CN116955948A - Bridge structure health prediction method and system - Google Patents
Bridge structure health prediction method and system Download PDFInfo
- Publication number
- CN116955948A CN116955948A CN202310828731.4A CN202310828731A CN116955948A CN 116955948 A CN116955948 A CN 116955948A CN 202310828731 A CN202310828731 A CN 202310828731A CN 116955948 A CN116955948 A CN 116955948A
- Authority
- CN
- China
- Prior art keywords
- bridge
- sequence
- data
- state data
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012544 monitoring process Methods 0.000 claims abstract description 63
- 238000009825 accumulation Methods 0.000 claims abstract description 51
- 230000004044 response Effects 0.000 claims abstract description 29
- 230000002087 whitening effect Effects 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000006073 displacement reaction Methods 0.000 claims description 23
- 230000001133 acceleration Effects 0.000 claims description 20
- 238000011156 evaluation Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000013500 data storage Methods 0.000 claims description 6
- 230000006835 compression Effects 0.000 claims description 2
- 238000007906 compression Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 28
- 230000002159 abnormal effect Effects 0.000 description 14
- 238000013461 design Methods 0.000 description 13
- 230000009471 action Effects 0.000 description 12
- 238000007689 inspection Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 11
- 238000012937 correction Methods 0.000 description 9
- 238000007726 management method Methods 0.000 description 9
- 230000003068 static effect Effects 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 239000004973 liquid crystal related substance Substances 0.000 description 8
- 238000012423 maintenance Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 7
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 6
- 230000006378 damage Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000001228 spectrum Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000012800 visualization Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013016 damping Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000006424 Flood reaction Methods 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012933 kinetic analysis Methods 0.000 description 1
- 230000009526 moderate injury Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- 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
- G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
Abstract
The invention belongs to the technical field of bridge structure monitoring, and particularly relates to a bridge structure health prediction method and system. The method comprises the following steps: monitoring the bridge state in real time by using a sensor to obtain bridge structure monitoring data; taking a bridge photo by using a camera, and calculating the bridge deformation; preprocessing the acquired bridge structure monitoring data and bridge deformation to obtain a time sequence of processed bridge state data, and performing accumulation and mean value operation on the time sequence of the bridge state data to obtain an accumulation sequence and a mean value sequence of the bridge state data; generating a gray prediction model through a whitening equation, and calculating a least square estimation parameter value of the gray prediction model; calculating a time response sequence of the gray prediction model and a time sequence predicted value of original bridge state data according to a least square estimated parameter value of the gray prediction model; and (5) checking the precision of the gray prediction model, and combining the gray prediction model meeting the prediction requirement to perform prediction.
Description
Technical Field
The invention belongs to the technical field of bridge structure monitoring, and particularly relates to a bridge structure health prediction method and system.
Background
The bridge is used as an important carrier for public transportation, and plays an important role in smooth running and socioeconomic development of regional transportation. With the leap-type development of social economy, the traffic flow of the bridge is rapidly improved, and the influence of safety hazard of the bridge is aggravated. Bridge damage is caused by factors such as severe service environment, load action, overlong years and the like, diseases are generated, bridge safety is threatened, and bridge accidents are caused. In recent years, bridge safety accidents frequently occur, the social influence is huge, and the life safety hazard of people is serious.
At present, bridge maintenance digitization is imperative. In order to realize the knowing and testability of the bridge life line state at each stage, the health dynamic and safety state of the bridge can be known and mastered in time, the design theory is verified, the subsequent bridge design of the same type is guided, and a scientific operation period health and safety monitoring system is established for the bridge. Based on the method, the invention provides a bridge structure health prediction method and a bridge structure health prediction system.
Disclosure of Invention
In order to overcome the problems in the prior art, the invention provides a bridge structure health prediction method and system.
The technical scheme for solving the technical problems is as follows:
in a first aspect, the invention provides a method for predicting bridge structural health, comprising the following steps:
step 1, monitoring the bridge state in real time by using a sensor, obtaining bridge structure monitoring data, shooting a bridge photo by using a camera, and calculating the bridge displacement, namely the bridge deformation;
step 2, preprocessing the acquired bridge structure monitoring data and bridge deformation amount to obtain a time sequence of the processed bridge state data, and performing accumulation and mean value operation on the time sequence of the bridge state data to obtain an accumulation sequence and a mean value sequence of the bridge state data;
step 3, generating a gray prediction model through a whitening equation according to the time accumulation sequence and the mean value sequence of the bridge state data, and calculating the least square estimation parameter value of the gray prediction model;
step 4, calculating a time response sequence of the gray prediction model and a time sequence predicted value of original bridge state data according to the least square estimated parameter value of the gray prediction model;
step 5, checking the precision of the prediction model, and if the precision of the prediction model does not meet the prediction requirement, correcting the prediction model until the prediction model meeting the prediction requirement is obtained; and carrying out prediction by combining a prediction model meeting the prediction requirements.
Further, the sensor includes: temperature and humidity meter, stress sensor, strain sensor, acceleration sensor, deflection sensor.
Further, in the step 1, a camera is used to take a photograph of the bridge, and the bridge displacement, that is, the bridge deformation, is calculated, and the specific steps include:
setting a calibration object at a bridge key point, taking a bridge local photo at fixed time by adopting a camera, calibrating a pixel at the initial calibration object position to be 0, acquiring a pixel for moving the calibration object by a machine vision algorithm, comparing the pixel with the pixel at the initial calibration object position, and calculating a displacement amount, namely a bridge deformation amount; the bridge key point comprises a bridge compression stress concentration area, or a bridge back tension stress concentration area between two bridge piers, or a guy cable or sling, or a key member.
Further, in the step 2, the time sequence of the bridge state data is subjected to accumulation and mean value operation, and the obtained accumulation sequence and mean value sequence of the bridge state data specifically include the following steps:
establishing a level ratio generating operator, comparing adjacent two processed time sequences of bridge state data with each other, and calculating to obtain the time sequence data level ratio of the bridge state data;
And judging whether the time sequence data level ratio of the bridge state data is in a coverage interval range, and if so, performing accumulation and mean value operation on the time sequence of the bridge state data to obtain an accumulation sequence and a mean value sequence of the bridge state data.
Further, step 4 specifically includes: discretizing the whitening equation to obtain a time response sequence of the gray prediction model: and obtaining a time sequence predicted value of the original bridge state data according to the weighted fractional order inverse accumulation operation.
In a second aspect, the invention also provides a bridge structure health prediction system, which comprises a data acquisition and data storage module and a bridge structure health index prediction algorithm module;
the data acquisition and data storage module comprises a plurality of sensors for detecting the bridge and cameras for locally and fixedly shooting the bridge, and the sensors are used for monitoring the bridge state in real time to obtain bridge structure monitoring data and bridge structure monitoring data; taking a bridge photo by using a camera, and calculating the bridge displacement, namely the bridge deformation; preprocessing the acquired bridge structure monitoring data and bridge deformation quantity to obtain a time sequence of processed bridge state data;
The bridge structure health index prediction algorithm module is used for carrying out accumulation and average value operation on the time sequence of the bridge state data to obtain an accumulation sequence and an average value sequence of the bridge state data; generating a gray prediction model through a whitening equation according to the accumulation sequence and the average value sequence of the bridge state data, and calculating the least square estimation parameter value of the gray prediction model; calculating a time response sequence of the gray prediction model and a time sequence predicted value of original bridge state data according to a least square estimated parameter value of the gray prediction model;
the bridge structure early warning and safety evaluation module is used for checking the precision of the prediction model, and if the precision of the prediction model does not meet the prediction requirement, the prediction model is corrected until the prediction model meeting the prediction requirement is obtained; and carrying out prediction by combining a prediction model meeting the prediction requirements.
