Method for predicting compressive strength of ordinary Portland cement based on ridge regression

Abstract

The invention discloses a method for predicting compressive strength of ordinary Portland cement based on ridge regression, comprising the following steps: collecting a plurality of groups of cement samples, each group of cement samples comprising mineral components, specific surface area and 28d compressive strength data, taking the mineral components and the specific surface area as independent variables, taking the 28d compressive strength data as dependent variables, and constructing and training a ridge regression model; and inputting mineral components and specific surface area data of to-be-detected cement into the ridge regression model to obtain a 28d compressive strength prediction value. According to the method, the mechanical property of the cement can be quickly and accurately predicted on the premise of not depending on the traditional 28-day test period, so that the cement quality is pre-judged in advance; potential unqualified materials can be identified before cement is put into use, the judgment period is greatly shortened, the quality control efficiency in the construction process is improved, the risk that a concrete structure does not reach the standard due to insufficient cement strength is reduced from the source, and the engineering quality and the structure safety are guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engineering materials, and particularly relates to a method for predicting compressive strength of ordinary Portland cement based on ridge regression. BACKGROUND

[0002] Concrete is an important building material widely used in modern construction engineering, and its quality is directly related to the safety and durability of engineering structures. Among the constituent materials of concrete, cement as the basic binding material plays a decisive role in the final strength of concrete. The compressive strength of cement is an important indicator for evaluating its performance and quality, especially for concrete used in load-bearing structures, the strength grade and quality stability of which are of great importance.

[0003] At present, the type of cement commonly used in construction engineering is ordinary Portland cement. According to the current national standards or industry specifications, the compressive strength of ordinary Portland cement needs to be determined after curing for 28 days (referred to as 28d) through standard test methods, which is used as the basis for final evaluation of its strength grade and whether it is qualified. However, the 28d compressive strength test period is relatively long, and it is often difficult to wait for the completion of the period before deciding whether to use a batch of cement in actual engineering.

[0004] Limited by the storage capacity of cement production enterprises and concrete mixing stations, as well as the requirements of construction site engineering progress and continuity, cement is usually used for pouring of concrete structures before the 28d strength test results are obtained. This "use first and evaluate later" approach has certain advantages in terms of construction efficiency, but it also brings greater quality risks: if the 28d strength of cement does not meet the standard, it may lead to insufficient overall strength of the concrete structure, thereby affecting the safety and service life of the project, and even causing rework, economic losses and safety hazards.

[0005] Therefore, how to evaluate the quality of cement as early as possible and accurately, especially to predict its 28d compressive strength, without affecting the construction progress, has become a technical problem to be solved in the field of building material detection and quality control. SUMMARY

[0006] In view of the above technical problems of the prior art, the present application aims to provide a method for predicting the compressive strength of ordinary Portland cement with short time consumption and high accuracy.

[0007] To solve the above technical problems, the technical scheme adopted by the present application is as follows:

[0008] A method for predicting the compressive strength of ordinary Portland cement based on ridge regression, comprising the following steps: collecting a plurality of groups of cement samples, each group of cement samples including mineral components, specific surface area and 28d compressive strength data, taking the mineral components and specific surface area as independent variables and the 28d compressive strength data as dependent variables, constructing a ridge regression model, and training the ridge regression model using the cement samples; inputting the mineral components and specific surface area data of the cement to be tested into the ridge regression model to obtain a 28d compressive strength prediction value.

[0009] As an optimization, the mineral components include tricalcium silicate, dicalcium silicate, tricalcium aluminate, tetracalcium aluminoferrite and gypsum.

[0010] As an optimization, the ridge regression model (Rc, 28) = aX1-bX2-cX3-dX4+eX5-fX6+j.

[0011] The coefficients satisfy:

[0012] a: 41.961-50.092, b: 182.553-271.758, c: 53.125-60.004, d: 7.115-22.005,

[0013] e: 275.182-338.027, f: 28.222-29.206, j: 17.714-23.773.

[0014] In the formula, X1 is the tricalcium silicate data, X2 is the dicalcium silicate data, X3 is the tricalcium aluminate data, X4 is the tetracalcium aluminoferrite data, X5 is the gypsum data, and X6 is the specific surface area data.

[0015] As an optimization, the mineral components further include F-glass, S-glass and inactive phase, the F-glass is an amorphous glass phase in fly ash, and the S-glass is an amorphous glass phase in mineral powder.

[0016] The ridge regression model (Rc, 28) = aX1-bX2-cX3-dX4+eX5-fX6-gX7-hX8+iX9+j.

[0017] The coefficients satisfy:

[0018] g: 0.500-2.446, h: 31.604-37.447, i: 0.053-0.072.

