CN106529062A - Bridge structure health diagnosis method based on deep learning - Google Patents
Bridge structure health diagnosis method based on deep learning Download PDFInfo
- Publication number
- CN106529062A CN106529062A CN201611029162.3A CN201611029162A CN106529062A CN 106529062 A CN106529062 A CN 106529062A CN 201611029162 A CN201611029162 A CN 201611029162A CN 106529062 A CN106529062 A CN 106529062A
- Authority
- CN
- China
- Prior art keywords
- deep learning
- data
- bridge
- bridge structure
- learning network
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The present invention provides a bridge structure health diagnosis method based on deep learning. The method comprises: step one, preprocessing data; step two, by using data in a design stage and a construction stage, establishing a precise finite element model of a bridge structure as a training input of a deep learning network; step three, constructing a five-layer deep learning network DN; step four, fine-tuning a fifth layer of the deep learning network; step five, input another part of data in a monitoring stage into the network to further optimize the whole deep learning network; and step six, according to the deep learning network that is formed in step five and can be used for structure health diagnosis, diagnosing whether a structure health state of any one bridge is normal or in which deterioration state level. According to the bridge structure health diagnosis method based on deep learning provided by the present invention, the health state of various bridge structures can be diagnosed and checked quickly and effectively by establishing the deep learning network.
Description
Technical field
The present invention relates to bridge technology field, more particularly to a kind of bridge structure health diagnosis side based on deep learning
Method.
Background technology
Bridge is the throat of traffic, and the safety problem of bridge structure is related to great property safety even life security, always
All paid much attention to by all circles.With the propulsion of active time, material aging aggravation, the volume of traffic and overload for increasing increasingly is added,
The local damage of bridge structure can be caused.The safety of final crisis bridge.However, due to bridge structure it is complicated, damage influence because
Element is numerous, using traditional diagnostic method data often only with a certain stage, it is difficult to obtain effective diagnostic result.Therefore
The Gernral Check-up problem of bridge structure has become a generally acknowledged difficult problem.In view of bridge structure is equal in design, construction, maintenance, monitoring
Mass data is saved, wherein necessarily having contained the various features of bridge structure health state, therefore a kind of effective base is studied
Have important practical significance in the bridge structure health diagnostic method of deep learning.
The content of the invention
The invention provides a kind of bridge structure health diagnostic method based on deep learning, it is intended to solve to tie due to bridge
Structure is complicated, influence factor is numerous, and the health status of bridge structure is difficult to the problem of efficient diagnosis.
A kind of bridge structure health diagnostic method based on deep learning, comprises the following steps：
Step one, data prediction, by many bridge blocks in design, construction, the Data Collection safeguarded, monitor four-stage
Afterwards, taxonomic revision is carried out according to data character difference, data fusion is carried out using big data processing method then, form depth
Practise all kinds of input datas needed for network；Bridge therein includes the bridge of certain type of different size, different geographical, and contains
There is the situation of normal condition and various deterioration states；
Step 2, using design phase and the data of construction stage, sets up the Deterministic Finite meta-model of bridge structure, respectively
The situation of simulation bridge structure normal condition and various deterioration states, and related data is preserved as the training of deep learning network
Input；
Step 3, builds one five layers of deep learning network DN, and ground floor SS adopts sparse autocoder, second,
The general autocoder of three layers of employing, the 4th layer of DS adopt noise reduction autocoder, layer 5 SVM to adopt SVMs, its
Input data is that (i=1,2 ..., n), the input data formed by step one can be Arbitrary Matrix to A [i].Output data is S
[j] (j=1,2 ..., m), represent the overall healthy shape of the concrete health status and bridge structure of bridge structure regional
State, can be Arbitrary Matrix；
Step 4, feature learning, by design, the data input deep learning network DN in two stages of construction, using without prison
Supervise and instruct white silk, obtain the feature of the normal all kinds of parameters of bridge structure；By maintenance phase and monitoring the stage a part of data and
The data input network of finite element modelling, using Training, obtains spy of the structure in all kinds of parameters of various deterioration states
Levy, and finely tune the layer 5 of deep learning network；
Step 5, data verification, by another part data input network in monitoring stage, carry out data verification, and according to
The result further optimizes entire deep learning network, ultimately forms one and can be common to different types of rridges structure for health diagnosis
Deep learning network；
Step 6, bridge structure health diagnosis, according to the deep learning that can be used for structure for health diagnosis that step 5 is formed
The various data of the bridge are pre-processed using the method for similar step one by network to arbitrary bridge, and formation can be input into number
The deep learning network successfully trained can be input to be diagnosed according to after, so as to accurately obtain the structural health shape of the bridge
State is normal or which rank of deterioration state is in.
Further, bridge structure health diagnostic method as above based on deep learning, number described in step one
Include according to property：Environment, geology, structure, time.
Further, bridge structure health diagnostic method as above based on deep learning, bad described in step 2
Change state is divided into slight, slight, intermediate, serious and unacceptable Pyatyi according to bridge structure reliability specification.
The bridge structure health diagnostic method based on deep learning that the present invention is provided, by setting up deep learning network,
Such that it is able to quickly and efficiently carry out deagnostic test to the health status of different types of rridges structure.
Description of the drawings
Fig. 1 is deep learning schematic network structure of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below the present invention in technical scheme carry out clearly
Chu, it is fully described by, it is clear that described embodiment is a part of embodiment of the invention, rather than the embodiment of whole.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
It is an object of the invention to provide a kind of bridge structure health diagnostic method based on deep learning, the method includes
Following steps：
Step one, data prediction.By many bridge blocks in design, construction, the Data Collection safeguarded, monitor four-stage
Afterwards, taxonomic revision is carried out according to data character (environment, geology, structure, time) difference, then using big data processing method
Mapreduce carries out data fusion, forms all kinds of input datas needed for depth below learning network.Bridge therein includes certain
The different size of type, the bridge of different geographical, and the situation containing normal condition and various deterioration states.
Step 2, using design phase and the data of construction stage, sets up the Deterministic Finite meta-model of bridge structure, respectively
The situation of simulation bridge structure normal condition and various deterioration states, and related data is preserved as the training of deep learning network
Input.Wherein deterioration state is divided into slight, slight, intermediate, serious and unacceptable Pyatyi according to bridge structure reliability specification.
Step 3, builds one five layers of deep learning network DN.Ground floor SS adopt sparse autocoder, second,
Three layers (respectively GS1, GS2), using general autocoder, the 4th layer of DS adopts noise reduction autocoder, layer 5 SVM to adopt
With SVMs (such as Fig. 1).Its input data is that (i=1,2 ..., n), the input data formed by step one can for A [i]
For Arbitrary Matrix.Output data be S [j] (j=1,2 ..., m), represent bridge structure regional concrete health status and
The overall health status of bridge structure, can be Arbitrary Matrix.
Step 4, feature learning.By design, the data input deep learning network in two stages of construction, using unsupervised
Training, obtains the feature of the normal all kinds of parameters of bridge structure；By maintenance phase and monitoring the stage a part of data and have
The data input network of limit unit simulation, using Training, obtains feature of the structure in all kinds of parameters of various deterioration states,
And finely tune the layer 5 of deep learning network.
Step 5, data verification.By another part data input network in monitoring stage, data verification is carried out, and according to
The result further optimizes entire deep learning network.Ultimately form one and can be common to different types of rridges structure for health diagnosis
Deep learning network.
Step 6, bridge structure health diagnosis.Have passed through step 5 and form the deep learning that can be used for structure for health diagnosis
After network, for arbitrary bridge block, need to carry out the various data of the bridge using the method for similar step one during diagnosis
Pretreatment, forms and the deep learning network successfully trained can be input to after input data be diagnosed, so as to accurate
Structural health conditions to the bridge are normal or which rank of deterioration state are in.
Finally it should be noted that：Above example only to illustrate technical scheme, rather than a limitation；Although
With reference to the foregoing embodiments the present invention has been described in detail, it will be understood by those within the art that：Which still may be used
To modify to the technical scheme described in foregoing embodiments, or equivalent is carried out to which part technical characteristic；
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (3)
1. a kind of bridge structure health diagnostic method based on deep learning, it is characterised in that comprise the following steps：
Step one, data prediction, by many bridge blocks after design, construction, the Data Collection safeguarded, monitor four-stage, root
Taxonomic revision is carried out according to data character difference, data fusion is carried out using big data processing method then, form deep learning net
All kinds of input datas needed for network；Bridge therein includes the bridge of certain type of different size, different geographical, and containing just
The situation of normal state and various deterioration states；
Step 2, using design phase and the data of construction stage, sets up the Deterministic Finite meta-model of bridge structure, simulates respectively
The situation of bridge structure normal condition and various deterioration states, and it is defeated as the training of deep learning network to preserve related data
Enter；
Step 3, builds one five layers of deep learning network DN, and ground floor SS adopts sparse autocoder, second and third layer
Using general autocoder, the 4th layer of DS adopts noise reduction autocoder, layer 5 SVM to adopt SVMs, its input
Data are that (i=1,2 ..., n), the input data formed by step one can be Arbitrary Matrix to A [i].Output data is S [j]
(j=1,2 ..., m), represent the overall health status of the concrete health status and bridge structure of bridge structure regional, can
Being Arbitrary Matrix；
Step 4, feature learning, by design, the data input deep learning network DN in two stages of construction, using unsupervised instruction
Practice, obtain the feature of the normal all kinds of parameters of bridge structure；By maintenance phase and monitoring a part of data in stage and limited
The data input network of unit's simulation, using Training, obtains feature of the structure in all kinds of parameters of various deterioration states, and
The layer 5 of fine setting deep learning network；
Step 5, data verification, by another part data input network in monitoring stage, carry out data verification, and according to checking
As a result further optimize entire deep learning network, ultimately form a depth that can be common to different types of rridges structure for health diagnosis
Degree learning network；
Step 6, bridge structure health diagnosis, according to the deep learning network that can be used for structure for health diagnosis that step 5 is formed,
Arbitrary bridge is pre-processed to the various data of the bridge using the method for similar step one, formation can after input data be
The deep learning network successfully trained can be input to be diagnosed, so as to the structural health conditions for accurately obtaining the bridge are just
Which rank of deterioration state be still in often.
2. the bridge structure health diagnostic method based on deep learning according to claim 1, it is characterised in that step one
Described in data character include：Environment, geology, structure, time.
3. the bridge structure health diagnostic method based on deep learning according to claim 1, it is characterised in that step 2
Described in deterioration state slight, slight, intermediate, serious and unacceptable Pyatyi is divided into according to bridge structure reliability specification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611029162.3A CN106529062B (en) | 2016-11-20 | 2016-11-20 | A kind of bridge structure health diagnostic method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611029162.3A CN106529062B (en) | 2016-11-20 | 2016-11-20 | A kind of bridge structure health diagnostic method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106529062A true CN106529062A (en) | 2017-03-22 |
| CN106529062B CN106529062B (en) | 2019-10-11 |
Family
ID=58353123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611029162.3A Expired - Fee Related CN106529062B (en) | 2016-11-20 | 2016-11-20 | A kind of bridge structure health diagnostic method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106529062B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108511064A (en) * | 2018-02-11 | 2018-09-07 | 河南工程学院 | The system for automatically analyzing healthy data based on deep learning |
| 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 |
| CN109256773A (en) * | 2018-10-19 | 2019-01-22 | 东北大学 | Power system state estimation method of the noise reduction from coding and depth support vector machines |
| CN110047145A (en) * | 2019-04-15 | 2019-07-23 | 山东师范大学 | Metaplasia simulation system and method based on deep learning and finite element modeling |
| CN110119656A (en) * | 2018-02-07 | 2019-08-13 | 中国石油化工股份有限公司 | Intelligent monitor system and the scene monitoring method violating the regulations of operation field personnel violating the regulations |
| CN110619345A (en) * | 2019-07-22 | 2019-12-27 | 重庆交通大学 | Cable-stayed bridge monitoring data validity-oriented label reliability comprehensive verification method |
| CN111222189A (en) * | 2019-12-31 | 2020-06-02 | 湖南工程学院 | Efficient bridge structure health early warning control system and method |
| CN111610406A (en) * | 2020-04-24 | 2020-09-01 | 国网河北省电力有限公司电力科学研究院 | Grounding grid corrosion prediction method based on deep learning |
| CN114612473A (en) * | 2022-05-11 | 2022-06-10 | 深圳联和智慧科技有限公司 | Bridge inspection processing method and system based on unmanned aerial vehicle and cloud platform |
| CN115371728A (en) * | 2022-08-05 | 2022-11-22 | 东北林业大学 | Bridge health preserving process multipoint temperature and humidity prediction system based on deep learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2131258A1 (en) * | 2008-06-06 | 2009-12-09 | Inotera Memories, Inc. | A Method for Prognostic Maintenance in Semiconductor Manufacturing Equipments |
| CN102663264A (en) * | 2012-04-28 | 2012-09-12 | 北京工商大学 | Semi-supervised synergistic evaluation method for static parameter of health monitoring of bridge structure |
| CN103033387A (en) * | 2012-12-28 | 2013-04-10 | 重庆交通大学 | Method for bridge girder dangerous condition diagnosis based on data drive |
| CN106017960A (en) * | 2016-06-01 | 2016-10-12 | 清华大学合肥公共安全研究院 | MIS and GIS combination-based bridge safety monitoring system |
-
2016
- 2016-11-20 CN CN201611029162.3A patent/CN106529062B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2131258A1 (en) * | 2008-06-06 | 2009-12-09 | Inotera Memories, Inc. | A Method for Prognostic Maintenance in Semiconductor Manufacturing Equipments |
| CN102663264A (en) * | 2012-04-28 | 2012-09-12 | 北京工商大学 | Semi-supervised synergistic evaluation method for static parameter of health monitoring of bridge structure |
| CN103033387A (en) * | 2012-12-28 | 2013-04-10 | 重庆交通大学 | Method for bridge girder dangerous condition diagnosis based on data drive |
| CN106017960A (en) * | 2016-06-01 | 2016-10-12 | 清华大学合肥公共安全研究院 | MIS and GIS combination-based bridge safety monitoring system |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110119656A (en) * | 2018-02-07 | 2019-08-13 | 中国石油化工股份有限公司 | Intelligent monitor system and the scene monitoring method violating the regulations of operation field personnel violating the regulations |
| CN108511064A (en) * | 2018-02-11 | 2018-09-07 | 河南工程学院 | The system for automatically analyzing healthy data based on deep learning |
| 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 |
| CN109256773B (en) * | 2018-10-19 | 2021-01-26 | 东北大学 | Power system state estimation method of noise reduction self-coding and depth support vector machine |
| CN109256773A (en) * | 2018-10-19 | 2019-01-22 | 东北大学 | Power system state estimation method of the noise reduction from coding and depth support vector machines |
| CN110047145A (en) * | 2019-04-15 | 2019-07-23 | 山东师范大学 | Metaplasia simulation system and method based on deep learning and finite element modeling |
| CN110047145B (en) * | 2019-04-15 | 2023-05-16 | 山东师范大学 | Tissue deformation simulation system and method based on deep learning and finite element modeling |
| CN110619345A (en) * | 2019-07-22 | 2019-12-27 | 重庆交通大学 | Cable-stayed bridge monitoring data validity-oriented label reliability comprehensive verification method |
| CN111222189A (en) * | 2019-12-31 | 2020-06-02 | 湖南工程学院 | Efficient bridge structure health early warning control system and method |
| CN111610406A (en) * | 2020-04-24 | 2020-09-01 | 国网河北省电力有限公司电力科学研究院 | Grounding grid corrosion prediction method based on deep learning |
| CN114612473A (en) * | 2022-05-11 | 2022-06-10 | 深圳联和智慧科技有限公司 | Bridge inspection processing method and system based on unmanned aerial vehicle and cloud platform |
| CN114612473B (en) * | 2022-05-11 | 2022-08-16 | 深圳联和智慧科技有限公司 | Bridge inspection processing method and system based on unmanned aerial vehicle and cloud platform |
| CN115371728A (en) * | 2022-08-05 | 2022-11-22 | 东北林业大学 | Bridge health preserving process multipoint temperature and humidity prediction system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106529062B (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106529062A (en) | Bridge structure health diagnosis method based on deep learning | |
| CN112382064B (en) | Power Internet of things fault early warning method and system based on digital twin technology | |
| WO2021000556A1 (en) | Method and system for predicting remaining useful life of industrial equipment, and electronic device | |
| EP3447642A1 (en) | System and method for predicting application performance for large data size on big data cluster | |
| CN111209131A (en) | Method and system for determining fault of heterogeneous system based on machine learning | |
| CN107358347A (en) | Equipment cluster health state evaluation method based on industrial big data | |
| CN109115879B (en) | Structural damage identification method based on modal shape and convolutional neural network | |
| CN108593260A (en) | Lightguide cable link fault location and detection method and terminal device | |
| CN104777418B (en) | A kind of analog-circuit fault diagnosis method based on depth Boltzmann machine | |
| CN110213087B (en) | Complex system fault positioning method based on dynamic multilayer coupling network | |
| CN115514627B (en) | Fault root cause positioning method and device, electronic equipment and readable storage medium | |
| CN109558621B (en) | Structural damage identification method and system | |
| CN107632590A (en) | A kind of bottom event sort method based on priority | |
| CN107239798A (en) | A kind of feature selection approach of software-oriented defect number prediction | |
| Zhou et al. | A hybrid methodology for structural damage detection uniting FEM and 1D-CNNs: Demonstration on typical high-pile wharf | |
| CN113849581A (en) | Alarm information processing method, device, equipment and storage medium | |
| CN116720728A (en) | Risk assessment method, electronic device and storage medium | |
| CN115585783A (en) | Building settlement long-term monitoring system and method based on Internet of things | |
| CN115660513A (en) | Monitoring method and system based on aqueduct deformation of hydraulic engineering | |
| CN117034430B (en) | Gate health monitoring method, system and computer readable storage medium based on deep learning and digital twin | |
| CN113313304A (en) | Power grid accident abnormity analysis method and system based on big data decision tree | |
| CN103399978B (en) | Bridge flexural rigidity identification method | |
| CN113742814B (en) | Dam safety early warning method, dam safety early warning device, computer equipment and storage medium | |
| CN114679335A (en) | Network security risk assessment training and assessment method and equipment for power monitoring system | |
| CN109598063A (en) | A kind of data-link networking dynamic model driving method based on AADL |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191011 Termination date: 20201120 |