CN115100176B - Reinforced concrete column damage assessment method based on neural network - Google Patents
Reinforced concrete column damage assessment method based on neural network Download PDFInfo
- Publication number
- CN115100176B CN115100176B CN202210825670.1A CN202210825670A CN115100176B CN 115100176 B CN115100176 B CN 115100176B CN 202210825670 A CN202210825670 A CN 202210825670A CN 115100176 B CN115100176 B CN 115100176B
- Authority
- CN
- China
- Prior art keywords
- damage
- neural network
- reinforced concrete
- model
- concrete column
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000006378 damage Effects 0.000 title claims abstract description 90
- 239000011150 reinforced concrete Substances 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 17
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 43
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 239000002360 explosive Substances 0.000 claims abstract description 16
- 238000012360 testing method Methods 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000005474 detonation Methods 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000007547 defect Effects 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 2
- 230000009525 mild injury Effects 0.000 description 2
- 230000009526 moderate injury Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000009528 severe injury Effects 0.000 description 2
- 208000037974 severe injury Diseases 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 231100000809 Damage Assessment Model Toxicity 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004567 concrete Substances 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a reinforced concrete column damage assessment method based on a neural network, which comprises the following steps: s1, establishing a damage data set of a reinforced concrete column model under explosive load by a finite element method; s2, sending the damage data set into the built convolutional neural network model for training, and storing the optimal training weight and the corresponding convolutional neural network model; s3, inputting the obtained target object photo into a stored convolutional neural network model for damage evaluation, and outputting a damage evaluation result, thereby overcoming the defects of time and labor waste, and insufficient accuracy and safety of a manual evaluation method based on expert experience.
Description
Technical Field
The invention relates to the technical field of neural networks, in particular to a reinforced concrete column damage assessment method based on a neural network.
Background
The reinforced concrete column is the most basic vertical bearing member in various engineering structures such as buildings, bridges, hydraulic engineering and the like, and the damage degree affects the local and the whole safety of the structure. Traditional reinforced concrete column damage detection mainly relies on-site investigation, highly relies on engineering experience, wastes time and labor, and is insufficient in accuracy and reliability. In particular, for post-earthquake field damage evaluation, the safety problem is more serious due to the possible subsequent aftershocks.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the reinforced concrete column damage evaluation method based on the neural network, which can directly evaluate the damage result of the reinforced concrete column and overcome the defects of time and labor waste, and insufficient accuracy and safety of the manual evaluation method based on expert experience.
The invention provides a reinforced concrete column damage assessment method based on a neural network, which comprises the following steps:
s1, establishing a damage data set of a reinforced concrete column model under explosive load by a finite element method;
S2, the damage data set is sent into a built convolutional neural network model for training, and the optimal training weight and the corresponding convolutional neural network model are stored;
And S3, inputting the obtained target object photo into a stored convolutional neural network model for damage evaluation, and outputting a damage evaluation result.
Preferably, the convolutional neural network model includes:
the backbone network is used for extracting image features and calculating the volume loss rate;
and the damage judging network is used for simulating the functional relation between the volume loss rate and the damage and outputting the damage grade.
Preferably, the backbone network employs MobilenetV-Small.
Preferably, the impairment judgment network comprises two fully connected linear layers.
Preferably, the step S1 specifically includes:
constructing a reinforced concrete column and an explosive finite element model;
Adjusting the equivalent weight and the detonation point of the explosive, and calculating a damaged reinforced concrete column model under the explosive load based on the reinforced concrete column and the explosive finite element model;
Applying an axial compressive load to the damaged reinforced concrete column model, and calculating the ultimate bearing capacity of the damaged reinforced concrete column model;
Calculating the ratio of the ultimate bearing capacity of the damaged reinforced concrete column model to the vertical ultimate bearing capacity of the complete reinforced concrete column model to obtain a damage value;
Selecting a typical angle, and acquiring image data of a damaged reinforced concrete column model;
And classifying the acquired image data of the damaged reinforced concrete column model according to the damage value to obtain a damage data set.
Preferably, the step S1 further includes:
And processing the classified image data of the damaged reinforced concrete column model by using a preset edge detection algorithm.
Preferably, the step S1 further includes:
And dividing the damage data set in proportion to obtain a training set, a verification set and a test set.
