CN110411686B - Bridge static and dynamic image holographic property health monitoring and diagnosis method and system - Google Patents
Bridge static and dynamic image holographic property health monitoring and diagnosis method and system Download PDFInfo
- Publication number
- CN110411686B CN110411686B CN201910187373.7A CN201910187373A CN110411686B CN 110411686 B CN110411686 B CN 110411686B CN 201910187373 A CN201910187373 A CN 201910187373A CN 110411686 B CN110411686 B CN 110411686B
- Authority
- CN
- China
- Prior art keywords
- bridge
- data
- dynamic
- theoretical
- holographic
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M5/00—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings
- G01M5/0008—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings of bridges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M5/00—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings
- G01M5/0033—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings by determining damage, crack or wear
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M5/00—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings
- G01M5/0041—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings by determining deflection or stress
- G01M5/005—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings by determining deflection or stress by means of external apparatus, e.g. test benches or portable test systems
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a holographic property state health monitoring and diagnosing method for a bridge, which comprises the steps of acquiring environmental information, bridge deck traffic state information and bridge facade image acquisition information for a healthy bridge, establishing a finite element simulation model of a lossless bridge according to the healthy bridge, acquiring the structural characteristic form and the structural dynamic characteristic of the simulation model by using the data, comparing the structural characteristic form and the structural dynamic characteristic with the real structural characteristic form and the real structural characteristic form of the healthy bridge, accumulating and counting difference values after circulation to obtain a difference value change rule, establishing an actual state function curve of the healthy bridge and a function curve of the theoretical state of the lossless bridge after machine deep learning of historical sample data, and acquiring the current health state of the bridge through function comparison when the method is used.
Description
Technical Field
The invention belongs to the field of civil structures and safety engineering, and particularly relates to a holographic property state health monitoring and diagnosis method for a bridge.
Background
In the field of civil and structural engineering, particularly for structures with a certain service life of heavy infrastructure such as large bridges and the like, practical and effective safety monitoring management measures need to be taken to ensure that the structures avoid heavy safety accidents during use.
The existing bridge safety inspection is roughly divided into three types, namely periodic inspection: the bridge is comprehensively checked once in every 2-6 years by means of special equipment, data is detailed, and the conclusion is credible, but the checking frequency is low, so that the problem of structural safety and health between two adjacent regular checks is difficult to know in time; second, the regular safety inspection: the bridge is required to be manually and safely patrolled not less than once every month, although the frequency is high, the actual patrolling effect is difficult to achieve due to the lack of quantitative data; thirdly, the conventional bridge long-term health monitoring system is characterized in that a series of sensors are arranged on a bridge, the performance response data of a service bridge can be acquired at high frequency, and the current structural state of the bridge can be analyzed and conjectured accordingly.
In the prior art, a simpler and more convenient and effective monitoring mode is to use fixed-point photography to obtain the change condition of the characteristic speckle pattern on the structural body under different time or different working conditions to carry out deformation monitoring on key points or local areas. To date, it has not been possible to economically and conveniently obtain holographic data of geometric variations of the whole and component parts of a large civil engineering structure.
In order to solve the above problems, the chinese patent ZL201610300691 "a structural deformation monitoring method based on contour line image overlay error analysis" discloses a method for detecting a bridge, the picture reflecting the main body of the structure and containing the main components of interest is obtained through fixed-point or multi-view photography, the picture processing is carried out to obtain a digital structure contour line image picture, and performing a differential overlay analysis on the contour lines of the same structural contour line image and the first structural image at each period to obtain structural deformation data at different periods, the safety condition of the structure is evaluated and predicted according to the analysis and comparison of the secondary deformation data, the whole process is simple and convenient, the defect that the deformation condition of a specified point or a specific small area can only be obtained according to the change of the characteristic speckles in the traditional image deformation test is avoided, and the holographic geometric deformation data of the whole large structure and all concerned parts and component parts in the photo range can be obtained; however, for a large bridge, the method needs to perform splicing processing on a plurality of image pictures, firstly, there is an image picture splicing error problem, and secondly, the theoretical requirement is that each spliced image should be obtained instantly and simultaneously when the bridge is in the same condition, which is actually not satisfied for the operation of the bridge, still exists artificial participation, a large error may exist, and the obtained result is still not objective enough.
Therefore, a monitoring and early warning method for large bridges is needed, which can objectively acquire the action and state data of the bridge and compare the action and state data with the theoretical data of a healthy bridge, so as to obtain the health condition of the bridge, and can automatically realize the acquisition and the transportation of big data through a computer.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for monitoring and diagnosing health of a holographic dynamic image of a bridge, which can objectively obtain action and state data of the bridge, form big data acquisition and transmission, automatically implement comparative analysis with theoretical data of a healthy bridge through a computer, and obtain a change rule of a structural state of the bridge under the action of an environment and a load changing along with time according to machine deep learning of the monitoring data of a past time, so as to obtain the health condition of the bridge.
