Mechanism sand fineness modulus prediction method and system based on multiple linear regression algorithm

Abstract

The application discloses a mechanism sand fineness modulus prediction method and system based on a multiple linear regression algorithm, and the method comprises the following steps: acquiring multiple operation parameters of a mechanism sand production system; analyzing influence factors of the fineness modulus of the mechanism sand by using the multiple operation parameters to obtain influence factor analysis results; obtaining real-time operation parameters of the mechanism sand production system influencing the fineness modulus according to the influence factor analysis results; inputting the real-time operation parameters into a constructed multiple linear regression model to predict the fineness modulus based on a parameter linear relationship and obtain a fineness modulus prediction result. The application can accurately predict the fineness modulus of the mechanism sand to guide industrial production.

Description

Technical Field

[0001] This invention relates to the field of fineness modulus prediction technology for manufactured sand, and in particular to a method and system for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm. Background Technology

[0002] Manufactured sand has gradually become the main type of sand used in the construction and road and bridge industries, effectively alleviating the shortage of construction sand. The fineness modulus of sand is a crucial technical indicator for judging its coarseness. Improving the manufacturing process of manufactured sand, enhancing its quality, and standardizing and regulating its preparation are essential. The fineness modulus of manufactured sand is a vital indicator for evaluating its quality. Compared to traditional laboratory tests for fineness modulus, the testing cycle is longer, resulting in a certain lag in guiding production and affecting the stability of manufactured sand product quality. Summary of the Invention

[0003] The present invention aims to at least partially solve one of the technical problems in the related art.

[0004] Therefore, the purpose of this invention is to propose a method for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm. This method predicts the variable relationship of the fineness modulus through a linear regression algorithm and applies the prediction results to production, demonstrating high consistency.

[0005] Another objective of this invention is to propose a system for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm.

[0006] To achieve the above objectives, this invention proposes a method for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm, comprising:

[0007] Obtain multiple operating parameters of the manufactured sand production system;

[0008] The influencing factors of the fineness modulus of manufactured sand were analyzed using the aforementioned multiple operating parameters, and the results of the influencing factor analysis were obtained.

[0009] Based on the analysis results of the influencing factors, the real-time operating parameters of the manufactured sand production system that affect the fineness modulus are obtained.

[0010] The real-time operating parameters are input into the constructed multiple linear regression model to obtain the fineness modulus prediction result based on the linear relationship of the parameters.

[0011] The method for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm according to embodiments of the present invention may also have the following additional technical features:

[0012] Furthermore, in one embodiment of the present invention, the real-time operating parameters include the flow rate of the quantitative feeder, the flow rate of the finished product quantitative feeder, the rotation speed of the vertical shaft impact crusher, the rotation speed of the V-type classifier, and the rotation speed of the dust removal fan.

[0013] Furthermore, in one embodiment of the present invention, before inputting the real-time operating parameters into the constructed multiple linear regression model, the method further includes constructing the multiple linear regression model, including:

[0014] Obtain sample data of the real-time operating parameters;

[0015] The multiple linear regression model is constructed based on the linear relationship of the sample data.

[0016] Furthermore, in one embodiment of the present invention, after obtaining the multiple linear regression model, the method further includes:

[0017] The data relationship test is performed on the multiple linear regression model to obtain the relationship test results; wherein, the data relationship test includes correlation coefficient test, F test and t test;

[0018] Based on the relationship test results, the model function of the multiple linear regression model is determined, and the model parameters are optimized by solving the function to obtain the constructed multiple linear regression model.

[0019] Furthermore, in one embodiment of the present invention, the method further includes:

[0020] The fineness modulus of manufactured sand was calculated by actual measurement to obtain the measured fineness modulus results;

[0021] By comparing the measured results of the fineness modulus with the predicted results of the fineness modulus, the model parameters of the multiple linear regression model are updated based on the data comparison results.

