CN106990018A - A kind of prestressed concrete beam Grouted density intelligent identification Method - Google Patents
A kind of prestressed concrete beam Grouted density intelligent identification Method Download PDFInfo
- Publication number
- CN106990018A CN106990018A CN201710113049.1A CN201710113049A CN106990018A CN 106990018 A CN106990018 A CN 106990018A CN 201710113049 A CN201710113049 A CN 201710113049A CN 106990018 A CN106990018 A CN 106990018A
- Authority
- CN
- China
- Prior art keywords
- prestressed concrete
- concrete beam
- svms
- identification method
- impact echo
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 239000011513 prestressed concrete Substances 0.000 title claims abstract description 30
- 238000012706 support-vector machine Methods 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 20
- 230000002123 temporal effect Effects 0.000 claims description 17
- 239000004567 concrete Substances 0.000 claims description 12
- 238000004088 simulation Methods 0.000 claims description 7
- 238000003556 assay Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 16
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000008569 process Effects 0.000 abstract description 6
- 230000007812 deficiency Effects 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 235000013336 milk Nutrition 0.000 description 2
- 239000008267 milk Substances 0.000 description 2
- 210000004080 milk Anatomy 0.000 description 2
- 238000009659 non-destructive testing Methods 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 230000009466 transformation 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
- 229920002472 Starch Polymers 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 235000019698 starch Nutrition 0.000 description 1
- 239000008107 starch Substances 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N9/00—Investigating density or specific gravity of materials; Analysing materials by determining density or specific gravity
- G01N9/002—Investigating density or specific gravity of materials; Analysing materials by determining density or specific gravity using variation of the resonant frequency of an element vibrating in contact with the material submitted to analysis
-
- 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]
Abstract
The invention discloses a kind of prestressed concrete beam Grouted density intelligent identification Method, this method is using technologies such as variation mode decomposition, finite element modelling and SVMs, the impact echo vibration signal gone out by finite element modelling under different operating modes, recycle variation mode decomposition and Hilbert transform to construct SVMs training sample, impact echo is finally detected that signal goes out prestressed concrete beam compactness using the SVMs quantitative forecast after training.Intelligent identification Method of the present invention, which can effectively overcome, there are the deficiencies such as the low, low precision of efficiency in existing impact echo detection process, eliminate the influence of human factor in detection process, farthest improve accuracy of detection and operating efficiency.
Description
Technical field
It is more particularly to a kind of based on punching the present invention relates to a kind of prestressed concrete beam Grouted density intelligent identification Method
The prestressed concrete beam Grouted density intelligent identification Method of echo is hit, belongs to civil structure engineering Inspection Technique field.
Background technology
With China's expanding economy, Prestressed Concrete Bridges are used widely.In order to improve deformed bar and
The globality that surrounding concrete is combined, it is necessary to be in the milk into bellows after deformed bar tensioning is to design load.Grouting
Compaction rate directly affect the corrosion resistance of deformed bar, the leakiness if bellows is in the milk, by the durability of bridge
Have adverse effect on, it is necessary to pay attention to grouting quality.There is spy ground to bridge bellows Grouted density lossless detection method at present
Radar method, ultrasonic method, thermal imaging method and Impact echo etc..GPR method is its essence is electromagnetic exploration method, due to electromagnetism
Method is easily influenceed and interference by reinforcing bar, in bellows grouting detection by many limitations;Supercritical ultrasonics technology belongs to stress
Ripple method, parameters,acoustic with mechanical performance of concrete there is good correlation to be widely used in concrete NDT, but for
The detection of prestressed concrete grouting quality is at present still in experimental stage;Although infrared imaging has success to concrete nondestructive testing
Application, but its detection depth of defect it is typically small.The Impact echo of method, is widely used to soil at present relatively above
In timber engineering detection, it was demonstrated that impact echo is a kind of relatively practical reliable technology.Although Impact echo, which is one kind, to be had
The prestressed concrete grouting quality detection method of effect, but the evaluation to grouting quality is qualitative evaluation at present, and need
Gathered data carries out substantial amounts of artificial cognition, has a strong impact on detection level and production efficiency.