The holographic property state health monitoring and diagnosing method for the static and dynamic images of the bridge comprises the following steps of:
a. acquiring initial information data of a bridge structure;
a1. collecting condition information data of Ti;
a2. acquiring Qj section structure static image data of the Ti-time bridge and Qj section structure dynamic video data of the Ti + delta time interval bridge under the condition information data of the step a 1;
a3. analyzing and processing a static image of a Qj section structure of the bridge in Ti to obtain geometric form holographic data Cs of the representation structure deformation characteristic of the actual Qj section of the bridge; analyzing and processing a dynamic video of the Qj section structure of the bridge at Ti + delta to obtain dynamic holographic form data Ds of the Qj section structure of the actual bridge;
b. establishing a refined finite element theoretical model of the lossless bridge;
b1. inputting a structural theoretical state parameter E of the lossless bridge when Ti is input;
b2. substituting the condition information data in the Ti step 1 into a refined finite element theoretical model of the lossless bridge;
b3. according to the steps b1 and b2, calculating theoretical geometric form holographic data Cw of the characteristic structural deformation characteristic of the Ti-time lossless bridge Qj section and theoretical dynamic form holographic data Dw of the Ti + delta-time period lossless bridge Qj section structure;
c. comparing and analyzing the geometric form holographic data Cs and the actual structure dynamic holographic form data Ds representing the actual structure deformation characteristics in the step a3 with the corresponding structure deformation theoretical data Cw and the theoretical dynamic characteristic data Dw in the step b3, wherein the difference value between the geometric form holographic data Cs and the actual structure dynamic holographic form data Ds relative to the structure deformation theoretical data Cw and the theoretical dynamic characteristic data Dw is within a set value, the Qj section structure of the bridge is judged to be in a normal state without obvious damage, otherwise, the Qj section structure of the bridge is judged to be in an abnormal structure state with obvious damage, and abnormal parts and degrees are output;
d. if the Qj section structure of the bridge in the step c is in a normal state, the ij loops the steps a2, a3, b2, b3 and c, and machine deep learning is carried out on the accumulated historical sample data;
d1. the method comprises the steps of accumulating the theoretical data Cw and the theoretical dynamic characteristic data Dw of the lossless bridge structure under different condition information data, establishing a judgment network model of the lossless bridge, continuously accumulating sample data, continuously correcting the judgment network model, and establishing a theoretical static and dynamic form change rule of the theoretical deformation data Cw and the theoretical dynamic characteristic data Dw of the lossless bridge structure along with the action of the different condition information data;
d2, performing machine deep learning on the accumulated historical sample data obtained by the actual bridge, and establishing the change rule of the static and dynamic forms of the actual bridge, wherein the change rule of the geometrical form holographic data Cs and the dynamic form data Ds of the actual bridge correspond to the actual bridge structure along with the action of different condition information data;
e. comparing and analyzing the theoretical state change rule model of the lossless bridge under the current condition information data with the structure state change rule model of the actual bridge, and determining that the bridge structure is in a normal state if the difference amplitude relationship between the actual static and dynamic state change rule of the bridge structure and the theoretical static and dynamic state change rule of the lossless bridge is within a set value range by stopping the current time period; otherwise, the bridge is considered to have abnormal structural response rules, and the monitoring system gives out early warning and outputs the position and degree of the out-of-range difference of the static and dynamic form rules.
Further, the condition information data at least comprises time duration data T, environmental climate data A of the bridge and traffic operation condition data B of vehicle crowds on the bridge deck;
d1, accumulating the lossless bridge structure deformation theoretical data Cw and the theoretical dynamic characteristic data Dw obtained under the duration T, the different environmental climate data A where the bridge is located and the traffic operation condition data B of the vehicle and people on the bridge surface in the vision field, and establishing a mathematical network model f (T/A/B) which is g (Cw/Dw) of the theoretical static and dynamic state change rule of the lossless bridge;
in step d2, a mathematical network model f '(T/a/B) ═ g' (Cs/Ds) of the actual static and dynamic form change law of the actual bridge structure geometric form holographic data Cs and the actual structure dynamic holographic form data Ds obtained under the duration T, the different environmental climate data a where the bridge is located, and the bridge deck vehicle crowd traffic operation condition data B within the field of view is accumulated.
Step e, comparing and analyzing a theoretical static and dynamic form change rule [ T/A/B/Cw/Dw ] of the lossless bridge under the environmental climate data A and the bridge deck vehicle crowd traffic operation condition data B in the view field in the current T time period with an actual static and dynamic form change rule [ T/A/B/Cs/Ds ] of the actual bridge, and determining that the bridge structure is in a normal state if the difference amplitude relationship between the actual static and dynamic form change rule f '(T/A/B) ═ g' (Cs/Ds) of the bridge structure and the theoretical static and dynamic form change rule f (T/A/B) ═ g (Cw/Dw) of the lossless bridge structure is within a set value range; otherwise, the bridge is considered to have abnormal structural form response rules, and the monitoring system gives out early warning and outputs the position and degree of the out-of-range difference of the static form rule and the dynamic form rule.
Further, in step a2, the climate data of the environment where the bridge is located at the time of Ti includes at least one of climate information data of temperature, humidity, sunshine, wind, rain and snow; and the traffic operation condition data of the bridge deck vehicles on the Ti time comprises at least one of the data of the number of the vehicles, the types of the vehicles, the weights of the vehicles, the positions, the speeds and the crowd distribution information in the vision range.
Further, in step a2 and step e, the acquisition of the Ti-time bridge structure static image data and the Ti + Δ time period bridge structure dynamic image data may be set as:
simultaneously acquiring static image data of a bridge structure in Ti time and dynamic image data of the bridge structure in Ti + delta time period for the same section structure of the bridge;
or sequentially and continuously acquiring static image data of a plurality of bridge section structures respectively, and sequentially acquiring dynamic image video data of the plurality of bridge section structures respectively;
or, setting a trigger type fixed camera for acquiring static image data and structural dynamic video data of a bridge structure aiming at a specific bridge or a specified structural area, wherein the trigger type acquisition refers to indicating the fixed camera to acquire the image data when a specific trigger condition is set for the bridge.
Further, the vibration mode, the amplitude and the vibration frequency can be obtained according to analysis of dynamic video data of the bridge structure.
