Internet of Things-based Construction Safety Monitoring System and Method for Highway Bridges

Abstract

This invention provides an IoT-based safety monitoring system and method for construction of highway bridges, comprising: constructing the current construction status of the bridge based on real-time construction parameters and fusing them in chronological order to obtain the real-time construction procedures and cumulative construction results; using a fused risk identification matrix to identify risks in the real-time construction procedures and to find corresponding risk factors in the cumulative construction results; constructing a risk decomposition tree for the bridge; transmitting historical stored data and on-site data of the bridge to a Bayesian network for risk tracing; constructing on-site risk classification rules for the bridge; using the on-site risk classification rules to classify and evaluate the risk decomposition tree to obtain several risk locations of the bridge; and generating and displaying a visualized risk report. This addresses the problems of limited scope, poor real-time performance, low data processing efficiency of traditional monitoring methods, and unstable transmission and low early warning accuracy of existing monitoring systems.

Description

Technical Field

[0001] This invention relates to the field of construction safety monitoring technology, and in particular to an Internet of Things-based construction safety monitoring system and method for cross-highway bridges. Background Technology

[0002] During the construction of bridges spanning highways, the bridge structure is prone to safety hazards such as stress concentration, excessive displacement, and abnormal vibration due to the influence of high-speed traffic flow, complex geological conditions, changes in construction load, and harsh environmental factors. If these hazards are not detected and addressed in time, they may lead to safety accidents such as bridge collapse and falling construction equipment, which will not only cause huge economic losses, but also threaten the lives of construction workers and the normal operation of highway traffic.

[0003] Traditional methods for monitoring the safety of construction on highway bridges mainly rely on manual inspections and portable monitoring equipment, which have the following shortcomings: First, the monitoring range is limited, as manual inspections cannot cover all critical parts of the bridge, especially areas that are difficult to reach, such as the bottom of the main beam and the base of the piers. Second, the monitoring frequency is low, as manual inspections are usually conducted only once or twice a day, making it impossible to achieve real-time monitoring and capture instantaneous safety hazards during construction. Third, the data processing efficiency is low, as manually collected monitoring data needs to be analyzed offline, making it impossible to generate risk assessment results in a timely manner, resulting in delayed early warnings. Fourth, it relies on human experience, and risk judgment is easily affected by subjective factors, making it difficult to guarantee accuracy.

[0004] With the development of IoT and AI technologies, some bridge construction safety monitoring systems have begun to adopt sensor and wireless transmission technologies. However, existing systems still suffer from problems such as poor data transmission stability, simple data analysis models, and low early warning accuracy, making it difficult to meet the high reliability, high real-time performance, and high accuracy requirements for safety monitoring in highway construction.

[0005] Therefore, the present invention provides an Internet of Things-based construction safety monitoring system and method for bridges spanning highways. Summary of the Invention

[0006] This invention relates to an Internet of Things-based construction safety monitoring system and method for cross-highway bridges, which aims to solve the problems of limited range, poor real-time performance, low data processing efficiency, unstable transmission, and low early warning accuracy of traditional monitoring methods.

[0007] This invention provides an Internet of Things-based construction safety monitoring system for highway bridges, comprising:

[0008] The construction identification module is used to construct the current construction status of the bridge based on the bridge's real-time construction parameters, and to merge the current construction status in chronological order to obtain the bridge's real-time construction procedures and cumulative construction results.

[0009] The risk identification module is used to identify risks in the real-time construction process using a fusion risk identification matrix, find corresponding risk factors in the cumulative construction results, and construct a risk decomposition tree for the bridge.

[0010] The deep analysis module is used to transmit historical stored data and on-site data of the bridge to a Bayesian network for risk tracing and to construct on-site risk classification rules for the bridge.

[0011] The safety detection module is used to classify and evaluate the risk decomposition tree using the on-site risk classification rules, obtain several risk locations of the bridge, generate a visual risk report, and display it.

[0012] In one feasible approach

[0013] Also includes:

[0014] A network execution module is used to connect several data acquisition devices of the bridge to a network;

[0015] The real-time data collected by each of the data acquisition devices is transmitted to the construction identification module.

[0016] In one feasible approach

[0017] The construction identification module includes:

[0018] The location determination unit is used to deduce several completed projects of the bridge based on the real-time construction parameters of the bridge and draw the bridge structure corresponding to each completed project, determine several constructable positions on each bridge structure, match each constructable position with the real-time construction parameters, and determine several current construction positions of the bridge.

[0019] The state construction unit is used to perform construction simulation at each current construction location based on the real-time construction parameters to obtain a real-time construction model of the bridge, run the real-time construction model to obtain the real-time construction features corresponding to each current construction location, and construct the current construction state of the bridge.

[0020] The state fusion unit is used to determine the coarse state logic between different current construction states based on the construction time corresponding to each current construction state, fuse the current construction states corresponding to different construction times based on the coarse state logic, and identify several fusion contradiction points.

