CN110705707A - Tunnel structure chlorine corrosion life prediction method based on genetic algorithm - Google Patents
Tunnel structure chlorine corrosion life prediction method based on genetic algorithm Download PDFInfo
- Publication number
- CN110705707A CN110705707A CN201910939981.9A CN201910939981A CN110705707A CN 110705707 A CN110705707 A CN 110705707A CN 201910939981 A CN201910939981 A CN 201910939981A CN 110705707 A CN110705707 A CN 110705707A
- Authority
- CN
- China
- Prior art keywords
- tunnel
- genetic algorithm
- tunnel structure
- life
- chlorine
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Physiology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention relates to a method for predicting the chlorine corrosion life of a tunnel structure based on a genetic algorithm, and belongs to the field of prediction of the damage life of the tunnel structure. The invention comprises the following steps: selecting multiple factors of tunnel structure chlorine erosion damage influence, implementing an MATLAB-based algorithm, performing genetic iteration operation on the primary population chromosome, analyzing the evolution of the average fitness and the optimal fitness of individuals in the evolution search process, decoding the optimal population chromosome, finally obtaining a structure chlorine erosion damage life prediction result after the algorithm is terminated, introducing corresponding tunnel chlorine erosion parameters, constructing a tunnel structure chlorine erosion damage life prediction model, and verifying the rationality of the model through a tunnel example. The method fully considers various factors causing the chlorine corrosion damage of the tunnel structure, embodies the robustness for predicting the service life of the tunnel structure, and can meet the actual engineering requirements.
Description
Technical Field
The invention relates to a method for predicting the chlorine corrosion life of a tunnel structure based on a genetic algorithm, and belongs to the field of prediction of the damage life of the tunnel structure.
Background
Compared with a common ground building, the tunnel structure is deeply buried in complex erosion environments such as mountains, underground and seabed, the construction process is difficult and long, the capital demand is large, and particularly, the tunnel structure is a one-time project and cannot be overturned to be reconstructed after being constructed. In addition, the early tunnels in China are mostly designed and constructed according to relevant specifications of the former Soviet Union, the durability problem is not sufficiently known, nearly half of the tunnel projects in service in China currently have the durability problem, and hidden dangers of different degrees are buried in the long-term service life of the tunnel projects. At present, the tunnel engineering business of China is in a large development period, so that the residual service life of the early tunnel is accurately predicted, the reasonable dimension repair strong time is determined, and the design service life of the tunnel built in the future for 100 years or even longer is ensured.
The corrosion of chloride salt is one of the most main factors causing the reduction of the durability service life of a tunnel structure, the inner side of the tunnel is a semi-closed atmospheric environment, the internal acid gas is the main factor influencing the service life and the durability of the tunnel structure, hidden danger is buried in the service life of the tunnel, the essence of the corrosion damage of the chloride salt is that chloride ions enter the interior of the tunnel lining through a certain transmission mode, the chloride ions are accumulated on the surface of reinforcing steel bars and rely on the powerful passivation removing capability to remove the passivation of the reinforcing steel bars, a corrosion battery is formed, and after the chloride ions are accumulated to a certain concentration, the reinforcing steel bars are corroded and expanded, so that the lining is cracked and damaged.
The research on the prediction of the service life of the tunnel structure is not common at present, and most of the researches are based on the method and conclusion of the service life prediction of the ground structure, namely, the research is developed on the concrete forming the tunnel lining structure. The current structural life criteria are varied and commonly used: a carbonization or chlorine corrosion criterion, a cracking criterion, a damage limit criterion, and a bearing capacity limit criterion. Generally, the engineering is biased toward safety, and the service life limit of the tunnel structure is governed by the first three. In the aspect of specific research results, the prediction research on the durability life of the lining under the action of single factor is more, such as a carbonization life prediction model, a chlorine corrosion life prediction model, a sulfate corrosion model, a freeze-thaw damage model and the like.
At present, research on a tunnel structure service life prediction model at home and abroad is developed by taking tunnel structure lining concrete as a research object by substantially using relevant theories and experimental research on concrete structure durability and service life prediction. The special attributes of the tunnel structure, such as tunnel buried depth, excavation surface size, surrounding rock level, underground water seepage condition and the like, are not considered, the model consideration factors are not comprehensive enough, and the values of all parameters in the model have no uniform standard.
Disclosure of Invention
The invention provides a tunnel structure chlorine corrosion life prediction method based on a genetic algorithm by applying the genetic algorithm (GP for short) and combining related engineering example data and the existing semi-theoretical semi-empirical formula for life prediction to demonstrate the rationality and robustness of the algorithm, so that the life of tunnel chlorine corrosion damage can be predicted more accurately.
The invention adopts the following technical scheme for solving the technical problems:
a method for predicting the chlorine corrosion life of a tunnel structure based on a genetic algorithm comprises the following steps:
step one, considering the average annual temperature t, the relative humidity RH, the water cement ratio R of tunnel lining concrete, the thickness C of a lining protection layer, the depth x of a convection zone, the design hourly speed V of a tunnel, the net width W of the tunnel, the chloride ion binding capacity R, the lining degradation coefficient K and the surface chloride ion concentration CsCritical chloride ion concentration CcInitial chloride ion concentration C0Defining a function set of a genetic algorithm and a multi-factor tunnel chlorine corrosion life expression based on algorithm parameters;
collecting tunnel structure example data in a chlorine corrosion environment, inquiring the actual life value of each group of structure examples, and constructing sample data searched by a GP chlorine corrosion model under multiple factors to serve as a database of a genetic algorithm;
defining a fitness function and main GP parameters, and setting the size of population scale in evolutionary search and the maximum evolutionary algebra allowed;
running MATLAB genetic algorithm codes based on the first 20 groups of training sample data, and analyzing the distribution of adaptive values increased along with evolution algebra and the integrated behavior corresponding to each evolution algebra; performing genetic iteration operation on the chromosomes of the initial generation population until the chromosomes of the offspring population meet the stopping criterion of the fitness function;
after the genetic algorithm is terminated, decoding the optimal population chromosome to finally obtain a chlorine corrosion damage life prediction result, introducing corresponding chlorine corrosion influence parameters, and generating a chlorine corrosion damage life prediction model;
and sixthly, verifying the correctness and reasonability of the prediction model obtained by genetic algorithm search through the first 20 groups of test sample data, performing prediction calculation on the last 5 groups of tunnel examples by using the obtained prediction model, and comparing the prediction model with an actual value to verify the robustness of the prediction model.
In the first step, the function set based on the genetic algorithm is S { +, -/, sin, cos, ln, exp },
the expression of the multi-factor tunnel structure chlorine corrosion life is T ═ F (T, RH, R, C, x, V, W, R, K, CS,CC,C0)。
In the second step, the tunnel structure example data in the chlorine corrosion environment is 25 groups of tunnel engineering example data, the first 20 groups are used as training samples for genetic algorithm research, and the last 5 groups are used as test sample data.
In step three, the adaptive metric function is
Wherein T is a training output life value, TiFor the actual life value, the number of training samples n is taken to be 20.
In the step three, the population scale M in the evolution search is 400; the maximum evolution algebra G is allowed to be 10.
Fifthly, after the genetic algorithm is terminated, decoding the optimal population chromosome to finally obtain the structure of the model solution:
T＝abs((sin((K-8)/17+1e-3)-(exp((Cc-0.04)/0.63+1e-3)+1e-3)-(exp(( c-25)/45+1e-3)-(sin((W-6.5)/9.1+1e-3)+1e-3)+1e-3))/(((exp((C0-0.01)/ 0.053+1e-3)+(exp((t-9.8)/14.35+1e-3)+1e-3)+(exp((V-0)/50+1e-3)-(lo g((RH-0.49)/0.4+1e-3)+1e-3)+1e-3))-((sin((r-0.2)/0.7+1e-3)+(sin((Cs- 0.1)/1.27+1e-3)+1e-3)*(sin((x-0.4)/13.1+1e-3)*(sin((R-0.25)/0.15+1e- 3)+1e-3)+1e-3))+1e-3))+1e-3))*54.0878+54.5352
wherein: abs () represents the absolute value of the model value solved in parentheses;
after introducing corresponding parameters and neglecting the influence of 1e-3 in the formula, the corresponding expression is obtained as follows:
wherein x is the depth of the convection zone; c is the thickness of the lining protective layer; r is the water cement ratio of the tunnel lining concrete; r is the annual average temperature; RH is relative humidity; r is chloride ion binding ability; k is a lining deterioration coefficient; v is the tunnel design speed per hour; c0Is the initial chloride ion concentration;
Ccis the critical chloride ion concentration; csSurface chloride ion concentration; w is the clear width of the tunnel.
The invention has the following beneficial effects:
the method considers the influence of various factors on the tunnel chlorine corrosion damage life, has more accurate prediction on the tunnel structure life, and provides a reasonable and practical method for predicting the tunnel structure life by considering the inevitable trend of development and continuous increase of tunnel engineering, the complexity and the changeability of factors influencing the tunnel engineering service life, the high repair cost of the tunnel engineering caused by the reduction of the service life and other factors, thereby having good benefits in all aspects.
Drawings
FIG. 1 is a diagram of the steps of genetic algorithm operation.
FIG. 2 evolution diagram of mean and best fitness.
FIG. 3(a) is a scatter plot of fitness value distributions for evolutionary algebras of 10 generations; FIG. 3(b) is a scatter plot of fitness value distributions for 20 evolutionary algebras; FIG. 3(c) is a scatter plot of fitness value distributions for evolutionary algebras of 30 generations; FIG. 3(d) is a scatter plot of fitness value distributions for 40 evolutionary algebras; FIG. 3(e) a scatter plot of the fitness value distribution when the evolutionary algebra is 50 generations; FIG. 3(f) is a scatter plot of fitness value distributions for evolutionary algebras of 60 generations; FIG. 3(g) a scatter plot of fitness value distributions for evolutionary algebras of 70 generations;
FIG. 3(h) is a scatter plot of the fitness value distribution when the evolutionary algebra is 80 generations; FIG. 3(i) a scatter plot of the fitness value distribution when the evolutionary algebra is 90 generations; FIG. 3(j) is a scatter diagram of the distribution of adaptive values when the evolution algebra is 100 generations.
FIG. 4 is a graph comparing a training value and an actual value of chlorine etching.
FIG. 5 is a graph comparing predicted values and actual values of multifactor erosion.
The specific implementation mode is as follows:
the prediction model research of the invention spreads the factors of engineering example collection in the chlorine salt corrosion environment and the service life of the tunnel chlorine corrosion structure based on the genetic algorithm. In the research of the tunnel life prediction in the chlorine salt erosion environment, almost all prediction models are established on the basis of Fick-2 diffusion law, but the consideration of the specific properties of the tunnel structure, such as tunnel burial depth, surrounding rock properties, excavation span and other structural properties is rare
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be fully described below with reference to the relevant cases in the embodiment of the present invention.
Wherein, FIG. 1 is a diagram of the operation steps of the genetic algorithm for predicting the corrosion life of the tunnel structure.
The method specifically comprises the following steps:
step one, considering the average annual temperature t, the relative humidity RH, the water cement ratio R of tunnel lining concrete, the thickness C of a lining protection layer, the depth x of a convection zone, the design hourly speed V of a tunnel, the net width W of the tunnel, the chloride ion binding capacity R, the lining degradation coefficient K and the surface chloride ion concentration CsCritical chloride ion concentration CcInitial chloride ion concentration C0Influence of multiple factors on the chlorine corrosion life of the tunnel structure, and defining genetic calculation based on algorithm parametersThe functional set of the method and the life expression of tunnel chlorine etching under multiple factors. The expression of the chlorine corrosion life of the multi-factor tunnel structure is
T＝F(t,RH,R,c,x,V,W,r,K,CS,CC,C0)，
The set of genetic algorithm functions is S { +, -,/, sin, cos, ln, exp }
And step two, constructing 25 groups of sample data searched by a genetic algorithm (GP) under the multi-factor condition, and inquiring the actual life value of each group of tunnel examples, wherein the first 20 groups are training samples, and the last 5 groups are testing samples as shown in the table 1. Adaptive value is according to
And calculating, wherein the value of the training sample number n is 20, F is an adaptability measurement function, Ti is an actual life value, and T is a training output life value. Defining main GP parameters, wherein the population scale M in evolutionary search is 400; allowing the maximum evolution algebra G to be 100; the replication probability Pr is 0.1; the crossover probability Pc is 0.9; the mutation probability Pm is 0.05.
TABLE 1 sample data for GP cavitation model search under multi-factor
And step three, substituting the first 20 groups of sample data in the step two, and running a genetic algorithm code based on MATLAB. Fig. 2 shows the obtained evolution diagram of the average fitness and the optimal fitness, and fig. 3 shows the obtained scatter diagram of the adaptive value distribution of the evolution algebra G of 10, 20, 30, 40, 50, 60, 70, 80, 90 and 100. And analyzing the distribution of the adaptive values which are increased along with the evolution algebra and the integrated behaviors corresponding to the evolution algebras. And performing genetic iterative operation on the initial generation population chromosomes until the offspring population chromosomes of the initial generation population chromosomes meet the stopping criterion of the fitness function.
Step four, when the offspring population meets the fitness function stopping criterion of the genetic code, the offspring is the optimal chromosome population, the optimal chromosome is decoded after the genetic algorithm is terminated, and the structure of the model solution is finally obtained:
T＝abs((sin((L-8)/17+1e-3)-(exp((Cc-0.04)/0.63+1e-3)+1e-3)-(exp(( c-25)/45+1e-3)-(sin((W-6.5)/9.1+1e-3)+1e-3)+1e-3))/(((exp((C0-0.01)/ 0.053+1e-3)+(exp((t-9.8)/14.35+1e-3)+1e-3)+(exp((V-0)/50+1e-3)-(lo g((RH-0.49)/0.4+1e-3)+1e-3)+1e-3))-((sin((r-0.2)/0.7+1e-3)+(sin((Cs- 0.1)/1.27+1e-3)+1e-3)*(sin((x-0.4)/13.1+1e-3)*(sin((R-0.25)/0.15+1e- 3)+1e-3)+1e-3))+1e-3))+1e-3))*54.0878+54.5352
wherein: abs () represents the absolute value of the model value solved in parentheses;
after introducing corresponding parameters and neglecting the influence of 1e-3 in the formula, the corresponding expression is obtained as follows:
wherein x is the depth of the convection zone; c is the thickness of the lining protective layer; r is the water cement ratio of the tunnel lining concrete; t is the annual average temperature; RH is relative humidity; r is chloride ion binding ability; k is a lining deterioration coefficient; v is the tunnel design speed per hour; c0Is the initial chloride ion concentration;
Ccis the critical chloride ion concentration; csSurface chloride ion concentration; w is the clear width of the tunnel.
Step five, carrying out life training calculation on the obtained life prediction model on the first 20 groups of tunnel examples in the table 1, and comparing the calculation result with an actual value to further obtain the accuracy of the prediction model, as shown in the table 2:
TABLE 2 actual values of multifactor training samples are compared to training values
From the data in the table, it can be known that the GP model training values obtained by the multi-factor evolution have better consistency, and since the scale of the search of the present evolution is larger, 400 × 100, the average absolute error and the relative error of the learning samples are smaller, which are respectively 3.21 years and 0.0366. The comparison curve of the training values and the actual values of the samples is shown in fig. 4:
in the current research on the service life of the tunnel in the chlorine corrosion environment, no scholars carry out relevant research on a prediction method or a model under the action of such factors, so that the accuracy and the reasonability of the prediction model obtained by searching a genetic algorithm are verified through a test sample. And the other 5 groups of tunnel examples are subjected to predictive calculation by using the GP model, and the ratio of the result and the actual value is shown in FIG. 5.
From the comparison results in fig. 5, it can be seen that the predicted results of the tunnel corrosion environmental life model under the influence of multiple factors, which is obtained based on the genetic algorithm search, for the 5 groups of examples are better matched with the actual values thereof, which indicates that the model has certain rationality.
Claims (6)
1. A tunnel structure chlorine corrosion life prediction method based on a genetic algorithm is characterized by comprising the following steps:
step one, considering the average annual temperature t, the relative humidity RH, the water cement ratio R of tunnel lining concrete, the thickness C of a lining protection layer, the depth x of a convection zone, the design hourly speed V of a tunnel, the net width W of the tunnel, the chloride ion binding capacity R, the lining degradation coefficient K and the surface chloride ion concentration CsCritical chloride ion concentration CcInitial chloride ion concentration C0Defining a function set of a genetic algorithm and a multi-factor tunnel chlorine corrosion life expression based on algorithm parameters;
collecting tunnel structure example data in a chlorine corrosion environment, inquiring the actual life value of each group of structure examples, and constructing sample data searched by a GP chlorine corrosion model under multiple factors to serve as a database of a genetic algorithm;
defining a fitness function and main GP parameters, and setting the size of population scale in evolutionary search and the maximum evolutionary algebra allowed;
running MATLAB genetic algorithm codes based on the first 20 groups of training sample data, and analyzing the distribution of adaptive values increased along with evolution algebra and the integrated behaviors corresponding to the evolution algebras; performing genetic iteration operation on the initial generation population chromosomes until the offspring population chromosomes meet the stopping criterion of the fitness function;
after the genetic algorithm is terminated, decoding the optimal population chromosome to finally obtain a chlorine corrosion damage life prediction result, introducing corresponding chlorine corrosion influence parameters, and generating a chlorine corrosion damage life prediction model;
and sixthly, verifying the correctness and reasonability of the prediction model obtained by genetic algorithm search through the first 20 groups of test sample data, performing prediction calculation on the last 5 groups of tunnel examples by using the obtained prediction model, and comparing the prediction model with an actual value to verify the robustness of the prediction model.
2. The method for predicting the corrosion lifetime of a tunnel structure based on a genetic algorithm according to claim 1, wherein the method comprises the following steps: in the first step, the function set based on the genetic algorithm is S { +, -/, sin, cos, ln, exp },
the expression of the multi-factor tunnel structure chlorine corrosion life is T ═ F (T, RH, R, C, x, V, W, R, K, CS,CC,C0)。
3. The method for predicting the corrosion lifetime of a tunnel structure based on a genetic algorithm according to claim 1, wherein the method comprises the following steps: in the second step, the tunnel structure example data in the chlorine corrosion environment is 25 groups of tunnel engineering example data, the first 20 groups are used as training samples for genetic algorithm research, and the last 5 groups are used as test sample data.
4. According to claim 1The method for predicting the chlorine corrosion life of the tunnel structure based on the genetic algorithm is characterized by comprising the following steps of: in step three, the adaptive metric function is
Wherein T is a training output life value, TiFor the actual life value, the number of training samples n is taken to be 20.
5. The method for predicting the corrosion lifetime of a tunnel structure based on a genetic algorithm according to claim 1, wherein the method comprises the following steps: in the step three, the population scale M in the evolution search is 400; the maximum evolution algebra G is allowed to be 10.
6. The method for predicting the corrosion lifetime of a tunnel structure based on a genetic algorithm according to claim 1, wherein the method comprises the following steps: fifthly, after the genetic algorithm is terminated, decoding the optimal population chromosome to finally obtain the structure of the model solution:
T＝abs((sin((K-8)/17+1e-3)-(exp((Cc-0.04)/0.63+1e-3)+1e-3)-(exp((c-25)/45+1e-3)-(sin((W-6.5)/9.1+1e-3)+1e-3)+1e-3))/(((exp((C0-0.01)/0.053+1e-3)+(exp((t-9.8)/14.35+1e-3)+1e-3)+(exp((V-0)/50+1e-3)-(log((RH-0.49)/0.4+1e-3)+1e-3)+1e-3))-((sin((r-0.2)/0.7+1e-3)+(sin((Cs-0.1)/1.27+1e-3)+1e-3)*(sin((x-0.4)/13.1+1e-3)*(sin((R-0.25)/0.15+1e-3)+1e-3)+1e-3))+1e-3))+1e-3))*54.0878+54.5352
wherein: abs () represents the absolute value of the model value solved in parentheses;
after introducing corresponding parameters and neglecting the influence of 1e-3 in the formula, the corresponding expression is obtained as follows:
wherein x is the depth of the convection zone; c is the thickness of the lining protective layer; r is the water cement ratio of the tunnel lining concrete; t is the annual average temperature; RH is relative humidity; r is chloride ion binding capacity; k is a lining deterioration coefficient; v is the tunnel design speed per hour; c0Is the initial chloride ion concentration; ccIs the critical chloride ion concentration; csSurface chloride ion concentration; w is the clear width of the tunnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910939981.9A CN110705707B (en) | 2019-09-30 | 2019-09-30 | Tunnel structure chlorine corrosion life prediction method based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910939981.9A CN110705707B (en) | 2019-09-30 | 2019-09-30 | Tunnel structure chlorine corrosion life prediction method based on genetic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110705707A true CN110705707A (en) | 2020-01-17 |
| CN110705707B CN110705707B (en) | 2022-08-19 |
Family
ID=69197407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910939981.9A Active CN110705707B (en) | 2019-09-30 | 2019-09-30 | Tunnel structure chlorine corrosion life prediction method based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705707B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112255393A (en) * | 2020-10-21 | 2021-01-22 | 中建三局绿色产业投资有限公司 | Sewage tunnel structure damage risk rating method and device |
| CN113204815A (en) * | 2021-04-19 | 2021-08-03 | 河海大学 | Data-driven underground structure service life prediction method in acidic environment |
| CN114722650A (en) * | 2022-01-21 | 2022-07-08 | 东南大学 | Tunnel structure residual life prediction method based on lining degradation |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951834A (en) * | 2015-06-24 | 2015-09-30 | 上海大学 | LSSVM (least squares support vector machine) wind speed forecasting method based on integration of GA (genetic algorithm) and PSO (particle swarm optimization) |
| CN110991067A (en) * | 2019-12-11 | 2020-04-10 | 河海大学 | Underground reinforced concrete structure carbonization life intelligent modeling method based on big data |
-
2019
- 2019-09-30 CN CN201910939981.9A patent/CN110705707B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951834A (en) * | 2015-06-24 | 2015-09-30 | 上海大学 | LSSVM (least squares support vector machine) wind speed forecasting method based on integration of GA (genetic algorithm) and PSO (particle swarm optimization) |
| CN110991067A (en) * | 2019-12-11 | 2020-04-10 | 河海大学 | Underground reinforced concrete structure carbonization life intelligent modeling method based on big data |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112255393A (en) * | 2020-10-21 | 2021-01-22 | 中建三局绿色产业投资有限公司 | Sewage tunnel structure damage risk rating method and device |
| CN112255393B (en) * | 2020-10-21 | 2022-11-04 | 中建三局绿色产业投资有限公司 | Sewage tunnel structure damage risk rating method and device |
| CN113204815A (en) * | 2021-04-19 | 2021-08-03 | 河海大学 | Data-driven underground structure service life prediction method in acidic environment |
| CN113204815B (en) * | 2021-04-19 | 2022-10-14 | 河海大学 | Data-driven underground structure service life prediction method in acidic environment |
| CN114722650A (en) * | 2022-01-21 | 2022-07-08 | 东南大学 | Tunnel structure residual life prediction method based on lining degradation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110705707B (en) | 2022-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110705707B (en) | Tunnel structure chlorine corrosion life prediction method based on genetic algorithm | |
| CN109543237B (en) | Foundation pit displacement prediction method based on GA-BP neural network | |
| CN111832101B (en) | Construction method of cement strength prediction model and cement strength prediction method | |
| Cannamela et al. | Controlled stratification for quantile estimation | |
| Zhao et al. | Inverse analysis of deep excavation using differential evolution algorithm | |
| Liu et al. | Prediction of concrete corrosion in sewers with hybrid Gaussian processes regression model | |
| CN110991067B (en) | Underground reinforced concrete structure carbonization life intelligent modeling method based on big data | |
| CN112100927A (en) | Prediction method for slope deformation and soft soil foundation settlement based on GA-BP neural network | |
| CN108536926A (en) | Based on the corrosion oil-gas pipeline Residual Life method for improving adaptive GEV distributions | |
| Aboutalebi et al. | Multiobjective design of water-quality monitoring networks in river-reservoir systems | |
| Muduli et al. | First-order reliability method for probabilistic evaluation of liquefaction potential of soil using genetic programming | |
| CN115130375A (en) | Rock burst intensity prediction method | |
| CN115796059A (en) | Electrical equipment service life prediction method and system based on deep learning | |
| CN112288147A (en) | Method for predicting insulation state of generator stator by BP-Adaboost strong predictor | |
| Xue et al. | PREDICTION OF SLOPE STABILITY BASED ON GA-BP HYBRID ALGORITHM. | |
| Guo et al. | Time-dependent reliability analysis based on point-evolution kernel density estimation: Comprehensive approach with continuous and shock deterioration and maintenance | |
| Farran et al. | New life‐cycle costing approach for infrastructure rehabilitation | |
| Rajabi et al. | Prediction of the degree of steel corrosion damage in reinforced concrete using field-based data by multi-gene genetic programming approach | |
| Younis et al. | Continuation ratio model for the performance behavior of wastewater collection networks | |
| CN114611832B (en) | Seawater intrusion prediction method based on Bayesian multi-model set pair analysis | |
| CN116010291A (en) | Multipath coverage test method based on equalization optimization theory and gray prediction model | |
| CN115358102A (en) | Corrosion pipeline failure probability analysis method under earthquake action of introduced internal detection data | |
| CN113378276A (en) | Composite foundation intelligent design method based on genetic algorithm and gene expression programming | |
| Song et al. | Parameter determination method of soil constitutive model based on machine learning | |
| CN114492964A (en) | Photovoltaic power ultra-short term probability prediction method based on wavelet decomposition and optimized deep confidence network |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |