CN113392588A - Bridge deck crack supervision method and system based on binocular vision - Google Patents
Bridge deck crack supervision method and system based on binocular vision Download PDFInfo
- Publication number
- CN113392588A CN113392588A CN202110714892.1A CN202110714892A CN113392588A CN 113392588 A CN113392588 A CN 113392588A CN 202110714892 A CN202110714892 A CN 202110714892A CN 113392588 A CN113392588 A CN 113392588A
- Authority
- CN
- China
- Prior art keywords
- crack
- bridge deck
- information
- training
- cracks
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/22—Measuring arrangements characterised by the use of optical techniques for measuring depth
-
- 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
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Immunology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Chemical & Material Sciences (AREA)
- Signal Processing (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Bridges Or Land Bridges (AREA)
Abstract
The invention discloses a bridge deck crack supervision method and a bridge deck crack supervision system based on binocular vision, which comprise the following steps: acquiring crack depth information and crack width data information which are arranged at fixed-point positions; extracting crack depth information and crack width information related to bridge deck cracks from the historical bridge deck detection information, and training the obtained information to obtain a training model of the crack depth information and the crack width information; judging formation information of the acquired crack depth information and crack width data information according to the training model; and predicting the development trend of the crack of the bridge deck according to the formation information. The width information and the depth information of the bridge deck cracks detected by the crack detection device in real time are compared with the data in the training model for judgment, and the development trend of the bridge deck cracks is judged based on the training model according to the detected data, so that the working personnel can timely make treatment measures according to the development trend of the cracks without regularly detecting the cracks, and the convenience is improved.
Description
Technical Field
The invention relates to the field of bridge deck crack supervision, in particular to a bridge deck crack supervision method and a bridge deck crack supervision system based on binocular vision.
Background
In the process of construction or after construction of the bridge floor, because concrete is dehydrated, shrinkage or the influence of temperature difference of hand temperature height is caused, expansion and shrinkage unevenness is caused, cracks appear on the bridge floor, or the connection part of a longitudinal crack bridge abutment and a roadbed or a roadbed concrete pavement can cause the phenomenon of uneven roadbed support under the action of uneven filled soil quality and temperature. In the bridge, if the roadbed sinks, the pressure of vehicle running and the self weight of the plate block jointly act on the bridge, and the longitudinal crack occurs. In the prior art, a regular detection mode is adopted for cracks, namely, the cracks are measured at intervals so as to judge the development trend of the cracks and make corresponding measures.
Therefore, the inventor thinks that the prior art needs a large amount of manpower and material resources for detecting the cracks at regular time.
Disclosure of Invention
In order to reduce the consumption of manpower and material resources, the application provides a bridge deck crack supervision method and a bridge deck crack supervision system based on binocular vision.
In a first aspect, the application provides a bridge deck crack supervision method based on binocular vision, which adopts the following technical scheme:
a bridge deck crack supervision method based on binocular vision comprises the following steps:
acquiring crack depth information and crack width data information about bridge deck cracks transmitted by a crack detection device arranged at a fixed point position in real time;
extracting crack depth information and crack width information related to bridge deck cracks from the historical bridge deck detection information, and training the obtained information to obtain a training model of the crack depth information and the crack width information;
judging formation information of the acquired crack depth information and crack width data information according to the training model; wherein the formation information comprises a formation reason and a formation duration;
and estimating the development trend of the bridge deck cracks according to the formation information.
By adopting the technical scheme, the information related to the depth and the width of the bridge deck crack recorded in the historical detection process is obtained, the information is trained to obtain the accurate training data for constructing the data model, then the data is utilized to construct the training model, the width information and the depth information of the bridge deck crack detected by the crack detection device in real time are compared and judged with the data in the training model to verify the formation reason, the existence time and the like of the depth and the width of the crack obtained from the data detected in real time, the development trend of the crack is judged based on the training model according to the detected data, so that a worker can timely make a treatment measure according to the development trend of the crack, the crack does not need to be detected at regular time, and the convenience is improved.