In recent years, information technology and artificial intelligence are continued to develop, and have promoted the continuous progress of engineering technology.Early stage people
Using Fourier transform, processing is filtered to signal in frequency domain.But Fourier transform is to assume signal as steady letter
A kind of method of sign signal frequency feature under the conditions of number, this method is the frequency in whole time-domain to analyzed signal
The average result of feature.M- dimensional analysis method when wavelet transformation is a kind of, with good Time-Frequency Localization characteristic, still
Basic function once it is determined that, can not change during analyzing and processing.Empirical mode decomposition method has adaptive feature, especially fits
Analyzing and processing for nonlinear and non local boundary value problem.But the subject matter of empirical mode decomposition method is a lack of mathematical theory,
Modeling is difficult.Variation mode decomposition is a kind of new mode decomposition method proposed in recent years, by the acquisition process of component of signal
It is transferred in variation framework, the decomposition of primary signal is realized by constructing and solving constraint variation problem, method has firm
Mathematical theory basis.On the other hand, in order to solve the influence of human factor and reduce substantial amounts of repeated work, nerve net
The intelligent algorithms such as network, decision Tree algorithms, SVMs and linear regression are used widely in the industrial production.Support
Vector machine method is built upon on the VC of Statistical Learning Theory dimensions theory and Structural risk minization basis, and it is solving sample
Originally, non-linear and high dimensional pattern identification has significant advantage.
Impact echo is as a kind of Stress Wave Method of Non-Destructive Testing, using advanced signal processing technology and artificial intelligence
Technology, using the feature of the vibration signal of test, sets up the prestressed concrete based on variation mode decomposition and SVMs
Grouted density quantified system analysis is possibly realized, and proposes a kind of prestressed concrete beam Grouted density intelligent identification Method tool
There is extensive realistic meaning.
The content of the invention
The technical problems to be solved by the invention are:A kind of prestressed concrete beam Grouted density Intelligent Recognition side is provided
Method, this method reduces influence of the human factor to differentiation result, improves detection efficiency and measuring accuracy, and prestressed concrete is filled
Starch compactness and carry out quantitative analysis, the applicability and reliability of Enhancement Method.
The present invention uses following technical scheme to solve above-mentioned technical problem:
A kind of prestressed concrete beam Grouted density intelligent identification Method, comprises the following steps:
Step 1, the influence factor in the identification of impact echo Grouted density is determined, each is designed using orthogonal array
The calculating operating mode of influence factor;
Step 2, the impact echo vibration signal under different calculating operating modes is simulated using finite element simulation;
Step 3, the impact echo vibration signal of simulation is obtained into each feature for calculating operating mode by variation mode decomposition
Modulus, and the temporal characteristics amount that Hilbert transform obtains each calculating operating mode is carried out to eigenanalysis;
Step 4, using the temporal characteristics amount of each calculating operating mode as input, by the mechanics parameter of concrete, geometric parameter
With compactness as output, the training set of SVMs is built;
Step 5, using training set Training Support Vector Machines, the SVMs trained, and utilize training set pair
The SVMs trained is verified, carries out step 6 if checking is correct, otherwise return to step 2;
Step 6, impact echo vibration signal is carried out to prestressed concrete beam to be identified using impact echo instrument to adopt
Collection;
Step 7, eigenanalysis is obtained to the impact echo vibration signal progress variation mode decomposition of collection, to eigenanalysis
Carry out Hilbert transform and obtain temporal characteristics amount;
Step 8, it regard step 7 temporal characteristics amount as the input of the SVMs trained, identification beams of concrete grouting
Compactness parameter is simultaneously examined, if assay is normal, end of identification, otherwise return to step 4.
As a preferred embodiment of the present invention, influence factor described in step 1 include thickness of slab, ripple pipe size and position,
The compactness of ripple.
As a preferred embodiment of the present invention, temporal characteristics amount described in step 3 includes frequency, amplitude and phase.
As a preferred embodiment of the present invention, each influence factor is designed using orthogonal array described in step 1
Calculate operating mode specific method be:The maximum and minimum value of each influence factor are obtained, by the minimum value of each influence factor
Maximum is incremented to by 10%, as the value of each influence factor, the meter of each influence factor is designed by orthogonal array
Calculate operating mode.
As a preferred embodiment of the present invention, the model of the SVMs trained described in step 5 is:Grouting is closely knit
Nonlinear Mapping relation between degree and temporal characteristics amount.
The present invention uses above technical scheme compared with prior art, with following technique effect:
1st, intelligent identification Method of the present invention, which can be effectively overcome in existing impact echo detection process, occurs that efficiency is low, low precision
Deng deficiency, the influence of human factor in detection process is eliminated, accuracy of detection and operating efficiency is farthest improved.