In a third aspect, the present invention also provides a bridge structure health prediction apparatus, including: a processor, a memory, and a program; the program is stored in the memory, and the processor calls the program stored in the memory to execute the bridge structure health prediction method according to any embodiment of the first aspect.
In a fourth aspect, the present invention also provides a computer readable storage medium, the computer readable storage medium comprising a stored computer program, wherein the computer program, when executed by a processor, controls a device in which the storage medium is located to perform the bridge structure health prediction method according to any one of the embodiments of the first aspect.
Compared with the prior art, the invention has the following technical effects:
according to the invention, a bridge structure health prediction algorithm library is established based on a gray model, and bridge structure health monitoring indexes with different time dimensions are processed to become regular time sequence data, so that the future development trend of the bridge structure health is predicted.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description is given below of the specific implementation, structure, features and effects of the technical solution according to the present invention with reference to the accompanying drawings and preferred embodiments. The particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
In one embodiment of the present invention, referring to fig. 1, there is provided a bridge structure health prediction method, comprising the steps of:
step 1, monitoring the bridge state in real time by using a sensor to obtain bridge structure monitoring data; and shooting a bridge photo by using a camera, and calculating the bridge displacement, namely the bridge deformation.
The sensor includes but is not limited to a hygrothermograph, a stress sensor, a strain sensor, an acceleration sensor, a deflection sensor. The temperature and humidity meter is used for detecting the temperature and humidity of the bridge key point, the stress sensor is used for detecting the real-time stress of the bridge key point, the strain sensor can be attached to the bridge key point to detect the real-time strain of the bridge key point, the acceleration sensor can detect the vibration speed of the bridge key point in the longitudinal direction of the bridge and the vibration speed of the bridge in the transverse direction of the bridge, and the deflection sensor is used for measuring the sedimentation of the center of the cross section in the vertical direction of the axis when the bridge is bent and deformed.
The key point positions of the sensor or the camera can be arranged in the compressive stress concentration area of the bridge pier, the tensile stress concentration area of the back surface of the middle of the bridge between the two bridge piers, or the position of a guy rope or a sling or a key member, and a group of devices comprising a stress sensor, a strain sensor, an acceleration sensor, the camera and the like can be arranged at each position of the key point positions, so that monitoring data and appearance conditions of the bridge can be recorded and transmitted in real time.
Setting a calibration object at a bridge key point, taking a bridge local photo at fixed time by adopting a camera, calibrating the position of an initial calibration object to be 0, comparing the initial position with a mobile pixel of the calibration object obtained by the existing machine vision algorithm, and calculating the displacement, namely the deformation.
Or setting a calibration object at the bridge key point, calculating the scaling of the bridge local photo according to the size of the calibration object on the bridge key point photo and the actual size of the calibration object, and converting the scaling of the deformation beam local photo at the same local position of the bridge on the bridge local photo at the adjacent time point into the actual bridge deformation.
It should be noted that, the monitoring data of the bridge structure and the key point photo of the bridge are preferably collected at the same time point each time, so that the complete data of the bridge at the time point can be formed.
And 2, preprocessing the acquired bridge structure monitoring data and bridge deformation amount to obtain a time sequence of the processed bridge state data, and performing accumulation and mean value operation on the time sequence of the structural health index data to obtain an accumulation sequence and a mean value sequence of the bridge state data.
And 21, carrying out statistical operation on the acquired bridge structure monitoring data and bridge deformation, wherein the calculation results such as the maximum value, the minimum value, the mean value, the variance, the standard deviation and the like in a preset time period can be used as the input of primary early warning.
The temperature and humidity instrument measures the temperature and humidity of the bridge structure, abnormal points are removed from temperature and humidity data of the bridge structure, and statistical value time-course curves such as the maximum value, the minimum value and the average value of the temperature and humidity are checked according to minutes, hours and days; and configuring an alarm condition of the hygrothermograph, namely setting an alarm threshold of the hygrothermograph, and alarming when the alarm condition of the hygrothermograph is met.
Preprocessing the corresponding data, and removing abnormal points; calculating stress values of all strain points in real time; performing fatigue analysis according to the measured value, and performing rain flow counting statistics on the dynamic strain data of each hour to count the fatigue damage value of each hour; and configuring a strain alarm condition, namely setting a strain alarm threshold value, and alarming when the strain alarm condition is met.
Preprocessing deflection data, and removing abnormal points; checking statistical value time course curves such as maximum deflection, minimum deflection, average deflection and the like according to minutes, hours and days; deflection statistics per hour, day, month, year; and configuring a deflection alarm condition, namely setting a deflection alarm threshold value, and alarming when the deflection alarm condition is met.
After preprocessing the collected bridge structure monitoring data, the method further comprises data secondary preprocessing, digital sampling is carried out on the bridge structure monitoring data measured by each sensor, mathematical transformation, time domain analysis, frequency domain analysis, statistical analysis, modal analysis and other processes are carried out, and statistics is carried out on the data according to the dimensions of time, area and the like, so that the data trend situation is displayed more intuitively, and scientific bridge health assessment and early warning are realized.
And carrying out data post-processing after the data secondary preprocessing, wherein the data post-processing process mainly carries out advanced analysis on bridge structure monitoring data, such as real-time modal analysis, correlation analysis between bridge characteristic quantity and environmental factors, nonlinear regression analysis and the like, and predicts the future development trend of the data, so as to support applications such as anomaly detection, fault diagnosis, health assessment, performance prediction and the like.
Step 22, establishing a time sequence of bridge state data according to four dimensions of time, day, week and month.
Based on bridge structure monitoring data and bridge deformation, such as index data of deflection, strain, displacement, temperature and humidity, four different dimension time sequences of time, day, week, month and the like are respectively generated for each index, and the four dimension time sequences are specifically as follows:
H (0) ＝(h (0) (1),h (0) (2),h (0) (3),h (0) (4),h (0) (5)……h (0) (n))
D (0) ＝(d (0) (1),d (0) (2),d (0) (3),d (0) (4),d (0) (5)……d (0) (n))
W (0) ＝(w (0) (1),w (0) (2),w (0) (3),w (0) (4),w (0) (5)……w (0) (n))
M (0) ＝(m (0) (1),m (0) (2),m (0) (3),m (0) (4),m (0) (5)……m (0) (n))
wherein H is (0) A time sequence series of representing structural health index data, h (0) (i) I=1, 2, 3..n is the sequence of structural health index data at i-th; d (D) (0) D, representing a sequence of days representing structural health index data (0) (i) I=1, 2, 3..n is the sequence of the i-th overpass status data; w (W) (0) Zhou Xulie, w representing bridge status data (0) (i) I=1, 2, 3..n is the sequence of bridge status data at week i; m is M (0) Month sequence representing bridge state data, m (0) (i) I=1, 2,3. N ith month a sequence of bridge status data is provided, n is the number of raw data needed to build the model.