Further, in step a1, the first-time acquired condition information data may be acquired in an unloaded state of the bridge and used as basic data for the start of bridge monitoring.
Further, if the bridge is a large bridge in construction, the Qj section is a bridge section already completed in the construction process, and the condition information data at least includes time duration data and bridge construction state data.
The invention also discloses a holographic property and state health monitoring system for the static and dynamic images of the bridge, which comprises the following components:
the condition information data acquisition unit is used for acquiring the condition information data of the bridge;
the image information data acquisition unit is used for acquiring static image data and dynamic video data of an actual bridge structure;
and the central processing unit is used for receiving, storing, analyzing and processing the condition information data to acquire the condition information data and the image information data of the bridge to acquire the holographic data of the geometric form and the holographic data of the structural dynamic characteristic of the actual bridge, storing, analyzing and processing the theoretical data of the lossless bridge, and completing the steps a to e of the holographic dynamic health monitoring and diagnosing method for the static and dynamic images of the bridge.
Further, the condition information data acquisition unit at least comprises a clock unit for acquiring the time duration data of the bridge, an environment information monitoring unit for acquiring the environment information data of the bridge and a bridge deck traffic information monitoring unit for acquiring the bridge deck traffic operation state data; the image information data acquisition unit is an intelligent image acquisition device capable of automatically performing itineration rotation in the horizontal direction and the vertical direction and is used for acquiring static images and dynamic videos in sections along the length direction and the height direction of a monitored bridge.
The invention has the beneficial effects that: compared with the conventional bridge health monitoring system for acquiring displacement, acceleration, strain and the like of a structural finite point by installing a sensor at a set part, the holographic performance state health monitoring and diagnosing method and system for the bridge static and dynamic images have the following characteristics:
1. and the data is reliably monitored in a non-contact way. The four components of the invention, namely the environmental climate, the vehicle action, the structural form and the theoretical analysis, are monitoring and analyzing devices independent of the bridge body, can be calibrated at regular intervals, and provide credible guarantee for the long-term reliability of the acquired data. The monitoring data acquisition does not influence the normal use of the bridge.
2. And the data is holographically acquired and the device is economical. The invention utilizes one (or more) high-speed high-definition image acquisition devices for fixed-point control of itinerant turning to acquire the structural still and moving image form holographic data of the large bridge subsections, and provides means for economically acquiring the non-missing structural still and moving image form holographic data.
3. The static and dynamic holographic morphology monitoring and diagnosis are more accurate. The invention obtains environmental climate information, bridge deck vehicle traffic operation information and static image and dynamic video acquisition information of a bridge structure from a healthy bridge, establishes a finite element theoretical model of a lossless bridge according to the healthy bridge, inputs the environmental climate and vehicle action into the theoretical model, analyzes to obtain the theoretical geometric shape change and dynamic characteristic response of the lossless bridge structure, and performs holographic comparison analysis with the actual geometric shape change and dynamic characteristic response of the current bridge structure obtained by acquiring the static image and the dynamic video, performs holographic comparison analysis (performing comprehensive comparison analysis on the geometric characteristics such as slope, convexity, inflection point, frequency, amplitude, phase and the like of a curve of the static and dynamic shapes) according to the theoretical static and dynamic shapes of the lossless bridge and the actual static and dynamic shapes of the current bridge at the initial stage of bridge health monitoring, and avoids the analysis and judgment (incapable of performing holographic characteristic shape analysis) only according to the static and dynamic monitoring data of limited measuring points in the conventional bridge health monitoring State comparison) may miss structural morphology information response generated by structural damage, and the initial health state diagnosis (equivalent to the medical practice of the students just after the medical school) is performed in combination with the traditional comparison of control point magnitude.
4. Image splicing is abandoned, and intelligent diagnosis is obtained through machine learning. Along with the gradual accumulation of [ T/A/B/Cw/Dw ] ij and [ T/A/B/Cs/Ds ] ij sample data, the mapping relation and the change rule of the static and dynamic states [ Cs ] and [ Ds ] of the actual structure of the bridge and the static and dynamic states [ Cw ] and [ Dw ] of the theoretical structure of the lossless bridge under various complex conditions (the annual time T, the environmental climate A and various vehicle load actions B) are gradually established and perfected through machine deep learning of historical sample data, so that the real-time health diagnosis obtained according to bridge monitoring big data and artificial intelligent analysis in the later period is more exquisite and accurate.
The bridge safety early warning system is used for detecting and evaluating the safety of bridges, is realized by storing and calculating data, is obtained by processing and running big data, is convenient to operate, short in time and high in efficiency, has low requirements for detecting the bridges, improves the safety early warning capability of structural bodies such as the bridges, and has the advantages of high working efficiency, low cost and capability of realizing high-frequency large-range bridge safety monitoring.
The invention can form the integral monitoring of the large bridge as required, and can also detect a certain characteristic area of the bridge as required, can quickly acquire data and obtain the integral result through calculation, and the data analysis and processing from the reading and storage of the detection data to the later stage are automatically completed by software in the background, thereby maximally avoiding the influence of artificial subjective factors;
the invention is used for detection and safety evaluation of structural bodies such as bridges, reduces the technical requirements of daily managers, can realize safety evaluation and early warning of large bridges, effectively ensures the safe operation of the structure, reduces the management and maintenance cost, has great social and economic significance and also has good application prospect.
Drawings
The invention is further described below with reference to the figures and examples.
FIG. 1 is a block flow diagram of the method of the present invention;
FIG. 2 is a functional block diagram of the system of the present invention;
FIG. 3 is a schematic (elevation) data acquisition distribution of the present invention;
fig. 4 is a schematic (plan) view of the data acquisition profile of the present invention.
