Intelligent bridge monitoring system and method based on wireless communication

Abstract

The invention relates to the technical field of bridge monitoring, in particular to an intelligent bridge monitoring system and method based on wireless communication, and the system comprises six modules: a digital twin engine module constructs a three-dimensional virtual model synchronous with a physical bridge; the information acquisition module acquires real-time operation data; the data fusion processing module fuses the real-time data, the cable static asset data and the historical operation and maintenance data and maps the data to a virtual entity; the knowledge graph construction and reasoning module realizes fault root tracing and influence analysis by means of entity association analysis and a Bayesian probability model; the early warning module judges the fault level, pushes a differential cooperation instruction and generates a customized diagnosis report; the simulation deduction module supports parameter modification, simulates a future state through a physical model, and visually outputs risk assessment. According to the invention, bridge frame virtual-real linkage monitoring, accurate fault handling and active risk pre-judgment are realized, and the operation and maintenance intelligence level and the system reliability are improved.

Description

Technical Field

[0001] This invention relates to the field of cable tray monitoring technology, and more specifically, to an intelligent cable tray monitoring system and method based on wireless communication. Background Technology

[0002] The intelligent cable tray monitoring system is a modern cable tray (cable tray) management system that integrates sensors, data acquisition modules, communication equipment, and software platforms. It transcends the traditional physical function of cable trays as merely supports and carries cables, using Internet of Things (IoT) technology to provide real-time, remote, and automated monitoring, early warning, and management of the internal environment of the cable tray, the status of the cables, and the health of the cable tray itself.

[0003] Existing technology involves deploying various sensors (such as temperature and leak detectors) inside the cable tray or at key nodes to collect environmental data in real time. The data is then uploaded to a centralized monitoring platform via wired or wireless communication technologies (such as LoRa and NB-IoT). Finally, the software system analyzes and displays the data and issues warnings when anomalies occur, thus achieving remote centralized management.

[0004] The existing technology has the following shortcomings, specifically: 1. Data is disconnected from physical objects, resulting in poor monitoring intuitiveness: Traditional cable tray monitoring mostly involves isolated parameter monitoring (such as measuring only temperature / current). The data lacks spatial correlation with physical equipment, and maintenance personnel need to manually match the data with the on-site location, which is inefficient, error-prone, and unable to form a global understanding.

[0005] 2. The fault source is unclear and the coordination of handling is weak: The existing system can only detect anomalies through threshold alarms, but it cannot trace the root cause of the fault (such as it is difficult to distinguish whether the temperature exceeds the standard due to cable aging or insufficient heat dissipation), and it is also difficult to analyze the downstream impact. In addition, the instruction push is singular and lacks cross-departmental coordination, resulting in insufficient targeting and efficiency of handling.

[0006] 3. Lack of future risk prediction and passive operation and maintenance: Existing technology lacks physical model simulation capabilities, making it impossible to predict the potential risks of parameter adjustments (such as adding cables or increasing load). Operation and maintenance decisions rely on experience, which can easily lead to over-maintenance or maintenance omissions, and it is difficult to avoid failures in advance. Summary of the Invention

[0007] The purpose of this invention is to provide an intelligent cable tray monitoring system and method based on wireless communication to solve the problems mentioned in the background art.

[0008] To achieve the above objectives, the present invention aims to provide an intelligent cable tray monitoring system based on wireless communication, comprising: a digital twin engine module: used to construct and render a digital twin synchronized with the physical entity based on the three-dimensional scanning data of the physical cable tray.

[0009] information acquisition module: for collecting real-time running state data of the bridge.

[0010] data fusion processing module: for obtaining static asset data and historical operation and maintenance data of the cable from the database, fusing the real-time running state data of the bridge, the static asset data and the historical operation and maintenance data of the cable, and mapping the corresponding virtual entity in the digital twin.

[0011] knowledge graph construction and reasoning module: for constructing a knowledge graph and receiving the output of the data fusion processing module, and performing fault root cause tracing and impact analysis when monitoring data anomalies.

