CN117420055A - Method for predicting chloride ion permeability of alkali-activated cementing material - Google Patents
Method for predicting chloride ion permeability of alkali-activated cementing material Download PDFInfo
- Publication number
- CN117420055A CN117420055A CN202311113367.XA CN202311113367A CN117420055A CN 117420055 A CN117420055 A CN 117420055A CN 202311113367 A CN202311113367 A CN 202311113367A CN 117420055 A CN117420055 A CN 117420055A
- Authority
- CN
- China
- Prior art keywords
- alkali
- factor
- initial
- activated
- cementing material
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000000463 material Substances 0.000 title claims abstract description 109
- 239000003513 alkali Substances 0.000 title claims abstract description 102
- 238000000034 method Methods 0.000 title claims abstract description 94
- VEXZGXHMUGYJMC-UHFFFAOYSA-M Chloride anion Chemical compound [Cl-] VEXZGXHMUGYJMC-UHFFFAOYSA-M 0.000 title claims abstract description 63
- 230000010220 ion permeability Effects 0.000 title claims abstract description 53
- 238000012360 testing method Methods 0.000 claims abstract description 53
- 230000008569 process Effects 0.000 claims abstract description 38
- 230000004044 response Effects 0.000 claims abstract description 34
- 230000006870 function Effects 0.000 claims abstract description 33
- 239000002243 precursor Substances 0.000 claims abstract description 27
- 239000012190 activator Substances 0.000 claims abstract description 14
- 239000003795 chemical substances by application Substances 0.000 claims description 31
- 238000012423 maintenance Methods 0.000 claims description 28
- HEMHJVSKTPXQMS-UHFFFAOYSA-M Sodium hydroxide Chemical compound [OH-].[Na+] HEMHJVSKTPXQMS-UHFFFAOYSA-M 0.000 claims description 27
- 238000004458 analytical method Methods 0.000 claims description 24
- 239000002893 slag Substances 0.000 claims description 23
- KWYUFKZDYYNOTN-UHFFFAOYSA-M Potassium hydroxide Chemical compound [OH-].[K+] KWYUFKZDYYNOTN-UHFFFAOYSA-M 0.000 claims description 21
- 230000004907 flux Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 17
- NTHWMYGWWRZVTN-UHFFFAOYSA-N sodium silicate Chemical compound [Na+].[Na+].[O-][Si]([O-])=O NTHWMYGWWRZVTN-UHFFFAOYSA-N 0.000 claims description 16
- CPLXHLVBOLITMK-UHFFFAOYSA-N Magnesium oxide Chemical compound [Mg]=O CPLXHLVBOLITMK-UHFFFAOYSA-N 0.000 claims description 14
- CDBYLPFSWZWCQE-UHFFFAOYSA-L Sodium Carbonate Chemical compound [Na+].[Na+].[O-]C([O-])=O CDBYLPFSWZWCQE-UHFFFAOYSA-L 0.000 claims description 14
- 239000004567 concrete Substances 0.000 claims description 14
- 239000004570 mortar (masonry) Substances 0.000 claims description 14
- 238000010206 sensitivity analysis Methods 0.000 claims description 14
- 239000002956 ash Substances 0.000 claims description 10
- 235000019353 potassium silicate Nutrition 0.000 claims description 10
- 230000035945 sensitivity Effects 0.000 claims description 10
- 239000011734 sodium Substances 0.000 claims description 9
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 8
- BWHMMNNQKKPAPP-UHFFFAOYSA-L potassium carbonate Chemical compound [K+].[K+].[O-]C([O-])=O BWHMMNNQKKPAPP-UHFFFAOYSA-L 0.000 claims description 8
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 claims description 7
- PMZURENOXWZQFD-UHFFFAOYSA-L Sodium Sulfate Chemical compound [Na+].[Na+].[O-]S([O-])(=O)=O PMZURENOXWZQFD-UHFFFAOYSA-L 0.000 claims description 7
- 229910000831 Steel Inorganic materials 0.000 claims description 7
- PNEYBMLMFCGWSK-UHFFFAOYSA-N aluminium oxide Inorganic materials [O-2].[O-2].[O-2].[Al+3].[Al+3] PNEYBMLMFCGWSK-UHFFFAOYSA-N 0.000 claims description 7
- 239000011575 calcium Substances 0.000 claims description 7
- 229910052791 calcium Inorganic materials 0.000 claims description 7
- 230000007613 environmental effect Effects 0.000 claims description 7
- 239000010881 fly ash Substances 0.000 claims description 7
- 239000000395 magnesium oxide Substances 0.000 claims description 7
- 230000035699 permeability Effects 0.000 claims description 7
- 238000007637 random forest analysis Methods 0.000 claims description 7
- 229910000029 sodium carbonate Inorganic materials 0.000 claims description 7
- 229910052938 sodium sulfate Inorganic materials 0.000 claims description 7
- 235000011152 sodium sulphate Nutrition 0.000 claims description 7
- 239000010959 steel Substances 0.000 claims description 7
- 239000004115 Sodium Silicate Substances 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 239000003469 silicate cement Substances 0.000 claims description 6
- 229910052911 sodium silicate Inorganic materials 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 229910000027 potassium carbonate Inorganic materials 0.000 claims description 4
- 239000000377 silicon dioxide Substances 0.000 claims description 4
- 102100028637 CLOCK-interacting pacemaker Human genes 0.000 claims description 3
- 101000766839 Homo sapiens CLOCK-interacting pacemaker Proteins 0.000 claims description 3
- 229910000720 Silicomanganese Inorganic materials 0.000 claims description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 claims description 3
- CWJSHJJYOPWUGX-UHFFFAOYSA-N chlorpropham Chemical compound CC(C)OC(=O)NC1=CC=CC(Cl)=C1 CWJSHJJYOPWUGX-UHFFFAOYSA-N 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- NLYAJNPCOHFWQQ-UHFFFAOYSA-N kaolin Chemical compound O.O.O=[Al]O[Si](=O)O[Si](=O)O[Al]=O NLYAJNPCOHFWQQ-UHFFFAOYSA-N 0.000 claims description 3
- -1 na 2 CO 3 Substances 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 229910052710 silicon Inorganic materials 0.000 claims description 3
- 239000010703 silicon Substances 0.000 claims description 3
- 235000012239 silicon dioxide Nutrition 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 13
- 238000005259 measurement Methods 0.000 description 11
- 239000007787 solid Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 239000004568 cement Substances 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000005684 electric field Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 239000011398 Portland cement Substances 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 150000003841 chloride salts Chemical class 0.000 description 1
- 150000001805 chlorine compounds Chemical group 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000012466 permeate Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/08—Investigating permeability, pore-volume, or surface area of porous materials
- G01N15/082—Investigating permeability by forcing a fluid through a sample
Landscapes
- Chemical & Material Sciences (AREA)
- Dispersion Chemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention relates to a method for predicting chloride ion permeability of an alkali-activated cementing material, which comprises the following steps: acquiring characteristic parameters corresponding to a plurality of influence factors of the alkali-activated cementing material to be predicted; the influencing factors include: a cementing material type factor, an alkali-activator factor, a test piece parameter factor, a precursor factor, a curing parameter factor and a test standard factor; based on the characteristic parameters, calculating an influence coefficient corresponding to each influence factor according to a locally prestored response surface function model; the response surface function model is obtained based on a pre-fitting process; and summing the influence coefficients to obtain a predicted value of the corresponding chloride ion permeability index so as to predict the chloride ion permeability of the alkali-activated cementing material to be predicted. The prediction method provided by the invention can be used for rapidly detecting the chloride ion permeability of the alkali-activated cementing material, and has the advantages of high detection efficiency, and good accuracy and reliability of the prediction result.
Description
Technical Field
The invention relates to the technical field of building materials, in particular to a method for predicting chloride ion permeability of an alkali-activated cementing material.
Background
The chloride ion permeability is an important index for evaluating the performance of the cementing material, and directly influences the engineering application of the concrete/mortar in a chloride salt environment, and can be embodied specifically through the chloride ion permeability coefficient and 6-hour electric flux.
The detection process of the chloride ion permeability coefficient and the 6-hour electric flux index of the cementing material generally comprises sample preparation and maintenance/on-site sampling, wherein chloride ions permeate into the concrete/mortar under the action of a natural electric field/an external electric field, and the chloride ion permeability coefficient and the electric flux index are determined by measuring the chloride ion permeability depth/the chloride ion concentration of a downstream groove and the current passing through the sample in a period of time in a steady state/an unsteady state. The detection process needs to prepare an entity sample or sample on site, and is realized by a complicated test means, and the detection process is complex in operation and low in detection speed.
Disclosure of Invention
First, the technical problem to be solved
In view of the defects and shortcomings of the prior art, the invention provides a method for predicting the chloride ion permeability of an alkali-activated cementing material, which solves the technical problems of complex and tedious detection process and low detection speed in the prior art.
(II) technical scheme
In order to achieve the above purpose, the main technical scheme adopted by the invention comprises the following steps:
in a first aspect, an embodiment of the present invention provides a method for predicting chloride ion permeability of an alkali-activated gelling material, including:
acquiring characteristic parameters corresponding to a plurality of influence factors of the alkali-activated cementing material to be predicted; the influencing factors include: a cementing material type factor, an alkali-activator factor, a test piece parameter factor, a precursor factor, a curing parameter factor and a test standard factor;
based on the characteristic parameters, calculating an influence coefficient corresponding to each influence factor according to a locally prestored response surface function model; the response surface function model is obtained based on a pre-fitting process;
and summing the influence coefficients to obtain a predicted value of the corresponding chloride ion permeability index so as to predict the chloride ion permeability of the alkali-activated cementing material to be predicted.
Optionally, the permeability index is chloride ion permeability coefficient;
and summing the influence coefficients to obtain a predicted value of the corresponding chloride ion permeability index, wherein the predicted value comprises the following components:
calculating according to a formula (1) to obtain a predicted value of the chloride ion permeability coefficient; the formula (1) is:
Wherein, CIPC represents the predicted value of chloride ion permeability coefficient;to->Respectively representing the influence coefficients corresponding to the cementing material type factor, the exciting agent concentration factor, the precursor type factor, the curing factor or the test standard factor.
Optionally, calculating an influence coefficient corresponding to each influence factor according to a locally pre-stored response surface function model includes: the response surface function model comprises formulas (2) - (7), wherein formulas (2) - (7) are as follows:
wherein,the influence coefficient corresponding to the cementing material type factor is represented, and MC represents the characteristic parameter corresponding to the cementing material type; the cementing material types include: alkali-activated concrete or alkali-activated mortar;
wherein,represent the corresponding influence coefficient of alkali-activator factor KOH, naOH, na 2 CO 3 、Na 2 SO 4 、K 2 CO 3 WG respectively represents corresponding characteristic parameters when the alkali-activated agent used for alkali-activated cementing material comprises potassium hydroxide, sodium carbonate, sodium sulfate, potassium carbonate or sodium silicate;
wherein,representing the influence coefficient corresponding to the parameter factor of the test piece, na 2 O% represents the alkali concentration of the alkali-activated agent, ms represents the water glass modulus of the alkali-activated agent, and w/b represents the water-gel ratio of the alkali-activated gelling material;
Wherein,representing the precursor factorCorresponding influence coefficient, CGP, slag, TP, ca, NA, mgO, siO 2 PC, fe and FA respectively represent the mass ratio of gangue, slag, volcanic ash, calcium-based material, alumina, magnesia, silicon dioxide material, silicate cement, steel slag or fly ash in the precursor used for alkali-activated cementing material;
wherein,the method is characterized by comprising the steps of representing an influence coefficient corresponding to a maintenance parameter factor, RH representing relative humidity in a maintenance process, T representing maintenance temperature, D representing maintenance duration, and CIC representing environmental chloride ion concentration;
wherein,the influence coefficients corresponding to the test standard factors are represented by NTBuild492, ASTMC1556, AASHTOT259, GB/T50082, NTBuild443 and ASTMC1218, and the characteristic parameters corresponding to the test standards of NTBuild492, ASTMC1556, AASHTOT259, GB/T50082, NTBuild443 and ASTMC1218 are respectively represented by the test standards.
Optionally, the permeability index is 6 hours electric flux;
and summing the influence coefficients to obtain a predicted value of the corresponding chloride ion permeability index, wherein the predicted value comprises the following components:
calculating according to a formula (8), and obtaining a predicted value of the 6-hour electric flux, wherein the formula (8) is as follows:
wherein CL represents 6 hours The predicted value of the electric flux is calculated,to->Respectively representing the influence coefficients corresponding to the cementing material type factor, the exciting agent concentration factor, the precursor type factor, the curing factor or the test standard factor.
