CN102539098A - Bridge dynamic load testing method based on neural network technology - Google Patents
Bridge dynamic load testing method based on neural network technology Download PDFInfo
- Publication number
- CN102539098A CN102539098A CN201110420093XA CN201110420093A CN102539098A CN 102539098 A CN102539098 A CN 102539098A CN 201110420093X A CN201110420093X A CN 201110420093XA CN 201110420093 A CN201110420093 A CN 201110420093A CN 102539098 A CN102539098 A CN 102539098A
- Authority
- CN
- China
- Prior art keywords
- dynamic load
- bridge
- neural network
- response
- load response
- 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.)
- Granted
Links
Images
Abstract
The invention provides a bridge dynamic load testing method based on neural network technology, which includes conducting statistic analysis on a large amount of existing bridge testing results, determining dynamic load response affecting parameters of a bridge structure, using the affecting parameters as an input layer to construct a neural network model, and deducing structural dynamic load response predicted value; and conducting dynamic load actual measurement on the bridge under single vehicle speed, conducting reliability inspection on neural network theoretical derivation value by using actual measurement value, obtaining dynamic response verified through the actual measurement and characteristics of the bridge structure, and judging actual states and safety performance of the bridge structure according to the dynamic response and the characteristics of the bridge. Due to the fact that the bridge dynamic load testing method combines advantages of a conventional dynamic load testing method and the neural network technology is used to optimize a testing process, bridge dynamic load testing estimation conducted by means of the method greatly reduces structural damage caused by conventional dynamic load testing and improves analysis efficiency and operability on the basis of being capable of guaranteeing accurate and reliable testing results.
Description
Technical field
The present invention relates to a kind of bridge dynamic load detection technique, be particularly useful for the dynamic load response test of all kinds of bridge structures and carry out the assessment of bridge power performance based on nerual network technique.
Background technology
The kinematic behavior of bridge structure is the important parameter of bridge capacity evaluation, also is simultaneously identification bridge structure serviceability and the important parameter that carries out the bridge structure dynamic analysis.Along with the needs that the popularization and the bridge security of highway in China bridge test evaluation system are assessed, bridge dynamic loading test more and more comes into one's own, and has become new bridge and has become axle load to carry the important means of test and old bridge Bearing Capacity Evaluation.The dynamic test of bridge mainly comprises preventing test, brake test, the test of jumping car, and is specific as follows:
1) preventing test mainly is a test loaded vehicle when crossing bridge with various different speed per hours, and the dynamic response at each principal character position of bridge obtains coefficient of impact etc. thus.Its speed of a motor vehicle can select 5,10,20,40,60,80km/h etc.; Every kind of speed of a motor vehicle sport car 3～4 times; Test findings is averaged, and notes the time-history curves of each measuring point under each preventing test speed, obtains the peak swing value of each measuring point under each speed of a motor vehicle and analyzes its rule.
2) automobile crosses bridge with half of design F-Zero in the brake test, and the location brake on the pier top of bridge braking pier is measured vertical amplitude, lateral amplitude of vibration and the pitch amplitude of each characteristic portion of bridge.Along the die-away curve of bridge to measuring point, the suitable bridge that can try to achieve bridge is to the natural frequency of vibration and damping ratio when analyzing automobile brake.
3) jump the car test and adopt loaded vehicle freely falling body exciting bridge from the high sleeper of 15cm.By the piezoelectric acceleration sensor pick-up, distribution lotus amplifier carries out conversion of signals, utilizes the dynamic signal acquisition analyser to carry out data acquisition and analysis, can draw bridge span structure natural frequency and damping ratio equally.
More than common bridge dynamic loading test often to spend several days time, need the traffic of enclosure portion bridge, and influenced by temperature, accuracy of instrument etc., the precision of test result is unstable, these realistic problems are perplexing correlative study person.In addition; Bridge structure is except bearing dead weight and the various additional dead load, also will bearing live loads such as vehicle, crowd, wind-force and earthquake, its vibration effect factors complex; Only depend on the site test analysis can't satisfy the needs of practical applications; Therefore, introduce the method that nerual network technique combines with site test, guarantee that test result accurately and reliably and the workload minimizing.
Nerual network technique is a human brain and a movable mathematical model that theorizes thereof, and it is to be interconnected by rights by a large amount of processing units to constitute, and is a large-scale nonlinear adaptive system.It has the architectural feature of MPP, distributed storage and fault-tolerance, has the ability characteristics of self study, self-organization and adaptivity.Neural network has not only been simulated biological nervous system in form, and has some essential characteristics of brain, and is on the form and connection mode of system's formation, all similar with biological nervous system basically.Because artificial neural network has very strong study and generalization ability; Can effective information be distributed and deposit; Nerual network technique is applied in the bridge dynamic loading test; Can overcome existing bridge dynamic load response needs the deficiency of artificial actual measurement fully, farthest reduces to survey quantities and engineering cost.
Reliability of structure is meant structure at the appointed time, under rated condition, accomplishes the ability of predetermined function, and its reliability index fiduciary level commonly used is described.The purpose of certificate authenticity is that required result's reliability is controlled, and checks out insecure situation also in time to handle, and makes its net result can reach structural safety assessment requirement.The fiduciary level check is applied in the bridge dynamic loading test; Can be when reducing to survey quantities and engineering cost; Guarantee test result accurately and reliably, therefore fiduciary level check has in recent years obtained using widely in the health monitoring and the safety evaluation field of engineering structure.
The present invention proposes a kind of bridge dynamic load measuring technology based on nerual network technique thus, can solve well that testing expenses are expensive, the time is long, precision is not enough and not have problem such as ubiquity, and the bridge dynamic load test in future is had the directiveness effect.
Summary of the invention
Technical matters: the present invention has carried out statistical study to the actual measurement dynamic load data in a large amount of bridge load tests; On this basis; As input layer, the structure dynamic load responds as output layer with structural parameters etc., obtains to have the bridge dynamic load response of certain fiduciary level through nerual network technique; And then carry out the bridge security Performance Evaluation, certain facilitation is played in the development of the bridge dynamic load measuring technology in future.
Technical scheme: in order to develop a kind of bridge dynamic load method of testing based on nerual network technique; To overcome the more deficiency that exists in the existing bridge dynamic load test; The existing a large amount of bridge dynamic load measured datas of statistical study of the present invention; Therefrom extracting bridge dynamic load response influence parameter, utilizes nerual network technique to derive to have the specific bridge dynamic load of certain fiduciary level to respond, and makes things convenient for the bridge worker to carry out the bridge Performance Evaluation.
Solving the problems of the technologies described above the technical scheme that is adopted is: the existing a large amount of bridge dynamic load test datas of statistical study, and determining the response of bridge structure dynamic load influences parameter; The dynamic load response of bridge structure is influenced the input layer of parameter as neural network, and its dynamic load under the different vehicle travelling speed is responded as output layer, the constructing neural network model is derived the dynamic load response of structure under the different speed of a motor vehicle; Bridge is carried out the dynamic load actual measurement, only survey the dynamic load response under a certain speed, and adopt measured result that the neural network derivation result is carried out the fiduciary level check, to guarantee the reliability of neural network derivation result; Thereby analyze the kinematic behavior, forced vibration response, the power performance that obtain bridge structure, identification bridge structure serviceability.
Bridge dynamic load method of testing based on nerual network technique may further comprise the steps:
The first step: separating out in the response of different dynamic loads based on existing dynamic load test data statistical influences dynamic load responses different under the parameter; Determining corresponding dynamic load response influences parameter, comprises the speed of a motor vehicle, spanning, bridge type, cross section geometric parameter, design reference period, years already spent and environmental factor;
Second step: the dynamic load response of bridge structure is influenced parameter as the neural network input layer, the dynamic load under the different vehicle travelling speed is responded as output layer, thus the constructing neural network model;
The 3rd step: the correlation parameter that needs are carried out dynamic load test bridge is input in the middle of the neural network model that second step constructed, and obtains the structure dynamic load response of being derived by neural network model;
The 4th step: bridge is carried out the dynamic load actual measurement, only survey the dynamic load response under a certain speed, and adopt measured result that gained derivation result in the 3rd step is carried out the fiduciary level check, to guarantee the reliability of neural network derivation result;
The 5th step: if the fiduciary level assay in the 4th step does not meet the demands, then this measured data is added the sample layer according to 20%～40% proportion, repeat 1～4 step, guarantee that the dynamic load response reliability meets the demands under this speed; And the fiduciary level check is carried out in the dynamic load response actual measurement under the additional again friction speed, and the reliability that responds until the 3rd step resulting structures dynamic load is guaranteed;
The 6th step: obtain the dynamic load response and the kinematic behavior of this bridge structure, be used for the security performance of evaluation structure.
