CN109271406A - A kind of bridge health monitoring system based on big data - Google Patents
A kind of bridge health monitoring system based on big data Download PDFInfo
- Publication number
- CN109271406A CN109271406A CN201811126361.5A CN201811126361A CN109271406A CN 109271406 A CN109271406 A CN 109271406A CN 201811126361 A CN201811126361 A CN 201811126361A CN 109271406 A CN109271406 A CN 109271406A
- Authority
- CN
- China
- Prior art keywords
- bridge structure
- data
- big data
- bridge
- intrinsic mode
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Abstract
The present invention provides a kind of bridge health monitoring systems based on big data, including bridge structure big data acquisition system, bridge structure big data storage system, bridge structure big data processing locality system, bridge structure big data wireless communication system and bridge structure big data rear end early warning system；The bridge structure big data processing locality system obtains the bridge structure data, and carries out Classification and Identification judgement to multidimensional data, if judge that bridge structure data are obviously abnormal, carries out local alarm rapidly；If do not judge that bridge structure data are obviously abnormal, the bridge structure data are sent to by bridge structure big data rear end early warning system by the bridge structure big data wireless communication system.The bridge health monitoring system that the present invention designs can the state to bridge structure make in time and accurate evaluation and prediction, strong applicability, good reliability are easy to promote and utilize.
Description
Technical field
The present invention relates to bridge structure monitoring technical field, especially a kind of bridge structural health monitoring based on big data
System.
Background technique
Due to large bridges will receive during operation weather, oxidation, corrosion or aging i.e. unexpected incidents etc. because
The influence of element, and various damages or part damage, strength and stiffness meeting can be generated under the action of dead load and mobile load for a long time
It reduces at any time, this not only affects safe driving, but will make its reduced service life.Therefore tight in maintenance fund at present
Lack, in the case where lacking effectively management, need to carry out bridge structure effective detection and assessment, monitoring and early warning, maintenance with
The technical measures such as management extend bridge service life to cut operating costs, and ensure circulation of traffic.Use newest distribution
Processing technique, sensor technology, wireless communication technique, data analysis technique develop a set of bridge structure health detection system, use
With the operational regime of testing and evaluation science of bridge building, scientific basis is provided for maintenance management.
To reduce resource consumed by bridge health monitoring system, system working life is improved, early warning efficiency is promoted, is used
Distributed data processing framework, inventing the distributed bridge health monitoring system based on big data of one kind just seems very
It is important.
Summary of the invention
In view of the above-mentioned problems, the present invention is intended to provide a kind of bridge health monitoring system based on big data, this is
System reduces the energy consumption of bridge health monitoring system, improves system lifetim, and pass through the reality to bridge structure
When acquire and processing, bridge structure health state can be made in time and accurately assess and predict.
The purpose of the present invention is realized using following technical scheme:
Provide a kind of bridge health monitoring system based on big data, including bridge structure big data acquisition system
System, bridge structure big data storage system, bridge structure big data processing locality system, bridge structure big data wireless communication system
System and bridge structure big data rear end early warning system；The bridge structure big data acquisition system includes for obtaining bridge
The multiclass sensor group of structured data；The bridge structure big data storage system and the bridge structure big data acquisition system
Connection, for storing the bridge structure data；The bridge structure big data processing locality system and the bridge structure are big
Data-storage system connection extracts the bridge structure data, and carries out Classification and Identification judgement to multidimensional data, if judging
When bridge structure data are obviously abnormal, local alarm is carried out rapidly；If do not judge that bridge structure data are obviously abnormal, lead to
It crosses after the bridge structure data are sent to the bridge structure big data by the bridge structure big data wireless communication system
Early warning system is held, bridge structure big data rear end early warning system, which is used to realize, evaluates the health status of bridge structure
Prediction.
Preferably, the multiclass sensor group includes Crack Monitoring sensor and piezoelectric acceleration transducer；Institute
It states and arranges multiclass sensor group different location is distributed on bridge.
Preferably, after the bridge structure data are collected, the bridge structure is transferred to by star-like transmission network
Big data storage system is stored；The star-like transmission network is based on Star Network framework, low-power consumption biography wireless over long distances
The data transmission network of multi-user's agreement of transferring technology and multiple access.
Preferably, the bridge structure big data processing locality system includes data preprocessing module, data threshold judgement
Module and warning module, the data preprocessing module are collected using multinomial least square method fracture monitoring sensor
Crack data carry out data burr and abnormal data rejecting, also the crack data are carried out by data smoothing algorithm flat
Cunning obtains process data；The data threshold judgment module is for splitting the process data and the bridge structure
The correspondence level threshold value of seam is compared, and judges the bridge structure with the presence or absence of surface obvious shortcoming；The warning module is used
According to the judging result of data threshold judgment module realization intelligent early-warning.
Preferably, bridge structure big data rear end early warning system be used for the bridge structure data received into
Row processing, includes data screening module, for filtering out the collected primary data of the piezoelectric acceleration transducer；Number
According to continuation module, secondary signal is obtained for carrying out interpolation fitting to primary data, expanding to extend, is facilitated at subsequent denoising
Reason；Data-signal denoises module, obtains validity feature signal for carrying out denoising to the secondary signal；Characteristic parameter mentions
Modulus block, for extracting the Faults by Vibrating for reflecting the bridge structure situation from the validity feature signal；Also wrap
Overall merit module is included, for commenting for the health status according to the Faults by Vibrating progress bridge structure acquired
Valence prediction.
Preferably, the data-signal denoising module obtains validity feature signal by being handled the secondary signal
Specific steps are as follows:
(1) white noise signal that amplitude standard deviation determines, the width of the white noise signal are added in the secondary signal
Value standard deviation is obtained by calculation；
(2) it takes empirical mode decomposition algorithm to decompose the signal that white noise is added, a series of orderly sheets can be obtained
Levy modular function component and a remainder；
(3) Effective selection is carried out to a series of obtained orderly intrinsic mode functions components, the Effective selection is according to each
A intrinsic mode functions component corresponding coefficient of efficiency carries out；Wherein, the calculation formula of the coefficient of efficiency are as follows:
In formula, XjFor the corresponding coefficient of efficiency of j-th of intrinsic mode functions component；α, β are weight coefficient, and wherein α, β are big
In 0 and alpha+beta=1；K is the total number of the intrinsic mode functions component, and j ∈ K；Ej(i) for j-th intrinsic mode functions component with
The cross-correlation coefficient between i-th of intrinsic mode functions component in addition to j-th of intrinsic mode functions component；EHIt (j) is j-th
Levy the auto-correlation coefficient of modular function component and the secondary signal；DmaxFor all corresponding information of the intrinsic mode functions component
Maximum value in closely related；DminFor all corresponding information of the intrinsic mode functions component it is closely related in minimum value；DjIt is intrinsic for j-th
The corresponding information of modular function component is closely related；GmaxFor the maximum in all corresponding high frequency coefficients of efficiency of the intrinsic mode functions component
Value；GminFor the minimum value in all corresponding high frequency coefficients of efficiency of the intrinsic mode functions component；GjFor j-th of eigen mode letter
The corresponding high frequency coefficient of efficiency of number component.
Then, effective threshold values is set, when the corresponding coefficient of efficiency of j-th of intrinsic mode functions component being calculated is big
When effective threshold values, that is, think that j-th of intrinsic mode functions component is active constituent；By whole intrinsic mode functions components into
After row differentiates one by one, only retain active constituent；
(4) synthesis is reconstructed to the active constituent, so obtain include bridge structure characteristic information effective spy
Reference number.
The invention has the benefit that the invention proposes a kind of bridge health monitoring system based on big data,
Designed concept based on local management and long-range monitoring and controlling forecast devises bridge structure big data processing locality system and bridge
Girder construction big data rear end early warning system, by that will reflect that the sensing data of the obvious fault of construction in bridge structure surface carries out this
Ground processing, judgement when guaranteeing that bridge surface defect occurs, can fast implement identification and find and then alarm；If no obvious surface lacks
It falls into, then sensing data is sent to bridge structure big data rear end early warning system, carry out the vibration of processing identification bridge structure
Characteristic parameter, and the state of bridge structure is carried out making timely and accurate evaluation and prediction in turn, the present invention has rational design,
Strong applicability, good reliability are easy to promote and utilize.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the general frame figure of bridge health monitoring system described in a preferred embodiment of the present invention；
Fig. 2 is the composition signal of bridge structure big data rear end early warning system described in a preferred embodiment of the present invention
Figure.
Specific embodiment
In conjunction with following application scenarios, the invention will be further described.
Referring to Fig. 1, in the present embodiment, a kind of bridge health monitoring system based on big data, including bridge are provided
Girder construction big data acquisition system, bridge structure big data storage system, bridge structure big data processing locality system, bridge knot
Structure big data wireless communication system and bridge structure big data rear end early warning system；The bridge structure big data acquisition system
It include the multiclass sensor group for obtaining bridge structure data；The bridge structure big data storage system and the bridge
Structure big data acquisition system connection, for storing the bridge structure data；The bridge structure big data processing locality system
System is connect with the bridge structure big data storage system, extracts the bridge structure data, and divide multidimensional data
If class identification judgement carries out rapidly local alarm judge that bridge structure data are obviously abnormal；If not judging bridge structure
When data are obviously abnormal, then the bridge structure data are sent to by institute by the bridge structure big data wireless communication system
Bridge structure big data rear end early warning system is stated, bridge structure big data rear end early warning system is used to realize to bridge structure
Health status carry out evaluation and foreca.
In the present embodiment, the multiclass sensor group includes Crack Monitoring sensor and piezoelectric type acceleration sensing
Device；Multiclass sensor group is arranged different location is distributed on the bridge.
In the present embodiment, after the bridge structure data are collected, the bridge is transferred to by star-like transmission network
Structure big data storage system is stored；The star-like transmission network is based on Star Network framework, low-power consumption long range nothing
The data transmission network of line transmission technology and multi-user's agreement of multiple access.
In the present embodiment, the bridge structure big data processing locality system includes data preprocessing module, data threshold
Judgment module and warning module, the data preprocessing module are adopted using multinomial least square method fracture monitoring sensor
The crack data that collect carry out the rejecting of data burr and abnormal data, also by data smoothing algorithm to the crack data into
Row smoothly obtains process data；The data threshold judgment module is used for the process data and the bridge knot
The correspondence level threshold value in crack is compared in structure, judges the bridge structure with the presence or absence of surface obvious shortcoming；The early warning
Module is used to realize intelligent early-warning according to the judging result of the data threshold judgment module.
In the present embodiment, bridge structure big data rear end early warning system is used for the bridge structure number received
It include data screening module according to being handled, for filtering out the collected initial number of the piezoelectric acceleration transducer
According to；Data extension module obtains secondary signal for carrying out interpolation fitting to primary data, expanding to extend, facilitates subsequent go
It makes an uproar processing；Data-signal denoises module, obtains validity feature signal for carrying out denoising to the secondary signal；Feature ginseng
Number extraction module, for extracting the Faults by Vibrating for reflecting the bridge structure situation from the validity feature signal；
It further include having overall merit module, for carrying out the health status of bridge structure according to the Faults by Vibrating acquired
Evaluation and foreca.
In the present embodiment, piezoelectric acceleration transducer acquisition be bridge operation stage outside under conditions by
The vibration data signal of excited vibration, and include in vibration data signal the characteristic information of bridge structure such as: bridge structure
Eigentone, damping ratio and mode factor；The characteristic information is obtained to need first to the vibration data signal
Noise reduction is carried out, is realized in the present embodiment using empirical mode decomposition algorithm and noise reduction is carried out to the primary data that screening obtains, and
When using the algorithm, it is contemplated that need to carry out curve fitting the Local Extremum in primary data to obtain its envelope, but just
There is distortion diverging in endpoint when carrying out spline curve fitting at the endpoint of beginning data, and information is lost when causing to decompose.
Therefore in the present embodiment, by Data extension module come continuation primary data, to avoid the endpoint of the primary data
When carrying out spline curve fitting during signal decomposition, endpoint distorts Divergent Phenomenon；Using a kind of signals extension algorithm, come
Obtain secondary signal, the treatment process of the continuation algorithm specifically:
(1) collected primary data is carried out curve fitting to obtain corresponding continuous initial signal；
(2) judge to determine at the endpoint of the left end point of initial signal for maximum or minimum；For above-mentioned judgement knot
Fruit obtains endpoint characteristics wave corresponding with left end point, specifically:
If 1), the left end point is minimum point, obtain and left end point successively closest first maximum point, the
One minimum point and second maximum point；It connects this four extreme points including left end point and constitutes four side of extreme value
Shape describes its endpoint characteristics wave by extreme value quadrangle；
If 2), the left end point is maximum point, obtain and left end point successively closest first minimum point, the
One maximum point and second minimum point；It connects this four extreme points including left end point and constitutes four side of extreme value
Shape describes its endpoint characteristics wave by extreme value quadrangle；
(3) it by finding out all extreme points except left end point, is searched and the extreme value quadrangle difference in primary signal
Degree minimum, the highest matching quadrangle of matching degree；The matching quadrangle is corresponding with the extreme value quadrangle of the left end point, it may be assumed that
If left end point is minimum, matching quadrangle, (the i.e. described matching extreme point is a pole in primary signal by matching extreme point
Small value point) and on the right of matching extreme point and with match extreme point successively neighbouring i-th of maximum point, i-th of minimum
Point and i+1 maximum point are constituted；If left end point is maximum, quadrangle is matched by matching extreme point (i.e. described
With the maximum point that extreme point is in primary signal) and with match extreme point successively neighbouring i-th of minimum point, i-th
+ 1 maximum point and i+1 minimum point are constituted；The i only represents the sequence label of extreme point, does not have limited；
Wherein, when left end point is minimum, the calculation formula of the matching degree of the matching quadrangle and extreme value quadrangle
Are as follows:
In formula, a1Left end point corresponding signal amplitude when for the left end point being minimum；s1For in primary signal with institute
State the closest corresponding signal amplitude of the first maximum point of left end point；d1For in primary signal with first maximum point
The corresponding signal amplitude of the first minimum point for keeping right neighbouring；s2To keep right neighbouring second greatly with first minimum point
The corresponding signal amplitude of value point；diFor among primary signal and be minimum point the corresponding signal amplitude of matching extreme point；
si+1For signal amplitude corresponding with the matching extreme point i+1 maximum point of keeping right neighbouring；di+1For with the i+1 pole
The corresponding signal amplitude of i+1 minimum point that big value point is kept right neighbouring；si+2It is neighbouring to keep right with the i+1 minimum point
The corresponding signal amplitude of the i-th+2 maximum point；PPDFor the matching quadrangle corresponding with matching extreme point and four side of extreme value
The matching degree of shape；
Wherein, when the left end point is maximum, the calculating of the matching degree of the matching quadrangle and extreme value quadrangle
Formula only needs basis to be symmetrically adaptively adjusted；
(3) matching extreme point corresponding with the most matched matching quadrangle of the extreme value quadrangle is found according to above-mentioned algorithm
Afterwards, and the corresponding time value of the matching extreme point is obtained, the data of the matching extreme point is subjected to continuation to initial signal
At left end point；
(4) and by right end of the above step to initial signal carry out continuation is ordered the same, after finally obtaining continuation processing
Secondary signal.
In this preferred embodiment, it is contemplated that need to be to signal extreme point or end when using empirical mode decomposition algorithm progress noise reduction
Point makees curve matching, and endpoint the problem of nearby only unilateral information and envelope that it is fitted will appear distortion diverging；It mentions
A kind of signals extension algorithm is gone out, the local signal behavior near endpoint is found and the endpoint in overall signal
Locate the most matched matching quadrangle of extreme value quadrangle, so that the matching extreme point continuation is solved above-mentioned ask at endpoint
Topic, this algorithm compared with the existing technology in many and diverse, the computationally intensive continuation algorithm of parameter, have that algorithm is simple and calculation amount is small
Advantage.
In the present embodiment, the data-signal denoising module to the secondary signal by being handled to obtain validity feature
The specific steps of signal are as follows:
(1) white noise signal that amplitude standard deviation determines, the width of the white noise signal are added in the secondary signal
Value standard deviation is obtained by calculation；
(2) it takes empirical mode decomposition algorithm to decompose the signal that white noise is added, a series of orderly sheets can be obtained
Levy modular function component (IMF component) and a remainder；
(3) Effective selection is carried out to a series of obtained orderly intrinsic mode functions components, the Effective selection is according to each
A intrinsic mode functions component corresponding coefficient of efficiency carries out；Wherein, the calculation formula of the coefficient of efficiency are as follows:
In formula, XjFor the corresponding coefficient of efficiency of j-th of intrinsic mode functions component；α, β are weight coefficient, and wherein α, β are big
In 0 and alpha+beta=1；K is the total number of the intrinsic mode functions component, and j ∈ K；Ej(i) for j-th intrinsic mode functions component with
The cross-correlation coefficient between i-th of intrinsic mode functions component in addition to j-th of intrinsic mode functions component；EHIt (j) is j-th
Levy the auto-correlation coefficient of modular function component and the secondary signal；DmaxFor all corresponding information of the intrinsic mode functions component
Maximum value in closely related；DminFor all corresponding information of the intrinsic mode functions component it is closely related in minimum value；DjIt is intrinsic for j-th
The corresponding information of modular function component is closely related；GmaxFor the maximum in all corresponding high frequency coefficients of efficiency of the intrinsic mode functions component
Value；GminFor the minimum value in all corresponding high frequency coefficients of efficiency of the intrinsic mode functions component；GjFor j-th of eigen mode letter
The corresponding high frequency coefficient of efficiency of number component.
Then, effective threshold values is set, when the corresponding coefficient of efficiency of j-th of intrinsic mode functions component being calculated is big
When effective threshold values, that is, think that j-th of intrinsic mode functions component is active constituent；By whole intrinsic mode functions components into
After row differentiates one by one, only retain active constituent；
(3) synthesis is reconstructed to the active constituent, so obtain include bridge structure characteristic information effective spy
Reference number.
In this preferred embodiment, propose using the algorithm for taking empirical mode decomposition algorithm to carry out noise reduction, wherein to noise reduction
The algorithm that effective intrinsic mode functions component in algorithm is screened is improved, so that having comprehensively considered each component when screening
Between related coefficient, component self information is closely related and high frequency coefficient of efficiency, compared with the existing technology in only consider point
Cross-correlation coefficient between amount, the screening effect in the present embodiment is good, the noise of the reconstruction signal after significantly improving screening
Than, so in the validity feature signal that ensure that characteristic information integrality.
In the present embodiment, calculating process that the amplitude standard deviation to white noise signal is calculated are as follows:
(1) initial signal is directly decomposed to obtain by empirical mode decomposition algorithm a series of orderly intrinsic
Modular function component；Calculate the corresponding high frequency coefficient of efficiency of each intrinsic mode functions component are as follows:
In formula, GjFor the corresponding high frequency coefficient of efficiency of j-th of intrinsic mode functions component；M is whole intrinsic mode functions components
Present in extreme point number；MjFor the number of extreme point present in j-th of intrinsic mode functions component；L is primary signal
Length；SjIt (k) is the amplitude of k-th of extreme point in j-th of intrinsic mode functions component；J is corresponding with intrinsic mode functions component
Serial number；MiFor the number of extreme point existing for i-th of intrinsic mode functions component；SiIt (k) is kth in i-th of intrinsic mode functions component
The amplitude of a extreme point.
(2) the corresponding high frequency coefficient of efficiency of each intrinsic mode functions component is subjected to sequence from low to high, and filtered out
The biggish N number of intrinsic mode functions component of high frequency coefficient of efficiency is as the radio-frequency component in primary signal；To these radio-frequency components into
Row reconstruct obtains amplitude standard deviation corresponding with the radio-frequency component；
(3) by the 1/4 amplitude standard deviation as the white noise of the corresponding amplitude standard deviation of the radio-frequency component.
In this preferred embodiment, the meter of the amplitude standard deviation for the white noise that a kind of pair of secondary signal compensates is proposed
Calculation method, the calculation method consider the self-characteristic for thermal compensation signal, add when compensating in the prior art to signal
The amplitude standard deviation of the white noise added is essentially experience setting or is randomly generated and compares, to secondary signal addition in the present embodiment
White noise is determined according to initial signal own characteristic, improves the fitness of white noise and secondary signal, and make it is subsequent right
The quality that signal is decomposed is high, and then ensure that the noise reduction effect to signal.
In the present embodiment, the characteristic parameter extraction module from the validity feature signal in order to extract described in reflection
The Faults by Vibrating of bridge structure situation needs to be known in advance the dynamic model of bridge structure；Therefore in the present embodiment, to described
Bridge structure carries out Systems Theory modeling, acquires the dynamic model of bridge structure and further obtains the bridge structure system
System order.
In the present embodiment, the vibration performance information for including in the validity feature signal is extracted, identifies and is shaken
The detailed process of dynamic characteristic parameter are as follows:
It is first depending on validity feature signal construction Hankel matrix, carrying out QR decomposition to the Hankel matrix can obtain
Singular value decomposition, the Observable matrix being expanded are carried out according to systematic education to projection matrix, and then to the projection matrix
And Kalman filtering status switch, then by the Observable matrix of obtained extension and Kalman filtering status switch from
It dissipates processing in time state spatial model and obtains eigenmatrix and output matrix；Finally, being identified from the eigenmatrix
The Faults by Vibrating of the bridge structure, i.e. eigentone, damping ratio and mode factor.
In the present embodiment, the overall merit module carries out the health status of bridge structure according to the Faults by Vibrating
Evaluation and foreca specific implementation are as follows:
It obtains bridge and just builds up the initial vibration characteristic parameter that corresponding monitoring obtains when putting into operation, including initial intrinsic frequency
Rate, initial damping ratio and initial mode factor；By the Faults by Vibrating of above-mentioned acquisition and initial vibration characteristic parameter
It compares, calculates structural health attenuation function when it just puts into operation relative to bridge；The health attenuation function reflection
The health status of the bridge structure in signal monitoring；Wherein, the calculation formula of the structural health attenuation function are as follows:
In formula, JmFor the healthy attenuation function value of m-th of piezoelectric acceleration transducer present position counter structure；
Wm0For the initial intrinsic frequency of m-th of piezoelectric acceleration transducer present position counter structure；Um0Add for m-th of piezoelectric type
The initial damping ratio of velocity sensor present position counter structure；Vm0For m-th of piezoelectric acceleration transducer present position pair
Answer the initial mode factor of structure；WmIt is obtained for the response signal that m-th of piezoelectric acceleration transducer acquires in real time through processing
The intrinsic frequency；UmIt is handled for the response signal that m-th of piezoelectric acceleration transducer acquires in real time described in obtaining
Damping ratio；VmThe mode factor obtained for the response signal that m-th of piezoelectric acceleration transducer acquires in real time through processing；
δ, ρ are the weight coefficient being randomly assigned, and δ2+ρ2=1.
If therefore the functional value of the healthy attenuation function acquired is smaller, the piezoelectric type acceleration sensing in signal monitoring
The health status of device installed position bridge structure is also better；By the way that in many places of bridge, there are the places of fault of construction to be surveyed
Examination obtains the decision threshold when judging the health status of bridge structure in larger confidence interval for defect, like that, in bridge
The stage of system vibration operation determines institute when the structural health attenuation function value calculated is greater than the decision threshold
State the bridge structure existing defects of piezoelectric acceleration transducer installation place；Wherein the decision threshold can be taking human as revision.And
It is possible thereby to which the remaining life to bridge structure carries out engineering experience prediction, it is also seen that safety that may be present in bridge structure
Hidden danger can check the security risk of bridge structure, and further maintenance if its healthy attenuation function is larger,
Bridge structure is largely avoided not in time, to cause safety accident because of safety problem discovery.
In the present embodiment, propose it is a kind of according to extract obtained Faults by Vibrating to the health status of bridge structure into
The overall merit module of row evaluation, the evaluation result of the module more can be realized reliably in engineer application to bridge knot
Whether structure may have major defect to be evaluated, so can be according to evaluation result to the bridge structure of sensor mounting location
Security risk is checked, and further maintenance, largely avoids bridge structure because safety problem is found not in time,
Cause safety accident.
In this preferred embodiment, a kind of bridge health monitoring system based on big data is proposed, based on local pipe
The designed concept of reason and long-range monitoring and controlling forecast, devises bridge structure big data processing locality system and the big number of bridge structure
Sentenced according to rear end early warning system by that will reflect that the sensing data of the obvious fault of construction in bridge structure surface carries out processing locality
It is disconnected, when guaranteeing that bridge surface defect occurs, identification can be fast implemented and find and then alarm；If will be passed without obvious surface defect
Sensor data are sent to bridge structure big data rear end early warning system, carry out the Faults by Vibrating of processing identification bridge structure,
And the state of bridge structure is carried out making timely and accurate evaluation and prediction in turn, the present invention has rational design, strong applicability,
Good reliability, it is easy to promote and utilize.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as analysis, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of bridge health monitoring system based on big data, which is characterized in that acquired including bridge structure big data
System, bridge structure big data storage system, bridge structure big data processing locality system, bridge structure big data wireless communication
System and bridge structure big data rear end early warning system；The bridge structure big data acquisition system includes for obtaining bridge
The multiclass sensor group of girder construction data；The bridge structure big data storage system and bridge structure big data acquisition are
System connection, for storing the bridge structure data；The bridge structure big data processing locality system and the bridge structure
The connection of big data storage system extracts the bridge structure data, and carries out Classification and Identification judgement to multidimensional data, if judgement
When bridge structure data are obviously abnormal out, local alarm is carried out rapidly；If do not judge that bridge structure data are obviously abnormal,
The bridge structure data are sent to the bridge structure big data by the bridge structure big data wireless communication system
Rear end early warning system, bridge structure big data rear end early warning system, which is used to realize, comments the health status of bridge structure
Valence prediction.
2. a kind of bridge health monitoring system based on big data according to claim 1, which is characterized in that described
Multiclass sensor group includes Crack Monitoring sensor and piezoelectric acceleration transducer, and the multiclass sensor group is distributed
The different location being arranged on bridge on.
3. a kind of bridge health monitoring system based on big data according to claim 1, which is characterized in that described
After bridge structure data are collected, the bridge structure big data storage system is transferred to by star-like transmission network and is deposited
Storage；The star-like transmission network is based on Star Network framework, low-power consumption long range Radio Transmission Technology and multiple access
Multi-user's agreement data transmission network.
4. a kind of bridge health monitoring system based on big data according to claim 1, which is characterized in that described
Bridge structure big data processing locality system includes data preprocessing module, data threshold judgment module and warning module, institute
It states data preprocessing module and carries out data using the collected crack data of multinomial least square method fracture monitoring sensor
The rejecting of burr and abnormal data also carries out the crack data by data smoothing algorithm smoothly to obtain processed number of passes
According to；The data threshold judgment module is used for the corresponding level threshold value of the process data and the bridge structure crack
It is compared, judges the bridge structure with the presence or absence of surface obvious shortcoming；The warning module is used for according to the data threshold
The judging result for being worth judgment module realizes intelligent early-warning.
5. a kind of bridge health monitoring system based on big data according to claim 1, which is characterized in that described
Bridge structure big data rear end early warning system includes data sieve for handling the bridge structure data received
Modeling block, for filtering out the collected primary data of the piezoelectric acceleration transducer；Data extension module, for first
Beginning data carry out interpolation fitting, expansion extension obtains secondary signal, facilitate subsequent denoising；Data-signal denoises module,
Validity feature signal is obtained for carrying out denoising to the secondary signal；Characteristic parameter extraction module, for having from described
The Faults by Vibrating for reflecting the bridge structure situation is extracted in effect characteristic signal；Further include having overall merit module, uses
In the evaluation and foreca for the health status for carrying out bridge structure according to the Faults by Vibrating acquired.
6. a kind of bridge health monitoring system based on big data according to claim 5, which is characterized in that described
Data-signal denoises module and obtains the specific steps of validity feature signal by being handled the secondary signal are as follows:
(1) white noise signal that amplitude standard deviation determines, the amplitude mark of the white noise signal are added in the secondary signal
Quasi- difference is obtained by calculation；
(2) it takes empirical mode decomposition algorithm to decompose the signal that white noise is added, a series of orderly eigen modes can be obtained
Function component and a remainder；
(3) Effective selection is carried out to a series of obtained orderly intrinsic mode functions components, the Effective selection is according to each
The corresponding coefficient of efficiency of modular function component is levied to carry out；Wherein, the calculation formula of the coefficient of efficiency are as follows:
In formula, XjFor the corresponding coefficient of efficiency of j-th of intrinsic mode functions component；α, β are weight coefficient, and wherein α, β are greater than 0 and α
+ β=1；K is the total number of the intrinsic mode functions component, and j ∈ K；Ej(i) for j-th of intrinsic mode functions component and except jth
The cross-correlation coefficient between i-th of intrinsic mode functions component except a intrinsic mode functions component；EHIt (j) is j-th of eigen mode
The auto-correlation coefficient of function component and the secondary signal；DmaxFor all corresponding information of the intrinsic mode functions component it is closely related in
Maximum value；DminFor all corresponding information of the intrinsic mode functions component it is closely related in minimum value；DjFor j-th of eigen mode letter
The corresponding information of number component is closely related；GmaxFor the maximum value in all corresponding high frequency coefficients of efficiency of the intrinsic mode functions component；
GminFor the minimum value in all corresponding high frequency coefficients of efficiency of the intrinsic mode functions component；GjFor j-th of intrinsic mode functions point
Measure corresponding high frequency coefficient of efficiency；
Then, effective threshold values is set, is had when the corresponding coefficient of efficiency of j-th of intrinsic mode functions component being calculated is greater than
When imitating threshold values, that is, think that j-th of intrinsic mode functions component is active constituent；Whole intrinsic mode functions components is carried out one
After one differentiates, only retain active constituent；
(4) synthesis is reconstructed to the active constituent, so obtain include bridge structure characteristic information validity feature letter
Number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811126361.5A CN109271406A (en) | 2018-09-26 | 2018-09-26 | A kind of bridge health monitoring system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811126361.5A CN109271406A (en) | 2018-09-26 | 2018-09-26 | A kind of bridge health monitoring system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109271406A true CN109271406A (en) | 2019-01-25 |
Family
ID=65198351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811126361.5A Pending CN109271406A (en) | 2018-09-26 | 2018-09-26 | A kind of bridge health monitoring system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109271406A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109870404A (en) * | 2019-03-06 | 2019-06-11 | 石家庄铁道大学 | A kind of awning Structural Damage Identification, device and terminal device |
| CN110147781A (en) * | 2019-05-29 | 2019-08-20 | 重庆交通大学 | Bridge vibration mode based on machine learning visualizes damnification recognition method |
| CN110472268A (en) * | 2019-06-25 | 2019-11-19 | 北京建筑大学 | A kind of bridge monitoring data modality recognition methods and device |
| CN111225000A (en) * | 2020-02-24 | 2020-06-02 | 南京震坤物联网科技有限公司 | Bridge structure health monitoring system based on block chain technology |
| CN111505010A (en) * | 2020-04-28 | 2020-08-07 | 张地林 | Bridge safety detection system based on cloud platform |
| CN111735532A (en) * | 2020-06-24 | 2020-10-02 | 淮阴工学院 | Bridge resonance testing device and method |
| CN112485030A (en) * | 2020-11-09 | 2021-03-12 | 深圳市桥博设计研究院有限公司 | Bridge structure dynamic monitoring method, system and equipment based on frequency coupling |
| CN113408396A (en) * | 2021-06-15 | 2021-09-17 | 广西交科集团有限公司 | Bridge intelligent sensing system based on cloud computing |
| CN113514110A (en) * | 2021-08-19 | 2021-10-19 | 张旭辉 | Road and bridge engineering intelligent measurement system |
| CN116842348A (en) * | 2023-08-31 | 2023-10-03 | 安徽省云鹏工程项目管理有限公司 | Bridge health monitoring system based on artificial intelligence |
| CN117191305A (en) * | 2023-11-06 | 2023-12-08 | 临沂市公路事业发展中心兰陵县中心 | State evaluation method and system for highway bridge |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100092028A1 (en) * | 2008-10-10 | 2010-04-15 | National Central University | Data Decomposition Method and Computer System Therefrom |
| CN101763053A (en) * | 2008-12-26 | 2010-06-30 | 上海交技发展股份有限公司 | Movable type bridge security detection and analysis management system |
| CN103926509A (en) * | 2014-04-01 | 2014-07-16 | 河南理工大学 | Power distribution network fault step type line section method based on spectral kurtosis relative energy entropies |
| CN103954450A (en) * | 2014-05-19 | 2014-07-30 | 重庆交通大学 | Bearing life degradation performance evaluation index construction method based on main component analysis |
| CN104864913A (en) * | 2015-06-04 | 2015-08-26 | 无锡市博尚光电科技有限公司 | Distributed health-monitoring system for tunnel structure of highway bridge |
| CN107783200A (en) * | 2017-11-21 | 2018-03-09 | 吉林大学 | Joint EMD and TFPF algorithms a kind of all-wave magnetic resonance signal random noise method for reducing |
-
2018
- 2018-09-26 CN CN201811126361.5A patent/CN109271406A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100092028A1 (en) * | 2008-10-10 | 2010-04-15 | National Central University | Data Decomposition Method and Computer System Therefrom |
| CN101763053A (en) * | 2008-12-26 | 2010-06-30 | 上海交技发展股份有限公司 | Movable type bridge security detection and analysis management system |
| CN103926509A (en) * | 2014-04-01 | 2014-07-16 | 河南理工大学 | Power distribution network fault step type line section method based on spectral kurtosis relative energy entropies |
| CN103954450A (en) * | 2014-05-19 | 2014-07-30 | 重庆交通大学 | Bearing life degradation performance evaluation index construction method based on main component analysis |
| CN104864913A (en) * | 2015-06-04 | 2015-08-26 | 无锡市博尚光电科技有限公司 | Distributed health-monitoring system for tunnel structure of highway bridge |
| CN107783200A (en) * | 2017-11-21 | 2018-03-09 | 吉林大学 | Joint EMD and TFPF algorithms a kind of all-wave magnetic resonance signal random noise method for reducing |
Non-Patent Citations (2)
| Title |
|---|
| ZHAOHUA WU 等: "ENSEMBLE EMPIRICAL MODE DECOMPOSITION: A NOISE-ASSISTED DATA ANALYSIS METHOD", 《ADVANCES IN ADAPTIVE DATA ANALYSIS》 * |
| 徐健: "环境激励下桥梁结构模态参数自动化识别方法研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109870404A (en) * | 2019-03-06 | 2019-06-11 | 石家庄铁道大学 | A kind of awning Structural Damage Identification, device and terminal device |
| CN110147781B (en) * | 2019-05-29 | 2022-11-15 | 重庆交通大学 | Bridge vibration mode visual damage identification method based on machine learning |
| CN110147781A (en) * | 2019-05-29 | 2019-08-20 | 重庆交通大学 | Bridge vibration mode based on machine learning visualizes damnification recognition method |
| CN110472268A (en) * | 2019-06-25 | 2019-11-19 | 北京建筑大学 | A kind of bridge monitoring data modality recognition methods and device |
| CN110472268B (en) * | 2019-06-25 | 2022-12-20 | 北京建筑大学 | Bridge monitoring data modal identification method and device |
| CN111225000A (en) * | 2020-02-24 | 2020-06-02 | 南京震坤物联网科技有限公司 | Bridge structure health monitoring system based on block chain technology |
| CN111505010A (en) * | 2020-04-28 | 2020-08-07 | 张地林 | Bridge safety detection system based on cloud platform |
| CN111735532A (en) * | 2020-06-24 | 2020-10-02 | 淮阴工学院 | Bridge resonance testing device and method |
| CN112485030B (en) * | 2020-11-09 | 2023-03-14 | 深圳市桥博设计研究院有限公司 | Bridge structure dynamic monitoring method, system and equipment based on frequency coupling |
| CN112485030A (en) * | 2020-11-09 | 2021-03-12 | 深圳市桥博设计研究院有限公司 | Bridge structure dynamic monitoring method, system and equipment based on frequency coupling |
| 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 |
| CN113408396A (en) * | 2021-06-15 | 2021-09-17 | 广西交科集团有限公司 | Bridge intelligent sensing system based on cloud computing |
| CN113514110A (en) * | 2021-08-19 | 2021-10-19 | 张旭辉 | Road and bridge engineering intelligent measurement system |
| CN116842348A (en) * | 2023-08-31 | 2023-10-03 | 安徽省云鹏工程项目管理有限公司 | Bridge health monitoring system based on artificial intelligence |
| CN116842348B (en) * | 2023-08-31 | 2023-12-01 | 安徽省云鹏工程项目管理有限公司 | Bridge health monitoring system based on artificial intelligence |
| CN117191305A (en) * | 2023-11-06 | 2023-12-08 | 临沂市公路事业发展中心兰陵县中心 | State evaluation method and system for highway bridge |
| CN117191305B (en) * | 2023-11-06 | 2024-02-02 | 临沂市公路事业发展中心兰陵县中心 | State evaluation method and system for highway bridge |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271406A (en) | A kind of bridge health monitoring system based on big data | |
| Liu et al. | Structure damage diagnosis using neural network and feature fusion | |
| Kopsaftopoulos et al. | Vibration based health monitoring for a lightweight truss structure: experimental assessment of several statistical time series methods | |
| CN109559025A (en) | A kind of bridge detecting/monitoring integrated health condition evaluation system and its application method | |
| CN106006344A (en) | Online escalator fault early warning system and fault diagnosis method | |
| CN102053016A (en) | System for monitoring vibration of rotating machinery rolling bearing in wireless mode | |
| CN109341848A (en) | A kind of safety monitoring system of tunnel operation stage | |
| US11614410B2 (en) | Integrated and automated video/structural health monitoring system | |
| CN107380201A (en) | Based on wide area network and LAN axletree health status monitoring method and monitoring system | |
| CN106649755A (en) | Threshold self-adaption setting abnormity detection method for multi-dimensional real-time power transformation device data | |
| Overbey et al. | A parametric investigation of state-space-based prediction error methods with stochastic excitation for structural health monitoring | |
| CN103674538A (en) | Multi-fault mode identification method and device of swashplate of helicopter | |
| Huang et al. | Online dual‐rate decentralized structural identification for wireless sensor networks | |
| CN104316167A (en) | Structure response abnormity detection method under the condition of low signal-to-noise ratio | |
| CN104215379B (en) | Landing stage, sloping quay mooring cable load monitoring early warning system and method | |
| CN114812984A (en) | Movable rapid monitoring system for railway bridge | |
| CN113641486B (en) | Intelligent turnout fault diagnosis method based on edge computing network architecture | |
| CN202025092U (en) | Earthquake monitoring and early warning device | |
| CN103929738B (en) | WSNs united intrusion detection method based on multiple danger agents | |
| CN102879475B (en) | Identification system for fatigue damage state of 16 manganese steel bearing member based on PCA and TDF | |
| JP2021047059A (en) | Drone system and program of drone system | |
| Bordignon et al. | Nonlinear analysis and prediction of river flow time series | |
| Hayden et al. | Selection of near-fault pulse motions for use in design | |
| EP3679787B1 (en) | Method and system for monitoring epidemic disease in piggery | |
| CN112529041A (en) | Icing quantitative monitoring method and device based on guided wave energy characteristic principal component 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190125 |
|
| RJ01 | Rejection of invention patent application after publication |