Preferably, the step S2 specifically includes:
sending the training set and the verification set into a built convolutional neural network model for preliminary training;
fusing the training set and the verification set, and sending the training set and the verification set into a preliminarily trained convolutional neural network model for further training, and obtaining a predicted damage result;
And sending the test set into a convolutional neural network model after further training, selecting optimal model parameters according to the accuracy and loss of the convolutional neural network model after further training on the test set, and storing the optimal training weight and the corresponding convolutional neural network model.
The invention has the beneficial effects that:
the damage data set is established through the finite element method, the convolutional neural network model is built, the model is trained through the damage data set, the target object picture is input into the training model for damage evaluation, the damage degree of the reinforced concrete column is directly predicted, and the defects that the manual evaluation method based on expert experience is time-consuming and labor-consuming, and is insufficient in accuracy and safety are overcome. And the convolutional neural network model comprises a main network and a damage judging network, so that the damage of the reinforced concrete column can be calculated according to the volume loss rate of the input image, and the interpretability of the damage evaluation result is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
FIG. 1 is a schematic flow chart of a first embodiment of the present invention;
FIG. 2 is a flow chart of a second embodiment of the present invention;
FIG. 3a is a picture before processing by the Canny edge detection algorithm;
FIG. 3b is a graph after being processed by the Canny edge detection algorithm;
FIG. 4 is a schematic diagram of a convolutional neural network model according to a second embodiment of the present invention;
fig. 5a is a photograph of a mild injury;
FIG. 5b is a photograph of moderate injury;
fig. 5c is a photograph of a severe injury.
Detailed Description
Embodiments of the technical scheme of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and thus are merely examples, and are not intended to limit the scope of the present invention.
It is noted that unless otherwise indicated, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs.
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Embodiment one:
As shown in fig. 1, the embodiment of the invention provides a reinforced concrete column damage assessment method based on a neural network, which comprises the following steps:
s1, establishing a damage data set of a reinforced concrete column model under explosive load by a finite element method;
S2, sending the damage data set into the built convolutional neural network model for training, and storing the optimal training weight and the corresponding convolutional neural network model;
And S3, inputting the obtained target object photo into a stored convolutional neural network model for damage evaluation, and outputting a damage evaluation result.
Embodiment two:
as shown in fig. 2, an embodiment of the present invention provides a method for evaluating damage to a reinforced concrete column based on a neural network, including:
Step one: modeling the concrete, the steel bars, the air domain and the explosive through HYPERMESH software to obtain a reinforced concrete column and an explosive finite element model;
step two: adjusting the equivalent weight and the detonation point of the explosive, and introducing the finite element model into LS-DYNA software for calculation to obtain a reinforced concrete column model with damage;
Step three: and re-introducing HYPERMESH the obtained damaged reinforced concrete column model into software, adding a rigid pressing plate model for applying axial pressure load, re-introducing LS-DYNA software, and calculating the calculated ratio of the ultimate bearing capacity of the damaged reinforced concrete column model to the vertical ultimate bearing capacity of the complete reinforced concrete column model to obtain a damage value. Automatic adjustment of explosive equivalent and detonation points and interface connection of HYPERMESH and LS-DYNA are realized by using a Python program;
step four: importing a damaged reinforced concrete column model into HYPERMESH software, selecting a typical angle, acquiring image data of the damaged reinforced concrete column model, writing a Python program, and calling HYPERMESH interface to perform batch operation;
step five: classifying the obtained image data of the damaged reinforced concrete column model according to the calculated damage value;
Step six: and processing the image data of the damaged reinforced concrete column model by using a Canny algorithm to obtain a damaged data set, and dividing the damaged data set proportionally to obtain a training set, a verification set and a test set. Because the two-dimensional image acquired in the finite element model may not restore the imaging effect of the structure in the real environment, such as reflection, shadow and the like, the embodiment of the invention adopts the Canny algorithm to extract the edge information of the image data, acquires the edge line of the image, and then carries out subsequent operation, so that the convolutional neural network model obtained by training has certain applicability in the actual situation, as shown in fig. 3a and 3 b.