Optionally, the step of predicting the development trend of the bridge deck crack according to the formation cause information includes:
and predicting critical time information of bridge deck collapse caused by the bridge deck cracks from the bridge deck crack data model based on the crack formation reason information and taking treatment measures in time.
By adopting the technical scheme, the reason for the crack detected by the crack detection device is obtained according to the trained model, and compared with the historical data information in the trained model, the temporary time for the bridge deck collapse caused by the crack according to the current development trend of the crack is estimated, so that the working personnel can take treatment measures in time according to the judged information, and the loss is reduced.
Optionally, the method for forming the training model includes the following steps:
dividing the acquired data into a training set and a testing set by using a cross-validation method;
inputting the training set into a neural network for training until the neural network converges to obtain an initial neural network model;
and inputting the test set into the currently obtained neural network model for testing to obtain a training set meeting the requirements and a final neural network training model.
By adopting the technical scheme, the acquired historical data is divided in a cross verification method, the data divided into the training set is trained, then the data in the testing set is used for testing to verify the accuracy of the data obtained by training the training set, and then the data obtained by training the training set is used for building a training model for detecting and judging the data obtained by real-time detection of the crack detection device.
Optionally, the step of inputting the training set into the neural network for training until the neural network converges to obtain an initial neural network model further includes:
and updating the crack depth information and the crack width data information detected by the crack detection device into a test set for data training so as to update the training model.
By adopting the technical scheme, the data detected in real time are put into the training set so as to enrich the database of the training set, improve the data training amount of the training set and further improve the accuracy of the data after training.
Optionally, the step of predicting the development trend of the bridge deck crack according to the formation information further includes:
and acquiring crack repairing information from the training model according to the development trend of the bridge deck cracks so as to repair the cracks.
By adopting the technical scheme, the data obtained at the fixed point is input into the training model for data analysis and judgment so as to obtain the repair scheme of the crack and make treatment measures in time.
In a second aspect, the application provides a bridge deck crack proctoring system based on binocular vision, adopts following technical scheme:
the utility model provides a bridge floor crack reason system of monitoring based on binocular vision, includes the mounting bracket and sets up the crack detection device on the mounting bracket, be provided with drive crack detection device on the mounting bracket towards keeping away from or being close to the drive assembly that the bridge floor crack removed.
Through adopting above-mentioned technical scheme, fix the mounting bracket at the bridge floor and have crack department, crack detection device stretches to crack department under drive assembly's drive to carry out the collection of relevant data to the crack, drive assembly can adjust the position relation between crack detection device and the crack, and the convenience is adjusted according to actual demand.
Optionally, the driving assembly comprises a slide rail, a transverse screw rod is connected to the slide rail in a rotating manner, a transverse sliding block is connected to the transverse screw rod in a threaded manner, the transverse sliding block is connected to the slide rail in a sliding manner, a longitudinal screw rod is connected to the transverse sliding block in a rotating manner, a longitudinal sliding block is connected to the transverse screw rod in a threaded manner, a guide rod is fixedly connected to the transverse sliding block and placed in parallel to the longitudinal screw rod, the guide rod penetrates through the longitudinal sliding block and is connected with the longitudinal sliding block in a sliding manner, and the crack detection is connected to the longitudinal sliding block.
Through adopting above-mentioned technical scheme, through mutually supporting of longitudinal threaded rod and horizontal threaded rod to crack detection device removes at will on the plane that is level mutually with the bridge floor under the drive of longitudinal sliding block, makes things convenient for crack detection device to detect. The guide rod limits the axial rotation of the longitudinal sliding block, so that the longitudinal sliding block moves along the length direction of the longitudinal sliding block under the driving of the longitudinal threaded rod.
Optionally, the driving member further includes a reciprocating screw rod rotatably connected to the mounting frame, and the reciprocating screw rod is slidably connected to the longitudinal sliding block.