And step 23, performing accumulation and mean value operation on the time sequence of the bridge state data to obtain an accumulation sequence and a mean value sequence of the bridge state data.
Step 231, aiming at the processed bridge shapeEstablishing a level ratio generating operator for comparing the time sequences of the bridge state data after two adjacent processes, and calculating whether the level result meets the requirement Wherein k=2, 3,4, … n; if so, step 232 may be performed.
H (0) The level ratio sigma (H) (k) The method comprises the following steps:
wherein H is (0) (k-1) represents a time series of bridge state data at k-1; h (0) (k) Representing the time series of bridge state data at k.
D (0) The level ratio sigma (D) (k) The method comprises the following steps:
wherein D is (0) (k-1) represents a time series of k-1 th overpass state data; d (D) (0) (k) Representing a time series of kth overpass state data.
W (0) The level ratio sigma (W) (k) The method comprises the following steps:
wherein W is (0) (k-1) represents a time series of bridge status data at week k-1; w (W) (0) (k) Representing the time series of the kth bridge status data.
M (0) The level ratio sigma (M) (k) The method comprises the following steps:
wherein M is (0) (k-1) represents a time series of bridge status data of the kth-1 month; m is M (0) (k) Representing a time series of bridge status data at month k.
Judging whether the time series of the bridge state data have the stage ratios within the range of the coverage range, if so, the stage ratios meetAt that time, the sequence may be modeled.
Step 232, building an accumulation generating operator aiming at the time sequence of the bridge state data, so that the time sequence data of two adjacent bridge state data are added in pairs to generate a time accumulation sequence of the bridge state data.
Accumulation sequence:
H (1) ＝(h (1) (1),h (1) (2),h (1) (3),h (1) (4),h (1) (5)……h (1) (n))
D (1) ＝(d (1) (1),d (1) (2),d (1) (3),d (1) (4),d (1) (5)……d (1) (n))
W (1) ＝(w (1) (1),w (1) (2),w (1) (3),w (1) (4),w (1) (5)……w (1) (n))
M (1) ＝(m (1) (1),m (1) (2),m (1) (3),m (1) (4),m (1) (5)……m (1) (n))
wherein H is (1) A time-accumulated sequence representing structural health index data, Time accumulation sequence of structural health index data at k time, D (1) Day accumulation sequence representing structural health index data, < >>Time accumulation sequence of structural health index data of k days, W (1) Zhou Leijia sequence representing structural health index data,time accumulation sequence of health index data of k-week structure, M (1) Month accumulation sequence representing structural health index data, < + >>A time-accumulated sequence of health index data is structured for k months.
Step 233, establishing a mean value generation operator aiming at the time sequence of the bridge state data, dividing two adjacent time sequence data of two bridge state data by 2, and generating a time mean value sequence of the bridge state data.
Time-average sequence of bridge status data: z is Z (1) (H)＝((h (0) (1)+h (0) (2))/2，(h (0) (2)+h (0) (3))/2，……，(h (0) (n-1)+h (0) (n))/2)；
The daily mean value sequence of bridge state data: z is Z (1) (D)＝((d (0) (1)+d (0) (2))/2，(d (0) (2)+d (0) (3))/2，……，(d (0) (n-1)+d (0) (n))/2)；
Zhou Junzhi sequence of bridge status data: z is Z (1) (W)＝((w (0) (1)+w (0) (2))/2，(w (0) (2)+w (0) (3))/2，……，(w (0) (n-1)+w (0) (n))/2)；
Moon average value sequence of bridge status data: z is Z (1) (M)＝((m (0) (1)+m (0) (2))/2，(m (0) (2)+m (0) (3))/2，……，(m (0) (n-1)+m (0) (n))/2)。
And 3, generating a gray prediction model through a whitening equation according to the time accumulation sequence and the mean value sequence of the bridge state data, and calculating the least square estimation parameter value of the gray prediction model.
Establishing a grey prediction model through a whitening equation:
H (0) (k)+aZ (1) (H)(k)＝b
D (0) (k)+aZ (1) (D)(k)＝b
W (0) (k)+aZ (1) (W)(k)＝b
M (0) (k)+aZ (1) (M)(k)＝b
wherein a is the development coefficient of the model, and b is the ash action amount.
Z (1) (H)(k)＝0.5h (1) (k)+0.5h (1) (k-1)
Z (1) (D)(k)＝0.5d (1) (k)+0.5d (1) (k-1)
Z (1) (M)(k)＝0.5m (1) (k)+0.5m (1) (k-1)
Z (1) (W)(k)＝0.5w (1) (k)+0.5w (1) (k-1)
In the above formula, k=2, 3,4, … n, Z (1) (H) Time-averaged sequence representing bridge status data, Z (1) (D) The space average value sequence representing bridge state data, Z (1) (M) represents a moon average value sequence of bridge state data, Z (1) (W) represents a moon average sequence of bridge status data.
Sequence of parametersThe parameters a and b are obtained by a least square method:
wherein, the liquid crystal display device comprises a liquid crystal display device,
and 4, calculating a time response sequence of the gray prediction model and a time sequence predicted value of the original bridge state data according to the least square estimated parameter value of the gray prediction model.
Discretizing the whitening equation to obtain a time response sequence of the gray prediction model:
where k=2, 3,4, … …, n,a predicted value of the bridge state data in time series when k+1 is the bridge state data;a time series predicted value of bridge state data of k+1 days; />A time series predicted value of bridge state data of k+1 weeks; />Is a time series predicted value of bridge state data of k+1 months.
When processing the original data, they are accumulated to generate data, so that the result of the prediction by the above formula is a predicted value of the generated data, and therefore they are subtracted from the former term to restore the original data. A predictive formula for the raw data is derived. Through the value of k, bridge health index values in four dimensions of time, day, week, month and the like in the future can be predicted. The time sequence predicted value of the original bridge state data is obtained according to the weighted fractional order inverse accumulation operation:
Wherein, the liquid crystal display device comprises a liquid crystal display device,a time sequence predicted value of the original bridge state data when k+1 is adopted; />A time series predicted value of the original bridge state data of k+1 days; />A time series predicted value of the original bridge state data of k+1 weeks; />A time sequence predicted value of the original bridge state data of k+1 months; />A predicted value of the bridge state data in time series when k is the bridge state data; />A time sequence predicted value of bridge state data of k days; />A time series predicted value of bridge state data of k weeks; />And the predicted value is a time sequence predicted value of bridge state data of k months.
The predicted value is compared with threshold values set in deflection, stress, displacement and the like when the bridge is designed, when the predicted value exceeds the alarm threshold value for many times in a certain time period in the future, the potential safety hazard of the bridge can be judged, maintenance measures can be adopted in advance to intervene, and the service life of the bridge is prolonged.
Step 5, checking the precision of the prediction model, and if the precision of the prediction model does not meet the prediction requirement, correcting the prediction model until the prediction model meeting the prediction requirement is obtained; and carrying out prediction by combining a prediction model meeting the prediction requirements.
And (3) adopting a model correction technology combining static and dynamic force, optimizing and calculating according to actual measurement static and dynamic response of a load test and initial data of health monitoring, so that the deviation between an actual model and a theoretical model is within an engineering allowable range, and a relatively real bridge model is obtained and is used for structural response early warning analysis and limit state evaluation.
