CN113933195A - Concrete compressive strength prediction method and system based on image digital processing - Google Patents

Concrete compressive strength prediction method and system based on image digital processing Download PDF

Info

Publication number
CN113933195A
CN113933195A CN202111197121.6A CN202111197121A CN113933195A CN 113933195 A CN113933195 A CN 113933195A CN 202111197121 A CN202111197121 A CN 202111197121A CN 113933195 A CN113933195 A CN 113933195A
Authority
CN
China
Prior art keywords
concrete
data
matrix
training
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111197121.6A
Other languages
Chinese (zh)
Inventor
要东明
黄启云
刘伟杰
张传海
谢景锋
冯梓豪
吴红细
谭艺炬
杨思宇
黄景坛
陈衣盈
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Nonferrous Industry Building Quality Inspection Station Co ltd
Original Assignee
Guangdong Nonferrous Industry Building Quality Inspection Station Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Nonferrous Industry Building Quality Inspection Station Co ltd filed Critical Guangdong Nonferrous Industry Building Quality Inspection Station Co ltd
Priority to CN202111197121.6A priority Critical patent/CN113933195A/en
Publication of CN113933195A publication Critical patent/CN113933195A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
    • G01N3/40—Investigating hardness or rebound hardness
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • 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
    • 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)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Immunology (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Molecular Biology (AREA)
  • Pathology (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to the field of artificial intelligence, in particular to a concrete compressive strength prediction method and a system based on image processing, wherein the method comprises the following steps: converting the image display brightness of the concrete section into a numerical matrix, wherein the number size in the matrix reflects the brightness of the concrete section image to obtain matrix data of the concrete section image; taking two opposite planes of a concrete sample, and measuring a rebound value to obtain rebound value data; carrying out normalization processing on matrix data and rebound value data of the concrete section picture, dividing the matrix data and the rebound value data into a training set and a testing set, and establishing and training a neural network learning prediction model; and inputting the test set data into the learning prediction model to predict the target value of the test set. The invention adopts a nondestructive detection mode, determines parameters such as the compressive strength of the concrete by utilizing the characteristic that different materials of the concrete section display different brightness on an image, and has the advantages of rapid detection and low cost.

Description

Concrete compressive strength prediction method and system based on image digital processing
Technical Field
The invention relates to the field of machine learning and artificial intelligence detection, in particular to a concrete compressive strength prediction method and system based on image processing.
Background
The strength of concrete is significantly affected by various environmental factors such as the surrounding environment, temperature and humidity. In addition, various quality problems may occur during construction due to temperature variations, poor compaction, careless construction, and the like. In view of these problems, researchers have generally suggested measuring the compressive strength of concrete by performing destructive testing on a concrete core extracted from a structure for more accurate diagnosis. Extraction of concrete cores is a useful method to accurately estimate compressive strength. However, this method also involves problems of time and cost.
Disclosure of Invention
In order to solve the problems in concrete detection, the invention provides a concrete compressive strength prediction method and system based on image processing.
The invention provides the following technical scheme: the concrete compressive strength prediction method based on image digital processing comprises the following steps:
step 1, converting the image display brightness of the concrete section into a numerical matrix, wherein the number size in the matrix reflects the brightness of the concrete section image to obtain matrix data of the concrete section image;
step 2, taking two opposite planes of the concrete sample, and measuring the rebound value to obtain the rebound value data;
step 3, carrying out normalization processing on the matrix data and the rebound value data of the concrete section picture;
step 4, dividing the data obtained after normalization into a training set and a testing set, and establishing a neural network learning prediction model;
and 5, training the neural network learning prediction model according to the training set data, checking and evaluating the learning prediction model, inputting the test set data into the learning prediction model, and predicting the target value of the test set to obtain the concrete rebound value prediction model value.
Correspondingly, the invention discloses a concrete compressive strength prediction system based on image digital processing, which comprises:
the numerical matrix conversion module is used for converting the image display brightness of the concrete section into a numerical matrix, and the number size in the matrix reflects the brightness of the concrete section image to obtain matrix data of the concrete section image;
the rebound value measuring module is used for measuring the rebound value of the concrete sample on two opposite planes to obtain rebound value data;
the normalization processing module is used for performing normalization processing on the matrix data and the rebound value data of the concrete section picture;
the neural network model building module is used for dividing the data obtained after the normalization processing into a training set and a testing set and building a neural network learning prediction model;
and the prediction module is used for training the neural network learning prediction model according to the training set data, checking and evaluating the learning prediction model, inputting the test set data into the learning prediction model, and predicting the target value of the test set to obtain the concrete rebound value prediction module value.
Compared with the prior art, the invention has the following beneficial effects:
the method adopts a machine learning method to predict the concrete strength, replaces the traditional method for measuring the concrete strength through a concrete proportioning maintenance experiment, is a nondestructive testing mode, and saves raw materials, a large amount of labor and time; the characteristics that different materials of the concrete section display different brightness on an image are utilized, parameters such as the compressive strength of the concrete are determined by combining the image processing method and the artificial neural network method, the mechanical property of the concrete is detected by a non-destructive method, and the method has the advantages of being rapid in detection and low in cost.
Drawings
FIG. 1 is a flow chart of a prediction method according to the present invention;
FIG. 2 is a schematic diagram of a prediction system according to the present invention;
FIG. 3 is a top view of the camera bellows apparatus;
FIG. 4 is a schematic flow chart of the operation of the prediction model in the embodiment of the present invention;
FIG. 5 is a schematic diagram of gridding an image according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating the digitization of an image according to an embodiment of the invention;
wherein: 1-dark box outer shell; 2-an imaging system; 3-a lighting system; 4-a sample to be tested; 5-a test bed; 6-processor and memory system.
Detailed Description
Embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form a part hereof, and which together with the embodiments of the invention serve to explain the principles of the invention and not to limit its scope.
Examples
The embodiment provides a concrete compressive strength prediction method based on image processing, as shown in fig. 1-6, the method includes the following steps:
step 1, converting the acquired concrete section picture into a digital form, namely converting the picture display brightness of the concrete section into a numerical matrix, wherein the digital size in the matrix reflects the brightness of the concrete section picture, and the matrix data of the concrete section picture is obtained. The specific implementation process is as follows:
(1) taking a plurality of samples of concrete sections;
in specific implementation, a concrete section sample is obtained in the following manner: a concrete cutting machine is used for intercepting a section of concrete sample, and the upper surface and the lower surface of the sample are ensured to be parallel.
(2) Putting the samples one by one on a test bed positioned in a black light-tight dark box, placing four light sources with proper light intensity at diagonal positions in the dark box, turning on the four light sources, and irradiating the light rays of the light sources on the section of the concrete;
in this example, the test stand is 30cm × 30cm × 30cm, and the dark box is 100cm × 100cm × 100 cm.
(3) Shooting the concrete section by using a photographic device placed in the center of the top in the dark box to obtain a concrete section picture; the camera is externally connected to a processing device, and the processing device can be a computer.
(4) Dividing the concrete section picture into a plurality of equally divided grids on a processing device externally connected with the photographic device through image processing software, and carrying out digital matrix processing on the grids according to different chromaticity of each grid to obtain a corresponding numerical matrix. The grid chromaticity is related to the adding proportion of materials such as aggregate, cement, water cement ratio, water reducing agent and mineral admixture in the concrete, the adding proportion of the materials determines the compressive strength of the concrete, therefore, the grid chromaticity is correspondingly related to the compressive strength of the concrete, and the grid chromaticity can be quantized through digital matrix processing to obtain a corresponding numerical matrix.
In the embodiment, a plurality of samples of the concrete section are sequentially placed on a test bed in a dark box, and after necessary setting of an imaging system is completed, the concrete section is photographed to obtain a sample image of the concrete section; and drawing 400 grids on the obtained sample image, and carrying out digital matrix processing on the sample image according to the difference of brightness on the sample image.
The digital matrix processing method is that each row in the sampling image (i.e. the concrete section picture) is taken as an input vector X, and the rows of the input vector X are respectively:
Figure BDA0003303466130000031
where M is the number of columns in the sample image data and N is the number of rows in the sample image data, and when some columns have less data than the column with the most data, the complement is made with 0, e.g.
Figure BDA0003303466130000032
In this embodiment, each column of the input vector X takes the following values:
Figure BDA0003303466130000033
when the number of data in a column is less than that of the column with the most number of data, complement by 0, e.g.
Figure BDA0003303466130000041
And 2, taking two opposite planes of a concrete sample, measuring the rebound value by adopting a method in the technical specification for detecting the compressive strength of the concrete by adopting a standard JGJ/T23-2011 rebound resilience method, taking 16 measuring points on one plane, measuring the rebound value, and converting the rebound value into the compressive strength Y corresponding to the concrete according to the technical specification for detecting the compressive strength of the concrete by adopting the national standard JGJ/T23-2011 rebound resilience method.
And 3, carrying out normalization processing on the matrix data of the concrete section picture obtained in the step 1.
And 4, dividing the data obtained after the normalization processing into a training set and a testing set, and establishing a BP neural network learning prediction model. When all data are divided into a training set and a test set, the test set accounts for 30-35% of the total number of samples; in this example, the test set accounts for 30% of the total number of samples.
In step 4, establishing a three-layer BP neural network based on a BP algorithm, wherein the three-layer BP neural network comprises an input layer, a hidden layer and an output layer; the number of hidden layer neuron nodes is as follows:
Figure BDA0003303466130000042
in the formula, P is the number of hidden layer neuron nodes, m is the number of output layer neurons, n is the number of input layer neurons, and a is a constant between 1 and 10. And setting the learning rate alpha, the training times gamma and the training target error, and training and verifying the neural network. During training, learning samples are input into a BP neural network, then the error between the output value of the neural network and an evaluation target value is calculated, and when the error is in an acceptable range (namely the error meets an expected value), a training error expression is as follows:
Figure BDA0003303466130000043
wherein A isiRepresenting the desired output value, BiRepresenting the output of the neural network model, K representing the number of data points in the training and testing data, X representing the neural network input data set in the training and testing data, Y representing the neural network output data set in the training and testing process, and λ being the training error. If the error does not meet the expected value, the connection weight is modified in the following way:
Figure BDA0003303466130000044
wherein
Figure BDA0003303466130000045
Is the gradient of the error function.
And 5, training the BP neural network learning prediction model according to the training set data, and storing the trained neural network learning prediction model on the equipment. And inspecting and evaluating the learning prediction model, inputting the data of the test set into the learning prediction model, and predicting the target value of the test set to obtain the predicted value of the compressive strength of the concrete.
In the embodiment, the total number of the concrete section pictures is 150, and 105 groups of data are used as a training set to train a prediction model; the 45 sets of data were used as test sets for evaluation of the prediction model. The neural network model meeting the prediction accuracy condition after training is the learning prediction model for predicting the concrete strength in the embodiment. Then, any concrete section image can be taken as input, and after digital processing, a prediction result, namely a prediction value of the concrete compressive strength, is obtained through a prediction model. The present embodiment compares and verifies the prediction accuracy with 10 sets of input data.
TABLE 1
Figure BDA0003303466130000051
As shown in table 1, in the present embodiment, the relative error between the predicted value and the actual value is less than 2.3%, which shows that the prediction error of the model in the present invention is small and the prediction effect is good.
The embodiment proves that the method has the advantages of high-efficiency and high-precision prediction effect, saves labor, materials and time cost compared with the traditional strength prediction method, and has great significance for the research of concrete strength prediction.
Based on the same inventive concept, the embodiment further provides a concrete compressive strength prediction system based on image processing, which includes:
the numerical matrix conversion module is used for converting the image display brightness of the concrete section into a numerical matrix, and the number size in the matrix reflects the brightness of the concrete section image to obtain matrix data of the concrete section image;
the rebound value measuring module is used for measuring the rebound value of the concrete sample on two opposite planes to obtain rebound value data;
the normalization processing module is used for performing normalization processing on the matrix data and the rebound value data of the concrete section picture;
the neural network model building module is used for dividing the data obtained after the normalization processing into a training set and a testing set and building a neural network learning prediction model;
and the prediction module is used for training the neural network learning prediction model according to the training set data, checking and evaluating the learning prediction model, inputting the test set data into the learning prediction model, and predicting the target value of the test set to obtain the concrete rebound value prediction module value.
The numerical matrix conversion module comprises a concrete section imaging device, the concrete section imaging device comprises a camera bellows, a test bed, lighting equipment and imaging equipment with a cache function, the test bed is located in a black and lightproof camera bellows, the lighting equipment is placed at the diagonal position in the camera bellows, the imaging equipment is placed in the camera bellows and is externally connected to processing equipment, and the processing equipment converts the image display brightness of the concrete section into a numerical matrix through image processing software.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.

