WO2022056677A1 - 监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品 - Google Patents

监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品 Download PDF

Info

Publication number
WO2022056677A1
WO2022056677A1 PCT/CN2020/115343 CN2020115343W WO2022056677A1 WO 2022056677 A1 WO2022056677 A1 WO 2022056677A1 CN 2020115343 W CN2020115343 W CN 2020115343W WO 2022056677 A1 WO2022056677 A1 WO 2022056677A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
bridge
real
subsystem
time
Prior art date
Application number
PCT/CN2020/115343
Other languages
English (en)
French (fr)
Inventor
孙天瑞
周晓舟
曹佃松
白新
亓欣波
Original Assignee
西门子股份公司
西门子（中国）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 西门子股份公司, 西门子（中国）有限公司 filed Critical 西门子股份公司
Priority to PCT/CN2020/115343 priority Critical patent/WO2022056677A1/zh
Publication of WO2022056677A1 publication Critical patent/WO2022056677A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management

Definitions

  • the embodiments of the present application relate to the technical field of industrial monitoring, and in particular, to a monitoring, collection, and analysis system and its method, device, storage medium, program, and program product.
  • the embodiments of the present invention provide a monitoring, collection, and analysis system and method, device, storage medium, program, and program product thereof, so as to at least partially solve the above problem.
  • a monitoring method for monitoring the health of a bridge.
  • the monitoring method includes: collecting real-time bridge response data, and collecting real-time bridge traffic data; generating predicted bridge response data according to the real-time bridge traffic data; comparing and analyzing the real-time bridge response data and the predicted bridge response data to obtain the abnormality indication data of the bridge health; and present the abnormality indication data of the bridge health.
  • the real-time bridge response data used in the comparative analysis comes from the data acquisition subsystem, and the predicted bridge response data used is obtained by predicting the real-time bridge traffic flow data by the prediction subsystem, the real-time bridge response data and the predicted bridge response data can be The correlation between the real-time bridge response data and the real-time bridge traffic data is effectively reflected, and the abnormal indicator data of bridge health is obtained by comparing and analyzing the above two, which improves the accuracy of bridge health monitoring.
  • the collecting real-time bridge response data includes: reading real-time sensing data of a plurality of sensors arranged on the bridge, and performing noise reduction processing on the sensing data to obtain the described real-time bridge response data.
  • the multiple sensors arranged on the bridge have the characteristics of low cost, thus reducing the deployment cost of the data acquisition subsystem.
  • noise reduction processing is performed on the sensing data to obtain real-time bridge response data, which improves the accuracy of data collection.
  • the real-time bridge traffic flow data includes vehicle observation data of multiple cameras disposed on the bridge.
  • the collecting real-time bridge traffic flow data includes: collecting the vehicle observation data through a visual recognition module.
  • the visual recognition module reads the vehicle observation data from the plurality of cameras.
  • the multiple cameras set on the bridge have the characteristics of low cost, so the deployment cost of the data acquisition subsystem is reduced.
  • the visual recognition module can be implemented by software, thus improving the configuration flexibility of the data acquisition subsystem, which is more conducive to the update of functions, and further reduces the deployment cost of the data acquisition subsystem due to the low deployment cost of the software.
  • the real-time bridge traffic flow data further includes vehicle weight data
  • the vehicle observation data includes vehicle management data
  • the collecting real-time bridge traffic flow data further includes: using the vehicle management data to access a vehicle management database to obtain the vehicle weight data.
  • the visual recognition module can generate vehicle weight data based on the vehicle observation data, no special vehicle weight measuring instrument is required, thereby further reducing the deployment cost of the data acquisition subsystem.
  • the vehicle weight data obtained by using the vehicle management data to access the vehicle management database has high accuracy.
  • generating the predicted bridge response data according to the real-time bridge traffic data includes: obtaining the predicted bridge by inputting the real-time bridge traffic data into a pre-trained simulation model response data. The method further includes training the real-time bridge response data and the real-time bridge traffic flow data collected during training of the simulation model as a model calibration sample set to update the simulation model.
  • the simulation model Since the simulation model has not been trained with the real-time bridge response data and real-time bridge traffic data collected during the training of the simulation model, and the above data is real-time and accurate for the simulation model, the above data is used as the model calibration sample set for model calibration. Updated to improve the prediction accuracy of the simulation model.
  • the method further includes: performing training based on a sample set of simulation results, and updating the simulation model.
  • the simulation result sample set is obtained by inputting the real-time bridge traffic flow data, the conventional bridge traffic flow sample set and bridge information into a three-dimensional simulation model.
  • the 3D simulation model can generate accurate samples, and the 3D simulation model itself can be updated or improved through training, the flexibility or accuracy of the simulation result samples is improved.
  • the bridge health abnormality indication data includes bridge structure fault indication data and non-bridge structure fault indication data.
  • the obtaining of the abnormality indication data of bridge health by comparing and analyzing the real-time bridge response data and the predicted bridge response data includes: obtaining an initial bridge structural fault by analyzing the real-time bridge response data and the predicted bridge response data Indication data and non-bridge structure fault indication data; and by analyzing the initial bridge structure fault indication data and the acquired external data, the bridge structure fault indication data is obtained; the bridge health abnormality indication is reported to the presentation subsystem data.
  • the bridge structure fault indication data is obtained by analyzing the initial bridge structure fault indication data and the acquired external data, the reliability of the bridge structure fault indication data is improved.
  • the non-bridge structure fault indication data is obtained, which improves the data processing efficiency of the non-bridge structure fault indication data.
  • the non-bridge structure fault indication data includes sensor fault indication data and vehicle overweight indication data.
  • the sensor fault indication data and the vehicle overweight indication data can effectively indicate non-bridge structural faults, the efficiency of troubleshooting non-bridge structural faults can be improved.
  • a collection method is provided, which is applied to a data collection subsystem of a monitoring system, the monitoring system is used for monitoring bridge health, and the monitoring system further includes a prediction subsystem and an analysis sub-system system, the method comprising: collecting real-time bridge response data and real-time bridge traffic data; sending the real-time bridge traffic data to the forecasting subsystem, and sending the real-time bridge response data to the analysis subsystem, so that The analysis subsystem compares, analyzes and predicts bridge response data and the real-time bridge traffic flow data, and obtains bridge health abnormality indication data.
  • the predicted bridge response data is generated by the prediction subsystem according to the real-time bridge traffic flow data.
  • the data acquisition subsystem, prediction subsystem, analysis subsystem and presentation subsystem included in the monitoring system are universal, it can overcome the geographical limitation and perform unified monitoring on most bridges, saving the cost of bridge monitoring.
  • the real-time bridge response data used in the comparative analysis comes from the data acquisition subsystem, and the predicted bridge response data used is obtained by predicting the real-time bridge traffic flow data by the prediction subsystem, the real-time bridge response data and the predicted bridge response The data can effectively reflect the relationship between the real-time bridge response data and the real-time bridge traffic flow data. By comparing and analyzing the above two, the abnormal indicator data of bridge health is obtained, which improves the accuracy of bridge health monitoring.
  • an analysis method is provided, which is applied to an analysis subsystem of a monitoring system, the monitoring system is used for monitoring bridge health, and the monitoring system further includes a data acquisition subsystem and a presentation subsystem system.
  • the method includes obtaining real-time bridge response data collected by the data collection subsystem, and obtaining the predicted bridge response data from the prediction subsystem.
  • the predicted bridge response data is generated based on the real-time bridge traffic flow data obtained from the data acquisition subsystem; by comparing and analyzing the real-time bridge response data and the predicted bridge response data, bridge health abnormality indication data is obtained;
  • the subsystem reports the abnormality indication data of the bridge health degree to present the abnormality indication data of the bridge health degree.
  • the data acquisition subsystem, prediction subsystem, analysis subsystem and presentation subsystem included in the monitoring system are universal, they can overcome the limitation of geographical location and perform unified monitoring on most bridges, saving the cost of bridge monitoring.
  • the real-time bridge response data used in the comparative analysis comes from the data acquisition subsystem, and the predicted bridge response data used is obtained by predicting the real-time bridge traffic flow data by the prediction subsystem, the real-time bridge response data and the predicted bridge response The data can effectively reflect the relationship between the real-time bridge response data and the real-time bridge traffic flow data.
  • the abnormal bridge health indicator data is obtained, which improves the accuracy of bridge health monitoring.
  • a data acquisition subsystem for a monitoring system is provided, the monitoring system is used for monitoring bridge health, the monitoring system further includes a prediction subsystem and an analysis subsystem, so
  • the data acquisition subsystem includes: one or more processors, a communication interface, a memory and a communication bus, and one or more programs.
  • One or more processors, a communication interface, and a memory communicate with each other through a communication bus, and one or more programs are stored in the memory and configured to be executed by the one or more processors to perform the second aspect. method described.
  • an analysis subsystem for a monitoring system the monitoring system is used for monitoring bridge health, the monitoring system further includes a data acquisition subsystem and a presentation subsystem, so
  • the analysis subsystem includes: one or more processors, a communication interface, a memory and a communication bus, and one or more programs.
  • One or more processors, a communication interface, and a memory communicate with each other through a communication bus, and one or more programs are stored in the memory and configured to be executed by the one or more processors to perform the third aspect. method described.
  • a monitoring system for monitoring bridge health comprising: a data acquisition subsystem for: collecting real-time bridge response data and real-time bridge traffic flow data; a prediction subsystem for: acquiring the real-time bridge traffic data from the data acquisition subsystem, and generating predicted bridge response data according to the real-time bridge traffic data; an analysis subsystem for: from the data The acquisition subsystem obtains the real-time bridge response data, and obtains the predicted bridge response data from the prediction subsystem; and obtains a bridge health abnormality indication by comparing and analyzing the real-time bridge response data and the predicted bridge response data data; and a presentation subsystem for: acquiring the bridge health abnormality indication data from the analysis subsystem, and presenting the bridge health abnormality indication data.
  • a storage medium is provided, and the storage medium includes a stored program.
  • the device including the storage medium is controlled to execute the method of the fourth aspect or the fifth aspect.
  • a computer program comprising computer-executable instructions which, when executed, cause at least one processor to perform the method according to the fourth or fifth aspect .
  • a computer program product tangibly stored on a computer-readable medium and comprising computer-readable instructions, the computer-executable instructions when executed At least one processor is caused to perform the method according to the fourth or fifth aspect.
  • the data acquisition subsystem, prediction subsystem, analysis subsystem and presentation subsystem included in the monitoring system are universal, they can overcome the limitation of geographical location and perform unified monitoring on most bridges, saving the cost of bridge monitoring.