The static and dynamic combined model correction technology can be used for more accurately evaluating the health condition of the bridge and more rapidly and efficiently monitoring the bridge, and specifically comprises the following steps:
step 51, adopting a stress balance equation to carry out statics analysis on the bridge;
and carrying out statics analysis on the bridge, determining stress characteristics of the bridge, and calculating parameters such as stress, deformation and the like of the bridge. These parameters can be used for subsequent kinetic analysis and grey prediction model correction.
Σfx=0: indicating that the resultant of all horizontal forces acting on the object in the horizontal direction of the beam or column is zero.
Σfy=0: indicating that the combined force of all vertically directed forces acting on the object in the vertical direction of the beam or column is zero.
Σm=0: indicating that the resultant of all forces acting on the object is zero against the moment generated by the centre of rotation in which the object is located.
Wherein Σ represents a symbol for summing all forces, fx and Fy represent forces in the horizontal and vertical directions, and M represents a moment generated by the force on the center of rotation.
Step 52, carrying out dynamics analysis on the bridge by adopting a modal analysis method;
the free vibration and the forced vibration of the bridge are obtained through the vibration sensor, the free vibration and the forced vibration of the bridge are analyzed to obtain vibration characteristic parameters of the bridge, such as resonance frequency, damping ratio, modal morphology and the like, the parameters can reflect the health state of the bridge structure, and whether the bridge is damaged or diseased is identified through comparison with a reference value of the health state.
Where x (t) represents the vibrational displacement of the structure at time t, an represents the amplitude of the nth vibrational mode,represents the phase angle, ζ represents the damping ratio of the structure, ωn represents the n-th structure natural frequency, +.>Represents the vibration phase angle, ωd represents the dynamic frequency of the structure, ωd= v (1- ζ 2) ×ωn.
Step 53, carrying out grey prediction model correction on the bridge by adopting a model test method;
based on the statics and dynamics analysis results, the gray prediction model is corrected, model parameters are adjusted, and the accuracy and reliability of the model are improved. In the correction process, a model test method is adopted to continuously compare actual measurement data with simulation prediction results, and the prediction accuracy of a model is optimized.
Q_m＝Q_s*(l_m/l_s)^n
Wherein Q_m represents the physical quantity of the model, Q_s represents the physical quantity of the actual structure, and n is the index of the physical quantity; l_s represents the actual structural length of the model, and l_m represents the characteristic length of the model.
Step 54, performing model verification by adopting an error analysis method;
and verifying the corrected gray prediction model by adopting an error analysis method, comparing the difference between the prediction result and actual monitoring data, and evaluating the accuracy and reliability of the corrected gray prediction model. If there is a deviation, the next round of correction is required.
The true value refers to the true value of the measured physical quantity, which is generally represented by the symbol x.
The measured value refers to the value predicted in the gray prediction model, and is generally represented by the symbol x'.
Absolute error refers to the difference between the measured value and the true value, and is generally represented by the symbol Δx. The absolute error is calculated by the following formula:
Δx＝x'-x
the relative error refers to the ratio between the absolute error and the true value, and is generally represented by the symbol epsilon. The calculation formula of the relative error is:
ε＝(Δx/x)*100％
the standard deviation refers to the square of the mean of the sum of squares of the deviations between the measured values obtained by the multiple measurements and the mean. The standard deviation is calculated by the following formula:
s＝√[Σ(x'-x)^2/(n-1)]
where n is the number of measurements.
In some embodiments, the method further comprises the step of evaluating the structural safety state of the bridge according to the prediction result of the gray prediction model, and mainly comprises the following steps:
performing security first-level evaluation according to the prediction result of the gray level prediction model, and starting security second-level evaluation when the integral response abnormality of the structure is found; when the local response abnormality of the structure is found, starting special examination; and if the bridge damage is found, carrying out safety secondary evaluation by using the monitoring data and the special inspection result.
The security level evaluation includes: the gray level prediction model can predict predicted values of temperature and humidity of bridge key points, real-time stress of the bridge key points, real-time strain of the bridge key points detected by the bridge key points, vibration speed of the bridge key points in the longitudinal direction of the bridge, vibration speed of the bridge in the transverse direction of the bridge, bridge type variable and the like, the predicted values are compared with threshold values set in deflection, stress, displacement and the like when the bridge is designed, when the predicted values exceed the alarm threshold values in a future time period, special inspection is started, curing measures are adopted in advance for intervention in a targeted mode, and the service life of the bridge is prolonged.
For example, a safety level assessment of critical components using strain: when the stress does not exceed a preset threshold value, the stress state of the member at the monitoring point is normal; when the stress exceeds a preset threshold, the stress state of the component at the monitoring point is abnormal.
And when the maximum stress value is smaller than the fatigue allowable stress of the components specified by the specification, the fatigue state of the components at the monitoring points is normal. Otherwise, the fatigue state of the member at the monitoring point is abnormal, and the fatigue accumulated damage index of the member at the monitoring point is calculated by adopting a rain flow method and a Miner criterion to evaluate the fatigue state.
First-level assessment of cable structure safety: when the stress of the inhaul cable or the sling is smaller than a preset threshold value, the inhaul cable is in a normal state; otherwise, the state of the inhaul cable is judged to be abnormal, and special inspection is carried out. And when the maximum stress of the inhaul cable or the sling is larger than the standard allowable fatigue stress, judging that the fatigue state of the inhaul cable or the sling is abnormal, and evaluating the fatigue state.
Carrying out security primary assessment by using an operation load structure check coefficient: under the action of natural vehicle load, the ratio of the structural response value at the loading moment of the least favorable position of the displacement influence line to the structural response calculated value under the action of the vehicle load at the moment is obtained, namely the operating load structural verification coefficient. When the total weight of a single vehicle passing through a heavy vehicle on a bridge at a specific moment is not less than 30t and the verification coefficient of an operation load structure is less than 1, the structure is judged to be in a normal state, otherwise, the structure is judged to be abnormal.
Non-monitored component safety primary assessment: and establishing a finite element model based on the geometric characteristic parameters of the actual physical characteristic parameters of the bridge member and the structural boundary conditions. And calculating the integral internal force and the linear shape of the structure by using the monitored environment, the vehicle load and the structural response, and comparing with a preset threshold value. The internal force and the line shape of the whole structure meet the design specification requirements of the bridge, and the structure is judged to be in a normal state, otherwise, the structure is judged to be abnormal.
Safety primary assessment is performed by utilizing structural dynamic characteristics: based on the monitored acceleration, a modal analysis is employed to obtain structural dynamics. And comparing the obtained structural dynamic characteristic with a preset threshold value. And monitoring that the ratio of the obtained self-vibration frequency of the bridge structure to the designed theoretical calculation frequency is greater than or equal to 1, and judging that the structure is in a normal state. Otherwise, judging that the structural state is abnormal.
The safety secondary evaluation triggering conditions are as follows: and according to the prediction result of the gray level prediction model, the whole is abnormal. The security secondary evaluation method is as follows: and carrying out structural damage identification and gray level prediction model correction on the basis of prediction data, a safety primary evaluation result and a special inspection result in the safety secondary evaluation, and then carrying out structural re-analysis and ultimate bearing capacity analysis on the basis of the corrected finite element model.
Special inspection trigger conditions: the structure locally responds to the effects of anomalies or external harsh factors. Structural local response anomalies such as: the accumulated days of the steel structure with the relative humidity of more than 60 percent are more than 365d; the key component tensile stress and the compressive stress are larger than a preset threshold value, and the component stress state at the monitoring point is judged to be abnormal; or the fatigue state of the key component exceeds the moderate damage, and judging that the fatigue state of the component at the monitoring point is abnormal; and the sling stress is larger than or equal to a preset threshold value, and the abnormal state of the cable body structure is judged. External bad factors such as: the bridge encounters floods; or subject to drift and ship impact; or the average wind speed is greater than the design wind speed; or the horizontal acceleration peak value of the earthquake motion is larger than the acceleration peak value of the earthquake action of the design E1; or special vehicle bridge crossing, truck traffic jam and other emergency events occur.
The special inspection method comprises the following steps:
(1) The average wind speed is greater than the design wind speed:
calculating wind parameters such as the average wind speed, the wind attack angle of wind direction, the turbulence intensity, the pulsation wind speed spectrum and the like of the strong wind and the change trend of the wind parameters along with time by taking 10 minutes as a time interval;
taking 10 minutes as a time interval, calculating and analyzing the amplitude value and the root mean square value of the acceleration of the bridge girder under the action of strong wind; when the actually measured average wind speed is in a girder vortex-induced vibration locking area and the root mean square value of the girder vibration acceleration exceeds the travelling comfort limit value, the occurrence of vortex-induced vibration of the bridge can be judged, and safety evaluation is carried out;
When the measured average wind speed is larger than the bridge flutter critical wind speed and the vibration amplitude of the bridge girder is continuously increased along with time, the occurrence of the bridge flutter can be judged, safety evaluation is carried out, and bridge emergency management measures are adopted;
and taking 10 minutes as a time interval, calculating and analyzing the maximum value, the minimum value, the change amplitude and the change trend of the maximum value, the minimum value, the change amplitude and the change trend along with time of the bridge girder horizontal deformation, the tower top deflection, the cable force, the key component strain and the like under the action of strong wind, and carrying out safety evaluation.
Selecting monitoring data of bridge acceleration before and after strong wind action, calculating the modal parameters and the change rules of the bridge at intervals of 10 minutes, and analyzing the correlation between the modal parameters and wind parameters of the bridge; when the bridge modal parameters obviously change before and after the strong wind acts, carrying out special inspection on the bridge, determining the reasons of the bridge modal parameter changes, and evaluating the bridge structural state;
and calculating the correlation between the data such as the displacement and acceleration of the bridge girder, the cable force and the strain of key components and wind parameters (including average wind speed, wind direction, wind attack angle, turbulence intensity and the like), and analyzing the change rule of the bridge structure response along with the wind parameters under the action of wind load.
(2) When the horizontal acceleration peak value of the earthquake is larger than the acceleration peak value corresponding to the earthquake action of the design E1:
analyzing the seismic data, and analyzing the seismic traveling wave effect characteristics of the three-dimensional seismic data at different positions;
the absolute maximum value, the root mean square value and the frequency spectrum of the response data of the bridge integral structure such as acceleration, deformation, displacement and the like in the earthquake process are analyzed, the absolute maximum value and the root mean square value of the local response data of the structure such as support displacement, strain, cable force and the like are analyzed, and safety evaluation is carried out according to relevant regulations;
the method comprises the steps of selecting acceleration monitoring data before and after earthquake action, analyzing modal parameters of a bridge structure, and evaluating the state of the bridge structure according to relevant regulations when the modal parameters are obviously changed;
and inputting the actually measured seismic acceleration time course into a corrected finite element model (considering the traveling wave effect of the earthquake) for structural power analysis, and evaluating the bridge structural state according to related regulations.
(3) Analyzing the absolute maximum value, the root mean square value, the frequency spectrum and the attenuation law of the acceleration response within 20 seconds after the bridge is impacted by the ship and near the bridge pier bottom, the girder and the top of the bridge tower at the ship collision position;
analyzing absolute maximum values, root mean square values and frequency spectrums of structural overall response monitoring data such as deformation, displacement and the like within 20 seconds after the ship is bumped, analyzing absolute maximum values and root mean square values of structural local response monitoring data such as support displacement, strain and cable force and the like, and carrying out safety evaluation according to relevant regulations;
The method comprises the steps of selecting acceleration monitoring data before and after the ship is bumped to perform modal analysis, and evaluating the bridge structure state according to relevant regulations when modal parameters are obviously changed;
and correcting the finite element model of the bridge according to relevant regulations after the ship is bumped. And carrying out stress re-analysis and ultimate bearing capacity analysis on the bridge structure by utilizing the modified bridge finite element model, evaluating the state of the bridge structure according to related regulations, and carrying out special inspection.
(4) Special vehicle bridge crossing, truck traffic jam and other emergency events;
and carrying out special evaluation according to specific conditions of special vehicle passing, truck traffic jam and other emergency events.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited in the present invention, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the invention also provides a bridge structure health prediction system for realizing the bridge structure health prediction method. The implementation of the solution provided by the system is similar to that described in the above method, so the specific limitation of one or more system embodiments provided below may be referred to the limitation of a bridge structure health prediction method hereinabove, and will not be described herein.
In one embodiment, a bridge structure health prediction system is provided, which comprises a data acquisition and data storage module, a bridge structure health index prediction algorithm module, a bridge structure early warning and safety evaluation module, a digital twin visualization module and a bridge daily nutrition module;
the data acquisition and data storage module comprises a plurality of sensors for detecting the bridge and cameras for locally and fixedly shooting the bridge, and the sensors are used for monitoring the bridge state in real time to obtain bridge structure monitoring data and bridge structure monitoring data; taking a bridge photo by using a camera, and calculating the bridge displacement, namely the bridge deformation; preprocessing the acquired bridge structure monitoring data and bridge deformation quantity to obtain a time sequence of processed bridge state data;
The bridge structure health index prediction algorithm module is used for carrying out accumulation and average value operation on the time sequence of the bridge state data to obtain an accumulation sequence and an average value sequence of the bridge state data; generating a gray prediction model through a whitening equation according to the accumulation sequence and the average value sequence of the bridge state data, and calculating the least square estimation parameter value of the gray prediction model; calculating a time response sequence of the gray prediction model and a time sequence predicted value of original bridge state data according to a least square estimated parameter value of the gray prediction model;
specifically, a time sequence of bridge state data is established according to four dimensions of time, day, week and month;
the sensor and the machine vision technology are used for collecting index data such as healthy deflection, strain, displacement, temperature and humidity of the bridge structure, and four different dimension time sequences such as time, day, week and month are respectively generated for each index, and the four dimension time sequences are specifically as follows:
H (0) ＝(h (0) (1),h (0) (2),h (0) (3),h (0) (4),h (0) (5)……h (0) (n))
D (0) ＝(d (0) (1),d (0) (2),d (0) (3),d (0) (4),d (0) (5)……d (0) (n))
W (0) ＝(w (0) (1),w (0) (2),w (0) (3),w (0) (4),w (0) (5)……w (0) (n))
M (0) ＝(m (0) (1),m (0) (2),m (0) (3),m (0) (4),m (0) (5)……m (0) (n))
wherein H is (0) Time sequence representing bridge state data, h (0) (1) A sequence of bridge state data at time 1; d (D) (0) Representing a sequence of days representing bridge status data, d (0) (1) A sequence of overpass status data 1; w (W) (0) Zhou Xulie, w representing bridge status data (0) (1) A sequence of bridge status data at week 1; m is M (0) Month sequence representing bridge state data, m (0) (1) Is the sequence of bridge state data of 1 month, nRepresenting the amount of data in the time frame.