2nd, intelligent identification Method of the present invention can carry out quantitative analysis, the side of enhancing to prestressed concrete Grouted density
The practicality and reliability of method.
Brief description of the drawings
Fig. 1 is a kind of flow chart of prestressed concrete beam Grouted density intelligent identification Method of the invention.
Fig. 2 is the structure schematic diagram of SVMs training sample in intelligent identification Method of the present invention.
Embodiment
Embodiments of the present invention are described below in detail, the example of the embodiment is shown in the drawings.Below by
The embodiment being described with reference to the drawings is exemplary, is only used for explaining the present invention, and is not construed as limiting the claims.
As shown in figure 1, being a kind of flow chart of prestressed concrete beam Grouted density intelligent identification Method of the invention.This
Invention is gone out under different operating modes using technologies such as variation mode decomposition, finite element modelling and SVMs by finite element modelling
Impact echo vibration signal, recycle variation mode decomposition and Hilbert transform to construct SVMs training sample,
Impact echo is finally detected that signal goes out prestressed concrete beam compactness using the SVMs quantitative forecast after training.
Prestressed concrete Grouted density assay method based on variation mode decomposition and SVMs, it mainly has
Following steps are realized:
1st, according to the excursion of prestressed concrete and grouted-aggregate concrete mechanics, model geometric parameter and compactness, if
Count out different calculating operating modes;
2nd, the impact echo vibration signal gone out using finite element modelling under different calculating operating modes;
3rd, the impact echo vibration signal of simulation is drawn into each eigenanalysis by variation mode decomposition, utilizes Martin Hilb
Spy's conversion draws the temporal characteristics amount of each eigenanalysis;
4th, using the temporal characteristics value of each operating mode as input quantity, and by the mechanics parameter of concrete, geometric parameter and close
Solidity constitutes the training set of supporting vector as output quantity;
5th, Training Support Vector Machines, and the model trained is verified, it is as a result correct to perform next step step, otherwise
Circulated again from step 2;
6th, signal acquisition is carried out to actual prestressed concrete beam using impact echo instrument;
7th, repeat step 3, draw the temporal characteristics amount of each eigenanalysis;
8th, temporal characteristics amount, using SVMs is obtained after being trained in step 4, is predicted into beams of concrete as input quantity
The parameters such as Grouted density;
9th, input results are examined, if it is normal to predict the outcome, otherwise terminal procedure circulates from step 4 again.
This method is simultaneously only defined in the prediction of prestressed concrete beam defect quantitative, it can also be used to other concrete structures scene
Detection;During prestressed concrete beam compactness, the quantitative forecast for being not limited to compactness can also be other ginsengs
Several predictions.It is not limited in algorithm of support vector machine or least square method supporting vector machine, neutral net in step 4
With the machine algorithm such as decision tree.The variation mode decomposition of step 3, can be traditional signal analysis method, including wavelet transformation,
The method such as short time discrete Fourier transform and empirical mode decomposition.The instantaneous flow of vibration signal is not limited in step 4 as defeated
Enter variable can also other physical parameters such as the statistical nature parameter of time domain.
As shown in Fig. 2 temporal characteristics sample composition step is as follows:
1) influence factor in impact echo detection, such as thickness of slab, ripple pipe size and position, compactness of ripple etc. are determined
The excursion of influence factor;
2) by the maximum and minimum value of influence factor, maximum is incremented by by 10% according to by the minimum value of each influence factor
Value, as the value of each influence factor, the calculating operating mode of each influence factor is designed by orthogonal array;
3) test result of each operating mode is simulated using finite element simulation, including impact load is determined, perimeter strip
Part setting and contact conditions etc., the impact load attack time can be determined by following equation:
Tc=0.0086R (1)
Wherein, TcFor shock duration, R is the impact radius of a ball;
4) eigenanalysis under each operating mode is drawn using variation mode decomposition technology, detailed step is shown in part 2;
5) change the instantaneous flow for drawing each modulus, including frequency, amplitude and phase by Hilbert, take each modulus
Instance variable maximum builds up sample set as sample value.
Variation mode decomposition is variational problem, then corresponding variational problem construction process is as follows:
1) Hilbert conversion is carried out to each IMF components and obtains its analytic signal:
Wherein, δ (t) is dirichlet function, and t is the time, and j is imaginary unit, uk(t) it is IMF components;
2) centre frequency is estimated to the analytic signal drawn, by frequency shift mode, the Spectrum Conversion of each analytic signal arrived
In base band:
Wherein, ωkFor circular frequency;
3) L of above-mentioned demodulated signal is calculated2Norm, estimates each modal bandwidth, and its variational problem is as follows:
Wherein, f is primary signal;
To above-mentioned variational problem, unconstrained problem is translated into using quadratic penalty function and Lagrange multipliers:
Wherein, α is penalty factor, and λ (t) is Lagrange multipliers.
