A method for predicting fatigue life of solid waste fiber concrete

Abstract

The application discloses a kind of solid waste fiber concrete fatigue life prediction method, belong to the technical field of concrete life detection;Including the following steps: step one: using solid waste to make concrete sample m parts, and the alkali activation is carried out to the concrete sample, the physical characteristics of concrete sample are measured;Step two: establish test environment, place concrete sample in test environment, according to cycle time, the property of concrete sample is measured, including n kinds of indexes, form data group;Step three: using data group as calculation data, data standardization is carried out, the calculation of information amount is carried out, and the constructed concrete life prediction model is input;Step four: by means of concrete life prediction model, the service life of concrete is obtained.The application adopts the above method, establishes concrete life prediction model, and the strength of concrete is predicted by the index change under simulated environment, and finally realizes the life prediction of concrete.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of concrete data calculation, and particularly relates to a method for predicting fatigue life of solid waste fiber concrete. BACKGROUND

[0002] With the continuous improvement of the quality requirements of building engineering, as a common building material, concrete is very widely used in long-term engineering. The concrete is affected by various factors in the use process, such as environment, wind speed, etc. These factors lead to the reduction of the service life of the concrete, and further affect the structural integrity and service life of the building. The traditional concrete crack resistance monitoring method mainly relies on manual detection and field test, and has the problems of low detection precision and low efficiency. SUMMARY

[0003] The purpose of the present application is to provide a method for predicting the fatigue life of solid waste fiber concrete. The data of short-period concrete samples is collected, and a concrete life prediction model is established to predict the strength change of the concrete, so as to realize the life prediction of the concrete. The service life of the concrete is predicted by the method, and the service life of the concrete is predicted.

[0004] To achieve the above purpose, the present application provides a method for predicting the fatigue life of solid waste fiber concrete, comprising the following steps:

[0005] Step one: m parts of concrete samples are made by using solid waste, and the concrete samples are subjected to alkali activation, and the physical properties of the concrete samples are measured;

[0006] Step two: a test environment is established, the concrete samples are placed in the test environment, and the concrete samples are collected according to the cycle time, including n indexes, to form a data set;

[0007] Step three: the data set is used as calculation data, and data standardization is performed first, and then information amount calculation is performed, and the established concrete life prediction model is inputted;

[0008] Step four: the service life of the concrete is obtained by means of the concrete life prediction model.

[0009] Preferably, the specific process of step one is as follows:

[0010] m parts of concrete samples are made, the size of the concrete samples is 100mm*100mm*100mm, and standard curing is performed. The concrete samples are subjected to alkali activation, and the physical properties of the concrete samples are measured, including compressive strength, water absorption rate and porosity.

[0011] Preferably, the specific process of step two is as follows:

[0012] The testing environments include marine, hot and humid, and cold and dry environments. Concrete samples are tested in these environments. There are two types of testing periods: positive and negative. Positive testing is conducted more frequently in the early stages of the test, while negative testing is conducted more frequently in the later stages. The collected indicators include the physical properties mentioned in step one, such as compressive strength, water absorption, and porosity. The mass change rate and expansion rate of the concrete samples are also measured. The above data are arranged in chronological order to form a data set.

[0013] Preferably, in step three, the data set collected in step two is input into the concrete life prediction model. Specifically, the concrete life prediction model is set as a LightGBM+CRITIC weighted model, and the processing procedure is as follows:

[0014] First, the weighting stage of CRITIC is performed. The positive index is set as compressive strength and standardized. The negative indexes are set as water absorption rate, porosity, and expansion rate and reverse standardized. The cycle time is logarithmically transformed and then standardized again. The information content is calculated using the above indicators. The weighting result is obtained according to the calculated information content. The specific calculation process is as follows:

[0015] The compressive strength is normalized using the following formula:

[0016]

[0017] In the above formula, x' ij Let x be the normalized value of the compressive strength of the i-th sample on the j-th day. ij x represents the compressive strength value of the i-th sample on the j-th day. j This represents the compressive strength value of all concrete samples on day j;

[0018] The process of reverse standardizing water absorption, porosity, and expansion rate is as follows:

[0019]

[0020] In the above formula, a' ij a represents the standardized value of water absorption, porosity, or expansion rate. ij This represents the original value of water absorption rate, porosity, or expansion rate for the i-th sample on the j-th day. j This represents the value of water absorption, porosity, or expansion rate of the corresponding concrete sample on day j.

