CN117935988A - Method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression - Google Patents
Method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression Download PDFInfo
- Publication number
- CN117935988A CN117935988A CN202410099015.1A CN202410099015A CN117935988A CN 117935988 A CN117935988 A CN 117935988A CN 202410099015 A CN202410099015 A CN 202410099015A CN 117935988 A CN117935988 A CN 117935988A
- Authority
- CN
- China
- Prior art keywords
- coarse aggregate
- compressive strength
- aggregate concrete
- recycled coarse
- support vector
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000013598 vector Substances 0.000 title claims abstract description 40
- 239000002994 raw material Substances 0.000 claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims abstract description 8
- 241000282461 Canis lupus Species 0.000 claims description 30
- 238000012360 testing method Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000000739 chaotic effect Effects 0.000 claims description 7
- 241000282421 Canidae Species 0.000 claims description 6
- 239000004568 cement Substances 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 239000003638 chemical reducing agent Substances 0.000 claims description 3
- 238000010835 comparative analysis Methods 0.000 claims description 3
- 239000010881 fly ash Substances 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 7
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000011161 development Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Landscapes
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
Abstract
The invention discloses a method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression, which specifically comprises the following steps: step one, collecting a sample; step two, building a model; step three, model evaluation; the invention relates to the technical field of compressive strength prediction of recycled concrete. According to the method for predicting the compressive strength of the recycled coarse aggregate concrete based on support vector regression, the intelligent prediction method is combined, the compressive strength of the recycled coarse aggregate concrete is predicted according to the raw material information of the mixing ratio of the recycled coarse aggregate concrete, the influence of the raw material change on the strength change can be predicted timely and rapidly, the raw material is used more accurately and more economically, the waste of resources and the damage to the environment are reduced, the economic and social benefits are further improved, and the sustainable development is realized.
Description
Technical Field
The invention relates to the technical field of compressive strength prediction of recycled concrete, in particular to a compressive strength prediction method of recycled coarse aggregate concrete based on support vector regression.
Background
The recycled coarse aggregate is a green material which is prepared by taking waste concrete blocks as raw materials, processing, crushing, grading and mixing according to a certain proportion, is used for replacing part of natural aggregate in concrete, and is one of measures for solving the problem of building rubbish pollution at present. The compressive strength is an important index for the structural design and performance evaluation of the recycled aggregate concrete, has important practical value for predicting the compressive strength of the recycled concrete, and has good generalization performance and robustness by carrying out nonlinear mapping on support vector regression to a high-dimensional space by utilizing an inner product function, so that the method is widely applied to the prediction problem. Therefore, the method can estimate the compressive strength of the concrete on the 28 th day in a short time and provide reference value for quality and control of the concrete.
The traditional compressive strength detection method is characterized in that sampling is firstly carried out, then a test piece is manufactured, and finally, a limit compressive test after 28 days of standard maintenance is carried out, so that the method has the defects of long test period, large workload, experimental error and the like, is seriously lagged behind the actual production process, and has the problems of time-varying time delay, multi-variable strong coupling, high nonlinearity, uncertainty and the like in the production process of concrete, the quality of the concrete is influenced, and the performance of a support vector regression model is sensitive to parameters and is extremely easy to influence by the kernel function type and corresponding parameters.
Based on the retrieval of the data, a method for predicting the compressive strength of the recycled coarse aggregate concrete based on support vector regression is specifically provided, and the compressive strength of the recycled coarse aggregate concrete is accurately and rapidly intelligently predicted.
Disclosure of Invention
(One) solving the technical problems
Aiming at the defects of the prior art, the invention provides a method for predicting the compressive strength of recycled coarse aggregate concrete based on support vector regression, which solves the problems.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme: the method for predicting the compressive strength of the recycled coarse aggregate concrete based on support vector regression specifically comprises the following steps:
Step one, sample collection: collecting historical recycled coarse aggregate concrete raw material parameter data and the actual measured compressive strength parameter data of the recycled coarse aggregate concrete 28d, taking the data as sample data, carrying out normalization processing on the sample data, and dividing the sample data into a training data set and a test data set according to a set proportion;
Step two, building a model: initializing initial parameters of a wolf algorithm by using Fuch chaotic map, calculating a fitness value, storing the first three wolves with the optimal fitness, introducing a nonlinear convergence factor strategy to improve the convergence factor of the wolf algorithm, updating the position of each wolf according to a wolf algorithm updating mechanism, optimizing a kernel function and a penalty factor in a support vector regression prediction model by adopting the improved wolf algorithm, combining the improved wolf algorithm with the support vector regression prediction model, and constructing a recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR;
Step three, model evaluation: inputting the training data set in the first step into the recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR in the second step, performing model training, obtaining an optimal parameter combination, optimizing the recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR according to the optimal parameter combination, and verifying the result of the compressive strength prediction of the optimized recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR by adopting the test data set.
The invention is further provided with: the historical recycled coarse aggregate concrete raw material parameter data in the first step comprises the following steps: cement, fly ash, fine aggregate, coarse aggregate, recycled coarse aggregate, water reducer and water-cement ratio of raw materials.
The invention is further provided with: the formula for initializing the initial population of the wolf through Fuch chaotic mapping in the second step comprises the following steps:
wherein x (T) noteq0, x e Z +, t=1, 2,..t.
The invention is further provided with: the formula of the nonlinear convergence factor strategy in the second step comprises the following steps:
where T represents the current iteration number and T represents the maximum iteration number.
The invention is further provided with: in the second step, the parameter setting of the gray wolf algorithm in the recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR model comprises the following steps: population number sizepop = (30-50), maximum iteration number max_iteration= (100-500), convergence factor a decreases nonlinearly from 2 to 0, r 1 and r 2 are random numbers between 0 and 1.
The invention is further provided with: in the second step, the support vector regression prediction model parameter setting in the recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR model comprises the following steps: penalty factor c= (0.1-100), the selected kernel function is RBF kernel function, kernel function parameter gamma= (0.1-100).
The invention is further provided with: in the third step, the method for verifying the result of the compressive strength prediction of the optimized recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR by adopting a test dataset comprises the following steps:
And designing a calculation formula of a model performance evaluation parameter fitting goodness coefficient, a root mean square error and an average absolute error, adopting a prediction result of an unoptimized support vector regression model to carry out comparative analysis, and verifying the prediction effect of the optimized recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR.
The invention is further provided with: the calculation formula of the model performance parameter fitting goodness is as follows;
Wherein Q i represents an actual value of the compressive strength of the i-th group data recycled coarse aggregate concrete 28d, Is the predicted value of the model,/>Then it is the average of the actual values.
The invention is further provided with: the root mean square error is calculated by the following formula:
Where T is the number of samples, Q i represents the actual value of the compressive strength of the i-th set of data recycled coarse aggregate concrete 28d, Is a predictive value of the model.
The invention is further provided with: the calculation formula of the average absolute error is as follows:
Where T is the number of samples, Q i represents the actual value of the compressive strength of the i-th set of data recycled coarse aggregate concrete 28d, Is a predictive value of the model.
(III) beneficial effects
The invention provides a method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression. The beneficial effects are as follows:
(1) According to the invention, by combining an intelligent prediction method, the compressive strength of the recycled coarse aggregate concrete is predicted by using the raw material information of the mixing ratio of the recycled coarse aggregate concrete, the influence of the raw material change on the strength change can be predicted timely and rapidly, and further, the raw material is used more accurately and more economically, so that the waste of resources and the damage to the environment are reduced, the economic and social benefits are further improved, and the sustainable development is realized.
(2) According to the invention, the gray wolf algorithm is improved by adding Fuch chaotic mapping and nonlinear convergence factor strategies, the problems that the gray wolf algorithm is easy to fall into local optimum and insufficient in population diversity are solved, an improved gray wolf algorithm is used for optimizing an SVR prediction model with RBF kernel functions, and the prediction accuracy of the model is enhanced.
(3) The invention also verifies the effectiveness and the correctness of the recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR in a comparative analysis mode.
Drawings
FIG. 1 is a schematic diagram of the steps of the present invention;
FIG. 2 is a table diagram of sample statistics in an embodiment of the present invention;
FIG. 3 is a graph showing the change of the convergence factor before and after improvement in the gray wolf algorithm according to the present invention;
FIG. 4 is a graph showing the results of the prediction of compressive strength of recycled coarse aggregate concrete in different models in an embodiment of the present invention;
FIG. 5 is a schematic diagram of a network structure of a support vector regression prediction model according to the present invention;
FIG. 6 is a schematic diagram of the result of fitting the FGWO-SVR predictive model of the invention to training set data;
FIG. 7 is a schematic representation of the result of fitting the FGWO-SVR predictive model of the invention to test set data;
fig. 8 is a flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Referring to fig. 1-8, the following technical solutions are provided in the embodiments of the present invention: the method for predicting the compressive strength of the recycled coarse aggregate concrete based on support vector regression specifically comprises the following steps:
S1, collecting 126 groups of actual data of recycled coarse aggregate concrete, wherein the actual data mainly comprise parameters of cement, fly ash, fine aggregate, coarse aggregate, recycled coarse aggregate, a water reducer and a water-cement ratio in raw materials of the recycled coarse aggregate concrete, and the actual measurement compressive strength parameters of the recycled coarse aggregate concrete 28d as sample data of an experiment, carrying out normalization processing on the sample data, and dividing the sample data into a training data set and a test data set according to a set proportion;
S2, initializing an initial population of a gray wolf algorithm by using Fuch chaotic mapping, increasing diversity of the population, and more comprehensively exploring a search space in a certain range to avoid the problem that the search space falls into a local optimal solution in an initial stage;
Fuch chaotic map initializes the initial population of the wolf, and the formula for increasing the population diversity is as follows:
Wherein x (T) noteq0, x ε Z +, t=1, 2,;
As a detailed description, the Hunter algorithm is a meta-heuristic algorithm proposed by Mirjalili et al according to social leadership mechanism and hunting behavior of the Hunter in nature, and the main process comprises three stages of tracking, surrounding and hunting;
When the wolf population surrounds the prey, the mathematical model of the wolf's surrounding the prey target during the tracking of the captured target prey is as follows:
wherein, Is the position vector of the gray wolf,/>Is the position vector of the prey, t is the current iteration number, A and D are coefficient vectors, and the calculation formula is as follows:
Where a is a convergence factor that converges linearly from 2 to 0 as the number of iterations increases, r 1、r2 is a random variable in [0,1], and T is the maximum number of iterations of the algorithm;
during the course of the gray wolf population tracking and hunting, the update of the position of the gray wolf population can be represented by the following mathematical model:
Wherein the method comprises the steps of And/>The spacing between the individual gray wolves and alpha, beta and delta wolves,/>, respectivelyAnd/>The first three best solutions of alpha, beta and delta wolves at the t-th iteration, namely the first three wolves with the best fitness, A 1、A2、A3、C1、C2 and C 3 can be calculated through the formulas;
S3, improving the convergence factor of the gray wolf algorithm by introducing a nonlinear convergence factor strategy to enhance the global and local exploitation capability of the gray wolf algorithm, wherein the specific formula is as follows:
wherein T represents the current iteration number, and T represents the maximum iteration number;
S4, optimizing a penalty factor and RBF kernel function parameters in the SVR model, namely the support vector regression prediction model, by using the two strategy improved gray wolf algorithm in a specific implementation process, wherein the formula of the RBF kernel function is as follows:
Wherein K (x, x i) is a nonlinear mapping result, x is an input vector, x i is the center of the RBF kernel function, σ is the width, m is the number of samples, and i x-x i i is the distance between the input x and the center x i. As shown in fig. 5, after the input of the SVR model is mapped to K (x, x i) through nonlinear mapping, the concrete strength y is obtained through a linear mapping formula, and the nonlinear mapping formula is as follows:
wherein, Alpha i and/>Is the support vector, n is the number of support vectors, b * is the offset;
S5, calculating formulas of a fitting goodness coefficient, a root mean square error and an average absolute error of performance evaluation parameters of the design model are adopted to conduct comparison analysis on a prediction result of an unoptimized support vector regression model, and the prediction effect of the optimized regenerated coarse aggregate concrete compressive strength prediction model is verified, wherein the calculating formulas of the fitting goodness coefficient R 2, the root mean square error RMSE and the average absolute error MAE are respectively as follows:
Where T is the number of samples, Q i represents the actual value of the compressive strength of the i-th set of data recycled coarse aggregate concrete 28d, Is the predicted value of the model, and Q is the average value of the actual values;
R 2 reveals the degree of linear correlation between the predicted and actual values, the better the model's performance when R 2 is closer to 1; the RMSE reflects the deviation degree between the predicted value and the actual value, can well reflect the measurement precision, and the MAE can well reflect the average difference condition between the predicted value and the actual value;
S6, constructing a recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR, dividing sample data into a training data set and a test data set according to the proportion of 8:2, performing model training by using the training data set, verifying the effect of the optimized recycled coarse aggregate concrete compressive strength prediction model by adopting the test data set, and outputting the compressive strength prediction result, wherein the result is shown in the figure 4, and the test and data result evaluation indexes are as follows: r 2 =0.9864, rmse=1.3345, mae= 1.0993.
As detailed description, the statistical result of the sample data in S1 is shown in fig. 2, and includes a variable number, a variable name, a minimum value, a maximum value, an average value, and a standard deviation.
In order to judge the strategy effect of the quoted nonlinear convergence factor, the iteration times and the convergence factor values are subjected to graph analysis, and the result is shown in fig. 3, and the improved nonlinear cosine convergence factor has relatively gentle initial change and relatively steep later change relative to the original linear convergence factor, so that the improved coefficient vector A is relatively larger in the iteration front-end numerical value, stronger in global exploration capacity, gradually converged in the later-end numerical value, gradually enhanced in local exploitation capacity, and is more suitable for solving the complex nonlinear optimization problem.
The comparison result of the real compressive strength of the recycled coarse aggregate concrete by the training set data shown in fig. 6 and the predicted value of the invention, and the comparison result of the real compressive strength of the recycled coarse aggregate concrete by the test set data shown in fig. 7 and the predicted value of the invention show that the predicted strength value obtained by the prediction method in the invention has higher correlation coefficient with the actual measured compressive strength value of the recycled coarse aggregate concrete 28d according to the data results, has higher prediction precision and accuracy, and has good application prospect in the field of prediction research of the compressive strength of the recycled coarse aggregate concrete based on materials and the mixing ratio.
Claims (10)
1. The method for predicting the compressive strength of the recycled coarse aggregate concrete based on support vector regression is characterized by comprising the following steps of: the method specifically comprises the following steps:
Step one, sample collection: collecting historical recycled coarse aggregate concrete raw material parameter data and the actual measured compressive strength parameter data of the recycled coarse aggregate concrete 28d, taking the data as sample data, carrying out normalization processing on the sample data, and dividing the sample data into a training data set and a test data set according to a set proportion;
Step two, building a model: initializing initial parameters of a wolf algorithm by using Fuch chaotic map, calculating a fitness value, storing the first three wolves with the optimal fitness, introducing a nonlinear convergence factor strategy to improve the convergence factor of the wolf algorithm, updating the position of each wolf according to a wolf algorithm updating mechanism, optimizing a kernel function and a penalty factor in a support vector regression prediction model by adopting the improved wolf algorithm, combining the improved wolf algorithm with the support vector regression prediction model, and constructing a recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR;
Step three, model evaluation: inputting the training data set in the first step into the recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR in the second step, performing model training, obtaining an optimal parameter combination, optimizing the recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR according to the optimal parameter combination, and verifying the result of the compressive strength prediction of the optimized recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR by adopting the test data set.
2. The method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression according to claim 1, wherein the method comprises the following steps: the historical recycled coarse aggregate concrete raw material parameter data in the first step comprises the following steps: cement, fly ash, fine aggregate, coarse aggregate, recycled coarse aggregate, water reducer and water-cement ratio of raw materials.
3. The method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression according to claim 1, wherein the method comprises the following steps: the formula for initializing the initial population of the wolf through Fuch chaotic mapping in the second step comprises the following steps:
wherein x (T) noteq0, x e Z +, t=1, 2,..t.
4. The method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression according to claim 1, wherein the method comprises the following steps: the formula of the nonlinear convergence factor strategy in the second step comprises the following steps:
where T represents the current iteration number and T represents the maximum iteration number.
5. The method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression according to claim 1, wherein the method comprises the following steps: in the second step, the parameter setting of the gray wolf algorithm in the recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR model comprises the following steps: population number sizepop = (30-50), maximum iteration number max_iteration= (100-500), convergence factor a decreases nonlinearly from 2 to 0, r 1 and r 2 are random numbers between 0 and 1.
6. The method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression according to claim 5, wherein the method comprises the following steps: in the second step, the support vector regression prediction model parameter setting in the recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR model comprises the following steps: penalty factor c= (0.1-100), the selected kernel function is RBF kernel function, kernel function parameter gamma= (0.1-100).