In second step, the response of the dynamic load of bridge structure influence the input layer of parameter as neural network, the dynamic load response under the different vehicle travelling speed is as output layer, middle knob husband (newff) the construction of function neural network model in utilization matrix experiment chamber (matlab); This model input layer has n neuron x, x ∈ (x
1, x
2L x
n), hidden layer has d neuron h, h ∈ (h
1, h
2L h
d), output layer has m neuron y, y ∈ (y
1, y
2L y
m); Weights and threshold value between input layer and the hidden layer are respectively w
IjAnd θ
j, weights and threshold value between hidden layer and the output layer are respectively w
JkAnd θ
k:
Hidden layer node:
The output layer node:
wherein f (x) is transport function.
In the 4th step, adopt measured result that gained derivation result in the 3rd step is carried out the fiduciary level check; Be specially: train the dynamic load response that obtains as theoretical derivation value μ by neural network model; Dynamic test actual measurement obtains under a certain speed dynamic load response and as measured value
theoretical value carried out the fiduciary level check:
is if α ∈ [5%, 5%] shows that then theoretical value has the fiduciary level of satisfying requirement; If above-mentioned fiduciary level assay does not meet the demands, then this measured data is added the sample layer according to 20%～40% proportion, repeat the first step～the 4th step, guarantee that the dynamic load response reliability meets the demands under this speed; And replenish the dynamic load response actual measurement under the friction speed again, carry out the fiduciary level check, till the reliability of resulting structures dynamic load response is guaranteed.
Beneficial effect: though existing bridge dynamic load measuring technology kind is more, tangible weak point is arranged all, long like the test duration, influence bridge deck traffic, cause structural damage, engineering cost is huge etc.To the problems referred to above; This patent has been invented the bridge dynamic load method of testing based on nerual network technique; This method has combined the advantage of conventional dynamic load method of testing; And used nerual network technique to optimize the dynamic load test process, inferred the dynamic load response of bridge under the different speed of a motor vehicle, significantly reduced the wherein number of times of preventing test by the sport car testing experiment result under the single speed of a motor vehicle.This patent can improve analysis efficiency and operability guaranteeing that test result accurately and reliably on the basis, reduces the structural damage that conventional dynamic load test is caused greatly.Perfect day by day in view of China's traffic infrastructure, old bridge unsafe bridge is also more and more thereupon, press for development one cover science, accurately, reliably, bridge monitoring technology easily.Therefore, this patent will be with a wide range of applications in following bridge dynamic load test, produces significant social and economic benefit.
Description of drawings
Fig. 1 is based on nerual network technique bridge dynamic load method of testing techniqueflow chart;
Fig. 2 neural network model synoptic diagram;
Fig. 3 normal distribution synoptic diagram.
Embodiment
The main flow process of implementation of the present invention (referring to Fig. 1) specific as follows:
1) existing a large amount of bridge structure dynamic load test datas are carried out statistical study, determining the dynamic load response influences parameter, like the speed of a motor vehicle, spanning, bridge type, cross section geometric parameter, design reference period, years already spent, environmental factor etc.;
2) the dynamic load response with bridge structure influences the input layer of parameter as neural network, and its dynamic load under the different vehicle travelling speed is responded as output layer, the constructing neural network model, and neural network algorithm model input layer has n neuron x, x ∈ (x
1, x
2L x
n), hidden layer has d neuron h, h ∈ (h
1, h
2L h
d), output layer has m neuron y, y ∈ (y
1, y
2L y
m).Weights and threshold value between input layer and the hidden layer are respectively w
IjAnd θ
j, weights and threshold value between hidden layer and the output layer are respectively w
JkAnd θ
k(referring to Fig. 2):
Hidden layer node:
The output layer node:
F in the following formula (x) is a transport function.
3) correlation parameter of specific bridge is input in the middle of the neural network model that second step constructed the dynamic load response under the different speed of a motor vehicle of structure that obtain to derive by neural network model; Bridge is carried out the dynamic load actual measurement, only survey the dynamic load response under a certain speed, and adopt measured result that the derivation result of gained is carried out the fiduciary level check, to guarantee the reliability of neural network derivation result.
Key based on nerual network technique bridge dynamic load method of testing is that neural network output layer theoretical value and dynamic test measured value are carried out the fiduciary level check; Obtain having the structural dynamic response and the kinematic behavior of certain fiduciary level, thereby bridge is carried out accurate safety assessment.According to mathematical statistics knowledge, establish X
1, X
2, X
3, L, X
nBe normal population N (μ, σ
2) sample, X, σ
2Be respectively sample average and sample variance, (referring to Fig. 3) then arranged:
Wherein:
Definition
is according to the requirement of statistical routine and bridge security assessment; As α ∈ [5%; 5%] satisfy the fiduciary level requirement time, this has just had quantitative estimation to the reliability of dynamic load response theory value.What deserves to be mentioned is, different structure form or different the detection, different for the requirement of fiduciary level and estimated accuracy, so should suitably adjust according to actual conditions.
If above-mentioned fiduciary level assay do not meet the demands, then this measured data is added the sample layer according to 20%～40% proportion, repeat 1～3 step, guarantee that the dynamic load response reliability meets the demands under this speed; And replenish the dynamic load response actual measurement under the friction speed again, carry out the fiduciary level check, till the reliability of structure dynamic load response is guaranteed;
4) obtain the dynamic load response and the kinematic behavior of this bridge structure, like coefficient of impact, damping ratio, the natural frequency of vibration, acceleration maximal value etc.(JTGD60-2004) stipulate by " highway bridge and culvert design general specification ", judge the influence that can tested bridge effectively avoid unusual impact that bridge is caused by coefficient of impact; Carry out the finite element model correction of structure and the damage identification of structure according to the variation of damping ratio, the natural frequency of vibration etc.; According to contrast of acceleration maximal value and human comfort index etc., come the tested Structure Safety for Bridge performance of multifactorial evaluation.
At present, a large amount of bridge structures comprise that newly-built bridge and old bridge all are directed against different demands and carried out loading test.Dynamic load test data based on a large amount of existing bridges; It is that the dynamic load response influences parameter that statistical is separated out its parameter input object; Separating out in the response of different dynamic loads based on existing dynamic load test data statistical influences dynamic load responses different under the parameter; Specifically influence the parameter such as the speed of a motor vehicle (5m/s, 10m/s, 20m/s, 30m/s, 40m/s, 50m/s), spanning (10～200m, 10m increases progressively), bridge type (freely-supported, continuous, firm structure, arch), cross section geometric parameter (cross section type, area, the moment of inertia), design reference period (30 years, 50 years, 70 years, 100 years, 120 years), years already spent (1～120 year), environmental factor (is I level, II level, III level, IV level by regulation and stipulation);
The newff function generates neural network among the utilization matlab, and the form that the newff function is commonly used is:
net＝newff(PR，[S
1，S
2L，S
N]，{TF
1，TF
2L，TF
N}，BTE) (4)
In the formula (4), PR is R * 2 dimension groups, the minimum value of every dimension input and the scope between the maximal value in the expression R dimension input vector; If neural network has N layer, then [S
1, S
2L, S
N] in each element represent each layer neuron number respectively; { TF
1, TF
2L, TF
NIn each element represent the transport function that each layer neuron adopts respectively; Employed training function when BTE representes neural metwork training.
The constructing neural network model is main according to following two governing principles:
1. for general considerations, adopt three-layer network to get final product fine solution;
2. in the three-layer network, the relation of hidden layer neuron number d and input layer number n is that the optimal number of hidden layer neuron is not what fix, need constantly adjust through hands-on but merit attention suc as formula (5):
d＝2n+1 (5)
Utilization matlab tool configuration is intensive through network model, obtains the dynamic load response of this bridge under the different speed of a motor vehicle by the neural network model training, and this value is theoretical derivation value μ; The actual measurement bridge is carried out dynamic test; Only survey the dynamic load response under a certain speed, this value is measured value
Theoretical value is carried out the fiduciary level check:
is if α ∈ [5%; 5%] show that then theoretical value satisfies the fiduciary level requirement, then the dynamic load response under other speed can directly be used;
If above-mentioned fiduciary level assay do not meet the demands, then this measured data is added the sample layer according to 20%～40% proportion, repeat 1～4 step in the implementation, guarantee that the dynamic load response reliability meets the demands under this speed; And replenish the dynamic load response actual measurement under the friction speed again, carry out the fiduciary level check, till the reliability of resulting structures dynamic load response is guaranteed; Obtain the dynamic load response and the kinematic behavior of this bridge structure, like coefficient of impact, damping ratio, the natural frequency of vibration, acceleration maximal value etc.(JTGD60-2004) stipulate by " highway bridge and culvert design general specification ", judge the influence that can tested bridge effectively avoid unusual impact that bridge is caused by coefficient of impact; Carry out the finite element model correction of structure and the damage identification of structure according to the variation of damping ratio, the natural frequency of vibration etc.; According to contrast of acceleration maximal value and human comfort index etc., come the tested Structure Safety for Bridge performance of multifactorial evaluation.
Claims (3)
1. bridge dynamic load method of testing based on nerual network technique is characterized in that this method may further comprise the steps:
The first step: separating out in the response of different dynamic loads based on existing dynamic load test data statistical influences dynamic load responses different under the parameter; Determining corresponding dynamic load response influences parameter, comprises the speed of a motor vehicle, spanning, bridge type, cross section geometric parameter, design reference period, years already spent and environmental factor;
Second step: the dynamic load response of bridge structure is influenced parameter as the neural network input layer, the dynamic load under the different vehicle travelling speed is responded as output layer, thus the constructing neural network model;
The 3rd step: the correlation parameter that needs are carried out dynamic load test bridge is input in the middle of the neural network model that second step constructed, and obtains the structure dynamic load response of being derived by neural network model;
The 4th step: bridge is carried out the dynamic load actual measurement, only survey the dynamic load response under a certain speed, and adopt measured result that gained derivation result in the 3rd step is carried out the fiduciary level check, to guarantee the reliability of neural network derivation result;
The 5th step: if the fiduciary level assay in the 4th step does not meet the demands, then this measured data is added the sample layer according to 20%～40% proportion, repeat 1～4 step, guarantee that the dynamic load response reliability meets the demands under this speed; And the fiduciary level check is carried out in the dynamic load response actual measurement under the additional again friction speed, and the reliability that responds until the 3rd step resulting structures dynamic load is guaranteed;
The 6th step: obtain the dynamic load response and the kinematic behavior of this bridge structure, be used for the security performance of evaluation structure.
2. the bridge dynamic load method of testing based on nerual network technique according to claim 1; It is characterized in that in second step; The dynamic load response of bridge structure is influenced the input layer of parameter as neural network; Dynamic load response under the different vehicle travelling speed is used knob husband newff construction of function neural network model among the matrix experiment chamber matlab as output layer; This model input layer has n neuron x, x ∈ (x
1, x
2L x
n), hidden layer has d neuron h, h ∈ (h
1, h
2L h
d), output layer has m neuron y, y ∈ (y
1, y
2L y
m); Weights and threshold value between input layer and the hidden layer are respectively w
IjAnd θ
j, weights and threshold value between hidden layer and the output layer are respectively w
JkAnd θ
k:
3. the bridge dynamic load method of testing based on nerual network technique according to claim 1; It is characterized in that adopting in the 4th step measured result that gained derivation result in the 3rd step is carried out the fiduciary level check; Be specially: train the dynamic load response that obtains as theoretical derivation value μ by neural network model; Dynamic test actual measurement obtains under a certain speed dynamic load response and as measured value
theoretical value carried out the fiduciary level check:
is if α ∈ [5%, 5%] shows that then theoretical value satisfies the fiduciary level requirement; If above-mentioned fiduciary level assay does not meet the demands, then this measured data is added the sample layer according to 20%～40% proportion, repeat the first step～the 4th step, guarantee that the dynamic load response reliability meets the demands under this speed; And replenish the dynamic load response actual measurement under the friction speed again, carry out the fiduciary level check, till the reliability of resulting structures dynamic load response is guaranteed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110420093.XA CN102539098B (en) | 2011-12-15 | 2011-12-15 | Bridge dynamic load testing method based on neural network technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110420093.XA CN102539098B (en) | 2011-12-15 | 2011-12-15 | Bridge dynamic load testing method based on neural network technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102539098A true CN102539098A (en) | 2012-07-04 |
| CN102539098B CN102539098B (en) | 2014-01-22 |
Family
ID=46346543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110420093.XA Expired - Fee Related CN102539098B (en) | 2011-12-15 | 2011-12-15 | Bridge dynamic load testing method based on neural network technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102539098B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104101472A (en) * | 2014-07-15 | 2014-10-15 | 同济大学 | Design response spectrum based floor structure dynamic response testing method under walking loading |
| CN104112073A (en) * | 2014-07-15 | 2014-10-22 | 同济大学 | Response spectrum method used for analyzing floor system vibration response under bounce load |
| CN104200004A (en) * | 2014-07-28 | 2014-12-10 | 东北大学 | Optimized bridge damage identification method based on neural network |
| CN104655390A (en) * | 2015-02-12 | 2015-05-27 | 西南交通大学 | Wind tunnel test device for vehicle model moving on bridge based on precision linear slide rails |
| CN105550506A (en) * | 2015-12-09 | 2016-05-04 | 东南大学 | Method for directly predicting wind-induced vibration response of bridge based on long-term actually measured data |
| CN104112071B (en) * | 2014-07-15 | 2017-02-01 | 同济大学 | Floor system vibration response computing method under jumping loads |
| CN108133070A (en) * | 2017-09-19 | 2018-06-08 | 广州市建筑科学研究院有限公司 | A kind of appraisal procedure and system of the bridge health situation based on radial basis function neural network |
| CN108446838A (en) * | 2018-03-08 | 2018-08-24 | 佛山科学技术学院 | A kind of bridge safety supervision system based on big data |
| CN108534967A (en) * | 2018-03-08 | 2018-09-14 | 佛山科学技术学院 | Bridge safety supervision system based on sensor network |
| CN109102016A (en) * | 2018-08-08 | 2018-12-28 | 北京新桥技术发展有限公司 | A kind of test method for bridge technology situation |
| CN110031175A (en) * | 2019-03-20 | 2019-07-19 | 东南大学 | A kind of bolt connection piece equivalent model parameter identification method based on dynamic response |
| CN110532657A (en) * | 2019-08-21 | 2019-12-03 | 哈尔滨工业大学 | Bridge pier structure state evaluating method based on transmission vehicle excitation and wavelet packet analysis |
| CN110704911A (en) * | 2019-09-19 | 2020-01-17 | 济南城建集团有限公司 | Bridge damage cross positioning method based on cluster structure similarity |
| CN110987499A (en) * | 2019-12-17 | 2020-04-10 | 中交路桥建设有限公司 | Bridge dynamic load test method |
| CN111674360A (en) * | 2019-01-31 | 2020-09-18 | 青岛科技大学 | Method for establishing distinguishing sample model in vehicle tracking system based on block chain |
| CN113627511A (en) * | 2021-08-04 | 2021-11-09 | 中国科学院科技战略咨询研究院 | Model training method and influence monitoring method for influence of climate change on traffic industry |
| CN116244803A (en) * | 2023-02-22 | 2023-06-09 | 合肥工业大学 | Bridge internal response reconstruction method based on physical and data dual drive |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5774376A (en) * | 1995-08-07 | 1998-06-30 | Manning; Raymund A. | Structural health monitoring using active members and neural networks |
| CN1740444A (en) * | 2005-09-23 | 2006-03-01 | 重庆交通学院 | Remote monitoring bridge evaluating method |
| CN101145214A (en) * | 2007-11-06 | 2008-03-19 | 东南大学 | Cable-stayed bridge cable damage positioning method based on modified reverse transmittance nerve network |
| CN101586996A (en) * | 2009-06-26 | 2009-11-25 | 贵州师范大学 | Cable force prediction method of cable stayed bridge based on artificial neural network |
-
2011
- 2011-12-15 CN CN201110420093.XA patent/CN102539098B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5774376A (en) * | 1995-08-07 | 1998-06-30 | Manning; Raymund A. | Structural health monitoring using active members and neural networks |
| CN1740444A (en) * | 2005-09-23 | 2006-03-01 | 重庆交通学院 | Remote monitoring bridge evaluating method |
| CN101145214A (en) * | 2007-11-06 | 2008-03-19 | 东南大学 | Cable-stayed bridge cable damage positioning method based on modified reverse transmittance nerve network |
| CN101586996A (en) * | 2009-06-26 | 2009-11-25 | 贵州师范大学 | Cable force prediction method of cable stayed bridge based on artificial neural network |
Non-Patent Citations (1)
| Title |
|---|
| 陈修辉: "《基于神经网络的桥梁移动荷载识别》", 31 December 2009 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104101472A (en) * | 2014-07-15 | 2014-10-15 | 同济大学 | Design response spectrum based floor structure dynamic response testing method under walking loading |
| CN104112073A (en) * | 2014-07-15 | 2014-10-22 | 同济大学 | Response spectrum method used for analyzing floor system vibration response under bounce load |
| CN104101472B (en) * | 2014-07-15 | 2017-01-18 | 同济大学 | Design response spectrum based floor structure dynamic response testing method under walking loading |
| CN104112071B (en) * | 2014-07-15 | 2017-02-01 | 同济大学 | Floor system vibration response computing method under jumping loads |
| CN104112073B (en) * | 2014-07-15 | 2017-04-05 | 同济大学 | The response spectrum method of superstructure Response Analysis under a kind of load for bounce |
| CN104200004A (en) * | 2014-07-28 | 2014-12-10 | 东北大学 | Optimized bridge damage identification method based on neural network |
| CN104655390A (en) * | 2015-02-12 | 2015-05-27 | 西南交通大学 | Wind tunnel test device for vehicle model moving on bridge based on precision linear slide rails |
| CN104655390B (en) * | 2015-02-12 | 2018-01-05 | 西南交通大学 | Mobile vehicle model wind tunnel test device on bridge based on accurate line slide rail |
| CN105550506A (en) * | 2015-12-09 | 2016-05-04 | 东南大学 | Method for directly predicting wind-induced vibration response of bridge based on long-term actually measured data |
| CN105550506B (en) * | 2015-12-09 | 2018-05-04 | 东南大学 | Bridge wind vibration response DIRECT FORECASTING METHOD based on long-term measured data |
| CN108133070A (en) * | 2017-09-19 | 2018-06-08 | 广州市建筑科学研究院有限公司 | A kind of appraisal procedure and system of the bridge health situation based on radial basis function neural network |
| CN108534967A (en) * | 2018-03-08 | 2018-09-14 | 佛山科学技术学院 | Bridge safety supervision system based on sensor network |
| CN108446838A (en) * | 2018-03-08 | 2018-08-24 | 佛山科学技术学院 | A kind of bridge safety supervision system based on big data |
| CN109102016A (en) * | 2018-08-08 | 2018-12-28 | 北京新桥技术发展有限公司 | A kind of test method for bridge technology situation |
| CN111674360A (en) * | 2019-01-31 | 2020-09-18 | 青岛科技大学 | Method for establishing distinguishing sample model in vehicle tracking system based on block chain |
| CN110031175B (en) * | 2019-03-20 | 2020-03-31 | 东南大学 | Bolt connecting piece equivalent model parameter identification method based on dynamic response |
| CN110031175A (en) * | 2019-03-20 | 2019-07-19 | 东南大学 | A kind of bolt connection piece equivalent model parameter identification method based on dynamic response |
| CN110532657B (en) * | 2019-08-21 | 2022-12-09 | 哈尔滨工业大学 | Pier structure state evaluation method based on variable speed vehicle excitation and wavelet packet analysis |
| CN110532657A (en) * | 2019-08-21 | 2019-12-03 | 哈尔滨工业大学 | Bridge pier structure state evaluating method based on transmission vehicle excitation and wavelet packet analysis |
| CN110704911A (en) * | 2019-09-19 | 2020-01-17 | 济南城建集团有限公司 | Bridge damage cross positioning method based on cluster structure similarity |
| CN110987499A (en) * | 2019-12-17 | 2020-04-10 | 中交路桥建设有限公司 | Bridge dynamic load test method |
| CN113627511A (en) * | 2021-08-04 | 2021-11-09 | 中国科学院科技战略咨询研究院 | Model training method and influence monitoring method for influence of climate change on traffic industry |
| CN113627511B (en) * | 2021-08-04 | 2024-02-02 | 中国科学院科技战略咨询研究院 | Model training method for influence of climate change on traffic and influence monitoring method |
| CN116244803A (en) * | 2023-02-22 | 2023-06-09 | 合肥工业大学 | Bridge internal response reconstruction method based on physical and data dual drive |
| CN116244803B (en) * | 2023-02-22 | 2023-09-12 | 合肥工业大学 | Bridge internal response reconstruction method based on physical and data dual drive |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102539098B (en) | 2014-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102539098B (en) | Bridge dynamic load testing method based on neural network technology | |
| CN108763763B (en) | Bridge structure strain response abnormity early warning method | |
| CN111144039B (en) | Train dynamic weighing system and weighing method based on deep learning | |
| CN108573601B (en) | Traffic safety risk field construction method based on WIM data | |
| CN103852269B (en) | Bullet train runs kinetic parameter detection method | |
| CN106197910A (en) | A kind of Bridges Detection based on Vehicle-bridge Coupling Analysis and detecting system | |
| CN104200005A (en) | Bridge damage identification method based on neural network | |
| CN107885927B (en) | Railway bridge operation state early warning method | |
| CN105956216A (en) | Finite element model correction method for large-span steel bridge based on uniform temperature response monitoring value | |
| CN104112080A (en) | Method for fast early warning against water body water bloom risk | |
| Tan et al. | Extracting mode shapes from drive-by measurements to detect global and local damage in bridges | |
| Ni et al. | Dynamic property evaluation of a long-span cable-stayed bridge (Sutong bridge) by a Bayesian method | |
| Li et al. | Evaluation of typhoon induced fatigue damage for Tsing Ma Bridge | |
| Li et al. | Monitoring abnormal vibration and structural health conditions of an in-service structure from its SHM data | |
| Su et al. | Automatic identification of modal parameters for structures based on an uncertainty diagram and a convolutional neural network | |
| CN103344395B (en) | A kind of confirmation method of bridge strengthening target bearing capacity and device | |
| Ye et al. | Prediction and early warning of wind-induced girder and tower vibration in cable-stayed bridges with machine learning-based approach | |
| CN110889196B (en) | Water environment bearing capacity assessment method and device based on water quality model and storage medium | |
| Getachew | Traffic load effects on bridges, statistical analysis of collected and Monte Carlo simulated vehicle data | |
| Liu et al. | Fatigue lifespan assessment of stay cables by a refined joint probability density model of wind speed and direction | |
| CN113935384B (en) | Bridge health monitoring method and system for self-adaptive decomposition and recognition of signals | |
| CN112362148B (en) | Method and system for dynamically identifying vehicle axle weight based on load of stay cable force influence surface | |
| Xiang et al. | Vibration-based structural damage identification using P-CNN and time-frequency hybrid index under the conditions of uncertainties and incomplete measurements | |
| Figueiredo et al. | Applicability of a Markov-Chain Monte Carlo method for damage detection on data from the Z-24 and Tamar suspension bridges | |
| Ren et al. | Estimation of extreme cable forces of cable-stayed bridges based on monitoring data and random vehicle models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140122 Termination date: 20161215 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |