Highway bridge bearing capacity detection device and use method thereof

Abstract

The invention discloses a highway bridge bearing capacity detection device and a use method thereof, and belongs to the technical field of highway bridge detection. The device comprises a multi-source data acquisition module for realizing omnibearing real-time data acquisition of bridge structural stress, environmental parameters and apparent characteristics; the edge calculation processing module is used for executing basic data processing, primary feature extraction, intelligent data compression and abnormal preliminary screening at a data source, and ensuring the balance between the data transmission efficiency and the processing real-time performance; the knowledge graph management module is used for constructing and maintaining a multi-level knowledge graph system covering bridge structure features, damage modes and historical cases; the intelligent analysis decision module is used for realizing intelligent decisions of bridge bearing capacity evaluation, risk early warning and detection strategy optimization; and the visual interaction module is used for realizing visual display, intelligent interaction, report management and authority management.

Description

Technical Field

[0001] The present application relates to the technical field of highway bridge detection, and more specifically, to a highway bridge load-bearing capacity detection device and a method for using the same. Background Art

[0002] With the acceleration of urbanization and the increase in transportation demand, highway bridges, as important infrastructure, are particularly important for their safety and carrying capacity. Existing bridge inspection technology mainly relies on manual inspection and traditional instruments and equipment, which makes it difficult to achieve comprehensive and real-time monitoring of bridge status. This method is not only inefficient, but also easily affected by human factors, and it is difficult to accurately reflect the actual health status of the bridge.

[0003] In recent years, with the development of sensor technology, Internet of Things and data processing technology, automated bridge inspection systems have gradually emerged. These systems can collect the stress, environmental parameters and surface characteristics of bridges in real time by deploying various sensing devices such as strain sensors and environmental monitoring equipment. However, existing technologies still have shortcomings in data processing and intelligent analysis. In particular, they cannot provide effective decision support in terms of data integration, processing efficiency and risk warning.

[0004] In addition, the application of knowledge graphs has not been fully explored in the field of bridge inspection. Knowledge graphs can effectively integrate and manage historical data, damage patterns and characteristics of bridges, and provide in-depth analysis and decision-making basis. However, existing systems often lack the ability to dynamically update and intelligently analyze knowledge graphs, resulting in the inability to timely identify potential risks and optimize inspection strategies.

[0005] To sum up, how to improve the real-time, intelligent and systematic performance of highway bridge bearing capacity detection has become a technical problem that needs to be solved urgently. Summary of the invention

[0006] In order to overcome a series of defects in the prior art, the purpose of this application is to provide a highway bridge bearing capacity detection device for the above-mentioned problems, including the following modules:

[0007] Multi-source data acquisition module, which realizes all-round real-time data acquisition of bridge structure stress, environmental parameters and surface characteristics;

[0008] The edge computing processing module performs basic data processing, primary feature extraction, intelligent data compression, and anomaly screening at the source of the data, ensuring a balance between data transmission efficiency and real-time processing.

[0009] Knowledge graph management module, which builds and maintains a multi-level knowledge graph system covering bridge structure characteristics, damage patterns and historical cases;

[0010] Intelligent analysis and decision-making module to achieve intelligent decision-making for bridge bearing capacity assessment, risk warning and detection strategy optimization;

[0011] Visual interaction module realizes visual display, intelligent interaction, report management and permission management.

[0012] Furthermore, the multi-source data acquisition module includes the following components:

[0013] Strain sensor arrays are deployed at key stress points of bridge structures to monitor structural stress distribution and deformation parameters in real time, and obtain basic data required for quantitative evaluation of bridge bearing capacity;

[0014] Environmental monitoring equipment collects environmental parameters in real time and evaluates the impact of environmental factors on bridge structural performance;

[0015] Visual acquisition equipment, integrated with high-resolution camera equipment or laser scanner, collects bridge surface characteristic data to provide auxiliary verification basis for stress-strain analysis;

[0016] Data acquisition control unit, which manages the acquisition process of various types of data, synchronizes and implements adaptive acquisition frequency adjustment;

[0017] The wireless transmission unit, based on low-power wide area network or cellular network technology, realizes efficient and reliable transmission of multi-source data, ensuring real-time transmission of data from the acquisition end to the edge computing processing module;

[0018] Distributed node controller coordinates distributed data collection nodes to ensure regional coverage and stability of data collection, and provides network health status monitoring and fault self-diagnosis functions.

[0019] Furthermore, the edge computing processing module includes the following components:

[0020] The data access unit is responsible for receiving data streams from multi-source data acquisition modules to ensure timely data access;

[0021] The data preprocessing unit performs preliminary cleaning and filtering on the received data to remove noise and invalid data;

[0022] The feature extraction unit extracts structural state features from the preprocessed data, realizes automatic recognition of time domain and frequency domain features, and constructs a multi-dimensional feature vector for state characterization;

[0023] Intelligent data compression unit, which uses adaptive compression algorithm to reduce data redundancy, optimize storage space while ensuring information integrity, and realize dynamic tuning of data transmission bandwidth;

[0024] The anomaly detection unit performs preliminary anomaly screening and promptly identifies potential data anomalies based on set thresholds;

[0025] The hierarchical processing unit adopts a hierarchical architecture to divide data processing tasks into different levels, reasonably allocate computing resources, and ensure that high-priority tasks can be processed in a timely manner.

[0026] Furthermore, the knowledge graph management module includes the following components:

[0027] The knowledge graph construction unit realizes the ontology modeling and structured representation of bridge domain knowledge, builds a multi-dimensional knowledge network including structural characteristics, damage patterns and historical cases, and establishes an entity relationship model and attribute feature mapping mechanism;

[0028] Multi-level data storage unit, using graph database to realize multi-dimensional knowledge storage, establishing hierarchical index structure to support efficient retrieval, and providing distributed storage solution to ensure data reliability;

[0029] The knowledge updating and maintenance unit monitors newly collected data and knowledge, automatically identifies and updates the information in the map to keep the knowledge current and accurate, and ensure that the map reflects the latest bridge health status;

[0030] The knowledge retrieval engine provides an efficient query mechanism, allowing users to quickly search and locate relevant knowledge and cases according to their needs, and supports multiple retrieval methods based on keywords, graph structures or contexts;

[0031] The reasoning engine integrates rule reasoning and machine learning algorithms, supports causal relationship deduction and knowledge discovery, and realizes cross-domain knowledge association analysis;

[0032] The knowledge optimization feedback unit builds a knowledge application effect evaluation system, optimizes the knowledge organization structure based on user feedback, and realizes the quantitative measurement and continuous optimization of knowledge value.

[0033] Furthermore, the ontology modeling and structured representation of bridge domain knowledge are realized, a multidimensional knowledge network including structural characteristics, damage patterns and historical cases is constructed, and an entity relationship model and attribute feature mapping mechanism are established, including the following steps:

[0034] Conduct systematic sorting and classification of professional knowledge in the field of bridges, including the concepts of bridge structure types, component composition, force characteristics and environmental influencing factors, and organize them hierarchically based on engineering practice experience and specifications and standards to form a preliminary ontology framework;

[0035] Based on the sorted knowledge system, the bridge domain ontology model is constructed to define the core concept classes, object attributes and data attributes, and at the same time establish the hierarchical relationship between concepts to form a complete semantic network structure;

[0036] Collect and organize historical bridge inspection cases, structure the case information according to the predefined ontology model, extract key features and attribute values, establish a case library containing multi-dimensional information including basic bridge information, inspection data, damage characteristics and treatment measures, and realize association mapping with ontology concepts through semantic annotation;

[0037] Design and implement entity relationship models, define association rules and constraints between entities, and associate different types of data with ontology concepts through attribute feature mapping to ensure semantic consistency and traceability of data;

[0038] Construct a multi-dimensional knowledge network, integrate the ontology model, case library and relational model through graph database technology, form a network structure with nodes representing entities and edges representing relationships, support semantic-based knowledge reasoning and association analysis, and realize multi-dimensional organization and flexible query of knowledge;

[0039] Develop knowledge verification and quality control mechanisms to ensure the accuracy and consistency of knowledge through rule verification and expert review, and establish knowledge updating mechanisms to support dynamic access to new knowledge and version management of historical knowledge to ensure the timeliness and maintainability of the knowledge graph.

[0040] Furthermore, the intelligent analysis and decision-making module includes the following components:

[0041] The data fusion processing unit integrates the data from the multi-source data acquisition module and the knowledge graph to form a unified multi-dimensional data set;

[0042] The load-bearing capacity assessment unit evaluates the load-bearing capacity of the bridge in real time based on multidimensional data sets and knowledge graphs, and provides analysis results of the bridge’s load-bearing capacity;

[0043] Risk warning unit, which monitors the health of the bridge in real time and automatically issues warnings when potential risks are detected so that preventive measures can be taken in a timely manner;

[0044] The detection strategy optimization unit intelligently generates and optimizes detection strategies based on the carrying capacity analysis results and historical data, and recommends the best detection methods and frequencies to improve the efficiency and effectiveness of detection;

[0045] Explainable analysis unit, which ensures the transparency of the analysis process by analyzing the contribution of key features and visualizing the basis for decision making;

[0046] The uncertainty assessment unit analyzes the uncertainty of the carrying capacity analysis results, quantitatively evaluates the confidence interval of the carrying capacity analysis results, and provides robustness analysis under multiple scenarios.

[0047] Furthermore, the bearing capacity of the bridge is evaluated in real time by the following formula: Among them, C(t) is the real-time bearing capacity of the bridge at time t, reflecting the maximum load that the bridge can withstand under current conditions; γ s is a coefficient defined according to the structural safety code, which is used to consider uncertainty and design redundancy; R i is the bearing capacity of the i-th key part; w i (t) is the real-time load of the i-th part at time t; n is the number of key parts in the bridge; D j (t) is the impact of the jth damage mode at time t; m represents the number of damage modes to be considered; K case is the correction factor for adjusting the current structural bearing capacity based on the historical data of bridges and typical case analysis in the knowledge graph; β is the weight parameter for adjusting the influence of historical data; T(t) is the temperature at time t; H(t) is the humidity at time t; L(t) is other environmental loads at time t; f env is the environmental correction function; μ is the weight of environmental impact, which is used to adjust the influence of the external environment on the carrying capacity assessment results.

[0048] Furthermore, the confidence interval of the carrying capacity analysis results is expressed as: Among them, CI α is the confidence interval of the bearing capacity assessment result, which is used to quantify the uncertainty of the bridge bearing capacity assessment; μ C is the average value of the bridge's bearing capacity assessment value in the current state; σ C is the standard deviation of the carrying capacity assessment results, reflecting the volatility under different assessment conditions; r represents the number of observation samples used for carrying capacity assessment; Z α / 2 is the critical value of the standard normal distribution, which is related to the confidence level α;

[0049] The robustness analysis under multiple scenarios is performed using the following formula: Where K is the number of different scenarios; For scenario S k The average value of the carrying capacity assessment under ; Scenario S k The confidence interval of the carrying capacity assessment results under R robust It is a robustness indicator for decision making and is used to evaluate the stability of evaluation results under different scenarios.

[0050] Furthermore, the data from the multi-source data collection module and the knowledge graph are integrated to form a unified multidimensional data set, including the following steps:

[0051] Comprehensively sort out and evaluate the data from the multi-source data collection module, and analyze the data structure and content of the knowledge graph, including the organization of entities, relationships, and attributes;

[0052] Based on the understanding of multi-source data and knowledge graphs, a multidimensional dataset is designed to accommodate all relevant information to reflect the characteristics of multidimensional data. At the same time, an integration solution for knowledge graph structured information and multidimensional datasets is designed.

[0053] According to the designed multidimensional data set, formulate detailed data mapping rules to map each field in the original data source to the corresponding position in the multidimensional data set;

[0054] Establish a mechanism to regularly obtain the latest data from various data sources, perform data transformation according to mapping rules, and load the transformed data into multidimensional datasets.

[0055] Furthermore, the visualization interaction module includes the following components:

[0056] The digital twin model building unit generates a three-dimensional digital twin model of the bridge based on real-time data and historical information, reflecting the physical state and health of the bridge in real time;

[0057] The visualization unit presents the digital twin model and related data in a graphical form, providing multiple perspectives and levels of detail to facilitate intuitive understanding of the structure and status of the bridge;

[0058] Interactive analysis unit, which allows users to explore data in a variety of interactive ways, conduct multi-dimensional analysis, support customized views and detailed inspection of key areas;

[0059] Intelligent report generation unit, which automatically generates bridge health reports based on user needs, summarizes analysis results, risk assessments and historical data, and supports export in multiple formats to facilitate subsequent management and decision-making;

[0060] The permission management unit controls user access and operation permissions, ensures the security of sensitive data and functions, and allows users of different roles to access relevant information according to their permissions;

[0061] The real-time data update unit continuously receives and updates the real-time data from the multi-source data acquisition module and the intelligent analysis and decision-making module to ensure that the information displayed on the visual interface always reflects the current bridge status;

[0062] The user feedback and optimization unit collects user feedback when using the visual interaction module to analyze user needs and usage experience, and regularly optimize the interface and functions.