Claims (8)

1. The concrete compressive strength prediction method based on image digital processing is characterized by comprising the following steps of:
step 1, converting the image display brightness of the concrete section into a numerical matrix, wherein the number size in the matrix reflects the brightness of the concrete section image to obtain matrix data of the concrete section image;
step 2, taking two opposite planes of the concrete sample, and measuring the rebound value to obtain the rebound value data;
step 3, carrying out normalization processing on the matrix data and the rebound value data of the concrete section picture;
step 4, dividing the data obtained after normalization into a training set and a testing set, and establishing a neural network learning prediction model;
and 5, training the neural network learning prediction model according to the training set data, checking and evaluating the learning prediction model, inputting the test set data into the learning prediction model, and predicting the target value of the test set to obtain the concrete rebound value prediction model value.
2. The method for predicting the compressive strength of concrete according to claim 1, wherein the step 1 comprises:
(1) taking a plurality of samples of concrete sections;
(2) putting the samples one by one on a test bed positioned in a black light-tight dark box, placing light sources with proper light intensity at diagonal positions in the dark box, turning on the light sources, and irradiating the light rays of the light sources on the section of the concrete;
(3) shooting a concrete section to obtain a concrete section picture;
(4) dividing the concrete section picture into a plurality of equally divided grids, and carrying out digital matrix processing on the grids according to different chromaticity of each grid to obtain corresponding numerical value matrixes.
3. The method for predicting concrete compressive strength according to claim 2, wherein the digitized matrix processing in step (4) is performed by taking each column in the concrete cross-sectional picture as an input vector X, and the columns of the input vector X are respectively:
Figure FDA0003303466120000011
where M is the number of columns in the sample image data and N is the number of rows in the sample image data, when data in some columnsIf the number is less than the column with the largest number of data, 0 is used for complement.
4. The concrete compressive strength prediction method of claim 1, wherein a three-layer BP neural network based on a BP algorithm is established in the step 4, and comprises an input layer, a hidden layer and an output layer; the number of hidden layer neuron nodes is as follows:
Figure FDA0003303466120000012
in the formula, P is the number of hidden layer neuron nodes, m is the number of output layer neurons, n is the number of input layer neurons, and a is a constant between 1 and 10.
5. The concrete compressive strength prediction method according to claim 4, wherein the learning rate α, the training times γ and the training target error are set in step 4, and the neural network is trained and verified; during training, after the learning sample is input into the neural network, the error between the output value of the neural network and the evaluation target value is calculated, and when the error meets the expected value, a training error expression is as follows:
Figure FDA0003303466120000021
wherein A isiRepresenting the desired output value, BiExpressing the output of a neural network model, K expressing the number of data points in training and testing data, X expressing a neural network input data set in the training and testing data, Y expressing a neural network output data set in the training and testing process, and lambda being a training error; if the error does not meet the expected value, the connection weight is modified in the following way:
Figure FDA0003303466120000022
wherein
Figure FDA0003303466120000023
Is the gradient of the error function.
6. Concrete compressive strength prediction system based on image digital processing is characterized by comprising:
the numerical matrix conversion module is used for converting the image display brightness of the concrete section into a numerical matrix, and the number size in the matrix reflects the brightness of the concrete section image to obtain matrix data of the concrete section image;
the rebound value measuring module is used for measuring the rebound value of the concrete sample on two opposite planes to obtain rebound value data;
the normalization processing module is used for performing normalization processing on the matrix data and the rebound value data of the concrete section picture;
the neural network model building module is used for dividing the data obtained after the normalization processing into a training set and a testing set and building a neural network learning prediction model;
and the prediction module is used for training the neural network learning prediction model according to the training set data, checking and evaluating the learning prediction model, inputting the test set data into the learning prediction model, and predicting the target value of the test set to obtain the concrete rebound value prediction module value.
7. The concrete compressive strength prediction system of claim 6, wherein the numerical matrix conversion module comprises a concrete section imaging device, the concrete section imaging device comprises a dark box, a test bed, an illumination device and an imaging device with a cache function, the test bed is located in the dark box which is black and light-tight, the illumination device is placed at a diagonal position in the dark box, the imaging device is placed in the dark box and is externally connected to the processing device, and the processing device converts the image display brightness of the concrete section into the numerical matrix through image processing software.
8. The coagulation of claim 6The system for predicting the compressive strength of the soil is characterized in that the method for processing the digital matrix in the numerical matrix conversion module is to take each column in a concrete section picture as an input vector X, and the columns of the input vector X are respectively as follows:
Figure FDA0003303466120000031
where M is the number of columns in the sample image data, N is the number of rows in the sample image data, and when the number of data in a column is less than the column with the largest number of data, the complement is performed with 0.
CN202111197121.6A 2021-10-14 2021-10-14 Concrete compressive strength prediction method and system based on image digital processing Pending CN113933195A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111197121.6A CN113933195A (en) 2021-10-14 2021-10-14 Concrete compressive strength prediction method and system based on image digital processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111197121.6A CN113933195A (en) 2021-10-14 2021-10-14 Concrete compressive strength prediction method and system based on image digital processing

Publications (1)

Publication Number Publication Date
CN113933195A true CN113933195A (en) 2022-01-14

Family

ID=79279346

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111197121.6A Pending CN113933195A (en) 2021-10-14 2021-10-14 Concrete compressive strength prediction method and system based on image digital processing

Country Status (1)

Country Link
CN (1) CN113933195A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114441351A (en) * 2022-01-28 2022-05-06 江苏瑞构新型材料有限公司 Method for detecting abrasion degree of rubber strip of sealing door
CN115268177A (en) * 2022-06-15 2022-11-01 华北水利水电大学 Simple and easy convenient concrete test block device of shooing
CN117470752A (en) * 2023-12-28 2024-01-30 广东省有色工业建筑质量检测站有限公司 Method for detecting prestress grouting content in steel pipe truss body

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002014039A (en) * 2000-04-24 2002-01-18 Shibaura Institute Of Technology Method and apparatus for measurement of percentage of moisture content of fine aggregate for concrete
CN103822922A (en) * 2014-02-11 2014-05-28 中国水利水电科学研究院 Method for rapidly determining the area content of aggregates/mortar in concrete slice
KR20200064485A (en) * 2018-11-29 2020-06-08 (주) 화승엑스윌 Concrete docking hose and measuring method for pressure resistance of the concrete docking hose
CN211453128U (en) * 2020-01-22 2020-09-08 广西世诚工程检测有限公司 Rotary type cement compression and bending resistance testing machine protection device
CN112684156A (en) * 2021-01-06 2021-04-20 汉谷云智(武汉)科技有限公司 Concrete strength prediction method based on deep learning

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002014039A (en) * 2000-04-24 2002-01-18 Shibaura Institute Of Technology Method and apparatus for measurement of percentage of moisture content of fine aggregate for concrete
CN103822922A (en) * 2014-02-11 2014-05-28 中国水利水电科学研究院 Method for rapidly determining the area content of aggregates/mortar in concrete slice
KR20200064485A (en) * 2018-11-29 2020-06-08 (주) 화승엑스윌 Concrete docking hose and measuring method for pressure resistance of the concrete docking hose
CN211453128U (en) * 2020-01-22 2020-09-08 广西世诚工程检测有限公司 Rotary type cement compression and bending resistance testing machine protection device
CN112684156A (en) * 2021-01-06 2021-04-20 汉谷云智(武汉)科技有限公司 Concrete strength prediction method based on deep learning

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
宁夏回族自治区住房和城乡建设厅 等: "宁夏回族自治区地方标准 回弹法检测高强混凝土抗压强度技术规程 DB64/T 1647-2019", pages: 1 - 15 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114441351A (en) * 2022-01-28 2022-05-06 江苏瑞构新型材料有限公司 Method for detecting abrasion degree of rubber strip of sealing door
CN114441351B (en) * 2022-01-28 2022-10-28 江苏瑞构新型材料有限公司 Method for detecting abrasion degree of rubber strip of sealing door
CN115268177A (en) * 2022-06-15 2022-11-01 华北水利水电大学 Simple and easy convenient concrete test block device of shooing
CN117470752A (en) * 2023-12-28 2024-01-30 广东省有色工业建筑质量检测站有限公司 Method for detecting prestress grouting content in steel pipe truss body
CN117470752B (en) * 2023-12-28 2024-05-07 广东省有色工业建筑质量检测站有限公司 Method for detecting prestress grouting content in steel pipe truss body

Similar Documents

Publication Publication Date Title
CN113933195A (en) Concrete compressive strength prediction method and system based on image digital processing
Dogan et al. Concrete compressive strength detection using image processing based new test method
TW202004661A (en) Classification system and classification method of autoantibody immunofluorescence image
Kabir Imaging-based detection of AAR induced map-crack damage in concrete structure
CN107742031B (en) Displacement experiment artificial rock core analysis preparation method based on experiment and mathematical algorithm
CN112634292A (en) Asphalt pavement crack image segmentation method based on deep convolutional neural network
CN103761537B (en) Image classification method based on low-rank optimization feature dictionary model
CN112215525B (en) Lake and reservoir water quality inversion and visual evaluation method
CN113108918B (en) Method for inverting air temperature by using thermal infrared remote sensing data of polar-orbit meteorological satellite
KR20190130257A (en) Prediction method for compression strength of concrete structure based on deep convolutional neural network algorithm and prediction system using the method
CN112149356A (en) Method, device, equipment and medium for predicting structural crack propagation path
CN114324336B (en) Nondestructive measurement method for biomass of soybean in whole growth period
Liu et al. Deep learning in frequency domain for inverse identification of nonhomogeneous material properties
Deng et al. Internal defect detection of structures based on infrared thermography and deep learning
CN115880257A (en) Method for rapidly predicting intensity of ocean porous reef limestone
CN112819813B (en) Intelligent underground pipeline identification method and device and storage medium
CN116030292A (en) Concrete surface roughness detection method based on improved ResNext
CN110473183B (en) Evaluation method, device, electronic equipment and medium for visible light full-link simulation image
CN111241725A (en) Structure response reconstruction method for generating countermeasure network based on conditions
CN111932642A (en) Method, device and equipment for measuring and calculating volume of structural crack and storage medium
KR20210155191A (en) Method of performing defect inspection of inspection object at high speed and apparatuses performing the same
CN117892590B (en) Concrete dam damage identification and safety assessment method based on crack intelligent identification and finite element inversion
Dekhterev et al. Diagnostics of defects of monolithic reinforced concrete structures using neural network technologies
CN111291490B (en) Nonlinear mapping intelligent modeling method for structure multi-scale heterogeneous response
CN110288573A (en) A kind of mammalian livestock illness automatic testing method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination