CN110765679A - Dam monitoring web display method based on finite element model and SVM regression algorithm - Google Patents
Dam monitoring web display method based on finite element model and SVM regression algorithm Download PDFInfo
- Publication number
- CN110765679A CN110765679A CN201910940775.XA CN201910940775A CN110765679A CN 110765679 A CN110765679 A CN 110765679A CN 201910940775 A CN201910940775 A CN 201910940775A CN 110765679 A CN110765679 A CN 110765679A
- Authority
- CN
- China
- Prior art keywords
- dam
- svm
- finite element
- element model
- section
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a dam monitoring web display method based on a finite element model and an SVM regression algorithm, which comprises the steps of selecting a typical section of a target dam, introducing the selected typical section of the dam into Hypermesh for grid division, and performing classified storage on node unit information in each grid; searching the profile outer contour through the corresponding information between the nodes and the units: forming a complete closed graph by using the edges of each grid which are used only once, wherein the closed graph can be used as the outer contour of the dam section; acquiring target measuring points and target date data from a monitoring platform database in real time; performing quadratic processing on the independent variable to expand the independent variable information; constructing an SVM regressor, selecting a relaxation variable, and adjusting SVM parameters according to a training set; carrying out coordinate preprocessing and target value calculation on finite element nodes, and diffusing the measuring point information to the full section; and (4) drawing a measured value cloud picture of the dam body section by interpolation, and displaying the drawn contour line in real time. The monitoring result of the invention has good timeliness.
Description
Technical Field
The invention relates to the technical field of dam detection, in particular to a dam monitoring web display method based on a finite element model and an SVM regression algorithm.
Background
As the water conservancy project plays an increasingly important role in the Chinese energy structure, the dam safety problem is increasingly prominent, so the dam safety monitoring field comes across. The specific mode is that a specific monitoring instrument is arranged in the dam body or on the outer surface of the dam body during and after the dam body is constructed, and the specific monitoring instrument is respectively responsible for different monitoring objects, such as horizontal displacement along the river direction, horizontal displacement along the river direction on the surface of the dam body or settlement of the measuring point position of the dam body in the vertical direction and the like.
The existing monitoring data analysis means mainly takes an off-line mode, namely takes a half year or a year as a period, and uniformly analyzes the characteristic value of data collected by a monitoring instrument, predicts the future development trend and judges the safety state of a building. However, this method has a certain degree of backward extension, and the dam body state cannot be analyzed in real time. The analysis algorithm is mainly a multiple linear regression method, has a simple principle, is easy to apply, has certain physical significance, and can be used for analyzing the amplitude of a measured value. However, under the comprehensive influence of increasingly complex environmental factors and dam body property changes, the multiple regression algorithm gradually loses the feasibility thereof. There is therefore a strong need for better performing algorithms to address these problems.
The traditional monitoring analysis is usually separated from a building body, data analysis is carried out only, the connection with engineering is not tight enough, and data of a single monitoring point is modeled and calculated. The cost is high, the safety of the structure needs to be ensured, and the position arrangement of the measuring points arranged inside and on the surface of the dam body is very sparse, so that the single-measuring-point model cannot meet the evaluation of the whole safety state of the dam.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a dam monitoring web display method based on a finite element model and an SVM regression algorithm, and solves the technical problem that the overall safety performance evaluation of a dam is inaccurate in the prior art.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a dam monitoring web display method based on a finite element model and an SVM regression algorithm is characterized in that:
selecting a typical section of a target dam, importing the selected typical section of the dam into Hypermesh for grid division, and performing classified storage on node unit information in each grid;
searching the profile outer contour through the corresponding information between the nodes and the units: forming a complete closed graph by using the edges of each grid which are used only once, wherein the closed graph can be used as the outer contour of the dam section;
acquiring target measuring points and target date data from a monitoring platform database in real time; performing quadratic processing on the independent variable to expand the independent variable information;
constructing an SVM regressor, selecting a relaxation variable, and adjusting SVM parameters according to a training set;
carrying out coordinate preprocessing and target value calculation on finite element nodes, and diffusing the measuring point information to the full section;
and (4) drawing a measured value cloud picture of the dam body section by interpolation, and displaying the drawn contour line in real time.
As a preferred embodiment of the present invention, the dam monitoring web display method based on the finite element model and the SVM regression algorithm is characterized in that: the grid division adopts quadrilateral grids.
As a preferred embodiment of the present invention, the dam monitoring web display method based on the finite element model and the SVM regression algorithm is characterized in that: the node unit information storage is to store the node number coordinates and the unit numbers into a folder; the constituent nodes are sequentially saved as another folder.