7. The method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression according to claim 1, wherein the method comprises the following steps: in the third step, the method for verifying the result of the compressive strength prediction of the optimized recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR by adopting a test dataset comprises the following steps:
And designing a calculation formula of a model performance evaluation parameter fitting goodness coefficient, a root mean square error and an average absolute error, adopting a prediction result of an unoptimized support vector regression model to carry out comparative analysis, and verifying the prediction effect of the optimized recycled coarse aggregate concrete compressive strength prediction model based on FGWO-SVR.
8. The method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression according to claim 7, wherein the method comprises the following steps: the calculation formula of the model performance parameter fitting goodness is as follows;
Wherein Q i represents an actual value of the compressive strength of the i-th group data recycled coarse aggregate concrete 28d, Is the predicted value of the model,/>Then it is the average of the actual values.
9. The method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression according to claim 7, wherein the method comprises the following steps: the root mean square error is calculated by the following formula:
Where T is the number of samples, Q i represents the actual value of the compressive strength of the i-th set of data recycled coarse aggregate concrete 28d, Is a predictive value of the model.
10. The method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression according to claim 7, wherein the method comprises the following steps: the calculation formula of the average absolute error is as follows:
Where T is the number of samples, Q i represents the actual value of the compressive strength of the i-th set of data recycled coarse aggregate concrete 28d, Is a predictive value of the model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410099015.1A CN117935988A (en) | 2024-01-24 | 2024-01-24 | Method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410099015.1A CN117935988A (en) | 2024-01-24 | 2024-01-24 | Method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117935988A true CN117935988A (en) | 2024-04-26 |
Family
ID=90760385
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410099015.1A Pending CN117935988A (en) | 2024-01-24 | 2024-01-24 | Method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117935988A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118133145A (en) * | 2024-05-07 | 2024-06-04 | 南京理工大学 | Data center rack air outlet temperature prediction method based on support vector machine |
-
2024
- 2024-01-24 CN CN202410099015.1A patent/CN117935988A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118133145A (en) * | 2024-05-07 | 2024-06-04 | 南京理工大学 | Data center rack air outlet temperature prediction method based on support vector machine |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110084367B (en) | Soil moisture content prediction method based on LSTM deep learning model | |
CN112069567B (en) | Method for predicting compressive strength of concrete based on random forest and intelligent algorithm | |
CN110782658B (en) | Traffic prediction method based on LightGBM algorithm | |
CN108009674A (en) | Air PM2.5 concentration prediction methods based on CNN and LSTM fused neural networks | |
CN107886161A (en) | A kind of global sensitivity analysis method for improving Complex Information System efficiency | |
CN117935988A (en) | Method for predicting compressive strength of recycled coarse aggregate concrete based on support vector regression | |
CN116721537A (en) | Urban short-time traffic flow prediction method based on GCN-IPSO-LSTM combination model | |
CN115347571B (en) | Photovoltaic power generation short-term prediction method and device based on transfer learning | |
Le et al. | Correlating the unconfined compressive strength of rock with the compressional wave velocity effective porosity and schmidt hammer rebound number using artificial neural networks | |
CN115271186B (en) | Reservoir water level prediction and early warning method based on delay factor and PSO RNN Attention model | |
CN112765902B (en) | Soft measurement modeling method for COD concentration in rural domestic sewage treatment process based on TentFWA-GD RBF neural network | |
Li et al. | A k-nearest neighbor locally weighted regression method for short-term traffic flow forecasting | |
CN114219131A (en) | Watershed runoff prediction method based on LSTM | |
Shang et al. | Research on intelligent pest prediction of based on improved artificial neural network | |
Wang et al. | A novel wind power forecasting system integrating time series refining, nonlinear multi-objective optimized deep learning and linear error correction | |
CN112507613B (en) | Second-level ultra-short-term photovoltaic power prediction method | |
CN113762591A (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM counterstudy | |
CN116189794A (en) | Rammed earth water salt content measurement method | |
CN117371616A (en) | Soil frost heaving rate prediction method for optimizing generalized regression neural network | |
CN117439053A (en) | Method, device and storage medium for predicting electric quantity of Stacking integrated model | |
CN110276478B (en) | Short-term wind power prediction method based on segmented ant colony algorithm optimization SVM | |
Wu et al. | Short-term electric load forecasting model based on PSO-BP | |
CN111310974A (en) | Short-term water demand prediction method based on GA-ELM | |
Cao et al. | Application of hybrid intelligent algorithm for multi-objective optimization of high performance concrete in complex alpine environment highway | |
Mazumdar et al. | Optimized machine learning model for predicting groundwater contamination |
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 |