  • the real-time bridge response data used in the comparative analysis comes from the data acquisition subsystem, and the predicted bridge response data used is obtained by predicting the real-time bridge traffic flow data by the prediction subsystem, the real-time bridge response data and the predicted bridge response The data can effectively reflect the relationship between the real-time bridge response data and the real-time bridge traffic flow data.
  • the abnormal bridge health indicator data is obtained, which improves the accuracy of bridge health monitoring.
  • FIG. 1A is a schematic block diagram of a monitoring system for monitoring bridge health according to an embodiment of the present invention
  • FIG. 1B is a schematic flowchart of a monitoring method for monitoring bridge health according to an embodiment of the present invention
  • FIG. 2 is a schematic block diagram of a monitoring system for monitoring bridge health according to another embodiment of the present invention.
  • FIG. 3 is a schematic block diagram of a data acquisition subsystem according to another embodiment of the present invention.
  • FIG. 4 is a schematic block diagram of a prediction subsystem according to another embodiment of the present invention.
  • FIG. 5 is a schematic block diagram of an analysis subsystem according to another embodiment of the present invention.
  • FIG. 6 is a schematic block diagram of a data acquisition subsystem according to another embodiment of the present invention.
  • FIG. 7 is a schematic block diagram of an analysis subsystem according to another embodiment of the present invention.
  • FIG. 8 is a schematic flowchart of a monitoring method for a data acquisition subsystem according to another embodiment of the present invention.
  • FIG. 9 is a schematic flowchart of a monitoring method for an analysis subsystem according to another embodiment of the present invention.
  • FIG. 10 is a schematic structural diagram of an electronic device according to another embodiment of the present invention.
  • FIG. 11 is a schematic structural diagram of an electronic device according to another embodiment of the present invention.
  • S110 Collect real-time bridge response data, and collect real-time bridge traffic flow data
  • S120 Generate predicted bridge response data according to real-time bridge traffic data
  • S130 Obtain bridge health abnormality indication data by comparing and analyzing real-time bridge response data and predicted bridge response data;
  • S140 Present the abnormal indication data of bridge health
  • 2000 Monitoring System; 2100: Data Acquisition Subsystem; 2200: Digital Twin Subsystem; 2210: Fast Simulation Module; 2300: Decision Subsystem; 2310: Anomaly Detection Module; 2320: Fault Diagnosis Module; 2400: Management Subsystem;
  • 3100 Bridge sensor; 3200: Weight acquisition system; 3300: Bridge camera; 3400: Visual recognition module; 3500: Noise removal module; 3600: Vehicle management database; 3700: Real-time bridge response data; 3800: Real-time bridge traffic flow data;
  • 4100 Bridge response data
  • 4200 Bridge traffic flow data
  • 4300 Conventional bridge traffic flow data set
  • 4400 Bridge information
  • 4500 Model calibration data set
  • 4600 Full 3D simulation model
  • 4700 Simulation result data set
  • 4800 fast simulation model
  • 5100 Real-time bridge response data
  • 5200 Predicted bridge response data
  • 5300 Anomaly detection module
  • 5400 Sensor fault indication data
  • 5500 Overweight vehicle indication data
  • 5600 Initial bridge structural fault indication data
  • 5700 Fault diagnosis module
  • 5800 external data;
  • 6000 data acquisition subsystem
  • 6100 acquisition module
  • 6200 sending module
  • S810 Collect real-time bridge response data and real-time bridge traffic flow data
  • S820 Send real-time bridge traffic flow data to the prediction subsystem, and send real-time bridge response data to the analysis subsystem, so that the analysis subsystem can compare and analyze the predicted bridge response data and the real-time bridge traffic flow data, and obtain bridge health abnormality indication data.
  • the predicted bridge response data is generated by the prediction subsystem according to the real-time bridge traffic data;
  • S910 Obtain the collected real-time bridge response data from the data collection subsystem, and obtain predicted bridge response data from the prediction subsystem.
  • the predicted bridge response data is generated based on real-time bridge traffic flow data obtained from the data acquisition subsystem;
  • S930 Report the abnormality indication data of the bridge health to the presentation subsystem, so as to present the abnormality indication data of the bridge health;
  • 1010 processor; 1020: communication interface; 1030: memory; 1040: communication bus;
  • 1110 processor; 1120: communication interface; 1130: memory; 1140: communication bus.
  • FIG. 1 is a schematic block diagram of a monitoring system for monitoring the health of a bridge according to an embodiment of the present invention. As shown, monitoring system 1000 is used to monitor bridge health. Monitoring system 1000 includes data acquisition subsystem 1100 , prediction subsystem 1200 , analysis subsystem 1300 , and presentation subsystem 1400 .
  • the data acquisition subsystem 1100 may be disposed at one or more target monitoring bridges, for example, may be disposed on the main beams, bridge towers, stay cables, railings or piers, etc. of the bridges.
  • the data collection subsystem 1100 is capable of collecting real-time bridge response data and real-time bridge traffic flow data. The above data can be realized by the real-time bridge response data acquisition module and the real-time bridge traffic flow data acquisition module respectively.
  • bridge response data may be bridge structural response data or the like.
  • Bridge structural response data can be acquired by multiple sensors placed on the bridge section, for example, when vehicles pass through various sections of the bridge, it will cause changes in the bridge structure. Each sensor can sequentially acquire bridge structural response data.
  • the bridge response data generated when the vehicle passes may be collected by a plurality of sensors (multiple monitoring sensors) disposed at the bridge, for example, the bridge response data may be peak data of the bridge structure response data.
  • real-time bridge traffic flow data can be obtained through vehicle monitoring video through a traffic monitoring device (ie, for example, a camera) disposed above the bridge deck, and the traffic monitoring device can capture video images of vehicles passing through the bridge deck.
  • a traffic monitoring device ie, for example, a camera
  • the senor may be a sensor such as a dynamic strain sensor for acquiring the longitudinal dynamic strain of the bridge generated when the vehicle passes.
  • the sensors may also be a number of other types of monitoring sensors for collecting other types of bridge structure response data generated by vehicles passing by.
  • Other types of monitoring sensors may be at least one of acceleration sensors, displacement sensors, vibration sensors, tilt sensors.
  • the forecasting subsystem 1200 may be disposed at one or more target monitoring bridges, or may be disposed separately from one or more target monitoring bridges.
  • the prediction subsystem 1200 obtains real-time bridge traffic data from the data acquisition subsystem, and generates predicted bridge response data according to the real-time bridge traffic data.
  • the prediction subsystem may correspond to multiple target monitoring bridges, and is configured to receive real-time bridge traffic flow data of the multiple target monitoring bridges, and generate predicted bridge response data of the multiple target monitoring bridges according to the real-time bridge traffic flow data.
  • the prediction subsystem can be implemented using digital twin technology, and the bridge digital twin model can be applied to the physical environment of the bridge, for example, to simulate the main girder, tower, cable, railing or pier of the bridge.
  • the analysis subsystem 1300 may be disposed at one or more target monitoring bridges, or may be disposed separately from one or more target monitoring bridges.
  • the analysis subsystem can be implemented as a decision-making subsystem, including an anomaly detection module and a fault diagnosis module.
  • the analysis subsystem and the prediction subsystem may be provided in a unified facility, and may be arranged in the same server or in a different server.
  • the analysis subsystem 1300 obtains real-time bridge response data from the data acquisition subsystem, and obtains predicted bridge response data from the prediction subsystem; and obtains bridge health abnormality indication data by comparing and analyzing the real-time bridge response data and the predicted bridge response data.
  • real-time bridge response data for one or more target monitored bridges can be obtained from the data acquisition subsystem.
  • predicted bridge response data for one or more target monitored bridges may be obtained from the prediction subsystem.
  • the presentation subsystem 1400 may be provided at the bridge management agency, and may be implemented as a management subsystem.
  • the presentation subsystem 1400 obtains bridge health abnormality indication data from the analysis subsystem, and presents the bridge health abnormality indication data.
  • the presentation subsystem may also present the location of one or more target monitoring bridges.
  • the data acquisition subsystem, forecasting subsystem, analysis subsystem and presentation subsystem included in the monitoring system are universal, they can overcome the limitation of geographical location and carry out unified monitoring of most bridges.
  • the real-time bridge response data used in the comparative analysis comes from the data acquisition subsystem, and the predicted bridge response data used is obtained by predicting the real-time bridge traffic flow data by the prediction subsystem, the real-time bridge response data and the predicted bridge response
  • the data can effectively reflect the relationship between the real-time bridge response data and the real-time bridge traffic flow data, so as to compare and analyze the above two to obtain the abnormal indicator data of bridge health, which improves the accuracy of bridge health monitoring.
  • the monitoring system can be implemented as different communication interaction modes of cloud computing and edge computing.
  • a prediction subsystem may correspond to a bridge or bridges (eg, all bridges in an area), and make predictions for real-time bridge traffic data for one or more bridges, implemented to correspond to the bridge or the area edge computing.
  • the analysis subsystem can be implemented as a cloud server corresponding to the prediction subsystem as the edge computing side.
  • the data collection subsystem may correspond to a bridge or bridges (eg, all bridges in an area) and collect real-time bridge traffic data and real-time bridge response data for one or more bridges , implemented as the edge computing end corresponding to the bridge or the area.
  • both the analysis subsystem and the prediction subsystem may be implemented as a first backend cloud server and a second backend cloud server corresponding to the data collection subsystem serving as the edge computing end.
  • the analysis subsystem and the prediction subsystem can be distributed and implemented as a back-end cloud server and a middle-end cloud server corresponding to the data acquisition subsystem serving as the edge computing end.
  • the presentation subsystem can be set in a fixed physical location, or can be deployed as an application in a mobile terminal such as a mobile phone, for example, in a mobile terminal used by bridge monitoring personnel or maintenance personnel.
  • An electronic map display is configured in the mobile terminal. On the electronic map, the distribution information of bridges (for example, the position of the bridge), the distribution information of the prediction subsystem (for example, the position of the prediction subsystem), the distribution information of the analysis subsystem (for example, the position of the distribution subsystem) can be displayed. )Wait.
  • FIG. 1B is a schematic flowchart of a monitoring method for monitoring the health of a bridge according to an embodiment of the present invention.
  • the monitoring method of Fig. 1B is used to monitor bridge health.
  • the monitoring method includes:
  • S110 Collect real-time bridge response data, and collect real-time bridge traffic flow data.
  • S120 Generate predicted bridge response data according to the real-time bridge traffic flow data.
  • S130 Obtain bridge health abnormality indication data by comparing and analyzing real-time bridge response data and predicted bridge response data.
  • S140 Present bridge health abnormality indication data.
  • the real-time bridge response data used in the comparative analysis comes from the data acquisition subsystem, and the predicted bridge response data used is obtained by predicting the real-time bridge traffic flow data by the prediction subsystem, the real-time bridge response data and the predicted bridge response data can be The correlation between the real-time bridge response data and the real-time bridge traffic data is effectively reflected, and the abnormal indicator data of bridge health is obtained by comparing and analyzing the above two, which improves the accuracy of bridge health monitoring.
  • collecting real-time bridge response data includes: reading real-time sensing data of multiple sensors disposed on the bridge, and performing noise reduction processing on the sensing data to obtain real-time bridge response data.
  • the multiple sensors arranged on the bridge have the characteristics of low cost, thus reducing the deployment cost of the data acquisition subsystem.
  • noise reduction processing is performed on the sensing data to obtain real-time bridge response data, which improves the accuracy of data collection.
  • the real-time bridge traffic flow data includes vehicle observation data of multiple cameras disposed on the bridge.
