CN107784191B - Anisotropic rock joint peak shear strength prediction technique based on neural network model - Google Patents
Anisotropic rock joint peak shear strength prediction technique based on neural network model Download PDFInfo
- Publication number
- CN107784191B CN107784191B CN201711322548.8A CN201711322548A CN107784191B CN 107784191 B CN107784191 B CN 107784191B CN 201711322548 A CN201711322548 A CN 201711322548A CN 107784191 B CN107784191 B CN 107784191B
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- shear strength
- rock joint
- anisotropic
- 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.)
- Active
Links
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
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Earth Drilling (AREA)
Abstract
The present invention provides a kind of anisotropic rock joint peak shear strength prediction technique based on neural network model, comprising the following steps: S1: acquiring the historical data of actual tests, is standardized after filtering out training data and verify data；S2: establishing BP neural network model, selects input and output parameter；S3: the optimal neural unit quantity of hidden layer is determined；S4: the training data training BP neural network model is used；S5: the BP neural network model is verified using the verify data；S6: to the BP neural network mode input parameter after verifying, anisotropic rock joint peak shear strength ratio predicted value is obtained, thus the anisotropic rock joint peak shear strength predicted.Beneficial effects of the present invention: the method for more accurate prediction anisotropic rock joint peak shear strength is provided, is of great significance for the estimation of stability of the rock slope containing anisotropic rock joint.
Description
Technical field
The present invention relates to the invention belongs to Geotechnical Engineering method fields, more particularly to one kind to be based on neural network model
Anisotropic rock joint peak shear strength prediction technique.
Background technique
Rock mass is the geologic body with certain component and structure formed in earth history period.It was subject to complexity
Geologic process is dispersed with various structural planes, such as tomography, joint, crack in rock mass.The intensity of rock mass, destroys spy at deformation properties
Sign etc. is closely related with the mechanical property and failure mechanism of rock mass discontinuity.The unstability of many engineering rock mass in history is mostly
Caused by rock mass is along weak structural face generation sliding failure, high landslide of big Levi of complying with one's wishes etc..So carrying out structural plane
The peak shear strength for studying, determining structural plane is of great significance.However, current research is mainly for two sidewalls lithology matter
Identical ordinary construction face, it is less to anisotropic rock joint concern, and the case where Practical Project rock mass lithology alternating variation, generally deposits
, anisotropic approach EDS maps are very extensive, mechanical property to engineering rock mass stability have great influence.Due to neural network
Method has nonlinear model identification, self establishes and the outstanding ability of self-teaching, is considering that structure faces the wall and meditates rock intensity, structure
The peak shear strength of anisotropic rock joint is predicted on the basis of surface roughness and normal stress with the method for neural network model,
The results show that the method precision based on Neural Network model predictive anisotropic rock joint peak shear strength is higher, error is smaller, energy
It is enough in the estimation of stability of the rock slope containing anisotropic rock joint.
Summary of the invention
In view of this, the embodiment provides a kind of anisotropic rock joint peak value shearing resistance based on neural network model
Intensity prediction method.
The embodiment of the present invention provides a kind of anisotropic rock joint peak shear strength prediction side based on neural network model
Method, comprising the following steps:
S1: acquiring the historical data of actual tests, is standardized after filtering out training data and verify data；
S2: establish include input layer, hidden layer and output layer BP neural network model, select anisotropic approach rock of facing the wall and meditating strong
Ratio, structural plane roughness coefficient and normal stress are spent as input parameter, and peak shear strength ratio is selected to join as output
Number；
S3: the optimal neural unit quantity of hidden layer is determined according to input number of parameters and output parameter quantity；
S4: the training data training BP neural network model is used；
S5: the BP neural network model is verified using the verify data；
S6: to the BP neural network mode input parameter after verifying, output parameter peak shear strength ratio is obtained
Predicted value, thus the peak shear strength for the anisotropic rock joint predicted.
Further, it is determined that the formula of optimal neural unit quantity is as follows:
Wherein, n indicates hidden layer neural unit quantity, n0Indicate the quantity of output parameter, niIndicate the number of input parameter
Amount, α is a constant from 1 to 10, and the size by changing α determines n value, then obtains same group of number in the training data
According to corresponding different anisotropic rock joint shearing strengths, the anisotropic rock joint shearing strength and actual history being respectively compared are different
Property structural face shear strength, determine that mean square error is minimum and the corresponding n value of the maximum anisotropic rock joint shearing strength of related coefficient
For the optimal neural unit quantity of hidden layer.
Further, the historical data is obtained by indoor direct shear test or is obtained by live in-situ test.
Further, to the standardization of the training data and the verify data be scaled down to 0 to 1 it
Between, it is as follows to reduce formula:
Wherein, xiIt is variable, xmax、xminFor maximum value and minimum value, xi,normFor standardized value.
Further, the BP neural network model training mode is by adjusting weight and critical value to establish input ginseng
Non-linear relation between number and output result.
Further, the objective function of the training BP neural network model are as follows:
Wherein CtIndicate the t times test BP neural network model output parameters, ytIndicate corresponding anticipated output ginseng
Number, T indicate the array quantity in the training data, and MSE indicates mean square error.
Further, evaluation trains the parameter of the BP neural network model qualification for root-mean-square error and related coefficient,
Root-mean-square error judges that the BP neural network model is qualified less than 0.1 and when related coefficient is greater than 0.85.
Further, when the root-mean-square error is minimum and the related coefficient maximum, judge the BP neural network mould
Type is qualified.
The embodiment of the present invention also provides a kind of anisotropic rock joint peak shear strength prediction based on neural network model
System, comprising:
Preprocessing module carries out after filtering out training data and verify data for acquiring the historical data of actual tests
Standardization；
Modeling module: establishing the BP neural network model comprising input layer, hidden layer and output layer, selects anisotropic rock joint
Wall rock volume efficiency, structural plane roughness coefficient and normal stress as input parameter, select peak shear strength ratio as
Output parameter determines the optimal neural unit quantity of hidden layer, determines that formula is as follows:
Wherein, n indicates hidden layer neural unit quantity, n0Indicate the quantity of output parameter, niIndicate the number of input parameter
Amount, α is a constant from 1 to 10, and the size by changing α determines n value, then obtains same group of number in the training data
According to corresponding different anisotropic rock joint shearing strengths, the anisotropic rock joint shearing strength and actual history being respectively compared are different
Property structural face shear strength, determines that mean square error is small and the corresponding n value of the maximum anisotropic rock joint shearing strength of related coefficient is
Optimal hidden layer neural unit quantity；
Training module: for using the training data training BP neural network model；
Authentication module: for verifying the BP neural network model using the verify data；
Output module: to the BP neural network mode input parameter after verifying, it is strong to obtain output parameter peak value shearing resistance
Spend ratio predicted value.
The technical solution that the embodiment of the present invention provides has the benefit that the present invention is based on neural network models
The peak shear strength that anisotropic rock joint peak shear strength prediction technique solves anisotropic rock joint in existing method cannot be calibrated
The problem of really obtaining provides the method for more accurate prediction anisotropic rock joint peak shear strength, can predict the opposite sex well
The peak shear strength of structural plane is of great significance for the estimation of stability of the rock slope containing anisotropic rock joint.
Detailed description of the invention
Fig. 1 is the flow chart of the anisotropic rock joint peak shear strength prediction technique the present invention is based on neural network model；
Fig. 2 is BP neural network model schematic.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is further described.
Fig. 1 and Fig. 2 are please referred to, the embodiment provides a kind of anisotropic rock joint peak based on neural network model
It is worth shearing strength prediction technique, comprising the following steps:
S1: acquiring the historical data of actual tests, is standardized after filtering out training data and verify data；
S2: establish include input layer, hidden layer and output layer BP neural network model, select anisotropic approach rock of facing the wall and meditating strong
Ratio, structural plane roughness coefficient and normal stress are spent as input parameter, and peak shear strength ratio is selected to join as output
Number；
S3: the optimal neural unit quantity of hidden layer is determined according to input number of parameters and output parameter quantity；
S4: the training data training BP neural network model is used；
S5: the BP neural network model is verified using the verify data；
S6: to the BP neural network mode input parameter after verifying, output parameter peak shear strength ratio is obtained
Predicted value, thus the peak shear strength for the anisotropic rock joint predicted.