[0012] early warning module: for receiving the fault tracing result of the knowledge graph, judging the fault level, pushing the collaborative disposal instruction to the terminal in parallel, and automatically generating a customized diagnostic report.

[0013] simulation and deduction module: for allowing a user to modify parameters on the digital twin, simulating future system states based on physical models, and outputting risk assessment in a visual manner.

[0014] Preferably, the fusing of the real-time running state data of the bridge, the static asset data and the historical operation and maintenance data of the cable is implemented by binding the real-time running state data as dynamic attributes to the virtual sensors of the digital twin, binding the specifications, models, rated currents and laying dates of the cables as static attributes to the virtual cables of the digital twin, and associating the historical work orders and maintenance records as time series attributes with the corresponding virtual entities.

[0015] Preferably, the construction of the knowledge graph is implemented by taking the cable, the sensor and the power distribution device as core entities and defining the specifications, parameters and operation and maintenance attributes of each entity, constructing three types of core relationships including electrical connection, spatial position and functional role among the entities by analyzing the electrical schematic diagram, the three-dimensional scanning data and the operation and maintenance documents, integrating the device account, the design drawings and the operation and maintenance records to complete the initialization of the graph, and dynamically updating the entity attributes and the associated relationships based on the entity state change data and the bridge structure adjustment information to form a knowledge graph that reflects the association of the bridge system in real time.

[0016] Preferably, the fault root cause tracing and impact analysis is implemented by taking the entity corresponding to the monitoring data anomaly as the starting point, traversing the electrical, spatial and functional associated nodes of the entity in the knowledge graph, combining the entity attributes and historical operation data, locating the core root cause leading to the anomaly through logical reasoning, calculating the confidence of each root node based on the Bayesian probability model, outputting the probability-ordered traceability list, and analyzing the downstream entities affected by the anomaly along the associated relationship chain to determine the scope and degree of the fault impact, and forming the analysis results including the root cause priority and the list of affected entities.

[0017] Preferably, the confidence of each root node is calculated by setting the monitoring data anomaly event as the result event and the abnormal state of the associated node in the knowledge graph as the cause event based on the Bayesian probability model, calculating the prior probability and joint probability by statistically analyzing the co-occurrence probability of the cause event and the result event based on the historical operation data, modifying the prior probability based on the parameters related to the fault in the entity attributes, and calculating the confidence of each root node.

[0018] Preferably, the collaborative treatment instructions are pushed to the terminal in parallel by automatically identifying the type of terminal that needs to be treated in collaboration based on the system association mapping table of the fault impact range, generating differentiated instruction content according to the fault level, and the emergency fault instruction containing real-time positioning coordinates, emergency operation permission key, countdown reminder, and the general fault instruction containing the general processing flow and the contact information of the responsible person.

[0019] Preferably, the customized diagnostic report is automatically generated by automatically filling the report content based on the knowledge graph fault traceability results and the multi-dimensional data of the data fusion processing module according to the preset template, including the basic information of the abnormal event, the fault root cause analysis, the historical similar records, and the equipment attribute information, and automatically adjusting the content dimension according to the role of the receiving object.

[0020] Preferably, the future system state is simulated based on the physical model by modifying the parameters in the virtual entity parameter editing window in the digital twin interface, including the cable load current, the environmental temperature setting value, the added equipment specification parameter, and the cooling device operating power, inputting the modified parameters into the pre-constructed physical model library, performing multi-physical field coupling calculation through the finite element analysis algorithm, simulating the system operation state at different time nodes, and outputting the change data of temperature distribution, current density, and equipment stress.

[0021] Preferably, the risk assessment is output in a visual manner by calculating the temperature exceeding probability based on the cable heating model, calculating the overload risk coefficient based on the ampacity calculation model, calculating the equipment stress safety margin based on the structural mechanics model, normalizing and weighting to obtain the comprehensive risk index.

[0022] The comprehensive risk index obtained by simulation calculation is mapped to the three-dimensional space of the digital twin, a dynamic heat map is used to display the temperature risk distribution, an arrow line is used to mark the fault diffusion path, a risk warning mark is superimposed on the virtual model through virtual-real fusion technology, a risk assessment board is generated, including a key parameter trend curve, a risk level radar chart and a sensitive parameter influence analysis table, and the risk evolution process at different simulation stages is traced back through a time axis control.

