CN112100721A - Bridge structure modal identification method based on mobile crowd sensing and deep learning - Google Patents
Bridge structure modal identification method based on mobile crowd sensing and deep learning Download PDFInfo
- Publication number
- CN112100721A CN112100721A CN202010929614.3A CN202010929614A CN112100721A CN 112100721 A CN112100721 A CN 112100721A CN 202010929614 A CN202010929614 A CN 202010929614A CN 112100721 A CN112100721 A CN 112100721A
- Authority
- CN
- China
- Prior art keywords
- bridge
- vehicle
- information
- neural network
- vibration
- 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
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Civil Engineering (AREA)
- Architecture (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Traffic Control Systems (AREA)
Abstract
The bridge structure modal identification method based on mobile crowd sensing and deep learning comprises the following steps: firstly, acquiring vehicle vibration information by using a mobile phone mobile terminal on a vehicle, calculating modal information of a bridge by using a finite element method, and establishing a bridge vibration database; secondly, training a long-term and short-term memory artificial neural network, and outputting a modal frequency corresponding to the bridge; thirdly, deploying a monitoring system on the computer, and automatically transmitting data to the computer when the vehicle passes through the bridge to be detected; and finally, analyzing and processing the monitoring data by using the trained long-short term memory artificial neural network, and sorting the analysis result to obtain the frequency corresponding to each order mode of the bridge. According to the invention, additional sensor equipment is not required, and the problem that the monitoring equipment needs to be periodically detected and maintained in the traditional method is solved.
Description
Technical Field
The invention relates to a bridge structure modal identification method based on mobile crowd sensing and deep learning.
Background
In modern transportation network systems, bridges are an indispensable important infrastructure as a means to help humans cross mountains and rivers. During the service period, the bridge structure bears the random loads such as wind load, vehicle load, crowd load and the like for a long time, and is inevitably damaged, and cracks, corrosion and other diseases affecting the safety and stability of the structure are generated. After the diseases such as cracks and corrosion occur, the rigidity and the mode of the bridge structure can be changed. Therefore, the structural safety condition of the bridge can be analyzed by monitoring the vibration mode change of the bridge.
The traditional bridge modal analysis mainly comprises two steps of bridge vibration data acquisition and spectrum analysis, wherein the bridge vibration data can be obtained by two methods of directly measuring by installing an acceleration sensor on a bridge and indirectly obtaining by vehicle vibration by installing the acceleration sensor on a mobile detection vehicle:
the acceleration sensor is directly arranged on the bridge, so that direct measurement can be realized, the measurement result is accurate and reliable, and the vehicle passing is not influenced. However, the acceleration sensor and the acquisition instrument are expensive, the installation process is time-consuming and labor-consuming, and the problems of field power supply and the like are also faced in the actual engineering. Furthermore, permanently mounted acceleration sensors can only serve a single bridge. The acceleration sensor installed temporarily has the problem of low monitoring frequency, and is difficult to timely carry out vibration monitoring on a bridge with huge number.
The method for identifying the bridge mode by moving the vehicle needs a lane sealing treatment before the test, and eliminates the interference of other vehicles. In the test process, a detection vehicle provided with an acceleration sensor is driven to pass through a target bridge, and vibration data of the vehicle in the driving process on the bridge floor are recorded. Based on structural information (structure type, bridge length, bridge width and composition materials) of the bridge, vehicle structural information (vehicle axle number, axle weight, axle distance and suspension rigidity) and vehicle vibration data, vibration of the bridge structure is calculated by using the vibration data of the vehicle through an axle coupling vibration relation, and then the modal frequency of the bridge is obtained through modal analysis. This method is more efficient than mounting an acceleration sensor on the bridge to make measurements, but requires a specially tailored expensive test vehicle. The limited detection vehicles are difficult to test a huge number of bridges on a large scale. In addition, the lane-closing process can affect the vehicle passing during the detection, and is difficult to implement on the road section with heavy traffic.