Step seven: adjusting parameters of a reinforced concrete column model with damage, sending a damage data set into a convolutional neural network for training, and obtaining a predicted damage result; specifically, sending the damage data set into a convolutional neural network for training, and obtaining a predicted damage result includes:
the training batch size is set to 128, the training set and the verification set are sent into the built convolutional neural network model for preliminary training, the iteration number is set to 30, and preliminary learning is carried out;
And fusing the training set and the verification set, sending the training set and the verification set into the preliminarily trained convolutional neural network model, further training, obtaining a predicted damage result, setting the iteration times to be 20 times, and further learning. The preliminary training phase uses Adam as an optimizer, the preliminary learning rate is 1×10 -3, the learning rate is reduced by half when the neural network model loses more than 3 times on the validation set without drop, β 1 and β 2 are set to 0.9 and 0.999, and ε is set to 1×10 -8. The further training phase uses SGDM as an optimizer, the initial learning rate is 1×10 -4, the learning rate is reduced by half when the neural network model loses more than 3 times on the validation set without dropping, and β is set to 0.9.
Step eight: sending the test set into a further trained convolutional neural network model, selecting optimal model parameters according to the accuracy and loss of the further trained convolutional neural network model on the test set, and storing optimal training weights and corresponding convolutional neural network models;
step nine: and calling the stored convolutional neural network model, shooting a target object photo, removing the background of the target object photo through an image processing tool such as PS, and sending the target object photo into the convolutional neural network model after further training to perform damage judgment and evaluation, so as to obtain a damage evaluation result.
In the embodiment of the application, the convolutional neural network model comprises a backbone network and a damage judging network, as shown in fig. 4, the backbone network is used for extracting image features to calculate the volume loss rate, and the damage judging network is used for simulating the functional relation between the volume loss rate and the damage and outputting the damage grade. The backbone network is selected MobilenetV-Small, the damage judging network is composed of two fully-connected linear layers, the input dimension of the first layer is 1, the output dimension is 64, the input dimension of the second layer is 64, and the output dimension is 3. When the error calculation is carried out in the training stage, double errors are adopted, the volume loss rate error and the damage level error are simultaneously considered, the calculation method of the volume loss rate error adopts average absolute error (Mean Absolute Error, MAE), the calculation result is multiplied by coefficient alpha, the calculation method of the damage level error adopts cross entropy (Cross Entropy), and the two errors are added to obtain the final error. When the method is used for optimizing the network, the volume loss error and the damage classification error are combined, so that the calculation precision of the image volume loss rate and the damage classification precision are balanced, and the whole network is balanced. Meanwhile, the network model is more in line with the pushing process from the volume loss rate to the damage level, and the classification effect is improved.
By adopting the embodiment of the invention to carry out simulation experiments, the convolutional neural network model operates under a preset platform, and specific parameters of the platform are CPU: intel (R) Xeon (R) Gold 6248@2.5Ghz ×80; RAM:128GB; GPU: geForce RTX 3090; operating system: ubuntu 18.04.5LTS. The alpha parameter of the model is set to 2 in the first stage and 10 in the second stage. The convolutional neural network model stored in the embodiment of the invention can obtain 99.71% of accuracy on the test set, and the structural damage assessment time based on the damage assessment model of the convolutional neural network model is far smaller than that of the traditional finite element method, so that the method is more suitable for quickly judging structural damage in emergency.
To test the application of the trained convolutional neural network model in reality, the 3D printing technique was used to print one of the mild, moderate and severe injury models, and fig. 5a, 5b and 5c show three sample photographs, all of which have their background removed by image processing. The test photographs were taken at different angles and 24 were taken altogether. The test photo is sent to the optimal model obtained by training, the final accuracy is 70.83%, and the convolutional neural network model stored in the embodiment of the invention can be considered to have a certain application value in practical samples.
According to the reinforced concrete column damage assessment method based on the neural network, the damage data set is established through the finite element method, the convolutional neural network model is built, the model is trained through the damage data set, the target object picture is input into the model for damage assessment, the damage degree of the reinforced concrete column can be directly predicted, and the defects of time and labor waste, and insufficient accuracy and safety of a manual assessment method based on expert experience are overcome. In the embodiment of the invention, the convolutional neural network model comprises a main network and a damage judging network, so that the damage of the reinforced concrete column can be calculated according to the volume loss rate of the input image, and the interpretability of the damage evaluation result is improved.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (7)
1. The reinforced concrete column damage assessment method based on the neural network is characterized by comprising the following steps of:
s1, establishing a damage data set of a reinforced concrete column model under explosive load by a finite element method;
S2, the damage data set is sent into a built convolutional neural network model for training, and the optimal training weight and the corresponding convolutional neural network model are stored; the convolutional neural network model includes:
the backbone network is used for extracting image features and calculating the volume loss rate;
The damage judging network is used for simulating the functional relation between the volume loss rate and the damage and outputting the damage grade;
And S3, inputting the obtained target object photo into a stored convolutional neural network model for damage evaluation, and outputting a damage evaluation result.
2. The method for evaluating damage to reinforced concrete columns based on a neural network according to claim 1, wherein the backbone network is MobilenetV-Small.
3. The method for evaluating damage to reinforced concrete columns based on a neural network according to claim 1, wherein the damage judgment network comprises two fully connected linear layers.
4. The method for evaluating damage to reinforced concrete columns based on the neural network according to claim 1, wherein the step S1 specifically comprises:
constructing a reinforced concrete column and an explosive finite element model;
Adjusting the equivalent weight and the detonation point of the explosive, and calculating a damaged reinforced concrete column model under the explosive load based on the reinforced concrete column and the explosive finite element model;
Applying an axial compressive load to the damaged reinforced concrete column model, and calculating the ultimate bearing capacity of the damaged reinforced concrete column model;
Calculating the ratio of the ultimate bearing capacity of the damaged reinforced concrete column model to the vertical ultimate bearing capacity of the complete reinforced concrete column model to obtain a damage value;
Selecting a typical angle, and acquiring image data of a damaged reinforced concrete column model;
And classifying the acquired image data of the damaged reinforced concrete column model according to the damage value to obtain a damage data set.
5. The method for evaluating damage to reinforced concrete columns based on neural network according to claim 4, wherein the step S1 further comprises:
And processing the classified image data of the damaged reinforced concrete column model by using a preset edge detection algorithm.
6. The method for evaluating damage to reinforced concrete columns based on the neural network according to claim 1, wherein,
The step S1 further includes:
And dividing the damage data set in proportion to obtain a training set, a verification set and a test set.
7. The method for evaluating damage to reinforced concrete columns based on neural network according to claim 6, wherein the step S2 specifically comprises:
sending the training set and the verification set into a built convolutional neural network model for preliminary training;
fusing the training set and the verification set, and sending the training set and the verification set into a preliminarily trained convolutional neural network model for further training, and obtaining a predicted damage result;
And sending the test set into a convolutional neural network model after further training, selecting optimal model parameters according to the accuracy and loss of the convolutional neural network model after further training on the test set, and storing the optimal training weight and the corresponding convolutional neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210825670.1A CN115100176B (en) | 2022-07-14 | 2022-07-14 | Reinforced concrete column damage assessment method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210825670.1A CN115100176B (en) | 2022-07-14 | 2022-07-14 | Reinforced concrete column damage assessment method based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115100176A CN115100176A (en) | 2022-09-23 |
| CN115100176B true CN115100176B (en) | 2024-05-14 |
Family
ID=83297041
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210825670.1A Active CN115100176B (en) | 2022-07-14 | 2022-07-14 | Reinforced concrete column damage assessment method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115100176B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117408139A (en) * | 2023-10-09 | 2024-01-16 | 东南大学 | Image recognition-based concrete member residual bearing performance quantitative prediction method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182586A (en) * | 2014-08-25 | 2014-12-03 | 西南科技大学 | Assessment system and method of blasting damage in reinforced concrete building structure |
| CN106407548A (en) * | 2016-09-13 | 2017-02-15 | 同济大学 | Anti-collapse optimization design method of reinforced concrete shear wall structure |
| CN109164117A (en) * | 2018-10-24 | 2019-01-08 | 东南大学 | Based on-bituminous concrete damage forecast the method for mortar interface Fracture of gathering materials |
| CN111159839A (en) * | 2019-05-27 | 2020-05-15 | 南京理工大学 | Method for efficiently simulating dynamic response of reinforced concrete member under explosive load |
| CN112668078A (en) * | 2020-12-24 | 2021-04-16 | 青岛理工大学 | Method for identifying damage of rusted reinforced concrete beam after fire disaster |
| CN113096088A (en) * | 2021-04-07 | 2021-07-09 | 浙江大学 | Concrete structure detection method based on deep learning |
| CN113450333A (en) * | 2021-06-30 | 2021-09-28 | 哈尔滨工业大学 | Machine learning-based reinforced concrete column earthquake damage degree evaluation method |
| CN113850024A (en) * | 2021-10-09 | 2021-12-28 | 长安大学 | Machine learning-based reinforced concrete member anti-collision performance prediction method |
| CN114722858A (en) * | 2022-03-09 | 2022-07-08 | 浙江大学 | Safety assessment method for prestressed concrete structure |
-
2022
- 2022-07-14 CN CN202210825670.1A patent/CN115100176B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182586A (en) * | 2014-08-25 | 2014-12-03 | 西南科技大学 | Assessment system and method of blasting damage in reinforced concrete building structure |
| CN106407548A (en) * | 2016-09-13 | 2017-02-15 | 同济大学 | Anti-collapse optimization design method of reinforced concrete shear wall structure |
| CN109164117A (en) * | 2018-10-24 | 2019-01-08 | 东南大学 | Based on-bituminous concrete damage forecast the method for mortar interface Fracture of gathering materials |
| CN111159839A (en) * | 2019-05-27 | 2020-05-15 | 南京理工大学 | Method for efficiently simulating dynamic response of reinforced concrete member under explosive load |
| CN112668078A (en) * | 2020-12-24 | 2021-04-16 | 青岛理工大学 | Method for identifying damage of rusted reinforced concrete beam after fire disaster |
| CN113096088A (en) * | 2021-04-07 | 2021-07-09 | 浙江大学 | Concrete structure detection method based on deep learning |
| CN113450333A (en) * | 2021-06-30 | 2021-09-28 | 哈尔滨工业大学 | Machine learning-based reinforced concrete column earthquake damage degree evaluation method |
| CN113850024A (en) * | 2021-10-09 | 2021-12-28 | 长安大学 | Machine learning-based reinforced concrete member anti-collision performance prediction method |
| CN114722858A (en) * | 2022-03-09 | 2022-07-08 | 浙江大学 | Safety assessment method for prestressed concrete structure |
Non-Patent Citations (1)
| Title |
|---|
| 基于实测频率的钢筋混凝土柱爆炸损伤快速评估方法;师燕超 等;《建筑结构学报》;20211130;第42卷(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115100176A (en) | 2022-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259930B (en) | General target detection method of self-adaptive attention guidance mechanism | |
| CN109934761B (en) | JPEG image steganalysis method based on convolutional neural network | |
| CN113450333B (en) | Machine learning-based reinforced concrete column earthquake damage degree evaluation method | |
| CN108230278B (en) | Image raindrop removing method based on generation countermeasure network | |
| CN111178206B (en) | Building embedded part detection method and system based on improved YOLO | |
| Zou et al. | Multicategory damage detection and safety assessment of post‐earthquake reinforced concrete structures using deep learning | |
| CN110969183B (en) | Method and system for determining damage degree of target object according to image data | |
| CN115100176B (en) | Reinforced concrete column damage assessment method based on neural network | |
| CN113868750B (en) | Building earthquake damage and residual capacity evaluation method based on deep machine learning | |
| CN111209620B (en) | Method for predicting residual bearing capacity and crack propagation path of crack-containing structure | |
| CN106023154A (en) | Multi-temporal SAR image change detection method based on dual-channel convolutional neural network (CNN) | |
| CN112950570B (en) | Crack detection method combining deep learning and dense continuous central point | |
| CN111523616A (en) | Coarse-grained soil filler grading identification method based on convolutional neural network and application system | |
| CN114596266B (en) | Concrete crack detection method based on ConcreteCrackSegNet model | |
| CN111597932A (en) | Road crack image identification method, device and system based on convolutional neural network | |
| CN115115924A (en) | Concrete image crack type rapid intelligent identification method based on IR7-EC network | |
| CN114972759A (en) | Remote sensing image semantic segmentation method based on hierarchical contour cost function | |
| Tuhta et al. | Determination of System Parameters on Model Lighting Pole Using ANN by Ambient Vibration | |
| CN112364974A (en) | Improved YOLOv3 algorithm based on activation function | |
| CN116012310A (en) | Cross-sea bridge pier surface crack detection method based on linear residual error attention | |
| Ji et al. | Vision‐based seismic damage detection and residual capacity assessment for an RC shaking table test structure | |
| CN115631192B (en) | Control method, device, equipment and medium for valve pressure tester | |
| Aguir et al. | Gurson-Tvergaard-Needleman parameters identification using artificial neural networks in sheet metal blanking | |
| CN110781755A (en) | Intelligent identification and metering method and system for construction steel bars | |
| CN115346125A (en) | Target detection method based on deep learning |
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 |