linear regression model, a multivariate nonlinear regression model, a neural network model, a decision tree model, and a support vector machine model.

[0034] For example, based on the preset initial model and according to the first reference mortar data, the generation of the mortar analysis model is specifically as follows: the first reference mortar data is divided into a training set and a validation set, the initial neural network is trained according to the training set, and the neural network model is verified through the validation set, and finally the mortar analysis model is obtained.

[0035] For example, based on the preset initial model and according to the first reference mortar data, the generation of the mortar analysis model is specifically as follows: the first reference mortar data is divided into a training set and a validation set, the initial neural network is trained according to the training set, and the neural network model is verified through the validation set, and finally the mortar analysis model is obtained.

[0036] In this embodiment, the preset initial model is a mathematical fitting model, but in other embodiments, it can be a neural network model. The mortar analysis model is a fitting function of the performance parameters of the lightweight gypsum-based self-leveling mortar with respect to the component contents of various substances included in the lightweight gypsum-based self-leveling mortar. Based on the preset initial model and according to the first reference mortar data, the generation of the mortar analysis model is as follows: based on the preset initial model, the first reference mortar data is fitted to obtain the mortar analysis model.

[0037] Exemplarily, the preset initial model is: wherein is a performance parameter, for example, density (p, kg / m³), compressive strength (f_c, MPa), and flexural strength (f_t, MPa), is a random coefficient, is a random error, wherein the values of variables i and j are in the range of 1-5, wherein X1 represents the content of gypsum powder in the mortar formula, X2 represents the content of lightweight aggregate, X3 represents the content of water reducing agent, X4 represents the content of retarder, and X5 represents the content of water retaining agent.

[0038] It should be noted that the initial model is obtained by response surface method and central composite design, wherein the response surface method (RSM) is a statistical and mathematical technique used to establish, improve and optimize processes or systems. It is mainly used to analyze the relationship between multiple independent variables (factors) and one or more response variables (results), and find the combination of factors that make the response optimal (such as maximum, minimum or target value). Central composite design (CCD) is one of the most commonly used experimental design methods in response surface method (RSM), which is used to efficiently fit second-order (quadratic) polynomial models to optimize multi-factor systems.

[0039] Step 203, obtaining the target performance parameter corresponding to the user demand.

[0040] The target performance parameter is the performance parameter that the user hopes the lightweight gypsum-based self-leveling mortar can achieve. Exemplarily, in the present embodiment, the target performance parameters are: density ≤ 950 kg / m³, compressive strength ≥ 8 MPa, and flexural strength ≥ 2 MPa.

[0041] Step 204, inputting the target performance parameter into the mortar analysis model to determine the target mortar formula corresponding to the target performance parameter.

[0042] The target mortar formula is a mortar formula whose performance parameters can meet the target performance parameters. That is, the target performance parameters are substituted into the mortar analysis model to solve, thereby obtaining the target mortar formula.

[0043] The method for determining the proportion of the light gypsum-based self-leveling mortar comprises the following steps: first, obtaining first reference mortar data, wherein the first reference mortar data comprises a plurality of first reference mortar formulations and a first reference performance parameter corresponding to each of the first reference mortar formulations; then, generating a mortar analysis model based on a preset initial model according to the first reference mortar data; then, obtaining a target performance parameter corresponding to a user requirement; and finally, inputting the target performance parameter into the mortar analysis model to determine a target mortar formulation corresponding to the target performance parameter, thereby efficiently and accurately determining the proportion of the light gypsum-based self-leveling mortar, and solving the problem that the traditional method for determining the proportion of the light gypsum-based self-leveling mortar is inefficient and difficult to accurately meet the target performance requirement.

[0044] It should be noted that the method for determining the proportion of the light gypsum-based self-leveling mortar can accurately meet the target performance requirement, and through reverse thinking, the raw material proportion and the preparation process are deduced reversely from the target performance, so that the requirements of lightness, high strength, self-leveling performance and the like can be more accurately met. In addition, the preparation efficiency can be improved: the use of reverse design method can avoid the complexity and uncertainty of the traditional trial-and-error method, greatly improving the preparation efficiency and success rate. Furthermore, the utilization of raw materials can be optimized: through accurate calculation and optimization of the proportion, the performance advantages of various raw materials are fully utilized, and waste and cost are reduced. Finally, the product stability can be enhanced: the light gypsum-based self-leveling mortar obtained by the present application has excellent self-leveling performance and durability, and can meet various complex construction environments and long-term use requirements.

[0045] In other embodiments of the present application, the preset initial model comprises a mathematical fitting model, and the first reference performance parameter comprises density, compressive strength and flexural strength. The generating of the mortar analysis model based on the preset initial model and the first reference mortar data comprises:

[0046] Step 1, constructing a first function based on density based on the preset initial model and the plurality of first reference mortar formulations and the density corresponding to each of the first reference mortar formulations.

[0047] It should be noted that in the present embodiment, the initial model for constructing the first function, the second function and the third function is the same initial model.