Aiming at the time series of bridge state data, a level ratio generating operator is established, the time series of two adjacent bridge state data are compared with each other, and whether the level result meets the requirement or not is calculatedWhere k=2, 3, 4, … … n.
H (0) The level ratio sigma (H) (k) The method comprises the following steps:
wherein H is (0) (k-1) represents a time series of bridge state data at k-1; h (0) (k) Representing the time series of bridge state data at k.
D (0) The level ratio sigma (D) (k) The method comprises the following steps:
wherein D is (0) (k-1) represents a time series of k-1 th overpass state data; d (D) (0) (k) Representing a time series of kth overpass state data.
W (0) The level ratio sigma (W) (k) The method comprises the following steps:
wherein W is (0) (k-1) represents a time series of bridge status data at week k-1; w (W) (0) (k) Representing the time series of the kth bridge status data.
M (0) The level ratio sigma (M) (k) The method comprises the following steps:
wherein M is (0) (k-1) represents a time series of bridge status data of the kth-1 month; m is M (0) (k) Representing a time series of bridge status data at month k.
Judging whether the level ratio of the bridge structure time sequence data is within the range of the coverage range, if so, the level ratio meets At that time, the sequence may be modeled.
And establishing an accumulation generating operator aiming at the time sequence of the bridge state data, so that the time sequence data of two adjacent bridge state data are added in pairs to generate a time accumulation sequence of the bridge state data.
Accumulation sequence:
H (1) ＝(h (1) (1),h (1) (2),h (1) (3),h (1) (4),h (1) (5)……h (1) (n))
D (1) ＝(d (1) (1),d (1) (2),d (1) (3),d (1) (4),d (1) (5)……d (1) (n))
W (1) ＝(w (1) (1),w (1) (2),w (1) (3),w (1) (4),w (1) (5)……w (1) (n))
M (1) ＝(m (1) (1),m (1) (2),m (1) (3),m (1) (4),m (1) (5)……m (1) (n))
wherein H is (1) A time-accumulated sequence representing structural health index data,time accumulation sequence of structural health index data at k time, D (1) Day accumulation sequence representing structural health index data, < >>Time accumulation sequence of structural health index data of k days, W (1) Representing structural health indexThe Zhou Leijia sequence of the data was taken,time accumulation sequence of health index data of k-week structure, M (1) Month accumulation sequence representing structural health index data, < + >>A time-accumulated sequence of health index data is structured for k months.
And establishing a mean value generation operator aiming at the time sequence of the bridge state data, dividing two adjacent two time sequence data of the bridge state data by 2, and generating a time mean value sequence of the bridge state data.
Time-average sequence of bridge status data: z is Z (1) (H)＝((h (0) (1)+h (0) (2))/2，(h (0) (2)+h (0) (3))/2，……，(h (0) (n-1)+h (0) (n))/2)；
The daily mean value sequence of bridge state data: z is Z (1) (D)＝((d (0) (1)+d (0) (2))/2，(d (0) (2)+d (0) (3))/2，……，(d (0) (n-1)+d (0) (n))/2)；
Zhou Junzhi sequence of bridge status data: z is Z (1) (W)＝((w (0) (1)+w (0) (2))/2，(w (0) (2)+w (0) (3))/2，……，(w (0) (n-1)+w (0) (n))/2)；
Moon average value sequence of bridge status data: z is Z (1) (M)＝((m (0) (1)+m (0) (2))/2，(m (0) (2)+m (0) (3))/2，……，(m (0) (n-1)+m (0) (n))/2)。
And generating a gray prediction model through a whitening equation according to the time accumulation sequence and the average value sequence of the bridge state data, and calculating the least square estimation parameter value of the gray prediction model.
Establishing a grey prediction model through a whitening equation:
H (0) (k)+aZ (1) (H)(k)＝b
D (0) (k)+aZ (1) (D)(k)＝b
W (0) (k)+aZ (1) (W)(k)＝b
M (0) (k)+aZ (1) (M)(k)＝b
wherein a is the development coefficient of the model, and b is the ash action amount.
Z (1) (H)(k)＝0.5h (1) (k)+0.5h (1) (k-1)
Z (1) (D)(k)＝0.5d (1) (k)+0.5d (1) (k-1)
Z (1) (M)(k)＝0.5m (1) (k)+0.5m (1) (k-1)
Z (1) (W)(k)＝0.5w (1) (k)+0.5w (1) (k-1)
In the above formula, k=2, 3,4, … n, Z (1) (H) Time-averaged sequence representing bridge status data, Z (1) (D) The space average value sequence representing bridge state data, Z (1) (M) represents a moon average value sequence of bridge state data, Z (1) (W) represents a moon average sequence of bridge status data.
Sequence of parametersThe parameters a and b are obtained by a least square method:
wherein, the liquid crystal display device comprises a liquid crystal display device,
/>
and calculating a time response sequence of the gray prediction model and a time sequence predicted value of the original bridge state data according to the least square estimation parameter value of the gray prediction model.
And whitening the gray model to obtain a time response sequence of the gray prediction model:
where k=2, 3,4, … …, n,a predicted value of the bridge state data in time series when k+1 is the bridge state data;a time series predicted value of bridge state data of k+1 days; />A time series predicted value of bridge state data of k+1 weeks; / >Is a time series predicted value of bridge state data of k+1 months.
The time sequence predicted value of the original bridge state data is obtained according to the weighted fractional order inverse accumulation operation:
wherein, the liquid crystal display device comprises a liquid crystal display device,a time sequence predicted value of the original bridge state data when k+1 is adopted; />A time series predicted value of the original bridge state data of k+1 days; />A time series predicted value of the original bridge state data of k+1 weeks; />A time sequence predicted value of the original bridge state data of k+1 months; />A predicted value of the bridge state data in time series when k is the bridge state data; />A time sequence predicted value of bridge state data of k days; />A time series predicted value of bridge state data of k weeks; />And the predicted value is a time sequence predicted value of bridge state data of k months.
The structure early warning and safety assessment module adopts a model correction technology combining static and dynamic force, optimizes and calculates according to actual measurement static and dynamic response of a load test and initial data of health monitoring, enables deviation between an actual model and a theoretical model to be in an engineering allowable range, realizes more accurate prediction and control of internal force and deformation of a bridge structure, and obtains a more real bridge model for structural response early warning analysis and limit state assessment; the static and dynamic combined model correction technology can evaluate the health condition of the bridge more accurately, monitor the bridge more rapidly and efficiently, improve the safety and reliability of the bridge, and reduce the bridge monitoring cost.
The system may further comprise: the digital twin visualization module is used for constructing a map of the bridge by means of various technologies such as GIS, BIM, machine vision, artificial intelligence and the Internet of things, and is combined with a bridge BIM model, a machine vision system, a sensing system and a bridge health management system to realize the integrated presentation of bridge dynamic sensing time and space, the visualization alarm positioning, event linkage and emergency dispatch and the like, so that rapid and effective decision support is provided for scientific management, safety early warning and accurate maintenance of the health state of the bridge.
And the global integrated live-action digital twin platform based on accurate geographic position data such as longitude, latitude, altitude and the like is realized by depending on a big data application platform from a global view angle positioning to a bridge three-dimensional scene. And 3, visual and accurate three-dimensional real scene management of spatial positions is performed, and global is summarized. The multi-path cameras are spliced and fused in a panoramic manner, and the panoramic dynamic control of the scene in the bridge deck area solves the problems of scattered, split and non-visual monitoring videos in a large number. And the whole video picture of the bridge can be browsed globally in one picture, so that the panoramic visual browsing of the wide-area scene is realized. The intelligent analysis result of the video is overlapped in the accurate area of the bridge three-dimensional space scene, and the linkage alarm information solves the problems that the area display is not visual and accurate. The patrol event alarm is displayed in three dimensions in real time, the patrol vehicle identification track is tracked in the whole course, intelligent service application space management is realized, quick response is realized, and the command is intuitive and accurate. Based on intelligent video analysis and diversified sensing measurement and data acquisition processing systems, monitoring parameters comprise temperature and humidity, wind power, load, stress, deflection, vibration, inclination, rotation angle, displacement and the like, and the health state of the bridge is monitored in real time. And carrying out digital sampling on the measurement signals of each sensor, and carrying out processing such as digital transformation, time domain analysis, frequency domain analysis, statistical analysis, modal analysis and the like to realize scientific bridge health evaluation and early warning. The method integrates real-time acquisition, intelligent damage identification and comprehensive pavement disease data management, provides huge data support for road management, and provides strong support for comprehensive maintenance decision schemes. The method has the advantages that the method realizes the highly intelligent application integrating three-dimensional geographic information, monitoring video fusion and special service analysis tools, creates dynamic emergency deployment and command electronic sand tables, and improves the three-dimensional prevention and control and comprehensive outburst capability. Panoramic visualization emergency path planning is performed, and rescue efficiency is improved.
The system may further comprise: the bridge daily management and maintenance module is used for managing bridge basic information, bridge technical index information, bridge archive information, sensor facility basic information, video monitoring equipment basic information, bridge daily monitoring information, bridge inspection records and maintenance records.
The basic information of the management bridge comprises bridge name, bridge number, belonging line, route grade, function type, design load, central point position, bridge gradient, bridge flat curve radius, construction time, design unit, construction unit, underpass name, supervision unit, owner unit, management unit and the like; the technical index information of the management bridge comprises the information of bridge full length, bridge deck total width, lane width, guardrail or anti-collision wall height, central partition width, bridge deck standard clearance, bridge deck actual clearance, under-bridge navigation grade and standard clearance, under-bridge actual clearance, guide track total width, guide track linear or curve radius, design flood frequency, design water level, historical maximum flood level, earthquake peak acceleration, bridge deck elevation and the like. Bridge file information including information such as design drawings, design documents, completion drawings, construction documents, acceptance documents, administrative approval documents, periodic inspection data, special inspection data, past maintenance, reinforcement data, other files, file formation, file creation time, and the like. The sensor facility basic information is managed, and comprises information such as facility names, facility numbers, access modes, facility types, production time, facility models, installation time, equipment specifications, operation time, sampling frequency, service life, resolution, measuring range, measuring precision, monitoring positions, monitoring content, monitoring directions and the like. And managing the basic information of the video monitoring equipment, wherein the basic information comprises equipment number, equipment name, equipment type, brand, model, equipment state, installation time, equipment performance, equipment position and the like.
In an embodiment of the present invention, there is also provided a bridge structure health prediction apparatus, including: comprises a processor, a memory and a program; the program is stored in the memory, and the processor calls the program stored in the memory to execute the bridge structure health prediction method.
In the implementation of the bridge structure health prediction device, the memory and the processor are directly or indirectly electrically connected to realize data transmission or interaction. For example, the elements may be electrically connected to each other via one or more communication buses or signal lines, such as through a bus connection. The memory stores computer-executable instructions for implementing the data access control method, including at least one software functional module that may be stored in the memory in the form of software or firmware, and the processor executes the software programs and modules stored in the memory to perform various functional applications and data processing.
The Memory may be, but is not limited to, random access Memory (Random Access Memory; RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory; PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory; EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory; EEPROM), etc. The memory is used for storing a program, and the processor executes the program after receiving the execution instruction.
The processor may be an integrated circuit chip with signal processing capabilities. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, abbreviated as CPU), a network processor (Network Processor, abbreviated as NP), and the like. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In an embodiment of the present invention, there is further provided a computer readable storage medium, where the computer readable storage medium includes a stored computer program, where the computer program, when executed by a processor, controls a device where the storage medium is located to execute the bridge structure health prediction method described above.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the invention may take the form of an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart.
The bridge structure health prediction method, the bridge structure health prediction system, the bridge structure health prediction device and the application of a computer readable storage medium provided by the invention are described in detail, and specific examples are applied to illustrate the principle and the implementation of the invention, and the description of the above examples is only used for helping to understand the method and the core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (8)
1. The bridge structure health prediction method is characterized by comprising the following steps of:
step 1, monitoring the bridge state in real time by using a sensor to obtain bridge structure monitoring data; taking a bridge photo by using a camera, and calculating the bridge displacement, namely the bridge deformation;
step 2, preprocessing the acquired bridge structure monitoring data and bridge deformation amount to obtain a time sequence of the processed bridge state data, and performing accumulation and mean value operation on the time sequence of the bridge state data to obtain an accumulation sequence and a mean value sequence of the bridge state data;
step 3, generating a gray prediction model through a whitening equation according to the time accumulation sequence and the mean value sequence of the bridge state data, and calculating the least square estimation parameter value of the gray prediction model;
step 4, calculating a time response sequence of the gray prediction model and a time sequence predicted value of original bridge state data according to the least square estimated parameter value of the gray prediction model;
step 5, checking the precision of the gray prediction model, and if the precision of the gray prediction model does not meet the prediction requirement, correcting the gray prediction model until the gray prediction model meeting the prediction requirement is obtained; and carrying out prediction by combining with a gray prediction model meeting the prediction requirements.
2. The method for predicting the health of a bridge structure according to claim 1, wherein the sensor in step 1 comprises: temperature and humidity meter, stress sensor, strain sensor, acceleration sensor, deflection sensor.
3. The method for predicting the health of a bridge structure according to claim 1, wherein in the step 1, a camera is used to take a photograph of the bridge, and the bridge displacement, namely, the bridge deformation, is calculated, and the specific steps include:
setting a calibration object at a bridge key point, taking a bridge local photo at fixed time by adopting a camera, calibrating a pixel at the initial calibration object position to be 0, acquiring a pixel for moving the calibration object by a machine vision algorithm, comparing the pixel with the pixel at the initial calibration object position, and calculating a displacement amount, namely a bridge deformation amount; the bridge key point comprises a bridge compression stress concentration area, or a bridge back tension stress concentration area between two bridge piers, or a guy cable or sling, or a key member.