  • Collect real-time bridge traffic data including: collecting vehicle observation data through the visual recognition module.
  • the visual recognition module reads vehicle observation data from multiple cameras.
  • the multiple cameras set on the bridge have the characteristics of low cost, so the deployment cost of the data acquisition subsystem is reduced.
  • the visual recognition module can be implemented by software, thus improving the configuration flexibility of the data acquisition subsystem, which is more conducive to the update of functions, and further reduces the deployment cost of the data acquisition subsystem due to the low deployment cost of the software.
  • the real-time bridge traffic flow data further includes vehicle weight data
  • the vehicle observation data includes vehicle management data.
  • the collection of real-time bridge traffic flow data also includes: using the vehicle management data to access the vehicle management database to obtain vehicle weight data. Since the visual recognition module can generate vehicle weight data based on vehicle observation data, there is no need for special vehicle weight measurement instruments, thereby further reducing the deployment cost of the data acquisition subsystem. In addition, since the reliability of the data in the vehicle management database is high, the vehicle weight data obtained by using the vehicle management data to access the vehicle management database has high accuracy.
  • generating predicted bridge response data according to real-time bridge traffic flow data includes: obtaining predicted bridge response data by inputting real-time bridge traffic flow data into a pre-trained simulation model.
  • the method further includes: training the real-time bridge response data and real-time bridge traffic flow data collected during the training of the simulation model as a model calibration sample set to update the simulation model. Since the simulation model has not been trained with the real-time bridge response data and real-time bridge traffic data collected during the training of the simulation model, and the above data is real-time and accurate for the simulation model, the above data is used as the model calibration sample set for model calibration. Updated to improve the prediction accuracy of the simulation model.
  • the method further includes: performing training based on the simulation result sample set, and updating the simulation model.
  • the simulation result sample set is obtained by inputting real-time bridge traffic flow data, conventional bridge traffic flow sample set and bridge information into the 3D simulation model. Since the 3D simulation model can generate accurate samples, and the 3D simulation model itself can be updated or improved through training, the flexibility or accuracy of the simulation result samples is improved.
  • the bridge health abnormality indication data includes bridge structure fault indication data and non-bridge structure fault indication data.
  • the abnormal bridge health indicator data is obtained, including: by analyzing the real-time bridge response data and the predicted bridge response data, the initial bridge structure fault indication data and the non-bridge structure fault indication data are obtained; And by analyzing the initial bridge structure fault indication data and the acquired external data, the bridge structure fault indication data is obtained; the bridge health abnormal indication data is reported to the presentation subsystem. Because the bridge structure fault indication data is obtained by analyzing the initial bridge structure fault indication data and the acquired external data, the reliability of the bridge structure fault indication data is improved. In addition, by analyzing the real-time bridge response data and the predicted bridge response data, the non-bridge structure fault indication data is obtained, which improves the data processing efficiency of the non-bridge structure fault indication data.
  • the non-bridge structure fault indication data includes sensor fault indication data and vehicle overweight indication data. Since the sensor fault indication data and the vehicle overweight indication data can effectively indicate non-bridge structural faults, the efficiency of troubleshooting non-bridge structural faults can be improved.
  • FIG. 2 is a schematic block diagram of a monitoring system for monitoring the health of a bridge according to another embodiment of the present invention.
  • the monitoring system 2000 includes a data acquisition subsystem 2100 , a digital twin subsystem 2200 , a decision-making subsystem 2300 and a management subsystem 2400 .
  • the digital twin subsystem 2200 may include a fast simulation module 2210 .
  • Decision making subsystem 2300 may include anomaly detection module 2310 and fault diagnosis module 2320 .
  • the digital twin subsystem 2200 receives the real-time bridge traffic flow data reported by the data acquisition subsystem 2100 .
  • the abnormality detection module 2310 receives the real-time bridge response data reported by the data acquisition subsystem 2100, and receives the predicted bridge response data generated according to the real-time bridge traffic flow data and sent by the digital twin subsystem 2200.
  • the abnormality detection module 2310 generates fault type indication data based on the above data, and sends at least part of the fault type indication data to the fault diagnosis module 2320 for processing such as analysis, judgment or confirmation.
  • the fault diagnosis module 2320 presents the above processing results to the management subsystem 2400 .
  • the data acquisition subsystem is used for: reading real-time sensing data of multiple sensors disposed on the bridge, and performing noise reduction processing on the sensing data to obtain real-time bridge response data.
  • the multiple sensors arranged on the bridge have the characteristics of low cost, thus reducing the deployment cost of the data acquisition subsystem.
  • noise reduction processing is performed on the sensing data to obtain real-time bridge response data, which improves the accuracy of data collection.
  • the plurality of sensors disposed on the bridge may include at least one of a displacement sensor, a vibration sensor, and a tilt sensor.
  • the real-time bridge traffic flow data includes vehicle observation data of multiple cameras disposed on the bridge.
  • the data acquisition subsystem is used to collect vehicle observation data through the visual recognition module.
  • the visual recognition module reads vehicle observation data from multiple cameras. Compared with the direct use of special bridge health monitoring instruments to collect data, the deployment cost of the data acquisition subsystem is reduced due to the low cost of multiple cameras installed on the bridge.
  • the visual recognition module can be implemented by software, thus improving the configuration flexibility of the data acquisition subsystem, which is more conducive to the update of functions, and further reduces the deployment cost of the data acquisition subsystem due to the low deployment cost of the software.
  • the vehicle observation data includes at least one of position data, vehicle speed data, and vehicle management data of a plurality of vehicles in the target monitoring bridge.
  • the real-time bridge traffic flow data further includes vehicle weight data.
  • the data collection subsystem is further used for: collecting vehicle weight data through the visual recognition module.
  • the visual recognition module generates vehicle weight data based on vehicle observation data. Since the visual recognition module can generate vehicle weight data based on vehicle observation data, there is no need for special vehicle weight measurement instruments, thereby further reducing the deployment cost of the data acquisition subsystem.
  • vehicle observation data may include vehicle management data.
  • the data acquisition subsystem is used for: using the vehicle management data to access the vehicle management database to obtain the vehicle weight data. Since the reliability of the data in the vehicle management database is high, the vehicle weight data obtained by using the vehicle management data to access the vehicle management database has high accuracy.
  • the vehicle management data includes vehicle license plate data (eg, license plate number information), vehicle data (eg, vehicle model information), and the like.
  • the vehicle weight data can be collected by a weight in motion (WIM) system, thereby improving the collection accuracy of the vehicle weight data.
  • WIM weight in motion
  • FIG. 3 is a schematic block diagram of a data acquisition subsystem according to another embodiment of the present invention.
  • the data acquisition subsystem of FIG. 3 includes a bridge sensor 3100 , a weight acquisition system 3200 , a bridge camera 3300 , a visual recognition module 3400 and a noise removal module 3500 .
  • the bridge sensor 3100 can report its sensing data to the de-noising module 3500, and after processing by the de-noising module 3500, real-time bridge response data 3700 is generated.
  • the weight collection system 3200 can directly collect vehicle weight information to generate real-time bridge traffic flow data 3800 .
  • the bridge camera 3300 collects vehicle observation data and sends it to the visual recognition module 3400 .
  • the visual recognition module 3400 can obtain vehicle weight data by accessing the vehicle management database 3600 to generate real-time bridge traffic flow data 3800 .
  • the prediction subsystem is configured to obtain predicted bridge response data by inputting real-time bridge traffic flow data into a pre-trained simulation model.
  • the prediction subsystem also obtains real-time bridge response data from the data acquisition subsystem, and trains the real-time bridge response data and real-time bridge traffic flow data collected during the training of the simulation model as a model calibration sample set to update the simulation model. Since the simulation model has not been trained with the real-time bridge response data and real-time bridge traffic data collected during the training of the simulation model, and the above data is real-time and accurate for the simulation model, the above data is used as the model calibration sample set for model calibration. Updated to improve the prediction accuracy of the simulation model. In addition, the computation time can be greatly reduced and the simulation accuracy can be improved.
  • current real-time bridge traffic data is obtained using a previously trained simulation model, and current predicted bridge response data is generated based on the current real-time bridge traffic data, and current Real-time bridge response data, and use the current real-time bridge response data and the current real-time bridge traffic flow data as the current model calibration samples to train the next model.
  • the model can be updated in time, which is further beneficial to the accuracy of bridge health monitoring.
  • the pre-trained simulation model may be trained using at least one training sample.
  • the at least one training sample may include at least one of a measured model correction sample and a simulation result sample of the three-dimensional simulation model.
  • FIG. 4 is a schematic block diagram of a prediction subsystem according to another embodiment of the present invention.
  • the prediction subsystem includes a full 3D simulation model 4600 and a fast simulation model 4800.
  • the fast simulation model 4800 uses the model calibration data set 4500 (sample) and the simulation result data set 4700 (sample) for current training.
  • Model calibration dataset 4500 may be generated based on bridge response data 4100 during previous training and bridge traffic data 4200 during previous training.
  • the simulation result dataset 4700 may be generated based on the bridge traffic data 4200 during the previous training period, the conventional bridge traffic dataset 4300 (sample), and the bridge information 4400 .
  • the bridge information 4400 includes bridge geometric feature information, bridge material information, sensor location information, and bridge building information model (building information model) data.
  • the prediction subsystem is further configured to: perform training based on the simulation result sample set, and update the simulation model.
  • the simulation result sample set is obtained by inputting real-time bridge traffic flow data, conventional bridge traffic flow sample set and bridge information into the 3D simulation model. Since the 3D simulation model can generate accurate samples, and the 3D simulation model itself can be updated or improved through training, the flexibility or accuracy of the simulation result samples is improved.
  • the bridge health abnormality indication data includes bridge structure fault indication data and non-bridge structure fault indication data.
  • the analysis subsystem is used to obtain the initial bridge structural fault indication data and non-bridge structural fault indication data by analyzing the real-time bridge response data and the predicted bridge response data. By analyzing the initial bridge structure fault indication data and the acquired external data, the bridge structure fault indication data is obtained. Report the bridge health abnormality indication data to the presentation subsystem. Because the bridge structure fault indication data is obtained by analyzing the initial bridge structure fault indication data and the acquired external data, the reliability of the bridge structure fault indication data is improved. In addition, by analyzing the real-time bridge response data and the predicted bridge response data, the non-bridge structure fault indication data is obtained, which improves the data processing efficiency of the non-bridge structure fault indication data.
  • the analysis subsystem may include an anomaly detection module and a fault diagnosis module.
  • the anomaly detection module can obtain initial bridge structural fault indication data and non-bridge structural fault indication data by analyzing real-time bridge response data and predicted bridge response data. For example, non-bridge structural fault indication data can be reported directly to the presentation subsystem to notify bridge managers of non-bridge structural faults.
  • the non-bridge structure fault indication data includes sensor fault indication data and vehicle overweight indication data. Since the sensor fault indication data and the vehicle overweight indication data can effectively indicate non-bridge structural faults, the efficiency of troubleshooting non-bridge structural faults can be improved.
  • non-bridge structural fault indication data can indicate the degree of the non-bridge structural fault, and the bridge management personnel can judge whether it needs to be manually checked or repaired again according to the degree of the non-bridge structural fault.
  • both the initial bridge structure failure indication data and the bridge structure failure indication data may indicate the degree of non-bridge structure failure.
  • the reliability or confidence of the bridge structural fault indication data is higher than the initial bridge structural fault indication data. Therefore, the initial bridge structure fault indication data is analyzed and processed in combination with external data to obtain bridge structure fault indication data with higher reliability.
  • bridge managers can judge whether manual inspection or maintenance is required based on the confidence or reliability of the bridge structural fault indication data.
  • bridge structural failure indication data may indicate damaged sections or broken locations of a bridge.
  • the acquired external data may include traffic accident records, manual inspection records, weather information records, etc. from the traffic management bureau or other data sources.
  • FIG. 5 is a schematic block diagram of an analysis subsystem according to another embodiment of the present invention.
  • the analysis subsystem 2300 includes an anomaly detection module 5300 and a fault diagnosis module 5700 .
  • the anomaly detection module 5300 receives the real-time bridge response data 5100 of the data acquisition subsystem and the predicted bridge response data 5200 of the digital twin subsystem, and based on the above data, determines the sensor fault indication data 5400, the overweight vehicle indication data 5500 and the initial bridge structure Fault indication data 5600, and report sensor fault indication data 5400 and overweight vehicle indication data 5500 to management subsystem 2400.
  • the fault diagnosis module 5700 generates bridge structure fault indication data based on the initial bridge structure fault indication data 5600 and the external data 5800, and reports it to the management subsystem 2400.
  • the anomaly detection module 5300 may also directly generate bridge structural fault indication data based on real-time bridge response data and predicted bridge response data.
  • FIG. 6 is a schematic block diagram of a data acquisition subsystem according to another embodiment of the present invention.
  • a data acquisition subsystem 6000 for a monitoring system is shown.
  • the monitoring system is used for monitoring bridge health.
  • the monitoring system also includes a prediction subsystem and an analysis subsystem.
  • the data acquisition subsystem 6000 includes a collection module. 6100 and sending module 6200.
  • the collection module 6100 collects real-time bridge response data and real-time bridge traffic flow data.
  • the sending module 6200 sends real-time bridge traffic flow data to the prediction subsystem, and sends real-time bridge response data to the analysis subsystem, so that the analysis subsystem compares and analyzes the predicted bridge response data and the real-time bridge traffic flow data to obtain bridge health abnormality indication data.
  • Predicted bridge response data is generated by the prediction subsystem based on real-time bridge traffic data.
  • the data acquisition subsystem, forecasting subsystem, analysis subsystem and presentation subsystem included in the monitoring system are universal, they can overcome the limitation of geographical location and carry out unified monitoring of most bridges.
  • the real-time bridge response data used in the comparative analysis comes from the data acquisition subsystem, and the predicted bridge response data used is obtained by predicting the real-time bridge traffic flow data by the prediction subsystem, the real-time bridge response data and the predicted bridge response
  • the data can effectively reflect the relationship between the real-time bridge response data and the real-time bridge traffic flow data, so as to compare and analyze the above two to obtain the abnormal indicator data of bridge health, which improves the accuracy of bridge health monitoring.
  • FIG. 7 is a schematic block diagram of an analysis subsystem according to another embodiment of the present invention.
  • an analysis subsystem 7000 for a monitoring system is shown for monitoring bridge health, and the monitoring system further includes a data acquisition subsystem and a presentation subsystem.
  • the analysis subsystem 7000 includes an acquisition module 7100 , an analysis module 7200 and a reporting module 7300 .
  • the acquisition module 7100 acquires its acquired real-time bridge response data from the data acquisition subsystem, and acquires predicted bridge response data from the prediction subsystem. Predicted bridge response data is generated based on real-time bridge traffic data obtained from the data acquisition subsystem.
  • the analysis module 7200 obtains bridge health abnormality indication data by comparing and analyzing the real-time bridge response data and the predicted bridge response data.
  • the reporting module 7300 reports the bridge health abnormality indication data to the presentation subsystem to present the bridge health abnormality indication data.
  • the data acquisition subsystem, forecasting subsystem, analysis subsystem and presentation subsystem included in the monitoring system are universal, they can overcome the limitation of geographical location and carry out unified monitoring of most bridges.
  • the real-time bridge response data used in the comparative analysis comes from the data acquisition subsystem, and the predicted bridge response data used is obtained by predicting the real-time bridge traffic flow data by the prediction subsystem, the real-time bridge response data and the predicted bridge response
  • the data can effectively reflect the relationship between the real-time bridge response data and the real-time bridge traffic flow data, so as to compare and analyze the above two to obtain the abnormal indicator data of bridge health, which improves the accuracy of bridge health monitoring.
  • FIG. 8 is a schematic flowchart of a monitoring method for a data acquisition subsystem according to another embodiment of the present invention. As shown in the figure, a monitoring method is shown, which is applied to the data acquisition subsystem of the monitoring system. The monitoring system is used to monitor the health of the bridge. The monitoring system also includes a prediction subsystem and an analysis subsystem. The monitoring method includes:
  • S810 Collect real-time bridge response data and real-time bridge traffic flow data
  • S820 Send real-time bridge traffic flow data to the prediction subsystem, and send real-time bridge response data to the analysis subsystem, so that the analysis subsystem can compare and analyze the predicted bridge response data and the real-time bridge traffic flow data, and obtain bridge health abnormality indication data.
  • Predicted bridge response data is generated by the prediction subsystem based on real-time bridge traffic data.
  • the data acquisition subsystem, forecasting subsystem, analysis subsystem and presentation subsystem included in the monitoring system are universal, they can overcome the limitation of geographical location and carry out unified monitoring of most bridges.
  • the real-time bridge response data used in the comparative analysis comes from the data acquisition subsystem, and the predicted bridge response data used is obtained by predicting the real-time bridge traffic flow data by the prediction subsystem, the real-time bridge response data and the predicted bridge response
  • the data can effectively reflect the relationship between the real-time bridge response data and the real-time bridge traffic flow data, so as to compare and analyze the above two to obtain the abnormal indicator data of bridge health, which improves the accuracy of bridge health monitoring.
  • FIG. 9 is a schematic flowchart of a monitoring method for an analysis subsystem according to another embodiment of the present invention.
  • Figure 9 shows a monitoring method applied to a monitoring system.
  • the monitoring system is used to monitor the health of the bridge.
  • the monitoring system also includes a data acquisition subsystem and a presentation subsystem.
  • the monitoring method includes:
  • S910 Obtain the collected real-time bridge response data from the data collection subsystem, and obtain predicted bridge response data from the prediction subsystem.
  • the predicted bridge response data is generated based on real-time bridge traffic flow data obtained from the data acquisition subsystem;
  • S930 Report the abnormality indication data of the bridge health to the presentation subsystem, so as to present the abnormality indication data of the bridge health.
  • the data acquisition subsystem, forecasting subsystem, analysis subsystem and presentation subsystem included in the monitoring system are universal, they can overcome the limitation of geographical location and carry out unified monitoring of most bridges.
  • the real-time bridge response data used in the comparative analysis comes from the data acquisition subsystem, and the predicted bridge response data used is obtained by predicting the real-time bridge traffic flow data by the prediction subsystem, the real-time bridge response data and the predicted bridge response
  • the data can effectively reflect the relationship between the real-time bridge response data and the real-time bridge traffic flow data, so as to compare and analyze the above two to obtain the abnormal indicator data of bridge health, which improves the accuracy of bridge health monitoring.
  • Embodiments of the present invention also provide a computer program product tangibly stored on a computer-readable medium and comprising computer-readable instructions that, when executed, cause at least one processor to Execute the above method.
  • FIG. 10 is a schematic structural diagram of an electronic device according to another embodiment of the present invention.
  • the electronic device can be applied to the data acquisition subsystem of the monitoring system, eg, one or more servers.
  • the electronic device of FIG. 10 includes one or more processors 1010, a communication interface 1020, a memory 1030 and a communication bus 1040, and one or more programs.
  • One or more processors 1010, the communication interface 1020, and the memory 1030 communicate with each other through the communication bus 1040, and one or more programs are stored in the memory 1030 and configured to be executed by the one or more processors 1010, One or more programs to perform: collect real-time bridge response data and real-time bridge traffic data; send real-time bridge traffic data to the prediction subsystem, and send real-time bridge response data to the analysis subsystem so that the analysis subsystem can compare and analyze predictions Bridge response data and real-time bridge traffic flow data are used to obtain bridge health abnormality indication data. Predicted bridge response data is generated by the prediction subsystem based on real-time bridge traffic data.
  • FIG. 11 is a schematic structural diagram of an electronic device according to another embodiment of the present invention.
  • the electronic device may be applied to the analysis subsystem of the monitoring system, eg, one or more servers.
  • the electronic device of FIG. 11 includes one or more processors 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, and one or more programs.
  • One or more processors 1110, a communication interface 1120, and a memory 1130 communicate with each other through a communication bus 1140, and one or more programs are stored in the memory 1030 and configured to be executed by the one or more processors 1010,
  • One or more programs are used to perform: obtain their collected real-time bridge response data from the data acquisition subsystem, and obtain predicted bridge response data from the prediction subsystem.
  • the predicted bridge response data is generated based on the real-time bridge traffic flow data obtained from the data acquisition subsystem; by comparing and analyzing the real-time bridge response data and the predicted bridge response data, the bridge health abnormality indication data is obtained; the bridge health abnormality indication is reported to the presentation subsystem data to present the abnormal indicator data of bridge health.
  • the computer storage medium of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two.
  • the computer readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above.
  • Computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access storage media (RAM), read only storage media (ROM), erasable storage media programmable read-only storage media (EPROM or flash memory), optical fiber, portable compact disk read-only storage media (CD-ROM), optical storage media devices, magnetic storage media devices, or any suitable combination of the foregoing.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program configured for use by or in connection with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品。监测系统包括数据采集子系统、预测子系统、分析子系统和呈现子系统。数据采集子系统采集实时桥梁响应数据和实时桥梁车流量数据。预测子系统从数据采集子系统获取实时桥梁车流量数据，并且根据实时桥梁车流量数据，生成预测桥梁响应数据。分析子系统通过对比分析实时桥梁响应数据与预测桥梁响应数据，得到桥梁健康度异常指示数据。呈现子系统从分析子系统获取桥梁健康度异常指示数据，并且呈现桥梁健康度异常指示数据。由此，节省了桥梁监控的成本并且提高了桥梁监控的准确度。

Description

监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品 技术领域
本申请实施例涉及工业监测技术领域，尤其涉及一种监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品。
背景技术
由于自然灾害、环境影响、交通事故、结构老化等原因，桥梁的结构健康度会随着时间不断变化。某些可能会造成重大损失的桥梁故障很难通过定期的手动检查而及时得到监控。桥梁结构的可靠性的准确测量以及桥梁的损坏位置的识别通常会花费大量的成本和时间。
大多数桥梁由于没有设置桥梁健康度监测仪器而得不到有效的监控，并且这些仪器由于价格昂贵难以在多数桥梁中设置，导致桥梁健康度监控的效果较差。
发明内容
为了解决上述问题，本发明实施例提供了一种监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品，以至少部分地解决上述问题。
根据本发明实施例的第一方面，提供了一种监测方法，用于监测桥梁健康度。所述监测方法包括：采集实时桥梁响应数据，并且采集实时桥梁车流量数据；根据所述实时桥梁车流量数据，生成预测桥梁响应数据；通过对比分析所述实时桥梁响应数据与所述预测桥梁响应数据，得到桥梁健康度异常指示数据；以及呈现所述桥梁健康度异常指示数据。
由于对比分析所采用的实时桥梁响应数据来自数据采集子系统，并且所采用的预测桥梁响应数据通过预测子系统对实时桥梁车流量数据进行预测得到，因此，实时桥梁响应数据与预测桥梁响应数据能够有效地反应出实时桥梁响应数据和实时桥梁车流量数据之间的关联，通过对比分析上述两者得到桥梁健康度异常指示数据，提高了桥梁健康度监控的准确度。
在本发明的另一实现方式中，所述采集实时桥梁响应数据，包括：读取设置在桥梁上的多个传感器的实时感测数据，并且对所述感测数据进行降噪处理，得到所述实时桥梁响应数据。
由于设置在桥梁上的多个传感器相比于专门的桥梁健康度监控仪器具有成本低的特点，因此降低了数据采集子系统的部署成本。此外，对所述感测数据进行降噪处理，得到的实时桥梁响应数据，提高了数据采集的准确度。
在本发明的另一实现方式中，所述实时桥梁车流量数据包括设置在桥梁上的多个摄像头的车辆观测数据。所述采集实时桥梁车流量数据，包括：通过视觉识别模块，采集所述车辆观测数据。所述视觉识别模块通过从所述多个摄像头读取所述车辆观测数据。
由于设置在桥梁上的多个摄像头相比于专门的桥梁健康度监控仪器具有成本低的特点，因此降低了数据采集子系统的部署成本。此外，视觉识别模块能够采用软件实现，因此提高了数据采集子系统的配置灵活度，更有利于功能的更新，并且由于软件的部署成本较低，进一步地降低了数据采集子系统的部署成本。
在本发明的另一实现方式中，所述实时桥梁车流量数据还包括车重数据，所述车辆观测数据包括车辆管理数据。所述采集实时桥梁车流量数据，还包括：利用所述车辆管理数据访问车辆管理数据库，得到所述车重数据。
由于视觉识别模块能够基于所述车辆观测数据，生成车重数据，因此无需专门的车重测量仪器，从而进一步降低了数据采集子系统的部署成本。此外，由于车辆管理数据库中的数据的可靠性较高，因此利用所述车辆管理数据访问车辆管理数据库，得到的车重的数据的准确度较高。
在本发明的另一实现方式中，所述根据所述实时桥梁车流量数据，生成预测桥梁响应数据，包括：通过向预先训练的模拟模型输入所述实时桥梁车流量数据，得到所述预测桥梁响应数据。所述方法还包括：将在所述模拟模型的训练期间采集的所述实时桥梁响应数据与所述实时桥梁车流量数据作为模型校准样本集进行训练，以更新所述模拟模型。
由于模拟模型未经过模拟模型的训练期间采集的实时桥梁响应数据与实时桥梁车流量数据进行训练，并且上述数据对模拟模型而言是实时而准确的，因此采用上述数据作为模型校准样本集进行模型更新，提高了模拟模型的预测精确度。
在本发明的另一实现方式中，所述方法还包括：基于模拟结果样本集进行训练，更新所述模拟模型。所述模拟结果样本集通过将所述实时桥梁车流量数据、常规桥梁车流量样本集和桥梁信息输入到三维模拟模型获得。
由于三维模拟模型能够生成准确的样本，并且三维模拟模型自身也可以通过训练更新或改进，因此提高了模拟结果样本的灵活性或准确性。
在本发明的另一实现方式中，所述桥梁健康度异常指示数据包括桥梁结构故障指示数据和非桥梁结构故障指示数据。所述通过对比分析所述实时桥梁响应数据与所述预测桥梁 响应数据，得到桥梁健康度异常指示数据，包括：通过分析所述实时桥梁响应数据与所述预测桥梁响应数据，得到初始桥梁结构故障指示数据和非桥梁结构故障指示数据；并且通过分析所述初始桥梁结构故障指示数据和获取的外部数据，得到所述桥梁结构故障指示数据；向所述呈现子系统上报所述桥梁健康度异常指示数据。
由于通过分析初始桥梁结构故障指示数据和获取的外部数据，得到桥梁结构故障指示数据，因此提高了桥梁结构故障指示数据的可靠性。此外，通过分析实时桥梁响应数据与预测桥梁响应数据，得到非桥梁结构故障指示数据，提高了非桥梁结构故障指示数据的数据处理效率。
在本发明的另一实现方式中，所述非桥梁结构故障指示数据包括传感器故障指示数据和车辆超重指示数据。
由于传感器故障指示数据和车辆超重指示数据能够有效地指示非桥梁结构故障，进而能够提高排查非桥梁结构故障的效率。
根据本发明实施例的第二方面，提供了一种采集方法，应用于监测系统的数据采集子系统，所述监测系统用于监测桥梁健康度，所述监测系统还包括预测子系统和分析子系统，所述方法包括：采集实时桥梁响应数据和实时桥梁车流量数据；向所述预测子系统发送所述实时桥梁车流量数据，并且向所述分析子系统发送所述实时桥梁响应数据，以便所述分析子系统对比分析预测桥梁响应数据和所述实时桥梁车流量数据，得到桥梁健康度异常指示数据。所述预测桥梁响应数据为所述预测子系统根据所述实时桥梁车流量数据生成。
由于监测系统包括的数据采集子系统、预测子系统、分析子系统和呈现子系统具有通用性，因此能够克服地理位置的限制，对多数桥梁进行的统一监控，节省了桥梁监控的成本。此外，由于对比分析所采用的实时桥梁响应数据来自数据采集子系统，并且所采用的预测桥梁响应数据通过预测子系统对实时桥梁车流量数据进行预测得到，因此，实时桥梁响应数据与预测桥梁响应数据能够有效地反应出实时桥梁响应数据和实时桥梁车流量数据之间的关联，通过从而对比分析上述两者得到桥梁健康度异常指示数据，提高了桥梁健康度监控的准确度。
根据本发明实施例的第三方面，提供了一种分析方法，应用于监测系统的分析子系统，所述监测系统用于监测桥梁健康度，所述监测系统还包括数据采集子系统和呈现子系统。所述方法包括：从所述数据采集子系统获取其采集的实时桥梁响应数据，并且从所述预测子系统获取所述预测桥梁响应数据。所述预测桥梁响应数据基于从所述数据采集子系统获取的实时桥梁车流量数据生成；通过对比分析所述实时桥梁响应数据与所述预测桥梁响应数据，得到桥梁健康度异常指示数据；向呈现子系统上报所述桥梁健康度异常指示数据， 以呈现所述桥梁健康度异常指示数据。
由于监测系统包括的数据采集子系统、预测子系统、分析子系统和呈现子系统具有通用性，能够克服地理位置的限制，对多数桥梁进行统一监控，节省了桥梁监控的成本。此外，由于对比分析所采用的实时桥梁响应数据来自数据采集子系统，并且所采用的预测桥梁响应数据通过预测子系统对实时桥梁车流量数据进行预测得到，因此，实时桥梁响应数据与预测桥梁响应数据能够有效地反应出实时桥梁响应数据和实时桥梁车流量数据之间的关联，通过对比分析上述两者得到桥梁健康度异常指示数据，提高了桥梁健康度监控的准确度。
根据本发明实施例的第四方面，提供了一种用于监测系统的数据采集子系统，所述监测系统用于监测桥梁健康度，所述监测系统还包括预测子系统和分析子系统，所述数据采集子系统包括：一个或多个处理器、通信接口、存储器和通信总线、以及一个或多个程序。一个或多个处理器、通信接口、存储器通过通信总线完成相互间的通信，一个或多个程序被存储在存储器中，并且被配置为由一个或多个处理器执行，以执行第二方面所述的方法。
根据本发明实施例的第五方面，提供了一种用于监测系统的分析子系统，所述监测系统用于监测桥梁健康度，所述监测系统还包括数据采集子系统和呈现子系统，所述分析子系统包括：一个或多个处理器、通信接口、存储器和通信总线、以及一个或多个程序。一个或多个处理器、通信接口、存储器通过通信总线完成相互间的通信，一个或多个程序被存储在存储器中，并且被配置为由一个或多个处理器执行，以执行第三方面所述的方法。
根据本发明实施例的第六方面，提供了一种监测系统，用于监测桥梁健康度，所述监测系统包括：数据采集子系统，用于：采集实时桥梁响应数据和实时桥梁车流量数据；预测子系统，用于：从所述数据采集子系统获取所述实时桥梁车流量数据，并且根据所述实时桥梁车流量数据，生成预测桥梁响应数据；分析子系统，用于：从所述数据采集子系统获取所述实时桥梁响应数据，并且从所述预测子系统获取所述预测桥梁响应数据；和通过对比分析所述实时桥梁响应数据与所述预测桥梁响应数据，得到桥梁健康度异常指示数据；以及呈现子系统，用于：从所述分析子系统获取所述桥梁健康度异常指示数据，并且呈现所述桥梁健康度异常指示数据。
根据本发明实施例的第七方面，提供了一种存储介质，所述存储介质包括存储的程序。在所述程序运行时控制包括所述存储介质的设备执行第四方面或第五方面所述的方法。
根据本发明实施例的第八方面，提供了一种计算机程序，包括计算机可执行指令，所述计算机执行指令在被执行时使至少一个处理器执行根据第四方面或第五方面所述的方法。
根据本发明实施例的第九方面，提供了一种计算机程序产品，所述计算机程序产品被有形地存储在计算机可读介质上并且包括计算机可读指令，所述计算机可执行指令在被执行时使至少一个处理器执行根据第四方面或第五方面所述的方法。
由于监测系统包括的数据采集子系统、预测子系统、分析子系统和呈现子系统具有通用性，能够克服地理位置的限制，对多数桥梁进行统一监控，节省了桥梁监控的成本。此外，由于对比分析所采用的实时桥梁响应数据来自数据采集子系统，并且所采用的预测桥梁响应数据通过预测子系统对实时桥梁车流量数据进行预测得到，因此，实时桥梁响应数据与预测桥梁响应数据能够有效地反应出实时桥梁响应数据和实时桥梁车流量数据之间的关联，通过对比分析上述两者得到桥梁健康度异常指示数据，提高了桥梁健康度监控的准确度。
附图说明
以下附图仅旨在于对本申请做示意性说明和解释，并不限定本申请的范围。其中，
图1A为本发明的一个实施例的用于监测桥梁健康度的监测系统的示意图框图；
图1B为本发明的一个实施例的用于监测桥梁健康度的监测方法的示意性流程图；
图2为本发明的另一实施例的用于监测桥梁健康度的监测系统的示意图框图；
图3为本发明的另一实施例的数据采集子系统的示意性框图；
图4为本发明的另一实施例的预测子系统的示意性框图；
图5为本发明的另一实施例的分析子系统的示意性框图；
图6为本发明的另一实施例的数据采集子系统的示意性框图；
图7为本发明的另一实施例的分析子系统的示意性框图；
图8为本发明的另一实施例的数据采集子系统的监测方法的示意性流程图；
图9为本发明的另一实施例的分析子系统的监测方法的示意性流程图；
图10为本发明的另一实施例的电子设备结构示意图；
图11为本发明的另一实施例的电子设备结构示意图。
附图标记列表：
1000：监测系统；1100：数据采集子系统；1200：预测子系统；1300：分析子系统；1400：呈现子系统；
S110：采集实时桥梁响应数据，并且采集实时桥梁车流量数据；
S120：根据实时桥梁车流量数据，生成预测桥梁响应数据；
S130：通过对比分析实时桥梁响应数据与预测桥梁响应数据，得到桥梁健康度异常指示数据；
S140：呈现桥梁健康度异常指示数据；
2000：监测系统；2100：数据采集子系统；2200：数字孪生子系统；2210：快速模拟模块；2300：决策子系统；2310：异常检测模块；2320：故障诊断模块；2400：管理子系统；
3100：桥梁传感器；3200：重量采集系统；3300：桥梁相机；3400：视觉识别模块；3500：去噪声模块；3600：车辆管理数据库；3700：实时桥梁响应数据；3800：实时桥梁车流量数据；
4100：桥梁响应数据；4200：桥梁车流量数据；4300：常规桥梁车流量数据集；4400：桥梁信息；4500：模型校准数据集；4600：全三维模拟模型；4700：模拟结果数据集；4800：快速模拟模型；
5100：实时桥梁响应数据；5200：预测桥梁响应数据；5300：异常检测模块；5400：传感器故障指示数据；5500：超重车辆指示数据；5600：初始桥梁结构故障指示数据；5700：故障诊断模块；5800：外部数据；
6000：数据采集子系统；6100：采集模块；6200：发送模块；
7000：分析子系统；7100：获取模块；7200：分析模块；7300：上报模块；
S810：采集实时桥梁响应数据和实时桥梁车流量数据；
S820：向预测子系统发送实时桥梁车流量数据，并且向分析子系统发送实时桥梁响应数据，以便分析子系统对比分析预测桥梁响应数据和实时桥梁车流量数据，得到桥梁健康度异常指示数据。预测桥梁响应数据为预测子系统根据实时桥梁车流量数据生成；
S910：从数据采集子系统获取其采集的实时桥梁响应数据，并且从预测子系统获取预测桥梁响应数据。预测桥梁响应数据基于从数据采集子系统获取的实时桥梁车流量数据生成；
S920：通过对比分析实时桥梁响应数据与预测桥梁响应数据，得到桥梁健康度异常指示数据；
S930：向呈现子系统上报桥梁健康度异常指示数据，以呈现桥梁健康度异常指示数据；
1010：处理器；1020：通信接口；1030：存储器；1040：通信总线；
1110：处理器；1120：通信接口；1130：存储器；1140：通信总线。
具体实施方式
为了对本申请实施例的技术特征、目的和效果有更加清楚的理解，现对照附图说明本申请实施例的具体实施方式。
图1为本发明的一个实施例的用于监测桥梁健康度的监测系统的示意图框图。如图所示，监测系统1000用于监测桥梁健康度。监测系统1000包括数据采集子系统1100、预测子系统1200、分析子系统1300和呈现子系统1400。
应理解，数据采集子系统1100可以设置在一个或多个目标监测桥梁处，例如，可以设置在桥梁的主梁、桥塔、拉索、栏杆或桥墩等上。数据采集子系统1100能够采集实时桥梁响应数据和实时桥梁车流量数据。上述数据可以分别由实时桥梁响应数据采集模块和实时桥梁车流量数据采集模块来实现。
应理解，桥梁响应数据可以为桥梁结构响应数据等。桥梁结构响应数据可以通过多个设置在桥梁截面上的传感器获取，例如，当车辆通过桥梁的各个截面部分时，会引起桥梁结构的变化。各个传感器可以依次获取桥梁结构响应数据。
此外，可以通过设置在桥梁处的多个传感器(多个监测传感器)对在车辆通过时产生的桥梁响应数据进行采集，例如，上述桥梁响应数据可以为桥梁结构响应数据的峰值数据。
此外，实时桥梁车流量数据可以通过车辆监控视频通过一个设置在桥面上方的交通监控装置(即，例如，摄像头)获取，交通监控装置能够对车辆通过桥面时的视频画面进行拍摄。
此外，在一个示例中，传感器可以为诸如动应变传感器的传感器，用于获取车辆通过时产生的桥梁纵向动应变。在其他示例中，传感器还可以是多个其他类型的监测传感器，用于采集车辆通过时产生的其他类型的桥梁结构响应数据。其他类型的监测传感器可以为加速度传感器、位移传感器、振动传感器、倾斜传感器中的至少一者。
预测子系统1200可以设置在一个或多个目标监测桥梁处，也可以与一个或多个目标监测桥梁分离设置。
此外，预测子系统1200从数据采集子系统获取实时桥梁车流量数据，并且根据实时桥梁车流量数据，生成预测桥梁响应数据。例如，预测子系统可以对应于多个目标监测桥梁，用于接收多个目标监测桥梁的实时桥梁车流量数据，并且根据实时桥梁车流量数据，生成多个目标监测桥梁的预测桥梁响应数据。预测子系统可以采用数字孪生技术实现，桥梁数字孪生模型可以应用于桥梁的物理环境，例如，对桥梁的主梁、桥塔、拉索、栏杆或桥墩等进行模拟。
分析子系统1300可以设置在一个或多个目标监测桥梁处，也可以与一个或多个目标监测桥梁分离设置。例如，分析子系统可以实现为决策子系统，包括异常检测模块和故障 诊断模块。此外，分析子系统可以与预测子系统设置于统一机构，并且可以布置在同一服务器或不同服务器中。
此外，分析子系统1300从数据采集子系统获取实时桥梁响应数据，并且从预测子系统获取预测桥梁响应数据；通过对比分析实时桥梁响应数据与预测桥梁响应数据，得到桥梁健康度异常指示数据。例如，可以从数据采集子系统获取一个或多个目标监测桥梁的实时桥梁响应数据。例如，可以从预测子系统获取一个或多个目标监测桥梁的预测桥梁响应数据。
呈现子系统1400可以设置在桥梁管理机构处，可以实现为管理子系统。呈现子系统1400从分析子系统获取桥梁健康度异常指示数据，并且呈现桥梁健康度异常指示数据。呈现子系统还可以呈现一个或多个目标监测桥梁的位置。
由于监测系统包括的数据采集子系统、预测子系统、分析子系统和呈现子系统具有通用性，能够克服地理位置的限制，对多数桥梁进行统一监控。此外，由于对比分析所采用的实时桥梁响应数据来自数据采集子系统，并且所采用的预测桥梁响应数据通过预测子系统对实时桥梁车流量数据进行预测得到，因此，实时桥梁响应数据与预测桥梁响应数据能够有效地反应出实时桥梁响应数据和实时桥梁车流量数据之间的关联，从而对比分析上述两者得到桥梁健康度异常指示数据，提高了桥梁健康度监控的准确度。
在一个示例中，监测系统可以实现为不同的云计算和边缘计算的通信交互模式。例如，预测子系统可以对应于一个桥梁或多个桥梁(例如，一个区域内的所有桥梁)，并且针对一个或多个桥梁的实时桥梁车流量数据进行预测，实现为对应于该桥梁或该区域的边缘计算端。分析子系统可以实现为与作为边缘计算端的预测子系统对应的云服务端。
在另一示例中，数据采集子系统可以对应于一个桥梁或多个桥梁(例如，一个区域内的所有桥梁)，并且针对一个或多个桥梁的实时桥梁车流量数据和实时桥梁响应数据进行采集，实现为对应于该桥梁或该区域的边缘计算端。此外，分析子系统和预测子系统两者可以实现为与作为边缘计算端的数据采集子系统对应的第一后台云服务端和第二后台云服务端。或者，分析子系统和预测子系统可以分布实现为与作为边缘计算端的数据采集子系统对应的后台云服务端和中台云服务端。
此外，呈现子系统可以设置在固定的物理位置，也可以作为应用程序配置在诸如手机的移动终端中，例如，配置在桥梁监测人员或维护人员所使用的移动终端中。该移动终端中配置有电子地图显示。在电子地图上，可以显示有桥梁的分布信息(例如，桥梁的位置)、预测子系统的分布信息(例如，预测子系统的位置)、分析子系统的分布信息(例如，分布子系统的位置)等。
图1B为本发明的一个实施例的用于监测桥梁健康度的监测方法的示意性流程图。图1B的监测方法，用于监测桥梁健康度。该监测方法包括：
S110：采集实时桥梁响应数据，并且采集实时桥梁车流量数据。
S120：根据实时桥梁车流量数据，生成预测桥梁响应数据。
S130：通过对比分析实时桥梁响应数据与预测桥梁响应数据，得到桥梁健康度异常指示数据。
S140：呈现桥梁健康度异常指示数据。
由于对比分析所采用的实时桥梁响应数据来自数据采集子系统，并且所采用的预测桥梁响应数据通过预测子系统对实时桥梁车流量数据进行预测得到，因此，实时桥梁响应数据与预测桥梁响应数据能够有效地反应出实时桥梁响应数据和实时桥梁车流量数据之间的关联，通过对比分析上述两者得到桥梁健康度异常指示数据，提高了桥梁健康度监控的准确度。
在本发明的另一实现方式中，采集实时桥梁响应数据，包括：读取设置在桥梁上的多个传感器的实时感测数据，并且对感测数据进行降噪处理，得到实时桥梁响应数据。由于设置在桥梁上的多个传感器相比于专门的桥梁健康度监控仪器具有成本低的特点，因此降低了数据采集子系统的部署成本。此外，对感测数据进行降噪处理，得到的实时桥梁响应数据，提高了数据采集的准确度。
在本发明的另一实现方式中，实时桥梁车流量数据包括设置在桥梁上的多个摄像头的车辆观测数据。采集实时桥梁车流量数据，包括：通过视觉识别模块，采集车辆观测数据。视觉识别模块通过从多个摄像头读取车辆观测数据。由于设置在桥梁上的多个摄像头相比于专门的桥梁健康度监控仪器具有成本低的特点，因此降低了数据采集子系统的部署成本。此外，视觉识别模块能够采用软件实现，因此提高了数据采集子系统的配置灵活度，更有利于功能的更新，并且由于软件的部署成本较低，进一步地降低了数据采集子系统的部署成本。
在本发明的另一实现方式中，实时桥梁车流量数据还包括车重数据，车辆观测数据包括车辆管理数据。采集实时桥梁车流量数据，还包括：利用车辆管理数据访问车辆管理数据库，得到车重数据。由于视觉识别模块能够基于车辆观测数据，生成车重数据，因此无需专门的车重测量仪器，从而进一步降低了数据采集子系统的部署成本。此外，由于车辆管理数据库中的数据的可靠性较高，因此利用车辆管理数据访问车辆管理数据库，得到的车重的数据的准确度较高。
在本发明的另一实现方式中，根据实时桥梁车流量数据，生成预测桥梁响应数据，包 括：通过向预先训练的模拟模型输入实时桥梁车流量数据，得到预测桥梁响应数据。该方法还包括：将在模拟模型的训练期间采集的实时桥梁响应数据与实时桥梁车流量数据作为模型校准样本集进行训练，以更新模拟模型。由于模拟模型未经过模拟模型的训练期间采集的实时桥梁响应数据与实时桥梁车流量数据进行训练，并且上述数据对模拟模型而言是实时而准确的，因此采用上述数据作为模型校准样本集进行模型更新，提高了模拟模型的预测精确度。
在本发明的另一实现方式中，该方法还包括：基于模拟结果样本集进行训练，更新模拟模型。模拟结果样本集通过将实时桥梁车流量数据、常规桥梁车流量样本集和桥梁信息输入到三维模拟模型获得。由于三维模拟模型能够生成准确的样本，并且三维模拟模型自身也可以通过训练更新或改进，因此提高了模拟结果样本的灵活性或准确性。
在本发明的另一实现方式中，桥梁健康度异常指示数据包括桥梁结构故障指示数据和非桥梁结构故障指示数据。通过对比分析实时桥梁响应数据与预测桥梁响应数据，得到桥梁健康度异常指示数据，包括：通过分析实时桥梁响应数据与预测桥梁响应数据，得到初始桥梁结构故障指示数据和非桥梁结构故障指示数据；并且通过分析初始桥梁结构故障指示数据和获取的外部数据，得到桥梁结构故障指示数据；向呈现子系统上报桥梁健康度异常指示数据。由于通过分析初始桥梁结构故障指示数据和获取的外部数据，得到桥梁结构故障指示数据，因此提高了桥梁结构故障指示数据的可靠性。此外，通过分析实时桥梁响应数据与预测桥梁响应数据，得到非桥梁结构故障指示数据，提高了非桥梁结构故障指示数据的数据处理效率。
在本发明的另一实现方式中，非桥梁结构故障指示数据包括传感器故障指示数据和车辆超重指示数据。由于传感器故障指示数据和车辆超重指示数据能够有效地指示非桥梁结构故障，进而能够提高排查非桥梁结构故障的效率。
图2为本发明的另一实施例的用于监测桥梁健康度的监测系统的示意图框图。如图所示，监测系统2000包括数据采集子系统2100、数字孪生子系统2200、决策子系统2300和管理子系统2400。其中，数字孪生子系统2200可以包括快速模拟模块2210。决策子系统2300可以包括异常检测模块2310和故障诊断模块2320。其中，数字孪生子系统2200接收数据采集子系统2100上报的实时桥梁车流量数据。异常检测模块2310接收数据采集子系统2100上报的实时桥梁响应数据，并且接收数字孪生子系统2200发送的根据实时桥梁车流量数据生成的预测桥梁响应数据。异常检测模块2310基于上述数据生成故障类型指示数据，至少将部分故障类型指示数据发送到故障诊断模块2320，进行诸如分析、判断或确认的处理。故障诊断模块2320向管理子系统2400呈现上述处理结果。
在本发明的另一实现方式中，数据采集子系统用于：读取设置在桥梁上的多个传感器的实时感测数据，并且对感测数据进行降噪处理，得到实时桥梁响应数据。由于设置在桥梁上的多个传感器相比于专门的桥梁健康度监控仪器具有成本低的特点，因此降低了数据采集子系统的部署成本。此外，对感测数据进行降噪处理，得到的实时桥梁响应数据，提高了数据采集的准确度。例如，设置在桥梁上的多个传感器可以包括位移传感器、振动传感器、倾斜传感器中的至少一者。
在本发明的另一实现方式中，实时桥梁车流量数据包括设置在桥梁上的多个摄像头的车辆观测数据。数据采集子系统用于：通过视觉识别模块，采集车辆观测数据。视觉识别模块通过从多个摄像头读取车辆观测数据。相比于直接采用专门的桥梁健康度监控仪器来采集，由于设置在桥梁上的多个摄像头具有成本低的特点，因此降低了数据采集子系统的部署成本。此外，视觉识别模块能够采用软件实现，因此提高了数据采集子系统的配置灵活度，更有利于功能的更新，并且由于软件的部署成本较低，进一步地降低了数据采集子系统的部署成本。例如，车辆观测数据包括目标监测桥梁中的多个车辆的位置数据、车速数据、车辆管理数据中的至少一者。
在本发明的另一实现方式中，实时桥梁车流量数据还包括车重数据。其中，在一个示例中，数据采集子系统还用于：通过视觉识别模块，采集车重数据。视觉识别模块基于车辆观测数据，生成车重数据。由于视觉识别模块能够基于车辆观测数据，生成车重数据，因此无需专门的车重测量仪器，从而进一步降低了数据采集子系统的部署成本。
具体而言，车辆观测数据可以包括车辆管理数据。数据采集子系统用于：利用车辆管理数据访问车辆管理数据库，得到车重数据。由于车辆管理数据库中的数据的可靠性较高，因此利用车辆管理数据访问车辆管理数据库，得到的车重的数据的准确度较高。例如，车辆管理数据包括车辆牌照数据(例如，车牌号信息)、车辆数据(例如，车辆型号的信息)等。
在另一示例中，车重数据可以通过重量采集(weight in motion,WIM)系统来采集，从而提高了车重数据的采集精度。
图3为本发明的另一实施例的数据采集子系统的示意性框图。图3的数据采集子系统包括桥梁传感器3100、重量采集系统3200、桥梁相机3300、视觉识别模块3400和去噪声模块3500。其中，桥梁传感器3100可以将其感测数据上报到去噪声模块3500，经过去噪声模块3500的处理，生成实时桥梁响应数据3700。对于实时桥梁车流量数据的采集，在一个例子中，重量采集系统3200可以直接采集车重信息，生成实时桥梁车流量数据3800。在另一个例子中，桥梁相机3300采集车辆观测数据，发送到视觉识别模块3400。视觉识 别模块3400可以通过访问车辆管理数据库3600得到车重数据，以便生成实时桥梁车流量数据3800。
在本发明的另一实现方式中，预测子系统用于：通过向预先训练的模拟模型输入实时桥梁车流量数据，得到预测桥梁响应数据。预测子系统还从数据采集子系统获取实时桥梁响应数据，并且将在模拟模型的训练期间采集的实时桥梁响应数据与实时桥梁车流量数据作为模型校准样本集进行训练，以更新模拟模型。由于模拟模型未经过模拟模型的训练期间采集的实时桥梁响应数据与实时桥梁车流量数据进行训练，并且上述数据对模拟模型而言是实时而准确的，因此采用上述数据作为模型校准样本集进行模型更新，提高了模拟模型的预测精确度。此外，还可以极大地减少计算时间并且提高模拟精度。
在一个示例中，在当前模型的训练期间，利用先前训练的模拟模型，获取当前的实时桥梁车流量数据，并且根据当前的实时桥梁车流量数据，生成当前的预测桥梁响应数据，并且获取当前的实时桥梁响应数据，并且利用当前的实时桥梁响应数据和当前的实时桥梁车流量数据作为当前模型校准样本，对下一模型进行训练。
由于实时桥梁响应数据和实时桥梁车流量数据均为实时数据，因此实现了模型及时更新，进一步有利于桥梁健康度监测的准确度。
在另一示例中，预先训练的模拟模型可以采用至少一种训练样本进行训练。至少一种训练样本可以包括测量的模型矫正样本和三维模拟模型的模拟结果样本中的至少一种。图4为本发明的另一实施例的预测子系统的示意性框图。如图所示，预测子系统包括全三维模拟模型4600和快速模拟模型4800。其中，快速模拟模型4800采用模型校准数据集4500(样本)和模拟结果数据集4700(样本)进行当前训练。模型校准数据集4500可以基于先前训练期间的桥梁响应数据4100和先前训练期间的桥梁车流量数据4200生成。此外，模拟结果数据集4700可以基于先前训练期间的桥梁车流量数据4200、常规桥梁车流量数据集4300(样本)和桥梁信息4400生成。其中，桥梁信息4400包括桥梁几何特征信息、桥梁材料信息、传感器的位置信息以及桥梁的建筑信息模型(building information model)数据。
在本发明的另一实现方式中，预测子系统还用于：基于模拟结果样本集进行训练，更新模拟模型。模拟结果样本集通过将实时桥梁车流量数据、常规桥梁车流量样本集和桥梁信息输入到三维模拟模型获得。由于三维模拟模型能够生成准确的样本，并且三维模拟模型自身也可以通过训练更新或改进，因此提高了模拟结果样本的灵活性或准确性。
在本发明的另一实现方式中，桥梁健康度异常指示数据包括桥梁结构故障指示数据和非桥梁结构故障指示数据。分析子系统用于：通过分析实时桥梁响应数据与预测桥梁响应 数据，得到初始桥梁结构故障指示数据和非桥梁结构故障指示数据。通过分析初始桥梁结构故障指示数据和获取的外部数据，得到桥梁结构故障指示数据。向呈现子系统上报桥梁健康度异常指示数据。由于通过分析初始桥梁结构故障指示数据和获取的外部数据，得到桥梁结构故障指示数据，因此提高了桥梁结构故障指示数据的可靠性。此外，通过分析实时桥梁响应数据与预测桥梁响应数据，得到非桥梁结构故障指示数据，提高了非桥梁结构故障指示数据的数据处理效率。
分析子系统可以包括异常检测模块和故障诊断模块。异常检测模块可以通过分析实时桥梁响应数据与预测桥梁响应数据，得到初始桥梁结构故障指示数据和非桥梁结构故障指示数据。例如，非桥梁结构故障指示数据可以直接上报至呈现子系统，以便向桥梁管理人员通知非桥梁结构故障。
作为一个示例，非桥梁结构故障指示数据包括传感器故障指示数据和车辆超重指示数据。由于传感器故障指示数据和车辆超重指示数据能够有效地指示非桥梁结构故障，进而能够提高排查非桥梁结构故障的效率。
应理解，非桥梁结构故障指示数据可以指示非桥梁结构故障的程度，桥梁管理人员可以根据非桥梁结构故障的程度判断是否需要人工再次排查或检修。
还应理解，初始桥梁结构故障指示数据和桥梁结构故障指示数据均可以指示非桥梁结构故障的程度。桥梁结构故障指示数据的可靠性或置信度高于初始桥梁结构故障指示数据。因此对初始桥梁结构故障指示数据结合外部数据进行分析处理，得到可靠性更高的桥梁结构故障指示数据。此外，桥梁管理人员可以根据桥梁结构故障指示数据的置信度或可靠性判断是否需要人工再次排查或检修。例如，桥梁结构故障指示数据可以指示桥梁的损坏部分或断裂位置。获取的外部数据可以包括来自交管局或其他数据源的交通事故记录、人工检测记录、天气信息记录等。
图5为本发明的另一实施例的分析子系统的示意性框图。如图所示，分析子系统2300包括异常检测模块5300和故障诊断模块5700。其中，异常检测模块5300接收数据采集子系统的实时桥梁响应数据5100和数字孪生子系统的预测桥梁响应数据5200，并且基于上述数据，判断传感器故障指示数据5400、超重车辆指示数据5500和初始桥梁结构故障指示数据5600，并且将传感器故障指示数据5400和超重车辆指示数据5500上报到管理子系统2400。故障诊断模块5700基于初始桥梁结构故障指示数据5600和外部数据5800，生成桥梁结构故障指示数据，并且上报到管理子系统2400。
此外，在其他示例中，异常检测模块5300也可以基于实时桥梁响应数据和预测桥梁响应数据，直接生成桥梁结构故障指示数据。
图6为本发明的另一实施例的数据采集子系统的示意性框图。如图所示，示出了一种用于监测系统的数据采集子系统6000，监测系统用于监测桥梁健康度，监测系统还包括预测子系统和分析子系统，数据采集子系统6000包括采集模块6100和发送模块6200。采集模块6100采集实时桥梁响应数据和实时桥梁车流量数据。发送模块6200向预测子系统发送实时桥梁车流量数据，并且向分析子系统发送实时桥梁响应数据，以便分析子系统对比分析预测桥梁响应数据和实时桥梁车流量数据，得到桥梁健康度异常指示数据。预测桥梁响应数据为预测子系统根据实时桥梁车流量数据生成。
由于监测系统包括的数据采集子系统、预测子系统、分析子系统和呈现子系统具有通用性，能够克服地理位置的限制，对多数桥梁进行统一监控。此外，由于对比分析所采用的实时桥梁响应数据来自数据采集子系统，并且所采用的预测桥梁响应数据通过预测子系统对实时桥梁车流量数据进行预测得到，因此，实时桥梁响应数据与预测桥梁响应数据能够有效地反应出实时桥梁响应数据和实时桥梁车流量数据之间的关联，从而对比分析上述两者得到桥梁健康度异常指示数据，提高了桥梁健康度监控的准确度。
图7为本发明的另一实施例的分析子系统的示意性框图。如图所示，示出了一种用于监测系统的分析子系统7000，用于监测桥梁健康度，监测系统还包括数据采集子系统和呈现子系统。分析子系统7000包括获取模块7100、分析模块7200和上报模块7300。获取模块7100从数据采集子系统获取其采集的实时桥梁响应数据，并且从预测子系统获取预测桥梁响应数据。预测桥梁响应数据基于从数据采集子系统获取的实时桥梁车流量数据生成。分析模块7200通过对比分析实时桥梁响应数据与预测桥梁响应数据，得到桥梁健康度异常指示数据。上报模块7300向呈现子系统上报桥梁健康度异常指示数据，以呈现桥梁健康度异常指示数据。
由于监测系统包括的数据采集子系统、预测子系统、分析子系统和呈现子系统具有通用性，能够克服地理位置的限制，对多数桥梁进行统一监控。此外，由于对比分析所采用的实时桥梁响应数据来自数据采集子系统，并且所采用的预测桥梁响应数据通过预测子系统对实时桥梁车流量数据进行预测得到，因此，实时桥梁响应数据与预测桥梁响应数据能够有效地反应出实时桥梁响应数据和实时桥梁车流量数据之间的关联，从而对比分析上述两者得到桥梁健康度异常指示数据，提高了桥梁健康度监控的准确度。
图8为本发明的另一实施例的数据采集子系统的监测方法的示意性流程图。如图所示，示出了一种监测方法，应用于监测系统的数据采集子系统。监测系统用于监测桥梁健康度，监测系统还包括预测子系统和分析子系统，该监测方法包括：
S810：采集实时桥梁响应数据和实时桥梁车流量数据；
S820：向预测子系统发送实时桥梁车流量数据，并且向分析子系统发送实时桥梁响应数据，以便分析子系统对比分析预测桥梁响应数据和实时桥梁车流量数据，得到桥梁健康度异常指示数据。预测桥梁响应数据为预测子系统根据实时桥梁车流量数据生成。
由于监测系统包括的数据采集子系统、预测子系统、分析子系统和呈现子系统具有通用性，能够克服地理位置的限制，对多数桥梁进行统一监控。此外，由于对比分析所采用的实时桥梁响应数据来自数据采集子系统，并且所采用的预测桥梁响应数据通过预测子系统对实时桥梁车流量数据进行预测得到，因此，实时桥梁响应数据与预测桥梁响应数据能够有效地反应出实时桥梁响应数据和实时桥梁车流量数据之间的关联，从而对比分析上述两者得到桥梁健康度异常指示数据，提高了桥梁健康度监控的准确度。
图9为本发明的另一实施例的分析子系统的监测方法的示意性流程图。图9示出了一种监测方法，应用于监测系统。监测系统用于监测桥梁健康度，监测系统还包括数据采集子系统和呈现子系统，该监测方法包括：
S910：从数据采集子系统获取其采集的实时桥梁响应数据，并且从预测子系统获取预测桥梁响应数据。预测桥梁响应数据基于从数据采集子系统获取的实时桥梁车流量数据生成；
S920：通过对比分析实时桥梁响应数据与预测桥梁响应数据，得到桥梁健康度异常指示数据；
S930：向呈现子系统上报桥梁健康度异常指示数据，以呈现桥梁健康度异常指示数据。
由于监测系统包括的数据采集子系统、预测子系统、分析子系统和呈现子系统具有通用性，能够克服地理位置的限制，对多数桥梁进行统一监控。此外，由于对比分析所采用的实时桥梁响应数据来自数据采集子系统，并且所采用的预测桥梁响应数据通过预测子系统对实时桥梁车流量数据进行预测得到，因此，实时桥梁响应数据与预测桥梁响应数据能够有效地反应出实时桥梁响应数据和实时桥梁车流量数据之间的关联，从而对比分析上述两者得到桥梁健康度异常指示数据，提高了桥梁健康度监控的准确度。
本发明实施例还提供了一种计算机程序产品，所述计算机程序产品被有形地存储在计算机可读介质上并且包括计算机可读指令，所述计算机可执行指令在被执行时使至少一个处理器执行上述的方法。
图10为本发明的另一实施例的电子设备结构示意图。该电子设备可以应用于监测系统的数据采集子系统，例如，一个或多个服务器。图10的电子设备包括一个或多个处理器1010、通信接口1020、存储器1030和通信总线1040、以及一个或多个程序。一个或多个处理器1010、通信接口1020、存储器1030通过通信总线1040完成相互间的通信，一 个或多个程序被存储在存储器1030中，并且被配置为由一个或多个处理器1010执行，一个或多个程序用于执行：采集实时桥梁响应数据和实时桥梁车流量数据；向预测子系统发送实时桥梁车流量数据，并且向分析子系统发送实时桥梁响应数据，以便分析子系统对比分析预测桥梁响应数据和实时桥梁车流量数据，得到桥梁健康度异常指示数据。预测桥梁响应数据为预测子系统根据实时桥梁车流量数据生成。
图11为本发明的另一实施例的电子设备结构示意图。该电子设备可以应用于监测系统的分析子系统，例如，一个或多个服务器。图11的电子设备包括一个或多个处理器1110、通信接口1120、存储器1130和通信总线1140、以及一个或多个程序。一个或多个处理器1110、通信接口1120、存储器1130通过通信总线1140完成相互间的通信，一个或多个程序被存储在存储器1030中，并且被配置为由一个或多个处理器1010执行，一个或多个程序用于执行：从数据采集子系统获取其采集的实时桥梁响应数据，并且从预测子系统获取预测桥梁响应数据。预测桥梁响应数据基于从数据采集子系统获取的实时桥梁车流量数据生成；通过对比分析实时桥梁响应数据与预测桥梁响应数据，得到桥梁健康度异常指示数据；向呈现子系统上报桥梁健康度异常指示数据，以呈现桥梁健康度异常指示数据。
需要说明的是，本发明的计算机存储介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读介质例如可以但不限于是电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储介质(RAM)、只读存储介质(ROM)、可擦式可编程只读存储介质(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储介质(CD-ROM)、光存储介质件、磁存储介质件、或者上述的任意合适的组合。在本发明中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本发明中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输配置为由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。
应当理解，虽然本发明是按照各个实施例描述的，但并非每个实施例仅包含一个独立的技术方案，说明书的这种叙述方式仅仅是为清楚起见，本领域技术人员应当将说明书作 为一个整体，各实施例中的技术方案也可以经适当组合，形成本领域技术人员可以理解的其他实施方式。
以上仅为本发明实施例示意性的具体实施方式，并非用以限定本发明实施例的范围。任何本领域的技术人员，在不脱离本发明实施例的构思和原则的前提下所作的等同变化、修改与结合，均应属于本发明实施例保护的范围。

Claims (16)

  1. 一种监测方法，用于监测桥梁健康度，所述监测方法包括：
    采集实时桥梁响应数据，并且采集实时桥梁车流量数据；
    根据所述实时桥梁车流量数据，生成预测桥梁响应数据；
    通过对比分析所述实时桥梁响应数据与所述预测桥梁响应数据，得到桥梁健康度异常指示数据；以及
    呈现所述桥梁健康度异常指示数据。
  2. 根据权利要求1所述的方法，其中，所述采集实时桥梁响应数据，包括：
    读取设置在桥梁上的多个传感器的实时感测数据，并且对所述感测数据进行降噪处理，得到所述实时桥梁响应数据。
  3. 根据权利要求1所述的方法，其中，所述实时桥梁车流量数据包括设置在桥梁上的多个摄像头的车辆观测数据，其中，所述采集实时桥梁车流量数据，包括：
    通过视觉识别模块，采集所述车辆观测数据，其中，所述视觉识别模块通过从所述多个摄像头读取所述车辆观测数据。
  4. 根据权利要求3所述的方法，其中，所述实时桥梁车流量数据还包括车重数据，所述车辆观测数据包括车辆管理数据，其中，所述采集实时桥梁车流量数据，还包括：
    利用所述车辆管理数据访问车辆管理数据库，得到所述车重数据。
  5. 根据权利要求1所述的方法，其中，所述根据所述实时桥梁车流量数据，生成预测桥梁响应数据，包括：
    通过向预先训练的模拟模型输入所述实时桥梁车流量数据，得到所述预测桥梁响应数据，
    其中，所述方法还包括：将在所述模拟模型的训练期间采集的所述实时桥梁响应数据与所述实时桥梁车流量数据作为模型校准样本集进行训练，以更新所述模拟模型。
  6. 根据权利要求5所述的方法，其中，所述方法还包括：基于模拟结果样本集进行训练，更新所述模拟模型，
    其中，所述模拟结果样本集通过将所述实时桥梁车流量数据、常规桥梁车流量样本集和桥梁信息输入到三维模拟模型获得。
  7. 根据权利要求1所述的方法，其中，所述桥梁健康度异常指示数据包括桥梁结构故障指示数据和非桥梁结构故障指示数据，
    其中，所述通过对比分析所述实时桥梁响应数据与所述预测桥梁响应数据，得到桥梁 健康度异常指示数据，包括：
    通过分析所述实时桥梁响应数据与所述预测桥梁响应数据，得到初始桥梁结构故障指示数据和非桥梁结构故障指示数据；并且
    通过分析所述初始桥梁结构故障指示数据和获取的外部数据，得到所述桥梁结构故障指示数据；
    向所述呈现子系统上报所述桥梁健康度异常指示数据。
  8. 根据权利要求7所述的方法，其中，所述非桥梁结构故障指示数据包括传感器故障指示数据和车辆超重指示数据。
  9. 一种采集方法，应用于监测系统的数据采集子系统，所述监测系统用于监测桥梁健康度，所述监测系统还包括预测子系统和分析子系统，所述方法包括：
    采集实时桥梁响应数据和实时桥梁车流量数据；
    向所述预测子系统发送所述实时桥梁车流量数据，并且向所述分析子系统发送所述实时桥梁响应数据，以便所述分析子系统对比分析预测桥梁响应数据和所述实时桥梁车流量数据，得到桥梁健康度异常指示数据，其中，所述预测桥梁响应数据为所述预测子系统根据所述实时桥梁车流量数据生成。
  10. 一种分析方法，应用于监测系统的分析子系统，所述监测系统用于监测桥梁健康度，所述监测系统还包括数据采集子系统和呈现子系统，所述方法包括：
    从所述数据采集子系统获取其采集的实时桥梁响应数据，并且从所述预测子系统获取所述预测桥梁响应数据，其中，所述预测桥梁响应数据基于从所述数据采集子系统获取的实时桥梁车流量数据生成；
    通过对比分析所述实时桥梁响应数据与所述预测桥梁响应数据，得到桥梁健康度异常指示数据；
    向呈现子系统上报所述桥梁健康度异常指示数据，以呈现所述桥梁健康度异常指示数据。
  11. 一种用于监测系统的数据采集子系统，所述监测系统用于监测桥梁健康度，所述监测系统还包括预测子系统和分析子系统，所述数据采集子系统包括：一个或多个处理器、通信接口、存储器和通信总线、以及一个或多个程序，其中，一个或多个处理器、通信接口、存储器通过通信总线完成相互间的通信，一个或多个程序被存储在存储器中，并且被 配置为由一个或多个处理器执行，以执行权利要求9所述的方法。
  12. 一种用于监测系统的分析子系统，所述监测系统用于监测桥梁健康度，所述监测系统还包括数据采集子系统和呈现子系统，所述分析子系统包括：一个或多个处理器、通信接口、存储器和通信总线、以及一个或多个程序，其中，一个或多个处理器、通信接口、存储器通过通信总线完成相互间的通信，一个或多个程序被存储在存储器中，并且被配置为由一个或多个处理器执行，以执行权利要求10所述的方法。
  13. 一种监测系统，用于监测桥梁健康度，所述监测系统包括：
    数据采集子系统，用于：采集实时桥梁响应数据和实时桥梁车流量数据；
    预测子系统，用于：从所述数据采集子系统获取所述实时桥梁车流量数据，并且根据所述实时桥梁车流量数据，生成预测桥梁响应数据；
    分析子系统，用于：从所述数据采集子系统获取所述实时桥梁响应数据，并且从所述预测子系统获取所述预测桥梁响应数据；和
    通过对比分析所述实时桥梁响应数据与所述预测桥梁响应数据，得到桥梁健康度异常指示数据；以及
    呈现子系统，用于：从所述分析子系统获取所述桥梁健康度异常指示数据，并且呈现所述桥梁健康度异常指示数据。
  14. 一种存储介质，所述存储介质包括存储的程序，其中，在所述程序运行时控制包括所述存储介质的设备执行权利要求1-10所述的方法。
  15. 一种计算机程序，包括计算机可执行指令，所述计算机执行指令在被执行时使至少一个处理器执行根据权利要求1-10所述的方法。
  16. 一种计算机程序产品，所述计算机程序产品被有形地存储在计算机可读介质上并且包括计算机可读指令，所述计算机可执行指令在被执行时使至少一个处理器执行根据权利要求1-10所述的方法。
PCT/CN2020/115343 2020-09-15 2020-09-15 监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品 WO2022056677A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/115343 WO2022056677A1 (zh) 2020-09-15 2020-09-15 监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/115343 WO2022056677A1 (zh) 2020-09-15 2020-09-15 监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品

Publications (1)

Publication Number Publication Date
WO2022056677A1 true WO2022056677A1 (zh) 2022-03-24

Family

ID=80777481

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/115343 WO2022056677A1 (zh) 2020-09-15 2020-09-15 监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品

Country Status (1)

Country Link
WO (1) WO2022056677A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118133215A (zh) * 2024-05-10 2024-06-04 兰州朗青交通科技有限公司 一种基于边缘计算的桥梁结构健康监测方法及装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004044116A (ja) * 2002-07-09 2004-02-12 Mitsubishi Heavy Ind Ltd 橋梁の余寿命予測方法
CN101615341A (zh) * 2009-07-17 2009-12-30 重庆交通大学 一种基于交通流控制的桥梁智能监控方法
JP2017020795A (ja) * 2015-07-07 2017-01-26 公益財団法人鉄道総合技術研究所 橋梁動的応答評価方法
CN109002622A (zh) * 2018-07-26 2018-12-14 广州大学 一种随机车流作用下大跨径桥梁总体荷载响应估算方法
CN110636134A (zh) * 2019-09-29 2019-12-31 江西建设职业技术学院 一种城市道路损伤监测维护方法及系统
CN111444252A (zh) * 2020-03-25 2020-07-24 重庆邮电大学 一种桥梁监测系统
CN111486893A (zh) * 2020-04-07 2020-08-04 中铁西南科学研究院有限公司 一种桥梁结构健康监测与预警系统及预警方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004044116A (ja) * 2002-07-09 2004-02-12 Mitsubishi Heavy Ind Ltd 橋梁の余寿命予測方法
CN101615341A (zh) * 2009-07-17 2009-12-30 重庆交通大学 一种基于交通流控制的桥梁智能监控方法
JP2017020795A (ja) * 2015-07-07 2017-01-26 公益財団法人鉄道総合技術研究所 橋梁動的応答評価方法
CN109002622A (zh) * 2018-07-26 2018-12-14 广州大学 一种随机车流作用下大跨径桥梁总体荷载响应估算方法
CN110636134A (zh) * 2019-09-29 2019-12-31 江西建设职业技术学院 一种城市道路损伤监测维护方法及系统
CN111444252A (zh) * 2020-03-25 2020-07-24 重庆邮电大学 一种桥梁监测系统
CN111486893A (zh) * 2020-04-07 2020-08-04 中铁西南科学研究院有限公司 一种桥梁结构健康监测与预警系统及预警方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118133215A (zh) * 2024-05-10 2024-06-04 兰州朗青交通科技有限公司 一种基于边缘计算的桥梁结构健康监测方法及装置

Similar Documents

Publication Publication Date Title
Khan et al. Integration of structural health monitoring and intelligent transportation systems for bridge condition assessment: Current status and future direction
CN110926523A (zh) 一种复杂恶劣条件下高速铁路桥梁安全感知与预警系统
CN114005278B (zh) 一种高速公路基础设施群智能监测与预警系统及方法
JP2012168152A (ja) 構造物安全性の分析方法
KR101903879B1 (ko) 구조물 지진 안전성 평가 장치 및 구조물 지진 안전성 평가 방법
KR20210085168A (ko) 머신러닝 기반 건축 구조물 고유 진동값 학습을 통한 안전 진단 시스템 및 방법
CN117629549B (zh) 一种桥梁建筑健康监测与安全预警系统
CN112488477A (zh) 高速公路应急管理系统及方法
CN115146230A (zh) 一种古建筑健康监测系统、方法及设备
JP2019079303A (ja) 道路設備点検システムおよび道路設備点検方法、ならびにそれに使用されるサーバ
CN114662619A (zh) 基于多源数据融合的桥梁监测系统
CN113503912A (zh) 一种城市轨道交通土建设施健康状态实时监控系统
CN114684217A (zh) 一种轨道交通健康监测系统及方法
WO2022056677A1 (zh) 监测、采集、分析系统及其方法、设备、存储介质、程序和程序产品
CN115761487A (zh) 一种基于机器视觉的中小跨径桥梁振动特性快速识别方法
CN113935384B (zh) 一种信号自适应分解和识别的桥梁健康监测方法及系统
CN114722480A (zh) 房屋建筑结构的安全监测系统及其建立、监测方法
CN112016739B (zh) 故障检测方法、装置、电子设备及存储介质
Zhou et al. Investigation on Monitoring System for Pantograph and Catenary Based on Condition‐Based Recognition of Pantograph
CN116754022A (zh) 电缆隧道的在线检测应急预警方法及系统
CN113267217B (zh) 一种桥群监测系统以及桥群监测方法
Fraser Development and implementation of an integrated framework for structural health monitoring
US20230024104A1 (en) Identification of false transformer humming using machine learning
CN115561163A (zh) 基于物联网通讯的桥梁结构监控方法
RU2308692C1 (ru) Способ мониторинга мостового перехода в процессе его эксплуатации и устройство для его реализации

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20953538

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20953538

Country of ref document: EP

Kind code of ref document: A1