[0063] The purpose of the present application is also to provide a method for using a highway bridge load-bearing capacity detection device, comprising the following steps:

[0064] According to the structural characteristics of the bridge, the strain sensor array is precisely installed at the key stress points to ensure that the sensor is in close contact with the bridge structure, and the signal calibration is completed at the same time to ensure the detection accuracy;

[0065] Install environmental monitoring equipment at appropriate locations around the bridge, ensuring that the equipment is stable and free from external interference so that environmental conditions can be continuously and accurately monitored;

[0066] Deploy visual acquisition equipment at important observation points on the bridge, and adjust the equipment angle and parameters to ensure that it can cover key areas and achieve effective image data acquisition;

[0067] Set the data collection frequency and establish a data synchronization mechanism to ensure the consistency of data collection timing between different sensors and ensure accurate fusion of multi-source data;

[0068] Establish a stable wireless transmission network, realize remote data transmission through low-power wide area network or cellular network, and test the connectivity of the network to ensure the stable transmission of real-time data;

[0069] Activate the strain sensor array, environmental monitoring equipment, and visual acquisition equipment to start collecting strain, environmental, and visual data in real time, and perform preliminary processing on the collected raw data to clean up noise and outliers;

[0070] Integrate multi-source data with knowledge graphs to calculate the load-bearing capacity of bridges, monitor bridge status in real time, and generate optimization suggestions and emergency plans based on detection results.

[0071] Compared with the prior art, the beneficial effects of this application are:

[0072] This application uses multi-source data collection, edge computing, knowledge graph management and intelligent analysis and decision-making modules to achieve all-round real-time data collection, processing and analysis of bridge structure stress, environmental parameters and surface characteristics, and provide intelligent bridge bearing capacity assessment and risk warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 This is a structural diagram of a highway bridge load-bearing capacity detection device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical scheme and advantages of the implementation of the present invention clearer, the technical scheme in the embodiment of the present invention will be described in more detail below in conjunction with the drawings in the embodiment of the present invention. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of the present invention, not all of the embodiments.

[0075] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0076] The embodiments and directional terms described below with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0077] like Figure 1 As shown, a highway bridge bearing capacity detection device includes the following modules:

[0078] Multi-source data acquisition module, which realizes all-round real-time data acquisition of bridge structure stress, environmental parameters and surface characteristics;

[0079] The edge computing processing module performs basic data processing, primary feature extraction, intelligent data compression, and anomaly screening at the source of the data, ensuring a balance between data transmission efficiency and real-time processing.

[0080] Knowledge graph management module, which builds and maintains a multi-level knowledge graph system covering bridge structure characteristics, damage patterns and historical cases;

[0081] Intelligent analysis and decision-making module to achieve intelligent decision-making for bridge bearing capacity assessment, risk warning and detection strategy optimization;

[0082] Visual interaction module realizes visual display, intelligent interaction, report management and permission management.

[0083] In this embodiment, the multi-source data acquisition module is the basis of the highway bridge bearing capacity detection device, and is responsible for comprehensive and real-time data acquisition of the structural stress, environmental parameters and apparent characteristics of the bridge. By integrating a variety of high-precision sensors, such as strain sensors, accelerometers, temperature sensors and humidity sensors, the module can monitor the dynamic behavior and environmental changes of the bridge in real time. This multi-dimensional data acquisition method not only improves the comprehensiveness and reliability of the data, but also provides rich raw data support for subsequent analysis. In addition, wireless communication technology is also used to quickly transmit the collected data to the edge computing processing module, ensuring the high efficiency and real-time nature of data transmission. Through real-time acquisition, the health status of the bridge can be understood at any time, and potential problems can be discovered in a timely manner, thereby effectively improving the safety and service life of the bridge.

[0084] In this embodiment, the edge computing processing module performs basic data processing and primary feature extraction at the data source, and can quickly analyze and process large amounts of data without relying on the central server. The module uses intelligent data compression technology to effectively compress the collected data, reduce the amount of data transmission, reduce bandwidth occupancy, and improve data transmission efficiency. At the same time, the edge computing module also has an abnormal initial screening function, which can identify and filter out potential abnormal data to reduce interference with subsequent analysis processes. This distributed computing method not only improves the real-time performance of data processing, but also reduces the burden on the central server and realizes the rational use of resources. Through edge computing, the operating status of the bridge can be fed back in the first time, and potential safety hazards can be quickly responded to, providing a timely basis for subsequent decision-making.

[0085] In this embodiment, the knowledge graph management module is responsible for building and maintaining a multi-level knowledge graph system covering bridge structural characteristics, damage patterns and historical cases. This module integrates expert knowledge and historical data to form a dynamically updated knowledge base, which can effectively support the work of the intelligent analysis and decision-making module. Through the knowledge graph, knowledge related to the status of a specific bridge can be quickly retrieved, potential risk patterns can be identified, and references can be provided in combination with historical cases. This visualization and structured management of knowledge makes the decision-making process more efficient and scientific, and reduces errors in manual judgment. In addition, the knowledge graph is scalable and can update itself as new data is continuously input to ensure that the system is always up to date. This provides strong support for the long-term monitoring and evaluation of bridges.

[0086] In this embodiment, the intelligent analysis and decision-making module is the core of the entire detection device, responsible for the evaluation of the bridge's bearing capacity, risk warning and optimization of the detection strategy. This module uses machine learning and data mining technology to conduct in-depth analysis of the collected multi-dimensional data, and can accurately identify the health status and bearing capacity of the bridge. This process can not only generate risk warnings in real time, but also optimize the detection strategy according to the actual situation of the bridge, and improve the pertinence and effectiveness of the detection. In addition, the decision-making function of the module supports flexible configuration, and can automatically adjust the evaluation algorithm and parameter settings according to different bridge characteristics and usage requirements to ensure the accuracy and operability of the analysis results. Through the intelligent decision-making process, the maintenance and management of the bridge can be more scientific and efficient, thereby reducing potential safety risks.