As a preferred embodiment of the present invention, the dam monitoring web display method based on the finite element model and the SVM regression algorithm is characterized in that: and listing edges of all grids, counting the edges which only form one grid to be 1, counting the edges which form two grids to be 2, deleting the edges with the counting number of 2, sequencing all the edges with the counting number of 1 through head and tail node numbers to form a complete closed graph, and using the closed graph as the outer contour of the dam section.
As a preferred embodiment of the present invention, the dam monitoring web display method based on the finite element model and the SVM regression algorithm is characterized in that: the first column of arguments is the X coordinate of the measured point as the first argument of X, the second column is the y coordinate of the measured point as the second argument of X, the arguments are combined quadratically to produce the square of the X coordinate as the third argument of X, the square of the y coordinate as the fourth argument of X, and X y of each measured point as the fifth argument of X.
As a preferred embodiment of the present invention, the dam monitoring web display method based on the finite element model and the SVM regression algorithm is characterized in that: the method for constructing the SVM regressor comprises the following steps: and (3) introducing the independent variable X serving as data into an SVM regressor, iteratively correcting the coefficient in the SVM by taking the dependent variable as a target, and reducing the output error of the regressor. In actual engineering, a specific mapping relation exists between an independent variable X and a dependent variable y in a function space, so that one X state can only correspond to one result state y, but most of the mapping relations are complex and changeable in a real state, and the function relation is difficult to accurately describe through the existing linear analysis means, so that a nonlinear algorithm SVM is adopted, the model is continuously close to the real mapping relation between the independent variable and the dependent variable through continuous training and error verification, and the real structure state can be effectively simulated.
As a preferred embodiment of the present invention, the dam monitoring web display method based on the finite element model and the SVM regression algorithm is characterized in that: the selected relaxation variables range from 0.01 to 1000.
As a preferred embodiment of the present invention, the dam monitoring web display method based on the finite element model and the SVM regression algorithm is characterized in that: and (3) keeping a coordinate system of the finite element model consistent with the actual engineering coordinate, outputting node coordinates of the finite element model, constructing five lines of data by using an independent variable information expansion method, using the five lines of data as independent variables of the test set, inputting the independent variables into the SVM regressor which is constructed in the SVM regressor, generating a prediction target value, and expanding a small amount of measuring point displacement and measured value information in the typical section to the whole section.
As a preferred embodiment of the present invention, the dam monitoring web display method based on the finite element model and the SVM regression algorithm is characterized in that: and interpolating the predicted value in the whole section by adopting a griddata function in python to form a continuously-changed target value on a typical section, removing redundant interpolation points through the searched profile outer contour, and finally drawing a corresponding cloud picture and a contour map.
As a preferred embodiment of the present invention, the dam monitoring web display method based on the finite element model and the SVM regression algorithm is characterized in that: the selected slack variable is equal to 1000.
The invention achieves the following beneficial effects:
according to the dam body section real-time monitoring method, the typical section of the dam is monitored in real time through the finite element model and the nonlinear algorithm, the monitoring result is good in timeliness, and the monitoring structure can be displayed in real time through drawing a dam body section measured value cloud picture.
The method can be used for preprocessing the finite element coordinates selected from the typical section of the dam and calculating the target value, and the primary square coordinates are combined and raised into the quadratic coordinates, so that the independent variable information is expanded, and the measured point information is diffused to the full section.
Drawings
FIG. 1 is a general flow diagram of the present invention;
FIG. 2 is a full section contour plot of the present method;
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
As shown in fig. 1: the embodiment discloses a dam monitoring web display method based on a finite element model and an SVM regression algorithm. The term "critical section" as used herein is to be understood as a section which is damaged first in the normal situation, assuming that the dam is crossed, and as a representative section for monitoring. The selected typical section of the dam is led into Hypermesh for grid division, because the selected typical section is a plane, the types of grids (units) on the plane mainly include triangle and quadrangle, the embodiment preferably adopts quadrangle grids, that is, each unit has four nodes. Then classifying and storing the node unit information in each grid; saving the node number coordinates and the unit numbers in the model into a folder; and sequentially saving the composition nodes as another folder, and putting the folder into the back end for subsequent data processing.
Searching the profile outer contour through the corresponding information between the nodes and the units: the whole section is composed of a plurality of quadrangles (units), so that the outline of the section is formed by connecting edge edges in the edge quadrangles end to end, and the outline of the edge edges of the edge quadrangles can be used as the outline of the section of the dam.