4. The method for predicting the health of a bridge structure according to claim 1, wherein in the step 2, the time sequence of the bridge state data is subjected to accumulation and mean value operation, and the obtained accumulation sequence and mean value sequence of the bridge state data specifically comprise the following steps:
Establishing a level ratio generating operator, comparing adjacent two processed time sequences of bridge state data with each other, and calculating to obtain the time sequence data level ratio of the bridge state data;
and judging whether the time sequence data level ratio of the bridge state data is in a coverage interval range, and if so, performing accumulation and mean value operation on the time sequence of the bridge state data to obtain an accumulation sequence and a mean value sequence of the bridge state data.
5. The method for predicting the health of a bridge structure according to claim 4, wherein the step 4 specifically comprises: discretizing the whitening equation to obtain a time response sequence of the gray prediction model: and obtaining a time sequence predicted value of the original bridge state data according to the weighted fractional order inverse accumulation operation.
6. The bridge structure health prediction system according to any one of claims 1-5, comprising a data acquisition and data storage module and a bridge structure health index prediction algorithm module;
the data acquisition and data storage module comprises a plurality of sensors for detecting the bridge and cameras for locally and fixedly shooting the bridge, and the sensors are used for monitoring the bridge state in real time to obtain bridge structure monitoring data and bridge structure monitoring data; taking a bridge photo by using a camera, and calculating the bridge displacement, namely the bridge deformation; preprocessing the acquired bridge structure monitoring data and bridge deformation quantity to obtain a time sequence of processed bridge state data;
The bridge structure health index prediction algorithm module is used for carrying out accumulation and average value operation on the time sequence of the bridge state data to obtain an accumulation sequence and an average value sequence of the bridge state data; generating a gray prediction model through a whitening equation according to the accumulation sequence and the average value sequence of the bridge state data, and calculating the least square estimation parameter value of the gray prediction model; calculating a time response sequence of the gray prediction model and a time sequence predicted value of original bridge state data according to a least square estimated parameter value of the gray prediction model;
the bridge structure early warning and safety evaluation module is used for checking the precision of the prediction model, and if the precision of the prediction model does not meet the prediction requirement, the prediction model is corrected until the prediction model meeting the prediction requirement is obtained; and carrying out prediction by combining a prediction model meeting the prediction requirements.
7. The utility model provides a healthy prediction unit of bridge structure which characterized in that, it includes: a processor, a memory, and a program; the program is stored in the memory, and the processor invokes the memory-stored program to perform the method of any one of claims 1-5.
8. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run by a processor, controls a device in which the storage medium is located to perform the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310828731.4A CN116955948A (en) | 2023-07-07 | 2023-07-07 | Bridge structure health prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310828731.4A CN116955948A (en) | 2023-07-07 | 2023-07-07 | Bridge structure health prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116955948A true CN116955948A (en) | 2023-10-27 |
Family
ID=88450380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310828731.4A Pending CN116955948A (en) | 2023-07-07 | 2023-07-07 | Bridge structure health prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116955948A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2199788A2 (en) * | 2008-12-18 | 2010-06-23 | Sikorsky Aircraft Corporation | Method and apparatus for montoring structural health |
| CN109186902A (en) * | 2018-09-26 | 2019-01-11 | 中国计量大学 | A kind of bridge structure health detection system of view-based access control model sensing |
| CN111272366A (en) * | 2020-03-02 | 2020-06-12 | 东南大学 | Bridge displacement high-precision measurement method based on multi-sensor data fusion |
| CN113158469A (en) * | 2021-04-25 | 2021-07-23 | 上海应用技术大学 | Asphalt pavement detection time prediction method based on longitudinal cracks |
| US20210405568A1 (en) * | 2020-06-30 | 2021-12-30 | Konica Minolta, Inc. | Operation Status Prediction System, Defect Occurrence Prediction System, Image Forming System, and Operation Status Prediction Method |
-
2023
- 2023-07-07 CN CN202310828731.4A patent/CN116955948A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2199788A2 (en) * | 2008-12-18 | 2010-06-23 | Sikorsky Aircraft Corporation | Method and apparatus for montoring structural health |
| CN109186902A (en) * | 2018-09-26 | 2019-01-11 | 中国计量大学 | A kind of bridge structure health detection system of view-based access control model sensing |
| CN111272366A (en) * | 2020-03-02 | 2020-06-12 | 东南大学 | Bridge displacement high-precision measurement method based on multi-sensor data fusion |
| US20210405568A1 (en) * | 2020-06-30 | 2021-12-30 | Konica Minolta, Inc. | Operation Status Prediction System, Defect Occurrence Prediction System, Image Forming System, and Operation Status Prediction Method |
| CN113158469A (en) * | 2021-04-25 | 2021-07-23 | 上海应用技术大学 | Asphalt pavement detection time prediction method based on longitudinal cracks |
Non-Patent Citations (1)
| Title |
|---|
| 王攀: "基于灰色理论的灾后桥梁结构损伤快速检测系统研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, no. 2, pages 034 - 220 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| He et al. | Integrated structural health monitoring in bridge engineering | |
| Yi et al. | Experimental assessment of high-rate GPS receivers for deformation monitoring of bridge | |
| US10345775B2 (en) | Methods and systems for infrastructure performance: monitoring, control, operations, analysis and adaptive learning | |
| Pyayt et al. | Machine learning methods for environmental monitoring and flood protection | |
| CN106156336A (en) | A kind of Cable-Stayed Bridge Structure state evaluation system and assessment method | |
| Cheung et al. | The application of statistical pattern recognition methods for damage detection to field data | |
| CN113900381B (en) | Steel structure remote health monitoring platform based on Internet of things and application method | |
| JP2015098686A (en) | Preventive maintenance monitoring system of structure | |
| CN110132511A (en) | A kind of bridge structure monitoring and assessing method based on dynamic deflection attenuation law | |
| CN116105802B (en) | Underground facility safety monitoring and early warning method based on Internet of things | |
| KR102097039B1 (en) | Intelligent structure safety monitoring platform based on space information | |
| Andersen | Structural health monitoring systems | |
| CN115601008A (en) | Engineering settlement deformation monitoring system and method based on digital twinning | |
| Ghiasi et al. | Damage detection of in-service steel railway bridges using a fine k-nearest neighbor machine learning classifier | |
| Alves et al. | An automated vibration-based structural damage localization strategy using filter-type feature selection | |
| Fang et al. | A web‐based and design‐oriented structural health evaluation system for long‐span bridges with structural health monitoring system | |
| CN101382474B (en) | Alarming method for bridge structure safety | |
| CN116955948A (en) | Bridge structure health prediction method and system | |
| Raphael et al. | Sensor data interpretation in bridge monitoring—A case study | |
| Sousa et al. | Next generation of Monitoring Systems towards Infrastructure Resilience | |
| Hu et al. | Examination of load-deformation characteristics of long-span bridges in harsh natural environments based on real-time updating artificial neural network | |
| Alovisi et al. | Bridges continuous dense monitoring network: A framework to support the infrastructures assessment and management process | |
| Nguyen et al. | Health Monitoring System for Long Span Bridges Across the Han River in Da Nang City, Vietnam | |
| Cross et al. | Filtering environmental load effects to enhance novelty detection on cable-supported bridge performance | |
| CN116906837B (en) | State monitoring system and monitoring method for underground pipeline |
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 |