4) finally, multiplier alternating direction algorithm is recycled to ask for equation (4) without constraint variation problem.
SVMs is main to be constituted by training and testing two parts, and its detailed step is as follows:
1) orthogonal array is designed to the calculating operating mode of each influence factor, and by finite element numerical simulation and variation mould
State is decomposed to form training sample;
2) by step 1) training sample that draws, Training Support Vector Machines model respectively joins in Support Vector Machines Optimized model
Numerical value, such as kernel parameter and penalty factor;
3) by learning sample Training Support Vector Machines model, set up out non-between Grouted density and characteristic instant amount
Linear mapping relation;
4) according to test sample, using training supporting vector machine model to predict, parameter was sought in Grouted density wait;
5) predicted value and experiment value are contrasted, assessment prediction reliability.
The technological thought of above example only to illustrate the invention, it is impossible to which protection scope of the present invention is limited with this, it is every
According to technological thought proposed by the present invention, any change done on the basis of technical scheme each falls within the scope of the present invention
Within.
Claims (5)
1. a kind of prestressed concrete beam Grouted density intelligent identification Method, it is characterised in that comprise the following steps:
Step 1, the influence factor in the identification of impact echo Grouted density is determined, each influence is designed using orthogonal array
The calculating operating mode of factor;
Step 2, the impact echo vibration signal under different calculating operating modes is simulated using finite element simulation;
Step 3, the impact echo vibration signal of simulation is obtained into each eigenanalysis for calculating operating mode by variation mode decomposition,
And the temporal characteristics amount that Hilbert transform obtains each calculating operating mode is carried out to eigenanalysis;
Step 4, using the temporal characteristics amount of each calculating operating mode as input, by the mechanics parameter of concrete, geometric parameter and close
Solidity builds the training set of SVMs as output;
Step 5, using training set Training Support Vector Machines, the SVMs trained, and using training set to training
Good SVMs is verified, carries out step 6 if checking is correct, otherwise return to step 2;
Step 6, impact echo vibration signals collecting is carried out to prestressed concrete beam to be identified using impact echo instrument;
Step 7, eigenanalysis is obtained to the impact echo vibration signal progress variation mode decomposition of collection, eigenanalysis is carried out
Hilbert transform obtains temporal characteristics amount;
Step 8, step 7 temporal characteristics amount is recognized that beams of concrete grouting is closely knit as the input of the SVMs trained
Degree parameter is simultaneously examined, if assay is normal, end of identification, otherwise return to step 4.
2. prestressed concrete beam Grouted density intelligent identification Method according to claim 1, it is characterised in that step 1
The influence factor includes thickness of slab, ripple pipe size and position, the compactness of ripple.
3. prestressed concrete beam Grouted density intelligent identification Method according to claim 1, it is characterised in that step 3
The temporal characteristics amount includes frequency, amplitude and phase.
4. prestressed concrete beam Grouted density intelligent identification Method according to claim 1, it is characterised in that step 1
The specific method that the utilization orthogonal array designs the calculating operating mode of each influence factor is:Obtain each influence factor
Maximum and minimum value, are incremented to maximum by 10% by the minimum value of each influence factor, are used as taking for each influence factor
Value, the calculating operating mode of each influence factor is designed by orthogonal array.