Detailed Description
The holographic property state health monitoring and diagnosing method for the static and dynamic images of the bridge comprises the following steps of:
a. acquiring initial information data of a bridge structure;
a1. collecting condition information data of Ti; the condition information data generally comprises data which have actual influence on the service life of the bridge, such as time duration data, environmental climate data of the bridge, traffic condition data of the bridge deck and the like;
a2. acquiring Qj section structure static image data of the Ti-time bridge and Qj section structure dynamic video data of the Ti + delta time interval bridge under the condition information data of the step a 1; the static image data can be obtained by using a method of a structure deformation monitoring method based on contour line image overlay error analysis in Chinese patent ZL201610300691, or by using the existing computer vision measurement technology to carry out structure probability edge extraction and holographic morphological parameter extraction, which is not described herein again; the dynamic video data generally comprises amplitude, vibration mode, vibration frequency and the like which can represent the state of a bridge, the Euler visual motion information amplification technology is realized by utilizing the existing computer visual measurement technology, and the motion key information extraction based on SVD (singular value decomposition) belongs to the application of the prior art, and is not repeated herein;
a3. analyzing and processing a static image of a Qj section structure of the bridge in Ti to obtain geometric form holographic data Cs of the representation structure deformation characteristic of the actual Qj section of the bridge; analyzing and processing a dynamic video of the Qj section structure of the bridge at Ti + delta to obtain dynamic holographic form data Ds of the Qj section structure of the actual bridge; the geometric form holographic data Cs and the dynamic holographic form data Ds are the actual response of the bridge;
b. establishing a refined finite element theoretical model of the lossless bridge;
b1. inputting a structural theoretical state parameter E of the lossless bridge when Ti is input; the structural theoretical state parameter E refers to a theoretical bridge influenced by characteristics when the material is counted when the time extends to Ti;
b2. substituting the condition information data in the Ti step 1 into a refined finite element theoretical model of the lossless bridge;
b3. according to the steps b1 and b2, calculating theoretical geometric shape holographic data Cw of the Ti-time lossless bridge Qj section representing structural deformation characteristics and theoretical dynamic characteristic data Dw of the Ti + delta time period lossless bridge Qj section structure (namely theoretical response of the lossless bridge); on the premise of knowing condition information data, obtaining the holographic data Cw of the theoretical geometric shape of the lossless bridge and the theoretical dynamic characteristic data Dw by calculation, belonging to the prior art and not being repeated herein;
c. comparing and analyzing the geometric form holographic data Cs and the actual structure dynamic holographic form data Ds representing the actual structure deformation characteristics in the step a3 with the corresponding structure deformation theoretical data Dw and the theoretical dynamic characteristic data Dw in the step b3, wherein the difference value between the geometric form holographic data Cs and the actual structure dynamic holographic form data Ds relative to the structure deformation theoretical data Cw and the theoretical dynamic characteristic data Dw is within a set value, the state is a healthy bridge state, otherwise, the state is a structure abnormality, and abnormal positions and degrees are output; the set value is according to the deformation characteristics that the healthy bridge should have under the specific conditions, and is not described herein again;
d. if the Qj section structure of the bridge in the step c is in a normal state, the ij loops the steps a2, a3, b2, b3 and c, and machine deep learning is carried out on the accumulated historical sample data; the ij cycle refers to data acquisition of geometric form holographic data Cs and actual structure dynamic holographic form data Ds of the bridge Qj section under different Ti times under different condition information data conditions in time continuation, and data calculation of structure deformation theoretical data Cw and theoretical dynamic characteristic data Dw, and forms a healthy bridge state actual static and dynamic form change rule and a lossless bridge theoretical structure state theoretical static and dynamic form change rule after machine deep learning;
d1. the method comprises the steps of accumulating the theoretical data Cw and the theoretical dynamic characteristic data Dw of the structure deformation of the lossless bridge under different condition information data, establishing a judgment network model of the lossless bridge, continuously accumulating sample data, continuously modifying (ij circulating) and perfecting the judgment network model, establishing a theoretical static and dynamic state change rule of the theoretical bridge structure according to the function of the theoretical deformation theoretical data Cw and the theoretical dynamic characteristic data Dw of the theoretical bridge structure along with the different condition information data, wherein the more the circulation times, the more accurate the rule modification is, and providing a basis for bridge health monitoring;
d2, performing machine deep learning (ij circulation) on the accumulated historical sample data obtained by the actual bridge, and establishing the actual static and dynamic form change rule of the geometric form holographic data Cs and the actual structure dynamic holographic form data Ds corresponding to the actual bridge structure along with the action of different condition information data;
e. comparing and analyzing the theoretical state change rule model of the lossless bridge under the current condition information data with the structure state change rule model of the actual bridge, and determining that the bridge structure is in a normal state if the difference amplitude relationship between the actual static and dynamic state change rule of the bridge structure and the theoretical static and dynamic state change rule of the lossless bridge is within a set value range by stopping the current time period; otherwise, the bridge is considered to have abnormal structural response rules (the structural response rules are generally abnormal due to gradual development of micro-damage), and the monitoring system gives out early warning and outputs the position and the degree of the out-of-range difference of the static and dynamic form rules.