The historical data is obtained by indoor direct shear test or is obtained by live in-situ test, peak shear strength ratio
Rate τi/τsIt faces the wall and meditates rock volume efficiency σ with three relating to parameters: anisotropic approachch/σcs, structural plane roughness coefficient JRC and normal direction answer
Power σn, wherein σ ch indicates that the uniaxial compressive strength in anisotropic rock joint compared with sclerine rock, σ cs indicate in anisotropic rock joint compared with flexible wall
The uniaxial compressive strength of rock, τ i indicate anisotropic rock joint shearing strength, and τ s indicates soft rock same sex structural face shear strength.
The anisotropic approach faces the wall and meditates rock volume efficiency as compared with sclerine rock and compared with the ratio between flexible wall rock uniaxial compressive strength, the peak
Being worth shearing strength ratio is the ratio between anisotropic rock joint and soft rock same sex structural face shear strength.
Since initial data is due to order of magnitude difference, the standardization to the training data and the verify data is
It is scaled down between 0 to 1, it is as follows to reduce formula:
Wherein, xiIt is variable, xmax、xminFor maximum value and minimum value, xi,normFor standardized value.
It determines optimal neural unit quantity, determines that formula is as follows:
Wherein, n indicates hidden layer neural unit quantity, n0Indicate the quantity of output parameter, niIndicate the number of input parameter
Amount, α is a constant from 1 to 10, and the size by changing α determines n value, then obtains same group of number in the training data
According to corresponding different anisotropic rock joint shearing strengths, the anisotropic rock joint shearing strength and actual history being respectively compared are different
Property structural face shear strength, determine that mean square error is minimum and the corresponding n value of the maximum anisotropic rock joint shearing strength of related coefficient
For the optimal neural unit quantity of hidden layer.
The specific training method of BP neural network model is as follows:
Assuming that hidden layer jth group neuron outputs and inputs respectively sj、bj, expression formula are as follows:
bj=f1(sj) j=1,2,3 ..., N (3-2)
ω in formula (3-1)ij、θiInput layer is respectively indicated to the weight and critical value between hidden layer, formula (3-3) is hidden
Containing the transmission function applied in layer.
In output layer, outputting and inputting for t group neuron is expressed as Lt、Ct, expression formula is
Ct=f2(Lt) t=1 (3-5)
f2(x)=x (3-6)
ν in formula (3-4)jt、γtHidden layer is respectively indicated to the weight and critical value between output layer, formula (3-3) provides
The linear equation applied in hidden layer.
The training of the BP neural network model be by adjusting weight and critical value with establish output and input between it is multiple
Miscellaneous non-linear relation.Formula (3-7) gives the objective function of the optimization training BP neural network model
Y in formula (3-7)tIndicate expected output valve, T indicates the array quantity in database for training.In order to obtain
The optimum training of the BP neural network model can use gradient decline learning method and make by adjusting weight and critical value
Target function value minimizes.νjt、γtAdjustment equation it is as follows
νjt(m+1)=vjt(m)+α(yt-Ct)Ct(1-Ct)bj (3-8)
γt(m+1)=γt(m)+α(yt-Ct)Ct(1-Ct) (3-9)
In formula (3-8), (3-9) m indicate the m time adjustment, α expression hidden layer between output layer pace of learning (0 < α <
1)；ωij、θiAdjustment equation it is as follows
β indicates input layer to the pace of learning (0 < β < 1) between hidden layer in formula (3-10), (3-11).
The parameter of the evaluation training BP neural network model qualification is root-mean-square error and related coefficient, root-mean-square error
Less than 0.1 and when related coefficient is greater than 0.85, judge that the BP neural network model is qualified, preferably, the root mean square misses
When the poor minimum and described related coefficient maximum, judge that the BP neural network model is qualified.
The embodiment of the present invention also provides a kind of anisotropic rock joint peak shear strength prediction based on neural network model
System, comprising:
Preprocessing module carries out after filtering out training data and verify data for acquiring the historical data of actual tests
Standardization；
Modeling module: establishing the BP neural network model comprising input layer, hidden layer and output layer, selects anisotropic rock joint
Wall rock volume efficiency, structural plane roughness coefficient and normal stress as input parameter, select peak shear strength ratio as
Output parameter determines the optimal neural unit quantity of hidden layer, determines that formula is as follows:
Wherein, n indicates hidden layer neural unit quantity, n0Indicate the quantity of output parameter, niIndicate the number of input parameter
Amount, α is a constant from 1 to 10, and the size by changing α determines n value, then obtains same group of number in the training data
According to corresponding different anisotropic rock joint shearing strengths, the anisotropic rock joint shearing strength and actual history being respectively compared are different
Property structural face shear strength, determines that mean square error is small and the corresponding n value of the maximum anisotropic rock joint shearing strength of related coefficient is
Optimal hidden layer neural unit quantity；
Training module: for using the training data training BP neural network model；
Authentication module: for verifying the BP neural network model using the verify data；
Output module: to the BP neural network mode input parameter after verifying, it is strong to obtain output parameter peak value shearing resistance
Spend ratio predicted value.
In the absence of conflict, the feature in embodiment and embodiment herein-above set forth can be combined with each other.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (8)
1. a kind of anisotropic rock joint peak shear strength prediction technique based on neural network model, which is characterized in that including with
Lower step:
S1: acquiring the historical data of actual tests, is standardized after filtering out training data and verify data；
S2: establish include input layer, hidden layer and output layer BP neural network model, select anisotropic approach to face the wall and meditate rock intensity ratio
Rate, structural plane roughness coefficient and normal stress select peak shear strength ratio as output parameter as input parameter；
S3: the optimal neural unit quantity of hidden layer is determined according to input number of parameters and output parameter quantity, determines optimal nerve
The formula of element number is as follows:
Wherein, n indicates hidden layer neural unit quantity, n0Indicate the quantity of output parameter, niIndicate the quantity of input parameter, α is
One constant from 1 to 10, the size by changing α determine n value, then show that same group of data is corresponding in the training data
Different anisotropic rock joint shearing strengths, the anisotropic rock joint shearing strength being respectively compared and actual history anisotropic approach
Face shearing strength determines that mean square error is minimum and the corresponding n value of the maximum anisotropic rock joint shearing strength of related coefficient is implicit
The optimal neural unit quantity of layer；
S4: the training data training BP neural network model is used；
S5: the BP neural network model is verified using the verify data；
S6: to the BP neural network mode input parameter after verifying, obtaining peak shear strength ratio predicted value, thus
To the peak shear strength of the anisotropic rock joint of prediction.
2. the anisotropic rock joint peak shear strength prediction technique based on neural network model as described in claim 1, special
Sign is: the historical data is obtained by indoor direct shear test or is obtained by live in-situ test.
3. the anisotropic rock joint peak shear strength prediction technique based on neural network model as described in claim 1, special
Sign is: the standardization to the training data and the verify data is to be scaled down between 0 to 1, is reduced public
Formula is as follows:
Wherein, xiIt is variable, xmax、xminFor maximum value and minimum value, xi,normFor standardized value.
4. the anisotropic rock joint peak shear strength prediction technique based on neural network model as described in claim 1, special
Sign is: the BP neural network model training mode is by adjusting weight and critical value to establish input parameter and output knot
Non-linear relation between fruit.
5. the anisotropic rock joint peak shear strength prediction technique based on neural network model as claimed in claim 4, special
Sign is, trains the objective function of the BP neural network model are as follows:
Wherein CtIndicate the t times test BP neural network model output parameters, ytIndicate corresponding anticipated output parameter, T table
Show the array quantity in the training data, MSE indicates mean square error.
6. the anisotropic rock joint peak shear strength prediction technique based on neural network model as claimed in claim 5, special
Sign is: the parameter of the evaluation training BP neural network model qualification is root-mean-square error and related coefficient, root-mean-square error
Less than 0.1 and when related coefficient is greater than 0.85, judge that the BP neural network model is qualified.
7. the anisotropic rock joint peak shear strength prediction technique based on neural network model as claimed in claim 6, special
Sign is: when the root-mean-square error minimum and the related coefficient maximum, judging that the BP neural network model is qualified.
8. the anisotropic rock joint peak shear strength forecasting system based on neural network model characterized by comprising
Preprocessing module filters out training data and the laggard rower of verify data is quasi- for acquiring the historical data of actual tests
Change processing；
Modeling module: establish include input layer, hidden layer and output layer BP neural network model, select anisotropic approach to face the wall and meditate rock
Volume efficiency, structural plane roughness coefficient and normal stress select peak shear strength ratio as output as input parameter
Parameter determines the optimal neural unit quantity of hidden layer, determines that formula is as follows:
Wherein, n indicates hidden layer neural unit quantity, n0Indicate the quantity of output parameter, niIndicate the quantity of input parameter, α is
One constant from 1 to 10, the size by changing α determine n value, then show that same group of data is corresponding in the training data
Different anisotropic rock joint shearing strengths, the anisotropic rock joint shearing strength being respectively compared and actual history anisotropic approach
Face shearing strength determines that mean square error is small and the corresponding n value of the maximum anisotropic rock joint shearing strength of related coefficient is optimal hidden
The quantity of neural unit containing layer；
Training module: for using the training data training BP neural network model；
Authentication module: for verifying the BP neural network model using the verify data；
Output module: to the BP neural network mode input parameter after verifying, peak shear strength ratio predicted value is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711322548.8A CN107784191B (en) | 2017-12-12 | 2017-12-12 | Anisotropic rock joint peak shear strength prediction technique based on neural network model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711322548.8A CN107784191B (en) | 2017-12-12 | 2017-12-12 | Anisotropic rock joint peak shear strength prediction technique based on neural network model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107784191A CN107784191A (en) | 2018-03-09 |
| CN107784191B true CN107784191B (en) | 2019-02-12 |
Family
ID=61437168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711322548.8A Active CN107784191B (en) | 2017-12-12 | 2017-12-12 | Anisotropic rock joint peak shear strength prediction technique based on neural network model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107784191B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108595784A (en) * | 2018-03-30 | 2018-09-28 | 南京航空航天大学 | Based on MBN signals full width at half maximum than the yield strength method of estimation with envelope size |
| CN108764568B (en) * | 2018-05-28 | 2020-10-23 | 哈尔滨工业大学 | Data prediction model tuning method and device based on LSTM network |
| CN110147835A (en) * | 2019-05-10 | 2019-08-20 | 东南大学 | Resisting shear strength of reinforced concrete beam-column joints prediction technique based on grad enhancement regression algorithm |
| CN110261578B (en) * | 2019-06-27 | 2020-07-31 | 东北大学 | Fractured rock mass stability analysis system considering structural surface roughness |
| CN110457746B (en) * | 2019-07-01 | 2022-12-13 | 绍兴文理学院 | BP neural network-based structural plane peak shear strength prediction model construction method |
| CN110377980B (en) * | 2019-07-01 | 2023-05-12 | 绍兴文理学院 | BP neural network-based rock joint surface peak shear strength prediction method |
| CN110763809B (en) * | 2019-11-15 | 2022-03-29 | 中国石油大学(华东) | Experimental verification method for optimal arrangement scheme of gas detector |
| CN111382802A (en) * | 2020-03-17 | 2020-07-07 | 桂林理工大学 | Dangerous rock stability discrimination method and device based on main control structural surface parameter identification |
| CN112668244B (en) * | 2021-01-06 | 2022-04-22 | 西南交通大学 | Slope earthquake stability prediction method, device and equipment and readable storage medium |
| CN112749514A (en) * | 2021-01-27 | 2021-05-04 | 西安石油大学 | Intelligent prediction method for casing pipe anti-extrusion strength based on data driving |
| CN113204830B (en) * | 2021-07-06 | 2021-08-27 | 中国铁路设计集团有限公司 | Correction method for determining cohesive soil foundation bearing capacity through shear wave velocity based on BP network |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220467A (en) * | 2017-07-07 | 2017-09-29 | 中国水利水电科学研究院 | The Forecasting Methodology of retaining phase storehouse bank rock side slope deformation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9747393B2 (en) * | 2011-02-09 | 2017-08-29 | Exxonmobil Upstream Research Company | Methods and systems for upscaling mechanical properties of geomaterials |
-
2017
- 2017-12-12 CN CN201711322548.8A patent/CN107784191B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220467A (en) * | 2017-07-07 | 2017-09-29 | 中国水利水电科学研究院 | The Forecasting Methodology of retaining phase storehouse bank rock side slope deformation |
Non-Patent Citations (3)
| Title |
|---|
| Application of back-propagation neural network on bank destruction forecasting for accumulative landslides in the three Gorges Reservoir Region, China;Changdong Li 等;《Stochastic Environmental Research and Risk Assessment》;20140122;第1465-1477页 |
| Modelling the Shear Behaviour of Clean Rock Discontinuities Using Artificial Neural Networks;Silvrano Adonias Dantas Neto 等;《Rock Mechanics and Rock Engineering》;20170310;第1817–1831页 |
| 基于颗粒流异性层面剪切特性及演化机理研究;方堃;《长江科学院院报》;20141130;第31卷(第11期);第31-37页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107784191A (en) | 2018-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784191B (en) | Anisotropic rock joint peak shear strength prediction technique based on neural network model | |
| WO2020048028A1 (en) | Fracturing potential-based fracturing design method and apparatus for horizontal well to be fractured | |
| Edeling et al. | Predictive RANS simulations via Bayesian model-scenario averaging | |
| Bauer et al. | Sources of uncertainty in shear stress and roughness length estimates derived from velocity profiles | |
| Richards et al. | Effects of lateral viscosity variations on long‐wavelength geoid anomalies and topography | |
| Owolabi et al. | Probabilistic framework for a microstructure-sensitive fatigue notch factor | |
| Khedmati et al. | Empirical formulations for estimation of ultimate strength of continuous aluminium stiffened plates under combined transverse compression and lateral pressure | |
| CN113722920B (en) | Rapid calculation method for reliability of side slope earthquake based on FLAC3D-Python secondary development | |
| Wang et al. | Two-dimensional mixed mode crack simulation using the material point method | |
| Vaziriastaneh | On the Forward and Inverse Computational Wave Propagation Problems. | |
| Teimouri et al. | A simple estimator for the Weibull shape parameter | |
| Vitkin et al. | Study of in situ calibration performance of co-located multi-sensor hot-film and sonic anemometers using a ‘virtual probe’algorithm | |
| Agius et al. | Optimising the multiplicative AF model parameters for AA7075 cyclic plasticity and fatigue simulation | |
| Mauprivez et al. | Artificial neural networks applied to the estimation of random variables associated to a two-mass model for the vocal folds | |
| Khare et al. | On the modelling of over‐ocean hurricane surface winds and their uncertainty | |
| Abu-Zinadah et al. | On estimations of parameters of generalized gompertz distribution | |
| CN110543613A (en) | Method for calculating and displaying beam-Criman information flow through multi-scale sliding window | |
| Yu et al. | Three-dimensional enhanced super-resolution generative adversarial network for super-resolution reconstruction of turbulent flows with tricubic interpolation-based transfer learning | |
| Zhang | Field Dislocation Mechanics with applications in atomic, mesoscopic and tectonic scale problems | |
| CN103810689A (en) | Novel image fusion effect evaluation algorithm | |
| Klungerbo | Stress Concentrations and Stress Gradients at Elliptical Through-Holes and Spheroidal Cavities | |
| Wahab | A data-assisted physics informed neural network (Da-Pinn) for fretting fatigue lifetime prediction | |
| Li et al. | Effect of time scale on PRP random flows in pipe network | |
| Feder | Machine-Learning-Based Early-Warning System Maintains Stable Production | |
| Karaouni et al. | Optimal fatigue analysis of structures during complex loadings |
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 |