Through adopting above-mentioned technical scheme, through setting up reciprocal lead screw, rotate reciprocal lead screw and move towards keeping away from or being close to the crack direction with the drive slide rail, and then drive crack detection device towards keeping away from or being close to the crack direction motion to carry out the fixed point to the crack on the bridge floor and detect.
In a third aspect, the present application provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the binocular vision based bridge deck crack monitoring method according to any one of the second aspect when executing the computer program.
In a fourth aspect, the present application provides a computer readable storage medium storing a computer program capable of being loaded by a processor and executing the second aspect.
In summary, the present application has the following beneficial effects:
1. the method comprises the steps of obtaining information related to the depth and the width of a bridge deck crack recorded in a historical detection process, training the information to obtain accurate training data for constructing a data model, constructing the training model by utilizing the data, comparing and judging the width information and the depth information of the bridge deck crack detected by a crack detection device in real time with the data in the training model to verify the formation reason, the existence time and the like of the depth and the width of the crack obtained from the data detected in real time, judging the development trend of the crack based on the training model according to the detected data, so that a worker can timely make treatment measures according to the development trend of the crack, the crack does not need to be detected at regular time, and convenience is improved.
2. And obtaining the reason for the crack detected by the crack detection device according to the trained model, comparing the reason with historical data information in the trained model, and estimating the temporary time for the crack to cause the collapse of the bridge deck according to the current development trend of the crack, so that a worker can take treatment measures in time according to the judged information to reduce loss.
Drawings
FIG. 1 is a flow chart of a binocular vision based bridge deck crack management method in one embodiment of the present application;
FIG. 2 is a schematic diagram of the overall structure of a binocular vision-based bridge deck crack management system according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a computer device according to an embodiment of the present application.
Description of reference numerals:
1. a mounting frame; 2. a crack detection device; 3. a drive assembly; 31. a transverse screw; 32. a transverse motor; 33. a transverse slide block; 34. a longitudinal screw; 35. a longitudinal motor; 36. a longitudinal slide block; 37. a guide bar; 38. rotating the ring; 39. and a reciprocating screw rod.
Detailed Description
The present application is described in further detail below with reference to figures 1-3.
The embodiment of the application discloses a bridge deck crack supervision method based on binocular vision, and the method comprises the following steps of:
s100: and acquiring crack depth information and crack width data information about the bridge deck crack transmitted by the crack detection device 2 arranged at the fixed point position in real time.
In the present embodiment, the crack detection device 2 refers to a detection instrument for detecting cracks on the bridge deck;
specifically, the crack detection device 2 is installed at a position for fixed-point detection of the bridge deck, so that the crack detection device 2 detects the crack to acquire detection data related to the crack and store the detected data into the system.
S200: and extracting crack depth information and crack width information related to the bridge deck cracks from the bridge deck historical detection information, and training the obtained information to obtain a training model of the crack depth information and the crack width information.
In this embodiment, the bridge deck history detection information refers to a data set recorded when a bridge deck crack is detected from the internet or before the detection date, and the data includes information such as a cause, a depth, a width, a processing scheme for the crack, and the like corresponding to the crack; training means that the obtained crack depth data and crack width data are trained by using a neural network; the training model refers to a three-dimensional model about the bridge deck cracks established by using the trained data.
Specifically, the collected data is divided into a training set and a test set by a cross-validation method, specifically, the initial sampling is divided into K sub-samples, one single sub-sample is reserved as data of a validation model, and the other K-1 samples are used for training. And repeating the cross validation for K times, validating each sub-sample once, and taking the average value of the accuracy of the K times as the evaluation index of the final model. The test set is then used to calculate the test error. And finally, establishing a training model about the bridge deck cracks by using the data which meet the requirements after training.
And further, updating the data detected by the crack detection device 2 into a training set to enrich data samples trained by the training set, updating the detected data into a model and displaying the data in the model, wherein the specific operation of updating the model is that the detected data is firstly put into a database, a mapping table corresponding to the model is entered, and an option of 'updating the model from the database' is clicked and selected.
S300: judging formation information of the acquired crack depth information and crack width data information according to the training model; wherein the formation information includes a formation reason and a formation time length.
In the present embodiment, the formation information refers to the cause of the occurrence of the crack of the bridge deck; the length of formation refers to the length of time between the occurrence of the crack and the acquisition of the test data.
Specifically, the detected data is updated into the training model to derive the cause of the crack formation. For example, stress analysis is performed on a part of a bridge with a crack in a training model, and it is obtained that the tensile strain of concrete at the crack exceeds a limit value, so that the reason for the crack generation is preliminarily judged according to the detected data to be the crack which appears when the tensile strain of the concrete reaches the limit value. Stress analysis is carried out according to crack positions (the concrete implementation mode is that the model is put into stress analysis software, the solid work software is adopted in the embodiment, then stress analysis is carried out on the three-dimensional model by using a finite element analysis module in the solid work software, so that stress data of each part in the model can be obtained), the time for the concrete to reach tensile strain can be estimated, and the time required from the generation of cracks to the formation of the cracks of the current scale from the generation of the cracks can be known from a training model; and estimating the development trend of the crack according to the detected data, namely finding out data which is the same as or similar to the current situation from the training model, and deducing the current development trend of the crack according to the development trend of the crack reflected by historical data so as to facilitate the working personnel to make treatment measures in time.
Further, the step 300 further includes predicting critical time information of the bridge deck collapse caused by the bridge deck cracks from the training model based on the crack formation reason information and making a treatment measure in time.
In this embodiment, the critical time information refers to a critical time point at which a change in the bridge structure occurs due to the crack, such as a sinking or a local sinking of the bridge deck.
Specifically, after the crack development trend is obtained, stress critical points of the bridge deck at the cracks are calculated from the crack development trend, time corresponding to the critical points is obtained, and a worker can specify corresponding measures according to the obtained information.
Further, step 300 further comprises: and acquiring crack repairing information from the training model according to the development trend of the bridge deck cracks so as to repair the cracks.
In the present embodiment, the crack repair information refers to a repair processing scheme for the crack.
Specifically, the crack-related repairing scheme is also formed in a training model in a data training mode, and after the crack width, depth and other related data are detected, the related crack processing scheme is obtained according to the data, so that convenience is improved. For example, the width of the crack detected at the fixed point position is 0.8 cm, the depth is 0.5 cm, the crack is formed because the tensile strain of the concrete reaches the limit, and the processing scheme corresponding to the crack is obtained from the historical data of the training model and is A.
The embodiment of the application also discloses bridge deck crack reason system of supervising based on binocular vision, see fig. 2, this system includes mounting bracket 1 and sets up crack detection device 2 on mounting bracket 1, and crack detection device 2 is used for detecting the bridge deck crack, is equipped with the flexible drive assembly 3 of drive bridge deck crack detection device 2 towards keeping away from or being close to bridge deck crack direction on mounting bracket 1.
The driving assembly 3 includes a slide rail (hidden in the figure), the reciprocating screw rod 39 is slidably connected to the slide rail, the slide rail is rotatably connected to the transverse screw rod 31, the transverse screw rod 31 is threadedly connected to the transverse slider 33, and the transverse slider 33 is located in the slide rail and slidably connected to the slide rail (in this embodiment, the rotation is achieved by fixing two bearings fixed to the slide rail to two ends of the transverse screw rod 31). One end of the transverse screw 31 is fixedly connected with a transverse motor 32, an output shaft of the transverse motor 32 is fixedly connected with the transverse screw 31, and the transverse motor 32 is fixedly connected with the sliding rail.
The slide rail is provided with two, two slide rail parallel arrangement, drive assembly 3 still includes vertical screw 34, the both ends correspondence of vertical screw 34 is rotated with two horizontal sliders 33 and is connected (specifically through will fixing towards the both ends of vertical screw 34 with two bearings of fixing on the slide rail in this embodiment, realize rotating), threaded connection has vertical slider 36 on the vertical screw 34, vertical slider 36 and vertical screw 34 threaded connection, horizontal slider 33 fixedly connected with guide bar 37, guide bar 37 and vertical screw 34 threaded connection, guide bar 37 wears to locate vertical slider 36 and with vertical slider 36 sliding connection. One end of the longitudinal screw 34 is fixedly connected with a longitudinal motor 35, and an output shaft of the longitudinal motor 35 is fixedly connected with the longitudinal screw 34. The longitudinal motor 35 is fixedly connected with the transverse sliding block 33.
The driving assembly 3 further comprises a reciprocating screw rod 39, the reciprocating screw rod 39 penetrates through the longitudinal sliding block 36 and is in sliding connection with the longitudinal sliding block 36, the reciprocating screw rod 39 is perpendicular to the longitudinal screw rod 34, a convex block (not shown in the figure) is arranged in the longitudinal sliding block 36, a sliding chute 3 is formed in the reciprocating screw rod 39 in a concave mode, the sliding chute 3 extends along the length direction of the reciprocating screw rod 39, the convex block extends into the sliding chute 3 and is in sliding connection with the sliding chute, a rotating ring 38 is rotatably connected to one end, located at the position where the reciprocating screw rod 39 extends, of the longitudinal sliding block 36, the rotating ring 38 is in threaded connection with the reciprocating screw rod 39, the crack detection device 2 is fixed at one end of the reciprocating screw rod 39, and the crack detection device 2.
In this embodiment, the crack detection device is a width detection sensor, a crack depth tester. In other embodiments, the crack detection device further includes a temperature detection sensor, a pressure detection sensor, and the like.
Further, the system further comprises: and the crack data acquisition module is used for acquiring crack depth information and crack width data information about the bridge deck crack transmitted by the crack detection device 2 arranged at the fixed point position in real time.
And the model training module is used for extracting crack depth information and crack width information related to the bridge deck cracks from the historical bridge deck detection information and training the obtained information to obtain a training model of the crack depth information and the crack width information.
The crack formation reason module is used for judging formation information of the acquired crack depth information and crack width data information according to the training model; wherein the formation information includes a formation reason and a formation time length.
And the crack trend analysis module is used for predicting the development trend of the bridge deck cracks according to the formation information.
Further, the system further comprises: and the critical point detection module is used for training the model to predict critical time information of bridge deck collapse caused by bridge deck cracks and timely making a treatment measure based on the crack formation reason information.
Further, the system further comprises: the training module is used for dividing the acquired data into a training set and a testing set by using a cross validation method; inputting the training set into a neural network for training until the neural network converges to obtain an initial neural network model; and inputting the test set into the currently obtained neural network model for testing to obtain a training set meeting the requirements and a final neural network training model.
Further, the system further comprises: and the model updating module is used for updating the crack depth information and the crack width data information detected by the crack detection device 2 into a test set to perform data training so as to update the training model.
Further, the system further comprises: and the crack repairing scheme module is used for acquiring crack repairing information from the training model according to the development trend of the bridge deck cracks so as to repair the cracks.
The embodiment of the application also discloses a computer device, which can be a server, with reference to fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store historical suspicious behavior data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a binocular vision based bridge deck crack supervision method, comprising the steps of:
s100: acquiring crack depth information and crack width data information about the bridge deck crack transmitted by a crack detection device 2 arranged at a fixed point position in real time;
s200: extracting crack depth information and crack width information related to bridge deck cracks from the historical bridge deck detection information, and training the obtained information to obtain a training model of the crack depth information and the crack width information;
s300: judging formation information of the acquired crack depth information and crack width data information according to the training model; wherein the formation information comprises a formation reason and a formation duration;
s400: and predicting the development trend of the crack of the bridge deck according to the formation information.
