Bridge health monitoring system based on wireless sensing technology
By deploying wireless sensor nodes on the bridge, dynamic response information of vehicles in motion is acquired and preprocessed in real time. Data is then filtered and compressed using a data evaluation model, which solves the problem of data noise interference in the bridge health monitoring system when vehicles are in motion, and improves data accuracy and system stability.
Patent Information
- Application Number
- CN202411077300.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing bridge health monitoring systems based on wireless sensing technology are subject to dynamic loads and vibration interference when vehicles are in motion, which increases data noise, affects data accuracy and reliability, and reduces the real-time performance and stability of the system.
By deploying multiple wireless sensor nodes on the bridge, dynamic response information of vehicles in motion is acquired in real time and preprocessed. An evaluation model is constructed using the data acquisition activity coefficient and signal effectiveness index to filter out necessary information for processing and compress and store unnecessary information.
It improves the accuracy and reliability of data, ensures the real-time performance and stability of data processing, reduces the frequency of system maintenance, and lowers operating costs.
Smart Images

Figure CN118999664A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of bridge health monitoring, and in particular to a bridge health monitoring system based on wireless sensor technology. Background Art
[0002] Bridge health monitoring is a system that uses advanced technology to monitor and evaluate the structure and functional status of bridges in real time. Its core is to obtain various data generated by bridges during operation, such as stress, strain, vibration, temperature and humidity, through sensor networks, and timely discover potential structural problems through data analysis. The main reason for monitoring bridge health is that bridges are key infrastructure for transportation, and their structural safety and normal function are directly related to public safety and economic operation. Regular and real-time health monitoring can detect and prevent structural damage early, avoid major accidents, extend the service life of bridges, and significantly reduce maintenance costs. At the same time, through accurate data analysis and prediction, bridge maintenance and management strategies can be optimized, resource utilization efficiency can be improved, and efficient and safe operation of transportation networks can be ensured. The significance of this system is not only to protect public safety, but also to promote the intelligence and modernization of infrastructure management.
[0003] The bridge health monitoring system based on wireless sensor technology relies on the development of wireless sensor networks (WSN). These sensors are installed on key parts of the bridge, such as the main beam, piers and slings, to collect data such as stress, strain, vibration, temperature and humidity. The wireless sensor nodes have a low-power design and can extend their working time through self-powered systems such as solar energy, and use wireless communication technology to achieve real-time data transmission. The central processing unit (CPU) aggregates and analyzes the collected data, identifies structural anomalies or potential problems in a timely manner through advanced data processing and machine learning algorithms, and provides visual monitoring results and early warning information through the user interface. Traditional bridge monitoring relies on wired systems, which are not only complex and costly to install, but also difficult to maintain. The application of wireless sensor technology has greatly simplified the deployment of the monitoring system, improved monitoring efficiency and flexibility, and reduced manual intervention and maintenance costs. In addition, the combination of big data and artificial intelligence technology enables the bridge health monitoring system to perform structural health assessment and fault prediction more accurately, providing strong technical support for the safe management and maintenance of bridges. Through this technical means, bridge management departments can carry out preventive maintenance more efficiently, avoid major accidents, and ensure the long-term safety and reliable operation of bridges.
[0004] The specific working process of the existing bridge health monitoring system based on wireless sensor technology includes the following steps: First, wireless sensor nodes are installed at key parts of the bridge, which are responsible for real-time collection of bridge stress, strain, vibration, temperature and humidity data; second, the sensor nodes transmit the collected data to the central processing unit (CPU) through wireless communication technology; after receiving the data, the central processing unit performs preliminary data cleaning and sorting, and evaluates the health status of the bridge through advanced data processing and analysis algorithms (including big data analysis and machine learning technology); then, the system visualizes the analysis results through the user interface, including structural health score, damage location and severity, and triggers the alarm system when abnormal conditions are detected, notifying relevant managers through SMS, email or other means; finally, the monitoring data and analysis results will be stored in the database for comparative analysis of historical data and long-term trend prediction, providing a scientific basis for bridge maintenance and management. The whole process forms a closed-loop system, from data collection, transmission, processing, analysis to feedback, to ensure the comprehensiveness and real-time nature of bridge health monitoring.
[0005] The prior art has the following deficiencies:
[0006] Due to the dynamic loads and vibrations generated when vehicles travel on bridges, the wireless sensor nodes installed on the bridges will be subject to a lot of noise interference when collecting data, resulting in a large amount of useless information mixed in the sensor data, increasing the high-frequency fluctuations and randomness of the data, and affecting the accuracy and reliability of the data. This interference complicates the signal filtering and data denoising process, making it difficult to distinguish between normal dynamic loads and structural anomalies, thereby increasing the difficulty of data analysis and anomaly detection and reducing the real-time and stability of the system. In addition, frequent vibrations affect the durability of sensors and increase the frequency of system maintenance and calibration. Existing technologies cannot effectively deal with these dynamic interferences, resulting in significant deficiencies in the accuracy, real-time and stability of bridge health monitoring systems.
[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0008] The purpose of the present invention is to provide a bridge health monitoring system based on wireless sensor technology to solve the problems in the above-mentioned background technology.
[0009] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a bridge health monitoring system based on wireless sensor technology, comprising a dynamic response acquisition module, a state data extraction module, a data acquisition and evaluation module, a bridge data acquisition module, a structural response analysis module and a health status evaluation module;
[0010] The dynamic response acquisition module deploys multiple wireless sensor nodes on the bridge to acquire the dynamic response information of the vehicle when it is driving on the bridge in real time and performs preprocessing after acquisition;
[0011] A state data extraction module extracts data acquisition state information from the dynamic response information obtained by the wireless sensor node when the vehicle is traveling on the bridge after preprocessing;
[0012] The data collection and evaluation module analyzes the extracted data collection status information and evaluates whether the wireless sensor nodes are collecting bridge health data when the vehicle is driving on the bridge;
[0013] The bridge data acquisition module acquires all bridge health data collected by the wireless sensor nodes when the vehicle is traveling on the bridge when the evaluation result is that the wireless sensor nodes are collecting bridge health data when the vehicle is traveling on the bridge;
[0014] The structural response analysis module extracts important information from all bridge health data collected by wireless sensor nodes, analyzes them, evaluates the necessity of each bridge health data, and divides each bridge health data collected by wireless sensor nodes into necessary information and non-essential information according to the evaluation results;
[0015] The health status assessment module extracts the health data of each bridge from the necessary information, processes it, and assesses the health status of the bridge. At the same time, it compresses and stores non-essential information for subsequent needs.
[0016] Preferably, the extracted data collection status information includes a data collection activity coefficient and a signal validity index. After extraction, the data collection activity coefficient and the signal validity index are used to construct a data evaluation model to generate an evaluation coefficient, and the generated evaluation coefficient is compared with a pre-set evaluation coefficient threshold to evaluate whether the wireless sensor node is collecting bridge health data when the vehicle is traveling on the bridge.