[0087] In this embodiment, the visualization interaction module realizes the visualization display of data and analysis results, intelligent interaction, report management and authority management. Through the friendly user interface, managers can intuitively view the health status, historical data and analysis results of the bridge. This module not only supports a variety of data visualization forms, such as charts, heat maps and three-dimensional models, but also can customize the display according to user needs. In addition, the intelligent interaction function allows users to interact with the system in real time, such as filtering, analyzing and generating reports on data, which greatly improves the user's operating experience and work efficiency. At the same time, the module also has a permission management function to ensure that users at different levels have corresponding access and operation permissions in the system, enhancing the security and flexibility of the system.

[0088] In summary, this highway bridge bearing capacity detection device achieves comprehensive monitoring and efficient management of bridge health status through the collaborative work of multi-source data collection, edge computing processing, knowledge graph management, intelligent analysis and decision-making, and visual interaction modules. The various modules not only support each other to form a complete data processing chain, but also improve the accuracy and efficiency of bridge monitoring through intelligent and automated methods. This advanced detection device provides a strong technical guarantee for the safe operation of bridges, can effectively prevent and reduce the occurrence of safety accidents, and promote the progress and development of bridge monitoring technology.

[0089] Furthermore, the multi-source data acquisition module includes the following components:

[0090] Strain sensor arrays are deployed at key stress points of bridge structures to monitor structural stress distribution and deformation parameters in real time, and obtain basic data required for quantitative evaluation of bridge bearing capacity;

[0091] Environmental monitoring equipment collects environmental parameters in real time and evaluates the impact of environmental factors on bridge structural performance;

[0092] Visual acquisition equipment, integrated with high-resolution camera equipment or laser scanner, collects bridge surface characteristic data to provide auxiliary verification basis for stress-strain analysis;

[0093] Data acquisition control unit, which manages the acquisition process of various types of data, synchronizes and implements adaptive acquisition frequency adjustment;

[0094] The wireless transmission unit, based on low-power wide area network or cellular network technology, realizes efficient and reliable transmission of multi-source data, ensuring real-time transmission of data from the acquisition end to the edge computing processing module;

[0095] Distributed node controller coordinates distributed data collection nodes to ensure regional coverage and stability of data collection, and provides network health status monitoring and fault self-diagnosis functions.

[0096] In summary, through an in-depth analysis of the various components of the multi-source data acquisition module, we can see that this module plays a vital role in the highway bridge bearing capacity detection device. The collaborative work of the strain sensor array, environmental monitoring equipment, visual acquisition equipment, data acquisition control unit, wireless transmission unit and distributed node controller can comprehensively and real-time monitor the health status of the bridge. The functions of each component complement each other, which not only improves the efficiency and accuracy of data acquisition, but also provides a solid foundation for subsequent data analysis and decision-making. This comprehensive monitoring solution provides important support for the safety management and maintenance decision-making of bridges, and greatly improves the safety and service life of highway bridges.

[0097] Furthermore, the edge computing processing module includes the following components:

[0098] The data access unit is responsible for receiving data streams from multi-source data acquisition modules to ensure timely data access;

[0099] The data preprocessing unit performs preliminary cleaning and filtering on the received data to remove noise and invalid data;

[0100] The feature extraction unit extracts structural state features from the preprocessed data, realizes automatic recognition of time domain and frequency domain features, and constructs a multi-dimensional feature vector for state characterization;

[0101] Intelligent data compression unit, which uses adaptive compression algorithm to reduce data redundancy, optimize storage space while ensuring information integrity, and realize dynamic tuning of data transmission bandwidth;

[0102] The anomaly detection unit performs preliminary anomaly screening and promptly identifies potential data anomalies based on set thresholds;

[0103] The hierarchical processing unit adopts a hierarchical architecture to divide data processing tasks into different levels, reasonably allocate computing resources, and ensure that high-priority tasks can be processed in a timely manner.

[0104] In the edge computing processing module, various components work together to achieve efficient data processing and status monitoring. First of all, the data access unit is the front end of the entire module, and it undertakes the key task of receiving data streams from multi-source data acquisition modules. Its innovation lies in ensuring timely access to data and ensuring the ability to respond to real-time data. In practical applications, the data access unit needs to be able to handle various data formats and protocols to adapt to the output of different devices and sensors. At the same time, it also needs to have the characteristics of high bandwidth and low latency to support fast data transmission and processing. Effective data access not only helps to improve real-time performance, but also provides a stable foundation for subsequent data preprocessing and analysis.

[0105] Next, the data preprocessing unit is responsible for the preliminary cleaning and filtering of the received data, which is crucial to ensuring data quality. Its innovation lies in the removal of noise and invalid data. Through a series of algorithms such as filtering, denoising and standardization, it ensures that the data entering the subsequent analysis link is accurate and reliable. Data preprocessing can also significantly improve the efficiency of subsequent processing and reduce the consumption of computing resources. In addition, it provides high-quality data input for the feature extraction unit, thereby improving the accuracy and efficiency of feature recognition. Therefore, the effectiveness of the data preprocessing unit directly affects the performance of the entire edge computing processing module and the reliability of the final analysis results.

[0106] Then, the innovation of the feature extraction unit is to extract structural state features from the preprocessed data. This process converts complex data into structured information through automatic recognition of time domain and frequency domain features, forming a multi-dimensional feature vector for state characterization. Feature extraction can not only improve the efficiency of data analysis, but also enhance the model's ability to understand and recognize data patterns.

[0107] Furthermore, the intelligent data compression unit uses an adaptive compression algorithm to reduce data redundancy. Its innovation lies in optimizing storage space while ensuring information integrity, helping to achieve dynamic tuning of data transmission bandwidth. As the amount of data continues to increase, how to effectively store and transmit data has become an important challenge. Intelligent data compression can improve storage efficiency and reduce the bandwidth required for data transmission by reducing redundant information, thereby improving overall response speed. Effective data compression strategies can also ensure data integrity and availability when the network environment is poor, ensuring system stability.

[0108] In addition, the anomaly detection unit is responsible for implementing preliminary anomaly screening and timely identifying potential data anomalies based on the set thresholds. Its innovation lies in the ability to monitor data flows in real time, quickly discover anomalies, and improve the ability to respond to anomalies. Anomaly detection not only helps ensure the reliability of data, but also provides a basis for decision-making and reduces risks.

[0109] Finally, the hierarchical processing unit adopts a hierarchical architecture to divide data processing tasks into different levels and reasonably allocate computing resources to ensure that high-priority tasks can be processed in a timely manner. Its innovation lies in improving the processing efficiency and responsiveness of the system. When faced with a large number of concurrent tasks, hierarchical processing can effectively manage resources and avoid performance bottlenecks caused by resource competition. By dynamically adjusting the processing strategies of different levels, the hierarchical processing unit can reasonably allocate computing resources according to the priority of the task and achieve efficient data processing.

[0110] In summary, the edge computing processing module effectively improves the real-time and accuracy of data processing through the collaborative work of multiple links such as data access, preprocessing, feature extraction, intelligent compression, anomaly detection and hierarchical processing. The comprehensive application of this module not only provides a solid foundation for data-driven decision-making, but also lays a good foundation for the construction of intelligent monitoring and management mechanisms.

[0111] Furthermore, the knowledge graph management module includes the following components:

[0112] The knowledge graph construction unit realizes the ontology modeling and structured representation of bridge domain knowledge, builds a multi-dimensional knowledge network including structural characteristics, damage patterns and historical cases, and establishes an entity relationship model and attribute feature mapping mechanism;

[0113] Multi-level data storage unit, using graph database to realize multi-dimensional knowledge storage, establishing hierarchical index structure to support efficient retrieval, and providing distributed storage solution to ensure data reliability;

[0114] The knowledge updating and maintenance unit monitors newly collected data and knowledge, automatically identifies and updates the information in the map to keep the knowledge current and accurate, and ensure that the map reflects the latest bridge health status;

[0115] The knowledge retrieval engine provides an efficient query mechanism, allowing users to quickly search and locate relevant knowledge and cases according to their needs, and supports multiple retrieval methods based on keywords, graph structures or contexts;

[0116] The reasoning engine integrates rule reasoning and machine learning algorithms, supports causal relationship deduction and knowledge discovery, and realizes cross-domain knowledge association analysis;

[0117] The knowledge optimization feedback unit builds a knowledge application effect evaluation system, optimizes the knowledge organization structure based on user feedback, and realizes the quantitative measurement and continuous optimization of knowledge value.

[0118] In summary, the knowledge graph management module plays an indispensable role in the highway bridge bearing capacity detection device. Through the efficient collaboration of the knowledge graph construction unit, multi-level data storage unit, knowledge update and maintenance unit, knowledge retrieval engine, reasoning engine and knowledge optimization feedback unit, this module not only improves the storage and management capabilities of knowledge, but also enhances the intelligent analysis and decision support of information. The dynamic update and optimization of the knowledge graph can always keep pace with the times, providing a scientific basis for the health management of bridges. In summary, the design and implementation of the knowledge graph management module significantly improves the overall intelligence level of the highway bridge bearing capacity detection device, and provides strong support for maintenance and management work.

[0119] Furthermore, the ontology modeling and structured representation of bridge domain knowledge are realized, a multidimensional knowledge network including structural characteristics, damage patterns and historical cases is constructed, and an entity relationship model and attribute feature mapping mechanism are established, including the following steps:

[0120] Conduct systematic sorting and classification of professional knowledge in the field of bridges, including the concepts of bridge structure types, component composition, force characteristics and environmental influencing factors, and organize them hierarchically based on engineering practice experience and specifications and standards to form a preliminary ontology framework;

[0121] Based on the sorted knowledge system, the bridge domain ontology model is constructed to define the core concept classes, object attributes and data attributes, and at the same time establish the hierarchical relationship between concepts to form a complete semantic network structure;

[0122] Collect and organize historical bridge inspection cases, structure the case information according to the predefined ontology model, extract key features and attribute values, establish a case library containing multi-dimensional information including basic bridge information, inspection data, damage characteristics and treatment measures, and realize association mapping with ontology concepts through semantic annotation;

[0123] Design and implement entity relationship models, define association rules and constraints between entities, and associate different types of data with ontology concepts through attribute feature mapping to ensure semantic consistency and traceability of data;

[0124] Construct a multi-dimensional knowledge network, integrate the ontology model, case library and relational model through graph database technology, form a network structure with nodes representing entities and edges representing relationships, support semantic-based knowledge reasoning and association analysis, and realize multi-dimensional organization and flexible query of knowledge;

[0125] Develop knowledge verification and quality control mechanisms to ensure the accuracy and consistency of knowledge through rule verification and expert review, and establish knowledge updating mechanisms to support dynamic access to new knowledge and version management of historical knowledge to ensure the timeliness and maintainability of the knowledge graph.

[0126] In summary, ontology modeling and structured representation of knowledge in the bridge field is a systematic and complex process, covering multiple steps such as knowledge combing, model construction, case organization, entity relationship design, knowledge network construction and quality control. Each step complements each other and lays the foundation for building an efficient and accurate knowledge graph. This knowledge graph can not only enhance the knowledge management capabilities in the bridge field, but also provide strong support for subsequent intelligent decision-making, and promote the digitalization and intelligentization of bridge engineering.

[0127] Furthermore, the intelligent analysis and decision-making module includes the following components:

[0128] The data fusion processing unit integrates the data from the multi-source data acquisition module and the knowledge graph to form a unified multi-dimensional data set;

[0129] The load-bearing capacity assessment unit evaluates the load-bearing capacity of the bridge in real time based on multidimensional data sets and knowledge graphs, and provides analysis results of the bridge’s load-bearing capacity;

[0130] Risk warning unit, which monitors the health of the bridge in real time and automatically issues warnings when potential risks are detected so that preventive measures can be taken in a timely manner;

[0131] The detection strategy optimization unit intelligently generates and optimizes detection strategies based on the carrying capacity analysis results and historical data, and recommends the best detection methods and frequencies to improve the efficiency and effectiveness of detection;

[0132] Explainable analysis unit, which ensures the transparency of the analysis process by analyzing the contribution of key features and visualizing the basis for decision making;

[0133] The uncertainty assessment unit analyzes the uncertainty of the carrying capacity analysis results, quantitatively evaluates the confidence interval of the carrying capacity analysis results, and provides robustness analysis under multiple scenarios.

[0134] In summary, the intelligent analysis and decision-making module builds a comprehensive, dynamic and intelligent decision-making support mechanism through the collaboration of components such as data fusion, load-bearing capacity assessment, risk warning, detection strategy optimization, explainability analysis and uncertainty assessment. This module not only improves the real-time and accuracy of bridge health monitoring, but also enhances the scientificity and effectiveness of decision-making, providing strong support for the safety management and maintenance of bridges.