[0022] To achieve the above objectives, another aspect of the present invention proposes a system for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm, comprising:

[0023] The initial parameter acquisition module is used to acquire multiple operating parameters of the manufactured sand production system;

[0024] The influencing factor analysis module is used to analyze the influencing factors of the fineness modulus of manufactured sand using the multiple operating parameters to obtain the influencing factor analysis results;

[0025] The operating parameter acquisition module is used to obtain the real-time operating parameters of the manufactured sand production system that affect the fineness modulus based on the analysis results of the influencing factors.

[0026] The modulus prediction module is used to input the real-time running parameters into the constructed multiple linear regression model to obtain the fineness modulus prediction result based on the linear relationship of the parameters.

[0027] The method and system for predicting the fineness modulus of manufactured sand based on the multiple linear regression algorithm of this invention predicts the variable relationship of fineness modulus through the linear regression algorithm, and uses the prediction results for production use, thereby improving the quality stability of manufactured sand products.

[0028] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0029] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0030] Figure 1 This is a flowchart of a method for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm according to an embodiment of the present invention;

[0031] Figure 2 This is a framework diagram of the dry sand making process according to an embodiment of the present invention;

[0032] Figure 3 This is a comparison chart of the measured and predicted fineness modulus values ​​of the finished sand according to an embodiment of the present invention.

[0033] Figure 4 This is a schematic diagram of the structure of a machined sand fineness modulus prediction system based on a multiple linear regression algorithm according to an embodiment of the present invention. Detailed Implementation

[0034] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0035] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0036] The following describes, with reference to the accompanying drawings, a method and system for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm, according to an embodiment of the present invention.

[0037] Figure 1 This is a flowchart of a method for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm, according to an embodiment of the present invention.

[0038] like Figure 1 As shown, the method includes, but is not limited to, the following steps:

[0039] S1, acquire multiple operating parameters of the manufactured sand production system;

[0040] S2, using multiple operating parameters to analyze the influencing factors of the fineness modulus of manufactured sand, and obtain the analysis results of the influencing factors;

[0041] S3, based on the analysis of influencing factors, obtain the real-time operating parameters of the manufactured sand production system that affect the fineness modulus;

[0042] S4 inputs the real-time running parameters into the constructed multiple linear regression model to obtain the fineness modulus prediction result based on the linear relationship of the parameters.

[0043] Understandably, taking a sand and gravel plant with an hourly output of 200 t / h as an example, the sand making process uses dry sand production, with cave debris gneiss as the raw material. The process flow is as follows: materials with a particle size of 0-30 mm are crushed, screened, and graded to produce finished sand with a particle size of 0-5 mm. The content of sand with different particle sizes in the finished sand is measured by the fineness modulus. (The process is described in the original text.) Figure 2 As shown, where:

[0044] A quantitative feeder is used for system feeding and can adjust the system feed flow rate.

[0045] Vertical shaft impact crushers achieve "stone-on-stone" and "stone-on-iron" crushing. The material is subjected to two or more impacts, friction and grinding in the vortex crushing chamber. In addition, the material is crushed into sand by impacting each other throughout the crushing process.

[0046] The V-type air classifier's matching fan generates airflow. The fine powder in the material at the feed inlet is less affected by gravity than by the horizontal force brought by the airflow, and is carried by the airflow out of the air classifier and into the sand and powder collector.

[0047] Under the action of the system fan, the dust-laden gas slows down due to the inertia and weight of the dust. Coarse dust particles fall directly into the ash hopper and are discharged through the ash discharge device. Other lighter and finer dust particles rise with the airflow and are adsorbed on the outer surface of the filter bags. After being filtered by the filter bags, the clean gas enters the clean air chamber of the upper box and is collected in the air outlet duct for discharge.

[0048] A vibrating screen uses a reasonably adjustable screen angle and mesh size to classify mixtures of different particle sizes according to particle size. The system is equipped with 3mm and 5mm screen openings, enabling the separation of sand in particle size ranges of 0-3mm and 3-5mm. The gradation of the finished sand is achieved through quantitative feeders 1 and 2.