Optionally, calculating an influence coefficient corresponding to each influence factor according to a locally pre-stored response surface function model includes: the response surface function model comprises formulas (9) - (14), wherein formulas (9) - (14) are as follows:
wherein,the influence coefficient corresponding to the cementing material type factor is represented, and MC represents the characteristic parameter corresponding to the cementing material type; the cementing material types include: alkali-activated concrete or alkali-activated mortar;
wherein,indicating the influence coefficient corresponding to alkali-exciting agent factors, naOH and Na 2 CO 3 、Na 2 SO 4 WG respectively represents corresponding characteristic parameters when alkali exciting agents used for alkali exciting the cementing material comprise sodium hydroxide, sodium carbonate, sodium sulfate or sodium silicate;
wherein,representing the influence coefficient corresponding to the parameter factor of the test piece, na 2 O% represents the alkali concentration of the alkali-activated agent, ms represents the water glass modulus of the alkali-activated agent, and w/b represents the water-gel ratio of the alkali-activated gelling material;
wherein,representing the corresponding influence coefficient of the precursor factor slag, SM, TP, ca, ash, NA, mgO, MK, siO 2 PC, fe and FA respectively represent the mass ratio of slag, silicomanganese slag, volcanic ash, calcium-based material, ash-like material, alumina, magnesia, metakaolin, silicon dioxide-like material, silicate cement, steel slag or fly ash in the precursor used for alkali-activated cementing material;
wherein,the method is characterized by comprising the steps of representing an influence coefficient corresponding to a maintenance parameter factor, RH representing relative humidity in a maintenance process, T representing maintenance temperature, D representing maintenance duration, and CIC representing environmental chloride ion concentration;
wherein the method comprises the steps ofRepresenting the corresponding influence coefficient of the test standard factor, ASTMC1202 denotes a feature parameter corresponding to the test standard astm c1202, and the astm c1202 has a value of 1.
Optionally, the pre-fitting process includes:
s01, acquiring a plurality of pieces of original data; each piece of the original data includes: original characteristic parameters and original performance index results corresponding to the plurality of influence factors;
s02, preprocessing the plurality of pieces of original data to obtain a plurality of pieces of original data; each piece of the initial data includes: an initial performance index result is obtained after the initial characteristic parameter is preprocessed and the initial performance index result is preprocessed;
S03, carrying out feature analysis based on the initial data to obtain an optimal feature combination;
and S04, fitting according to initial data corresponding to the characteristic parameters based on the characteristic parameters corresponding to the optimal characteristic combination to obtain a response surface function model.
Optionally, in the S02, the preprocessing operation includes: at least one of data cleaning processing, data normalization processing, outlier removal processing, and missing value interpolation processing.
Optionally, the S03 includes:
s03-1, carrying out variable correlation analysis on characteristic parameters in initial data based on the initial data to obtain correlation among the characteristic parameters, and carrying out combination processing on the characteristics with the correlation larger than a first preset value to obtain initial characteristic combination;
s03-2, based on the initial data, carrying out variable sensitivity analysis on the characteristic parameters in the initial characteristic combination, and eliminating the characteristic with the sensitivity smaller than a second preset value to obtain the optimal characteristic combination. .
Optionally, the S03-1 includes:
a1, randomly selecting a plurality of pieces of initial data from the plurality of pieces of initial data to serve as random samples, and inputting the random samples into a random forest model;
A2, the random forest model selects a plurality of initial characteristic parameters from initial characteristic parameters contained in all random samples to serve as a characteristic subset, and a decision tree is constructed;
a3, repeating the steps A1 to A2 to establish a plurality of decision trees;
a4, calculating importance scores of each initial characteristic parameter according to the use frequency of the initial characteristic parameter and the accuracy of node splitting;
a5, calculating the similarity between any two initial characteristic parameters according to the importance score of each initial characteristic parameter;
and A6, judging whether the correlation degree is larger than a first preset value, if so, combining two initial characteristic parameters corresponding to the correlation degree into one initial characteristic parameter to obtain an initial characteristic combination.
Optionally, the step S03-2 includes:
performing a first sensitivity analysis process on the characteristic parameters in the initial characteristic combination by using a principal component analysis method to obtain a first analysis result;
performing a second sensitivity analysis process on the characteristic parameters in the initial characteristic combination by using a recursive characteristic elimination method to obtain a second analysis result;
the first analysis result and the second analysis result both comprise: sensitivity of the initial performance index result to the feature parameters in the initial feature combination;
And eliminating characteristic parameters with sensitivity lower than a second preset value in the first analysis result and the second analysis result from the initial characteristic combination to obtain an optimal characteristic combination.
(III) beneficial effects
According to the prediction method provided by the embodiment of the invention, the chloride ion permeability of the alkali-activated cementing material is predicted through a locally prestored response surface function model, the response surface function model can be based on characteristic parameters corresponding to various influencing factors such as cementing material type factors, alkali-activated agent factors, test piece parameter factors, precursor factors, maintenance parameter factors, test standard factors and the like, and the chloride ion permeability of the alkali-activated cementing material is predicted.
In addition, the characteristic parameters adopted by the response surface function model provided by the embodiment of the invention are determined by analyzing mass data according to specific chloride ion permeability indexes based on a pre-fitting process, so that the characteristic parameter data input in the prediction process has better generalization performance, and the accuracy and reliability of a prediction result are ensured.
Drawings
FIG. 1 is a schematic flow chart of a method for predicting chloride ion permeability of an alkali-activated gelling material according to an embodiment;
FIG. 2 is a histogram of the chloride ion permeability coefficient of the alkali-activated gelling material according to the present embodiment;
FIG. 3 is a histogram of the measured and predicted 6-hour electric fluxes of the alkali-activated gelling material according to the example;
FIG. 4 is a flow chart of a pre-fitting process provided in an embodiment;
FIG. 5 is a regression curve and probability distribution map corresponding to the raw data of 32 raw characteristic parameters provided in the example;
FIG. 6 is a schematic diagram showing a comparison between predicted values of a plurality of pieces of original data and corresponding initial performance index results in an embodiment;
fig. 7 is a thermodynamic diagram corresponding to the correlation degree of 32 initial feature parameters in the embodiment.
Detailed Description
The invention will be better explained by the following detailed description of the embodiments with reference to the drawings.
In order that the above-described aspects may be better understood, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Example 1
As shown in fig. 1, the embodiment provides a method for predicting chloride ion permeability of an alkali-activated gel material, which includes the following steps:
s10, acquiring characteristic parameters corresponding to a plurality of influence factors of the alkali-activated cementing material to be predicted; the influencing factors include: the method comprises the steps of cementing material type factors, alkali-exciting agent factors, test piece parameter factors, precursor factors, maintenance parameter factors and test standard factors.