[0021] The state generation unit is used to optimize each of the fusion contradiction points according to the real-time construction parameters to obtain the current fusion state of the bridge, find several current construction features of the bridge in the current fusion state to generate real-time construction procedures, and accumulate the real-time construction procedures corresponding to different construction times to obtain the cumulative construction results of the bridge.

[0022] In one feasible approach

[0023] Also includes:

[0024] The logic optimization unit is used to obtain the optimization process corresponding to each point of convergence contradiction, and to optimize the coarse state logic according to the optimization process to obtain the effective state logic between different current construction states.

[0025] The current construction state of the bridge is rearranged using the effective state logic to obtain the current fusion state of the bridge.

[0026] In one feasible approach

[0027] The risk identification module includes:

[0028] The matrix analysis unit is used to determine several risk identification dimensions of the bridge using several risk identification dimensions of the fused risk identification matrix and several basic information of the bridge, and to determine the identification conditions corresponding to each risk identification dimension. The real-time construction procedures are input into the fused risk identification matrix for identification, and the risk identification results corresponding to each risk identification dimension are obtained.

[0029] The feature generation unit is used to determine several single risk features of each real-time construction process based on several risk identification results corresponding to each real-time construction process, and to fuse the several risk identification results corresponding to each real-time construction process to obtain the comprehensive risk features corresponding to each real-time construction process.

[0030] The factor matching unit is used to perform process traversal on the process operations between different real-time construction processes using each of the single risk features and the comprehensive risk features respectively, to obtain several single risk factors corresponding to each of the single risk features and comprehensive risk factors corresponding to each of the comprehensive risk features.

[0031] The dynamic analysis unit is used to determine several risk items of the bridge based on the single risk factor and the comprehensive risk factor, identify the risk dynamic characteristics corresponding to each risk item, and dynamically couple the risk dynamic characteristics to obtain the risk decomposition tree of the bridge.

[0032] In one feasible approach

[0033] The deep analysis module includes:

[0034] The data fusion unit is used to construct the on-site data of the bridge based on the real-time construction parameters, and at the same time acquire the historical stored data of the bridge, and fuse the on-site data and the historical stored data to obtain the comprehensive on-site data of the bridge.

[0035] The risk tracing unit is used to identify several risk sub-data contained in the comprehensive field data according to the risk decomposition tree, and input each risk sub-data into the Bayesian network for risk tracing to obtain the risk information corresponding to each risk sub-data in the bridge.

[0036] The rule construction unit is used to perform semantic recognition on each of the aforementioned risk information to obtain several key risk features of the bridge, search for the risk consequences corresponding to each of the aforementioned key risk features in the big data, and construct the on-site risk classification rules of the bridge based on the risk consequences in descending order and in combination with the risk information.

[0037] In one feasible approach

[0038] Based on the risk consequences in descending order and combined with the risk information, a site risk classification rule for the bridge is constructed, including:

[0039] The bridge is constructed according to several classification criteria based on the risk consequences from high to low, and each risk information is matched with a corresponding classification criterion.

[0040] Each grading standard is described based on the risk information corresponding to each grading standard, thereby obtaining the on-site grading rules for the bridge.

[0041] In one feasible approach

[0042] The security detection module includes:

[0043] The graded assessment unit is used to identify the bridge risk characteristics corresponding to each branch of the risk decomposition tree, divide the bridge risk characteristics into several grades using the on-site risk rules, and conduct a safety assessment for each grade to determine the safety probability corresponding to each grade.

[0044] A visual positioning unit is used to identify several risk locations corresponding to each of the aforementioned classifications in the bridge, set corresponding risk markers for each of the aforementioned risk locations according to the classifications, construct a visual report of the bridge based on the bridge structure and the risk markers, and display the report.

[0045] This invention provides an Internet of Things-based method for monitoring the construction safety of bridges spanning highways, including:

[0046] Step 1: Construct the current construction status of the bridge based on the real-time construction parameters of the bridge, and merge the current construction status in chronological order to obtain the real-time construction procedures and cumulative construction results of the bridge.

[0047] Step 2: Use the fusion risk identification matrix to identify risks in the real-time construction process, find the corresponding risk factors in the cumulative construction results, and construct the risk decomposition tree of the bridge;

[0048] Step 3: Transmit historical stored data and on-site data of the bridge to a Bayesian network for risk tracing and construct on-site risk classification rules for the bridge;

[0049] Step 4: Use the on-site risk classification rules to classify and evaluate the risk decomposition tree, obtain several risk locations of the bridge, generate a visual risk report and display it.

[0050] In one feasible approach

[0051] Step 1 includes:

[0052] Step 11: Based on the real-time construction parameters of the bridge, deduce several completed projects of the bridge and draw the bridge structure corresponding to each completed project. Determine several constructable positions on each bridge structure and match each constructable position with the real-time construction parameters to determine several current construction positions of the bridge.