The specific way of this embodiment is: and listing edges of all grids, wherein the number of the edges forming only one grid is 1, the number of the edges forming two grids is 2, the edges with the number of 1 are positioned at the edge, the edges with the number of 2 are deleted, all the edges with the number of 1 are sequenced through head and tail node numbers to form a complete closed graph, and the closed graph can be used as the outer contour of the dam section.
Acquiring target measuring points and target date data from a monitoring platform database in real time; and performing quadratic processing on the independent variable to expand the independent variable information.
Since the typical section of the intercepting dam is a plane, a biaxial coordinate system is adopted for calculation, namely an x axis and a y axis. A quadratic combination of the coordinates is calculated. The following were used:
point _ data [: 0] # measures point x-direction coordinate
Point _ data [: 1] # measures point y-direction coordinate
row＝x.shape[0]
x _2 ═ pow (x,2) # x coordinate squared
y _2 ═ pow (y,2) # y squared coordinate
x y # x in combination with y coordinates
one＝np.ones((row,1))
# are combined into a high-dimensional argument X as input data for the SVM
X＝np.column_stack((np.double(one),np.double(x),np.double(y),np.double(z),np.double(x_2),np.double(y_2),np.double(xy))
And (4) taking the measured value of the # measuring point as training target data of the SVM.
disp＝point_data[:,3]
The variable point _ data stores four rows of data, the first row is an X coordinate of a measuring point and serves as a first independent variable of X, the second row is a y coordinate of the measuring point and serves as a second independent variable of X, the independent variables are combined quadratically to generate a quadratic form of the X coordinate and serve as a third independent variable of X, the quadratic form of the y coordinate serves as a fourth independent variable of X, and X and y of each measuring point serve as a fifth independent variable of X. The combined X is an independent variable training set of the SVM regressor. The fourth column in the point _ data is a measured point target date measured value disp which is used as a target variable training set of the SVM regressor.
And constructing an SVM regressor, selecting a relaxation variable, training an SVM internal parameter gradient according to a training data set, and adjusting the functional relation between a model input variable and a model output variable. And (3) introducing the independent variable X serving as data into an SVM (support vector machine) regressor, iteratively correcting the coefficient in the SVM by taking the dependent variable as a target, reducing the output error of the regressor, and approximating the implicit functional relation between the independent variable and the dependent variable. The value of the relaxation variable C is determined according to trial calculation, after the relaxation variable C is manually selected before the training stage begins, the parameter is kept unchanged in the training process, the span range is 0.01-1000, and the value C corresponding to the minimum output error is finally selected to be 1000. And generating a target model regressor after the training is finished.
Carrying out coordinate preprocessing and target value calculation on finite element nodes, and diffusing the measuring point information to the full section; the method comprises the following steps: and (3) keeping a coordinate system of the finite element model consistent with the actual engineering coordinate, outputting node coordinates of the finite element model, constructing five rows of data (five independent variables of X) by the method for expanding independent variable information, using the five rows of data as the independent variables of the test set, inputting the independent variables into the SVM regressor constructed in the SVM regressor, generating a predicted target value, and reasonably expanding a small amount of measuring point displacement and measured value information in the typical section to the whole section.
Interpolating to draw a measured value cloud picture of the dam body section, and displaying the drawn contour line in real time; and (3) interpolating the predicted value in the whole section by adopting a griddata function in python to form a continuously-changed target value on the typical section, removing redundant interpolation points through the searched section outer contour, namely deleting the redundant interpolation points outside the section outer contour, and finally drawing a corresponding cloud graph and a contour graph as shown in a second drawing.
According to the dam body section real-time monitoring method, the typical section of the dam is monitored in real time through the finite element model and the nonlinear algorithm, the monitoring result is good in timeliness, and the monitoring structure can be displayed in real time through drawing a dam body section measured value cloud picture.
The method can be used for preprocessing the finite element coordinates selected from the typical section of the dam and calculating the target value, and the primary square coordinates are combined and raised into the quadratic coordinates, so that the independent variable information is expanded, and the measured point information is diffused to the full section.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A dam monitoring web display method based on a finite element model and an SVM regression algorithm is characterized in that:
selecting a typical section of a target dam, importing the selected typical section of the dam into Hypermesh for grid division, and performing classified storage on node unit information in each grid;
searching the profile outer contour through the corresponding information between the nodes and the units: forming a complete closed graph by using the edges of each grid which are used only once, wherein the closed graph can be used as the outer contour of the dam section;
acquiring target measuring points and target date data from a monitoring platform database in real time; performing quadratic processing on the independent variable to expand the independent variable information;
constructing an SVM regressor, selecting a relaxation variable, and adjusting SVM parameters according to a training set;
carrying out coordinate preprocessing and target value calculation on finite element nodes, and diffusing the measuring point information to the full section;
and (4) drawing a measured value cloud picture of the dam body section by interpolation, and displaying the drawn contour line in real time.
2. The dam monitoring web display method based on the finite element model and the SVM regression algorithm as claimed in claim 1, wherein: the grid division adopts quadrilateral grids.
3. The dam monitoring web display method based on the finite element model and the SVM regression algorithm as claimed in claim 2, wherein: the node unit information storage is to store the node number coordinates and the unit numbers into a folder; the constituent nodes are sequentially saved as another folder.
4. The dam monitoring web display method based on finite element model and SVM regression algorithm as claimed in claim 1 or 2, wherein: and listing edges of all grids, counting the edges which only form one grid to be 1, counting the edges which form two grids to be 2, deleting the edges with the counting number of 2, sequencing all the edges with the counting number of 1 through head and tail node numbers to form a complete closed graph, and using the closed graph as the outer contour of the dam section.
5. The dam monitoring web display method based on the finite element model and the SVM regression algorithm as claimed in claim 1, wherein: the first column of arguments is the X coordinate of the measured point as the first argument of X, the second column is the y coordinate of the measured point as the second argument of X, the arguments are combined quadratically to produce the square of the X coordinate as the third argument of X, the square of the y coordinate as the fourth argument of X, and X y of each measured point as the fifth argument of X.
6. The dam monitoring web display method based on the finite element model and the SVM regression algorithm as claimed in claim 5, wherein: the method for constructing the SVM regressor comprises the following steps: and (3) introducing the independent variable X serving as data into an SVM regressor, iteratively correcting the coefficient in the SVM by taking the dependent variable as a target, and reducing the output error of the regressor. In actual engineering, a specific mapping relation exists between an independent variable X and a dependent variable y in a function space, so that one X state can only correspond to one result state y, but most of the mapping relations are complex and changeable in a real state, and the function relation is difficult to accurately describe through the existing linear analysis means, so that a nonlinear algorithm SVM is adopted, the model is continuously close to the real mapping relation between the independent variable and the dependent variable through continuous training and error verification, and the real structure state can be effectively simulated.
7. The dam monitoring web display method based on the finite element model and the SVM regression algorithm as claimed in claim 6, wherein: the selected relaxation variables range from 0.01 to 1000.
8. The dam monitoring web display method based on the finite element model and the SVM regression algorithm as claimed in claim 5, wherein: and (3) keeping a coordinate system of the finite element model consistent with the actual engineering coordinate, outputting node coordinates of the finite element model, constructing five lines of data by using an independent variable information expansion method, using the five lines of data as independent variables of the test set, inputting the independent variables into the SVM regressor which is constructed in the SVM regressor, generating a prediction target value, and expanding a small amount of measuring point displacement and measured value information in the typical section to the whole section.
9. The dam monitoring web display method based on the finite element model and the SVM regression algorithm as claimed in claim 8, wherein: and interpolating the predicted value in the whole section by adopting a griddata function in python to form a continuously-changed target value on a typical section, removing redundant interpolation points through the searched profile outer contour, and finally drawing a corresponding cloud picture and a contour map.
10. The dam monitoring web display method based on the finite element model and the SVM regression algorithm as claimed in claim 7, wherein: the selected slack variable is equal to 1000.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910940775.XA CN110765679B (en) | 2019-09-30 | 2019-09-30 | Dam monitoring web display method based on finite element model and SVM regression algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910940775.XA CN110765679B (en) | 2019-09-30 | 2019-09-30 | Dam monitoring web display method based on finite element model and SVM regression algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110765679A true CN110765679A (en) | 2020-02-07 |
| CN110765679B CN110765679B (en) | 2023-07-07 |
Family
ID=69330054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910940775.XA Active CN110765679B (en) | 2019-09-30 | 2019-09-30 | Dam monitoring web display method based on finite element model and SVM regression algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110765679B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111309065A (en) * | 2020-02-12 | 2020-06-19 | 广东韶钢松山股份有限公司 | Pressure model establishing method, pressure adjusting method and device |
| CN112487533A (en) * | 2020-11-30 | 2021-03-12 | 北京航空航天大学 | Full-section stress sensing method of tunnel structure health monitoring system |
| CN112749438A (en) * | 2021-01-22 | 2021-05-04 | 中国水利水电科学研究院 | Three-dimensional dam body structure model construction method based on two-dimensional virtual section |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881546A (en) * | 2015-06-01 | 2015-09-02 | 中国科学院上海高等研究院 | Method for improving prediction efficiency of atmospheric pollution model |
| CN107480341A (en) * | 2017-07-21 | 2017-12-15 | 河海大学 | A kind of dam safety comprehensive method based on deep learning |
| CN108334668A (en) * | 2018-01-09 | 2018-07-27 | 天津大学 | Consider the earth and rockfill dam compaction quality method for quick predicting that parameter uncertainty influences |
-
2019
- 2019-09-30 CN CN201910940775.XA patent/CN110765679B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881546A (en) * | 2015-06-01 | 2015-09-02 | 中国科学院上海高等研究院 | Method for improving prediction efficiency of atmospheric pollution model |
| CN107480341A (en) * | 2017-07-21 | 2017-12-15 | 河海大学 | A kind of dam safety comprehensive method based on deep learning |
| CN108334668A (en) * | 2018-01-09 | 2018-07-27 | 天津大学 | Consider the earth and rockfill dam compaction quality method for quick predicting that parameter uncertainty influences |
Non-Patent Citations (1)
| Title |
|---|
| 杨杰等: "基于相关向量机与随机有限元的筑坝材料参数不确定性反分析" * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111309065A (en) * | 2020-02-12 | 2020-06-19 | 广东韶钢松山股份有限公司 | Pressure model establishing method, pressure adjusting method and device |
| CN111309065B (en) * | 2020-02-12 | 2023-08-01 | 广东韶钢松山股份有限公司 | Pressure model building method, pressure adjusting method and device |
| CN112487533A (en) * | 2020-11-30 | 2021-03-12 | 北京航空航天大学 | Full-section stress sensing method of tunnel structure health monitoring system |
| CN112749438A (en) * | 2021-01-22 | 2021-05-04 | 中国水利水电科学研究院 | Three-dimensional dam body structure model construction method based on two-dimensional virtual section |
| CN112749438B (en) * | 2021-01-22 | 2023-09-22 | 中国水利水电科学研究院 | Method for constructing three-dimensional dam body structure model based on two-dimensional virtual section |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110765679B (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020000248A1 (en) | Space reconstruction based method for predicting key performance parameters of transition state acceleration process of aircraft engine | |
| CN110765679A (en) | Dam monitoring web display method based on finite element model and SVM regression algorithm | |
| Jiang et al. | Geometric verification of swirling features in flow fields | |
| CN105157590A (en) | Construction health monitoring system based on three-dimensional laser scanning technology | |
| Mao et al. | Subsurface velocity inversion from deep learning-based data assimilation | |
| JP2019537079A (en) | How to build stochastic models for large-scale renewable energy data | |
| CN105550691A (en) | Self-adaptive valley and ridge line extraction method and system based on scale space | |
| CN107908864A (en) | A kind of complex device remaining life Forecasting Methodology of feature based fusion | |
| CN112904139A (en) | High-voltage switch cabinet partial discharge positioning method and system considering temperature field change | |
| de Almeida et al. | Power system observability analysis based on gram matrix and minimum norm solution | |
| US20150073730A1 (en) | Mechanical strain gauge simulation | |
| CN112257021A (en) | Selectable kriging spatial interpolation rainfall estimation method | |
| CN110334450A (en) | A kind of multi-blocked structure grid generate in object plane erroneous projection restorative procedure | |
| CN108574290B (en) | Method, device, terminal and readable storage medium for positioning oscillation source of forced oscillation | |
| CN114022586A (en) | Defect image generation method based on countermeasure generation network | |
| CN116227045B (en) | Local stress strain field construction method and system for structural test piece | |
| CN115510732B (en) | Shelter infrared characteristic simulation rapid algorithm based on deep learning | |
| CN110083849A (en) | Flexible measurement method, computer and the computer-readable medium of semiconductor manufacturing facility | |
| CN114526118A (en) | Method and device for measuring gas flow of roadway section and storage medium | |
| Rus et al. | Hypersingular shape sensitivity boundary integral equation for crack identification under harmonic elastodynamic excitation | |
| CN106339588A (en) | Discrete modeling method of accelerated degradation data based on grey system theory | |
| CN102781016B (en) | Method for analyzing user behaviors in wireless local area network | |
| Zhang | Deep learning-based hybrid short-term solar forecast using sky images and meteorological data | |
| Kumratova et al. | Hybrid instrumental means of predic-tive analysis of the dynamics of natural and economic processes | |
| CN111210877A (en) | Method and device for deducing physical property parameters |
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 |