[0019] In the formula, X7 is the F-glass data, X8 is the S-glass data, and X9 is the inactive phase data.

[0020] As an optimization, the ridge parameter K value of the ridge regression model is determined by a ridge trace analysis method, and the K value is selected in the range of 0.01-0.15.

[0021] Compared with the prior art, the cement mechanical property can be quickly and accurately predicted without relying on the traditional 28-day test cycle, so that the quality of the cement is judged in advance; the prediction model constructed by using the ridge regression algorithm has good fitting performance, can effectively alleviate the problem of multicollinearity, improve the stability and prediction accuracy of the model, has the ability of rapid analysis and processing, and meets the dual demands of timeliness and accuracy in engineering practice; various factors affecting the 28d compressive strength of the cement are fully considered, the model parameters are reasonably set, the model has strong generalization ability, is suitable for various production batches and ordinary portland cement of different sources, and has wide engineering applicability; through the early prediction of the 28d compressive strength of the cement, potential unqualified materials can be identified before the cement is put into use, the judgment cycle is greatly shortened, the quality control efficiency in the construction process is improved, the risk of substandard concrete structure caused by insufficient cement strength is reduced from the source, and the engineering quality and structure safety are ensured. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 is a flowchart of the present application;

[0023] Figure 2 is a 28d compressive strength ridge regression ridge trace diagram of the present application;

[0024] Figure 3 is a comparison diagram of the 28d compressive strength measured value and the predicted value of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0026] The common portland cement compressive strength prediction method based on the ridge regression in the specific embodiment collects a plurality of groups of cement samples, each group of cement samples including mineral components, specific surface area and 28d compressive strength data, wherein the mineral components include tricalcium silicate, dicalcium silicate, tricalcium aluminate, tetracalcium aluminoferrite, gypsum, F-glass body, S-glass body and non-active phase, the F-glass body is an amorphous glass body phase in fly ash, and the S-glass body is an amorphous glass body phase in mineral powder; the mineral components and the specific surface area are taken as independent variables, and the 28d compressive strength data is taken as a dependent variable to construct a ridge regression model, and the ridge regression model is trained by using the cement samples; the mineral component and the specific surface area data of the cement to be measured are input into the ridge regression model to obtain a 28d compressive strength prediction value.

[0027] The ridge regression model (Rc, 28) = aX1-bX2-cX3-dX4+eX5-fX6-gX7-hX8+iX9+j;

[0028] The coefficients satisfy:

[0029] a: 41.961-50.092, b: 182.553-271.758, c: 53.125-60.004, d: 7.115-22.005, e: 275.182-338.027, f: 28.222-29.206, j: 17.714-23.773; g: 0.500-2.446, h: 31.604-37.447, i: 0.053-0.072;

[0030] In the formula, X1 is the tricalcium silicate data, X2 is the dicalcium silicate data, X3 is the tricalcium aluminate data, X4 is the tetracalcium aluminoferrite data, X5 is the gypsum data, X6 is the specific surface area data, X7 is the F-glass body data, X8 is the S-glass body data, and X9 is the non-active phase data.

[0031] The ridge parameter K value of the ridge regression model is determined by a ridge trace analysis method, and the K value is selected in the range of 0.01-0.15.

[0032] In the specific implementation, the cement mineral composition data is collected by XRD full spectrum fitting quantitative analysis technology, the cement specific surface area is measured by a cement specific surface area measurement method, and the 28d compressive strength of the cement is measured by referring to a cement mortar strength test method; finally, the cement mineral composition (tricalcium silicate, dicalcium silicate, tricalcium aluminate, tetracalcium aluminoferrite, gypsum, F-glass body, S-glass body and non-active phase), the specific surface area are taken as independent variables, and the 28d compressive strength is taken as a dependent variable to form a sample set, and the effective sample amount in the example is 115 groups.

[0033] Multiple regression analysis needs to be based on the highly correlated between variables, need to each independent variable and dependent variable for a separate normality test, and then analyze the correlation between independent variables and dependent variables.

[0034] The normality test is performed on the sample data set of each variable by statistical test method. The effective sample size is 115 groups. The Kolmogorov-Smirnov test is used. If the absolute value of kurtosis is less than 10 and the absolute value of skewness is less than 3, it is basically acceptable as normal distribution. After testing, all variable data sets in this embodiment can be considered to have normality characteristics.

[0035] The correlation between independent variables and dependent variables is analyzed by using the bivariate correlation module in the data analysis software. According to the normality characteristics of the variable data set, Pearson correlation coefficient and two-tailed significance test are selected for analysis. The significance p value is used to determine whether the variables are correlated, and the correlation coefficient is used to determine the strength of the correlation. Through the analysis of the output results, most of the independent variables are significantly correlated with the dependent variables, that is, most of the mineral composition and specific surface area of Portland cement are correlated with the 28d compressive strength.

[0036] First ridge regression analysis: the independent variables and dependent variables are substituted into the ridge regression model to obtain the ridge trace graph (standardized regression coefficient trend graph with K value change, as shown in Figure 2 ), in which the independent variables are tricalcium silicate (X1), dicalcium silicate (X2), tricalcium aluminate (X3), tetracalcium alumino-ferite (X4), gypsum (X5), F-glass body (X6), S-glass body (X7), non-active phase (X8), and specific surface area (X9), and Y is the dependent variable. Confirm the K value combined with the ridge trace graph. The K value is selected in the range of 0.01-0.15.

[0037] Second ridge regression analysis: the K value is substituted into the ridge regression model again for regression fitting to obtain the ridge regression prediction model of the 28d compressive strength of Portland cement: (Rc, 28) = aX1-bX2-cX3-dX4+eX5-fX6-gX7-hX8+iX9+j;

[0038] In which different K values correspond to different non-standardized regression coefficients, and the selection range of each coefficient is:

[0039] a: 41.961-50.092, b: 182.553-271.758, c: 53.125-60.004, d: 7.115-22.005,

[0040] e: 275.182-338.027, f: 28.222-29.206, g: 0.500-2.446, h: 31.604-37.447, i: 0.053-0.072, j: 17.714-23.773;

[0041] In this example, K=0.01, the cement mineral composition and specific surface area data are substituted into the ridge regression prediction model to obtain the 28d mechanical property prediction value, the calculation of the correlation error value is shown in Table 1, and compared with the measured value, the results are shown in Figure 3 The average error of the 28d compressive strength prediction value is 1.731MPa, which is relatively small compared with the measured value, and has high accuracy, providing a new method for predicting the 28d compressive strength of Portland cement.

[0042]

[0043] Table 1

[0044] Finally, it should be pointed out that the above examples are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described by referring to the preferred embodiments of the present application, it should be understood by those skilled in the art that various changes can be made in form and details without departing from the spirit and scope of the present application as defined by the appended claims.

Claims

1. A method for predicting the compressive strength of ordinary Portland cement based on ridge regression, characterized in that: Several sets of cement samples were collected. Each set of cement samples included mineral composition, specific surface area and 28-day compressive strength data. Mineral composition and specific surface area were used as independent variables and 28-day compressive strength data were used as dependent variables. A ridge regression model was constructed and trained using cement samples. The mineral composition and specific surface area data of the cement to be tested are input into the ridge regression model to obtain the predicted value of the 28-day compressive strength.

2. The method for predicting the compressive strength of ordinary Portland cement based on ridge regression according to claim 1, characterized in that: The mineral components include tricalcium silicate, dicalcium silicate, tricalcium aluminate, tetracalcium aluminoferrite, and gypsum.

3. The method for predicting the compressive strength of ordinary Portland cement based on ridge regression according to claim 2, characterized in that: The ridge regression model (Rc, 28) = aX1 - bX2 - cX3 - dX4 + eX5 - fX6 + j; The coefficients satisfy: a: 41.961~50.092, b: 182.553~271.758, c: 53.125~60.004, d: 7.115~22.005, e: 275.182~338.027, f: 28.222~29.206, j: 17.714~23.773; In the formula, X1 is the tricalcium silicate data, X2 is the dicalcium silicate data, X3 is the tricalcium aluminate data, X4 is the tetracalcium aluminoferrite data, X5 is the gypsum data, and X6 is the specific surface area data.

4. The method for predicting the compressive strength of ordinary Portland cement based on ridge regression according to claim 3, characterized in that: The mineral components also include F-glass, S-glass and inactive phases, where F-glass is the amorphous glass phase in fly ash and S-glass is the amorphous glass phase in mineral powder; The ridge regression model (Rc, 28) = aX1 - bX2 - cX3 - dX4 + eX5 - fX6 - gX7 - hX8 + iX9 + j; The coefficients satisfy: g: 0.500~2.446, h: 31.604~37.447, i: 0.053~0.072; In the formula, X7 represents F-vitreous phase data, X8 represents S-vitreous phase data, and X9 represents inactive phase data.

5. The method for predicting the compressive strength of ordinary Portland cement based on ridge regression according to any one of claims 1 to 4, characterized in that: The ridge parameter K value of the ridge regression model is determined by ridge trace plot analysis, and the K value is selected in the range of 0.01 to 0.15.

Images