5. prestressed concrete beam Grouted density intelligent identification Method according to claim 1, it is characterised in that step 5
The model of the SVMs trained is:Nonlinear Mapping relation between Grouted density and temporal characteristics amount.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710113049.1A CN106990018B (en) | 2017-02-28 | 2017-02-28 | A kind of prestressed concrete beam Grouted density intelligent identification Method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710113049.1A CN106990018B (en) | 2017-02-28 | 2017-02-28 | A kind of prestressed concrete beam Grouted density intelligent identification Method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106990018A true CN106990018A (en) | 2017-07-28 |
CN106990018B CN106990018B (en) | 2019-09-10 |
Family
ID=59413061
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710113049.1A Expired - Fee Related CN106990018B (en) | 2017-02-28 | 2017-02-28 | A kind of prestressed concrete beam Grouted density intelligent identification Method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106990018B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107730494A (en) * | 2017-10-24 | 2018-02-23 | 河海大学 | A kind of anchor pole detection method based on variation mode decomposition |
CN108844856A (en) * | 2018-07-04 | 2018-11-20 | 四川升拓检测技术股份有限公司 | Based on elastic impact wave and the sleeve of machine learning grouting defect lossless detection method |
CN108896996A (en) * | 2018-05-11 | 2018-11-27 | 中南大学 | A kind of Pb-Zn deposits absorbing well, absorption well water sludge interface ultrasonic echo signal classification method based on random forest |
CN108918679A (en) * | 2018-07-11 | 2018-11-30 | 四川升拓检测技术股份有限公司 | Based on elastic wave and the prefabricated post sleeve of machine learning grouting lossless detection method |
CN109469112A (en) * | 2018-11-09 | 2019-03-15 | 北京市道路工程质量监督站 | Pile defect severity automatic identifying method based on support vector machines |
CN110440728A (en) * | 2019-05-31 | 2019-11-12 | 特斯联(北京)科技有限公司 | A kind of structural safety monitoring method and system detecting echo intellectual analysis |
CN110455678A (en) * | 2019-09-07 | 2019-11-15 | 北京市政建设集团有限责任公司 | A kind of packaged type bridges pier stud node Grouted density detection method |
CN110608066A (en) * | 2019-10-10 | 2019-12-24 | 中国五冶集团有限公司 | Detection system for tunnel grouting depth |
CN111238997A (en) * | 2020-02-12 | 2020-06-05 | 江南大学 | On-line measurement method for feed density in crude oil desalting and dewatering process |
CN112525467A (en) * | 2020-11-26 | 2021-03-19 | 山东科技大学 | Impact damage area identification method and device suitable for cantilever beam |
CN114018800A (en) * | 2021-10-29 | 2022-02-08 | 福建工程学院 | Device and method for measuring grouting compactness of prestressed duct |
CN114137090A (en) * | 2021-10-27 | 2022-03-04 | 郑州大学 | Grouting compactness identification method and system based on RF-GA-SVM model and storage medium |
CN114894897A (en) * | 2022-05-11 | 2022-08-12 | 郑州大学 | Sleeve grouting defect nondestructive detection method and device based on one-dimensional convolutional neural network and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102629107A (en) * | 2012-04-18 | 2012-08-08 | 长沙理工大学 | Pressure closed loop control method for large-circulation grouting monitor system |
CN106019271A (en) * | 2016-04-27 | 2016-10-12 | 南京理工大学 | Multi-person through-wall time varying breathing signal detection method based on VMD |
-
2017
- 2017-02-28 CN CN201710113049.1A patent/CN106990018B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102629107A (en) * | 2012-04-18 | 2012-08-08 | 长沙理工大学 | Pressure closed loop control method for large-circulation grouting monitor system |
CN106019271A (en) * | 2016-04-27 | 2016-10-12 | 南京理工大学 | Multi-person through-wall time varying breathing signal detection method based on VMD |
Non-Patent Citations (1)
Title |
---|
郭佳: "基于冲击回波法与支持向量机的预应力管道压浆质量评定", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107730494A (en) * | 2017-10-24 | 2018-02-23 | 河海大学 | A kind of anchor pole detection method based on variation mode decomposition |
CN108896996A (en) * | 2018-05-11 | 2018-11-27 | 中南大学 | A kind of Pb-Zn deposits absorbing well, absorption well water sludge interface ultrasonic echo signal classification method based on random forest |
CN108896996B (en) * | 2018-05-11 | 2019-09-20 | 中南大学 | A kind of Pb-Zn deposits absorbing well, absorption well water sludge interface ultrasonic echo signal classification method based on random forest |
CN108844856B (en) * | 2018-07-04 | 2023-08-15 | 四川升拓检测技术股份有限公司 | Sleeve grouting defect nondestructive testing method based on impact elastic wave and machine learning |
CN108844856A (en) * | 2018-07-04 | 2018-11-20 | 四川升拓检测技术股份有限公司 | Based on elastic impact wave and the sleeve of machine learning grouting defect lossless detection method |