The embodiment of the application also discloses a computer readable storage medium. In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
s100: acquiring crack depth information and crack width data information about the bridge deck crack transmitted by a crack detection device 2 arranged at a fixed point position in real time;
s200: extracting crack depth information and crack width information related to bridge deck cracks from the historical bridge deck detection information, and training the obtained information to obtain a training model of the crack depth information and the crack width information;
s300: judging formation information of the acquired crack depth information and crack width data information according to the training model; wherein the formation information comprises a formation reason and a formation duration;
s400: and predicting the development trend of the crack of the bridge deck according to the formation information.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A bridge deck crack supervision method based on binocular vision is characterized by comprising the following steps: the method comprises the following steps:
acquiring crack depth information and crack width data information about the bridge deck crack transmitted by a crack detection device (2) arranged at a fixed point position in real time;
extracting crack depth information and crack width information related to bridge deck cracks from the historical bridge deck detection information, and training the obtained information to obtain a training model of the crack depth information and the crack width information;
judging formation information of the acquired crack depth information and crack width data information according to the training model; wherein the formation information comprises a formation reason and a formation duration;
and estimating the development trend of the bridge deck cracks according to the formation information.
2. The binocular vision-based bridge deck crack supervision method according to claim 1, wherein: the step of predicting the development trend of the bridge deck cracks according to the formation reason information comprises the following steps:
and based on the crack formation reason information, the training model predicts critical time information of bridge deck collapse caused by the bridge deck cracks and takes treatment measures in time.
3. The binocular vision-based bridge deck crack supervision method according to claim 1, wherein: the method for forming the training model comprises the following steps:
dividing the acquired data into a training set and a testing set by using a cross-validation method;
inputting the training set into a neural network for training until the neural network converges to obtain an initial neural network model;
and inputting the test set into the currently obtained neural network model for testing to obtain a training set meeting the requirements and a final neural network training model.
4. The binocular vision-based bridge deck crack supervision method according to claim 3, wherein: the step of inputting the training set into the neural network for training until the neural network converges to obtain an initial neural network model further comprises:
and updating the crack depth information and the crack width data information detected by the crack detection device (2) into a test set for data training so as to update the training model.
5. The binocular vision-based bridge deck crack supervision method according to claim 1, wherein: the step of predicting the development trend of the bridge deck cracks according to the formation information further comprises the following steps:
and acquiring crack repairing information from the training model according to the development trend of the bridge deck cracks so as to repair the cracks.
6. The utility model provides a bridge deck crack reason system of monitoring based on binocular vision which characterized in that: the bridge deck crack detection device comprises an installation frame (1) and a crack detection device (2) arranged on the installation frame (1), wherein a driving assembly (3) for driving the crack detection device (2) to move towards a far position or a position close to a bridge deck crack is arranged on the installation frame (1).
7. The binocular vision-based bridge deck crack proctoring system of claim 6, wherein: drive assembly (3) includes the slide rail, it is connected with horizontal screw rod (31) to rotate on the slide rail, threaded connection has horizontal slider (33) on horizontal screw rod (31), horizontal slider (33) with slide rail sliding connection, it is connected with vertical screw rod (34) to rotate on horizontal slider (33), vertical screw rod (34), threaded connection has vertical slider (36) on horizontal screw rod (31), fixedly connected with on horizontal slider (33) with guide bar (37) that vertical screw rod (34) parallel was placed, guide bar (37) pass vertical slider (36) and with vertical slider (36) sliding connection, the crack detects connect in vertical slider (36).
8. The binocular vision based bridge deck crack proctoring system of claim 7, wherein: the driving piece further comprises a reciprocating screw rod (39) rotatably connected with the mounting rack (1), and the reciprocating screw rod (39) is slidably connected with the longitudinal sliding block (36).
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: the processor, when executing the computer program, performs the steps of a binocular vision based bridge deck crack governing method as claimed in any one of claims 1 to 5.