[0021] The amount of information is calculated using the contrast intensity formula, as follows:

[0022]

[0023] In the above formula, m represents the number of concrete samples. This represents the standardized mean, including the preceding x'. ij and a' ij The formula for calculating information content is as follows:

[0024] C j =σ j ×R j

[0025]

[0026] In the above formula, R j The conflicting nature of the current indicators, r jk This represents the correlation coefficient between indicator j and indicator k, where n represents the total number of indicators, and C... j This represents the overall information carrying capacity of the j-th indicator;

[0027] The LightGBM model was built and its parameters were trained. The training process used temporal cross-validation and early stopping mechanisms to assist training. The features were weighted according to the weight allocation results obtained by CRITIC weight calculation.

[0028] Preferably, the parameters of the LightGBM model are set as follows, including tree structure parameters, regularization parameters, and training parameters; the tree structure control parameters are as follows: the number of leaf nodes is 30, the maximum tree depth is set to 5, and the minimum number of samples per leaf node is 20; the regularization parameters are as follows: the regularization coefficient L1 is set to 0.1, the regularization coefficient L2 is set to 0.2, and the minimum increment threshold for classification is set to 0.3; the training parameters are as follows: the learning rate is 0.3, the number of iterations is 300, and the number of early stopping rounds is set to 8.

[0029] According to the method for predicting the fatigue life of solid waste fiber reinforced concrete, the following is a characteristic feature: the weight allocation result is calculated as follows:

[0030] The formula for weight allocation is as follows:

[0031]

[0032] In the above formula, w j It is the final weight, C k It represents the sum of the information content of all indicators.

[0033] Therefore, the present invention employs the above-described method for predicting the fatigue life of solid waste fiber reinforced concrete, which has the following advantages:

[0034] In this invention, by setting positive and negative periodic sampling methods, the degree of change in the physical properties of concrete samples at different time intervals can be collected, thereby enabling the prediction of changes in concrete sample indicators. By establishing a mapping relationship between period days, indicators, and lifespan, and through different simulation environments, the lifespan of concrete can ultimately be predicted.

[0035] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0036] Figure 1 This is a flowchart of a method for predicting the fatigue life of solid waste fiber concrete according to the present invention. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Specific model specifications need to be selected and determined according to the actual specifications of the device, etc. The specific selection calculation method adopts existing technology in the art, and therefore will not be described in detail.

[0038] Example

[0039] like Figure 1 As shown, this invention provides a method for predicting the fatigue life of solid waste fiber reinforced concrete, comprising the following steps:

[0040] Step 1: Prepare m concrete samples using solid waste materials, and perform alkali activation on the concrete samples. Calculate the physical properties of the concrete samples. Specifically, solid waste materials, including steel slag and fly ash, are used to prepare the concrete samples, with steel fibers added accordingly. The concrete samples are rectangular, with dimensions of 100mm*100mm*100mm. Standard curing is performed, and after alkali activation, the physical properties of the concrete samples are calculated, including compressive strength, water absorption, and porosity.

[0041] Step 2: Establish the test environment, place the concrete sample in the test environment, and collect indicators from the concrete sample according to the periodic time, including n indicators, to form a data set;

[0042] The testing environments include marine, humid and hot, and dry and cold environments. Concrete samples are tested in these environments using two time periods: positive and negative. Positive testing is conducted frequently in the early stages of the test, suitable for calibrating concrete samples with significant changes in the initial phase. Negative testing is conducted frequently in the later stages of the test, suitable for calibrating concrete samples with significant changes in the middle phase. This process determines the changes in concrete under different environments. The data collected in step two include the physical properties from step one, such as compressive strength, water absorption, and porosity. The mass change rate and volume expansion rate of the concrete samples are also measured, providing better quantification of the concrete samples. The above data are then grouped into a dataset in chronological order.