[0023] The second aspect of the present application provides a method of intelligent bridge monitoring system based on wireless communication, comprising: S1, digital twin engine: for constructing and rendering a digital twin synchronized with the physical entity according to the three-dimensional scanning data of the physical bridge.

[0024] S2, information acquisition: for collecting real-time running state data of the bridge.

[0025] S3, data fusion processing: for obtaining static asset data and historical operation and maintenance data of the cable from the database, fusing the real-time running state data of the bridge, the static asset data and the historical operation and maintenance data of the cable, and mapping the corresponding virtual entity in the digital twin.

[0026] S4, knowledge graph construction and reasoning: for constructing a knowledge graph and receiving the output of the data fusion processing module, and when monitoring data anomalies, performing fault root cause tracing and impact analysis.

[0027] S5, early warning: for receiving the fault tracing result of the knowledge graph, judging the fault level, pushing the collaborative disposal instruction to the terminal in parallel, and automatically generating a customized diagnosis report.

[0028] S6, simulation deduction: for allowing users to modify parameters on the digital twin, simulating future system states based on physical models, and outputting risk assessment in a visual manner.

[0029] Compared with the prior art, the present application has the following advantages: 1. Full-dimensional precise monitoring of virtual-real linkage: a three-dimensional virtual model synchronized with the physical bridge is constructed through the digital twin engine, real-time data, static asset data and historical operation and maintenance data are associated and mapped to the virtual entity through the data fusion module, the visual linkage of "data-equipment-location" is realized, and the system global state can be intuitively mastered by the operation and maintenance personnel without manual matching of data and field equipment.

[0030] 2. Efficient fault handling driven by knowledge graph: relying on the entity association relationship of knowledge graph and Bayesian probability model, it can accurately locate the fault root cause (confidence quantization sorting) and analyze the influence range, and push differential collaborative instructions with hierarchical early warning mechanism, which can greatly shorten the fault troubleshooting time and avoid the blindness of treatment measures.

[0031] 3. Active risk prediction supported by physical model: the simulation and deduction module simulates the future system state after parameter adjustment through physical models such as cable heating and load capacity, and outputs risk assessment in the form of dynamic thermal map and trend curve, helping operation and maintenance to shift from "passive repair" to "active prevention" and reduce potential faults. BRIEF DESCRIPTION OF DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0033] Figure 1 It is a schematic diagram of the system structure of the present application. Figure 2 It is a schematic diagram of the method implementation step flow of the present application. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0035] Embodiment: Please refer to Figure 1 As shown, an intelligent bridge monitoring system based on wireless communication is provided, which comprises: a digital twin engine module: for constructing and rendering a digital twin body synchronized with the physical entity according to the three-dimensional scanning data of the physical bridge.

[0036] It should be noted that the three-dimensional scanning data of the physical bridge is stored in the database, and the physical entity here refers to the bridge.

[0037] Information acquisition module: for collecting real-time running state data of the bridge.

[0038] It should be noted that the information acquisition module is a protocol adaptive fusion gateway; through the built-in AI protocol self-learning unit, the sensor data stream of unknown protocol is listened to, the feature is extracted and the pattern matching is matched, the analysis driving template is automatically generated, the plug and play and data acquisition of heterogeneous sensors are realized. Through the LoRa / NB-IoT wireless communication protocol, the sensor data distributed in the bridge nodes is received, and the wireless acquisition and uploading of real-time running state data are realized.

[0039] The data fusion processing module is used for acquiring the static asset data and historical operation and maintenance data of the cable from the database, fusing the real-time running state data of the bridge, the static asset data and the historical operation and maintenance data of the cable, and mapping the corresponding virtual entity in the digital twin.

[0040] In one embodiment, the fusion of the real-time running state data of the bridge, the static asset data and the historical operation and maintenance data of the cable is realized by binding the real-time running state data as dynamic attributes to the virtual sensors of the digital twin, binding the specifications, models, rated currents and laying dates of the cables as static attributes to the virtual cables of the digital twin, and associating the historical work orders and maintenance records as time series attributes with the corresponding virtual entities.

[0041] The knowledge graph construction and reasoning module is used for constructing a knowledge graph and receiving the output of the data fusion processing module, and when monitoring data anomalies, performing fault root cause tracing and impact analysis.

[0042] In one embodiment, the construction of the knowledge graph is realized by taking the cable, the sensor and the power distribution equipment as the core entities and defining the specifications, parameters and operation and maintenance attributes of each entity, constructing three types of core relationships of electrical connection, spatial position and function between entities by analyzing the electrical schematic diagram, three-dimensional scanning data and operation and maintenance documents, integrating device account, design drawings and operation and maintenance records to complete the initialization of the graph, and dynamically updating the entity attributes and associated relationships based on the entity state change data and bridge structure adjustment information to form a knowledge graph reflecting the association of the bridge system in real time.

[0043] It should be noted that in the knowledge graph construction and reasoning module, the "electrical, spatial and functional relationships" of the knowledge graph include but are not limited to "power supply for", "power supply from", "monitoring", "cooling", "physical proximity" relationships.

[0044] In one specific embodiment, the fault root cause tracing and impact analysis is performed by taking the entity corresponding to the monitoring data anomaly as the starting point, traversing the electrical, spatial, and functional association nodes of the entity in the knowledge graph, combining the entity attributes and historical operation and maintenance data, locating the core root causes (such as upstream power distribution equipment overload and adjacent equipment failure impact) that lead to the anomaly through logical reasoning, calculating the confidence of each root cause node based on a Bayesian probability model, outputting a probability-ordered traceability list, and analyzing the downstream entities (such as affected cables and power distribution circuits dependent on the device) affected by the anomaly along the association relationship chain to determine the scope and extent of the fault impact and form an analysis result including root cause priority and a list of affected entities.

[0045] In one specific embodiment, the confidence of each root cause node is calculated by setting the monitoring data anomaly event as the result event and the abnormal state of the association node in the knowledge graph as the cause event based on the Bayesian probability model, calculating the prior probability and joint probability by statistically analyzing the co-occurrence probability of the cause event and the result event from the historical operation and maintenance data, modifying the prior probability in combination with the parameters related to the fault in the entity attributes, and calculating the confidence of each root cause node.

[0046] It should be noted that the confidence of the root cause node is calculated using the following formula: Confidence ; Wherein, is the conditional probability of abnormal event A when cause event B occurs (the frequency of A appearing after B occurs is statistically analyzed from historical data), is the prior probability of cause event B (the frequency of B occurring in historical data), is the overall probability of abnormal event A (the total frequency of A occurring in historical data), is the entity attribute correction coefficient, and the calculation formula is: ; Wherein, is the weight coefficient of the i-th fault-related attribute (such as a device aging degree weight of 0.4, a load rate weight of 0.3, and a maintenance period weight of 0.3), is the state deviation coefficient of the i-th attribute, (taking a value range of [0, 1], the greater the current state is closer to the historical fault state), i represents the number of fault-related attributes, is the relationship strength coefficient, which is assigned according to the relationship type between entities in the knowledge graph and set by professionals, for example, electrical connection relationship , functional dependency relationship , and spatial adjacent relationship .

[0047] The confidence values of each root node are calculated by the above formula, arranged in descending order to form a traceability list, and the higher the value, the greater the possibility that the node is the root cause of the fault.

[0048] The early warning module is used to receive the fault traceability result of the knowledge graph, judge the fault level, push the collaborative disposal instruction to the terminal in parallel, and automatically generate a customized diagnostic report.

[0049] It should be noted that the judgment of the fault level is specifically: A grading model is constructed based on three dimensions of fault influence range, emergency level and disposal time limit, and the comprehensive score is determined by weighted calculation of quantitative indicators, wherein the number and importance of affected entities are determined by knowledge graph correlation analysis (such as entities related to the main power supply loop have higher weights than branch circuit); the emergency level is evaluated according to the magnitude of the abnormal parameter deviation from the threshold (such as a temperature deviation within 5°C is considered mild, and a temperature deviation above 15°C is considered severe); and the parameter change rate (such as a temperature increase of 10°C within 10 minutes is determined as rapid deterioration); the disposal time limit determines the baseline value by combining the average repair time of similar faults in historical data and the equipment downtime loss coefficient, and the fault level score is calculated by the formula, and the specific calculation formula is as follows: ; Where S represents the fault level score, represents the influence range score, represents the emergency level score, represents the disposal time limit score, , , respectively represent the weight factor of the influence range score, the weight factor of the emergency level score, and the weight factor of the disposal time limit score, which are set by professionals, for example, the scene core target needs to be determined first (such as emergency events prioritize response speed, and routine tasks prioritize coverage completeness), and then combined with historical data or expert analysis to allocate: if the focus is on "fast risk control", the emergency level weight can be set to the highest (such as 40%-50%), followed by the disposal time limit (30%-40%), and the influence range is auxiliary (20%-30%); if the focus is on "comprehensive loss reduction", the influence range weight is set to the maximum (40%-50%), and the remaining weight is allocated to the emergency level and the disposal time limit according to the "coverage first and then speed up" logic; in general scenarios, a balanced allocation of "emergency level 35% + influence range 35% + disposal time limit 30%" can be used.

[0050] ; In the formula, is the number of the xth type of affected entities (such as main loop cables, branch equipment, sensors, etc.), Weight coefficient of the xth entity (main power supply loop entity = 2.0, branch loop entity = 1.0, auxiliary device = 0.5).

[0051] In the formula, Parameter deviation (Parameter deviation = |measured value - threshold value| / threshold value). Parameter change rate (Parameter change rate = parameter change amount in unit time / threshold value).

[0052] In the formula, Average repair time of historical same-type faults (unit: hours). Device downtime loss coefficient (critical device = 1.0, ordinary device = 0.5).

[0053] The fault level score is compared with the fault level score ranges corresponding to no fault, general fault, and emergency fault stored in the database. If the fault level score is within the fault level score range corresponding to no fault stored in the database, it is determined that the bridge is fault-free. If the fault level score is within the fault level score range corresponding to general fault stored in the database, it is determined that the bridge is a general fault. If the fault level score is within the fault level score range corresponding to emergency fault stored in the database, it is determined that the bridge is an emergency fault. The fault level score ranges corresponding to no fault, general fault, and emergency fault stored in the database are set by professionals. For example, based on a three-dimensional (impact range, emergency degree, and disposal time limit) quantitative scoring formula, combined with historical operation and maintenance data and actual risk matching, no fault is set to 0-10 points, corresponding to no affected entity, no parameter deviation, and no need for disposal. General fault is set to 11-40 points, corresponding to local branch impact, slight parameter deviation, and relaxed disposal. Emergency fault is set to 41-100 points, corresponding to main loop impact, serious parameter deviation, and urgent disposal. At the same time, the interval needs to be verified and dynamically adjusted through historical data to ensure adaptation to actual operation and maintenance scenarios.

[0054] In one specific embodiment, the parallel pushing of collaborative disposal instructions to the terminal is implemented by: automatically identifying the terminal type that needs to be collaboratively disposed based on a fault impact range and system association mapping table, generating differentiated instruction content according to the fault level, and including real-time positioning coordinates, emergency operation permission key, and countdown reminder in the emergency fault instruction, and including regular processing procedures and contact information of the person in charge in the general fault instruction.

[0055] ​​​​In one specific embodiment, the automatically generated customized diagnostic report is implemented by automatically filling in the report content based on the knowledge graph fault tracing result and the multi-dimensional data of the data fusion processing module according to a preset template, including abnormal event basic information, fault root cause analysis, historical similar records, and device attribute information, while automatically adjusting the content dimension according to the role of the receiving object.

[0056] It should be noted that the abnormal event basic information includes but is not limited to the occurrence time, location coordinates, and abnormal parameter value, the fault root cause analysis includes but is not limited to the root cause nodes and associated evidence sorted by confidence, the historical similar records include but are not limited to the historical processing scheme and effect of similar faults, and the device attribute information includes but is not limited to the specification parameters and running state of the associated entity; the terminal types for collaborative disposal include but are not limited to handheld terminals of operation and maintenance personnel, power distribution control systems, and heating management systems, and parallel transmission is realized through multi-protocol push channels (MQTT protocol push to operation and maintenance terminals, OPCUA protocol push to industrial control systems, and HTTP protocol push to management platforms), while the instruction receiving state and feedback information of each terminal are recorded to ensure the timeliness and closed-loop management of instruction transmission.

[0057] Simulation and deduction module: for allowing users to modify parameters on the digital twin, simulating future system state based on physical model, and outputting risk assessment in a visual manner.

[0058] In one specific embodiment, the future system state is simulated based on the physical model, and the implementation method is as follows: the parameters are modified by clicking the virtual entity parameter editing window on the digital twin interface, the modifiable parameters include cable load current, environmental temperature setting value, new device specification parameter, and cooling device running power, the modified parameters are input into the pre-built physical model library, multi-physical field coupling calculation is performed through finite element analysis algorithm, system running state at different time nodes is simulated, and change data of temperature distribution, current density, and device stress are output.

[0059] It should be noted that the pre-built physical model library includes but is not limited to temperature field model based on heat transfer, current-carrying capacity calculation model based on circuit theory, and cooling simulation model based on fluid mechanics.

[0060] In one specific embodiment, the risk assessment is output in a visual manner, and the implementation method is as follows: the temperature exceeding probability is calculated based on the cable heating model, the overload risk coefficient is calculated based on the current-carrying capacity calculation model, the device stress safety margin is calculated based on the structural mechanics model, normalization processing is performed, and a comprehensive risk index is obtained through weighted calculation.

[0061] The specific formula for calculating the temperature exceeding probability based on the cable heating model is as follows: ; wherein, is the cumulative length of time (unit: s) that the cable temperature exceeds the rated temperature threshold within the simulation time, is the total simulation time (unit: s), and the rated temperature threshold is determined according to the cable insulation grade (for example, 90°C for XLPE insulated cable).

[0062] The specific formula for calculating the overload risk coefficient based on the ampacity calculation model is: ; wherein, is the actual load current of the mth simulation period (unit: A), is the rated ampacity of the cable (unit: A), is the duration of the mth simulation period (unit: s), is the overload coefficient, which is set by professionals, for example, when ≤ , =1.0; when 1.0 ≤1.2, =1.5; when >1.2, =2.0, m represents the number of simulation periods, and n represents the total number of simulation periods.

[0063] The specific formula for calculating the equipment stress safety margin based on the structural mechanics model is: ; wherein, is the allowable stress of the equipment material (unit: MPa, determined according to the material manual), is the actual stress of the equipment obtained by simulation calculation (unit: MPa, obtained by finite element analysis), when > , is a negative value, indicating that there is a structural risk.

[0064] The comprehensive risk index obtained by simulation calculation is mapped to the three-dimensional space of the digital twin, a dynamic heat map is used to display the temperature risk distribution, an arrow line is used to mark the failure propagation path, a virtual-real fusion technology is used to superimpose risk warning marks on the virtual model, a risk assessment dashboard is generated, including key parameter trend curves (such as temperature change curve in the next 24 hours), risk level radar chart (multi-dimensional risk quantitative score), sensitive parameter influence analysis table (correlation between parameter variation and risk value), and the risk evolution process at different simulation stages is traced back through the time axis control.

[0065] It should be noted that the virtual-real fusion technology is prior art, and will not be described in detail here.

[0066] It should be noted that the system also includes a database, and the data interaction between the modules of the system is realized through a wireless communication network.

[0067] Please refer to Figure 2 As shown in the drawings, a method for monitoring an intelligent bridge based on wireless communication is provided, comprising: S1, a digital twin engine: for constructing and rendering a digital twin body synchronized with the physical entity according to the three-dimensional scanning data of the physical bridge.

[0068] S2, information acquisition: for collecting real-time running state data of the bridge.

[0069] S3, data fusion processing: for obtaining static asset data and historical operation and maintenance data of the cable from the database, fusing the real-time running state data of the bridge, the static asset data and the historical operation and maintenance data of the cable, and mapping the corresponding virtual entity in the digital twin body.

[0070] S4, knowledge graph construction and reasoning: for constructing a knowledge graph and receiving the output of the data fusion processing module, and when monitoring data anomalies, performing fault root cause tracing and impact analysis.

[0071] S5, early warning: for receiving the fault tracing result of the knowledge graph, judging the fault level, pushing the collaborative disposal instruction to the terminal in parallel, and automatically generating a customized diagnostic report.

[0072] S6, simulation and deduction: for allowing the user to modify the parameters on the digital twin body, simulating the future system state based on the physical model, and outputting the risk assessment in a visual manner.

[0073] The above shows and describes the basic principles, main features and advantages of the present application. It should be understood by those skilled in the art that the present application is not limited by the above examples, and the above examples and descriptions in the specification are only preferred examples of the present application and are not intended to limit the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the present application.

Claims

1. A wireless communication based intelligent bridge monitoring system, characterized in that, include: Digital Twin Engine Module: Used to build and render a digital twin synchronized with the physical entity based on the 3D scan data of the physical cable tray; Information acquisition module: used to collect real-time operating status data of the cable tray; Data fusion processing module: used to obtain static asset data and historical operation and maintenance data of cables from the database, merge the real-time operation status data of cable trays, static asset data and historical operation and maintenance data of cables, and map them to the corresponding virtual entities in the digital twin; Knowledge graph construction and reasoning module: used to construct knowledge graphs and receive the output of the data fusion processing module; when monitoring data anomalies, it performs fault root cause tracing and impact analysis. Early warning module: Used to receive fault tracing results from knowledge graph, determine fault level, push collaborative handling instructions to the terminal in parallel, and automatically generate customized diagnostic reports. Simulation module: Allows users to modify parameters on a digital twin, simulate the future system state based on a physical model, and output risk assessment in a visual manner.

2. The intelligent bridge monitoring system based on wireless communication according to claim 1, wherein, The method for integrating the real-time operating status data of cable trays, the static asset data of cables, and historical maintenance data is as follows: Real-time operating status data is bound as a dynamic attribute to the virtual sensor of the digital twin; the cable specifications, model, rated current, and laying date are bound as static attributes to the virtual cable of the digital twin; historical work orders and maintenance records are associated with the corresponding virtual entities as time-series attributes.

3. The intelligent bridge monitoring system based on wireless communication according to claim 2, wherein, The specific implementation method for constructing the knowledge graph is as follows: Using cables, sensors, and power distribution equipment as core entities, and defining the specifications, parameters, and operation and maintenance attributes of each entity, the system constructs three core relationships between entities—electrical connections, spatial locations, and functional roles—by analyzing electrical schematics, 3D scanning data, and operation and maintenance documents. It integrates multi-source data such as equipment ledgers, design drawings, and operation and maintenance records to complete the initialization of the knowledge graph. At the same time, it dynamically updates entity attributes and relationships based on entity status change data and cable tray structure adjustment information, forming a knowledge graph that reflects the real-time relationships of the cable tray system.

4. The intelligent bridge monitoring system based on wireless communication according to claim 3, wherein, The specific method for performing fault root cause tracing and impact analysis is as follows: Starting with the entity corresponding to the abnormal monitoring data, the system traverses the electrical, spatial, and functional related nodes of that entity in the knowledge graph. Combining entity attributes with historical operation and maintenance data, it uses logical reasoning to locate the core root cause of the abnormality. Based on the Bayesian probability model, it calculates the confidence level of each root cause node and outputs a source tracing list sorted by probability. At the same time, it analyzes the downstream entities affected by the abnormality along the relationship chain to clarify the scope and degree of the fault's impact, forming an analysis result that includes the root cause priority and a list of affected entities.

5. The intelligent bridge monitoring system based on wireless communication according to claim 4, wherein, The specific method for calculating the confidence level of each root source node is as follows: Based on the Bayesian probability model, abnormal events in the monitored data are set as result events, and abnormal states of related nodes in the knowledge graph are set as cause events. The co-occurrence probabilities of cause events and result events are statistically analyzed using historical operation and maintenance data to obtain prior probabilities and joint probabilities. The prior probabilities are then corrected by combining fault-related parameters in the entity attributes, and the confidence level of each root node is calculated.

6. The intelligent bridge monitoring system based on wireless communication according to claim 4, wherein, The method for pushing the collaborative treatment instruction to the terminal in parallel comprises the following steps: Based on the fault influence range and the system association mapping table, the terminal type that needs to be collaboratively treated is automatically identified, and differentiated instruction content is generated according to the fault level. The emergency fault instruction contains real-time positioning coordinates, emergency operation permission key, countdown reminder, and the general fault instruction contains the general processing flow and the contact information of the person in charge.

7. The intelligent bridge monitoring system based on wireless communication according to claim 6, wherein, The method for automatically generating a customized diagnostic report comprises the following steps: Based on the knowledge graph fault tracing result and the multi-dimensional data of the data fusion processing module, the report content is automatically filled in according to the preset template, including abnormal event basic information, fault root analysis, historical similar records, and device attribute information. At the same time, the content dimension is automatically adjusted according to the role of the receiving object.

8. The intelligent bridge monitoring system based on wireless communication according to claim 7, wherein, The method for simulating the future system state based on a physical model comprises the following steps: In the digital twin interface, the parameters can be modified by clicking the virtual entity parameter editing window. The modifiable parameters include cable load current, environment temperature setting value, newly added device specification parameter, and heat dissipation device operating power. The modified parameters are input into the pre-constructed physical model library, and multi-physical field coupling calculation is performed through the finite element analysis algorithm. The system running state at different time nodes is simulated, and the change data of temperature distribution, current density, and device stress are output.

9. The intelligent bridge monitoring system based on wireless communication according to claim 8, wherein, The method for outputting risk assessment in a visual manner comprises the following steps: Based on the cable heating model, the temperature exceeding probability is calculated. Based on the ampacity calculation model, the overload risk coefficient is calculated. Based on the structural mechanics model, the device stress safety margin is calculated. The normalized processing and weighted calculation are performed to obtain the comprehensive risk index. The comprehensive risk index obtained by simulation calculation is mapped to the three-dimensional space of the digital twin. The temperature risk distribution is displayed using a dynamic heat map. The fault diffusion path is marked with an arrow line. The risk warning mark is superimposed on the virtual model through virtual-real fusion technology. The risk assessment board is generated, including the key parameter trend curve, risk level radar chart, and sensitive parameter influence analysis table. The risk evolution process at different simulation stages is traced back through the time axis control.

10. A method for performing the intelligent bridge monitoring system based on wireless communication according to any one of claims 1-9, characterized in that, It comprises: S1, digital twin engine: used for constructing and rendering a digital twin body synchronized with the physical entity according to the three-dimensional scanning data of the physical bridge; S2, information acquisition: used for collecting the real-time running state data of the bridge; S3, data fusion processing: used for obtaining the static asset data and historical operation and maintenance data of the cable from the database, fusing the real-time running state data of the bridge, the static asset data and the historical operation and maintenance data of the cable, and associating and mapping them to the corresponding virtual entities in the digital twin body; S4, knowledge graph construction and reasoning: used for constructing a knowledge graph and receiving the output of the data fusion processing module, and performing fault root tracing and influence analysis when monitoring data abnormity; S5, early warning: used for receiving the fault tracing result of the knowledge graph, judging the fault level, pushing the collaborative treatment instruction to the terminal in parallel, and automatically generating a customized diagnostic report; S6, simulation and deduction: used for allowing a user to modify parameters on the digital twin body, simulating the future system state based on a physical model, and outputting risk assessment in a visual manner.

Images