[0049] The main equipment selection is shown in Table 1:

[0050] Table 1

[0051]

[0052] Specifically, the influencing factors are first analyzed based on the multi-state operating parameters of the manufactured sand production system.

[0053] The effects of feed rate and vertical shaft impact crusher speed on fineness modulus were determined. It can be understood that, with the same material particle size and crusher rotor speed, increasing the feed rate decreases the stone powder content in the finished sand and increases the fineness modulus. When the material moisture content, feed rate, and crusher rotor speed are stable, increasing the material particle size increases the stone powder content and decreases the fineness modulus. With the same material particle size, moisture content, and feed rate, increasing the crusher rotor speed increases the stone powder content in the sand and decreases the fineness modulus.

[0054] The influence of a V-type air classifier on the fineness modulus was determined. Different airflow volumes correspond to different classification particle sizes; larger particle sizes require higher airflow velocities, thus necessitating larger airflow volumes. The minimum particle size range selected by the V-type air classifier is inversely proportional to the airflow volume. With a fixed feed rate, increasing the airflow volume leads to an increase in the fineness modulus.

[0055] Determine the impact of the dust collector on the fineness modulus. The filtration velocity of a pulse-jet bag filter is directly proportional to the logarithm of the dust particle size. Since the internal structure of the dust collector's duct is fixed and does not change, the filtration velocity can be adjusted by regulating the fan airflow. That is, with a fixed feed rate, increasing the airflow will increase the fineness modulus.

[0056] The influence of the finished product quantitative feeder ratio on the fineness modulus was determined. Finished product quantitative feeder 1 feeds sand and gravel with a particle size range of 3-5mm, while finished product quantitative feeder 2 feeds sand and gravel with a particle size range of 0-3mm. When there is more 3-5mm sand and gravel in the ratio, the degree of increase in fineness modulus is greater; when there is more 0-3mm sand and gravel in the ratio, the degree of decrease in fineness modulus is less.

[0057] Furthermore, based on the above influencing factors, the flow rate of the quantitative feeder, the flow rate of the finished product quantitative feeder 1, the flow rate of the finished product quantitative feeder 2, the speed of the vertical shaft crusher, the speed of the V-type classifier, and the speed of the dust removal fan are selected as the research objects of the manufactured sand production system.

[0058] Furthermore, a multiple linear regression model is constructed.

[0059] When a random variable y has a linear relationship with two or more variables, it is called a multiple linear regression relationship. The linear regression model is as follows:

[0060] y = α0 + α1x1 + α2x2 + ... + α m x m +β (1)

[0061] In the formula: α0, α1, α2,…, α m Here, β is the regression coefficient, and β is the random error. The sample has n sets of test data (x...). i1 x i2 , ..., x im ;y i (i = 1, 2, ..., m), then the above linear regression model can be expressed as

[0062]

[0063] Its matrix form is

[0064]

[0065] The simplified form of matrix (3) is:

[0066] Y = Xα + β (4)

[0067] The adjustment model Q of the multiple linear regression equation is

[0068]

[0069] Apply equation (5) to α0, α1, α2, ..., α m Taking the partial derivatives and applying the extremum principle, we set the partial derivatives to zero. After simplification, we obtain the following matrix-form system of multivariate normal equations.

[0070] x T (YX·α)=O, that is

[0071] X T ·X·α=X T ·Y (6)

[0072] Solving this system of equations yields the estimated matrix of regression parameters.

[0073]

[0074] Furthermore, the multiple linear regression model was tested.

[0075] Correlation coefficient test: The correlation coefficient is an indicator used to measure the goodness of fit of a linear model. Mathematically, it is the ratio of the regression square to the total sum of squares, as shown in the following formula:

[0076]

[0077]

[0078] In the formula, k is the number of independent variables, n is the total number of samples, SSR is the deviation caused by the independent variables, i.e., the regression sum of squares, and the formula is as follows: SST represents the sum of squares of the deviations between the observed values ​​and the mean of the dependent variable, and SSE is the sum of squares of the residuals caused by experimental errors, etc. If xi represents the true observed value, then... The average value of the actual observations is represented by... The fitted value is represented by . Then the formulas for SSR, SSE, and SST can be expressed as equations (10) to (12), respectively.