[0043] Step 3: Use the data set as the calculation data, standardize the data, calculate the amount of information, and input it into the constructed concrete life prediction model;

[0044] The data collected in step two is input into the concrete life prediction model, which is specifically set as a LightGBM+CRITIC weighted model. The processing procedure is as follows:

[0045] First, the weighting stage of CRITIC is performed. The positive index is set as compressive strength, and min-max standardization is used. The negative indexes are set as water absorption rate, porosity, and expansion rate, and inverse standardization is performed. The cycle time is logarithmically transformed and then standardized. The information content is calculated using the above indices, and the weighting results are obtained according to the calculated information content. The specific calculation process is as follows:

[0046] The formula for standardizing compressive strength is as follows:

[0047]

[0048] In the above formula, x' ij x is the normalized value of compressive strength. ij x represents the compressive strength value of the i-th sample on the j-th day. j This represents the compressive strength value of all concrete samples on day j;

[0049] The process of reverse standardizing water absorption, porosity, and expansion rate is as follows:

[0050]

[0051] In the above formula, a' ij a represents the standardized values ​​of water absorption, porosity, and expansion rate. ij This represents the original value of water absorption rate, porosity, or expansion rate for the i-th sample on the j-th day. jThis represents the value of water absorption, porosity, or expansion rate of the corresponding concrete sample on day j.

[0052] In the formula above, x' ij and a' ij These are all indicators of concrete samples, using T' ij This indicates that the information content is calculated using indicators, employing a contrast strength formula, as follows:

[0053]

[0054] In the above formula, m represents the number of concrete samples. This represents the standardized mean of the corresponding indicator; the amount of information calculated is:

[0055] C j =σ j ×R j

[0056]

[0057] In the above formula, R j The conflicting nature of the current indicators, r jk This represents the correlation coefficient between indicator j and indicator k, where n represents the total number of indicators, and C... j This represents the overall information carrying capacity of the j-th indicator;

[0058] The LightGBM model was built and its parameters trained. Temporal cross-validation and early stopping were used to assist training. The LightGBM model parameters were set as follows, including tree structure parameters, regularization parameters, and training parameters. The tree structure control parameters were as follows: 30 leaf nodes, a maximum tree depth of 5, and a minimum number of samples per leaf node of 20. The regularization parameters were as follows: L1 regularization coefficient was set to 0.1, L2 regularization coefficient was set to 0.2, and the minimum increment threshold for classification was set to 0.3. The training parameters were as follows: learning rate of 0.3, number of iterations of 300, and number of early stopping rounds of 8.

[0059] Based on the weight allocation results obtained from the CRITIC weight calculation, feature weighting is performed. The specific formula for weight allocation is as follows:

[0060]

[0061] In the above formula, w j C represents the final weight of the corresponding indicator j. k It represents the sum of the information content of all indicators.

[0062] Step 4: Referring to the weights obtained in Step 3, and using the concrete life prediction model, obtain the service life of the concrete by inputting the above indicators into the concrete life prediction model.