S20, calculating an influence coefficient corresponding to each influence factor according to a locally prestored response surface function model based on the characteristic parameters; the response surface function model is obtained based on a pre-fitting process.
And S30, summing the influence coefficients to obtain a predicted value of a corresponding chloride ion permeability index so as to predict the chloride ion permeability of the alkali-activated cementing material to be predicted.
Specifically, the chloride ion permeation performance includes: chloride ion permeability coefficient, 6 hours electric flux. Both can be used for evaluating the chloride ion permeability of the alkali-activated cementing material alone or in combination.
In a preferred embodiment of this example, the permeability index is chloride permeability coefficient.
Step S20 includes: based on the characteristic parameters corresponding to the cementing material type factors, the alkali-exciting agent factors, the test piece parameter factors, the precursor factors, the curing parameter factors and the test standard factors, calculating the influence coefficients corresponding to each influence factor according to a response surface function model stored in advance locally.
The response surface function model comprises formulas (2) - (7), wherein formulas (2) - (7) are as follows:
wherein,the influence coefficient corresponding to the cementing material type factor is represented, and MC represents the characteristic parameter corresponding to the cementing material type; the cementing material types include: alkali-activated concrete or alkali-activated mortar;
wherein,represent the corresponding influence coefficient of alkali-activator factor KOH, naOH, na 2 CO 3 、Na 2 SO 4 、K 2 CO 3 WG respectively represents corresponding characteristic parameters when the alkali-activated agent used for alkali-activated cementing material comprises potassium hydroxide, sodium carbonate, sodium sulfate, potassium carbonate or sodium silicate;
wherein,representing the influence coefficient corresponding to the parameter factor of the test piece, na 2 O% represents the alkali concentration of the alkali-activated agent, ms represents the water glass modulus of the alkali-activated agent, and w/b represents the water-gel ratio of the alkali-activated gelling material;
wherein,representing the corresponding influence coefficient of the precursor factor CGP, slag, TP, ca, NA, mgO, siO 2 PC, fe and FA respectively represent the mass ratio of gangue, slag, volcanic ash, calcium-based material, alumina, magnesia, silicon dioxide material, silicate cement, steel slag or fly ash in the precursor used for alkali-activated cementing material;
wherein,the method is characterized by comprising the steps of representing an influence coefficient corresponding to a maintenance parameter factor, RH representing relative humidity in a maintenance process, T representing maintenance temperature, D representing maintenance duration, and CIC representing environmental chloride ion concentration;
wherein,the influence coefficients corresponding to the test standard factors are represented by NTBuild492, ASTMC1556, AASHTOT259, GB/T50082, NTBuild443 and ASTMC1218, and the characteristic parameters corresponding to the test standards of NTBuild492, ASTMC1556, AASHTOT259, GB/T50082, NTBuild443 and ASTMC1218 are respectively represented by the test standards.
Step S30 includes: and (3) calculating according to the formula (1) to obtain a predicted value of the chloride ion permeability coefficient so as to predict the chloride ion permeability of the alkali-activated cementing material. The formula (1) is:
wherein, CIPC represents the predicted value of chloride ion permeability coefficient;to->Respectively representing the influence coefficients corresponding to the cementing material type factor, the exciting agent concentration factor, the precursor type factor, the curing factor and the test standard factor.
In order to verify the accuracy and reliability of the prediction method provided in this embodiment, this example also prepares two groups of a and B physical samples for detection to obtain actual measurement values, so as to verify the prediction values obtained based on the prediction method of this embodiment.
Table 1 shows the measured values of the characteristic parameters and the chloride ion permeability coefficients corresponding to the prepared solid samples, and the predicted values of the chloride ion permeability coefficients were calculated based on formulas (1) to (7) according to the characteristic parameters.
TABLE 1 actual measurement values and predicted values of characteristic parameters and chloride ion permeability coefficients of solid samples
In table 1, M represents the sample type of alkali-activated mortar, C represents the sample type of alkali-activated concrete, WG represents the excitant used for the solid sample as water glass, and NaOH represents the excitant used for the solid sample as sodium hydroxide.
The measured values and predicted values of the chloride ion permeability coefficients of the alkali-activated gelling materials in table 1 are visually compared by the histogram shown in fig. 2. It can be seen that the predicted value and the measured value substantially match when the heights of the measured value (true value) and the predicted value are observed.
According to the actual measurement values and the predicted values corresponding to the data of the group A and the data of the group B in the table 1, the relative errors corresponding to the actual measurement values and the predicted values in the data of the group A and the data of the group B are respectively 3.03 percent and 2.18 percent, which shows that the errors of the predicted values and the actual measurement values are smaller.
In another preferred embodiment of this example, the permeability index is 6 hours of electrical flux.
Step S20 includes: based on the characteristic parameters corresponding to the cementing material type factors, the alkali-exciting agent factors, the test piece parameter factors, the precursor factors, the curing parameter factors and the test standard factors, calculating the influence coefficients corresponding to each influence factor according to a locally prestored response surface function model.
The response surface function model includes formulas (9) to (14), the formulas (9) to (14) being:
wherein,the influence coefficient corresponding to the cementing material type factor is represented, and MC represents the characteristic parameter corresponding to the cementing material type; the cementing material types include: alkali-activated concrete or alkali-activated mortar;
wherein,indicating the influence coefficient corresponding to alkali-exciting agent factors, naOH and Na 2 CO 3 、Na 2 SO 4 WG respectively represents corresponding characteristic parameters when alkali exciting agents used for alkali exciting the cementing material comprise sodium hydroxide, sodium carbonate, sodium sulfate or sodium silicate;
wherein,representing the influence coefficient corresponding to the parameter factor of the test piece, na 2 O% represents the alkali concentration of the alkali-activated agent, ms represents the water glass modulus of the alkali-activated agent, and w/b represents the water-gel ratio of the alkali-activated gelling material;
Wherein,representing the corresponding influence coefficient of the precursor factor slag, SM, TP, ca, ash, NA, mgO, MK, siO 2 PC, fe and FA respectively represent the mass ratio of slag, silicomanganese slag, volcanic ash, calcium-based material, ash-like material, alumina, magnesia, metakaolin, silicon dioxide-like material, silicate cement, steel slag or fly ash in the precursor used for alkali-activated cementing material;
wherein,the method is characterized by comprising the steps of representing an influence coefficient corresponding to a maintenance parameter factor, RH representing relative humidity in a maintenance process, T representing maintenance temperature, D representing maintenance duration, and CIC representing environmental chloride ion concentration;
wherein the method comprises the steps ofThe influence coefficient corresponding to the test standard factor is represented, astm c1202 represents the characteristic parameter corresponding to the test standard astm c1202, and the astm c1202 has a value of 1.