[0053] Step 12: Perform construction simulation at each current construction location based on the real-time construction parameters to obtain a real-time construction model of the bridge. Run the real-time construction model to obtain the real-time construction features corresponding to each current construction location and construct the current construction state of the bridge.

[0054] Step 13: Determine the coarse state logic between different current construction states based on the construction time corresponding to each current construction state, merge the current construction states corresponding to different construction times based on the coarse state logic, and identify several points of fusion contradiction.

[0055] Step 14: Optimize each of the aforementioned fusion contradiction points according to the real-time construction parameters to obtain the current fusion state of the bridge. In the current fusion state, find several current construction features of the bridge to generate real-time construction procedures. Accumulate the real-time construction procedures corresponding to different construction times to obtain the cumulative construction results of the bridge.

[0056] The beneficial effects of the above technical solution are as follows: To improve the quality and efficiency of safety monitoring at bridge construction sites, firstly, real-time construction parameters are constructed and the current construction status is integrated in a time sequence to form real-time construction procedures and cumulative construction results. This not only achieves dynamic perception of the construction status to eliminate management blind spots, but also provides accurate data support for subsequent stages. Then, by using a fused risk identification matrix, high-risk procedures are quickly identified and a risk decomposition tree is constructed, effectively improving the efficiency of risk identification and the visualization of source tracing, avoiding misjudgments and delays in handling. Furthermore, by integrating historical and on-site data through a Bayesian network, the scientific nature of risk source tracing is enhanced. At the same time, a unified on-site risk classification rule is constructed to solve the problem of inconsistent traditional classification standards. Finally, based on the classification rule, the risk location is accurately located and a visual report is generated, realizing differentiated risk management to reduce resource waste. It also improves management decision-making efficiency and cross-departmental collaboration capabilities, forming a full-process monitoring system. Ultimately, this significantly improves monitoring accuracy, accelerates response speed, reduces management costs, and effectively ensures the safety of construction on highway bridges.

[0057] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0058] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0059] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0060] Figure 1 This is a schematic diagram of the components of the IoT-based construction safety monitoring system for highway bridges in this embodiment of the invention.

[0061] Figure 2 This is a schematic diagram illustrating the workflow of the IoT-based construction safety monitoring method for highway bridges in this embodiment of the invention. Detailed Implementation

[0062] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0063] Example 1:

[0064] This embodiment provides an IoT-based construction safety monitoring system for bridges spanning highways, such as... Figure 1 As shown, it includes:

[0065] The construction identification module is used to construct the current construction status of the bridge based on the bridge's real-time construction parameters, and to merge the current construction status in chronological order to obtain the bridge's real-time construction procedures and cumulative construction results.

[0066] The risk identification module is used to identify risks in the real-time construction process using a fusion risk identification matrix, find corresponding risk factors in the cumulative construction results, and construct a risk decomposition tree for the bridge.

[0067] The deep analysis module is used to transmit historical stored data and on-site data of the bridge to a Bayesian network for risk tracing and to construct on-site risk classification rules for the bridge.

[0068] The safety detection module is used to classify and evaluate the risk decomposition tree using the on-site risk classification rules, obtain several risk locations of the bridge, generate a visual risk report, and display it.

[0069] In this example, the fusion risk identification matrix is ​​a tool that uses quantitative assessment and graphical representation of the probability and impact of risks;

[0070] In this example, real-time construction parameters refer to real-time parameters generated at the construction site;

[0071] In this example, the current construction status refers to the state of the bridge at the current moment;

[0072] In this example, the real-time construction procedure refers to the procedure that the bridge is currently undertaking at the moment of construction.

[0073] In this example, the cumulative construction results represent the final outcome of the bridge construction.

[0074] In this example, the risk decomposition tree is represented as a binary tree used to show the relationships between different risks;

[0075] In this example, risk factors represent potential risks in the cumulative construction results;

[0076] In this example, the risk location refers to the location in the bridge where a risk is present.

[0077] The working principle and beneficial effects of the above technical solution are as follows: To improve the quality and efficiency of safety monitoring at bridge construction sites, firstly, real-time construction parameters are used to construct and sequentially integrate the current construction status, forming real-time construction procedures and cumulative construction results. This not only achieves dynamic perception of the construction status to eliminate management blind spots but also provides accurate data support for subsequent stages. Then, a risk identification matrix is ​​used to quickly identify high-risk procedures and construct a risk decomposition tree, effectively improving risk identification efficiency and source visualization, avoiding misjudgments and delays in handling. Furthermore, a Bayesian network is used to integrate historical and on-site data to enhance the scientific nature of risk source tracing. At the same time, a unified on-site risk classification rule is constructed to solve the problem of inconsistent traditional classification standards. Finally, based on the classification rule, the risk location is accurately located and a visual report is generated, achieving differentiated risk control to reduce resource waste. It also improves management decision-making efficiency and cross-departmental collaboration capabilities, forming a full-process monitoring system. Ultimately, this significantly improves monitoring accuracy, accelerates response speed, reduces management costs, and effectively ensures the safety of construction on highway bridges.

[0078] Example 2:

[0079] Based on Example 1, the IoT-based construction safety monitoring system for highway bridges further includes:

[0080] A network execution module is used to connect several data acquisition devices of the bridge to a network;

[0081] The real-time data collected by each of the data acquisition devices is transmitted to the construction identification module.

[0082] The working principle and beneficial effects of the above technical solution are as follows: connecting the data acquisition equipment at the construction site to the network facilitates real-time data upload.

[0083] Example 3:

[0084] Based on Example 1, the construction identification module of the IoT-based cross-highway bridge construction safety monitoring system includes:

[0085] The location determination unit is used to deduce several completed projects of the bridge based on the real-time construction parameters of the bridge and draw the bridge structure corresponding to each completed project, determine several constructable positions on each bridge structure, match each constructable position with the real-time construction parameters, and determine several current construction positions of the bridge.

[0086] The state construction unit is used to perform construction simulation at each current construction location based on the real-time construction parameters to obtain a real-time construction model of the bridge, run the real-time construction model to obtain the real-time construction features corresponding to each current construction location, and construct the current construction state of the bridge.

[0087] The state fusion unit is used to determine the coarse state logic between different current construction states based on the construction time corresponding to each current construction state, fuse the current construction states corresponding to different construction times based on the coarse state logic, and identify several fusion contradiction points.

[0088] The state generation unit is used to optimize each of the fusion contradiction points according to the real-time construction parameters to obtain the current fusion state of the bridge, find several current construction features of the bridge in the current fusion state to generate real-time construction procedures, and accumulate the real-time construction procedures corresponding to different construction times to obtain the cumulative construction results of the bridge.

[0089] In this example, "completed project" refers to a project that has already been constructed.

[0090] In this example, a workable location refers to a location on a completed project where construction can be carried out;

[0091] In this example, the current construction location refers to the location on the bridge that is currently under construction.

[0092] In this example, the real-time construction model represents a virtual model used to present the construction process of the bridge;

[0093] In this example, the coarse state logic represents the approximate logic between different current construction states based on the time sequence.

[0094] In this example, the point of inconsistency refers to the point that cannot be integrated after merging the current construction status.

[0095] The working principle and beneficial effects of the above technical solution are as follows: First, by accurately locking the current construction location through real-time construction parameters, the misjudgment and omissions of traditional manual inspections are avoided, laying a spatial foundation for subsequent monitoring. Then, the construction unit generates a real-time construction model and extracts features through construction simulation, solving the problem that traditional text records cannot intuitively reflect construction details, and facilitating timely detection of deviations. Next, the status logic is sorted out according to the construction time and contradictions are identified and integrated, avoiding the chaotic situation of traditional data integration and ensuring data continuity. Finally, after optimizing the contradictions, real-time construction procedures and cumulative construction results are generated, solving the traditional data integration problem, providing reliable data for risk identification, and providing a basis for managers to adjust plans. It provides accurate, reliable, and continuous data support for safety monitoring of cross-highway bridge construction, comprehensively improving monitoring accuracy and management efficiency, and reducing safety control loopholes and quality risks.

[0096] Example 4:

[0097] Based on Example 3, the IoT-based construction safety monitoring system for highway bridges further includes:

[0098] The logic optimization unit is used to obtain the optimization process corresponding to each point of convergence contradiction, and to optimize the coarse state logic according to the optimization process to obtain the effective state logic between different current construction states.

[0099] The current construction state of the bridge is rearranged using the effective state logic to obtain the current fusion state of the bridge.

[0100] The working principle and beneficial effects of the above technical solution are as follows: it identifies the logic between different current construction states, which facilitates the subsequent state arrangement.

[0101] Example 5:

[0102] Based on Example 1, the risk identification module of the IoT-based construction safety monitoring system for highway bridges includes:

[0103] The matrix analysis unit is used to determine several risk identification dimensions of the bridge using several risk identification dimensions of the fused risk identification matrix and several basic information of the bridge, and to determine the identification conditions corresponding to each risk identification dimension. The real-time construction procedures are input into the fused risk identification matrix for identification, and the risk identification results corresponding to each risk identification dimension are obtained.

[0104] The feature generation unit is used to determine several single risk features of each real-time construction process based on several risk identification results corresponding to each real-time construction process, and to fuse the several risk identification results corresponding to each real-time construction process to obtain the comprehensive risk features corresponding to each real-time construction process.

[0105] The factor matching unit is used to perform process traversal on the process operations between different real-time construction processes using each of the single risk features and the comprehensive risk features respectively, to obtain several single risk factors corresponding to each of the single risk features and comprehensive risk factors corresponding to each of the comprehensive risk features.

[0106] The dynamic analysis unit is used to determine several risk items of the bridge based on the single risk factor and the comprehensive risk factor, identify the risk dynamic characteristics corresponding to each risk item, and dynamically couple the risk dynamic characteristics to obtain the risk decomposition tree of the bridge.

[0107] In this example, the integrated risk identification matrix means that the integrated risk identification matrix combines multiple risk assessment dimensions to form a more comprehensive risk assessment tool;

[0108] In this example, the basic information represents the information used to describe the bridge;

[0109] In this example, the risk identification dimensions include: hazard probability, hazard impact, hazard controllability, hazard exposure, and hazard timeliness;

[0110] In this example, a single risk feature represents the characteristics of a construction procedure under a risk identification dimension;

[0111] In this example, the comprehensive risk characteristics represent the features of a construction process under the combined influence of several risk identification results;

[0112] In this example, the risk dynamics feature represents the dynamics contained in a risk item.

[0113] The working principle and beneficial effects of the above technical solution are as follows: First, by using a fusion risk identification matrix and basic bridge information, suitable risk identification dimensions and conditions are determined. The fusion risk identification matrix efficiently identifies risks in each dimension, avoiding the problems of fixed dimensions and low efficiency in traditional methods. Then, risk determination is carried out by extracting single and comprehensive risk features, capturing both independent risk signals and understanding the superposition effect of risks, thus overcoming the limitations of traditional methods that only focus on a single dimension. Furthermore, risk features are used to traverse the process to locate risk factors, solving the problems of low efficiency and easy omissions in manual investigation, and providing clear direction for disposal. Finally, risk features are dynamically coupled to generate a risk decomposition tree, reflecting the evolution of risks in real time, avoiding the problem of fixed decomposition trees in traditional methods, greatly improving the accuracy, comprehensiveness and dynamic control capabilities of risk identification in the construction of cross-highway bridges, shortening the response time and reducing the probability of safety accidents.

[0114] Example 6:

[0115] Based on Example 1, the IoT-based construction safety monitoring system for highway bridges includes a deep analysis module comprising:

[0116] The data fusion unit is used to construct the on-site data of the bridge based on the real-time construction parameters, and at the same time acquire the historical stored data of the bridge, and fuse the on-site data and the historical stored data to obtain the comprehensive on-site data of the bridge.

[0117] The risk tracing unit is used to identify several risk sub-data contained in the comprehensive field data according to the risk decomposition tree, and input each risk sub-data into the Bayesian network for risk tracing to obtain the risk information corresponding to each risk sub-data in the bridge.

[0118] The rule construction unit is used to perform semantic recognition on each of the aforementioned risk information to obtain several key risk features of the bridge, search for the risk consequences corresponding to each of the aforementioned key risk features in the big data, and construct the on-site risk classification rules of the bridge based on the risk consequences in descending order and in combination with the risk information.

[0119] In this example, the risk information represents the information presented by the risk sub-data in the bridge;

[0120] In this example, the key risk features represent the risk characteristics presented in the bridge.

[0121] The working principle and beneficial effects of the above technical solution are as follows: By constructing on-site data and integrating historical stored data to obtain comprehensive on-site data, the limitations of traditional monitoring that relies solely on single data points and is prone to analytical bias due to incomplete data are overcome. This makes the data more complete and valuable for reference, laying a comprehensive data foundation for subsequent risk tracing. Then, risk sub-data is extracted from the comprehensive on-site data using a risk decomposition tree, and risk information is obtained through precise tracing using a Bayesian network. This solves the problems of traditional risk tracing relying on human experience, low efficiency, and poor accuracy. It can quickly locate the root cause of risks and provide precise direction for risk management. Furthermore, key risk features are extracted through semantic recognition, and on-site risk classification rules are constructed by combining risk consequences found through big data analysis. This avoids the defects of traditional classification rules that are subjective and lack data support, making risk classification more scientific and reasonable. It provides a unified standard for the classification and evaluation of subsequent safety detection modules, significantly improving the comprehensiveness, accuracy, and standardization of risk analysis for construction of highway bridges, and providing strong technical support for safety management.

[0122] Example 7:

[0123] Based on Example 6, the IoT-based construction safety monitoring system for highway bridges constructs on-site risk classification rules for the bridge according to the risk consequences in descending order, combined with the risk information, including:

[0124] The bridge is constructed according to several classification criteria based on the risk consequences from high to low, and each risk information is matched with a corresponding classification criterion.

[0125] Each grading standard is described based on the risk information corresponding to each grading standard, thereby obtaining the on-site grading rules for the bridge.

[0126] The working principle and beneficial effects of the above technical solution are as follows: by setting on-site classification rules, a foundation is laid for subsequent safety monitoring.

[0127] Example 8:

[0128] Based on Example 1, the IoT-based construction safety monitoring system for highway bridges includes a safety detection module comprising:

[0129] The graded assessment unit is used to identify the bridge risk characteristics corresponding to each branch of the risk decomposition tree, divide the bridge risk characteristics into several grades using the on-site risk rules, and conduct a safety assessment for each grade to determine the safety probability corresponding to each grade.

[0130] A visual positioning unit is used to identify several risk locations corresponding to each of the aforementioned classifications in the bridge, set corresponding risk markers for each of the aforementioned risk locations according to the classifications, construct a visual report of the bridge based on the bridge structure and the risk markers, and display the report.

[0131] The working principle and beneficial effects of the above technical solution are as follows: By identifying the bridge risk characteristics of each branch of the risk decomposition tree, and combining on-site risk rules to complete risk classification and determine the safety probability of each level, it breaks through the limitations of traditional risk assessment, which is only qualitative and subjective in standards. It clarifies the risk level and quantifies the degree of safety, avoiding over- or under-management. It can also accurately locate the key control points of different levels to improve the targeting of control. Then, it accurately identifies the risk locations corresponding to each level and sets exclusive risk markers. Combined with the bridge structure construction visualization report, it solves the problems of traditional risk notification relying on text and difficulty in location. Managers can intuitively grasp the risk distribution and its relationship with key components without being on-site, providing a clear basis for prioritizing the handling of high-risk locations. It transforms abstract monitoring data into intuitive action guidelines, significantly improving the scientific nature of risk assessment and the efficiency of response, and effectively ensuring the safety of personnel, equipment and road traffic during the construction of highway bridges.

[0132] Example 9:

[0133] This embodiment provides a method for monitoring the construction safety of bridges spanning highways based on the Internet of Things, such as... Figure 2 As shown, it includes:

[0134] Step 1: Construct the current construction status of the bridge based on the real-time construction parameters of the bridge, and merge the current construction status in chronological order to obtain the real-time construction procedures and cumulative construction results of the bridge.

[0135] Step 2: Use the fusion risk identification matrix to identify risks in the real-time construction process, find the corresponding risk factors in the cumulative construction results, and construct the risk decomposition tree of the bridge;

[0136] Step 3: Transmit historical stored data and on-site data of the bridge to a Bayesian network for risk tracing and construct on-site risk classification rules for the bridge;

[0137] Step 4: Use the on-site risk classification rules to classify and evaluate the risk decomposition tree, obtain several risk locations of the bridge, generate a visual risk report and display it.

[0138] In this example, real-time construction parameters refer to real-time parameters generated at the construction site;

[0139] In this example, the current construction status refers to the state of the bridge at the current moment;

[0140] In this example, the real-time construction procedure refers to the procedure that the bridge is currently undertaking at the moment of construction.

[0141] In this example, the cumulative construction results represent the final outcome of the bridge construction.

[0142] In this example, the risk decomposition tree is represented as a binary tree used to show the relationships between different risks;

[0143] In this example, risk factors represent potential risks in the cumulative construction results;

[0144] In this example, the risk location refers to the location in the bridge where a risk is present.

[0145] The working principle and beneficial effects of the above technical solution are as follows: To improve the quality and efficiency of safety monitoring at bridge construction sites, firstly, real-time construction parameters are used to construct and sequentially integrate the current construction status, forming real-time construction procedures and cumulative construction results. This not only achieves dynamic perception of the construction status to eliminate management blind spots but also provides accurate data support for subsequent stages. Then, a risk identification matrix is ​​used to quickly identify high-risk procedures and construct a risk decomposition tree, effectively improving risk identification efficiency and source visualization, avoiding misjudgments and delays in handling. Furthermore, a Bayesian network is used to integrate historical and on-site data to enhance the scientific nature of risk source tracing. At the same time, a unified on-site risk classification rule is constructed to solve the problem of inconsistent traditional classification standards. Finally, based on the classification rule, the risk location is accurately located and a visual report is generated, achieving differentiated risk control to reduce resource waste. It also improves management decision-making efficiency and cross-departmental collaboration capabilities, forming a full-process monitoring system. Ultimately, this significantly improves monitoring accuracy, accelerates response speed, reduces management costs, and effectively ensures the safety of construction on highway bridges.

[0146] Example 10:

[0147] Based on Example 9, the IoT-based method for monitoring the construction safety of highway bridges, step 1 includes:

[0148] Step 11: Based on the real-time construction parameters of the bridge, deduce several completed projects of the bridge and draw the bridge structure corresponding to each completed project. Determine several constructable positions on each bridge structure and match each constructable position with the real-time construction parameters to determine several current construction positions of the bridge.

[0149] Step 12: Perform construction simulation at each current construction location based on the real-time construction parameters to obtain a real-time construction model of the bridge. Run the real-time construction model to obtain the real-time construction features corresponding to each current construction location and construct the current construction state of the bridge.

[0150] Step 13: Determine the coarse state logic between different current construction states based on the construction time corresponding to each current construction state, merge the current construction states corresponding to different construction times based on the coarse state logic, and identify several points of fusion contradiction.

[0151] Step 14: Optimize each of the aforementioned fusion contradiction points according to the real-time construction parameters to obtain the current fusion state of the bridge. In the current fusion state, find several current construction features of the bridge to generate real-time construction procedures. Accumulate the real-time construction procedures corresponding to different construction times to obtain the cumulative construction results of the bridge.

[0152] In this example, "completed project" refers to a project that has already been constructed.

[0153] In this example, a workable location refers to a location on a completed project where construction can be carried out;

[0154] In this example, the current construction location refers to the location on the bridge that is currently under construction.

[0155] In this example, the real-time construction model represents a virtual model used to present the construction process of the bridge;

[0156] In this example, the coarse state logic represents the approximate logic between different current construction states based on the time sequence.

[0157] In this example, the point of inconsistency refers to the point that cannot be integrated after merging the current construction status.

[0158] The working principle and beneficial effects of the above technical solution are as follows: First, by accurately locking the current construction location through real-time construction parameters, the misjudgment and omissions of traditional manual inspections are avoided, laying a spatial foundation for subsequent monitoring. Then, the construction unit generates a real-time construction model and extracts features through construction simulation, solving the problem that traditional text records cannot intuitively reflect construction details, and facilitating timely detection of deviations. Next, the status logic is sorted out according to the construction time and contradictions are identified and integrated, avoiding the chaotic situation of traditional data integration and ensuring data continuity. Finally, after optimizing the contradictions, real-time construction procedures and cumulative construction results are generated, solving the traditional data integration problem, providing reliable data for risk identification, and providing a basis for managers to adjust plans. It provides accurate, reliable, and continuous data support for safety monitoring of cross-highway bridge construction, comprehensively improving monitoring accuracy and management efficiency, and reducing safety control loopholes and quality risks.

[0159] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. The Internet of Things-based cross-high-speed bridge construction safety monitoring system is characterized in that, The application comprises: a construction identification module, which is used to construct a current construction state of a bridge according to real-time construction parameters of the bridge, and fuse the current construction state in time sequence to obtain a real-time construction procedure and cumulative construction achievement of the bridge; a risk identification module, which is used to identify risks of the real-time construction procedure by using a fused risk identification matrix, and find corresponding risk factors in the cumulative construction achievement to construct a risk breakdown tree of the bridge; a deep analysis module, which is used to transmit historical storage data and field data of the bridge to a Bayesian network for risk tracing to construct field risk grading rules of the bridge; a safety detection module, which is used to grade and evaluate the risk breakdown tree by using the field risk grading rules to obtain a plurality of risk positions of the bridge, generate a visual risk report and display the report. The construction identification module comprises: a position determination unit, which is used to deduce a plurality of completed projects of the bridge according to real-time construction parameters of the bridge, draw a bridge structure corresponding to each completed project, determine a plurality of constructible positions corresponding to each bridge structure, match each constructible position with the real-time construction parameters, and determine a plurality of current construction positions of the bridge; a state construction unit, which is used to simulate construction at each current construction position according to the real-time construction parameters to obtain a real-time construction model of the bridge, run the real-time construction model to obtain real-time construction characteristics corresponding to each current construction position, and construct a current construction state of the bridge; a state fusion unit, which is used to determine a coarse state logic between different current construction states according to a construction time corresponding to each current construction state, fuse the current construction states corresponding to different construction times according to the coarse state logic, and identify a plurality of fusion conflict points; a state generation unit, which is used to optimize each fusion conflict point according to the real-time construction parameters to obtain a current fusion state of the bridge, find a plurality of current construction characteristics of the bridge in the current fusion state to generate a real-time construction procedure, accumulate real-time construction procedures corresponding to different construction times to obtain a cumulative construction achievement of the bridge.

2. The IoT based cross high speed bridge construction safety monitoring system as claimed in claim 1, wherein, The application further comprises: a network execution module, which is used to connect a plurality of data acquisition devices of the bridge to a network; real-time acquisition data of each data acquisition device is transmitted to the construction identification module.

3. The IoT based cross high speed bridge construction safety monitoring system as claimed in claim 1, wherein, The application further comprises: a logic optimization unit, which is used to obtain an optimization process corresponding to each fusion conflict point, optimize the coarse state logic according to the optimization process to obtain an effective state logic between different current construction states, and rearrange the current construction state of the bridge according to the effective state logic to obtain a current fusion state of the bridge. The risk identification module comprises:

4. The IoT based cross high speed bridge construction safety monitoring system as claimed in claim 1, wherein, ​ A matrix analysis unit is configured to determine a plurality of risk identification dimensions of the bridge by using the plurality of risk identification dimensions of the fusion risk identification matrix and the plurality of basic information of the bridge, determine an identification condition corresponding to each of the risk identification dimensions, and input the real-time construction process into the fusion risk identification matrix for identification to obtain a risk identification result corresponding to each of the risk identification dimensions. A feature generation unit is configured to determine a plurality of single risk features of each of the real-time construction processes according to the plurality of risk identification results corresponding to each of the real-time construction processes, fuse the plurality of risk identification results corresponding to each of the real-time construction processes to obtain a comprehensive risk feature corresponding to each of the real-time construction processes. A factor matching unit is configured to perform process iteration on process operations between different real-time construction processes by using each of the single risk features and the comprehensive risk feature to obtain a plurality of single risk factors corresponding to each of the single risk features and a comprehensive risk factor corresponding to each of the comprehensive risk features. A dynamic analysis unit is configured to determine a plurality of risk items of the bridge according to the single risk factors and the comprehensive risk factors, identify a risk dynamic feature corresponding to each of the risk items, and dynamically couple the risk dynamic features to obtain a risk resolution tree of the bridge.

5. The IoT based cross high speed bridge construction safety monitoring system as claimed in claim 1, wherein, The deep analysis module comprises: A data fusion unit is configured to construct field data of the bridge according to the real-time construction parameters, acquire historical storage data of the bridge, fuse the field data and the historical storage data to obtain comprehensive field data of the bridge. A risk traceability unit is configured to identify a plurality of risk sub-data contained in the comprehensive field data according to the risk resolution tree, input each of the risk sub-data into the Bayesian network for risk traceability to obtain risk information corresponding to each of the risk sub-data in the bridge. A rule construction unit is configured to perform semantic identification on each of the risk information to obtain a plurality of risk key features of the bridge, find a risk consequence corresponding to each of the risk key features in big data, and construct a field risk classification rule of the bridge by combining the risk information in a descending order of the risk consequence.

6. The IoT-based cross-highway bridge construction safety monitoring system of claim 5, wherein, The field risk classification rule of the bridge is constructed by combining the risk information in a descending order of the risk consequence, comprising: constructing a plurality of classification standards of the bridge according to the descending order of the risk consequence, and matching a corresponding classification standard to each of the risk information; describing each of the classification standards according to the risk information corresponding to each of the classification standards to obtain a field classification rule of the bridge.

7. The IoT based cross high speed bridge construction safety monitoring system as claimed in claim 1, wherein, The safety detection module comprises: A classification evaluation unit is configured to identify a bridge risk feature corresponding to each of the tree branches in the risk resolution tree, divide the bridge risk feature into a plurality of classifications by using the field risk classification rule, perform safety evaluation on each of the classifications, and determine a safety probability corresponding to each of the classifications. A visual positioning unit is configured to identify a plurality of risk positions corresponding to each of the hierarchical levels in the bridge, set corresponding risk marks for each of the risk positions according to the hierarchical levels, construct a visual report of the bridge according to the bridge structure and the risk marks of the bridge, and display the visual report.

8. The method for monitoring the safety of construction of a cross-highway bridge based on the Internet of Things, characterized in that, The method comprises the following steps: Step 1: constructing a current construction state of the bridge according to real-time construction parameters of the bridge, fusing the current construction state in time sequence to obtain real-time construction procedures and cumulative construction achievements of the bridge; Step 2: identifying risks in the real-time construction procedures by using a fused risk identification matrix, and searching for corresponding risk factors in the cumulative construction achievements to construct a risk decomposition tree of the bridge; Step 3: transmitting historical storage data and field data of the bridge to a Bayesian network to trace risks and construct field risk grading rules of the bridge; Step 4: grading and evaluating the risk decomposition tree by using the field risk grading rules to obtain a plurality of risk positions of the bridge, generating a visual risk report and displaying the visual risk report; The step 1 comprises the following steps: Step 11: deriving a plurality of completed projects of the bridge according to real-time construction parameters of the bridge, drawing a bridge structure corresponding to each of the completed projects, determining a plurality of constructible positions corresponding to each of the bridge structures, matching each of the constructible positions with the real-time construction parameters, and determining a plurality of current construction positions of the bridge; Step 12: performing construction simulation at each of the current construction positions according to the real-time construction parameters to obtain a real-time construction model of the bridge, running the real-time construction model to obtain real-time construction characteristics corresponding to each of the current construction positions, and constructing a current construction state of the bridge; Step 13: determining coarse state logic between different current construction states according to construction time corresponding to each of the current construction states, fusing the current construction states corresponding to different construction times according to the coarse state logic, and identifying a plurality of fusion conflict points; Step 14: optimizing each of the fusion conflict points according to the real-time construction parameters to obtain a current fusion state of the bridge, searching for a plurality of current construction characteristics of the bridge in the current fusion state to generate real-time construction procedures, accumulating the real-time construction procedures corresponding to different construction times to obtain cumulative construction achievements of the bridge.

Images