[0063] Therefore, this invention employs a method for predicting the fatigue life of solid waste fiber concrete. By setting positive and negative periodic sampling methods, the degree of change in the physical properties of concrete samples at different time intervals can be collected, thereby enabling the prediction of changes in concrete sample indicators. By establishing a mapping relationship between the number of days in the cycle, indicators, and lifespan, and then through different simulation environments, the lifespan of concrete can ultimately be predicted.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for predicting the fatigue life of solid waste fiber reinforced concrete, characterized in that: Includes the following steps: Step 1: Prepare concrete samples using solid waste. The concrete samples were alkali-activated and their physical properties were calculated. Step Two: Establish the testing environment. Place the concrete sample in the testing environment and collect data on the concrete sample according to the specified time intervals, including... Various indicators are used to form data sets; Step 3: Use the data set as the calculation data, first standardize the data, then calculate the information content, and input it into the constructed concrete life prediction model; The data collected in step two is input into the concrete life prediction model, which is specifically set as a LightGBM+CRITIC weighted model. The processing procedure is as follows: First, the weighting stage of CRITIC is performed. The positive index is set as compressive strength and standardized. The negative indexes are set as water absorption rate, porosity, and expansion rate and reverse standardized. The cycle time is logarithmically transformed and then standardized again. The information content is calculated using the above indicators. The weighting result is obtained according to the calculated information content. The specific calculation process is as follows: The compressive strength is normalized using the following formula: In the above formula, Let be the normalized value of the compressive strength of the i-th sample at the j-th day. This represents the compressive strength value of the i-th sample on the j-th day. This represents the compressive strength value of all concrete samples on day j; The process of reverse standardizing water absorption, porosity, and expansion rate is as follows: In the above formula, This represents the standardized value of water absorption, porosity, or expansion rate. This represents the original value of water absorption rate, porosity, or expansion rate for the i-th sample on the j-th day. This represents the value of water absorption, porosity, or expansion rate of the corresponding concrete sample on day j. The amount of information is calculated using the contrast intensity formula, as follows: In the above formula, The number of concrete samples. This represents the standardized mean, including the preceding values. and The formula for calculating information content is as follows: In the above formula, The conflicting nature of the current indicators express Indicators and The correlation coefficient between indicators Indicates the total number of indicators. This represents the overall information carrying capacity of the j-th indicator; The LightGBM model was built and its parameters were trained. The training process used temporal cross-validation and early stopping mechanism to assist training. The feature weighting was performed according to the weight allocation results obtained by CRITIC weight calculation. Step 4: Obtain the service life of the concrete using a concrete life prediction model.

2. The method for predicting the fatigue life of solid waste fiber reinforced concrete according to claim 1, characterized in that: The specific process of step one is as follows: Production A concrete sample, specifically 100 mm in size. 100mm The concrete samples were cut to 100mm thick and cured according to standard. The samples were then subjected to alkali activation, and the physical properties of the concrete samples were calculated, including compressive strength, water absorption and porosity.

3. The method for predicting the fatigue life of solid waste fiber reinforced concrete according to claim 1, characterized in that: The specific process in step two is as follows: The testing environments include marine, hot and humid, and cold and dry environments. Concrete samples are tested in these environments. There are two types of testing periods: positive and negative. Positive testing is conducted more frequently in the early stages of the test, while negative testing is conducted more frequently in the later stages. The collected indicators include the physical properties mentioned in step one, such as compressive strength, water absorption, and porosity. The mass change rate and expansion rate of the concrete samples are also measured. The above data are arranged in chronological order to form a data set.

4. The method for predicting the fatigue life of solid waste fiber reinforced concrete according to claim 1, characterized in that: The parameters of the LightGBM model are set as follows, including tree structure parameters, regularization parameters, and training parameters; the tree structure control parameters are as follows: the number of leaf nodes is 30, the maximum tree depth is set to 5, and the minimum number of samples per leaf node is 20; the regularization parameters are as follows: the regularization coefficient L1 is set to 0.1, the regularization coefficient L2 is set to 0.2, and the minimum increment threshold for classification is set to 0.

3. The training parameters are as follows: learning rate is 0.3, number of iterations is 300, and number of early stopping rounds is set to 8.

5. The method for predicting the fatigue life of solid waste fiber reinforced concrete according to claim 4, characterized in that: The weight allocation results are calculated as follows: The formula for weight allocation is as follows: In the above formula, It is the final weight. It represents the sum of the information content of all indicators.

Images