[0048] The constructing of the first function based on density based on the preset initial model and the plurality of first reference mortar formulations and the density corresponding to each of the first reference mortar formulations is specifically: substituting the plurality of first reference mortar formulations and the density corresponding to each of the first reference mortar formulations into the preset initial model respectively, and jointly solving and fitting, thereby constructing the first function based on density.

[0049] Exemplarily, the first function is:

[0050] .

[0051] The first function is a fitting function of the density of the lightweight gypsum-based self-leveling mortar with respect to the component content of each type of substance included in the lightweight gypsum-based self-leveling mortar.

[0052] Step 2, based on the preset initial model, a second function based on the compressive strength is constructed according to the plurality of first reference mortar formulations and the compressive strength corresponding to each first reference mortar formulation.

[0053] Based on the preset initial model, a second function based on the compressive strength is constructed according to the plurality of first reference mortar formulations and the compressive strength corresponding to each first reference mortar formulation. Specifically, the plurality of first reference mortar formulations and the compressive strength corresponding to each first reference mortar formulation are substituted into the preset initial model respectively, and a joint solution fitting is performed to construct the second function based on the compressive strength.

[0054] Exemplarily, the second function is:

[0055] .

[0056] The second function is a fitting function of the compressive strength of the lightweight gypsum-based self-leveling mortar with respect to the component content of each type of substance included in the lightweight gypsum-based self-leveling mortar. And f c That is, the compressive strength (f_c, MPa) mentioned above.

[0057] Step 3, based on the preset initial model, a third function based on the flexural strength is constructed according to the plurality of first reference mortar formulations and the flexural strength corresponding to each first reference mortar formulation.

[0058] Exemplarily, based on the preset initial model, a third function based on the flexural strength is constructed according to the plurality of first reference mortar formulations and the flexural strength corresponding to each first reference mortar formulation. Specifically, the plurality of first reference mortar formulations and the flexural strength corresponding to each first reference mortar formulation are substituted into the preset initial model respectively, and a joint solution fitting is performed to construct the third function based on the flexural strength.

[0059] Exemplarily, the third function is:

[0060] .

[0061] The third function is a fitting function of the flexural strength of the lightweight gypsum-based self-leveling mortar with respect to the component content of each type of substance included in the lightweight gypsum-based self-leveling mortar. And f t That is, the flexural strength (f_t, MPa) mentioned above.

[0062] Step 4, taking the first function, the second function and the third function as a mortar analysis model.

[0063] Exemplarily, based on the preset initial model, the second function based on the compressive strength is constructed according to a plurality of first reference mortar formulations and the compressive strength corresponding to each first reference mortar formulation, and the second function based on the compressive strength is specifically:

[0064] The plurality of first reference mortar formulations and the compressive strength corresponding to each first reference mortar formulation are shown in Table 1 as follows:

[0065] Table 1

[0066]

[0067] Each first reference mortar formulation and the compressive strength corresponding to each first reference mortar formulation in Table 1 above are substituted into the preset initial model respectively: After fitting and solving, the second function is finally obtained:

[0068] .

[0069] In other embodiments of the present application, the inputting of the target performance parameter into the mortar analysis model to determine the target mortar formulation corresponding to the target performance parameter comprises:

[0070] Step 1, obtaining boundary conditions of a plurality of components corresponding to a target performance parameter.

[0071] The boundary condition is the range of the component content of each type of substance contained in the mortar formulation. Exemplarily, the boundary condition is: gypsum powder (X1): 40%-70%, perlite (X2): 20%-50%, water reducing agent (X3): 0.1%-0.5%, retarder (X4): 0.05%-0.15%, water retaining agent (X5): 0.1%-0.3%.

[0072] Step 2, substituting the density corresponding to the target performance parameter into the first function, substituting the compressive strength corresponding to the target performance parameter into the second function, and substituting the flexural strength corresponding to the target performance parameter into the third function, and solving to obtain the target mortar formulation corresponding to the target performance parameter under the constraint condition of the boundary condition of the plurality of components.

[0073] The requirement about the density in the target performance parameter is substituted into the first function to obtain an inequality about the density, the requirement about the compressive strength in the target performance parameter is substituted into the second function to obtain an inequality about the compressive strength, and the requirement about the flexural strength in the target performance parameter is substituted into the third function to obtain an inequality about the flexural strength. The inequalities about the density, the compressive strength and the flexural strength are combined, and the boundary conditions of the multiple components are used as constraint conditions to finally obtain the target mortar formula corresponding to the target performance parameter.

[0074] For example, the target mortar formula is gypsum powder X1 = 58%, perlite X2 = 28.5%, water reducing agent X3 = 0.42%, retarder X4 = 0.08%, water retaining agent X5 = 0.18%.

[0075] In other embodiments of the present application, the method further comprises:

[0076] Step 1, determining the actual performance parameter corresponding to the target mortar formula according to the target mortar formula.

[0077] The actual performance parameter is the actual performance parameter of the lightweight gypsum-based self-leveling mortar corresponding to the target mortar formula.

[0078] According to the target mortar formula, the actual performance parameter corresponding to the target mortar formula is: configuring the corresponding lightweight gypsum-based self-leveling mortar according to the target mortar formula in the laboratory, and testing the actual performance parameter of the lightweight gypsum-based self-leveling mortar.

[0079] Step 2, determining whether the target mortar formula meets the user's demand based on the actual performance parameter and the target performance parameter.

[0080] Specifically, it is determined whether the actual performance parameter matches the target performance parameter, and the predicted performance parameter of the target mortar formula is calculated according to the target mortar formula and the mortar analysis model, and the relative error between the predicted performance parameter and the actual performance parameter is calculated. If the actual performance parameter does not match the target performance parameter, the preset initial model is replaced to re-execute the generation of the mortar analysis model based on the preset initial model according to the first reference mortar data. The replaced preset initial model is one of the linear regression model, the multivariate nonlinear regression model, the neural network model, the decision tree model and the support vector machine model. If the actual performance parameter matches the target performance parameter, the target mortar formula is considered to be qualified.

[0081] Table 2

[0082]

[0083] Exemplarily, as shown in Table 2 above, in a specific embodiment of the present application, the target performance parameters are: density ≤ 950 kg / m³, compressive strength ≥ 8 MPa, and flexural strength ≥ 2 MPa, the predicted performance parameters are: density 920 kg / m³, compressive strength 8.5 MPa, and flexural strength 2.00 MPa, and the actual performance parameters are: density 925 kg / m³, compressive strength 8.3 MPa, and flexural strength 2.03 MPa. The relative error of density is 0.5%, the relative error of compressive strength is 2.4%, and the relative error of flexural strength is 1.4%. The actual performance parameters match the target performance parameters, that is, the density, compressive strength, and flexural strength in the actual performance parameters are all within the ranges of the density, compressive strength, and flexural strength required in the target performance parameters, and thus the target mortar formulation is qualified.

[0084] It should be noted that, in the present embodiment, the target performance parameters are: density ≤ 950 kg / m³, compressive strength ≥ 8 MPa, and flexural strength ≥ 2 MPa, and thus there can be multiple mortar formulations that meet the target performance parameters. In this case, one of the mortar formulations whose actual performance parameters or predicted performance parameters are closest to the target performance parameters is selected as the target mortar formulation according to the priority order of compressive strength, flexural strength, and density in turn.

[0085] In other embodiments of the present application, as shown in Table 3, Figure 3 the method for determining the ratio of the lightweight gypsum-based self-leveling mortar further comprises:

[0086] Step 301: obtaining second reference mortar data.

[0087] The second reference mortar data includes a plurality of second reference mortar formulations and a plurality of second reference performance parameters corresponding to the plurality of second reference mortar formulations. The second reference mortar formulation is a component formulation of an actual lightweight gypsum-based self-leveling mortar, which includes the contents of gypsum powder, lightweight aggregate, retarder, water-retaining agent, and additive. For example, gypsum powder 45 parts, vermiculite 25 parts, tartaric acid 1.5 parts, and starch ether 0.8 parts. The second reference performance parameter is the actual performance parameter of the second reference mortar formulation. That is, the second reference mortar data is the second reference mortar formulation and the second reference performance parameter corresponding to the second reference mortar formulation, which are different from the first reference mortar data.

[0088] Step 302: determining, based on the mortar analysis model, the predicted performance parameters corresponding to the plurality of second reference mortar formulations according to the plurality of second reference mortar formulations.

[0089] That is, the plurality of second reference mortar formulations are respectively substituted into the mortar analysis model to calculate the predicted performance parameters corresponding to the plurality of second reference mortar formulations.

[0090] Step 303, verifying the mortar analysis model based on the plurality of prediction performance parameters and the plurality of second reference performance parameters.

[0091] Step 304, replacing the preset initial model if the verification fails.

[0092] That is, the mortar analysis model established according to the originally preset initial model does not meet the requirements of engineering application, the preset initial model is replaced, and the related steps are re-executed. The preset initial model replaced is one of the linear regression model, the multivariate nonlinear regression model, the neural network model, the decision tree model, and the support vector machine model.

[0093] Exemplarily, when the other preset initial model is the support vector machine model, the preset initial model is: wherein and is a Lagrange multiplier, and , , C is a penalty coefficient, which controls the model complexity and fault tolerance, is a kernel function, and b is a bias term, which is the intercept of the decision hyperplane.

[0094] Exemplarily, when the other preset initial model is the decision tree model, the preset initial model is: wherein is the output of the final model after m rounds of iteration, is the base learner (decision tree) of the mth round of training.

[0095] In other embodiments of the present application, the verifying the mortar analysis model based on the plurality of prediction performance parameters and the plurality of second reference performance parameters comprises:

[0096] Step 1, calculating the performance parameter mean value based on the plurality of second reference performance parameters.

[0097] That is, the mean value of the plurality of densities, the mean value of the plurality of compressive strengths, and the mean value of the plurality of flexural strengths in the plurality of second reference performance parameters are taken as the performance parameter mean value.

[0098] Step 2, calculating the determination coefficient according to the performance parameter mean value and the prediction performance parameter and the second reference performance parameter corresponding to each second reference mortar formula.

[0099] Exemplarily, the calculation formula of the determination coefficient is: wherein is the second reference performance parameter, is the prediction performance parameter, is the performance parameter mean value.

[0100] It should be noted that, based on the average performance parameters and the predicted performance parameters and second reference performance parameters corresponding to each second reference mortar formula, the determination coefficients calculated in the process of calculating the determination coefficients are the determination coefficients of density, compressive strength, and flexural strength.

[0101] Step 3: Calculate the relative error corresponding to each second reference mortar formula based on the predicted performance parameters and second reference performance parameters corresponding to each second reference mortar formula.

[0102] For example, the formula for calculating relative error is: ,in This is the second reference performance parameter. To predict performance parameters.

[0103] It should be noted that, in the process of calculating the relative error corresponding to each second reference mortar formula based on the predicted performance parameters and second reference performance parameters, the relative errors calculated are the relative errors of density, compressive strength, and flexural strength.

[0104] Step 4: Determine the mean error based on the relative error corresponding to each second reference mortar formula.

[0105] That is, the average value of the relative error of density, relative error of compressive strength and relative error of flexural strength corresponding to each second reference mortar formula is taken as the mean error.

[0106] Step 5: If the determination coefficient meets the first preset requirement and the mean error meets the second preset requirement, then the mortar analysis model is verified.

[0107] In this embodiment, the first preset requirement is >0.9, when the coefficient of determination R 2 If the coefficient of determination is greater than 0.9, then the coefficient of determination meets the first preset requirement. The second preset requirement is less than 5%, that is, when the mean error is less than 5%, then the mean error meets the second preset requirement.

[0108] It should be noted that in other embodiments of this application, cross-validation is used to verify the mortar analysis model. For example, taking the 15 sets of first reference mortar data in Table 1 as an example, 14 sets of first reference mortar data are taken in sequence to construct a mortar analysis model. The relative error between the predicted performance parameters and the actual performance parameters of each mortar analysis model is calculated, and the mean of the 15 sets of relative errors is taken to determine whether it is <3%. If the mean of the relative error is <3%, it is determined that the mean of the relative error of the mortar analysis model meets the requirements.

[0109] In other embodiments of the present application, taking the 15 groups of first reference mortar data in Table 1 as an example, the 15 groups of first reference mortar data in Table 1 are randomly divided into ten groups of first reference mortar data sets, and a mortar analysis model is constructed, wherein the same first reference mortar data can exist in multiple first reference mortar data sets at the same time, the relative error between the prediction performance parameters and the actual performance parameters of each mortar analysis model is calculated, and the average of the relative errors of the 10 groups is taken to judge whether it is < 3%, if the average of the relative errors is < 3%, it is judged that the average of the relative errors of the mortar analysis model meets the requirements.

[0110] In a specific embodiment of the present application, as shown in Figure 4 The performance target is set: the target performance parameters of the lightweight gypsum-based self-leveling mortar are set as density less than 1800 kg / m³, compressive strength greater than 30 MPa, flexural strength greater than 8 MPa, and antibacterial effect.

[0111] Data collection and analysis: collect performance data of lightweight gypsum-based self-leveling mortar with different formulations, including density, strength, fluidity, etc.

[0112] Establish a relationship model: use machine learning techniques such as neural networks to establish a mathematical model between performance parameters and formulation components.

[0113] Reverse design optimization: use genetic algorithms to solve the optimal formulation ratio in reverse according to the performance target. Through iterative calculation, find the formulation combination that meets the target performance requirements.

[0114] Laboratory test: according to the optimization results, the laboratory small test formulation is: gypsum powder 50 parts, expanded perlite 20 parts, citric acid 1 part, cellulose ether 0.5 parts, nano-silver ion antibacterial agent 0.3 parts. Small-scale test is carried out, and the formulation is adjusted until the performance target is met. Pilot scale-up verifies the feasibility of the formulation, and adjusts the production process to adapt to industrial production.

[0115] Performance verification: test the performance of the produced mortar, and the performance meets the design requirements.

[0116] In a specific embodiment of the present application, the performance target is set: the target performance parameters of the lightweight gypsum-based self-leveling mortar are set as density less than 1700 kg / m³, compressive strength greater than 35 MPa, flexural strength greater than 10 MPa, and antibacterial effect.

[0117] Data collection and analysis: collect performance data of lightweight gypsum-based self-leveling mortar with different formulations.

[0118] Establish a relationship model: use decision tree model to establish a mathematical model between performance parameters and formulation components.

[0119] Reverse design optimization: Utilize genetic algorithms to inversely solve the optimal formulation proportions based on performance targets. Through iterative calculations, find the formulation combination that meets the target performance requirements.

[0120] Laboratory testing: Based on the optimization results, the laboratory small-scale test formulation is: gypsum powder 45 parts, vermiculite 25 parts, tartaric acid 1.5 parts, starch ether 0.8 parts, quaternary ammonium salt antibacterial agent 0.5 parts. Conduct small-scale tests to adjust the formulation until the performance targets are met. Pilot-scale amplification verifies the feasibility of the formulation, and adjusts the production process to adapt to industrial production.

[0121] Performance verification: Test the performance of the produced mortar, and the performance meets the design requirements.

[0122] In a specific embodiment of the present application, the performance target is set: the target performance parameters of the lightweight gypsum-based self-leveling mortar are set as density less than 1600 kg / m³, compressive strength greater than 40 MPa, and flexural strength greater than 12 MPa.

[0123] Data collection and analysis: Collect performance data of lightweight gypsum-based self-leveling mortar with different formulations.

[0124] Establish a relationship model: Use machine learning techniques such as support vector machines (SVM) to establish a mathematical model between performance parameters and formulation components.

[0125] Reverse design optimization: Utilize genetic algorithms to inversely solve the optimal formulation proportions based on performance targets. Through iterative calculations, find the formulation combination that meets the target performance requirements.

[0126] Laboratory testing: Based on the optimization results, the laboratory small-scale test formulation is: gypsum powder 55 parts, ceramic particles 15 parts, phosphoric acid 0.8 parts, polyacrylamide 0.3 parts, and glass fiber 3 parts. Conduct small-scale tests to adjust the formulation until the performance targets are met. Pilot-scale amplification verifies the feasibility of the formulation, and adjusts the production process to adapt to industrial production.

[0127] Performance verification: Test the performance of the produced mortar, and the performance meets the design requirements.

[0128] In a specific embodiment of the present application, the performance target is set: the target performance parameters of the lightweight gypsum-based self-leveling mortar are set as density less than 1600 kg / m³, compressive strength greater than 40 MPa, flexural strength greater than 12 MPa, and color red.

[0129] Data collection and analysis: Collect performance data of lightweight gypsum-based self-leveling mortar with different formulations.

[0130] Establish a relationship model: Use linear regression models to establish a mathematical model between performance parameters and formulation components.

[0131] Reverse design optimization: Utilize genetic algorithms to inversely solve optimal formulation ratios based on performance targets. Through iterative calculations, find formulation combinations that meet target performance requirements.

[0132] Laboratory testing: Based on optimization results, laboratory small-scale test formulation is: gypsum powder 55 parts, ceramic granules 15 parts, phosphoric acid 0.8 parts, polyacrylamide 0.3 parts, red pigment 0.1 part. Conduct small-scale tests, adjust formulation until performance targets are met. Pilot-scale upscaling verifies formulation feasibility, adjust production process to adapt to industrial production.

[0133] Performance verification: Test the performance of the produced mortar, which meets the design requirements.

[0134] In a specific embodiment of the present application, the performance target is set: the target performance parameters of lightweight gypsum-based self-leveling mortar are set as density less than 1550 kg / m³, compressive strength greater than 43 MPa, and flexural strength greater than 11 MPa.

[0135] Data collection and analysis: Collect performance data of lightweight gypsum-based self-leveling mortar with different formulations.

[0136] Establish a relationship model: Use a multivariate nonlinear regression model to establish a mathematical model between performance parameters and formulation components.

[0137] Reverse design optimization: Utilize genetic algorithms to inversely solve optimal formulation ratios based on performance targets. Through iterative calculations, find formulation combinations that meet target performance requirements.

[0138] Laboratory testing: Based on optimization results, laboratory small-scale test formulation is: gypsum powder 60 parts, fly ash 10 parts, tartaric acid 1 part, cellulose ether 0.5 parts, glass fiber 3 parts. Conduct small-scale tests, adjust formulation until performance targets are met. Pilot-scale upscaling verifies formulation feasibility, adjust production process to adapt to industrial production.

[0139] Performance verification: Test the performance of the produced mortar, which meets the design requirements.

[0140] In a specific embodiment of the present application, the performance target is set: the target performance parameters of lightweight gypsum-based self-leveling mortar are set as density less than 1500 kg / m³, compressive strength greater than 45 MPa, and flexural strength greater than 14 MPa.

[0141] Data collection and analysis: Collect performance data of lightweight gypsum-based self-leveling mortar with different formulations.

[0142] Establish a relationship model: Use a multivariate nonlinear regression model to establish a mathematical model between performance parameters and formulation components.

[0143] Reverse design optimization: Utilize genetic algorithms to inversely solve optimal formulation ratios based on performance targets. Through iterative calculations, find formulation combinations that meet target performance requirements.

[0144] Laboratory testing: Based on optimization results, laboratory small-scale formulation is: gypsum powder 48 parts, pumice 22 parts, polyvinyl alcohol 1.2 parts, bentonite 0.6 parts, polypropylene fiber 2 parts. Conduct small-scale tests, adjust the formulation until it meets the performance target. Pilot-scale amplification verifies the feasibility of the formulation, and adjusts the production process to adapt to industrial production.

[0145] Performance verification: Test the performance of the produced mortar, which meets the design requirements.

[0146] In a specific embodiment of the present application, the performance target is set: The target performance parameters of lightweight gypsum-based self-leveling mortar are set as density less than 1490 kg / m³, compressive strength greater than 39 MPa, flexural strength greater than 10 MPa, and fireproof effect.

[0147] Data collection and analysis: Collect performance data of lightweight gypsum-based self-leveling mortar with different formulations.

[0148] Establish a relationship model: Use machine learning techniques such as neural networks to establish a mathematical model between performance parameters and formulation ingredients.

[0149] Reverse design optimization: Utilize genetic algorithms to inversely solve optimal formulation ratios based on performance targets. Through iterative calculations, find formulation combinations that meet target performance requirements.

[0150] Laboratory testing: Based on optimization results, laboratory small-scale formulation is: gypsum powder 51 parts, volcanic slag 24 parts, montmorillonite 1.1 parts, polyacrylamide 0.7 parts, fire retardant 0.1 parts. Conduct small-scale tests, adjust the formulation until it meets the performance target. Pilot-scale amplification verifies the feasibility of the formulation, and adjusts the production process to adapt to industrial production.

[0151] Performance verification: Test the performance of the produced mortar, which meets the design requirements.

[0152] In a specific embodiment of the present application, the performance target is set: The target performance parameters of lightweight gypsum-based self-leveling mortar are set as density less than 1510 kg / m³, compressive strength greater than 41 MPa, flexural strength greater than 13 MPa, and water resistance effect.

[0153] Data collection and analysis: Collect performance data of lightweight gypsum-based self-leveling mortar with different formulations.

[0154] Establish a relationship model: Use machine learning techniques such as support vector machines (SVM) to establish a mathematical model between performance parameters and formulation ingredients.

[0155] Reverse design optimization: Utilize genetic algorithms to inversely solve optimal formulation ratios based on performance targets. Through iterative calculations, find formulation combinations that meet target performance requirements.

[0156] Laboratory testing: Based on optimization results, laboratory small-scale test formulation is: gypsum powder 53 parts, ceramic granules 16 parts, citric acid 1.3 parts, starch ether 0.7 parts, water-resistant agent 0.2 parts. Conduct small-scale tests to adjust the formulation until the performance targets are met. Pilot-scale amplification verifies the feasibility of the formulation, and adjusts the production process to adapt to industrial production.

[0157] Performance verification: Test the performance of the produced mortar, which meets the design requirements.

[0158] In a specific embodiment of the present application, the performance target is set: the target performance parameters of the lightweight gypsum-based self-leveling mortar are set as density less than 1570 kg / m³, compressive strength greater than 45 MPa, flexural strength greater than 10 MPa, and green color.

[0159] Data collection and analysis: Collect performance data of lightweight gypsum-based self-leveling mortar with different formulations.

[0160] Establish a relationship model: Use a multivariate nonlinear regression model to establish a mathematical model between performance parameters and formulation components.

[0161] Reverse design optimization: Utilize genetic algorithms to inversely solve optimal formulation ratios based on performance targets. Through iterative calculations, find formulation combinations that meet target performance requirements.

[0162] Laboratory testing: Based on optimization results, laboratory small-scale test formulation is: gypsum powder 59 parts, vermiculite 11 parts, phosphoric acid 1.5 parts, cellulose ether 0.6 parts, green pigment 0.1 parts. Conduct small-scale tests to adjust the formulation until the performance targets are met. Pilot-scale amplification verifies the feasibility of the formulation, and adjusts the production process to adapt to industrial production.

[0163] Performance verification: Test the performance of the produced mortar, which meets the design requirements.

[0164] In a specific embodiment of the present application, the performance target is set: the target performance parameters of the lightweight gypsum-based self-leveling mortar are set as density less than 1560 kg / m³, compressive strength greater than 40 MPa, flexural strength greater than 9 MPa, and yellow color while having antibacterial effect.

[0165] Data collection and analysis: Collect performance data of lightweight gypsum-based self-leveling mortar with different formulations.

[0166] Establish relationship model: use decision tree model to establish mathematical model between performance parameters and formulation components.

[0167] Reverse design optimization: use genetic algorithm to solve optimal formulation proportion inversely according to performance target. Find formulation combination meeting target performance requirement through iterative calculation.

[0168] Laboratory test: according to optimization result, laboratory small test formulation is: gypsum powder 54 parts, fly ash 16 parts, polyvinyl alcohol 1.3 parts, montmorillonite and bentonite each 0.2 parts, yellow pigment 0.1 part, nano silver ion antibacterial agent 0.2 part. Small scale test is carried out, and formulation is adjusted until performance target is met. Pilot scale amplification verifies feasibility of formulation, and production process is adjusted to adapt to industrial production.

[0169] Performance verification: test performance of produced mortar, and performance meets design requirement.

[0170] In other embodiments of the present application, the gypsum powder, the lightweight aggregate, the retarder, the water-retaining agent, and the additive. The weight ratio of each component is 45-60:10-25:0.8-1.5:0.3-0.8:0.1-5. The lightweight aggregate is at least one of expanded perlite, vermiculite, ceramsite, fly ash, pumice or volcanic slag; the retarder is at least one of citric acid, tartaric acid, phosphoric acid or polyvinyl alcohol; the water-retaining agent is at least one of cellulose ether, starch ether, polyacrylamide, bentonite or montmorillonite; and the additive is at least one of glass fiber, polypropylene fiber, pigment, nano silver ion antibacterial agent, quaternary ammonium salt antibacterial agent, fire retardant and water-resistant agent, which is used to adjust specific performance of the mortar, including but not limited to enhancing crack resistance, improving durability, imparting antibacterial performance, increasing fire resistance or enhancing water resistance.

[0171] It should be understood that, although each step in the flowchart involved in each embodiment as described above is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0172] Based on the same inventive concept, the application further provides a device for determining the proportion of the lightweight gypsum-based self-leveling mortar according to the method described above. The device provides a solution to the problem similar to the solution described in the method above, so the specific limitations in one or more device embodiments for determining the proportion of the lightweight gypsum-based self-leveling mortar provided below can refer to the limitations of the method for determining the proportion of the lightweight gypsum-based self-leveling mortar described above, which will not be repeated here.

[0173] In one embodiment of the application, as shown in Figure 5 A device for determining the proportion of a lightweight gypsum-based self-leveling mortar is provided, the device comprising:

[0174] The acquisition module 100 is configured to acquire first reference mortar data, the first reference mortar data comprising a plurality of first reference mortar formulations and a first reference performance parameter corresponding to each of the first reference mortar formulations.

[0175] The analysis module 200 is configured to generate a mortar analysis model based on a preset initial model and according to the first reference mortar data.

[0176] The acquisition module 100 is further configured to acquire a target performance parameter corresponding to a user demand.

[0177] The determination module 300 is configured to input the target performance parameter into the mortar analysis model and determine a target mortar formulation corresponding to the target performance parameter.

[0178] In another embodiment of the application, the analysis module 200 is further configured to construct a first function based on density based on a plurality of the first reference mortar formulations and a density corresponding to each of the first reference mortar formulations, construct a second function based on compressive strength based on a plurality of the first reference mortar formulations and a compressive strength corresponding to each of the first reference mortar formulations, and construct a third function based on flexural strength based on a plurality of the first reference mortar formulations and a flexural strength corresponding to each of the first reference mortar formulations, and use the first function, the second function, and the third function as the mortar analysis model.

[0179] In another embodiment of the application, the determination module 300 is further configured to acquire boundary conditions of a plurality of components corresponding to the target performance parameter, substitute a density corresponding to the target performance parameter into the first function, substitute a compressive strength corresponding to the target performance parameter into the second function, and substitute a flexural strength corresponding to the target performance parameter into the third function, and solve the target mortar formulation corresponding to the target performance parameter with the boundary conditions of the plurality of components as constraint conditions.

[0180] In another embodiment of the present application, the determining module 300 is further configured to determine actual performance parameters corresponding to the target mortar formula according to the target mortar formula, and determine whether the target mortar formula meets the user demand based on the actual performance parameters and the target performance parameters.

[0181] In another embodiment of the present application, the obtaining module 100 is further configured to obtain second reference mortar data including a plurality of second reference mortar formulas and second reference performance parameters corresponding to the plurality of second reference mortar formulas, determine predicted performance parameters corresponding to the plurality of second reference mortar formulas based on the mortar analysis model and the plurality of second reference mortar formulas, verify the mortar analysis model based on the plurality of predicted performance parameters and the plurality of second reference performance parameters, and replace the preset initial model if the verification fails.

[0182] In another embodiment of the present application, the obtaining module 100 is further configured to calculate a performance parameter mean value based on the plurality of second reference performance parameters, calculate a determination coefficient based on the performance parameter mean value and the predicted performance parameters and the second reference performance parameters corresponding to each second reference mortar formula, calculate a relative error corresponding to each second reference mortar formula based on the predicted performance parameters and the second reference performance parameters corresponding to each second reference mortar formula, determine an error mean value based on the relative error corresponding to each second reference mortar formula, and determine that the verification of the mortar analysis model is passed if the determination coefficient meets a first preset requirement and the error mean value meets a second preset requirement.

[0183] The above-described various modules in the proportioning device for the lightweight gypsum-based self-leveling mortar can be realized by software, hardware, or a combination thereof. The above-described various modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform operations corresponding to the above-described various modules.

[0184] In one embodiment of the present application, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in FIG. 1. Figure 6As shown in the figure. The computer device includes a processor, a memory and a network interface connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all related data for executing the light gypsum-based self-leveling mortar proportioning determination method. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to implement a light gypsum-based self-leveling mortar proportioning determination method.

[0185] Those skilled in the art can understand that, Figure 6 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0186] In an embodiment of the present application, a computer device is provided, including a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the light gypsum-based self-leveling mortar proportioning determination method in the above-mentioned embodiments.

[0187] In an embodiment of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the light gypsum-based self-leveling mortar proportioning determination method in the above-mentioned method embodiments.

[0188] In an embodiment of the present application, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps of the light gypsum-based self-leveling mortar proportioning determination method in the above-mentioned method embodiments.

[0189] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0190] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, the processes of the above-mentioned embodiments of each method can be included. Any reference to memory, database or other medium used in each embodiment provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in each embodiment provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in each embodiment provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0191] Each technical feature of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of each technical feature in the above embodiments are not described, however, as long as the combination of these technical features does not exist contradictory, it should be considered as the scope of the present application.

[0192] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for determining the mix proportion of lightweight gypsum-based self-leveling mortar, characterized in that, The method includes: Obtain first reference mortar data, which includes multiple first reference mortar formulations and a first reference performance parameter corresponding to each first reference mortar formulation; Based on the preset initial model, a mortar analysis model is generated according to the first reference mortar data; Obtain the target performance parameters corresponding to user requirements; Input the target performance parameters into the mortar analysis model to determine the target mortar formula corresponding to the target performance parameters; The preset initial model includes a mathematical fitting model, and the first reference performance parameters include density, compressive strength, and flexural strength; the generation of the mortar analysis model based on the preset initial model and the first reference mortar data includes: Based on a preset initial model, a density-based first function is constructed according to multiple first reference mortar formulations and the density corresponding to each first reference mortar formulation; Based on the preset initial model, a second function based on compressive strength is constructed according to multiple first reference mortar formulations and the compressive strength corresponding to each first reference mortar formulation; Based on the preset initial model, a third function based on flexural strength is constructed according to multiple first reference mortar formulations and the flexural strength corresponding to each first reference mortar formulation; The first function, the second function, and the third function are used as the mortar analysis model.

2. The method for determining the mix proportion of lightweight gypsum-based self-leveling mortar according to claim 1, characterized in that, The preset initial model includes at least one of the following: linear regression model, multivariate nonlinear regression model, neural network model, decision tree model, and support vector machine model.

3. The method for determining the mix proportion of lightweight gypsum-based self-leveling mortar according to claim 1, characterized in that, The step of inputting the target performance parameters into the mortar analysis model to determine the target mortar formula corresponding to the target performance parameters includes: Obtain the boundary conditions of multiple components corresponding to the target performance parameters; The target mortar formula corresponding to the target performance parameter is obtained by substituting the density corresponding to the target performance parameter into the first function, the compressive strength corresponding to the target performance parameter into the second function, and the flexural strength corresponding to the target performance parameter into the third function, and using the boundary conditions of multiple components as constraints.

4. The method for determining the mix proportion of lightweight gypsum-based self-leveling mortar according to claim 1, characterized in that, The method further includes: Based on the target mortar formula, determine the actual performance parameters corresponding to the target mortar formula; Based on actual performance parameters and target performance parameters, determine whether the target mortar formula meets the user's needs.

5. The method for determining the mix proportion of lightweight gypsum-based self-leveling mortar according to claim 1, characterized in that, The method for determining the mix proportion of the lightweight gypsum-based self-leveling mortar also includes: Obtain second reference mortar data, which includes multiple second reference mortar formulations and corresponding second reference performance parameters; Based on the mortar analysis model, the predicted performance parameters corresponding to the multiple second reference mortar formulations are determined according to the multiple second reference mortar formulations. The mortar analysis model is validated based on multiple predicted performance parameters and multiple second reference performance parameters. If the verification fails, the preset initial model will be replaced.

6. The method for determining the mix proportion of lightweight gypsum-based self-leveling mortar according to claim 5, characterized in that, The verification of the mortar analysis model based on multiple predicted performance parameters and multiple second reference performance parameters includes: The mean of the performance parameters is calculated based on multiple second reference performance parameters; The determination coefficient is calculated based on the average performance parameter and the predicted performance parameter and second reference performance parameter corresponding to each second reference mortar formula. Calculate the relative error corresponding to each second reference mortar formula based on the predicted performance parameters and second reference performance parameters corresponding to each second reference mortar formula; The mean error is determined based on the relative error corresponding to each second reference mortar formula; If the determination coefficient meets the first preset requirement and the mean error meets the second preset requirement, then the mortar analysis model is verified.

7. A device for determining the proportion of lightweight gypsum-based self-leveling mortar, characterized in that, The device includes: The acquisition module is used to acquire first reference mortar data, which includes multiple first reference mortar formulations and a first reference performance parameter corresponding to each first reference mortar formulation. The analysis module is used to generate a mortar analysis model based on a preset initial model and the first reference mortar data. The acquisition module is also used to acquire the target performance parameters corresponding to user requirements; The determination module is used to input the target performance parameters into the mortar analysis model and determine the target mortar formula corresponding to the target performance parameters. The preset initial model includes a mathematical fitting model, and the first reference performance parameters include density, compressive strength, and flexural strength. The analysis module is further configured to: construct a first function based on density according to the preset initial model, based on multiple first reference mortar formulations and the density corresponding to each first reference mortar formulation; construct a second function based on compressive strength according to the preset initial model, based on multiple first reference mortar formulations and the compressive strength corresponding to each first reference mortar formulation; construct a third function based on flexural strength according to the preset initial model, based on multiple first reference mortar formulations and the flexural strength corresponding to each first reference mortar formulation; and use the first function, the second function, and the third function as the mortar analysis model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images