[0079]

[0080]

[0081]

[0082] F-test: The F-test is used to test whether the relationship between the independent and dependent variables in a linear model is significant, as shown in equation (13).

[0083]

[0084] In the formula, k is the number of independent variables and n is the total number of samples.

[0085] t-test: The t-test can be used to determine whether a variable should be retained as an independent variable in the model, as shown in equation (14).

[0086]

[0087] In the formula,

[0088] Furthermore, this invention performs actual calculations on the fineness modulus of manufactured sand to obtain the measured fineness modulus results; compares the measured fineness modulus results with the predicted fineness modulus results, and updates the model parameters of the multiple linear regression model based on the data comparison results.

[0089] As an example, with the feeder at the inlet end maintaining a stable feed rate of 180 t / h, the operating speed of one piece of equipment was adjusted every hour. After the adjustment, samples were taken at 40-minute intervals. First, the surface layer of the sample was removed, and then eight approximately equal amounts of sand were randomly selected from different parts of the stockpile to form a sample group, totaling 4.4 kg. The samples were dried, sieved, and weighed in the laboratory to determine the fineness modulus of the sand.

[0090] Record the equipment parameters corresponding to the fineness modulus values ​​of each group of sand: flow rate of finished product feeder 1, flow rate of finished product feeder 2, speed of vertical shaft impact crusher, speed of V-type classifier, and speed of dust collector fan.

[0091] Within each set of data, the relevant equipment parameters and the fineness modulus have a certain correlation. Check whether there are abnormal or contradictory values ​​in each set of data, remove abnormal and invalid data, and select representative parameters with regularity for model building and parameter optimization.

[0092] Furthermore, the present invention provides a prediction model.

[0093] A multiple linear regression model was constructed using the preprocessed data, with the fineness modulus M as the dependent variable. x The independent variables are the batching ratio (x1), vertical shaft crusher speed (x2), V-type blower speed (x3), and dust collector fan speed (x4). Correlation coefficient tests, F-tests, and t-tests were performed, and the predicted results were then compared with the test data.

[0094] The correlation coefficient test of this invention. The results of the correlation coefficient test are shown in Table 2. R represents the fitting effect; the larger the value, the better the fitting effect.

[0095] Table 2 Correlation coefficient test

[0096]

[0097] The F-test results are shown in Table 3. As can be seen from Table 3, the F-test results are less than 0.01. Based on the actual results, it was determined whether there was a significant impact on the fineness modulus of Mx, and insignificant equipment was eliminated. Factors showing significant effects are listed in Table 4.

[0098] Table 3 Significance Tests

[0099] Model sum of squares Degrees of freedom Mean Square F Significance return 3.819 4 0.955 57.45 0 residual 0.349 21 0.017 - - Total variation 4.168 25 - - -

[0100] The t-test results are shown in Table 4. Unstandardized coefficients are used to establish the regression equation. Standardized coefficients represent the degree of influence of the independent variable on the dependent variable; partial regression coefficients are used to determine whether the influence of a certain independent variable on the dependent variable is statistically significant. When it is less than 0.05, it is statistically significant; when it is less than 0.01, it is highly statistically significant.

[0101] Table 4. Results of the T-test

[0102]

[0103] Furthermore, by substituting the standardized coefficients into equation (1), the multiple linear regression equation is obtained, as shown in equation (15).

[0104] M x =3.298x1-0.037x2+0.007x3+0.02x4+2.34 (15)

[0105] Where x1 is the batching ratio, x2 is the vertical shaft crusher speed, x3 is the V-type classifier speed, and x4 is the dust removal fan speed.

[0106] To verify the established multiple linear regression model, the measured and predicted fineness modulus values ​​of the finished sand produced by the sand and gravel plant were compared, for example... Figure 3 As shown, the average deviation between the predicted and measured values ​​was found to be 0.02, indicating a high degree of model fit and accurate prediction of the fineness modulus.

[0107] By implementing the method of this invention, it can be seen that when the strength, composition, moisture content, and mud content of the parent material are stable, the model established based on the test data has high accuracy and the deviation of the predicted product fineness modulus value is small. It was found that the deviation between the actual measured value and the predicted value fluctuates within ±0.2, which has good guiding significance.

[0108] The model was established by selecting variables that affect the fineness modulus value through theoretical analysis and eliminating invalid variables through model optimization. The model is correlated with the variables; even after significant changes in the parent material, only the accuracy of the fineness modulus value is affected, but the trend of the fineness modulus value change is consistent with the theoretical analysis. Due to the limited number of samples selected, the predictive accuracy of the model is affected.

[0109] The method for predicting the fineness modulus of manufactured sand based on the multiple linear regression algorithm according to embodiments of the present invention predicts the variable relationship of fineness modulus through the linear regression algorithm and uses the prediction results for production, exhibiting high consistency.

[0110] To achieve the above embodiments, such as Figure 4 As shown, this embodiment also provides a system 10 for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm. The system 10 includes: an initial parameter acquisition module 100, an influencing factor analysis module 200, an operating parameter acquisition module 300, and a modulus result prediction module 400.

[0111] The initial parameter acquisition module 100 is used to acquire multiple operating parameters of the manufactured sand production system.

[0112] The influencing factor analysis module 200 is used to analyze the influencing factors of the fineness modulus of manufactured sand using multiple operating parameters to obtain the influencing factor analysis results;

[0113] The operating parameter acquisition module 300 is used to obtain the real-time operating parameters of the manufactured sand production system that affect the fineness modulus based on the results of the influencing factor analysis.

[0114] The modulus prediction module 400 is used to input real-time running parameters into a pre-constructed multiple linear regression model to obtain the modulus prediction result based on the linear relationship of the parameters.

[0115] Furthermore, real-time operating parameters include the flow rate of the quantitative feeder, the flow rate of the finished product quantitative feeder, the speed of the vertical shaft impact crusher, the speed of the V-type classifier, and the speed of the dust collector fan.

[0116] Furthermore, prior to the modulus result prediction module 400, a model construction module is also included, comprising:

[0117] The data acquisition subunit is used to acquire sample data of real-time operating parameters;

[0118] The model construction sub-unit is used to construct a multiple linear regression model based on the linear relationship of the sample data, so as to obtain the constructed multiple linear regression model.

[0119] Furthermore, the model construction module is also used for:

[0120] The constructed multiple linear regression model is subjected to data relationship tests to obtain the relationship test results; the data relationship tests include correlation coefficient tests, F-tests and t-tests.

[0121] Based on the relationship test results, determine the model function of the multiple linear regression model, and solve it to optimize the model parameters to obtain the constructed multiple linear regression model.

[0122] Furthermore, system 10 also includes a model update module for:

[0123] The fineness modulus of manufactured sand was calculated by actual measurement to obtain the measured fineness modulus results;

[0124] By comparing the measured results of the fineness modulus with the predicted results of the fineness modulus, the model parameters of the multiple linear regression model are updated based on the data comparison results.

[0125] The fineness modulus prediction system for manufactured sand based on the multiple linear regression algorithm according to embodiments of the present invention predicts the variable relationship of fineness modulus through the linear regression algorithm and uses the prediction results for production, exhibiting high consistency.

[0126] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0127] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0128] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for predicting the fineness modulus of manufactured sand based on a multiple linear regression algorithm, characterized by, The method comprises the following steps: obtaining a plurality of operating parameters of a manufactured sand production system; analyzing influencing factors of a fineness modulus of manufactured sand by using the plurality of operating parameters to obtain an influencing factor analysis result; obtaining real-time operating parameters of the manufactured sand production system that affect the fineness modulus according to the influencing factor analysis result; obtaining sample data of the real-time operating parameters; constructing the multiple linear regression model according to a linear relationship of the sample data; inputting the real-time operating parameters into the constructed multiple linear regression model to predict the fineness modulus based on a linear relationship of parameters to obtain a fineness modulus prediction result; the multiple linear regression model is constructed, comprising: constructing a linear regression model: wherein ; The sample has n groups of test data The linear regression model is: ； a correction model Q of the multiple linear regression equation is: ； The partial derivatives are taken to obtain a system of multivariate normal equations: The partial derivatives are taken to obtain a system of multivariate normal equations: ； solving the multiple normal equation set to obtain an estimated value matrix of regression parameters: ； testing a correlation coefficient of the multiple linear regression model by a ratio of a regression square to a total square: where k is the number of independent variables, n is the total number of samples, SSR is a deviation caused by independent variables, i.e., a regression square sum, SST represents a deviation square sum of a difference between observed values of a dependent variable and a mean value, and SSE is a residual square sum caused by experimental errors; If represents the true observed value, represents the mean of the true observed value, and represents the fitted value, then the SSR, SSE, and SST formulas are respectively ； testing a relationship between independent variables and a dependent variable in the linear model based on F testing; deciding independent variables to be retained in the model by t testing; determining a model function of the multiple linear regression model according to a relationship test result, and solving to optimize model parameters to obtain the constructed multiple linear regression model.

2. The method of claim 1, wherein, The real-time operating parameters include a flow of a quantitative feeder, a flow of a finished product quantitative feeder, a rotational speed of a vertical shaft crusher, a rotational speed of a V-type powder concentrator, and a rotational speed of a dust removal fan.

3. The method of claim 1, wherein, The method further comprises: actually measuring and calculating the fineness modulus of manufactured sand to obtain a fineness modulus actual measurement result; comparing the fineness modulus actual measurement result and the fineness modulus prediction result, and updating model parameters of the multiple linear regression model according to a data comparison result.

4. A mechanism sand fineness modulus prediction system based on a multiple linear regression algorithm, characterized by, The system is used to implement the method for predicting the fineness modulus of manufactured sand based on the multiple linear regression algorithm, and comprises: an initial parameter obtaining module configured to obtain a plurality of operating parameters of a manufactured sand production system; an influencing factor analysis module configured to analyze influencing factors of a fineness modulus of manufactured sand by using the plurality of operating parameters to obtain an influencing factor analysis result; an operating parameter obtaining module configured to obtain real-time operating parameters of the manufactured sand production system that affect the fineness modulus according to the influencing factor analysis result; a model constructing module configured to construct a multiple linear regression model; a modulus result predicting module configured to input the real-time operating parameters into the constructed multiple linear regression model to predict the fineness modulus based on a linear relationship of parameters to obtain a fineness modulus prediction result; the model constructing module comprises: a data obtaining subunit configured to obtain sample data of the real-time operating parameters; a model constructing subunit configured to construct the multiple linear regression model according to a linear relationship of the sample data to obtain the constructed multiple linear regression model; the model constructing module is further configured to: The constructed multiple linear regression model is subjected to data relationship test to obtain a relationship test result; wherein, the data relationship test comprises correlation coefficient test, F test and t test; According to the relationship test result, a model function of the multiple linear regression model is determined, and the constructed multiple linear regression model is solved to obtain an optimized model parameter.

5. The system of claim 4, wherein, The real-time operation parameters comprise quantitative feeder flow, finished product quantitative feeder flow, vertical shaft crusher rotating speed, V-type powder concentrator rotating speed and dust removal fan rotating speed.

6. The system of claim 4, wherein, The system further comprises a model updating module configured to: The fineness modulus of the machine-made sand is subjected to real measurement calculation to obtain a fineness modulus real measurement result; The fineness modulus real measurement result is compared with the fineness modulus prediction result, and the model parameter of the multiple linear regression model is updated according to a data comparison result.

Images