In this embodiment, the condition information data at least includes time duration data T, environmental climate data a of the bridge and bridge deck traffic condition data B;
d1, accumulating the lossless bridge structure deformation theoretical data Cw and the theoretical dynamic characteristic data Dw obtained under the duration T, the environmental climate data A of different bridges and the sight field bridge deck traffic condition data B, and establishing a theoretical static and dynamic form change law function f (T/A/B) of the lossless bridge as g (Cw/Dw); the method comprises the steps that structural deformation theoretical data Cw and theoretical dynamic characteristic data Dw of theoretical bridges are obtained through calculation under duration time T, environmental climate data A of different bridges and view field bridge deck traffic condition data B, and after certain duration time T, environmental climate data A of different bridges and view field bridge deck traffic condition data B are accumulated, a function of corresponding relation is formed and used as a standard for judging whether actual bridges are healthy or not;
in the step d2, accumulating the actual static and dynamic form change law function f '(T/a/B) ═ g' (Cs/Ds) of the actual bridge structure geometric form holographic data Cs and the actual structure dynamic holographic form data Ds obtained under the duration T, the environmental climate data a of different bridges and the visual field bridge deck traffic condition data B; acquiring actual bridge structure geometric form holographic data Cs and actual structure dynamic holographic form data Ds by shooting under the duration T, the environmental climate data A of different bridges and the vision field bridge deck traffic condition data B, and forming a function curve of a corresponding relation after accumulating the certain duration T, the environmental climate data A of different bridges and the vision field bridge deck traffic condition data B for comparing with f (T/A/B) g (Cw/Dw) to judge whether the actual bridge is healthy;
step e, comparing and analyzing a theoretical static and dynamic form change rule [ T/A/B/Cw/Dw ] of the lossless bridge, namely f (T/A/B) ═ g (Cw/Dw), and an actual static and dynamic form change rule [ T/A/B/Cs/Ds ] of the actual bridge, namely f '(T/A/B) ═ g' (Cs/Ds) under the current T time interval and the sight field bridge deck traffic condition data B, and determining that the bridge structure is in a normal state if the difference amplitude relationship between the actual static and dynamic form change rule f '(T/A/B) ═ g' (Cs/Ds) of the bridge structure and the theoretical static and dynamic form change rule f (T/A/B) ═ g (Cw/Dw) of the lossless bridge structure is within a set value range; otherwise, the bridge is considered to have abnormal structural response rules (the structural response rules are generally abnormal due to gradual development of micro-damage), and the monitoring system gives out early warning and outputs the position and the degree of the out-of-range difference of the static and dynamic form rules.
In this embodiment, in step a2, the climate data of the environment where the bridge is located at Ti includes at least one of climate information data of temperature, humidity, sunshine, wind, rain, and snow, and certainly, may further include all climate conditions that affect the bridge, such as earthquake, tsunami, and air ph, and may have a side weight for the difference of the environment where the bridge is located; the data of the traffic condition of the bridge deck at the time of Ti comprises at least one of data of the number of traveling vehicles, the type of vehicles, the weight of the vehicles, the position and the speed in a visual field range, and the data can comprise the passing frequency, the weight of the vehicles and the speed of subways, light rails, trains and the like according to different using conditions of the bridge, and are not described herein again.
In this embodiment, in steps a2 and e, the acquisition of the static image data of the bridge structure at Ti and the dynamic image data of the bridge structure at Ti + Δ time interval may be set as:
simultaneously acquiring static image data of a bridge structure in Ti time and dynamic image data of the bridge structure in Ti + delta time period for the same section structure of the bridge;
or sequentially and continuously acquiring static image data of the bridge structure of the bridge with the plurality of section structures, and sequentially and respectively acquiring dynamic image data of the bridge structure of the plurality of sections;
or, a fixed camera which is set to trigger to acquire static image data and structure dynamic image data of the bridge structure aiming at a specific bridge or a specified structure area, the trigger type acquisition means that when a specific trigger condition is set for the bridge, the fixed camera is instructed to acquire image data, according to the characteristics of the bridge and the traffic routine, triggered data acquisition can be adopted, for example, the static and dynamic deformation of the bridge in the process of passing through the load-carrying vehicle can obviously reflect the health condition of the bridge, triggering to acquire data when the truck with set parameters passes, wherein the condition information data comprises triggering conditions, that is, the trigger data such as the truck and the like, of course, include other condition information data having an influence on the life of the bridge, and the trigger-acquired data includes bridge structure static image data and bridge structure dynamic image data.
In this embodiment, the dynamic video data of the bridge structure includes a vibration mode, an amplitude and a vibration frequency, and the acquisition of these data realizes the euler visual motion information amplification technology by using the existing high-definition camera and the existing computer visual measurement technology, and extracts the motion key information based on SVD decomposition (singular value decomposition), which belongs to the application of the prior art and is not described herein again.
In this embodiment, in step a1, the first acquired condition information data may be acquired in an unloaded state of the bridge, and used as the basic data of the bridge monitoring start to provide the basic data for the final acquisition of the difference amplitude relationship curve.
The monitoring method can also be used for large bridges in construction, the Qj section is a finished bridge section in the construction process, and the spliced sections are suitable for the steps of a, b, c and d in the construction process; however, the condition information data at least includes time duration data and bridge construction state data, and the bridge construction state data generally includes data such as splice length data (having an influence on bridge weight) that has an influence on the bridge structure static image data and the bridge structure dynamic image data of the bridge, and is not described herein again.
The invention also discloses a holographic property and state health monitoring system for the static and dynamic images of the bridge, which comprises the following components:
the condition information data acquisition unit is used for acquiring the condition information data of the bridge;
the image information data acquisition unit is used for acquiring the holographic data of the geometrical form of the bridge and the dynamic holographic characteristic data of the actual structure;
the central processing unit is used for receiving, storing, analyzing and processing the information data of the condition information data acquisition unit, the bridge geometric form holographic data and the actual structure dynamic holographic characteristic data of the image information data acquisition unit, storing, analyzing and processing the theoretical data of the lossless bridge and completing the steps a to e of the bridge static and dynamic image holographic performance health monitoring and diagnosis method;
in this embodiment, the condition information data obtaining unit at least includes a clock unit for obtaining time duration data of the bridge a, an environment information monitoring unit 2 for obtaining environment information data of the bridge, and a bridge deck traffic information monitoring unit 1 for obtaining bridge deck traffic state data; the condition information data comprises time duration data, environmental climate data of the bridge and bridge deck traffic condition data; of course, necessary sensors for acquiring data information of temperature, humidity, sunshine, wind, rain, snow and the like of the representative position at the time of Ti are required, and the details are not repeated herein; the traffic condition data of the bridge deck can be acquired through the video camera, and the detailed description is omitted here
The image information data acquisition unit 3 is an intelligent image acquisition camera capable of automatically rotating in a circling manner in the horizontal direction and the vertical direction, and is used for acquiring a static image and a dynamic video in sections along the length or height of the monitored bridge; the automatic rotation can adopt the existing mechanical driving structure, namely the existing power (motor) is used for driving the camera to rotate in each direction, and the remote control can be used for controlling the camera in the prior art, so that the detailed description is omitted.
As mentioned above and shown in the figures, the system of the present invention is composed of an environmental information monitoring unit (monitoring the environmental climate information of the bridge), a bridge deck traffic information monitoring unit (monitoring the traffic information of the bridge deck), an image information data obtaining unit (monitoring the dynamic and static images of the bridge structure) and a central processing unit (storing an online analysis system of a lossless bridge finite element theoretical model); the environmental climate information monitoring is used for obtaining the environmental climate change information of the bridge, the bridge deck traffic information monitoring is used for obtaining the vehicle load change information acting on the bridge, the image monitoring is used for obtaining the static state form change data of the bridge structure, the video monitoring is used for obtaining the vibration form and dynamic characteristic change data of the bridge structure, and the theoretical response data of the structure of the healthy bridge under the action of the environmental load and the vehicle load are obtained through the theoretical analysis of the lossless bridge.
When the system is used, the central processing unit is used for receiving, storing, analyzing and processing the information data of the clock unit (time duration data T), the environment information monitoring unit (environmental climate data A where the bridge is located), the bridge deck traffic information monitoring unit (bridge deck traffic condition data B) and the image information data acquisition unit, and comparing the actual static and dynamic response [ Cs/Ds ] of each section structure of the bridge under the action of [ T/A/B ] with the theoretical static and dynamic response [ Cw/Dw ] of the lossless bridge to judge whether the structure has obvious damage; and then, performing machine deep learning on historical sample data to obtain a change rule of an actual bridge structure response [ Cs/Ds ] along with [ T/A/B ], performing comparative analysis on the change rule of the actual bridge structure response [ Cs/Ds ] along with the change rule of the theoretical static and dynamic response [ Cw/Dw ] of the lossless bridge along with [ T/A/B ], and judging whether the bridge has micro-damage which causes the abnormal static and dynamic response rule of the actual bridge structure to gradually develop or not according to the conformity.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.
Claims (9)
1. A holographic dynamic health monitoring and diagnosing method for bridge static and dynamic images is characterized in that: comprises the following steps:
a. acquiring initial information data of a bridge structure;
a1. collecting condition information data of Ti;
a2. acquiring Qj section structure static image data of the Ti-time bridge and Qj section structure dynamic video data of the Ti + delta time interval bridge under the condition information data of the step a 1;
a3. analyzing and processing a static image of a Qj section structure of the bridge in Ti to obtain geometric form holographic data Cs of the representation structure deformation characteristic of the actual Qj section of the bridge; analyzing and processing a dynamic video of the Qj section structure of the bridge at Ti + delta to obtain dynamic holographic form data Ds of the Qj section structure of the actual bridge;
b. establishing a refined finite element theoretical model of the lossless bridge;
b1. inputting a structural theoretical state parameter E of the lossless bridge when Ti is input;
b2. substituting the condition information data in the Ti step 1 into a refined finite element theoretical model of the lossless bridge;
b3. according to the steps b1 and b2, calculating theoretical geometric form holographic data Cw of the characteristic structural deformation characteristic of the Ti-time lossless bridge Qj section and theoretical dynamic characteristic data Dw of the Ti + delta-time lossless bridge Qj section structure;
c. comparing and analyzing the geometric form holographic data Cs and the actual structure dynamic holographic form data Ds representing the actual structure deformation characteristics in the step a3 with the corresponding structure deformation theoretical data Cw and the theoretical dynamic characteristic data Dw in the step b3, wherein the difference value between the geometric form holographic data Cs and the actual structure dynamic holographic form data Ds relative to the structure deformation theoretical data Cw and the theoretical dynamic characteristic data Dw is within a set value, the Qj section structure of the bridge is judged to be in a normal state without obvious damage, otherwise, the Qj section structure of the bridge is judged to be in an abnormal structure state with obvious damage, and abnormal parts and degrees are output;
d. if the Qj section structure of the bridge in the step c is in a normal state, the ij loops the steps a2, a3, b2, b3 and c, and machine deep learning is carried out on the accumulated historical sample data;
d1. the method comprises the steps of accumulating the lossless bridge structure deformation theoretical data Cw and the theoretical dynamic characteristic data Dw under different condition information data, establishing a judgment network model of the lossless bridge, continuously accumulating sample data, continuously modifying the judgment network model, and establishing a theoretical static and dynamic form change rule of the structure deformation theoretical data Cw and the theoretical dynamic characteristic data Dw of the theoretical bridge structure along with the action of the different condition information data;
d2, performing machine deep learning on the accumulated historical sample data obtained by the actual bridge, and establishing an actual static and dynamic form change rule of the geometric form holographic data Cs and the actual structure dynamic holographic form data Ds corresponding to the actual bridge structure along with the action of different condition information data;
e. comparing and analyzing the theoretical state change rule model of the lossless bridge under the current condition information data with the structure state change rule model of the actual bridge, and determining that the bridge structure is in a normal state if the difference amplitude relationship between the actual static and dynamic state change rule of the bridge structure and the theoretical static and dynamic state change rule of the lossless bridge is within a set value range by stopping the current time period; otherwise, the bridge is considered to have abnormal structural response rules, and the monitoring system gives out early warning and outputs the position and degree of the out-of-range difference of the static and dynamic form rules.
2. The holographic dynamic image health monitoring and diagnosing method for bridges of claim 1, wherein the method comprises the following steps: the condition information data at least comprises time duration data T, environmental climate data A of the bridge and bridge deck traffic condition data B;
d1, accumulating the lossless bridge structure deformation theoretical data Cw and the theoretical dynamic characteristic data Dw obtained under the duration T, the environmental climate data A of different bridges and the sight field bridge deck traffic condition data B, and establishing a theoretical static and dynamic form change law function f (T/A/B) of the lossless bridge as g (Cw/Dw);
in the step d2, accumulating the actual static and dynamic form change law function f '(T/a/B) ═ g' (Cs/Ds) of the actual bridge structure geometric form holographic data Cs and the actual structure dynamic holographic form data Ds obtained under the duration T, the environmental climate data a of different bridges and the visual field bridge deck traffic condition data B;
step e, comparing and analyzing the theoretical static and dynamic form change rule [ T/A/B/Cw/Dw ] of the lossless bridge under the current T time interval environmental climate data A and the sight field bridge deck traffic condition data B with the actual static and dynamic form change rule [ T/A/B/Cs/Ds ] of the actual bridge, and determining that the bridge structure is in a normal state if the difference amplitude relationship between the actual static and dynamic form change rule f '(T/A/B) ═ g' (Cs/Ds) of the bridge structure and the theoretical static and dynamic form change rule f (T/A/B) ═ g (Cw/Dw) of the lossless bridge structure is within a set value range by stopping the current time interval; otherwise, the bridge is considered to have abnormal structural response rules, and the monitoring system gives out early warning and outputs the position and degree of the out-of-range difference of the static and dynamic form rules.
3. The holographic dynamic image health monitoring and diagnosing method for bridges of claim 1, wherein the method comprises the following steps: in the step a2, the climate data of the environment where the bridge is located at the time of Ti comprises at least one of climate information data of temperature, humidity, sunshine, wind, rain and snow; and the bridge deck traffic condition data at the time of Ti comprises at least one of the data of the number of traveling vehicles, the vehicle type, the vehicle weight, the position and the speed in the visual field range.
4. The holographic dynamic image health monitoring and diagnosing method for bridges of claim 1, wherein the method comprises the following steps: in steps a2 and e, the acquisition of the Ti-time bridge structure static image data and the Ti + Δ time period bridge structure dynamic image data may be set as:
simultaneously acquiring static image data of a bridge structure in Ti time and dynamic image data of the bridge structure in Ti + delta time period for the same section structure of the bridge;
or sequentially and continuously acquiring static image data of the bridge structure of the bridge with the plurality of section structures, and sequentially and respectively acquiring dynamic image data of the bridge structure of the plurality of sections;
or, setting a trigger type fixed camera for acquiring static image data and dynamic image data of the bridge structure aiming at a specific bridge or a specified structural area, wherein the trigger type acquisition refers to indicating the fixed camera to acquire the image data when a specific trigger condition is set for the bridge.
5. The holographic dynamic image health monitoring and diagnosing method for bridges of claim 1, wherein the method comprises the following steps: the bridge structure dynamic video data comprises vibration mode, amplitude and vibration frequency.
6. The holographic dynamic image health monitoring and diagnosing method for bridges of claim 1, wherein the method comprises the following steps: in step a1, the first acquired condition information data may be acquired in an unloaded state of the bridge and used as basic data for the initial monitoring of the bridge.
7. The holographic dynamic image health monitoring and diagnosing method for bridges of claim 1, wherein the method comprises the following steps: if the bridge is a large bridge in construction, the Qj section is a finished bridge section in the construction process, and the condition information data at least comprises time duration data and bridge construction state data.
8. The utility model provides a holographic property health monitoring system of bridge static and dynamic image which characterized in that: the method comprises the following steps:
the condition information data acquisition unit is used for acquiring the condition information data of the bridge;
the image information data acquisition unit is used for acquiring the holographic data of the geometrical form of the bridge and the dynamic holographic characteristic data of the actual structure;
a central processing unit for receiving, storing, analyzing and processing the information data of the condition information data acquisition unit and the bridge geometric shape holographic data and the actual structure dynamic holographic characteristic data of the image information data acquisition unit, and for storing, analyzing and processing the theoretical data of the lossless bridge, and performing the steps a to e of the bridge static and dynamic image holographic performance health monitoring and diagnosis method as claimed in any one of claims 1 to 7.
9. The holographic property health monitoring system of bridge still and moving images of claim 8, wherein: the condition information data acquisition unit at least comprises a clock unit for acquiring the time duration data of the bridge, an environment information monitoring unit for acquiring the environment information data of the bridge and a bridge deck traffic information monitoring unit for acquiring the traffic state data of the bridge deck; the image information data acquisition unit is an intelligent image acquisition camera capable of automatically rotating in a horizontal direction and a vertical direction in a circulating manner and is used for acquiring static images and dynamic videos in sections along the length or height of the monitored bridge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910187373.7A CN110411686B (en) | 2019-03-13 | 2019-03-13 | Bridge static and dynamic image holographic property health monitoring and diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910187373.7A CN110411686B (en) | 2019-03-13 | 2019-03-13 | Bridge static and dynamic image holographic property health monitoring and diagnosis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110411686A CN110411686A (en) | 2019-11-05 |
| CN110411686B true CN110411686B (en) | 2021-03-23 |
Family
ID=68358151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910187373.7A Active CN110411686B (en) | 2019-03-13 | 2019-03-13 | Bridge static and dynamic image holographic property health monitoring and diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110411686B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818455B (en) * | 2021-02-22 | 2023-04-18 | 深圳市市政设计研究院有限公司 | Bridge structure response monitoring method and system |
| CN113408396B (en) * | 2021-06-15 | 2022-03-18 | 广西交科集团有限公司 | Bridge intelligent sensing system based on cloud computing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102645173A (en) * | 2011-02-16 | 2012-08-22 | 张文杰 | Multi-vision-based bridge three-dimensional deformation monitoring method |
| CN104199410A (en) * | 2014-08-27 | 2014-12-10 | 重庆大学 | Bridge-structure universal acquisition control system for health monitoring |
| CN105987672A (en) * | 2016-05-09 | 2016-10-05 | 周劲宇 | Structural deformation monitoring method based on contour line image stacking difference analysis |
| CN108776040A (en) * | 2018-06-11 | 2018-11-09 | 重庆交通大学 | Bridge security cruising inspection system based on tcm methods and diagnostic method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101613815B1 (en) * | 2015-01-29 | 2016-04-20 | 연세대학교 산학협력단 | System and method for image-based structural health monitoring suitable for structures having uncertain load conditions and support conditions |
-
2019
- 2019-03-13 CN CN201910187373.7A patent/CN110411686B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102645173A (en) * | 2011-02-16 | 2012-08-22 | 张文杰 | Multi-vision-based bridge three-dimensional deformation monitoring method |
| CN104199410A (en) * | 2014-08-27 | 2014-12-10 | 重庆大学 | Bridge-structure universal acquisition control system for health monitoring |
| CN105987672A (en) * | 2016-05-09 | 2016-10-05 | 周劲宇 | Structural deformation monitoring method based on contour line image stacking difference analysis |
| CN108776040A (en) * | 2018-06-11 | 2018-11-09 | 重庆交通大学 | Bridge security cruising inspection system based on tcm methods and diagnostic method |
Non-Patent Citations (2)
| Title |
|---|
| 基于NURBS曲面叠差分析的桥面变形监测方法;侯旭 等;《实验室研究与探索》;20181031;第37卷(第10期);第38-42页 * |
| 高速铁路大型桥梁结构健康监测与状态评估研究;魏召兰;《中国博士学位论文全文数据库 工程科技Ⅱ辑》;20131015(第10期);第C034-20页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110411686A (en) | 2019-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3457326B1 (en) | Method and device for monitoring icing of wind turbine blade | |
| CN111710165B (en) | Bridge supervision and early warning method and system based on multi-source monitoring data fusion and sharing | |
| CN105528891A (en) | Traffic flow density detection method and system based on unmanned aerial vehicle monitoring | |
| CN110411686B (en) | Bridge static and dynamic image holographic property health monitoring and diagnosis method and system | |
| DE102017219747A1 (en) | Device for detecting the state of a built-in object, device for detecting an operation and method for detecting the state of a built-in object | |
| CN115808324B (en) | Light safety management monitoring method and system for small and medium span bridges | |
| CN115373403B (en) | Inspection service system for construction machinery equipment | |
| CN112000654B (en) | High-speed railway strong wind monitoring data quality control method and device | |
| CN108776040B (en) | Bridge safety inspection system and diagnosis method | |
| CN117172414A (en) | Building curtain construction management system based on BIM technology | |
| CN115527364B (en) | Traffic accident tracing method and system based on radar data fusion | |
| CN111259770A (en) | Rapid cable force testing system and method based on unmanned aerial vehicle platform and deep learning under complex background | |
| CN116912551A (en) | Expressway equipment monitoring system based on Internet of vehicles | |
| CN116295637A (en) | Intelligent monitoring method and system for safety of high-altitude building | |
| CN115761487A (en) | Method for quickly identifying vibration characteristics of small and medium-span bridges based on machine vision | |
| CN117314397B (en) | Safety inspection method based on bridge construction, electronic equipment and storage medium | |
| CN116311150B (en) | Bridge damage assessment and early warning method based on specific vehicle deflection monitoring | |
| CN116665125A (en) | Intelligent recognition system for bridge tunnel diseases | |
| CN116306262A (en) | Galvanized steel corrosion prediction method based on ensemble learning algorithm | |
| CN114333331B (en) | Method and system for identifying vehicle passing information and vehicle weight of multi-lane bridge | |
| CN115685786A (en) | Bridge online simulation and evaluation system based on temperature monitoring load | |
| CN112801072A (en) | Elevator non-flat-layer door opening fault recognition device and method based on computer vision | |
| CN112415217A (en) | Vehicle speed measuring method based on video | |
| Song et al. | Design of cable detection robot and image detection method | |
| CN116560219B (en) | Self-adaptive monitoring control method and system based on transmission tower wind speed joint analysis |
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 |