CN108918679A (en) * | 2018-07-11 | 2018-11-30 | 四川升拓检测技术股份有限公司 | Based on elastic wave and the prefabricated post sleeve of machine learning grouting lossless detection method |
CN109469112A (en) * | 2018-11-09 | 2019-03-15 | 北京市道路工程质量监督站 | Pile defect severity automatic identifying method based on support vector machines |
CN110440728A (en) * | 2019-05-31 | 2019-11-12 | 特斯联(北京)科技有限公司 | A kind of structural safety monitoring method and system detecting echo intellectual analysis |
CN110455678A (en) * | 2019-09-07 | 2019-11-15 | 北京市政建设集团有限责任公司 | A kind of packaged type bridges pier stud node Grouted density detection method |
CN110608066A (en) * | 2019-10-10 | 2019-12-24 | 中国五冶集团有限公司 | Detection system for tunnel grouting depth |
CN111238997B (en) * | 2020-02-12 | 2021-07-27 | 江南大学 | On-line measurement method for feed density in crude oil desalting and dewatering process |
CN111238997A (en) * | 2020-02-12 | 2020-06-05 | 江南大学 | On-line measurement method for feed density in crude oil desalting and dewatering process |
CN112525467A (en) * | 2020-11-26 | 2021-03-19 | 山东科技大学 | Impact damage area identification method and device suitable for cantilever beam |
CN112525467B (en) * | 2020-11-26 | 2022-09-13 | 山东科技大学 | Impact damage area identification method and device suitable for cantilever beam |
CN114137090A (en) * | 2021-10-27 | 2022-03-04 | 郑州大学 | Grouting compactness identification method and system based on RF-GA-SVM model and storage medium |
CN114018800A (en) * | 2021-10-29 | 2022-02-08 | 福建工程学院 | Device and method for measuring grouting compactness of prestressed duct |
CN114018800B (en) * | 2021-10-29 | 2023-06-30 | 福建工程学院 | Device and method for measuring grouting compactness of prestressed duct |
CN114894897A (en) * | 2022-05-11 | 2022-08-12 | 郑州大学 | Sleeve grouting defect nondestructive detection method and device based on one-dimensional convolutional neural network and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN106990018B (en) | 2019-09-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106990018B (en) | A kind of prestressed concrete beam Grouted density intelligent identification Method | |
Holford et al. | A new methodology for automating acoustic emission detection of metallic fatigue fractures in highly demanding aerospace environments: An overview | |
CN105929024B (en) | Concrete defect intellectualized detection and quantitative identification method | |
Ijjeh et al. | Full wavefield processing by using FCN for delamination detection | |
Lv et al. | Steel corrosion prediction based on support vector machines | |
Qiao et al. | Waveform fractal dimension for mode shape-based damage identification of beam-type structures | |
Zheng et al. | Monitor concrete moisture level using percussion and machine learning | |
Zhang et al. | Onset detection of ultrasonic signals for the testing of concrete foundation piles by coupled continuous wavelet transform and machine learning algorithms | |
KR20190080712A (en) | Methods for differentiation of earthquake signal and prediction of earthquake intensity using randomly generated artificial seismic training data for an arbitrary zone | |
Lai et al. | An evaluation of Mahalanobis Distance and grey relational analysis for crack pattern in concrete structures | |
Jiang et al. | A hybrid data-fusion system using modal data and probabilistic neural network for damage detection | |
Awadallah et al. | Effect and detection of cracks on small wind turbine blade vibration using special Kriging analysis of spectral shifts | |
CN101706355A (en) | NExT/ARMA-based structural response analysis method | |
Alvanitopoulos et al. | Seismic intensity feature construction based on the Hilbert–Huang transform | |
Shu et al. | A multi-task learning-based automatic blind identification procedure for operational modal analysis | |
Yuan et al. | An improved time-frequency analysis method for structural instantaneous frequency identification based on generalized S-transform and synchroextracting transform | |
Yu et al. | Automated health condition diagnosis of in situ wood utility poles using an intelligent non-destructive evaluation (NDE) framework | |
CN116401571A (en) | Concrete filled steel tube abnormal shape void identification method based on knocking sound wave and MiniRoccket | |
CN111443131B (en) | Method for detecting grouting compactness of steel bar sleeve | |
CN113468804B (en) | Underground pipeline identification method based on matrix bundles and deep neural network | |
Tang et al. | Explainable deep learning based ultrasonic guided wave pipe crack identification method | |
Vy et al. | Damage localization using acoustic emission sensors via convolutional neural network and continuous wavelet transform | |
García-Fernández et al. | A review on fatigue monitoring of structures | |
Katam et al. | A review on structural health monitoring: past to present | |
Diao et al. | Structural damage identification based on variational mode decomposition–Hilbert transform and CNN |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190910 |