10. A computer-readable storage medium, in which a computer program is stored which can be loaded by a processor and which executes the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110714892.1A CN113392588A (en) | 2021-06-25 | 2021-06-25 | Bridge deck crack supervision method and system based on binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110714892.1A CN113392588A (en) | 2021-06-25 | 2021-06-25 | Bridge deck crack supervision method and system based on binocular vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113392588A true CN113392588A (en) | 2021-09-14 |
Family
ID=77624013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110714892.1A Withdrawn CN113392588A (en) | 2021-06-25 | 2021-06-25 | Bridge deck crack supervision method and system based on binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392588A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114354625A (en) * | 2021-12-30 | 2022-04-15 | 中铁大桥局集团有限公司 | Prefabricated pier detection device |
| CN117470141A (en) * | 2023-12-26 | 2024-01-30 | 临沂市泉金木业有限公司 | Panel surface smoothness check out test set |
-
2021
- 2021-06-25 CN CN202110714892.1A patent/CN113392588A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114354625A (en) * | 2021-12-30 | 2022-04-15 | 中铁大桥局集团有限公司 | Prefabricated pier detection device |
| CN114354625B (en) * | 2021-12-30 | 2023-10-20 | 中铁大桥局集团有限公司 | Prefabricated pier detection device |
| CN117470141A (en) * | 2023-12-26 | 2024-01-30 | 临沂市泉金木业有限公司 | Panel surface smoothness check out test set |
| CN117470141B (en) * | 2023-12-26 | 2024-03-12 | 临沂市泉金木业有限公司 | Panel surface smoothness check out test set |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113392588A (en) | Bridge deck crack supervision method and system based on binocular vision | |
| CN101782372B (en) | Intelligent diagnosis method for bridge telescopic seam injury based on girder end longitudinal displacement | |
| CN103048102B (en) | A kind of state evaluating method of beam bridge | |
| CN111784070A (en) | Intelligent landslide short-term early warning method based on XGboost algorithm | |
| CN103486971B (en) | A kind of subway tunnel fracture width detection and correcting algorithm | |
| CN116227752A (en) | Park facility management system based on Internet of things | |
| CN110645934A (en) | Online calibration method of displacement sensor | |
| CN102998136A (en) | Linear monitoring method of pre-stressed concrete continuous rigid frame beams | |
| CN117252042B (en) | Urban underground space comprehensive bearing capacity evaluation system and method | |
| CN112762885A (en) | Bridge real-time deflection check coefficient calculation method based on monitoring data | |
| CN117610375A (en) | Bridge suspension casting construction digital twin method, device and equipment based on machine vision | |
| CN114315057B (en) | Water treatment control method, system, computer equipment and storage medium | |
| CN116651971A (en) | Online detection method and system for automobile stamping die | |
| Shen et al. | Rate-dependent characteristics of damage and roughness degradation of three-dimensional artificial joint surfaces | |
| RU2699918C1 (en) | Diagnostic method of technical state of buildings and structures | |
| CN113158558B (en) | High-speed railway roadbed continuous compaction analysis method, device and analyzer | |
| CN113283182A (en) | Method, device, medium and equipment for predicting and analyzing formation pressure | |
| CN118013617A (en) | Bridge construction monitoring method, device, equipment and storage medium | |
| CN112459136A (en) | Deep foundation pit construction safety risk monitoring method, device, equipment and medium | |
| CN116663126A (en) | Bridge temperature effect prediction method based on channel attention BiLSTM model | |
| CN113466083B (en) | High-precision asphalt pavement density processing method, system, device and storage medium | |
| Lu et al. | A Robust Image Processing Algorithm for Optical-Based Stress–Strain Curve Corrections after Necking | |
| CN113326559A (en) | Municipal bridge engineering construction supervision method and system | |
| CN117928643B (en) | Concrete dam stress-strain analysis method and device based on multi-measuring-point combined calculation | |
| Leonetti et al. | Fatigue behavior of transverse attachments under constant and variable amplitude loading from a Swiss motorway bridge |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210914 |