[0017] Preferably, the acquisition logic of the data acquisition activity coefficient and the signal validity index is as follows:
[0018] Obtain activity records and signal transmission records of wireless sensor nodes when vehicles travel on bridges;
[0019] The total activation time and the number of transmitted data packets of the wireless sensor nodes during the vehicle driving period in the activity records of the wireless sensor nodes are extracted. After extraction, the total activation time and the number of transmitted data packets of the wireless sensor nodes during the vehicle driving period in the activity records of the wireless sensor nodes are calibrated as T activ e and N data ;
[0020] The total time that the vehicle travels on the bridge and the number of packets expected to be transmitted by the wireless sensor node are obtained. After obtaining, the total time that the vehicle travels on the bridge and the number of packets expected to be transmitted by the wireless sensor node are calibrated as T total and N expected ;
[0021] Calculate the data collection activity coefficient. The specific calculation formula is as follows:
[0022]
[0023] Where DCAC is the data acquisition activity coefficient;
[0024] Extract all signal strength values in the signal transmission records of the wireless sensor nodes. After extraction, calibrate all signal strength values in the signal transmission records of the wireless sensor nodes as S i , S i represents the i-th signal strength reading, i represents the number of all signal strength values in the signal transmission record of the wireless sensor node, i=1, 2, 3, ..., d, d is a positive integer;
[0025] Calculate the average value of all signal strength values. The specific calculation formula is as follows:
[0026]
[0027] In the formula, S avg is the average value of all signal strength values;
[0028] Extract the number of data packets successfully transmitted by the sensor node and the total number of data packets attempted to be transmitted during the vehicle driving on the bridge from the signal transmission record of the wireless sensor node, and calibrate the number of data packets successfully transmitted by the sensor node and the total number of data packets attempted to be transmitted during the vehicle driving on the bridge as N success and N total ;
[0029] Calculate the data packet transmission success rate of the sensor node during the vehicle driving on the bridge. The specific calculation formula is as follows:
[0030]
[0031] In the formula, R success is the data packet transmission success rate of the sensor node during the vehicle driving on the bridge;
[0032] Calculate the signal effectiveness index. The specific calculation formula is as follows:
[0033] SVI=S avg *R success
[0034] Where SVI is the signal validity index.
[0035] Preferably, the data collection activity coefficient DCAC and the signal validity index SVI are used to construct a data evaluation model, and an evaluation coefficient PG is generated by weighted summation, and the generated evaluation coefficient PG is compared with a preset evaluation coefficient threshold PG. yz Compare and evaluate whether the wireless sensor nodes are collecting bridge health data when the vehicle is driving on the bridge. The specific analysis is as follows:
[0036] If PG≤PG yz ,The wireless sensor nodes are not collecting bridge health data when the vehicle is driving on the bridge;
[0037] If PG>PG yz ,The wireless sensor nodes collect bridge health data when the vehicle is driving on the bridge.
[0038] Preferably, important information of the data in all bridge health data collected by the wireless sensor nodes is extracted, including the data correlation coefficient and the data change rate index. After the information is obtained, the data correlation coefficient and the data change rate index of each bridge health data are calibrated as DCC m and DRCI m , DCC m Represents the data correlation coefficient of the mth bridge health data, DRCI m The data change rate index of the mth bridge health data is represented, m=1, 2, 3, ..., g, g is a positive integer, a necessity analysis model is constructed for the data correlation coefficient and the data change rate index of each bridge health data, and the necessary coefficient of each bridge health data is generated. The necessary coefficient of each bridge health data is compared with a preset necessary coefficient threshold, the necessity of each bridge health data is evaluated, and the bridge health data collected by the wireless sensor node is divided into necessary information and non-essential information according to the evaluation result.
[0039] Preferably, the logic for obtaining the data correlation coefficient and data change rate index of each bridge health data is as follows:
[0040] Extract all the actual data values of each bridge health data collected by the wireless sensor nodes during the time period when the vehicle is traveling on the bridge, and calibrate all the actual data values of each bridge health data collected by the wireless sensor nodes during the time period when the vehicle is traveling on the bridge as represents the nth actual data value of the mth bridge health data collected by the wireless sensor node during the time period when the vehicle travels on the bridge, n=1, 2, 3, ..., k, k is a positive integer;
[0041] Extract all historical data values of each bridge health data collected by the wireless sensor node in the corresponding time period from the historical data records, and calibrate all historical data values of each bridge health data collected by the wireless sensor node in the corresponding time period as It means extracting the nth historical data value of the mth bridge health data collected by the wireless sensor node in the corresponding time period from the historical data record;
[0042] Calculate the average value of all actual data values of each bridge health data collected by the wireless sensor nodes According to the formula:
[0043] Calculate the average value Y of all historical data values of each bridge health data collected by the wireless sensor node m , according to the formula:
[0044] Calculate the covariance between all actual data values and all historical data values of each bridge health data collected by the wireless sensor node according to the formula:
[0045]
[0046] Where Cov(X, Y) is the covariance between all actual data values and all historical data values of the mth bridge health data collected by the wireless sensor node;
[0047] Calculate the standard deviation of all actual data values of each bridge health data collected by the wireless sensor node According to the formula:
[0048] Calculate the standard deviation of all historical data values of each bridge health data collected by the wireless sensor node According to the formula:
[0049] Calculate the data correlation coefficient of each bridge health data. The specific calculation formula is:
[0050]
[0051] In the formula, DCC m is the data correlation coefficient of the mth bridge health data;
[0052] Calculate the adjacent actual data values of each bridge health data collected by the wireless sensor nodes during the time period when the vehicle is traveling on the bridge and The rate of change between According to the formula: Δt is the adjacent actual data value and The data sampling time interval between
[0053] Calculate the data change rate index of each bridge health data. The specific calculation formula is as follows:
[0054]
[0055] Where, DRCI m is the data change rate index of the mth bridge health data.
[0056] Preferably, the data correlation coefficient DCC of each bridge health data m and data rate of change index DRCI m Construct a necessity analysis model and generate the necessary coefficient NC of each bridge health data through weighted summation m , the necessary coefficients NC of each bridge health data m The required coefficient threshold NC is set in advance y Compare and evaluate the necessity of each bridge health data, and divide the bridge health data collected by the wireless sensor node into necessary information and non-essential information according to the evaluation results. The specific division process is as follows:
[0057] If NC m ≤NC yz , the necessity of the bridge health data is low, and the bridge health data is classified as non-essential information;
[0058] If NC m >NC yz , the necessity of the bridge health data is high, and the bridge health data is classified as necessary information.
[0059] Preferably, the health data of each bridge classified as necessary information is extracted, and the extracted necessary information is processed by a preset data processing algorithm, the processing steps include data cleaning, anomaly detection, trend analysis and feature extraction, and the health status of the bridge is evaluated based on the processing results to generate a health status report; at the same time, the health data of each bridge classified as non-essential information is compressed, and the compression steps include data downsampling, redundancy removal and coding compression, and the compressed non-essential information is stored in a designated database for subsequent call and analysis when needed.
[0060] In the above technical solution, the technical effects and advantages provided by the present invention are:
[0061] 1. The present invention deploys multiple wireless sensor nodes on the bridge to obtain the dynamic response information of the vehicle when it is traveling on the bridge in real time, and performs preprocessing after acquisition, which significantly improves the accuracy and reliability of the data. The state data extraction module can extract the data acquisition state information from the dynamic response information, and analyze and evaluate whether the wireless sensor nodes are collecting bridge health data when the vehicle is traveling on the bridge through the data acquisition evaluation module, thereby ensuring the validity of the data. In particular, by introducing the data acquisition activity coefficient and the signal validity index to construct a data evaluation model, it is possible to effectively filter noise interference and ensure the extraction of useful information in the sensor data, thereby improving the accuracy and reliability of the data and solving the problem that the existing technology is difficult to deal with the dynamic interference caused by vehicle driving.
[0062] 2. By introducing a structural response analysis module and a health status assessment module, the present invention can process and analyze the bridge health data collected by wireless sensor nodes in real time. During the data collection process, the system can evaluate and obtain the importance of bridge health data in real time, generate necessary coefficients through weighted summation, and compare them with preset thresholds to quickly evaluate the necessity of the data. Necessary information will be processed first, and non-essential information will be compressed and stored to reduce the burden on the system. This process not only improves the real-time performance of data processing, but also ensures the stability of data transmission. Even in the case of high-frequency fluctuations and large amounts of data transmission, the system can still operate efficiently and stably.
[0063] 3. The present invention adopts a preset data processing algorithm, including data cleaning, anomaly detection, trend analysis and feature extraction, to perform fine processing on necessary information, so as to accurately evaluate the health status of the bridge. At the same time, by downsampling, removing redundancy and encoding compression of non-essential information, the storage space occupied is reduced and the data storage cost is reduced. In addition, the data acquisition and evaluation module can identify the effective data acquisition status of the sensor node under the influence of dynamic loads and vibrations, reduce the need for frequent maintenance and calibration, and improve the durability of the sensor nodes, thereby optimizing the maintenance cost and overall operating cost of the system. Through these technical means, the present invention significantly improves the accuracy, real-time and stability of the bridge health monitoring system, and overcomes the shortcomings of the prior art. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0065] Figure 1This is a module schematic diagram of a bridge health monitoring system based on wireless sensing technology in the present invention. DETAILED DESCRIPTION
[0066] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.
[0067] The present invention provides Figure 1 A bridge health monitoring system based on wireless sensor technology is shown, comprising a dynamic response acquisition module, a state data extraction module, a data acquisition and evaluation module, a bridge data acquisition module, a structural response analysis module and a health status evaluation module;
[0068] The dynamic response acquisition module deploys multiple wireless sensor nodes on the bridge to acquire the dynamic response information of the vehicle when it is driving on the bridge in real time and performs preprocessing after acquisition;
[0069] The dynamic response acquisition module plays a vital role in the bridge health monitoring system. By deploying multiple wireless sensor nodes on the bridge, various dynamic response information generated by vehicles driving on the bridge can be acquired in real time. This module is not only responsible for real-time data collection, but also includes preliminary processing of these data to ensure the accuracy and reliability of subsequent analysis. The preprocessing step can clean and organize the data to meet the requirements of the analysis algorithm and provide a high-quality data foundation.
[0070] The specific methods of deploying multiple wireless sensor nodes on a bridge include: First, conduct a detailed analysis of the bridge structure to identify key monitoring points, such as the bridge's supporting piers, main beams, suspension cables and cables. According to the bridge design drawings and structural characteristics, the wireless sensor nodes are firmly installed in these key locations to ensure that the sensors can fully cover the stress conditions and dynamic responses of the bridge. The installation method can use strong glue, bolt fixing and other methods to ensure the stability of the sensor when the vehicle is driving. The sensor nodes are connected through wireless networks (such as ZigBee, LoRa or Wi-Fi) to form a stable wireless sensor network to ensure real-time transmission and synchronization of data.
[0071] Real-time acquisition of dynamic response information of vehicles traveling on bridges is achieved through wireless sensor nodes deployed at key locations of bridges. These nodes continuously monitor and record parameters such as stress, strain, vibration, and displacement of the bridge. When a vehicle passes through the bridge, the sensor nodes capture these dynamic responses and transmit the data to the central processing unit through a wireless network. The specific information obtained includes stress and strain (such as tension and compression) of the bridge structure, vibration frequency and amplitude, displacement changes (such as sinking and lifting of the bridge deck), and acceleration changes. This information not only reflects the dynamic behavior of the bridge when vehicles are traveling, but also includes the instantaneous impact characteristics when vehicles pass through, which is used for subsequent data processing and evaluation.
[0072] The specific method of data preprocessing includes the following steps: first, remove noise and outliers through data cleaning to ensure the purity of the data; then, normalize the data to ensure the consistency and comparability of data from different types of sensors; next, perform time alignment to ensure the synchronization of data collected by sensor nodes in time; finally, apply filtering technology (such as low-pass filtering, high-pass filtering or wavelet transform) to remove high-frequency noise and environmental interference. The reason for preprocessing is to improve data quality and reliability, ensure that the subsequent analysis process is not disturbed by noise and outliers, and accurately evaluate the health status of the bridge. The preprocessed data is more accurate and meets the requirements of the analysis algorithm, which improves the accuracy and stability of the algorithm and ensures the effectiveness of the bridge health monitoring system. These steps can all be implemented through software algorithms to ensure the automation and efficiency of data processing.
[0073] A state data extraction module extracts data acquisition state information from the dynamic response information obtained by the wireless sensor node when the vehicle is traveling on the bridge after preprocessing;
[0074] The main task of the state data extraction module is to extract data acquisition state information from the preprocessed dynamic response information. This can be achieved in the following ways: First, monitor the activity logs of sensor nodes during vehicle driving, including the node's on and off status, data packet sending and receiving records, etc. By analyzing these log information, the activity level and data transmission status of sensor nodes in a specific time period can be identified. Secondly, network performance indicators such as signal strength indicator (RSSI) value and packet arrival rate (PDR) are used to evaluate the signal quality and data transmission success rate of sensor nodes during vehicle driving. The specific extraction method includes: parsing the sensor node log file to extract timestamp, node status and data packet information; using RSSI value and PDR indicators, by setting thresholds and filtering rules, to filter out records with frequent data acquisition activities and good signal quality during vehicle driving. Finally, this information is aggregated and statistically analyzed to generate data acquisition state information. These steps can be automatically processed by software algorithms to ensure the efficiency and accuracy of the extraction process.
[0075] The data collection and evaluation module analyzes the extracted data collection status information and evaluates whether the wireless sensor nodes are collecting bridge health data when the vehicle is driving on the bridge;
[0076] In this embodiment, the extracted data collection status information includes a data collection activity coefficient and a signal validity index. After extraction, the data collection activity coefficient and the signal validity index are used to construct a data evaluation model to generate an evaluation coefficient. The generated evaluation coefficient is compared with a pre-set evaluation coefficient threshold to evaluate whether the wireless sensor node is collecting bridge health data when the vehicle is traveling on the bridge.
[0077] In this embodiment, the acquisition logic of the data collection activity coefficient and the signal validity index is as follows:
[0078] Obtain activity records and signal transmission records of wireless sensor nodes when vehicles travel on bridges;
[0079] To obtain the activity records and signal transmission records of wireless sensor nodes when the vehicle is traveling on the bridge, it can be achieved in the following ways: First, the real-time log recording function needs to be configured inside the sensor node to record the various activity states and signal transmission conditions of the sensor node. When the vehicle is traveling on the bridge, the sensor node will continue to record its activation time, signal strength, number of data packet transmissions and other information, and these records are stored based on the timestamp. The specific acquisition method includes: the sensor node regularly packages the log records and transmits them to the central processing unit through a wireless network (such as ZigBee, LoRa or Wi-Fi). After the central processing unit receives the log package, it parses and stores it. When processing these log records, the software can align and filter the data by timestamp to extract the relevant activity records and signal transmission records during the vehicle's driving. In this way, the system can completely obtain and save the activity and transmission data of the sensor nodes, providing basic data for subsequent analysis and evaluation.
[0080] The total activation time and the number of transmitted data packets of the wireless sensor nodes during the vehicle driving period in the activity records of the wireless sensor nodes are extracted. After extraction, the total activation time and the number of transmitted data packets of the wireless sensor nodes during the vehicle driving period in the activity records of the wireless sensor nodes are calibrated as T active and N data ;
[0081] Extracting the total activation time and number of transmitted packets from the activity records of wireless sensor nodes can be achieved in the following ways: First, when the sensor node records its activity status, it will contain information such as timestamps, activation status, and packet transmission events. The software can parse these log records to filter out records related to the vehicle driving time period. The specific extraction method includes: sorting all log records by time, identifying the time window during vehicle driving, and accumulating the total activation time of the sensor node in the time window by checking the timestamp and activation status; at the same time, counting the packet transmission events recorded in the time period, and calculating the total number of packets transmitted by the sensor node during this period. These steps can be automated through software algorithms to ensure the accuracy and efficiency of data extraction.
[0082] The total activation time of the wireless sensor node during vehicle travel refers to the cumulative time that the sensor node is active during the vehicle's passage through the bridge, which means that the sensor node is monitoring and recording the dynamic response information of the bridge. Specifically, the total activation time is the sum of all time periods from the start of data recording to the end of data recording by the sensor node. The number of transmitted packets refers to the total number of packets successfully sent by the sensor node during the vehicle's travel, including all packets of the bridge's dynamic response information. These packets are transmitted to the central processing unit via the wireless network for subsequent analysis and evaluation.active reflects the working time of the sensor node during vehicle driving, while N data It reflects the amount of data transmitted by the sensor node during this period. The combination of the two can evaluate the data collection activities of the sensor node during vehicle driving.
[0083] The total time that the vehicle travels on the bridge and the number of packets expected to be transmitted by the wireless sensor node are obtained. After obtaining, the total time that the vehicle travels on the bridge and the number of packets expected to be transmitted by the wireless sensor node are calibrated as T total and N expected ;
[0084] Extracting the total time a vehicle travels on a bridge and the number of packets expected to be transmitted by the wireless sensor nodes can be achieved in the following ways: First, the timestamps of vehicles entering and leaving the bridge are recorded by sensors or cameras installed at the entrance and exit of the bridge. The software can calculate the total time T that the vehicle travels on the bridge by comparing the timestamps of the entrance and exit. total At the same time, according to the working frequency of the sensor node and the total time the vehicle travels on the bridge, the expected number of transmission data packets N is calculated. expected The specific method includes: reading the vehicle's entry and exit timestamps, calculating the time difference between the two timestamps, and obtaining T total ; According to the preset data transmission frequency of the sensor node (such as once per second), T total Multiply by the transmission frequency to get N expected Software algorithms can automate these steps, ensuring the accuracy of data extraction and calculations.
[0085] The total time T that the vehicle travels on the bridge total It refers to the time interval from the entry point of the vehicle into the bridge to the exit point of the bridge. Specifically, this time reflects the duration of the entire process of the vehicle traveling on the bridge, usually in seconds or minutes. By setting up timestamp recording devices at the entrance and exit of the bridge, the software can accurately capture and calculate the total travel time of the vehicle. The number of packets N expected to be transmitted by the wireless sensor node expected It is calculated based on the operating frequency of the sensor node and the total time the vehicle travels on the bridge. Assuming that the sensor node transmits one data packet per second, the expected number of data packets is the total travel time multiplied by the transmission frequency. For example, if the vehicle travels on the bridge for 60 seconds and the sensor node transmits one data packet per second, the expected number of data packets is 60. This parameter is used to evaluate the consistency of the actual data transmission of the sensor node during the vehicle's travel with the expected data transmission.
[0086] Calculate the data collection activity coefficient. The specific calculation formula is as follows:
[0087]
[0088] Where DCAC is the data acquisition activity coefficient;
[0089] The size of the data collection activity coefficient directly reflects the activity and data transmission of the sensor node during the vehicle driving period. The larger the value, the longer the total activation time of the sensor node during the vehicle driving period and the closer the number of transmitted data packets is to the expected number, which means that the sensor node is effectively collecting bridge health data. If the data collection activity coefficient is high (close to 1), it can be evaluated that the sensor node is indeed collecting bridge health data when the vehicle is driving; conversely, if the data collection activity coefficient is low, it means that the sensor node is activated for a short time during this period or the number of transmitted data packets is insufficient, and the bridge health data may not be effectively collected. Therefore, the size of the data collection activity coefficient has a direct positive correlation with whether the sensor node is collecting bridge health data. The higher the coefficient, the higher the reliability of data collection.
[0090] Extract all signal strength values in the signal transmission records of the wireless sensor nodes. After extraction, calibrate all signal strength values in the signal transmission records of the wireless sensor nodes as S i , S i represents the i-th signal strength reading, i represents the number of all signal strength values in the signal transmission record of the wireless sensor node, i=1, 2, 3, ..., d, d is a positive integer;
[0091] To extract all signal strength data from the signal transmission records of wireless sensor nodes, the following methods can be used: First, the sensor node records the signal strength value of each data transmission internally. These records contain timestamps and signal strength values. The software can parse these signal transmission record files to extract the signal strength data of each record. The specific extraction method includes: reading the log file or database of the sensor node, sorting by timestamp, extracting the signal strength value one by one, and marking it as S i By traversing all the signal strength data in the record file, we extract and mark them as S i , where i is the record number and d is the total number of records. These operations can be implemented through automated software algorithms to ensure the efficiency and accuracy of the data extraction process.
[0092] All signal strength data S i It refers to the signal strength value recorded by the sensor node each time the vehicle transmits data during driving. Specifically, S iIndicates the signal strength at the i-th data transmission, i is the number of the signal strength record, ranging from 1 to d, where d is the total number of transmissions recorded by the sensor node during the period. The signal strength data reflects the wireless communication quality of the sensor node at each data transmission. A higher signal strength generally indicates better data transmission quality and lower packet loss rate. By collecting and analyzing these signal strength data, the communication performance of the sensor node during vehicle driving can be evaluated, and the signal effectiveness index can be further calculated to evaluate whether the sensor node is effectively collecting and transmitting bridge health data.
[0093] Calculate the average value of all signal strength values. The specific calculation formula is as follows:
[0094]
[0095] In the formula, S avg is the average value of all signal strength values;
[0096] Extract the number of data packets successfully transmitted by the sensor node and the total number of data packets attempted to be transmitted during the vehicle driving on the bridge from the signal transmission record of the wireless sensor node, and calibrate the number of data packets successfully transmitted by the sensor node and the total number of data packets attempted to be transmitted during the vehicle driving on the bridge as N success and N total ;
[0097] To extract the number of data packets successfully transmitted by the sensor node and the total number of data packets attempted to be transmitted from the signal transmission record of the wireless sensor node during the vehicle's driving on the bridge, it can be achieved in the following way: First, the sensor node records the results of each data packet transmission in its log file or internal database, including successfully transmitted data packets and failed data packets. These records usually contain information such as timestamp, data packet ID, and transmission status (successful or failed). The specific extraction method includes: reading the log file or database record of the sensor node, filtering out the records during the vehicle's driving on the bridge according to the timestamp, and counting the number of successfully transmitted data packets N by checking the transmission status field. success and the total number of packets N that are attempted to be transmitted total These operations can be automated through software algorithms to ensure the efficiency and accuracy of the extraction process.
[0098] The number of data packets successfully transmitted by the sensor node during the vehicle driving on the bridge is N success It refers to the total number of data packets successfully sent by the sensor node to the receiver during the time period. These successfully transmitted data packets represent the effective data transmission of the sensor node during the specified time period. totalIt refers to the total number of all data packets that the sensor node attempts to send in the same time period, including those that are successfully transmitted and those that fail to be transmitted. These quantities can be used to calculate the packet transmission success rate, that is, the ratio of successfully transmitted data packets to attempted transmission data packets, thereby evaluating the data transmission performance of the sensor node during vehicle driving. success and N total The combined use of can accurately reflect the communication quality and reliability of sensor nodes during vehicle driving, and provide basic data for calculating the signal effectiveness index.
[0099] Calculate the data packet transmission success rate of the sensor node during the vehicle driving on the bridge. The specific calculation formula is as follows:
[0100]
[0101] In the formula, R success is the data packet transmission success rate of the sensor node during the vehicle driving on the bridge;
[0102] Calculate the signal effectiveness index. The specific calculation formula is as follows:
[0103] SVI=S avR *R success
[0104] Where SVI is the signal validity index.
[0105] The size of the signal validity index directly reflects the data transmission quality and reliability of the sensor node during the vehicle driving period. The larger the value, the higher the signal strength of the sensor node during the period and the higher the data packet transmission success rate, which means that the sensor node is effectively collecting and transmitting bridge health data. If the signal validity index is high, it can be evaluated that the sensor node is indeed collecting bridge health data when the vehicle is driving; conversely, if the signal validity index is low, it means that the sensor node has a weak signal strength or a high data transmission failure rate during this period, and may not be able to effectively collect bridge health data. Therefore, the size of the signal validity index has a direct positive correlation with whether the sensor node is collecting bridge health data. The higher the index, the higher the reliability and effectiveness of data collection.
[0106] In this embodiment, the data collection activity coefficient DCAC and the signal validity index SVI are used to construct a data evaluation model, and an evaluation coefficient PG is generated by weighted summation, and the generated evaluation coefficient PG is compared with a preset evaluation coefficient threshold PG. yz Compare and evaluate whether the wireless sensor nodes are collecting bridge health data when the vehicle is driving on the bridge. The specific analysis is as follows:
[0107] If PG≤PG yz,The wireless sensor nodes are not collecting bridge health data when the vehicle is driving on the bridge;
[0108] When the evaluation coefficient is less than or equal to the pre-set evaluation coefficient threshold, this indicates that the sensor node's data collection activities during the vehicle driving period are not active enough, or the data transmission quality is not up to standard. This means that the sensor node may not effectively collect bridge health data during this period. Therefore, the system will determine that the sensor data during this period is invalid and will not perform subsequent data acquisition and analysis steps. This evaluation result helps save computing resources and storage space and avoid processing invalid data.
[0109] If PG>PG yz ,The wireless sensor nodes collect bridge health data when the vehicle is driving on the bridge;
[0110] When the evaluation coefficient is greater than the pre-set evaluation coefficient threshold, it means that the data collection activity of the sensor node during the vehicle driving period is active enough and the data transmission quality meets the requirements. This indicates that the sensor node effectively collected bridge health data during the period. Therefore, the system will judge that the sensor data during this period is valid and continue with the subsequent data acquisition and analysis steps.
[0111] The determination of the evaluation coefficient threshold is achieved through historical data analysis and machine learning algorithms, as follows: First, collect a large number of historical data of sensor nodes under different conditions, including dynamic response data of vehicles driving on bridges, data collection activity coefficients, and signal validity indexes; then, ensure the quality and consistency of the data through data cleaning and preprocessing; next, use supervised learning algorithms such as logistic regression, support vector machines, or random forests to train these historical data and build a model that can predict whether data collection is effective based on the input data collection activity coefficients and signal validity indexes; during the model training process, use cross-validation methods to select the best model parameters and evaluation thresholds; finally, determine an evaluation coefficient threshold that can accurately distinguish between effective and invalid data collection through model evaluation and optimization. This process can be fully automated through software to ensure the accuracy and dynamic adaptability of the threshold.
[0112] To construct a data evaluation model with the data acquisition activity coefficient DCAC and the signal validity index SVI and generate an evaluation coefficient PG by weighted summation, it is first necessary to determine the weight coefficients ω1 and ω2 of the two parameters. These weight coefficients are set based on application scenarios and expert experience to ensure that the influence of the two parameters on the evaluation results is reasonable. In the specific implementation process, DCAC reflects the activity and data transmission of the sensor node during the vehicle driving period, and SVI reflects the data transmission quality and reliability of the sensor node during the same period. By multiplying these two parameters by their corresponding weight coefficients and then adding the results, a comprehensive evaluation coefficient PG can be obtained. The formula is as follows: PG = ω1*DCAC + ω2*SVI. This comprehensive evaluation coefficient combines the activity and transmission quality of the sensor node, and can fully reflect the data acquisition performance of the sensor node during the vehicle driving period. By calculating PG and comparing it with the preset threshold, it is possible to accurately evaluate whether the sensor node is effectively collecting bridge health data.
[0113] The bridge data acquisition module acquires all bridge health data collected by the wireless sensor nodes when the vehicle is traveling on the bridge when the evaluation result is that the wireless sensor nodes are collecting bridge health data when the vehicle is traveling on the bridge;
[0114] To obtain all the bridge health data collected by the wireless sensor nodes when the vehicle is traveling on the bridge, it can be achieved in the following ways: First, the sensor nodes will record and store the dynamic response information of the bridge in real time during the vehicle driving, such as stress, strain, vibration and displacement data. These data are usually stored in the internal memory of the sensor node in the form of time series. The software can communicate with the sensor node through a wireless network (such as ZigBee, LoRa or Wi-Fi) and send a data request command. After receiving the data request command, the sensor node will package all the bridge health data stored in it and transmit it to the central processing unit (CPU) or data server through the wireless network. The specific acquisition method includes: the software sends data requests at regular intervals, parses and confirms the received data packets, ensures that the data is complete and correct, and stores the data in the central processing unit or data server for subsequent processing. In this way, all the bridge health data collected by the wireless sensor nodes during the vehicle driving on the bridge can be efficiently acquired and centrally managed, providing basic data for subsequent analysis and evaluation.
[0115] The structural response analysis module extracts important information from all bridge health data collected by wireless sensor nodes, analyzes them, evaluates the necessity of each bridge health data, and divides each bridge health data collected by wireless sensor nodes into necessary information and non-essential information according to the evaluation results;
[0116] In this embodiment, important information of the data in all bridge health data collected by the wireless sensor nodes is extracted, including the data correlation coefficient and the data change rate index. After acquisition, the data correlation coefficient and the data change rate index of each bridge health data are calibrated as DCC m and DRCI m , dCC m Represents the data correlation coefficient of the mth bridge health data, DRCI m The data change rate index of the mth bridge health data is represented, m=1, 2, 3, ..., g, g is a positive integer, a necessity analysis model is constructed for the data correlation coefficient and the data change rate index of each bridge health data, and the necessary coefficient of each bridge health data is generated. The necessary coefficient of each bridge health data is compared with a preset necessary coefficient threshold, the necessity of each bridge health data is evaluated, and the bridge health data collected by the wireless sensor node is divided into necessary information and non-essential information according to the evaluation result.
[0117] In this embodiment, the logic for obtaining the data correlation coefficient and data change rate index of each bridge health data is as follows:
[0118] Extract all the actual data values of each bridge health data collected by the wireless sensor nodes during the time period when the vehicle is traveling on the bridge, and calibrate all the actual data values of each bridge health data collected by the wireless sensor nodes during the time period when the vehicle is traveling on the bridge as represents the nth actual data value of the mth bridge health data collected by the wireless sensor node during the time period when the vehicle travels on the bridge, n=1, 2, 3, ..., k, k is a positive integer;
[0119] Extracting all the actual data values of each bridge health data collected by the wireless sensor node during the time period when the vehicle is traveling on the bridge can be achieved in the following way: First, the wireless sensor node monitors the various bridge health data during the vehicle driving on the bridge in real time and stores these data in the internal memory of the node. These data include specific values such as stress, strain, vibration, displacement, etc. The software establishes a connection with the sensor node through a wireless communication network (such as ZigBee, LoRa or Wi-Fi) and sends a data request command. After receiving the request command, the sensor node packages the stored actual data values and transmits them to the central processing unit (CPU) or data server through the wireless communication network. After receiving the data packet, the software parses and extracts the various bridge health data therein and sorts them by timestamp to ensure the time continuity and integrity of the data. In this way, the system can efficiently obtain all the actual data values collected by the wireless sensor node during the vehicle driving on the bridge, providing basic data for subsequent analysis and processing.
[0120] Extract all historical data values of each bridge health data collected by the wireless sensor node in the corresponding time period from the historical data records, and calibrate all historical data values of each bridge health data collected by the wireless sensor node in the corresponding time period as It means extracting the nth historical data value of the mth bridge health data collected by the wireless sensor node in the corresponding time period from the historical data record;
[0121] Extracting all historical data values of each bridge health data collected by the wireless sensor node in the corresponding time period from the historical data record can be achieved in the following ways: First, the bridge health monitoring system will regularly store all data collected by the sensor node in the central database, and these data are indexed and stored according to the timestamp to ensure the orderliness and retrievability of the data. The software can extract the historical data in a specific time period by querying the database. The specific method includes: the software generates the corresponding timestamp range query conditions according to the time period when the vehicle travels on the bridge. Then, by executing the database query statement, all bridge health data collected by the wireless sensor node in the corresponding time period are retrieved from the central database. These data include specific values such as stress, strain, vibration, displacement, etc. The query results are arranged in chronological order, and the software parses and extracts the historical data values of each bridge health data to ensure the consistency of the time period with the current actual data. In this way, the system can accurately obtain the historical data in the corresponding time period and provide reliable benchmark data for subsequent data correlation analysis.
[0122] Calculate the average value of all actual data values of each bridge health data collected by the wireless sensor nodes According to the formula:
[0123] Calculate the average value of all historical data values of each bridge health data collected by the wireless sensor node According to the formula:
[0124] Calculate the covariance between all actual data values and all historical data values of each bridge health data collected by the wireless sensor node according to the formula:
[0125]
[0126] Where Cov(X, Y) is the covariance between all actual data values and all historical data values of the mth bridge health data collected by the wireless sensor node;
[0127] Calculate the standard deviation of all actual data values of each bridge health data collected by the wireless sensor node According to the formula:
[0128] Calculate the standard deviation of all historical data values of each bridge health data collected by the wireless sensor node According to the formula:
[0129] Calculate the data correlation coefficient of each bridge health data. The specific calculation formula is:
[0130]
[0131] In the formula, DCC m is the data correlation coefficient of the mth bridge health data;
[0132] In calculating the data correlation coefficient DCC of the mth bridge health data m The various calculation formulas involved are to quantify the linear relationship between the current actual data value and the historical data value. First, calculate the mean of the actual data value and the historical data value and The purpose of this calculation is to obtain the central tendency of the data and calculate the deviation of each data point from the mean. Next, the covariance Cov(X, Y) is calculated to evaluate the direction and degree to which the two variables deviate from their means at the same time. The larger the covariance, the stronger the positive correlation between the two variables. and It is used to quantify the dispersion of data. The larger the standard deviation, the more dispersed the data. Finally, the data correlation coefficient DCC m The covariance is divided by the product of the standard deviations of the two variables to standardize the results so that the value is between -1 and 1, indicating the strength and direction of the correlation between the data. This standardization step ensures that the results are dimensionless and comparable, thereby accurately reflecting the linear correlation between the current actual data and historical data, and then evaluating the importance of the data.
[0133] Data correlation coefficient DCC of the mth bridge health data m The size of DCC directly reflects the linear correlation between the current actual data value and the historical data value. m The higher the value, the more consistent the trend and fluctuation of current data are with historical data, the higher the importance and credibility of the data are, and therefore it is evaluated as data with higher necessity. On the contrary, DCC m The lower the value, the weaker the correlation between the current data and the historical data, the lower the importance and credibility of the data, and therefore it is evaluated as data with lower necessity. In this way, the system can effectively evaluate the necessity of each bridge health data and ensure that the data analysis and processing process focuses on those data with higher relevance and importance.
[0134] Calculate the adjacent actual data values of each bridge health data collected by the wireless sensor nodes during the time period when the vehicle is traveling on the bridge and The rate of change between According to the formula: Δt is the adjacent actual data value and The data sampling time interval between
[0135] Calculate the data change rate index of each bridge health data. The specific calculation formula is as follows:
[0136]
[0137] Where, DRCI m is the data change rate index of the mth bridge health data.
[0138] In calculating the data change rate index DRCI of the mth bridge health data m The various calculation formulas involved are to quantify the speed and magnitude of data changes over time. First, calculate the adjacent actual data values and The rate of change between The purpose is to evaluate the degree of change of the data within each sampling time interval Δt, which reflects the dynamic characteristics and fluctuations of the data. Then, the average value of the absolute values of all change rates is calculated to obtain an overall change rate index. This average value DRCI m It can comprehensively reflect the changes in data over the entire time period. m This indicates that the data changes frequently and dramatically, which may indicate abnormal or significant changes in the bridge structure, so the data is more important and necessary; a lower DRCI m Indicates that the data changes slowly and steadily, which may reflect that the structural state is relatively normal. Through these calculation steps, the system can accurately evaluate the rate of change of data and thus determine the importance and necessity of the data.
[0139] Data change rate index DRCI of the mth bridge health data m The size of DRCI directly reflects the speed and amplitude of data changes over time. m The higher the value, the more frequent and dramatic the data changes are, which may indicate that there are abnormalities or significant changes in the bridge structure, and therefore it is assessed as data with higher necessity. On the contrary, DRCI m The lower the value, the slower and more stable the data change, which may reflect that the bridge structure is in a relatively normal state, and is therefore considered to be less necessary. mThe system can effectively identify and focus on bridge health data that have changed significantly and may be of higher importance and necessity.
[0140] In this embodiment, the data correlation coefficient DCC of each bridge health data is m and data rate of change index DRCI m Construct a necessity analysis model and generate the necessary coefficient NC of each bridge health data through weighted summation m , the necessary coefficients NC of each bridge health data m The required coefficient threshold NC is set in advance yz Compare and evaluate the necessity of each bridge health data, and divide the bridge health data collected by the wireless sensor node into necessary information and non-essential information according to the evaluation results. The specific division process is as follows:
[0141] If NC m ≤NC yz , the necessity of the bridge health data is low, and the bridge health data is classified as non-essential information;
[0142] When the necessary coefficient NC of the mth bridge health data m Less than or equal to the preset necessary coefficient threshold NC yz This indicates that the weighted sum of the correlation coefficient and the rate of change index of the data is not high, which means that the data has a low correlation with the historical data, and the rate of change is not significant, and the importance and credibility of the data are low. Therefore, the bridge health data is evaluated as data with low necessity, and the system will classify it as non-essential information. Although this non-essential information is retained in the system, it will be compressed and stored to reduce the storage and computing burden of the system, and detailed analysis will only be performed when needed to optimize resource utilization.
[0143] If NC m >NC yz , the necessity of the bridge health data is high, and the bridge health data is classified as necessary information;
[0144] When the necessary coefficient NC of the mth bridge health data m Greater than the preset necessary coefficient threshold NC yz This indicates that the weighted sum of the correlation coefficient and the rate of change index of the data is high, which means that the data is highly correlated with historical data and has a significant rate of change, and the data is highly important and reliable. Therefore, the bridge health data is evaluated as highly necessary data, and the system will classify it as necessary information. This necessary information will be analyzed and processed in the subsequent health status assessment to identify and monitor potential abnormalities and significant changes in the bridge structure to ensure the safety and stability of the bridge.
[0145] To calculate the data correlation coefficient DCC of each bridge health data m and data rate of change index DRCI m Construct a necessity analysis model and generate the necessary coefficient NC of each bridge health data through weighted summation m First, the DCC of each bridge health data needs to be calculated separately m and DRCI m Next, two weight coefficients ω3 and ω4 are set to balance DCC m and DRCI m The degree of influence in the necessity assessment. Then, DCC is calculated by weighted summation formula. m and DRCI m Combined, the necessary coefficient NC for the mth bridge health data is generated m , the specific formula is as follows: NC m =ω3*DCC m +ω4*DRCI m , where the values of ω3 and ω4 are set according to actual needs and experience to ensure the accuracy and reliability of the evaluation results. This process combines the relevance and change rate of the data and fully reflects the importance and necessity of the data.
[0146] The health status assessment module extracts the health data of each bridge from the necessary information, processes it, and assesses the health status of the bridge. At the same time, it compresses and stores non-essential information for subsequent needs.
[0147] In this embodiment, the health data of each bridge classified as necessary information is extracted, and the extracted necessary information is processed by a preset data processing algorithm. The processing steps include data cleaning, anomaly detection, trend analysis and feature extraction. The health status of the bridge is evaluated based on the processing results and a health status report is generated. At the same time, the health data of each bridge classified as non-essential information is compressed. The compression steps include data downsampling, redundancy removal and coding compression. The compressed non-essential information is stored in a designated database for subsequent call and analysis when needed.
[0148] After extracting the health data of each bridge classified as necessary information, the software is used to implement data cleaning, anomaly detection, trend analysis and feature extraction: data cleaning improves data quality by removing missing values and correcting erroneous values; anomaly detection identifies and marks abnormal data points through statistical analysis and machine learning algorithms (such as isolation forests or density-based spatial clustering); trend analysis identifies long-term trends and seasonal patterns through time series analysis (such as ARIMA models); feature extraction extracts key feature parameters through signal processing techniques (such as Fourier transform and wavelet transform). The processed data is used to evaluate the health status of the bridge and generate reports. At the same time, the data classified as non-essential information is compressed, the data volume is reduced by using data downsampling methods, duplicate data is removed by de-redundancy technology, and the data is compressed using coding compression algorithms (such as Huffman coding or LZ77). The compressed non-essential information is stored in the database, and the software stores and subsequently manages the data by calling the database API interface.
[0149] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0150] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0151] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0152] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0153] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0154] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0155] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0156] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A bridge health monitoring system based on wireless sensing technology, characterized in that: It includes dynamic response acquisition module, status data extraction module, data acquisition and evaluation module, bridge data acquisition module, structural response analysis module and health status evaluation module; The dynamic response acquisition module deploys multiple wireless sensor nodes on the bridge to acquire the dynamic response information of the vehicle when it is driving on the bridge in real time and performs preprocessing after acquisition; A state data extraction module extracts data acquisition state information from the dynamic response information obtained by the wireless sensor node when the vehicle is traveling on the bridge after preprocessing; The data collection and evaluation module analyzes the extracted data collection status information and evaluates whether the wireless sensor nodes are collecting bridge health data when the vehicle is driving on the bridge; The bridge data acquisition module acquires all bridge health data collected by the wireless sensor nodes when the vehicle is traveling on the bridge when the evaluation result is that the wireless sensor nodes are collecting bridge health data when the vehicle is traveling on the bridge; The structural response analysis module extracts important information from all bridge health data collected by wireless sensor nodes, analyzes them, evaluates the necessity of each bridge health data, and divides each bridge health data collected by wireless sensor nodes into necessary information and non-essential information according to the evaluation results; The health status assessment module extracts the health data of each bridge from the necessary information, processes it, and assesses the health status of the bridge. At the same time, it compresses and stores non-essential information for subsequent needs.
2. A bridge health monitoring system based on wireless sensing technology according to claim 1, characterized in that: The extracted data collection status information includes the data collection activity coefficient and the signal validity index. After extraction, the data collection activity coefficient and the signal validity index are used to construct a data evaluation model to generate an evaluation coefficient. The generated evaluation coefficient is compared with the pre-set evaluation coefficient threshold to evaluate whether the wireless sensor nodes are collecting bridge health data when the vehicle is driving on the bridge.
3. A bridge health monitoring system based on wireless sensing technology according to claim 2, characterized in that: The acquisition logic of the data acquisition activity coefficient and the signal validity index is as follows: Obtain activity records and signal transmission records of wireless sensor nodes when vehicles travel on bridges; The total activation time and the number of transmitted data packets of the wireless sensor nodes during the driving of the vehicle are extracted from the activity records of the wireless sensor nodes. After extraction, the total activation time and the number of transmitted data packets of the wireless sensor nodes during the driving of the vehicle are calibrated as T active and N data ; The total time that the vehicle travels on the bridge and the number of packets expected to be transmitted by the wireless sensor node are obtained. After obtaining, the total time that the vehicle travels on the bridge and the number of packets expected to be transmitted by the wireless sensor node are calibrated as T total and N expected ; Calculate the data collection activity coefficient. The specific calculation formula is as follows: Where DCAC is the data acquisition activity coefficient; Extract all signal strength values in the signal transmission records of the wireless sensor nodes. After extraction, calibrate all signal strength values in the signal transmission records of the wireless sensor nodes as S i , S i represents the i-th signal strength reading, i represents the number of all signal strength values in the signal transmission record of the wireless sensor node, i=1, 2, 3, ..., d, d is a positive integer; Calculate the average value of all signal strength values. The specific calculation formula is as follows: In the formula, S avg is the average value of all signal strength values; Extract the number of data packets successfully transmitted by the sensor node and the total number of data packets attempted to be transmitted during the vehicle driving on the bridge from the signal transmission record of the wireless sensor node, and calibrate the number of data packets successfully transmitted by the sensor node and the total number of data packets attempted to be transmitted during the vehicle driving on the bridge as N success and N total ; Calculate the data packet transmission success rate of the sensor node during the vehicle driving on the bridge. The specific calculation formula is as follows: In the formula, R success is the data packet transmission success rate of the sensor node during the vehicle driving on the bridge; Calculate the signal effectiveness index. The specific calculation formula is as follows: ALL=S avg *R success Where SVI is the signal validity index.
4. A bridge health monitoring system based on wireless sensing technology according to claim 3, characterized in that: The data collection activity coefficient DCAC and the signal validity index SVI are used to construct a data evaluation model, and an evaluation coefficient PG is generated by weighted summation. The generated evaluation coefficient PG is compared with the pre-set evaluation coefficient threshold PG. yz Compare and evaluate whether the wireless sensor nodes are collecting bridge health data when the vehicle is driving on the bridge. The specific analysis is as follows: If PG≤PG yz ,The wireless sensor nodes are not collecting bridge health data when the vehicle is driving on the bridge; If PG>PG yz ,The wireless sensor nodes collect bridge health data when the vehicle is driving on the bridge.
5. The bridge health monitoring system based on wireless sensing technology according to claim 1 is characterized in that: Extract important information from all bridge health data collected by wireless sensor nodes, including data correlation coefficient and data change rate index. After acquisition, the data correlation coefficient and data change rate index of each bridge health data are calibrated as DCC m and DRCI m , DCC m Represents the data correlation coefficient of the mth bridge health data, DRCI m The data change rate index of the mth bridge health data is represented, m=1, 2, 3, ..., g, g is a positive integer, a necessity analysis model is constructed for the data correlation coefficient and the data change rate index of each bridge health data, and the necessary coefficient of each bridge health data is generated. The necessary coefficient of each bridge health data is compared with a preset necessary coefficient threshold, the necessity of each bridge health data is evaluated, and the bridge health data collected by the wireless sensor node is divided into necessary information and non-essential information according to the evaluation result.
6. A bridge health monitoring system based on wireless sensing technology according to claim 5, characterized in that: The logic for obtaining the data correlation coefficient and data change rate index of each bridge health data is as follows: Extract all the actual data values of each bridge health data collected by the wireless sensor nodes during the time period when the vehicle is traveling on the bridge, and calibrate all the actual data values of each bridge health data collected by the wireless sensor nodes during the time period when the vehicle is traveling on the bridge as represents the nth actual data value of the mth bridge health data collected by the wireless sensor node during the time period when the vehicle travels on the bridge, n=1, 2, 3, ..., k, k is a positive integer; Extract all historical data values of each bridge health data collected by the wireless sensor node in the corresponding time period from the historical data records, and calibrate all historical data values of each bridge health data collected by the wireless sensor node in the corresponding time period as It means extracting the nth historical data value of the mth bridge health data collected by the wireless sensor node in the corresponding time period from the historical data record; Calculate the average value of all actual data values of each bridge health data collected by the wireless sensor nodes According to the formula: Calculate the average value of all historical data values of each bridge health data collected by the wireless sensor node According to the formula: Calculate the covariance between all actual data values and all historical data values of each bridge health data collected by the wireless sensor node according to the formula: Where Cov(X, Y) is the covariance between all actual data values and all historical data values of the mth bridge health data collected by the wireless sensor node; Calculate the standard deviation of all actual data values of each bridge health data collected by the wireless sensor node According to the formula: Calculate the standard deviation of all historical data values of each bridge health data collected by the wireless sensor node According to the formula: Calculate the data correlation coefficient of each bridge health data. The specific calculation formula is: In the formula, DCC m is the data correlation coefficient of the mth bridge health data; Calculate the adjacent actual data values of each bridge health data collected by the wireless sensor nodes during the time period when the vehicle is traveling on the bridge and The rate of change between According to the formula: Δt is the adjacent actual data value and The data sampling time interval between Calculate the data change rate index of each bridge health data. The specific calculation formula is as follows: Where, DRCI m is the data change rate index of the mth bridge health data.
7. A bridge health monitoring system based on wireless sensing technology according to claim 6, characterized in that: Data correlation coefficient DCC for each bridge health data m and data rate of change index DRCI m Construct a necessity analysis model and generate the necessary coefficient NC of each bridge health data through weighted summation m , the necessary coefficients NC of each bridge health data m The required coefficient threshold NC is set in advance y Compare and evaluate the necessity of each bridge health data, and divide the bridge health data collected by the wireless sensor node into necessary information and non-essential information according to the evaluation results. The specific division process is as follows: If NC m ≤NC yz , the necessity of the bridge health data is low, and the bridge health data is classified as non-essential information; If NC m >NC yz , the necessity of the bridge health data is high, and the bridge health data is classified as necessary information.
8. The bridge health monitoring system based on wireless sensing technology according to claim 1 is characterized in that: The health data of each bridge classified as necessary information is extracted, and the extracted necessary information is processed through a preset data processing algorithm. The processing steps include data cleaning, anomaly detection, trend analysis and feature extraction. The health status of the bridge is evaluated based on the processing results and a health status report is generated. At the same time, the health data of each bridge classified as non-essential information is compressed. The compression steps include data downsampling, redundancy removal and encoding compression. The compressed non-essential information is stored in a specified database for subsequent call and analysis when needed.
