Bridge detection method and system based on Internet of Things and big data

Abstract

The invention discloses a bridge detection method and system based on Internet of Things and big data, and the method comprises the steps: regularly obtaining bridge image data and bridge vibration data, and carrying out the preprocessing of the bridge image data and the bridge vibration data, and obtaining first monitoring data; performing state evaluation on the bridge according to the first monitoring data to obtain a bridge evaluation report, acquiring bridge real-time vibration data as second monitoring data according to the bridge evaluation report, and analyzing the second monitoring data to obtain a bridge health report; and generating a bridge use decision and a maintenance suggestion according to the bridge health report. Through secondary analysis and processing of the data, a comprehensive and complete bridge health report is obtained; the generated use decision can play a role in warning and early warning, for example, for a use decision in a dangerous state, a manager can be prompted to adjust the use of the bridge in time, cope with the crisis of the bridge in time, make up defects in time, and avoid danger caused by update lag.

Description

Technical Field

[0001] The present invention belongs to the technical field of Internet of Things and big data, and specifically relates to a bridge detection method and system based on Internet of Things and big data. Background Art

[0002] With the acceleration of urbanization and the continuous development of transportation networks, bridges, as important transportation infrastructure, bear huge traffic pressure. Especially in modern highway and railway networks, bridges are key nodes, and their safety and stability directly affect traffic flow and public safety. Therefore, regular inspection and maintenance of bridges are the core content to ensure the safe operation of transportation facilities.

[0003] Traditional bridge inspection methods usually rely on manual inspections or regular special inspections, which have certain limitations. First, manual inspections are inefficient and difficult to detect potential hidden dangers in a timely manner, especially for bridges with heavy traffic or complex geographical conditions. Manual inspections may have the risk of omissions or misjudgments. Second, traditional inspections usually rely on professionals to conduct visual inspections of bridges, which are easily affected by the experience and subjective factors of the inspectors, resulting in large differences in the reliability and accuracy of the results. Finally, the frequency of regular inspections is limited by the availability of personnel and resources, and it is impossible to achieve all-weather, all-round real-time monitoring of bridges.

[0004] With the rapid development of Internet of Things technology and the increasing maturity of big data analysis technology, more and more industries are beginning to apply these advanced technologies to improve the efficiency and accuracy of monitoring. Internet of Things technology can realize real-time networking of equipment, allowing various sensors to continuously monitor the health of bridge structures and transmit data to the monitoring platform in real time through the network. Big data technology can conduct in-depth analysis of the massive data transmitted back, providing more accurate bridge health assessment and maintenance prediction.

[0005] However, although there are some bridge monitoring methods based on IoT technology on the market, most systems still have problems such as insufficient data integration, untimely information processing, and imperfect maintenance and management solutions. Existing systems usually lack intelligent analysis and real-time warning functions for sensor data, and cannot effectively diagnose the structural health status of bridges, nor can they provide targeted real-time maintenance recommendations. Therefore, how to improve the accuracy and efficiency of bridge monitoring through innovative technical means, reduce the cost of manual inspections, and provide scientific maintenance solutions has become an urgent problem to be solved in the industry. Summary of the invention

[0006] The purpose of the present invention is to provide a bridge detection method and system based on the Internet of Things and big data to solve the problems of lack of intelligent analysis and real-time early warning functions of sensor data, inability to effectively diagnose the structural health status of the bridge, and difficulty in providing targeted real-time maintenance suggestions.

[0007] To achieve the above object, the present invention provides the following technical solution: a bridge detection method and system based on the Internet of Things and big data, comprising:

[0008] regularly acquiring bridge image data and bridge vibration data, and preprocessing the bridge image data and bridge vibration data to obtain first monitoring data;

[0009] According to the first monitoring data, a condition assessment is performed on the bridge to obtain a bridge assessment report, and according to the bridge assessment report, real-time vibration data of the bridge is obtained as second monitoring data, and the second monitoring data is analyzed to obtain a bridge health report;

[0010] Based on the bridge health report, make bridge usage decisions and maintenance recommendations.

[0011] Preferably, the preprocessing of the bridge image data comprises the following steps:

[0012] Obtaining manually input bridge image data with original image pixels, digitizing, geometrically transforming, normalizing, smoothing, restoring and enhancing the bridge image data to obtain an image set;

[0013] Based on the image set, manually input numbers are obtained one by one;

[0014] The image sets are automatically classified and stored according to the numbers.

[0015] Preferably, the bridge vibration data preprocessing comprises the following steps:

[0016] Obtain bridge vibration data, and perform data cleaning and data conversion on the bridge vibration data to obtain standard data;

[0017] Standard data storage is associated with the image set and stored.

[0018] Preferably, the bridge condition assessment comprises the following steps:

[0019] Acquire bridge image data, identify images with cracks, and obtain crack images;

[0020] Input the crack image into the crack analysis model to obtain the crack width and depth;

[0021] Based on the data of crack width and depth, the preset health threshold is compared to obtain a bridge assessment report, which includes a health status and a warning status.

[0022] Preferably, the analyzing the second monitoring data comprises the following steps:

[0023] Obtain bridge assessment report and obtain assessment information;

[0024] According to the evaluation information, real-time vibration data is input, and the real-time vibration data is intercepted multiple times to generate second monitoring data;

[0025] The second monitoring data is obtained, and a bridge health report is output based on a preset prediction model.

[0026] Preferably, the generation of bridge use decisions and maintenance recommendations requires the following operations:

[0027] Get a bridge health report;

[0028] Input the bridge health report into the preset decision template, obtain the response characteristics, get the bridge use decision, and obtain the corresponding maintenance recommendations based on the use decision;

[0029] Output bridge usage decisions and maintenance recommendations.

[0030] A bridge detection system based on the Internet of Things and big data, comprising:

[0031] Data acquisition module: used to regularly acquire manually input bridge image data and automatically acquired bridge vibration data;

[0032] A preprocessing module, used for preprocessing the bridge image data and the bridge vibration data to obtain first monitoring data;

[0033] A state assessment module, used to obtain first monitoring data, perform a state assessment on the bridge according to the first monitoring data, and obtain a bridge assessment report;

[0034] A data monitoring module is used to obtain a bridge assessment report, obtain real-time vibration data of the bridge as second monitoring data according to the bridge assessment report, analyze the second monitoring data, and obtain a bridge health report;

[0035] The decision generation module is used to obtain the bridge health report and generate bridge use decisions and maintenance recommendations based on the bridge health report.

[0036] Preferably, the data acquisition module includes:

[0037] The sensor acquisition module is used to collect bridge vibration data, including bridge stress, strain, displacement, vibration and temperature information.

[0038] A data input module, used for providing a port for manually inputting bridge image data;

[0039] The preprocessing module comprises:

[0040] An image preprocessing module is used to obtain manually input bridge image data with original image pixels, digitize, geometrically transform, normalize, smooth, restore and enhance the bridge image data to obtain an image set, obtain the manually input numbers of the image set one by one, and automatically classify them;

[0041] A vibration data processing module is used to obtain bridge vibration data, clean and convert the bridge vibration data to obtain standard data;

[0042] The data storage module is used to obtain the image set and the standard data, associate the standard data with the image set, and store them.

[0043] A computer device, comprising: the computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps as claimed in any one of claims 1 to 6 are implemented.

[0044] A computer-readable storage medium comprises: a computer program is stored on the computer-readable storage medium, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

[0045] The technical effects and advantages of the present invention are as follows: by performing secondary analysis and processing on the data, a more comprehensive and complete bridge health report is obtained; the usage decision ultimately generated by the decision template improves accuracy while serving as a warning and early warning. For example, for usage decisions in dangerous states, management personnel can be prompted to adjust the use of the bridge in a timely manner, respond to bridge crises in a timely manner, make up for deficiencies in a timely manner, and avoid dangers caused by delayed data updates. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0047] Figure 2 It is a system schematic diagram of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] The present invention provides Figure 1-2 A bridge detection method based on the Internet of Things and big data is shown in the figure, including:

[0050] S1: periodically acquiring bridge image data and bridge vibration data through a data acquisition module, and preprocessing the bridge image data and bridge vibration data through a preprocessing module to obtain first monitoring data;

[0051] S2: obtaining first monitoring data through a state assessment module, and performing a state assessment on the bridge according to the first monitoring data to obtain a bridge assessment report, and then obtaining real-time vibration data of the bridge as second monitoring data through a data monitoring module according to the bridge assessment report, and analyzing the second monitoring data to obtain a bridge health report;

[0052] S3: The decision generation module generates bridge usage decisions and maintenance recommendations based on the bridge health report.

[0053] The preprocessing performed in step S1 includes preprocessing the bridge image data and preprocessing the bridge vibration data, which are respectively as follows:

[0054] The bridge image data and bridge vibration data are obtained through the sensor acquisition module and the data input module respectively; the bridge image data with original image pixels input manually are digitized, geometrically transformed, normalized, smoothed, restored and image enhanced through the image preprocessing module to obtain an image set, and the numbers of the manually input and image set are obtained one by one, and automatically classified; the bridge vibration data is obtained through the vibration data processing module, and the bridge vibration data is cleaned and converted to obtain standard data;

[0055] The image set and standard data obtained after preprocessing are stored through the data storage module, and the two are associated with each other in the dimension of time to facilitate subsequent calls. In addition, image sets of multiple periods are stored, which is conducive to tracing the generation and development of bridge cracks and facilitating investigation. In addition, the interrelated image sets and standard data are conducive to rapid tracing when abnormal situations occur, which is convenient for coordinating the acquired data.

[0056] Specifically, the following steps are required to execute the bridge assessment report:

[0057] Obtain a preprocessed image set, identify images with cracks, and obtain crack images;

[0058] Input the crack image into the crack analysis model to obtain the crack width and depth;

[0059] Based on the data of crack width and depth, the preset health threshold is compared to obtain a bridge assessment report, which includes a health status and a warning status; wherein the health threshold can be set according to the attributes of the bridge, such as: the width is 0≤0.1mm; the depth is ≤10mm. If it is within the health threshold, the crack is temporarily in a healthy state. If it is greater than the preset threshold, the bridge assessment report is output as a warning state;

[0060] The bridge assessment report is further processed to obtain a bridge health report, which is specifically performed as follows:

[0061] Obtain bridge assessment report and obtain assessment information (health status or warning status);

[0062] According to the evaluation information, real-time vibration data is input, and the real-time vibration data is intercepted multiple times to generate second monitoring data;

[0063] Acquire the second monitoring data and output a bridge health report based on a preset prediction model;

[0064] In order to better process the second monitoring data, the prediction model first obtains the second monitoring data, performs adaptive optimization based on fixed rules, benchmark data and historical data, and dynamically adjusts the detection threshold. The formula is as follows:

[0065]

[0066] T adj : Dynamically adjusted threshold; T nom : original threshold, based on the preliminary design setting; α: environmental factor weighting coefficient, reflecting the impact of environmental changes on the threshold; ΔT i : The temperature change value at the i-th time point; β: The weighting coefficient of historical data, which reflects the impact of historical data on the threshold; : The standard deviation of historical data, which reflects the amplitude of data fluctuation. If the data fluctuates greatly, the threshold is increased to improve the tolerance;

[0067] Dynamically adjust the detection threshold based on the following factors:

[0068] Environmental factors: the impact of external environmental factors such as temperature, humidity, and wind speed on the sensor. For example, temperature changes may cause sensor deviations, and the threshold needs to be automatically adjusted according to ambient temperature changes;

[0069] Bridge structural characteristics: Different bridges have different designs and stress modes, so the threshold should be set according to the specific structural type of the bridge (such as suspension bridge, cable-stayed bridge, beam bridge, etc.);

[0070] Historical data learning: Through historical monitoring data, especially common damage patterns, the threshold can be continuously optimized and adjusted. The threshold setting not only relies on simple statistical rules, but can also be adjusted according to the dynamic changes of the data through adaptive algorithms.

[0071] Next, based on the obtained dynamically adjusted detection threshold, the health assessment index is calculated to determine whether the bridge is in a normal state, so that a warning can be issued immediately when abnormal bridge vibration occurs. The formula is as follows:

[0072]

[0073] Among them, HI(t): is the health assessment index; α i and β: weight coefficient; W i (t): sensor data; E(t): influencing factors of environmental changes (such as temperature, humidity, etc.).

[0074] Based on the health assessment index, the detection threshold is dynamically adjusted and compared, and finally a bridge health report is output.

[0075] After determining the cracks in the bridge, the real-time vibration data is combined with the prediction model to comprehensively calculate and analyze the bridge, correct the content that may cause errors in manual input or sensor module input, combine the response of the bridge at a fixed time point with the real-time response of multiple time periods, and comprehensively calculate and judge the health status of the bridge to generate a bridge health report; through multiple data analysis and verification, errors are reduced and the accuracy of the output bridge health report is increased. In addition, through the second monitoring data, the status of the bridge can be followed up in time to facilitate timely warning or rapid response to dangerous situations.

[0076] In step S3, the generated bridge usage decision and maintenance suggestion are specifically performed as follows:

[0077] Input the bridge health report, apply the bridge health report to the preset decision template, obtain the response characteristics, and obtain the bridge use decision;

[0078] Get corresponding maintenance suggestions based on usage decisions;

[0079] Output bridge usage decisions and maintenance recommendations;

[0080] Among them, the decision template obtains the bridge health report and outputs the following health status: intact state, slightly damaged state, dangerous state;

[0081] The usage decisions and maintenance suggestions corresponding to different health status presets in the decision template are as follows:

[0082] In good condition: The overall safety reserve of the structure for vehicle load and wind resistance is greater than 2; under the design load and monitoring load, the internal force and deformation of all components are less than the design allowable value of the specification, and do not affect the structural safety, driving comfort and durability;

[0083] Usage decision: The bridge is intact and can be maintained in use;

[0084] Maintenance recommendations: Bridge image data and bridge vibration data should be obtained regularly, and bridge health reports should be updated.

[0085] Good condition: The overall safety reserve of the structure for vehicle load and wind resistance is between 1.6 and 2.0; under the design load and monitoring load, the key components are in good condition, and the internal force and deformation of some minor components (within 10%) are greater than 5% of the allowable value of the specification design, but do not affect the structural safety, driving comfort and durability;

[0086] Usage decision: The bridge is in normal use;

[0087] Maintenance recommendations: Bridge image data and bridge vibration data should be obtained regularly, and bridge health reports and usage should be monitored in real time.

[0088] Dangerous state: The main frequency of the structure is significantly reduced; the overall safety reserve of the structure's vehicle load and wind resistance is between 1.2-1.6; under the action of design load and monitoring load, the internal force of some key components (within 10%) is greater than the allowable value of the specification design by 10% or the fatigue cumulative damage index of the key components is 0.5-0.9, and the bearing capacity is reduced by less than 10%, affecting the safety of the structure.

[0089] Usage decision: If the bridge is in a dangerous state, output a bridge traffic warning;

[0090] Maintenance suggestions: Bridge image data and bridge vibration data should be obtained regularly, attention should be paid to bridge vibration data, the latest bridge status should be obtained in a timely manner, vehicles passing through the bridge should be restricted or prohibited from passing, and the bridge should be repaired in a timely manner.

[0091] In summary, through the combination of manual input and automatic acquisition, bridge image data and bridge vibration data are obtained, and the bridge image data and bridge vibration data are preprocessed respectively to obtain picture sets and standard data. The first monitoring data performs the first analysis on the bridge to obtain a bridge assessment report. Considering that the bridge image data taken during manual inspection may be misjudged after preprocessing, the real-time vibration data is obtained again for the output bridge assessment report, and the real-time vibration data of multiple periods are intercepted as the second monitoring data. The second monitoring data is combined with the bridge assessment report for analysis to obtain a more comprehensive and complete bridge health report. The decision template is pre-set. After obtaining the bridge health report, the use decision that meets the bridge in a certain state can be determined by matching, and the corresponding maintenance suggestions are confirmed based on the use decision. Through two data processing, the accuracy of the output results can be ensured, and more practical maintenance suggestions can be provided for bridges in different states. In addition, the use decision finally generated by the decision template can improve the accuracy and play a role of warning and early warning. For example, for the use decision of dangerous state, it can prompt the management personnel to adjust the use of the bridge in time, respond to the bridge crisis in time, make up for the shortcomings in time, and avoid the danger caused by the delay in data update.

[0092] The embodiment of the present application provides a computer device, which may be a device with data processing function such as a personal computer, a notebook computer, a server, etc. The computer device may include a processor, a memory, a communication interface, and a communication bus.

[0093] The communication bus can be of any type, and is used to interconnect the processor, memory, and communication interface. The communication interface includes input / output (I / O) interface, physical interface, and logical interface, which are used to interconnect the devices inside the computer device, and the interface used to interconnect the computer device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0094] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0095] The processor may be a general-purpose processor, which may call a program stored in a memory and execute the bridge detection method based on the Internet of Things and big data provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU).

[0096] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A bridge detection method based on the Internet of Things and big data, characterized by: include: regularly acquiring bridge image data and bridge vibration data, and preprocessing the bridge image data and bridge vibration data to obtain first monitoring data; According to the first monitoring data, a condition assessment is performed on the bridge to obtain a bridge assessment report, and according to the bridge assessment report, real-time vibration data of the bridge is obtained as second monitoring data, and the second monitoring data is analyzed to obtain a bridge health report; Based on the bridge health report, make bridge usage decisions and maintenance recommendations.

2. The bridge detection method based on the Internet of Things and big data according to claim 1 is characterized in that: The preprocessing of the bridge image data comprises the following steps: Obtaining manually input bridge image data with original image pixels, digitizing, geometrically transforming, normalizing, smoothing, restoring and enhancing the bridge image data to obtain an image set; Based on the image set, manually input numbers are obtained one by one; The image sets are automatically classified and stored according to the numbers.

3. The bridge detection method based on the Internet of Things and big data according to claim 2 is characterized in that: The bridge vibration data preprocessing comprises the following steps: Obtain bridge vibration data, and perform data cleaning and data conversion on the bridge vibration data to obtain standard data; Standard data storage is associated with the image set and stored.

4. The bridge detection method based on the Internet of Things and big data according to claim 3 is characterized by: The bridge condition assessment comprises the following steps: Acquire bridge image data, identify images with cracks, and obtain crack images; Input the crack image into the crack analysis model to obtain the crack width and depth; Based on the data of crack width and depth, the preset health threshold is compared to obtain a bridge assessment report, which includes a health status and a warning status.

5. The bridge detection method based on the Internet of Things and big data according to claim 4 is characterized in that: The analyzing of the second monitoring data comprises the following steps: Obtain bridge assessment report and obtain assessment information; According to the evaluation information, real-time vibration data is input, and the real-time vibration data is intercepted multiple times to generate second monitoring data; Acquire the second monitoring data and output a bridge health report based on a preset prediction model; The prediction model also needs to perform the following steps: Get the dynamically adjusted detection threshold of the bridge, the formula is as follows: T adj is the threshold after dynamic adjustment; T nom is the original threshold, which is set based on the preliminary design; α is the weighting coefficient of environmental factors, which reflects the impact of environmental changes on the threshold; ΔT i is the temperature change value at the i-th time point; β is the weighting coefficient of historical data, reflecting the impact of historical data on the threshold; σ hist is the standard deviation of historical data, reflecting the amplitude of data fluctuation. If the data fluctuates greatly, the threshold is increased to improve the tolerance; Based on the obtained dynamically adjusted detection threshold, the health assessment index is calculated, and the formula is as follows: Among them, HI(t) is the health assessment index; α i and β are weight coefficients; W i (t) is the sensor data; E(t) is the influencing factor of environmental changes; Compare the health assessment index with the dynamically adjusted detection threshold to determine the health of the bridge and output a bridge health report.

6. The bridge detection method based on the Internet of Things and big data according to claim 5 is characterized in that: The generation of bridge use decisions and maintenance recommendations requires the following operations: Get a bridge health report; Input the bridge health report into the preset decision template, obtain the response characteristics, get the bridge use decision, and obtain the corresponding maintenance recommendations based on the use decision; Output bridge usage decisions and maintenance recommendations.

7. A bridge detection system based on the Internet of Things and big data, characterized by: include: Data acquisition module: used to regularly acquire manually input bridge image data and automatically acquired bridge vibration data; A preprocessing module, used for preprocessing the bridge image data and the bridge vibration data to obtain first monitoring data; A state assessment module, used to obtain first monitoring data, perform a state assessment on the bridge according to the first monitoring data, and obtain a bridge assessment report; A data monitoring module is used to obtain a bridge assessment report, obtain real-time vibration data of the bridge as second monitoring data according to the bridge assessment report, analyze the second monitoring data, and obtain a bridge health report; The decision generation module is used to obtain the bridge health report and generate bridge use decisions and maintenance recommendations based on the bridge health report.

8. The bridge detection system based on the Internet of Things and big data according to claim 7 is characterized by: The data acquisition module comprises: The sensor acquisition module is used to collect bridge vibration data, including bridge stress, strain, displacement, vibration and temperature information. A data input module, used for providing a port for manually inputting bridge image data; The preprocessing module comprises: An image preprocessing module is used to obtain manually input bridge image data with original image pixels, digitize, geometrically transform, normalize, smooth, restore and enhance the bridge image data to obtain an image set, obtain the manually input numbers of the image set one by one, and automatically classify them; A vibration data processing module is used to obtain bridge vibration data, clean and convert the bridge vibration data to obtain standard data; The data storage module is used to obtain the image set and the standard data, associate the standard data with the image set, and store them.

9. A computer device, characterized in that: include: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: include: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images