Step S30 includes: and (3) calculating according to a formula (8) to obtain a predicted value of the 6-hour electric flux so as to predict the chloride ion permeability of the alkali-activated cementing material.
The formula (8) is:
wherein,to->Respectively representing the influence coefficients corresponding to the cementing material type factor, the exciting agent concentration factor, the precursor type factor, the curing factor and the test standard factor.
In order to verify the accuracy and reliability of the prediction method provided in this embodiment, this example also prepares two groups of entity samples C and D to be detected, and obtains actual measurement values, so as to verify the prediction values obtained based on the prediction method of this embodiment.
Table 2 shows the characteristic parameters and measured values corresponding to the prepared solid samples, and the 6-hour electric flux predicted values calculated based on formulas (8) to (14) according to the characteristic parameters.
TABLE 2 actual measurement values and predicted values of the characteristic parameters and 6-hour electric fluxes of the solid samples
In table 2, M represents the sample type of alkali-activated mortar, C represents the sample type of alkali-activated concrete, WG represents the excitant used for the solid sample as water glass, and NaOH represents the excitant used for the solid sample as sodium hydroxide.
The measured and predicted values of 6-hour electric flux of the alkali-activated gelling material in table 2 were visually compared by the histogram shown in fig. 3. The observed value and the corresponding height of the observed value can be seen that the predicted value and the observed value basically accord.
According to the actual measurement values and the predicted values corresponding to the data of the group C and the data of the group D in the table 2, the relative errors corresponding to the actual measurement values and the predicted values in the data of the group C and the data of the group D are respectively 1.73 percent and 4.50 percent, which shows that the errors of the predicted values and the actual measurement values are smaller.
Based on the verification results of the two chloride ion permeability indexes, the prediction method provided by the embodiment has good performance in the aspects of measuring the chloride ion permeability coefficient and the 6-hour electric flux of the alkali-activated cementing material, and the error can be controlled within 5%, so that the engineering requirements are greatly met. Compared with the traditional detection method, the prediction method can remarkably improve the accuracy and reliability of the test result. In addition, the prediction method does not need to carry out expensive and time-consuming laboratory tests, and can save a great deal of time and cost, so that the chloride ion permeability evaluation work is more economical and efficient. Therefore, the method has important application value and popularization prospect in engineering practice of alkali-activated cementing materials.
Example two
In order to better understand the first embodiment, this embodiment takes the chloride ion permeability coefficient as the chloride ion permeability index as an example, and further describes the detailed steps of the fitting process in advance.
As shown in fig. 4, the pre-fitting process provided in this embodiment includes the following sub-steps:
s01, acquiring a plurality of pieces of original data; each piece of the original data includes: the above 6 influence factors correspond to 32 original characteristic parameters and corresponding original performance index results.
The characteristic parameters corresponding to the cementing material type factors comprise: whether the cementing material type is alkali-activated concrete or not and whether the cementing material type is alkali-activated mortar or not. These two characteristic parameters can be represented by 0 and 1, if they are 1, otherwise they are 0.
The characteristic parameters corresponding to the alkali-activator factor comprise: whether the alkali-activator comprises potassium hydroxide, whether the alkali-activator comprises sodium carbonate, whether the alkali-activator comprises sodium sulfate, whether the alkali-activator comprises potassium carbonate, and whether the alkali-activator comprises water glass. These characteristic parameters can be represented by 0 and 1, if they are 1, otherwise 0.
The characteristic parameters corresponding to the test piece parameter factors comprise: alkali concentration of alkali-activator, water glass modulus of alkali-activator, water-gel ratio of alkali-activated cementing material.
The characteristic parameters corresponding to the precursor factors include: gangue, slag, volcanic ash, calcium-based materials, alumina, magnesia, silica materials, portland cement, steel slag and fly ash in the precursor used for alkali-activated cementing materials.
The characteristic parameters corresponding to the maintenance parameter factors comprise: relative humidity during curing, curing temperature, curing time and environmental chloride ion concentration.
The characteristic parameters corresponding to the test standard factors comprise: whether the test standard is NTBuild492, whether the test standard is ASTMC1556, whether the test standard is AASHTOT259, whether the test standard is GB/T50082, whether the test standard is NTBuild443, and whether the test standard is ASTMC1218. These characteristic parameters can be represented by 0 and 1, if they are 1, otherwise 0.
It should be noted that the above raw data may be obtained through public channels, such as published literature data and laboratory data, or may be obtained based on a previous experimental process. In order to make the original data have better representativeness and improve the generalization performance of the finally obtained response surface function model on the input data (namely, the characteristic parameters of the alkali-activated cementing material to be predicted), after the original data are obtained, the embodiment performs statistical analysis on the data corresponding to each characteristic parameter, and determines that the original data corresponding to the characteristic parameter are representative by analyzing the distribution condition of the data. In this embodiment, the regression curve and probability distribution diagram corresponding to the raw data of each characteristic parameter obtained by analysis are shown as 5-1 to 5-32 in fig. 5, and it can be seen that, except that the discrete data are distributed only at two points of 0 and 1, other data are uniformly distributed in a large numerical interval, so that the method has better representativeness.
S02, preprocessing the plurality of pieces of original data to obtain a plurality of pieces of original data; each piece of the initial data includes: the initial characteristic parameters obtained after the pretreatment of the initial characteristic parameters and the initial performance index results obtained after the pretreatment of the initial performance index results.
The preprocessing operation includes: at least one of data cleaning processing, data normalization processing, outlier removal processing, and missing value interpolation processing.
Specifically, the data cleaning process includes: remove duplicate data and convert data formats.
The data normalization process comprises the following steps: all initial performance indexes are uniformly scaled to the range of [0,1] to normalize the data so as to eliminate the dimensional difference and the data deviation problem between different indexes.
The missing value interpolation processing includes: interpolation is performed based on a multiple interpolation method, a mean interpolation method, a regression interpolation method, and an EM (Expectation Maximization ) algorithm to improve the accuracy and reliability of the original data. Preferably, the missing values of the original data are interpolated using a multiple interpolation method.
The outlier removal process includes: and detecting the abnormal value by using a unit mean value vector method, and removing the piece of data where the abnormal value is located.
It should be noted that, the "unit" in this embodiment refers to a piece of data corresponding to a test or detection, and specifically includes all initial feature parameters and initial performance index results corresponding to the test or detection. Outliers are values that deviate significantly from most observations in the original data, possibly due to measurement errors, data entry errors, or other reasons. In this embodiment, whether the average value of the unit is abnormal is determined by detecting the unit average value vector, and if so, the data of the unit is removed.
The method comprises the following specific steps: first, the mean vector and standard deviation of each cell are calculated, and then the upper and lower bounds of outlier recognition are determined. The limit is obtained by subtracting three times the standard deviation vector from the mean vector as shown in equation (15). Notably, cell mean vector detection is a method of detecting outliers across groups, as it is per cell within a group. In this case we use a unit mean vector detection method to identify outliers and remove them to avoid local bias.
The above formula (15) is:
in the formula (15), n represents the sample size,represents the sample mean vector, mu 0 Representing a preset specific mean vector, S represents an estimate of the sample covariance matrix, typically using the sample covariance matrix.
And S03, carrying out feature analysis based on the initial data to obtain an optimal feature combination.
And S04, fitting according to initial data corresponding to the characteristic parameters based on the characteristic parameters corresponding to the optimal characteristic combination to obtain a response surface function model.
Specifically, the method for performing fitting according to the initial data corresponding to the characteristic parameters may be ridge regression fitting, polynomial regression fitting, and the like.
Based on the response surface function model obtained by fitting, the embodiment also inputs the initial characteristic parameters corresponding to the initial data into formulas (2) to (7) to obtain the influence coefficients corresponding to the influence factors, and sums the influence coefficients corresponding to the influence factors according to formula (1) to obtain the predicted value. The comparison of the initial performance index results and the corresponding predicted values of the plurality of pieces of original data is shown in fig. 6, and the initial performance index results and the corresponding predicted values can be found to be basically coincident, which indicates that the response surface function model provided by the embodiment has better accuracy and reliability.
In a preferred implementation of the present example, the step S03 includes substeps S03-1 to S03-2:
s03-1, based on the initial data, carrying out variable correlation analysis on the characteristic parameters in the candidate characteristic set to obtain the correlation degree among the characteristic parameters, and carrying out combination processing on the characteristics with the correlation degree larger than a first preset value to obtain an initial characteristic combination.
The correlation between the feature parameters is an important criterion for determining the feature parameters of the response surface function regression model. If the correlation between the characteristic parameters is large, the model has multiple collinearity problems, and the accuracy of the final prediction result is affected. The present embodiment uses a random forest model to analyze the characteristic parameters. Specifically, the step S03-1 includes the sub-steps of:
a1, randomly selecting a plurality of pieces of initial data from the plurality of pieces of initial data to serve as random samples, and inputting the random samples into a random forest model.
A2, the random forest model selects a plurality of initial characteristic parameters from the initial characteristic parameters contained in all random samples to serve as a characteristic subset, and a decision tree is constructed.
A3, repeating the steps A1 to A2 to establish a plurality of decision trees.
And A4, calculating the importance score of each initial characteristic parameter according to the use frequency of the initial characteristic parameter and the accuracy of node splitting.
A5, calculating the similarity between any two initial characteristic parameters according to the importance scores of the initial characteristic parameters.
Generally, the higher the correlation of two initial feature parameters, the closer the importance scores of the two. Thus, the similarity of the two can be calculated from the importance scores of the initial feature parameters.
In this embodiment, the correlation degree of the 32 initial feature parameters may be presented by a thermodynamic diagram as shown in fig. 7. In fig. 7, the initial feature parameters corresponding to the abscissa and the ordinate are arranged in the forward direction from the origin to the coordinate axis in the forward order and the reverse order, respectively, and each square indicates the degree of correlation between the initial feature parameters corresponding to the abscissa and the ordinate, and the darker the color of the square indicates the higher the degree of correlation. It can be seen that: firstly, the square on the 135 degree diagonal corresponds to the correlation of an initial characteristic parameter with itself, which is certainly the highest, so the color is the deepest; secondly, the correlation between "whether the cement type is alkali-activated concrete" (indicated by M on the axis in fig. 7) and "whether the cement type is alkali-activated mortar" (indicated by C on the axis in fig. 7) is high.
And A6, judging whether the correlation degree is larger than a first preset value, if so, combining two initial characteristic parameters corresponding to the correlation degree into one initial characteristic parameter to obtain an initial characteristic combination. Preferably, the value of the first preset value ranges from [0.7 to 0.9], and more preferably, the first preset value is 0.8.
Specifically, the method for combining the two initial characteristic parameters corresponding to the phase Guan Du into one initial characteristic parameter may be set according to the data type of the actual characteristic parameter, for example, in this embodiment, the characteristic parameter correlation of the two discrete amounts of data, i.e., whether the cementitious material type is alkali-activated concrete and whether the cementitious material type is alkali-activated mortar, is greater than a first preset value, and may be combined into one characteristic parameter: "cement type"; when the type of the alkali-activated cementing material is alkali-activated concrete, the value of the characteristic parameter is 1; when the type of the alkali-activated cementing material is alkali-activated mortar, the value of the characteristic parameter is 0.
If the two initial characteristic parameters to be combined are continuous data, one initial characteristic parameter can be represented by the other initial characteristic parameter according to the mapping relation between the two initial characteristic parameters.
By combining initial characteristic parameters with high correlation degree, the aim of lightening a response surface function model obtained by subsequent fitting can be fulfilled, the calculation force requirement on operation equipment in practical application is reduced, and the response speed in predicting the chloride ion permeability is improved.
S03-2, based on the initial data, carrying out variable sensitivity analysis on the characteristic parameters in the initial characteristic combination, and eliminating the characteristic with the sensitivity smaller than a second preset value to obtain the optimal characteristic combination.
In order to prevent the limitation of a single variable sensitivity analysis method and eliminate feature parameters which cannot be ignored, the embodiment uses two variable sensitivity analysis methods to analyze, and eliminates two feature parameters which are obtained by using the variable sensitivity analysis methods and have lower sensitivity so as to obtain the optimal feature combination. Specifically, step S03-3 includes substeps B1 through B4:
and B1, performing a first sensitivity analysis process on the characteristic parameters in the initial characteristic combination by using a principal component analysis method to obtain a first analysis result. In particular, the first sensitivity analysis process may be an analysis process using Principal Component Analysis (PCA).
And B2, performing a second sensitivity analysis process on the characteristic parameters in the initial characteristic combination by using a recursive characteristic elimination method to obtain a second analysis result. In particular, the second sensitivity analysis process may be an analysis process using a feature recursive elimination (RFE).
B3, the first analysis result and the second analysis result comprise: sensitivity of the initial performance index results to the feature parameters in the initial feature combination.
And B4, eliminating characteristic parameters with sensitivity lower than a second preset value in the first analysis result and the second analysis result from the initial characteristic combination to obtain an optimal characteristic combination.
It should be noted that, the response surface function model for predicting the 6-hour electric flux is also obtained based on the fitting process described above, and this embodiment will not be described in detail.
From the fitting process, it can be seen that the response surface function model provided by the embodiment of the invention is obtained based on processing, analyzing and fitting a large amount of original data, so that the characteristic parameter data input in the prediction process has better generalization performance, and the accuracy and reliability of the prediction result are further ensured.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the terms first, second, third, etc. are for convenience of description only and do not denote any order. These terms may be understood as part of the component name.
Furthermore, it should be noted that in the description of the present specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with the embodiment or example being included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art upon learning the basic inventive concepts. Therefore, the appended claims should be construed to include preferred embodiments and all such variations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, the present invention should also include such modifications and variations provided that they come within the scope of the following claims and their equivalents.
Claims (10)
1. The method for predicting the chloride ion permeability of the alkali-activated cementing material is characterized by comprising the following steps of:
acquiring characteristic parameters corresponding to a plurality of influence factors of the alkali-activated cementing material to be predicted; the influencing factors include: a cementing material type factor, an alkali-activator factor, a test piece parameter factor, a precursor factor, a curing parameter factor and a test standard factor;
based on the characteristic parameters, calculating an influence coefficient corresponding to each influence factor according to a locally prestored response surface function model; the response surface function model is obtained based on a pre-fitting process;
And summing the influence coefficients to obtain a predicted value of the corresponding chloride ion permeability index so as to predict the chloride ion permeability of the alkali-activated cementing material to be predicted.
2. The method of claim 1, wherein the permeability index is chloride ion permeability coefficient;
and summing the influence coefficients to obtain a predicted value of the corresponding chloride ion permeability index, wherein the predicted value comprises the following components:
calculating according to a formula (1) to obtain a predicted value of the chloride ion permeability coefficient; the formula (1) is:
wherein, CIPC represents the predicted value of chloride ion permeability coefficient;to->Respectively representing the influence coefficients corresponding to the cementing material type factor, the exciting agent concentration factor, the precursor type factor, the curing factor or the test standard factor.
3. The prediction method according to claim 2, wherein calculating the influence coefficient corresponding to each influence factor according to the locally pre-stored response surface function model includes: the response surface function model comprises formulas (2) - (7), wherein formulas (2) - (7) are as follows:
wherein,the influence coefficient corresponding to the cementing material type factor is represented, and MC represents the characteristic parameter corresponding to the cementing material type; the cementing material types include: alkali-activated concrete or alkali-activated mortar;
Wherein,represent the corresponding influence coefficient of alkali-activator factor KOH, naOH, na 2 CO 3 、Na 2 SO 4 、K 2 CO 3 WG respectively represents corresponding characteristic parameters when the alkali-activated agent used for alkali-activated cementing material comprises potassium hydroxide, sodium carbonate, sodium sulfate, potassium carbonate or sodium silicate;
wherein,representing the influence coefficient corresponding to the parameter factor of the test piece, na 2 O% represents the alkali concentration of the alkali-activated agent, ms represents the water glass modulus of the alkali-activated agent, and w/b represents the water-gel ratio of the alkali-activated gelling material;
wherein,representing the corresponding influence coefficient of the precursor factor CGP, slag, TP, ca, NA, mgO, siO 2 PC, fe and FA respectively represent the mass ratio of gangue, slag, volcanic ash, calcium-based material, alumina, magnesia, silicon dioxide material, silicate cement, steel slag or fly ash in the precursor used for alkali-activated cementing material;
wherein,the method is characterized by comprising the steps of representing an influence coefficient corresponding to a maintenance parameter factor, RH representing relative humidity in a maintenance process, T representing maintenance temperature, D representing maintenance duration, and CIC representing environmental chloride ion concentration;
wherein,the influence coefficients corresponding to the test standard factors are represented by NTBuild492, ASTMC1556, AASHTOT259, GB/T50082, NTBuild443 and ASTMC1218, and the characteristic parameters corresponding to the test standards of NTBuild492, ASTMC1556, AASHTOT259, GB/T50082, NTBuild443 and ASTMC1218 are respectively represented by the test standards.
4. The method of claim 1, wherein the permeability index is 6 hours electrical flux;
and summing the influence coefficients to obtain a predicted value of the corresponding chloride ion permeability index, wherein the predicted value comprises the following components:
calculating according to a formula (8), and obtaining a predicted value of the 6-hour electric flux, wherein the formula (8) is as follows:
wherein CL represents a predicted value of 6-hour electric flux,to->Respectively representing the influence coefficients corresponding to the cementing material type factor, the exciting agent concentration factor, the precursor type factor, the curing factor or the test standard factor.
5. The prediction method according to claim 4, wherein calculating the influence coefficient corresponding to each influence factor according to the locally pre-stored response surface function model includes: the response surface function model comprises formulas (9) - (14), wherein formulas (9) - (14) are as follows:
wherein,the influence coefficient corresponding to the cementing material type factor is represented, and MC represents the characteristic parameter corresponding to the cementing material type; the cementing material types include: alkali-activated concrete or alkali-activated mortar;
wherein,indicating the influence coefficient corresponding to alkali-exciting agent factors, naOH and Na 2 CO 3 、Na 2 SO 4 WG respectively represents corresponding characteristic parameters when alkali exciting agents used for alkali exciting the cementing material comprise sodium hydroxide, sodium carbonate, sodium sulfate or sodium silicate;
wherein,representing the influence coefficient corresponding to the parameter factor of the test piece, na 2 O% represents the alkali concentration of the alkali-activated agent, ms represents the water glass modulus of the alkali-activated agent, and w/b represents the water-gel ratio of the alkali-activated gelling material;
wherein,representing the corresponding influence coefficient of the precursor factor slag, SM, TP, ca, ash, NA, mgO, MK, siO 2 PC, fe and FA respectively represent the mass ratio of slag, silicomanganese slag, volcanic ash, calcium-based material, ash-like material, alumina, magnesia, metakaolin, silicon dioxide-like material, silicate cement, steel slag or fly ash in the precursor used for alkali-activated cementing material;
wherein,the method is characterized by comprising the steps of representing an influence coefficient corresponding to a maintenance parameter factor, RH representing relative humidity in a maintenance process, T representing maintenance temperature, D representing maintenance duration, and CIC representing environmental chloride ion concentration;
wherein the method comprises the steps ofThe influence coefficient corresponding to the test standard factor is represented, astm c1202 represents the characteristic parameter corresponding to the test standard astm c1202, and the astm c1202 has a value of 1.
6. The prediction method according to claim 1, wherein the pre-fitting process comprises:
S01, acquiring a plurality of pieces of original data; each piece of the original data includes: original characteristic parameters and original performance index results corresponding to the plurality of influence factors;
s02, preprocessing the plurality of pieces of original data to obtain a plurality of pieces of original data; each piece of the initial data includes: an initial performance index result is obtained after the initial characteristic parameter is preprocessed and the initial performance index result is preprocessed;
s03, carrying out feature analysis based on the initial data to obtain an optimal feature combination;
and S04, fitting according to initial data corresponding to the characteristic parameters based on the characteristic parameters corresponding to the optimal characteristic combination to obtain a response surface function model.
7. The prediction method according to claim 6, wherein in S02, the preprocessing operation includes: at least one of data cleaning processing, data normalization processing, outlier removal processing, and missing value interpolation processing.
8. The prediction method according to claim 6, wherein the step S03 includes:
s03-1, carrying out variable correlation analysis on characteristic parameters in initial data based on the initial data to obtain correlation among the characteristic parameters, and carrying out combination processing on the characteristics with the correlation larger than a first preset value to obtain initial characteristic combination;
S03-2, based on the initial data, carrying out variable sensitivity analysis on the characteristic parameters in the initial characteristic combination, and eliminating the characteristic with the sensitivity smaller than a second preset value to obtain the optimal characteristic combination.
9. The prediction method according to claim 8, wherein the S03-1 includes:
a1, randomly selecting a plurality of pieces of initial data from the plurality of pieces of initial data to serve as random samples, and inputting the random samples into a random forest model;
a2, the random forest model selects a plurality of initial characteristic parameters from initial characteristic parameters contained in all random samples to serve as a characteristic subset, and a decision tree is constructed;
a3, repeating the steps A1 to A2 to establish a plurality of decision trees;
a4, calculating importance scores of each initial characteristic parameter according to the use frequency of the initial characteristic parameter and the accuracy of node splitting;
a5, calculating the similarity between any two initial characteristic parameters according to the importance score of each initial characteristic parameter;
and A6, judging whether the correlation degree is larger than a first preset value, if so, combining two initial characteristic parameters corresponding to the correlation degree into one initial characteristic parameter to obtain an initial characteristic combination.
10. The prediction method according to claim 8, wherein the S03-2 includes:
performing a first sensitivity analysis process on the characteristic parameters in the initial characteristic combination by using a principal component analysis method to obtain a first analysis result;
performing a second sensitivity analysis process on the characteristic parameters in the initial characteristic combination by using a recursive characteristic elimination method to obtain a second analysis result;
the first analysis result and the second analysis result both comprise: sensitivity of the initial performance index result to the feature parameters in the initial feature combination;
and eliminating characteristic parameters with sensitivity lower than a second preset value in the first analysis result and the second analysis result from the initial characteristic combination to obtain an optimal characteristic combination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311113367.XA CN117420055A (en) | 2023-08-31 | 2023-08-31 | Method for predicting chloride ion permeability of alkali-activated cementing material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311113367.XA CN117420055A (en) | 2023-08-31 | 2023-08-31 | Method for predicting chloride ion permeability of alkali-activated cementing material |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117420055A true CN117420055A (en) | 2024-01-19 |
Family
ID=89525339
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311113367.XA Pending CN117420055A (en) | 2023-08-31 | 2023-08-31 | Method for predicting chloride ion permeability of alkali-activated cementing material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117420055A (en) |
-
2023
- 2023-08-31 CN CN202311113367.XA patent/CN117420055A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113096088B (en) | Concrete structure detection method based on deep learning | |
| CN116347318B (en) | Intelligent production test method and system for sound equipment | |
| CN113378967A (en) | Structural health monitoring multivariate data anomaly diagnosis method based on convolutional neural network and transfer learning | |
| CN114677362A (en) | Surface defect detection method based on improved YOLOv5 | |
| CN114330120A (en) | 24-hour PM prediction based on deep neural network2.5Method of concentration | |
| CN117420055A (en) | Method for predicting chloride ion permeability of alkali-activated cementing material | |
| CN112945772A (en) | Engineering rock body mechanical property analysis method under water rock circulation | |
| CN111141472B (en) | Anti-seismic support and hanger detection method and system | |
| CN111881800A (en) | Concrete filled steel tube void defect detection method based on AR model and self-service inspection | |
| CN111524114A (en) | Steel plate surface defect detection method based on deep learning | |
| CN116051496A (en) | Real-time sewer defect detection method | |
| CN115876987A (en) | CPVC-based cable protection pipe field rapid nondestructive quality testing method | |
| CN114970977A (en) | Abnormal data detection method and system for digital urban air quality monitoring data | |
| CN115540752A (en) | Engineering quality allowable deviation detection system based on laser point cloud and construction method | |
| CN113702431A (en) | Nondestructive testing system and method for prefabricated shell-concrete combined shear wall | |
| CN112992293A (en) | Concrete strength evolution prediction method in marine environment based on big data analysis | |
| CN117789867A (en) | Method for constructing alkali-activated cementing material sulfate corrosion performance model | |
| CN112229212A (en) | Roller kiln energy consumption abnormity detection method based on dynamic principal component analysis | |
| CN118013636B (en) | Masonry structure compressive property detection equipment and detection method | |
| CN111507418A (en) | Encaustic tile quality detection method | |
| CN105046056A (en) | Cloud-derived wind data testing method and apparatus | |
| CN114021467A (en) | Prediction method and system for sulfate corrosion damage of in-service tunnel lining structure | |
| CN111125902B (en) | Method and system for determining correlation of mechanical properties of materials of intelligent measurement equipment | |
| CN117523470B (en) | Steel structure fatigue crack identification method and system | |
| CN116630676B (en) | Large-scale-range field classification processing method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |