CN110245370A - A kind of high CFRD multiple target mechanics parameter inversion method - Google Patents
A kind of high CFRD multiple target mechanics parameter inversion method Download PDFInfo
- Publication number
- CN110245370A CN110245370A CN201811543322.5A CN201811543322A CN110245370A CN 110245370 A CN110245370 A CN 110245370A CN 201811543322 A CN201811543322 A CN 201811543322A CN 110245370 A CN110245370 A CN 110245370A
- Authority
- CN
- China
- Prior art keywords
- panel
- parameter
- stress
- deflection
- sedimentation
- 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 20
- 238000012544 monitoring process Methods 0.000 claims abstract description 22
- 230000006870 function Effects 0.000 claims abstract description 21
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 230000002068 genetic effect Effects 0.000 claims abstract description 5
- 230000001537 neural effect Effects 0.000 claims abstract description 4
- 238000004062 sedimentation Methods 0.000 claims description 37
- 238000013461 design Methods 0.000 claims description 25
- 238000004458 analytical method Methods 0.000 claims description 20
- 239000000463 material Substances 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 11
- 230000035945 sensitivity Effects 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 5
- 238000005192 partition Methods 0.000 claims description 5
- 239000011435 rock Substances 0.000 claims description 5
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010206 sensitivity analysis Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims 6
- 230000000694 effects Effects 0.000 abstract description 2
- 238000013507 mapping Methods 0.000 abstract 1
- 238000005457 optimization Methods 0.000 description 5
- 230000007812 deficiency Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000004218 nerve net Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
Abstract
The invention discloses a kind of high CFRD multiple target mechanics parameter inversion methods, by making full use of high CFRD monitoring data (dam body settlement abundant, dam body horizontal distortion, panel stress and panel deflection) multiple objective functions are established respectively, analog mechanics parameter is respectively trained and surveys multiple RBF neurals of Nonlinear Mapping relationship between effect quantity, it obtains more comprehensively characterizing dam body settlement with above-mentioned objective function and neural network iteration optimizing using non-dominated ranking multi-objective genetic algorithm (NSGA-II), horizontal distortion, panel stress, the rockfill mechanics parameter of the characteristics such as panel deflection and high CFRD work condition.
Description
Technical field
The invention belongs to mechanics of materials technical fields, more specifically say it is a kind of high CFRD multiple target mechanics ginseng
Number inversion method.
Background technique
The rockfill mechanics parameter for accurately holding high CFRD is evaluation high CFRD panel seepage prevention system
The precondition of barrier performance, dam operation condition and Accurate Prediction rock space-time deformation rule, while being to guarantee height
One of the key of rock safety and stability.
The mechanics material parameter of current high rock-fill dams mainly passes through laboratory test or field test obtains, however due to tested
Test the factors such as condition, scale effect, construction quality, construction technology influence, test measurement mechanics parameter and actual value exist compared with
Big difference, rock-fill dams stress deformation, panel stress and the amount of deflection thus calculated inevitably differ larger with actual value.In conjunction with
The observational deformation data of dam carries out back analysis to rockfill mechanics parameter and has been widely used in engineering practice, and at
For one of the main method for obtaining dam body authentic material mechanics parameter.
But for high CFRD, in addition to sinking deformation monitoring data, also have other monitoring projects abundant and
Full and accurate monitoring result, for example, dam body along river to horizontal distortion, panel stress, panel deflection.However, anti-in traditional mechanics parameter
It drills in method, carries out back analysis just with material parameter of the sedimentation and deformation inside dam body to rockfill, inversion result is only
It is higher with settlement deformation condition relevance, the spies such as the horizontal distortion, panel stress, panel deflection of dam body cannot be characterized completely
Property, it can not reflect the work condition of high CFRD completely.
Summary of the invention
In order to solve the above deficiency, and in order to more comprehensively reflect each work condition of dam body and being associated with for material parameter
Property, while making full use of magnanimity monitoring data, the present invention provide it is a kind of using sedimentation inside dam body, along river to horizontal distortion, face
Plate stress and panel deflection monitoring data construct multiple objective function, and are iterated optimizing using multi-objective optimization algorithm, into
And the method for obtaining more reasonable inverted parameters value.
The technical scheme adopted by the invention is that: a kind of high CFRD mechanics parameter multiple target inversion method, it is special
Sign is, comprising the following steps:
Step 1: being established using each section design drawing of rock, material partition situation, dam body multi-stage construction program
Rock three-dimensional finite element model including panel, bed course, Transition Materials.
Step 2: analyze parameter sample with orthogonal design principle designing sensitiveness, and using finite element analysis software and
Above-mentioned model built carries out stress and deformation analysis to test parameters sample, and sedimentation, dam body inside are along river Xiang Shui inside analysis dam body
Flat deformation, panel stress, panel deflection determine that the stronger mechanics parameter of sensibility is used as and join to inverting to the sensibility of parameter
Number.
Step 3: design parameter training sample simultaneously carries out FEM calculation to every group of sample, is respectively trained using calculated result
To inverting mechanics parameter with sedimentation, to inverting mechanics parameter and horizontal distortion, to inverting mechanics parameter and panel stress, to inverting
4 trained neural networks are obtained in neural network between mechanics parameter and panel deflection.
Step 4: objective function is established respectively with sedimentation, horizontal distortion, panel stress, panel deflection measured data, totally 4
A objective function.
Step 5: collaboration optimizing being carried out to 4 objective functions using multi-objective optimization algorithm and using 4 nerve nets, is obtained
It can reflect dam body settlement, the inverted parameters value along river to characteristics such as horizontal distortion, panel stress, panel deflections comprehensively.
Preferably, high CFRD three-dimensional finite element model described in step 1 is that large-scale three dimensional finite element analysis is soft
Threedimensional model in part includes rockfill subregion, construction classification and bed course and panel assembly in threedimensional model;
Preferably, carrying out sensitivity to parameter point with orthogonal design principle design experiment parameter sample described in step 2
Analyse specific steps are as follows:
Step 2.1: with orthogonal design principle to mechanics Material Design sensitivity analysis sample, with Three-D limited
Meta analysis software carries out stress and deformation analysis to each sample parameter group, and extracts the sedimentation of rockfill, horizontal distortion, panel stress
And amount of deflection.
Step 2.2: reflect the sensibility of parameter with sensitivity index S:
In formula, S is sensitivity index, yiOutput valve is calculated for model i-th;y0For the corresponding model output of initial parameter
Value;xiFor model i-th calculating parameter;x0For initial parameter;N is calculation times.Y value is respectively
Sedimentation in step 2.1, horizontal distortion, panel stress and amount of deflection extraction as a result, selected according to sensitivity index S it is heavy
Drop, horizontal distortion, panel stress and amount of deflection sensitive parameter, comprehensive analysis selects to sedimentation, horizontal distortion, panel stress and scratches
More sensitive parameter is spent to be used as to inverted parameters.
Preferably, the neural network specific steps of training described in step 3 are as follows:
Step 3.1: the parameter training sample of neural network is generated with orthogonal design principle and random algorithm, utilization is limited
Meta analysis software carries out stress and deformation analysis to each group parameter training sample, extracts the sedimentation of rockfill, horizontal distortion, panel are answered
Power and panel panel deflection.
Step 3.2: using parameter sample group as input, respectively by corresponding sedimentation, horizontal distortion, panel stress and panel
Amount of deflection is respectively trained and examines the RBF neural of sedimentation, horizontal distortion, panel stress and panel deflection as output, obtain
Trained 4 neural networks about sedimentation, horizontal distortion, panel stress and panel deflection.
Preferably, 4 objective functions described in step 4 are respectively as follows:
Wherein, minE (1), minE (2), minE (3), minE (4) are respectively sedimentation, horizontal distortion, panel stress and face
The objective function of plate amount of deflection;M, n, j, k are the total number of monitoring point selected by each monitoring quantity;I represents the number of observation point;S1i
(x)、S2i(x)、S3i(x)、S4iIt (x) is respectively dam body settlement, horizontal distortion, monitoring point selected by panel stress and panel deflection
In i-th of observation point calculated value;S′1i、S′2i、S′3i、S′4iRespectively dam body settlement, horizontal distortion, panel stress and face
The measured value of i-th of observation point in monitoring point selected by plate amount of deflection.
Preferably, non-dominant multi-objective Genetic, which can be selected, in multi-objective optimization algorithm described in step 5 calculates (NSGA-II),
Optimizing is iterated using equal weight mode for 4 objective functions with the algorithm, obtain with Tested settlement, horizontal distortion,
Panel stress and the most matched rockfill mechanics parameter of panel deflection.
The monitoring data and multi-objective optimization algorithm that the present invention is directed to high CFRD magnanimity are in high CFRD
Application in parametric inversion, the innovative one kind that proposes comprehensively answer by reflection high CFRD sedimentation, horizontal distortion, panel
The mechanics parameter inversion method of power, panel deflection working characteristics.Effectively overcome consider in traditional parameters inversion method it is single because
The deficiency of element, the inverted parameters made have more reliability and reasonability, can more reflect that the work of high CFRD is special comprehensively
Property.
Detailed description of the invention
Fig. 1 is the flow chart that the present invention is implemented;
Fig. 2 is high CFRD settlement monitoring result signal enlarged drawing;
Fig. 3 is high CFRD horizontal distortion monitoring result signal enlarged drawing;
Fig. 4 is high CFRD panel deflection monitoring result signal Fang great Tu;
Fig. 5 is high CFRD slab reinforcement stress monitoring point arrangement schematic diagram.
Specific embodiment
Below with reference to the embodiments and with reference to the accompanying drawing the technical solutions of the present invention will be further described.Fig. 1 is
The flow chart that the present invention is implemented, embodiment specific implementation process are as follows:
Step 1: being established using each section design drawing of rock, material partition situation, dam body multi-stage construction program
Rock three-dimensional finite element model including panel, bed course, Transition Materials.Specific implementation step is as follows:
Step 1.1: three-dimensional finite element model, three-dimensional mould being established according to design drawing, material partition etc. with ANSYS software
It include rockfill subregion, construction classification and the components such as bed course and panel in type;
Step 1.2: using APDL order by ABAQUS modeling required input format export ANSYS in threedimensional model unit,
Node, contact surface, module information * .inp file, by these files importing ABAQUS can establish Three-D limited in ABAQUS
Meta-model.
Step 2: analyze parameter sample with orthogonal design principle designing sensitiveness, and using finite element analysis software and
Above-mentioned model built carries out stress and deformation analysis to test parameters sample, and sedimentation, dam body inside are along river Xiang Shui inside analysis dam body
Flat deformation, panel stress, panel deflection determine that the stronger mechanics parameter of sensibility is used as and join to inverting to the sensibility of parameter
Number.Specific implementation step are as follows:
Step 2.1: soft with ABAQUS with orthogonal design principle to mechanics Material Design sensitivity analysis sample
Part carries out stress and deformation analysis to each sample parameter group, and sedimentation, the horizontal distortion, panel of rockfill are extracted with Python script
Stress and amount of deflection.
Step 2.2: reflect the sensibility of parameter using sensitivity index S:
In formula, S is sensitivity index, yiOutput valve is calculated for model i-th;y0For the corresponding model output of initial parameter
Value;xiFor model i-th calculating parameter;x0For initial parameter;N is calculation times.Y value is respectively sedimentation in step 2.1, level
The extraction of deformation, panel stress and amount of deflection is as a result, select sedimentation, horizontal distortion, panel stress and amount of deflection according to sensitivity index S
Sensitive parameter, comprehensive analysis select to the more sensitive parameter of sedimentation, horizontal distortion, panel stress and amount of deflection be used as to inverting
Parameter.
Step 3: design parameter training sample simultaneously carries out finite element analysis, using calculated result be respectively trained mechanics parameter with
Neural network between sedimentation, mechanics parameter and horizontal distortion, mechanics parameter and panel stress, mechanics parameter and panel deflection,
Totally 4 trained neural networks.Specific implementation step is as follows:
Step 3.1: generating the parameter training sample of neural network with orthogonal design principle and random algorithm, utilize
ABAQUS software carries out stress and deformation analysis to each group parameter training sample, extracts the heavy of rockfill with Python scripting language
Drop, horizontal distortion, panel stress and panel panel deflection.
Step 3.2: using parameter sample group as input, respectively by corresponding sedimentation, horizontal distortion, panel stress and panel
Amount of deflection is respectively trained and examines the RBF neural of sedimentation, horizontal distortion, panel stress and panel deflection as output, obtain
Trained 4 neural networks about sedimentation, horizontal distortion, panel stress and panel deflection.
Step 4: objective function is established respectively with sedimentation, horizontal distortion, panel stress, panel deflection measured data, totally 4
A objective function.Dam body settlement, horizontal distortion, panel stress and deflection monitoring point and monitoring result schematic diagram such as Fig. 2~Fig. 5 institute
Show, 4 objective functions are respectively as follows:
Wherein, minE (1), minE (2), minE (3), minE (4) are respectively sedimentation, horizontal distortion, panel stress and face
The objective function of plate amount of deflection;M, n, j, k are the total number of selected monitoring point;I represents the number of observation point;S1i(x)、S2i
(x)、S3i(x)、S4iIt (x) is respectively dam body settlement, horizontal distortion, i-th in monitoring point selected by panel stress and panel deflection
The calculated value of a observation point;S′1i、S′2i、S′3i、S′4iRespectively dam body settlement, horizontal distortion, panel stress and panel deflection institute
Select the measured value of i-th of observation point in monitoring point.
Step 5: collaboration optimizing, optimizing being carried out to 4 objective functions using multi-objective optimization algorithm and using 4 nerve nets
For example (NSGA-II) specifically can be calculated using non-dominant multi-objective Genetic in the process and use equal weight mode for 4 objective functions
It is iterated optimizing, obtains and joins with the most matched enrockment mechanics of Tested settlement, horizontal distortion, panel stress and panel deflection
Number.
Specific embodiment described herein is only an example for the spirit of the invention.The neck of technology belonging to the present invention
The technical staff in domain can make various modifications or additions to the described embodiments or replace by a similar method
In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
It is other unspecified to belong to the prior art.
Claims (6)
1. a kind of high CFRD mechanics parameter multiple target inversion method, which comprises the following steps:
Step 1: including using each section design drawing of rock, material partition situation, the foundation of dam body multi-stage construction program
Rock three-dimensional finite element model including panel, bed course, Transition Materials;
Step 2: using orthogonal design principle design experiment parameter sample, and using finite element analysis software and above-mentioned modeled
Type carries out non-linear stress deformation analysis, analysis sedimentation, horizontal displacement, panel stress, panel deflection to test parameters sample
Sensibility mechanics parameter determines that the stronger mechanics parameter of sensibility is used as inverted parameters;
Step 3: design parameter training sample simultaneously carries out FEM calculation to sample, is respectively trained using calculated result to inverting power
Learn parameter and sedimentation, to inverting mechanics parameter and horizontal displacement, to inverting mechanics parameter and panel stress, to inverting mechanics parameter
Neural network between panel deflection, it is total to obtain four trained neural networks.
Step 4: objective function is established respectively with sedimentation, horizontal displacement, panel stress, panel deflection measured data, totally four
Objective function;
Step 5: (NSGA-II) is calculated and using four trained neural networks to four targets using non-dominant multi-objective Genetic
Function carries out collaboration optimizing, obtains to reflect dam body settlement, horizontal displacement, the inverting of panel stress, panel deflection characteristic comprehensively
Parameter value.
2. high CFRD mechanics parameter multiple target inversion method according to claim 1, which is characterized in that step 1
Described in high CFRD three-dimensional finite element model be applied with finite element software according to design drawing, material partition, dam body
Engineering sequence establishes three-dimensional finite element model, includes rockfill subregion, construction classification and bed course and panel assembly in threedimensional model.
3. high CFRD mechanics parameter multiple target inversion method according to claim 1, which is characterized in that step 2
Described in orthogonal design principle design experiment parameter sample carry out parameters sensitivity analysis specific steps are as follows:
Step 2.1: with orthogonal design principle to mechanics Material Design test sample, with finite element software to each sample
Parameter group carries out stress and deformation analysis, and extracts sedimentation, horizontal distortion, panel stress and the amount of deflection of rockfill;
Step 2.2: reflect the sensibility of parameter with sensitivity index S:
In formula, S is sensitivity index, yiOutput valve is calculated for model i-th;y0For the corresponding model output value of initial parameter;xi
For model i-th calculating parameter;x0For initial parameter;N is calculation times;Y value be respectively sedimentation in step 2.1, horizontal distortion,
The extraction of panel stress and amount of deflection is as a result, select the quick of sedimentation, horizontal distortion, panel stress and amount of deflection according to sensitivity index S
Feel parameter, comprehensive analysis is selected to be used as the more sensitive parameter of sedimentation, horizontal displacement, panel stress and amount of deflection joins to inverting
Number.
4. high CFRD mechanics parameter multiple target inversion method according to claim 1, which is characterized in that step 3
Described in training neural network specific steps are as follows:
Step 3.1: generating the parameter training sample of neural network with orthogonal design principle and random algorithm, utilize finite element fraction
Analyse software and stress and deformation analysis carried out to each group parameter training sample, extract the sedimentation of rockfill, horizontal distortion, panel stress and
Panel panel deflection.
Step 3.2: using parameter sample group as input, respectively by corresponding sedimentation, horizontal distortion, panel stress and panel deflection
As output, be respectively trained and examine the RBF neural of sedimentation, horizontal distortion, panel stress and panel deflection, obtain about
Sedimentation, horizontal distortion, panel stress and panel deflection trained four neural networks.
5. high CFRD mechanics parameter multiple target inversion method according to claim 1, which is characterized in that step 4
Described in four objective functions be respectively as follows:
Wherein, minE (1), minE (2), minE (3), minE (4) are respectively that sedimentation, horizontal displacement, panel stress and panel are scratched
The objective function of degree;M, n, j, k are the total number of selected monitoring point;I represents the number of observation point;S1i(x)、S2i(x)、S3i
(x)、S4iIt (x) is respectively dam body settlement, horizontal distortion, i-th of observation in monitoring point selected by panel stress and panel deflection
The calculated value of point;S1′i、S2′i、S3′i、S4′iThe respectively selected prison of dam body settlement, horizontal distortion, panel stress and panel deflection
The measured value of i-th of observation point in measuring point.
6. high CFRD mechanics parameter multiple target inversion method according to claim 1, which is characterized in that step 5
Described in non-dominant multi-objective Genetic calculate (NSGA-II) optimizing and be iterated for four objective functions using equal weight mode and seek
It is excellent, it obtains and the most matched rockfill mechanics parameter of Tested settlement, horizontal distortion, panel stress and panel deflection.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811543322.5A CN110245370A (en) | 2018-12-17 | 2018-12-17 | A kind of high CFRD multiple target mechanics parameter inversion method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811543322.5A CN110245370A (en) | 2018-12-17 | 2018-12-17 | A kind of high CFRD multiple target mechanics parameter inversion method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110245370A true CN110245370A (en) | 2019-09-17 |
Family
ID=67882426
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811543322.5A Pending CN110245370A (en) | 2018-12-17 | 2018-12-17 | A kind of high CFRD multiple target mechanics parameter inversion method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110245370A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111259594A (en) * | 2020-02-10 | 2020-06-09 | 中国机械设备工程股份有限公司 | Long-term post-construction settlement prediction method based on settlement monitoring result of filling engineering |
CN112347670A (en) * | 2020-10-26 | 2021-02-09 | 青海大学 | Rockfill material creep parameter prediction method based on neural network response surface |
CN113204870A (en) * | 2021-04-28 | 2021-08-03 | 中国电建集团贵阳勘测设计研究院有限公司 | On-site original-grade rockfill mechanical parameter conjecture method |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105787174A (en) * | 2016-02-25 | 2016-07-20 | 武汉大学 | High-rockfill-dam transient-rheological-parameter inversion method based on response surface method |
-
2018
- 2018-12-17 CN CN201811543322.5A patent/CN110245370A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105787174A (en) * | 2016-02-25 | 2016-07-20 | 武汉大学 | High-rockfill-dam transient-rheological-parameter inversion method based on response surface method |
Non-Patent Citations (2)
Title |
---|
李少林等: "高心墙堆石坝瞬变-流变参数解耦反分析方法及变形预测", 《长江科学院院报》 * |
温少雄等: "基于NSGA-Ⅱ算法的堆石坝多目标参数反演方法", 《水力发电学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111259594A (en) * | 2020-02-10 | 2020-06-09 | 中国机械设备工程股份有限公司 | Long-term post-construction settlement prediction method based on settlement monitoring result of filling engineering |
CN112347670A (en) * | 2020-10-26 | 2021-02-09 | 青海大学 | Rockfill material creep parameter prediction method based on neural network response surface |
CN113204870A (en) * | 2021-04-28 | 2021-08-03 | 中国电建集团贵阳勘测设计研究院有限公司 | On-site original-grade rockfill mechanical parameter conjecture method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | State-of-the-art review of machine learning applications in constitutive modeling of soils | |
Jin et al. | Bayesian model selection for sand with generalization ability evaluation | |
Yu et al. | An intelligent displacement back-analysis method for earth-rockfill dams | |
Kang et al. | Dynamic parameter inverse analysis of concrete dams based on Jaya algorithm with Gaussian processes surrogate model | |
Yang et al. | Improved PLS and PSO methods-based back analysis for elastic modulus of dam | |
CN107301282B (en) | Concrete dam mechanical parameter inversion method based on multi-source monitoring time sequence data | |
CN102425148B (en) | Rapid sub-grade settlement predicting method based on static sounding and BP (Back Propagation) neural network | |
CN110245370A (en) | A kind of high CFRD multiple target mechanics parameter inversion method | |
CN104200005A (en) | Bridge damage identification method based on neural network | |
Wang et al. | Correction of soil parameters in calculation of embankment settlement using a BP network back-analysis model | |
Faramarzi et al. | EPR-based material modelling of soils considering volume changes | |
Zhang et al. | A novel seepage behavior prediction and lag process identification method for concrete dams using HGWO-XGBoost model | |
CN115654381A (en) | Water supply pipeline leakage detection method based on graph neural network | |
CN111950140A (en) | Dam seepage behavior analysis method considering multiple uncertainties | |
YiFei et al. | Metamodel-assisted hybrid optimization strategy for model updating using vibration response data | |
Li et al. | An advanced Bayesian parameter estimation methodology for concrete dams combining an improved extraction technique of hydrostatic component and hybrid response surface method | |
Liu et al. | Dynamic material parameter inversion of high arch dam under discharge excitation based on the modal parameters and Bayesian optimised deep learning | |
CN112347670B (en) | Rockfill material creep parameter prediction method based on neural network response surface | |
CN117113854A (en) | Salt tide forecasting method based on ConvLSTM and three-dimensional numerical simulation | |
CN111582634A (en) | Multi-factor safety grading method and system for underground large-space construction | |
Elshamy et al. | Using application of an artificial neural network system to backcalculate pavement elastic modulus | |
Zhang et al. | An application of soft computing for the earth stress analysis in hydropower engineering | |
CN113221228B (en) | Hydropower station underground cave group surrounding rock mechanical parameter inversion method | |
CN115577856A (en) | Method and system for predicting construction cost and controlling balance of power transformation project | |
Li et al. | Identifying geomechanical parameters of high cut rock slopes by an improved multi-output support vector machine method |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190917 |