At present, mobile devices such as smartphones and the like widely carried by people integrate various types of high-precision sensors such as a GPS (global positioning system), an acceleration sensor and the like, and can become a natural sensing node. And a large number of vehicles passing through the bridge can excite axle coupling vibration when passing through the bridge. The axle coupling relationship can be established to calculate the bridge vibration through the bridge structure information, the structure information of the vehicles passing on the bridge, the space-time distribution information of the vehicle positions on the bridge and the vehicle vibration information recorded by the mobile equipment. However, how to select a proper axle model, the mass of a related structure and the structural rigidity to establish axle coupling vibration still is a difficult problem which besets the academic and engineering circles. In addition, due to the fact that the bridge is continuously driven to get on or off, the coupling relation can change along with time, and the calculation difficulty is further increased.
Deep learning is a theoretical method which is rapidly developed in recent years, and can autonomously learn and update network structure parameters through a deep neural network, and extract data characteristics from massive raw data to perform data analysis. The method provides a powerful technical means for solving the problem of high nonlinearity. And the long-short term memory artificial neural network in the deep neural network can effectively process sequence data, and potential rules are mined from the original sequence data for data analysis.
Disclosure of Invention
Based on the analysis, the invention provides a bridge structure modal identification method based on mobile crowd sensing and deep learning, which overcomes the defects of the prior art.
The bridge structure modal identification method based on mobile crowd sensing and deep learning comprises the following steps: firstly, acquiring vehicle vibration information by using a mobile phone mobile terminal on a vehicle, calculating modal information of a bridge by using a finite element method, and establishing a bridge vibration database; secondly, training a long-term and short-term memory artificial neural network, and outputting a modal frequency corresponding to the bridge; thirdly, deploying a monitoring system on the computer, and automatically transmitting data to the computer when the vehicle passes through the bridge to be detected; and finally, analyzing and processing the monitoring data by using the trained long-short term memory artificial neural network, and sorting the analysis result to obtain the frequency corresponding to each order mode of the bridge.
The invention relates to a bridge structure modal identification method based on mobile crowd sensing and deep learning, which comprises the following specific implementation steps of:
a, collecting bridge information and vehicle data;
A1. fixing a mobile phone mobile terminal carrying a GPS and an acceleration sensor on the centroid position of the experimental vehicle, wherein the GPS sensor of the mobile phone mobile terminal can acquire the position information of the vehicle, the acceleration sensor can acquire vibration information, and simultaneously record the vehicle information such as the number of axles, the distance of axles, the weight of axles and the like of the experimental vehicle;
A2. selecting a bridge to be tested, recording bridge information, and marking a starting point and an end point of the bridge by using GPS equipment; when a vehicle passes through the bridge, acquiring vibration information of the vehicle to obtain vibration data of various vehicles when the vehicles run on the bridge;
A3. modeling and analyzing the bridge to be tested by using finite element analysis software, and calculating the modal frequency of the bridge;
A4. repeating the steps A2 and A3 on other bridges, and establishing a database containing bridge information, bridge modal frequency information, vehicle information and vehicle vibration data; with the increase of the trip times of the experimental vehicle, the database collects massive information of the type;
training a long-short term memory artificial neural network;
B1. and B, performing the steps of A, and mixing the database obtained in the step A according to the ratio of 0.9: dividing the ratio of 0.1 into a training set and a testing set randomly;
B2. and training the long-short term memory artificial neural network based on a training set in a B1 database, so that the long-short term memory artificial neural network can calculate the modal frequency of the bridge based on the bridge information, the vehicle information and the vehicle vibration data. When the neural network is trained, the input data are bridge information, vehicle information and vehicle vibration, and the output result is the modal frequency of the bridge. In the training process, the weight of the neural network is updated by using gradient descent, so that the neural network can automatically learn the relationship between bridge information, vehicle vibration and bridge modes, and the mode frequency of the bridge structure is fitted;
