CN103914594A - Concrete thermodynamic parameter intelligent recognition method based on support vector machine - Google Patents
Concrete thermodynamic parameter intelligent recognition method based on support vector machine Download PDFInfo
- Publication number
- CN103914594A CN103914594A CN201410117419.5A CN201410117419A CN103914594A CN 103914594 A CN103914594 A CN 103914594A CN 201410117419 A CN201410117419 A CN 201410117419A CN 103914594 A CN103914594 A CN 103914594A
- Authority
- CN
- China
- Prior art keywords
- vector machine
- support vector
- concrete
- parameters
- thermal parameters
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a concrete thermodynamic parameter intelligent recognition method based on a support vector machine. The method includes firstly determining the range of inverse parameters; designing sample schemes of concrete thermodynamic parameters by an uniform design method; acquiring one temperature value of each feature point in the sample schemes through finite element forward modeling, utilizing the temperature values and corresponding thermodynamic parameters in the sample schemes as study samples, and establishing a support vector machine model; utilizing the differential evolution algorithm to perform global search, searching and acquiring each coefficient of the support vector machine, determining the nonlinear relationship between the inverse parameters and actual temperature values of monitoring points, and establishing a support vector machine prediction model; utilizing the support vector machine prediction model as a forward model, utilizing the differential evolution algorithm to perform global search for the concrete thermodynamic parameters, and searching and acquiring inverse parameters closest to the actual temperature values of the monitoring points as the optimal concrete thermodynamic parameters. The method has the advantages of rapidness in recognition and simpleness.
Description
Technical field
The present invention relates to a kind of concrete thermal parameters intelligent identification Method based on support vector machine, belong to the technical field of Hydraulic and Hydro-Power Engineering.
Background technology
In large volume temperature controlled anticracking, the accuracy that the setting logarithm value of concrete thermal parameters is calculated produces impact greatly, in concrete thermal parameters identification, there are a lot of methods at present, for example Liu Ning introduces the thermodynamic parameter stochastic inverse of large volume temperature field by parameter estimation and analyzes, Li Jun adopts Flexible Tolerance method to carry out inverting to concrete thermal parameters, and Wang Zhen is red, and incorporation engineering practice utilizes genetic algorithm in identification to go out concrete thermal parameters etc.These searching algorithms, in concrete thermal parameters identifying, optimized algorithm need to constantly repeat to call temperature calculation program and iterates, in general obtain assessing the cost of temperature field relatively high, special in concrete dam is in the time that water flowing is cooling, need to consider tiny chilled water unit, in practical engineering calculation, be difficult to realize so large-scale calculating.
Afterwards, the people such as Yu Meng carried out back analysis by neural network to the temperature field of concrete dam in order to reduce to assess the cost, and nerual network technique is to a certain degree alleviating calculated amount, and neural computing exists and is easily absorbed in local minizing point simultaneously.Support vector machine (SVM based on minimization principle, Support Vector Machine) be a kind of new algorithm, there is the feature of global optimization, at interference free performance with solve speed method more in the past and will get well, be particularly suitable for processing the nonlinear problem under Small Sample Size.
Above-mentioned research contents comes from the sub-problem " the coupling mechanism in stress field and temperature field " in state natural sciences fund " major mechanical problems of extra-high-speed concrete dam failure damage under catastrophe condition ".
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of concrete thermal parameters intelligent identification Method based on support vector machine, overcomes the deficiency in the recognition methods of existing mass concrete thermodynamic parameter, and a kind of recognition methods of Intelligent practical is provided.
The present invention is for solving the problems of the technologies described above by the following technical solutions:
The present invention, in conjunction with Uniform ity Design Method, support vector machine, three kinds of methods of differential evolution algorithm, provides a kind of concrete thermal parameters intelligent identification Method based on support vector machine.Wherein, Uniform ity Design Method is a kind of test method that the consistent distribution theory of number theory and multivariate statistical analysis is combined to use, and it is uniformly distributed testing site in trial stretch, makes every effort to obtain maximum information with minimum test.Support vector machine is to be based upon on the theoretical and structure risk minimum principle basis of the VC dimension of Statistical Learning Theory, seeks optimal compromise, in the hope of obtaining best Generalization Ability according to limited sample information between the complicacy of model and learning ability.Differential evolution algorithm is a kind of heuritic approach for optimization problem, adopts man-to-man superseded mechanism to carry out Population Regeneration, and the probabilistic model of simulation biological evolution, by iterating, makes those individualities that conform be saved.
A kind of concrete thermal parameters intelligent identification Method based on support vector machine of the present invention, comprises following concrete steps:
Step 1, the feature of the concrete thermal parameters of inverting as required, determines the span of inverted parameters;
Step 2, utilizes Uniform ity Design Method, the sample plan of design concrete thermal parameters;
Step 3, is just drilling the temperature value that draws each unique point in sample plan by finite element;
Step 4, is just drilling thermodynamic parameter value corresponding in the temperature value of each unique point drawing and sample plan as learning sample using finite element in step 3, sets up supporting vector machine model, carries out the study of support vector machine, is specially:
Utilize differential evolution algorithm to carry out global search, search to obtain each coefficient of support vector machine, determine the nonlinear relationship between the inverted parameters of monitoring point and the actual temperature value of monitoring point simultaneously, set up SVM prediction model;
Step 5, with the SVM prediction model of having trained in step 4 as forward model, utilize differential evolution algorithm global search concrete thermal parameters, search with the immediate inverted parameters of monitoring point actual temperature value, be optimum concrete thermal parameters value.
As further prioritization scheme of the present invention, described concrete thermal parameters comprises concrete coefficient of heat conductivity, surface heat transfer coefficient, adiabatic heating speed, water pipe surface heat coefficient.
As further prioritization scheme of the present invention, the model of the model selection least square vector machine of support vector machine described in step 4.
The present invention adopts above technical scheme compared with prior art, has following technique effect:
1) recognition speed of the present invention is fast, can significantly improve at concrete;
2) the present invention adopts differential evolution algorithm to identify, and has the advantages that method is simple, can identify globally optimal solution;
3) the present invention, the in the situation that of small sample, can correctly identify concrete thermal parameters value;
4) thermodynamics inverted parameters is replaced into temperature control measures such as building temperature, surface heat preservation, water flowing temperature, water flowing time by the present invention, also can be optimized temperature controlled method for mass concrete.
Brief description of the drawings
Fig. 1 is method flow diagram of the present invention.
Fig. 2 is the process flow diagram of support vector machine.
Fig. 3 is the process flow diagram of differential evolution method.
Embodiment
Describe embodiments of the present invention below in detail, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has the element of identical or similar functions from start to finish.Be exemplary below by the embodiment being described with reference to the drawings, only for explaining the present invention, and can not be interpreted as limitation of the present invention.
Those skilled in the art of the present technique are understandable that, unless specially statement, singulative used herein " ", " one ", " described " and " being somebody's turn to do " also can comprise plural form.Should be further understood that, the wording using in instructions of the present invention " comprises " and refers to and have described feature, integer, step, operation, element and/or assembly, exists or adds one or more other features, integer, step, operation, element, assembly and/or their group but do not get rid of.Should be appreciated that, when we claim element to be " connected " or " coupling " when another element, it can be directly connected or coupled to other elements, or also can have intermediary element.In addition, " connection " used herein or " coupling " can comprise wireless connections or couple.Wording "and/or" used herein comprises arbitrary unit of listing item and all combinations that one or more is associated.
Those skilled in the art of the present technique are understandable that, unless otherwise defined, all terms used herein (comprising technical term and scientific terminology) have with the present invention under the identical meaning of the general understanding of those of ordinary skill in field.Should also be understood that such as those terms that define in general dictionary and should be understood to have the meaning consistent with meaning in the context of prior art, unless and definition as here, can not explain by idealized or too formal implication.
Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:
The present invention designs a kind of concrete thermal parameters intelligent identification Method based on support vector machine, as shown in Figure 1, comprises following concrete steps:
Step 1, the feature of the concrete thermal parameters of inverting as required, determines the span of inverted parameters;
Step 2, utilizes Uniform ity Design Method, the sample plan of design concrete thermal parameters;
Step 3, is just drilling the temperature value that draws each unique point in sample plan by finite element;
Step 4, is just drilling thermodynamic parameter value corresponding in the temperature value of each unique point drawing and sample plan as learning sample using finite element in step 3, sets up supporting vector machine model, carries out the study of support vector machine, is specially:
Utilize differential evolution algorithm to carry out global search, search to obtain each coefficient of support vector machine, determine the nonlinear relationship between the inverted parameters of monitoring point and the actual temperature value of monitoring point simultaneously, set up SVM prediction model;
Step 5, with the SVM prediction model of having trained in step 4 as forward model, utilize differential evolution algorithm global search concrete thermal parameters, search with the immediate inverted parameters of monitoring point actual temperature value, be optimum concrete thermal parameters value.
In conjunction with Uniform ity Design Method, support vector machine, three methods of differential evolution algorithm, specific as follows in a kind of concrete thermal parameters intelligent identification Method based on support vector machine of the present invention:
Uniform ity Design Method is a kind of test method that the consistent distribution theory of number theory and multivariate statistical analysis is combined to use, and it is uniformly distributed testing site in trial stretch, makes every effort to obtain maximum information with minimum test.Confirm concrete thermal parameters with and span after, according to Uniform ity Design Method, can draw sample plan, be expressed as
wherein, U
*represent uniform Design, q is number of levels number, and S is columns, and n is sample number.
Support vector machine method is that the VC that is based upon Statistical Learning Theory ties up on theoretical and structure risk minimum principle basis, between the complicacy of model and learning ability, seek optimal compromise according to limited sample information, in the hope of obtaining best Generalization Ability, specifically as shown in Figure 2:
1, obtain learning sample;
2, set up and support least square vector machine model, expression formula is as follows:
In formula, a
i, b is coefficient, K (x, x
i) be kernel function;
Parameter a
i, b establishes an equation and draws by down:
In formula, y is output variable matrix; C is penalty factor; Θ=[1 ..., 1], K is kernel function;
3, determine in support vector machine that inverted parameters is as the calculation of parameter such as nuclear parameter, penalty factor scope;
4, solve each coefficient in support vector machine by differential evolution algorithm;
5, determine the Nonlinear Mapping relation of input quantity and output quantity, the nonlinear relationship between the inverted parameters of monitoring point and the actual temperature value of monitoring point, sets up SVM prediction model;
6, in forecast model using concrete thermal parameters as input quantity, can draw temperature value output quantity by forecast model.
Differential evolution algorithm is a kind of heuritic approach for optimization problem, adopt man-to-man superseded mechanism to carry out Population Regeneration, the probabilistic model of simulation biological evolution, by iterating, make those individualities that conform be saved, specifically as shown in Figure 3:
1, initiation parameter, comprises population scale NP, zoom factor K, crossover probability CR; The each individuality of each variable random initializtion in field of definition, arranges maximum iteration time T, and current iteration timer t=0 is set;
2, calculate the fitness of each individuality, obtain the individuality of optimal-adaptive degree;
3, judge whether to reach precision or maximum iteration time, calculate then Output rusults if exit, otherwise carry out next step operation;
4, to each target individual execution step 5~step 7, generate t+1 for population;
5, in population, randomly draw Different Individual, by mutation operation, generate variation individual;
6, carry out interlace operation, generate test individual;
7, select operation, generate t+1 for individuality;
8, t=t+1, returns to step 2.
The above; it is only the embodiment in the present invention; but protection scope of the present invention is not limited to this; any people who is familiar with this technology is in the disclosed technical scope of the present invention; can understand conversion or the replacement expected; all should be encompassed in of the present invention comprise scope within, therefore, protection scope of the present invention should be as the criterion with the protection domain of claims.
Claims (3)
1. the concrete thermal parameters intelligent identification Method based on support vector machine, is characterized in that, the method comprises following concrete steps:
Step 1, the feature of the concrete thermal parameters of inverting as required, determines the span of inverted parameters;
Step 2, utilizes Uniform ity Design Method, the sample plan of design concrete thermal parameters;
Step 3, is just drilling the temperature value that draws each unique point in sample plan by finite element;
Step 4, is just drilling thermodynamic parameter value corresponding in the temperature value of each unique point drawing and sample plan as learning sample using finite element in step 3, sets up supporting vector machine model, carries out the study of support vector machine, is specially:
Utilize differential evolution algorithm to carry out global search, search to obtain each coefficient of support vector machine, determine the nonlinear relationship between the inverted parameters of monitoring point and the actual temperature value of monitoring point simultaneously, set up SVM prediction model;
Step 5, with the SVM prediction model of having trained in step 4 as forward model, utilize differential evolution algorithm global search concrete thermal parameters, search with the immediate inverted parameters of monitoring point actual temperature value, be optimum concrete thermal parameters value.
2. want a kind of concrete thermal parameters intelligent identification Method based on support vector machine described in 1 according to right, it is characterized in that, described concrete thermal parameters comprises concrete coefficient of heat conductivity, surface heat transfer coefficient, adiabatic heating speed, water pipe surface heat coefficient.
3. want a kind of concrete thermal parameters intelligent identification Method based on support vector machine described in 1 according to right, it is characterized in that, the model of the model selection least square vector machine of support vector machine described in step 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410117419.5A CN103914594A (en) | 2014-03-26 | 2014-03-26 | Concrete thermodynamic parameter intelligent recognition method based on support vector machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410117419.5A CN103914594A (en) | 2014-03-26 | 2014-03-26 | Concrete thermodynamic parameter intelligent recognition method based on support vector machine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103914594A true CN103914594A (en) | 2014-07-09 |
Family
ID=51040270
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410117419.5A Pending CN103914594A (en) | 2014-03-26 | 2014-03-26 | Concrete thermodynamic parameter intelligent recognition method based on support vector machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103914594A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104238588A (en) * | 2014-09-01 | 2014-12-24 | 中国水利水电科学研究院 | Intelligent heat preservation monitoring system and method for mass concrete |
CN106959360A (en) * | 2017-03-18 | 2017-07-18 | 江西理工大学 | The rare-earth mining area farmland water pH value flexible measurement method developed using backward difference |
CN108549770A (en) * | 2018-04-13 | 2018-09-18 | 西安理工大学 | The adaptive inversion method of Parameters for Rockfill Dams based on QGA-MMRVM |
CN108801474A (en) * | 2018-06-05 | 2018-11-13 | 哈尔滨工程大学 | A kind of four spectrum turbo blade radiative thermometric methods |
CN109164852A (en) * | 2018-07-27 | 2019-01-08 | 同济大学 | A kind of mass concrete self-adaptive temperature and stress control method |
CN110210114A (en) * | 2019-05-30 | 2019-09-06 | 中国电建集团昆明勘测设计研究院有限公司 | Highest temperature prediction algorithm for roller compacted concrete gravity dam construction period |
CN110364229A (en) * | 2019-07-12 | 2019-10-22 | 国家纳米科学中心 | Thermodynamics spectrum unscrambling error analysis method, device, electronic equipment and storage medium |
CN110379466A (en) * | 2019-07-12 | 2019-10-25 | 国家纳米科学中心 | Thermodynamics Spectra Unfolding Methods, device, electronic equipment and storage medium |
CN110442967A (en) * | 2019-08-05 | 2019-11-12 | 华能澜沧江水电股份有限公司 | Concrete thermal parameter inverse analysis method |
CN110619623A (en) * | 2019-08-08 | 2019-12-27 | 广东工业大学 | Automatic identification method for heating of joint of power transformation equipment |
CN112561246A (en) * | 2020-11-27 | 2021-03-26 | 国网山东省电力公司建设公司 | Intelligent control method for mass concrete quality |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102436722A (en) * | 2011-12-05 | 2012-05-02 | 中国水利水电科学研究院 | Temperature control and crack prevention monitoring method of concrete dam |
-
2014
- 2014-03-26 CN CN201410117419.5A patent/CN103914594A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102436722A (en) * | 2011-12-05 | 2012-05-02 | 中国水利水电科学研究院 | Temperature control and crack prevention monitoring method of concrete dam |
Non-Patent Citations (4)
Title |
---|
SHEN DONG-SHENG 等: "Study on the Drafting and Early-warning of Temperature Double-control Index of Different Sections & Periods of Concrete Block", 《APPLIED MECHANICS AND MATERIALS》 * |
于猛 等: "基于BP神经网络的碾压混凝土坝温度场反分析", 《电网与水力发电进展》 * |
宫经伟: "水工准大体积混凝土分布式光纤温度监测与智能反馈研究", 《中国博士学位论文全文数据库-工程科技Ⅱ辑》 * |
陈涛 等: "基于差分进化算法的支持向量机参数选择", 《计算机工程与应用》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104238588A (en) * | 2014-09-01 | 2014-12-24 | 中国水利水电科学研究院 | Intelligent heat preservation monitoring system and method for mass concrete |
CN106959360A (en) * | 2017-03-18 | 2017-07-18 | 江西理工大学 | The rare-earth mining area farmland water pH value flexible measurement method developed using backward difference |
CN106959360B (en) * | 2017-03-18 | 2019-03-29 | 江西理工大学 | The rare-earth mining area farmland water pH value flexible measurement method to develop using backward difference |
CN108549770A (en) * | 2018-04-13 | 2018-09-18 | 西安理工大学 | The adaptive inversion method of Parameters for Rockfill Dams based on QGA-MMRVM |
CN108549770B (en) * | 2018-04-13 | 2022-04-12 | 西安理工大学 | Adaptive inversion method for rock-fill dam material parameters based on QGA-MMRVM |
CN108801474A (en) * | 2018-06-05 | 2018-11-13 | 哈尔滨工程大学 | A kind of four spectrum turbo blade radiative thermometric methods |
CN109164852B (en) * | 2018-07-27 | 2020-11-27 | 同济大学 | Self-adaptive temperature and stress control method for mass concrete |
CN109164852A (en) * | 2018-07-27 | 2019-01-08 | 同济大学 | A kind of mass concrete self-adaptive temperature and stress control method |
CN110210114A (en) * | 2019-05-30 | 2019-09-06 | 中国电建集团昆明勘测设计研究院有限公司 | Highest temperature prediction algorithm for roller compacted concrete gravity dam construction period |
CN110210114B (en) * | 2019-05-30 | 2022-09-30 | 中国电建集团昆明勘测设计研究院有限公司 | Highest temperature prediction algorithm for roller compacted concrete gravity dam construction period |
CN110379466A (en) * | 2019-07-12 | 2019-10-25 | 国家纳米科学中心 | Thermodynamics Spectra Unfolding Methods, device, electronic equipment and storage medium |
CN110379466B (en) * | 2019-07-12 | 2021-07-06 | 国家纳米科学中心 | Thermodynamic spectrum solving method and device, electronic equipment and storage medium |
CN110364229B (en) * | 2019-07-12 | 2021-08-03 | 国家纳米科学中心 | Thermodynamic solution spectrum error analysis method and device, electronic equipment and storage medium |
CN110364229A (en) * | 2019-07-12 | 2019-10-22 | 国家纳米科学中心 | Thermodynamics spectrum unscrambling error analysis method, device, electronic equipment and storage medium |
CN110442967A (en) * | 2019-08-05 | 2019-11-12 | 华能澜沧江水电股份有限公司 | Concrete thermal parameter inverse analysis method |
CN110619623A (en) * | 2019-08-08 | 2019-12-27 | 广东工业大学 | Automatic identification method for heating of joint of power transformation equipment |
CN110619623B (en) * | 2019-08-08 | 2023-01-20 | 广东工业大学 | Automatic identification method for heating of joint of power transformation equipment |
CN112561246A (en) * | 2020-11-27 | 2021-03-26 | 国网山东省电力公司建设公司 | Intelligent control method for mass concrete quality |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103914594A (en) | Concrete thermodynamic parameter intelligent recognition method based on support vector machine | |
Lu et al. | Probabilistic analyses of structural dynamic response with modified Kriging-based moving extremum framework | |
Li et al. | Prediction of gas solubility in polymers by back propagation artificial neural network based on self-adaptive particle swarm optimization algorithm and chaos theory | |
Diez et al. | Modelling of a flat-plate solar collector using artificial neural networks for different working fluid (water) flow rates | |
Zhang et al. | Computational fluid dynamics-based hull form optimization using approximation method | |
Izadyar et al. | Intelligent forecasting of residential heating demand for the District Heating System based on the monthly overall natural gas consumption | |
Mogilicharla et al. | Kriging surrogate based multi-objective optimization of bulk vinyl acetate polymerization with branching | |
CN101799888B (en) | Industrial soft measurement method based on bionic intelligent ant colony algorithm | |
CN104200087A (en) | Parameter optimization and feature tuning method and system for machine learning | |
Ji et al. | Urban water demand forecasting by LS-SVM with tuning based on elitist teaching-learning-based optimization | |
Pasquier et al. | Application of artificial neural networks to near-instant construction of short-term g-functions | |
CN105354363A (en) | Fluctuation wind speed prediction method based on extreme learning machine | |
CN109711617A (en) | A kind of medium-term and long-term Runoff Forecast method based on BLSTM deep learning | |
CN106199174A (en) | Extruder energy consumption predicting abnormality method based on transfer learning | |
Kicsiny | Multiple linear regression based model for solar collectors | |
Hamzaoui et al. | Optimization of operating conditions for steam turbine using an artificial neural network inverse | |
Wang et al. | Novel fuzzy reliability analysis for heat transfer system based on interval ranking method | |
Duan et al. | A Multimode Dynamic Short‐Term Traffic Flow Grey Prediction Model of High‐Dimension Tensors | |
Xiao et al. | A Kriging-assisted sampling method for reliability analysis of structures with hybrid uncertainties | |
Zheng et al. | Operational flexibility analysis of high-dimensional systems via cylindrical algebraic decomposition | |
Klimanek et al. | CFD two-scale model of a wet natural draft cooling tower | |
CN104966130A (en) | Data-driven spacecraft state prediction method | |
Wang et al. | Dynamic heat supply prediction using support vector regression optimized by particle swarm optimization algorithm | |
Li et al. | Jaya-ICSM: A rapid inverse method driven by monitoring data for concrete-faced rockfill dams static displacement simulation | |
Zhou et al. | Leakage diagnosis of heating pipe-network based on BP neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140709 |
|
WD01 | Invention patent application deemed withdrawn after publication |