[0135] Furthermore, the bearing capacity of the bridge is evaluated in real time by the following formula: Among them, C(t) is the real-time bearing capacity of the bridge at time t, reflecting the maximum load that the bridge can withstand under current conditions; γ s is a coefficient defined according to the structural safety code, which is used to consider uncertainty and design redundancy; R i is the bearing capacity of the i-th key part; w i (t) is the real-time load of the i-th part at time t; n is the number of key parts in the bridge; D j (t) is the impact of the jth damage mode at time t; m represents the number of damage modes to be considered; K case is the correction factor for adjusting the current structural bearing capacity based on the historical data of bridges and typical case analysis in the knowledge graph; β is the weight parameter for adjusting the influence of historical data; T(t) is the temperature at time t; H(t) is the humidity at time t; L(t) is other environmental loads at time t; fenv is the environmental correction function; μ is the weight of environmental impact, which is used to adjust the influence of the external environment on the carrying capacity assessment results.

[0136] By applying the above formula, it is possible to dynamically evaluate the bearing capacity of bridges, identify potential risks in a timely manner and provide support for decision-making. This real-time evaluation not only takes into account the structural characteristics and historical data of the bridge, but also effectively integrates external environmental factors to ensure that the analysis of bearing capacity is comprehensive and accurate.

[0137] Furthermore, the confidence interval of the carrying capacity analysis results is expressed as: Among them, CI α is the confidence interval of the bearing capacity assessment result, which is used to quantify the uncertainty of the bridge bearing capacity assessment; μ C is the average value of the bridge's bearing capacity assessment value in the current state; σ C is the standard deviation of the carrying capacity assessment results, reflecting the volatility under different assessment conditions; r represents the number of observation samples used for carrying capacity assessment; Z α / 2 is the critical value of the standard normal distribution, which is related to the confidence level α;

[0138] The robustness analysis under multiple scenarios is performed using the following formula: Where K is the number of different scenarios; For scenario S k The average value of the carrying capacity assessment under ; Scenario S k The confidence interval of the carrying capacity assessment results under R robust It is a robustness indicator for decision making and is used to evaluate the stability of evaluation results under different scenarios.

[0139] In summary, by calculating the confidence interval of the load-bearing capacity assessment results and conducting robustness analysis under multiple scenarios, we can comprehensively assess the uncertainty of the bridge's load-bearing capacity and its sensitivity to changes in the external environment. This process not only enhances the understanding of bridge safety, but also provides strong data support for decision makers to ensure that reasonable and scientific maintenance and management decisions can be made under changing environmental conditions.

[0140] Furthermore, the data from the multi-source data collection module and the knowledge graph are integrated to form a unified multidimensional data set, including the following steps:

[0141] Comprehensively sort out and evaluate the data from the multi-source data collection module, and analyze the data structure and content of the knowledge graph, including the organization of entities, relationships, and attributes;

[0142] Based on the understanding of multi-source data and knowledge graphs, a multidimensional dataset is designed to accommodate all relevant information to reflect the characteristics of multidimensional data. At the same time, an integration solution for knowledge graph structured information and multidimensional datasets is designed.

[0143] According to the designed multidimensional data set, formulate detailed data mapping rules to map each field in the original data source to the corresponding position in the multidimensional data set;

[0144] Establish a mechanism to regularly obtain the latest data from various data sources, perform data transformation according to mapping rules, and load the transformed data into multidimensional datasets.

[0145] In summary, through the above steps, the data from the multi-source data acquisition module and the knowledge graph are integrated into a unified multidimensional data set, which provides a solid foundation for subsequent data analysis and decision support. This process not only improves the efficiency of data integration, but also ensures the accuracy and reliability of the data, so that the multidimensional data set can effectively support complex analysis needs. At the same time, the establishment of a dynamic update mechanism also ensures the real-time and relevance of the data set, providing a guarantee for organizations to make timely and accurate decisions in a rapidly changing environment.

[0146] Furthermore, the visualization interaction module includes the following components:

[0147] The digital twin model building unit generates a three-dimensional digital twin model of the bridge based on real-time data and historical information, reflecting the physical state and health of the bridge in real time;

[0148] The visualization unit presents the digital twin model and related data in a graphical form, providing multiple perspectives and levels of detail to facilitate intuitive understanding of the structure and status of the bridge;

[0149] Interactive analysis unit, which allows users to explore data in a variety of interactive ways, conduct multi-dimensional analysis, support customized views and detailed inspection of key areas;

[0150] Intelligent report generation unit, which automatically generates bridge health reports based on user needs, summarizes analysis results, risk assessments and historical data, and supports export in multiple formats to facilitate subsequent management and decision-making;

[0151] The permission management unit controls user access and operation permissions, ensures the security of sensitive data and functions, and allows users of different roles to access relevant information according to their permissions;

[0152] The real-time data update unit continuously receives and updates the real-time data from the multi-source data acquisition module and the intelligent analysis and decision-making module to ensure that the information displayed on the visual interface always reflects the current bridge status;

[0153] The user feedback and optimization unit collects user feedback when using the visual interaction module to analyze user needs and usage experience, and regularly optimize the interface and functions.

[0154] In summary, the visualization interaction module provides comprehensive support for bridge health monitoring and management by integrating multiple functional components such as digital twin model construction, visualization display, interactive analysis, intelligent report generation, authority management, real-time data update and user feedback. This module not only improves the efficiency of data visualization, but also enhances the intuitiveness and accuracy of users in bridge management decisions. Through continuous optimization and updating, it can ensure that the system always stays at the forefront of technology to better meet the complex needs of bridge safety management. Overall, the effective implementation of the visualization interaction module not only improves the safety monitoring capabilities of bridges, but also provides strong support for decision makers to ensure that the bridge is always in the best condition during operation.

[0155] The purpose of the present application is also to provide a method for using a highway bridge load-bearing capacity detection device, comprising the following steps:

[0156] According to the structural characteristics of the bridge, the strain sensor array is precisely installed at the key stress points to ensure that the sensor is in close contact with the bridge structure, and the signal calibration is completed at the same time to ensure the detection accuracy;

[0157] Install environmental monitoring equipment at appropriate locations around the bridge, ensuring that the equipment is stable and free from external interference so that environmental conditions can be continuously and accurately monitored;

[0158] Deploy visual acquisition equipment at important observation points on the bridge, and adjust the equipment angle and parameters to ensure that it can cover key areas and achieve effective image data acquisition;

[0159] Set the data collection frequency and establish a data synchronization mechanism to ensure the consistency of data collection timing between different sensors and ensure accurate fusion of multi-source data;

[0160] Establish a stable wireless transmission network, realize remote data transmission through low-power wide area network or cellular network, and test the connectivity of the network to ensure the stable transmission of real-time data;

[0161] Activate the strain sensor array, environmental monitoring equipment, and visual acquisition equipment to start collecting strain, environmental, and visual data in real time, and perform preliminary processing on the collected raw data to clean up noise and outliers;

[0162] Integrate multi-source data with knowledge graphs to calculate the load-bearing capacity of bridges, monitor bridge status in real time, and generate optimization suggestions and emergency plans based on detection results.

[0163] In summary, a series of precise steps and technologies have been used to achieve comprehensive monitoring and evaluation of bridge conditions. From the precise installation of strain sensors, the stable layout of environmental monitoring, to the effective deployment of visual equipment and the establishment of a data synchronization mechanism, each link lays the foundation for subsequent data processing and analysis. Ultimately, through the fusion and analysis of multi-source data, not only can the bridge status be monitored in real time, but also optimization suggestions can be provided to decision makers to ensure the safety and stability of the bridge during long-term use.

[0164] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A highway bridge bearing capacity detection device, characterized in that: Includes the following modules: Multi-source data acquisition module, which realizes all-round real-time data acquisition of bridge structure stress, environmental parameters and surface characteristics; The edge computing processing module performs basic data processing, primary feature extraction, intelligent data compression, and anomaly screening at the source of the data, ensuring a balance between data transmission efficiency and real-time processing. Knowledge graph management module, which builds and maintains a multi-level knowledge graph system covering bridge structure characteristics, damage patterns and historical cases; Intelligent analysis and decision-making module to achieve intelligent decision-making for bridge bearing capacity assessment, risk warning and detection strategy optimization; Visual interaction module realizes visual display, intelligent interaction, report management and permission management.

2. A highway bridge bearing capacity detection device according to claim 1, characterized in that: The multi-source data acquisition module includes the following components: Strain sensor arrays are deployed at key stress points of bridge structures to monitor structural stress distribution and deformation parameters in real time, and obtain basic data required for quantitative evaluation of bridge bearing capacity; Environmental monitoring equipment collects environmental parameters in real time and evaluates the impact of environmental factors on bridge structural performance; Visual acquisition equipment, integrated with high-resolution camera equipment or laser scanner, collects bridge surface characteristic data to provide auxiliary verification basis for stress-strain analysis; Data acquisition control unit, which manages the acquisition process of various types of data, synchronizes and implements adaptive acquisition frequency adjustment; The wireless transmission unit, based on low-power wide area network or cellular network technology, realizes efficient and reliable transmission of multi-source data, ensuring real-time transmission of data from the acquisition end to the edge computing processing module; Distributed node controller coordinates distributed data collection nodes to ensure regional coverage and stability of data collection, and provides network health status monitoring and fault self-diagnosis functions.

3. A highway bridge bearing capacity detection device according to claim 1, characterized in that: The edge computing processing module includes the following components: The data access unit is responsible for receiving data streams from multi-source data acquisition modules to ensure timely data access; The data preprocessing unit performs preliminary cleaning and filtering on the received data to remove noise and invalid data; The feature extraction unit extracts structural state features from the preprocessed data, realizes automatic recognition of time domain and frequency domain features, and constructs a multi-dimensional feature vector for state characterization; Intelligent data compression unit, which uses adaptive compression algorithm to reduce data redundancy, optimize storage space while ensuring information integrity, and realize dynamic tuning of data transmission bandwidth; The anomaly detection unit performs preliminary anomaly screening and promptly identifies potential data anomalies based on set thresholds; The hierarchical processing unit adopts a hierarchical architecture to divide data processing tasks into different levels, reasonably allocate computing resources, and ensure that high-priority tasks can be processed in a timely manner.

4. A highway bridge bearing capacity detection device according to claim 1, characterized in that: The knowledge graph management module includes the following components: The knowledge graph construction unit realizes the ontology modeling and structured representation of bridge domain knowledge, builds a multi-dimensional knowledge network including structural characteristics, damage patterns and historical cases, and establishes an entity relationship model and attribute feature mapping mechanism; Multi-level data storage unit, using graph database to realize multi-dimensional knowledge storage, establishing hierarchical index structure to support efficient retrieval, and providing distributed storage solution to ensure data reliability; The knowledge updating and maintenance unit monitors newly collected data and knowledge, automatically identifies and updates the information in the map to keep the knowledge current and accurate, and ensure that the map reflects the latest bridge health status; The knowledge retrieval engine provides an efficient query mechanism, allowing users to quickly search and locate relevant knowledge and cases according to their needs, and supports multiple retrieval methods based on keywords, graph structures or contexts; The reasoning engine integrates rule reasoning and machine learning algorithms, supports causal relationship deduction and knowledge discovery, and realizes cross-domain knowledge association analysis; The knowledge optimization feedback unit builds a knowledge application effect evaluation system, optimizes the knowledge organization structure based on user feedback, and realizes the quantitative measurement and continuous optimization of knowledge value.

5. A highway bridge load-bearing capacity detection device according to claim 4, characterized in that: To realize the ontology modeling and structured representation of bridge domain knowledge, build a multidimensional knowledge network including structural characteristics, damage patterns and historical cases, and establish an entity relationship model and attribute feature mapping mechanism, including the following steps: Conduct systematic sorting and classification of professional knowledge in the field of bridges, including the concepts of bridge structure types, component composition, force characteristics and environmental influencing factors, and organize them hierarchically based on engineering practice experience and specifications and standards to form a preliminary ontology framework; Based on the sorted knowledge system, the bridge domain ontology model is constructed to define the core concept classes, object attributes and data attributes, and at the same time establish the hierarchical relationship between concepts to form a complete semantic network structure; Collect and organize historical bridge inspection cases, structure the case information according to the predefined ontology model, extract key features and attribute values, establish a case library containing multi-dimensional information including basic bridge information, inspection data, damage characteristics and treatment measures, and realize association mapping with ontology concepts through semantic annotation; Design and implement entity relationship models, define association rules and constraints between entities, and associate different types of data with ontology concepts through attribute feature mapping to ensure semantic consistency and traceability of data; Construct a multi-dimensional knowledge network, integrate the ontology model, case library and relational model through graph database technology, form a network structure with nodes representing entities and edges representing relationships, support semantic-based knowledge reasoning and association analysis, and realize multi-dimensional organization and flexible query of knowledge; Develop knowledge verification and quality control mechanisms to ensure the accuracy and consistency of knowledge through rule verification and expert review, and establish knowledge updating mechanisms to support dynamic access to new knowledge and version management of historical knowledge to ensure the timeliness and maintainability of the knowledge graph.

6. A highway bridge bearing capacity detection device according to claim 1, characterized in that: The intelligent analysis and decision-making module includes the following components: The data fusion processing unit integrates the data from the multi-source data acquisition module and the knowledge graph to form a unified multi-dimensional data set; The load-bearing capacity assessment unit evaluates the load-bearing capacity of the bridge in real time based on multidimensional data sets and knowledge graphs, and provides analysis results of the bridge’s load-bearing capacity; Risk warning unit, which monitors the health of the bridge in real time and automatically issues warnings when potential risks are detected so that preventive measures can be taken in a timely manner; The detection strategy optimization unit intelligently generates and optimizes detection strategies based on the carrying capacity analysis results and historical data, and recommends the best detection methods and frequencies to improve the efficiency and effectiveness of detection; Explainable analysis unit, which ensures the transparency of the analysis process by analyzing the contribution of key features and visualizing the basis for decision making; The uncertainty assessment unit analyzes the uncertainty of the carrying capacity analysis results, quantitatively evaluates the confidence interval of the carrying capacity analysis results, and provides robustness analysis under multiple scenarios.

7. A highway bridge load-bearing capacity detection device according to claim 6, characterized in that: The bearing capacity of the bridge is evaluated in real time using the following formula: Among them, C(t) is the real-time bearing capacity of the bridge at time t, reflecting the maximum load that the bridge can withstand under current conditions; γ s is a coefficient defined according to the structural safety code, which is used to consider uncertainty and design redundancy; R i is the bearing capacity of the i-th key part; w i (t) is the real-time load of the i-th part at time t; n is the number of key parts in the bridge; D j (t) is the impact of the jth damage mode at time t; m represents the number of damage modes to be considered; K case is the correction factor for adjusting the current structural bearing capacity based on the historical data of bridges and typical case analysis in the knowledge graph; β is the weight parameter for adjusting the influence of historical data; T(t) is the temperature at time t; H(t) is the humidity at time t; L(t) is other environmental loads at time t; f env is the environmental correction function; μ is the weight of environmental impact, which is used to adjust the influence of the external environment on the carrying capacity assessment results; The confidence interval of the carrying capacity analysis results is expressed as: Among them, CI α is the confidence interval of the bearing capacity assessment result, which is used to quantify the uncertainty of the bridge bearing capacity assessment; μ C is the average value of the bridge's bearing capacity assessment value in the current state; σ C is the standard deviation of the carrying capacity assessment results, reflecting the volatility under different assessment conditions; r represents the number of observation samples used for carrying capacity assessment; Z α / 2 is the critical value of the standard normal distribution, which is related to the confidence level α; The robustness analysis under multiple scenarios is performed using the following formula: Where K is the number of different scenarios; For scenario S k The average value of the carrying capacity assessment under ; Scenario S k The confidence interval of the carrying capacity assessment results under R robust It is a robustness indicator for decision making and is used to evaluate the stability of evaluation results under different scenarios.

8. A highway bridge load-bearing capacity detection device according to claim 6, characterized in that: Integrate the data from the multi-source data collection module and the knowledge graph to form a unified multidimensional data set, including the following steps: Comprehensively sort out and evaluate the data from the multi-source data collection module, and analyze the data structure and content of the knowledge graph, including the organization of entities, relationships, and attributes; Based on the understanding of multi-source data and knowledge graphs, a multidimensional dataset is designed to accommodate all relevant information to reflect the characteristics of multidimensional data. At the same time, an integration solution for knowledge graph structured information and multidimensional datasets is designed. According to the designed multidimensional data set, formulate detailed data mapping rules to map each field in the original data source to the corresponding position in the multidimensional data set; Establish a mechanism to regularly obtain the latest data from various data sources, perform data transformation according to mapping rules, and load the transformed data into multidimensional datasets.

9. A highway bridge bearing capacity detection device according to claim 1, characterized in that: The visual interaction module includes the following components: The digital twin model building unit generates a three-dimensional digital twin model of the bridge based on real-time data and historical information, reflecting the physical state and health of the bridge in real time; The visualization unit presents the digital twin model and related data in a graphical form, providing multiple perspectives and levels of detail to facilitate intuitive understanding of the structure and status of the bridge; Interactive analysis unit, which allows users to explore data in a variety of interactive ways, conduct multi-dimensional analysis, support customized views and detailed inspection of key areas; Intelligent report generation unit, which automatically generates bridge health reports based on user needs, summarizes analysis results, risk assessments and historical data, and supports export in multiple formats to facilitate subsequent management and decision-making; The permission management unit controls user access and operation permissions, ensures the security of sensitive data and functions, and allows users of different roles to access relevant information according to their permissions; The real-time data update unit continuously receives and updates the real-time data from the multi-source data acquisition module and the intelligent analysis and decision-making module to ensure that the information displayed on the visual interface always reflects the current bridge status; The user feedback and optimization unit collects user feedback when using the visual interaction module to analyze user needs and usage experience, and regularly optimize the interface and functions.

10. A method for using a highway bridge load-bearing capacity detection device, implemented based on a highway bridge load-bearing capacity detection device according to any one of claims 1 to 9, characterized in that: The following steps are involved: According to the structural characteristics of the bridge, the strain sensor array is precisely installed at the key stress points to ensure that the sensor is in close contact with the bridge structure, and the signal calibration is completed at the same time to ensure the detection accuracy; Install environmental monitoring equipment at appropriate locations around the bridge, ensuring that the equipment is stable and free from external interference so that environmental conditions can be continuously and accurately monitored; Deploy visual acquisition equipment at important observation points on the bridge, and adjust the equipment angle and parameters to ensure that it can cover key areas and achieve effective image data acquisition; Set the data collection frequency and establish a data synchronization mechanism to ensure the consistency of data collection timing between different sensors and ensure accurate fusion of multi-source data; Establish a stable wireless transmission network, realize remote data transmission through low-power wide area network or cellular network, and test the connectivity of the network to ensure the stable transmission of real-time data; Activate the strain sensor array, environmental monitoring equipment, and visual acquisition equipment to start collecting strain, environmental, and visual data in real time, and perform preliminary processing on the collected raw data to clean up noise and outliers; Integrate multi-source data with knowledge graphs to calculate the load-bearing capacity of bridges, monitor bridge status in real time, and generate optimization suggestions and emergency plans based on detection results.

Images