B3. carrying out performance test on the accuracy of the trained long-short term memory artificial neural network by using a test set, and checking the accuracy of the neural network;
monitoring bridge vibration;
C1. deploying a bridge vibration monitoring system in a computer, wherein the bridge vibration monitoring system comprises a data collection module, a neural network module and a structural modal analysis module;
C2. the method comprises the following steps that the position of a vehicle is automatically measured through a GPS of a mobile phone mobile terminal installed on an experimental vehicle, when the experimental vehicle is located between a starting point and an end point of a bridge to be measured, vehicle vibration information is obtained through an acceleration sensor and is sent to a computer;
c3.A1, enabling the experimental vehicle to pass through the bridge for multiple times to generate a large amount of monitoring data; the data of the vehicles are arranged by using a computer, and corresponding vehicle information and vibration data are recorded during each passing;
d, identifying the modal frequency of the bridge structure;
D1. importing the bridge vibration data obtained in the step C3 into a long-term and short-term memory artificial neural network, and calculating the modal frequency of the bridge;
D2. because mass vibration data can be generated by crowd sensing, the bridge modal frequency obtained by calculation of a neural network possibly has a distribution range, and processing results of data acquired on different mobile terminals are clustered by using a k-means clustering algorithm to obtain frequency distribution of each order of the bridge;
D3. and for the data clustered by the k-means to the same order frequency, obtaining a fused optimal value as the frequency of the bridge at the corresponding order by taking the minimum mean square error of the fused value as an optimization condition.
The bridge information in step a2 includes: structure type, bridge length, bridge width and constituent materials.
Compared with the prior art, the technology has the following advantages:
1. the sensor on the mobile terminal of the mobile phone is directly used, and sensor equipment does not need to be additionally installed, so that the construction cost is reduced.
2. Based on the crowd sensing technology, the larger the accumulated data volume of the bridge, the vehicle and the vehicle vibration is, the more stable the system working condition is, and the more accurate the result is.
3. The problem that the monitoring equipment needs to be regularly detected and maintained in the traditional method is solved.
4. The method gives play to the advantages of the long-term and short-term memory artificial neural network in processing the sequence data, and has the advantages of strong fitting capability, high robustness and accurate result.
5. The system can be fully automated after being built, and does not need manual participation.
Drawings
FIG. 1 is a schematic view of the data collection of the present invention.
FIG. 2 is a diagram of a long-term and short-term memory artificial neural network according to the present invention.
Fig. 3 is a flow chart of an implementation of the present invention.
Illustration of the drawings:
1-the starting point of the bridge to be detected;
2-the bridge termination point to be detected;
3-test vehicle;
4-computer;
5-long-short term memory artificial neural network module;
6-vehicle, bridge data and vibration information input by the neural network;
7-bridge frequency of neural network output.
Detailed Description
The following further describes the embodiments of the present invention with reference to the data collection diagram shown in fig. 1, the long-short term memory artificial neural network diagram shown in fig. 2, and the implementation flow chart shown in fig. 3. The method comprises the following specific steps:
a, collecting bridge information and vehicle data;
A1. fixing a mobile phone mobile terminal carrying a GPS and an acceleration sensor on the centroid position of the experimental vehicle, wherein the GPS sensor of the mobile phone mobile terminal can acquire the position information of the vehicle, the acceleration sensor can acquire vibration information, and simultaneously record the vehicle information such as the number of axles, the distance of axles, the weight of axles and the like of the experimental vehicle;
A2. selecting a bridge to be tested, recording bridge information, and marking a starting point 1 and an end point 2 of the bridge by using GPS equipment; when a vehicle passes through the bridge, acquiring vibration information of the vehicle to obtain vibration data of various vehicles when the vehicles run on the bridge;
A3. modeling and analyzing the bridge to be tested by using finite element analysis software, and calculating the modal frequency of the bridge;
A4. repeating the steps A2 and A3 on other bridges, and establishing a database containing bridge information, bridge modal frequency information, vehicle information and vehicle vibration data; with the increase of the trip times of the experimental vehicle, the database collects massive information of the type;
training a long-short term memory artificial neural network;
B1. and B, performing the steps of A, and mixing the database obtained in the step A according to the ratio of 0.9: dividing the ratio of 0.1 into a training set and a testing set randomly;
B2. and training the long-short term memory artificial neural network 5 based on the training set in the B1 database, so that the long-short term memory artificial neural network can calculate the modal frequency 7 of the bridge based on the bridge information, the vehicle information and the vehicle vibration data 6. When the neural network is trained, the input data are bridge information, vehicle information and vehicle vibration, and the output result is the modal frequency of the bridge. In the training process, the weight of the neural network is updated by using gradient descent, so that the neural network can automatically learn the relationship between bridge information, vehicle vibration and bridge modes, and the mode frequency of the bridge structure is fitted;
B3. carrying out performance test on the accuracy of the trained long-short term memory artificial neural network by using a test set, and checking the accuracy of the neural network;
monitoring bridge vibration;
C1. deploying a bridge vibration monitoring system in a computer, wherein the bridge vibration monitoring system comprises a data collection module, a neural network module and a structural modal analysis module;
C2. the method comprises the steps that the position of a vehicle is automatically measured through a GPS of a mobile phone mobile terminal installed on an experimental vehicle 3, when the experimental vehicle 3 is located between a starting point 1 and an end point 2 of a bridge to be measured, an acceleration sensor is used for obtaining vehicle vibration information, and the vehicle vibration information is sent to a computer 4;
c3.A1, enabling the experimental vehicle to pass through the bridge for multiple times to generate a large amount of monitoring data; the data of the vehicles are arranged by using a computer, and corresponding vehicle information and vibration data are recorded during each passing;
d, identifying the modal frequency of the bridge structure;
D1. importing the bridge vibration data obtained in the step C3 into a long-term and short-term memory artificial neural network, and calculating the modal frequency of the bridge;
D2. because mass vibration data can be generated by crowd sensing, the bridge modal frequency obtained by calculation of a neural network possibly has a distribution range, and processing results of data acquired on different mobile terminals are clustered by using a k-means clustering algorithm to obtain frequency distribution of each order of the bridge;
D3. and for the data clustered by the k-means to the same order frequency, obtaining a fused optimal value as the frequency of the bridge at the corresponding order by taking the minimum mean square error of the fused value as an optimization condition.
The embodiments described in this specification are merely illustrative of implementations of the inventive concept and the scope of the present invention should not be considered limited to the specific forms set forth in the embodiments but rather by the equivalents thereof as may occur to those skilled in the art upon consideration of the present inventive concept.
Claims (2)
1. The bridge structure modal identification method based on mobile crowd sensing and deep learning comprises the following steps:
a, collecting bridge information and vehicle data;
A1. fixing a mobile phone mobile terminal carrying a GPS and an acceleration sensor on the centroid position of the experimental vehicle, wherein the GPS sensor of the mobile phone mobile terminal can acquire the position information of the vehicle, the acceleration sensor can acquire vibration information, and simultaneously record the vehicle information such as the number of axles, the distance of axles, the weight of axles and the like of the experimental vehicle;
A2. selecting a bridge to be tested, recording bridge information, and marking a starting point and an end point of the bridge by using GPS equipment; when a vehicle passes through the bridge, acquiring vibration information of the vehicle to obtain vibration data of various vehicles when the vehicles run on the bridge;
A3. modeling and analyzing the bridge to be tested by using finite element analysis software, and calculating the modal frequency of the bridge;
A4. repeating the steps A2 and A3 on other bridges, and establishing a database containing bridge information, bridge modal frequency information, vehicle information and vehicle vibration data; with the increase of the trip times of the experimental vehicle, the database collects massive information of the type;
training a long-short term memory artificial neural network;
B1. and B, performing the steps of A, and mixing the database obtained in the step A according to the ratio of 0.9: dividing the ratio of 0.1 into a training set and a testing set randomly;
B2. and training the long-short term memory artificial neural network based on a training set in a B1 database, so that the long-short term memory artificial neural network can calculate the modal frequency of the bridge based on the bridge information, the vehicle information and the vehicle vibration data. When the neural network is trained, the input data are bridge information, vehicle information and vehicle vibration, and the output result is the modal frequency of the bridge. In the training process, the weight of the neural network is updated by using gradient descent, so that the neural network can automatically learn the relationship between bridge information, vehicle vibration and bridge modes, and the mode frequency of the bridge structure is fitted;
B3. carrying out performance test on the accuracy of the trained long-short term memory artificial neural network by using a test set, and checking the accuracy of the neural network;
monitoring bridge vibration;
C1. deploying a bridge vibration monitoring system in a computer, wherein the bridge vibration monitoring system comprises a data collection module, a neural network module and a structural modal analysis module;
C2. the method comprises the following steps that the position of a vehicle is automatically measured through a GPS of a mobile phone mobile terminal installed on an experimental vehicle, when the experimental vehicle is located between a starting point and an end point of a bridge to be measured, vehicle vibration information is obtained through an acceleration sensor and is sent to a computer;
c3.A1, enabling the experimental vehicle to pass through the bridge for multiple times to generate a large amount of monitoring data; the data of the vehicles are arranged by using a computer, and corresponding vehicle information and vibration data are recorded during each passing;
d, identifying the modal frequency of the bridge structure;
D1. importing the bridge vibration data obtained in the step C3 into a long-term and short-term memory artificial neural network, and calculating the modal frequency of the bridge;
D2. because mass vibration data can be generated by crowd sensing, the bridge modal frequency obtained by calculation of a neural network possibly has a distribution range, and processing results of data acquired on different mobile terminals are clustered by using a k-means clustering algorithm to obtain frequency distribution of each order of the bridge;
D3. and for the data clustered by the k-means to the same order frequency, obtaining a fused optimal value as the frequency of the bridge at the corresponding order by taking the minimum mean square error of the fused value as an optimization condition.
2. The bridge structure modal identification method based on mobile crowd sensing and deep learning of claim 1, wherein: the bridge information in step a2 includes: structure type, bridge length, bridge width and constituent materials.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010929614.3A CN112100721B (en) | 2020-09-07 | 2020-09-07 | Bridge structure modal identification method based on mobile crowd sensing and deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010929614.3A CN112100721B (en) | 2020-09-07 | 2020-09-07 | Bridge structure modal identification method based on mobile crowd sensing and deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112100721A true CN112100721A (en) | 2020-12-18 |
| CN112100721B CN112100721B (en) | 2022-08-26 |
Family
ID=73750797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010929614.3A Active CN112100721B (en) | 2020-09-07 | 2020-09-07 | Bridge structure modal identification method based on mobile crowd sensing and deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112100721B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114323512A (en) * | 2021-12-17 | 2022-04-12 | 中铁桥隧技术有限公司 | Heavy-load vehicle identification method and system |
| CN114444366A (en) * | 2022-04-08 | 2022-05-06 | 深圳市城市交通规划设计研究中心股份有限公司 | Bridge digital twin model updating method and device based on finite element simulation |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100242609A1 (en) * | 2009-03-26 | 2010-09-30 | Wei-Feng Lee | Bridge monitoring and safety evaluation method using a vibration technique |
| CN108376184A (en) * | 2018-01-05 | 2018-08-07 | 深圳市市政设计研究院有限公司 | A kind of method and system of bridge health monitoring |
| CN111144039A (en) * | 2019-12-04 | 2020-05-12 | 东南大学 | Train dynamic weighing system and weighing method based on deep learning |
| CN111353238A (en) * | 2020-03-25 | 2020-06-30 | 山东建筑大学 | Pier scouring depth identification method based on vehicle sensing |
| WO2020168589A1 (en) * | 2019-02-19 | 2020-08-27 | 大连理工大学 | Method for automatically detecting free vibration response of high-speed rail bridge to identify mode |
-
2020
- 2020-09-07 CN CN202010929614.3A patent/CN112100721B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100242609A1 (en) * | 2009-03-26 | 2010-09-30 | Wei-Feng Lee | Bridge monitoring and safety evaluation method using a vibration technique |
| CN108376184A (en) * | 2018-01-05 | 2018-08-07 | 深圳市市政设计研究院有限公司 | A kind of method and system of bridge health monitoring |
| WO2020168589A1 (en) * | 2019-02-19 | 2020-08-27 | 大连理工大学 | Method for automatically detecting free vibration response of high-speed rail bridge to identify mode |
| CN111144039A (en) * | 2019-12-04 | 2020-05-12 | 东南大学 | Train dynamic weighing system and weighing method based on deep learning |
| CN111353238A (en) * | 2020-03-25 | 2020-06-30 | 山东建筑大学 | Pier scouring depth identification method based on vehicle sensing |
Non-Patent Citations (4)
| Title |
|---|
| MUSTAPHA,S.ETC.: "Crowdsensing Framework for", 《AUTOMATION IN CONSTRUCTION》 * |
| 李小珍等: "公路桥梁与车辆耦合振动研究现状与发展趋势", 《工程力学》 * |
| 熊红霞: "桥梁结构模态参数辨识与损伤识别方法研究", 《中国优秀博士学位论文全文数据库工程科技Ⅱ辑》 * |
| 黄方林等: "大型桥梁健康监测研究进展", 《中国铁道科学》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114323512A (en) * | 2021-12-17 | 2022-04-12 | 中铁桥隧技术有限公司 | Heavy-load vehicle identification method and system |
| CN114323512B (en) * | 2021-12-17 | 2023-06-16 | 中铁桥隧技术有限公司 | Heavy-load vehicle identification method and system |
| CN114444366A (en) * | 2022-04-08 | 2022-05-06 | 深圳市城市交通规划设计研究中心股份有限公司 | Bridge digital twin model updating method and device based on finite element simulation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112100721B (en) | 2022-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110346517B (en) | Smart city industrial atmosphere pollution visual early warning method and system | |
| CN110704801B (en) | Bridge cluster structure operation safety intelligent monitoring and rapid detection complete method | |
| Forslöf et al. | Roadroid: Continuous road condition monitoring with smart phones | |
| CN112100721B (en) | Bridge structure modal identification method based on mobile crowd sensing and deep learning | |
| Lynch et al. | Validation of a large-scale wireless structural monitoring system on the Geumdang Bridge | |
| CN109753745B (en) | Road detection and evaluation method based on BIM and Internet of things technology | |
| CN111833604B (en) | Vehicle load state identification method and device based on driving behavior feature extraction | |
| CN104164829A (en) | Pavement smoothness detection method based on mobile terminal and intelligent pavement information real-time monitoring system | |
| CN108254495B (en) | Tunnel motor vehicle pollutant monitoring method and system | |
| CN109615860A (en) | A kind of signalized intersections method for estimating state based on nonparametric Bayes frame | |
| Rolfes et al. | Integral SHM-system for offshore wind turbines using smart wireless sensors | |
| CN112729370A (en) | Bridge dynamic strain monitoring system calibration method | |
| CN110990505A (en) | Loran-C ASF correction method based on neural network | |
| Alamdari et al. | Non-contact structural health monitoring of a cable-stayed bridge: Case study | |
| Sousa et al. | Assessment of traffic load events and structural effects on road bridges based on strain measurements | |
| CN113223294B (en) | Expressway automobile balance period checking method based on social vehicle big data | |
| Cetin et al. | Key factors affecting the accuracy of reidentification of trucks over long distances based on axle measurement data | |
| CN113053106B (en) | Traffic state estimation method and device based on multi-sensor information fusion | |
| CN107657147B (en) | Coil data-based method for calculating exhaust pollutant emission of motor vehicle | |
| Zhan et al. | Data accuracy oriented method for deploying fixed and mobile traffic sensors along a freeway | |
| CN112199872B (en) | Tunnel modal identification method | |
| Riyanti et al. | An Automatic Load Detector Design to Determine the Strength of Pedestrian Bridges Using Load Cell Sensor Based on Arduino | |
| CN113091708A (en) | Road subsection gradient estimation method and system based on multi-sample GPS quality control data | |
| JP2018036076A (en) | Facility management device and method for facility management | |
| CN111368782A (en) | Training method of coal fire area identification model, and coal fire area identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |