Cable bridge fault positioning method and system based on multilayer sensing data fusion

Abstract

The invention provides a cable bridge fault positioning method and system based on multi-layer sensing data fusion, and relates to the technical field of data processing. Fault monitoring feature compensation is carried out by analyzing fault features of a cable bridge and establishing a fault evaluation list, and a multi-layer sensor network is constructed; a digital twin space is constructed according to a physical structure and operation data of a cable bridge, and a multi-layer sensing configuration module is established based on a multi-layer sensor network and is embedded into the digital twin space; and according to sensing configuration parameters of the multi-layer sensing configuration module, fault identification and positioning are carried out through a digital twin space. The technical problems of low fault identification precision and large positioning error caused by monitoring blind areas and data loss in cable bridge fault monitoring in the prior art are solved, and the technical effects of improving the fault positioning accuracy and reliability and enhancing the fault monitoring comprehensiveness and real-time performance are achieved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and specifically relates to a cable tray fault location method and system for multi-layer sensing data fusion. Background Art

[0002] In modern power transmission and information wiring systems, as a key support structure, the operating state of cable trays is directly related to the stability of power supply and the security of information transmission. At present, cable tray fault location mainly relies on single-type sensors such as vibration sensors, temperature sensors, or current sensors deployed at tray nodes or key parts for monitoring, and combines abnormal threshold judgment for preliminary fault identification and location. However, the sensor deployment mode of such methods is relatively single, and it is impossible to comprehensively perceive the fault characteristics of cable trays under the combined action of various factors such as structural vibration, temperature change, and current abnormality, which is prone to monitoring blind spots, resulting in some faults being difficult to be detected in time. Especially for some complex fault types, single sensors are difficult to capture their key characteristics, thus prone to false alarms or missed alarms, affecting the stability of fault identification and the positioning accuracy. Summary of the Invention

[0003] This application provides a cable tray fault location method and system for multi-layer sensing data fusion, which solves the technical problems in the prior art that due to single sensor deployment and inability to perform hierarchical configuration for different fault types, there are monitoring blind spots and data missing in cable tray fault monitoring, resulting in low fault identification accuracy and large positioning error, and achieves the technical effect of improving the accuracy and reliability of fault location, and enhancing the comprehensiveness and real-time of fault monitoring through multi-layer sensor fusion and digital twin space embedding.

[0004] In view of the above problems, on the one hand, this application provides a cable tray fault location method for multi-layer sensing data fusion, and the method includes: analyzing the fault characteristics of the cable tray, establishing a fault evaluation list, including fault type, monitoring sensor, success probability, and abnormal missing characteristics; performing fault monitoring feature compensation according to the fault evaluation list, constructing a multi-layer sensor network, where the multi-layer sensor network has fault type labels and hierarchical granularity; constructing a digital twin space based on the physical structure and operating data of the cable tray, and establishing a multi-layer induction configuration module based on the multi-layer sensor network and embedding it into the digital twin space, where the multi-layer induction configuration module is used for multi-level sensing data identification configuration; according to the sensing configuration parameters of the multi-layer induction configuration module, performing fault identification and location through the digital twin space to obtain fault location information.

[0005] On the other hand, the present application also provides a cable tray fault location system for multi-layer sensing data fusion. The system includes: a fault feature analysis module for analyzing the fault features of the cable tray and establishing a fault evaluation list, which includes fault types, monitoring sensors, success probabilities, and abnormal missing features; a sensing construction module for performing fault monitoring feature compensation according to the fault evaluation list and constructing a multi-layer sensor network, where the multi-layer sensor network has fault type tags and hierarchical granularities; a digital twin module for constructing a digital twin space based on the physical structure and operation data of the cable tray, and establishing a multi-layer induction configuration module based on the multi-layer sensor network and embedding it into the digital twin space, where the multi-layer induction configuration module is used for multi-level sensing data identification configuration; and a fault location module for performing fault identification and location through the digital twin space according to the sensing configuration parameters of the multi-layer induction configuration module to obtain fault location information.

[0006] One or more technical solutions provided in the present application have at least the following beneficial effects: By analyzing the fault features of the cable tray and establishing a fault evaluation list, a structured reference standard is provided for subsequent monitoring and identification. The introduction of success probabilities and abnormal missing features provides an intelligent compensation ability for dealing with incomplete data and uncertain conditions. Fault monitoring feature compensation is performed according to the fault evaluation list, and a multi-layer sensor network is constructed, realizing refined perception of different fault types and different-level data, improving the adaptability and perception ability of the sensor network to complex cable tray faults, and providing a more comprehensive and accurate data basis for subsequent fault identification and location. By converting the physical structure and operation data of the cable tray into a digital twin space, a virtual mapping environment highly matching the physical entity is provided for fault identification and location. The embedded multi-layer induction configuration module can perform multi-level sensing data identification configuration in this digital twin space, giving full play to the high fidelity and dynamic characteristics of the digital twin technology, further improving the accuracy and reliability of fault identification, realizing the effective fusion and collaborative work of the physical entity and the virtual space, enabling subsequent fault identification to be efficiently simulated, verified, and inferred in the virtual space, and improving the dynamic fault identification ability. Fault identification and location are performed through the digital twin space according to the sensing configuration parameters of the multi-layer induction configuration module, so as to obtain a more accurate and stable fault location result.

[0007] In summary, the present application realizes panoramic perception and high-precision location of the operating state of the cable tray by constructing an evaluation mechanism driven by fault features, a multi-source sensing network deployed in layers, and a digital twin space integrating the cable tray structure and real-time data. Through the dynamic configuration and deduction of the digital twin environment, the accuracy of cable tray fault identification and the real-time response under complex working conditions are greatly improved, and the comprehensiveness and reliability of cable tray fault monitoring are overall enhanced.

[0008] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically given below. Description of the Drawings

[0009] Figure 1 It is a schematic flow chart of a cable tray fault location method for multi-layer sensing data fusion provided by an embodiment of this application.

[0010] Figure 2 It is a schematic flow chart of constructing a multi-layer sensor network in the cable tray fault location method for multi-layer sensing data fusion provided by an embodiment of this application.

[0011] Figure 3 It is a schematic structural diagram of a cable tray fault location system for multi-layer sensing data fusion provided by an embodiment of this application.

[0012] Description of the reference numerals: Fault feature analysis module 10, sensing construction module 20, digital twin module 30, fault location module 40. Specific Embodiments

[0013] By providing a cable tray fault location method and system for multi-layer sensing data fusion in the embodiments of this application, the technical problems in the prior art that due to the single layout of sensors and the inability to perform hierarchical configuration for different fault types, there are monitoring blind spots and data missing in the cable tray fault monitoring, resulting in low fault recognition accuracy and large positioning error are solved, and the technical effects of improving the accuracy and reliability of fault location, enhancing the comprehensiveness and real-time of fault monitoring through multi-layer sensor fusion and digital twin space embedding are achieved.

[0014] Embodiment 1, as Figure 1 shown, the embodiments of this application provide a cable tray fault location method for multi-layer sensing data fusion, and the method includes: Step S100: Analyze the fault features of the cable tray and establish a fault evaluation list, where the fault evaluation list includes fault types, monitoring sensors, success probabilities, and abnormal missing features.

[0015] Specifically, fault characteristics refer to the abnormal manifestation forms that may occur during the operation of cable trays, such as abnormal temperature, abnormal current, structural stress deviation, etc. The fault evaluation list is a database or table structure used to systematically describe the relationship between fault characteristics and monitoring resources, including fault types, monitoring sensors, success probability, abnormal missing characteristics, etc. Among them, fault types include different categories such as short circuit, overload, fracture, corrosion, etc.; monitoring sensors are sensors that perform real-time data acquisition, and the types include temperature sensors, current sensors, voltage sensors, vibration sensors, image acquisition modules, etc. The success probability refers to the historical or statistical probability value of a certain type of sensor successfully detecting a specific fault, reflecting the monitoring reliability of the sensor for a specific fault. Abnormal missing characteristics refer to the key fault characteristic information that cannot be obtained due to reasons such as insufficient sensor layout, insufficient performance, or equipment failure. Classify and summarize the common fault types of cable trays, analyze the possible physical or electrical characteristics of various faults, and establish a fault evaluation list. This list details the key monitoring sensors corresponding to each fault type, the monitoring success probability of this type of fault in history, and the abnormal characteristic items that may be missing in a specific scenario, providing basic data support for the compensation and layout of subsequent multi-layer sensing networks. Exemplarily, "cable overheating" belongs to the temperature abnormal fault category and requires the configuration of an infrared thermal imager and a spot temperature sensor; its success probability is 85%, but there may be a thermal imaging dead angle at the corner of the cable tray, resulting in "missing thermal imaging characteristics".

[0016] In the actual operation process, the key characteristics of various faults can be determined by referring to a large number of historical fault records, cable tray fault cases that have occurred, and using computer simulation of the fault occurrence process. For example, abnormal vibration caused by mechanical damage, temperature changes caused by overheating, sudden increase in current caused by short circuit, release of specific gases caused by insulation aging, etc. At the same time, identify and obtain the monitoring sensors already deployed in the current cable tray. Then, based on historical monitoring data and experimental statistics, estimate the success probability of each sensor in monitoring the corresponding fault, and quantify the reliability of each sensor in actual applications. At the same time, by comparing with the ideal monitoring model, find out the abnormal missing characteristics that occur in actual monitoring. These missing characteristics may be caused by reasons such as unreasonable layout of existing sensors, inability to cover fault-prone parts, or insufficient monitoring accuracy of sensors, unable to capture weak fault characteristic signals, etc. Finally, organize the information such as fault types, monitoring sensors, success probability, and abnormal missing characteristics obtained from the above analysis into a detailed fault evaluation list, providing a comprehensive and accurate basis for subsequent fault monitoring feature compensation and the construction of multi-layer sensor networks.

[0017] Step S200: Perform fault monitoring feature compensation according to the fault evaluation list, and construct a multi-layer sensor network, where the multi-layer sensor network has fault type labels and hierarchical granularity.

[0018] Specifically, the fault type label is an identification for marking the types of faults in the monitoring tasks to which the sensors belong. The hierarchical granularity refers to the layout density and monitoring range of sensors at different levels in the sensor network. The larger the hierarchical granularity, the wider the monitoring range of the sensors at that level or the more macroscopic the monitoring features; conversely, the more microscopic and precise. According to the fault evaluation list established in step S100, analyze the abnormal missing features in each fault type and supplement the corresponding types of sensors. For example, if there is a lack of stress monitoring in a certain area, add a stress gauge; if image information needs to be compensated, introduce a high-definition camera. Construct a sensor set for each fault type, and divide the levels according to dimensions such as the size of the monitoring space and the requirements for sensing accuracy, generating a multi-layer sensor network with a hierarchical structure and labeled markings to make up for the blind spots in sensing coverage, achieve an adaptive sensor combination layout for fault targets, and improve the comprehensiveness of monitoring.

[0019] Step S300: Construct a digital twin space based on the physical structure and operation data of the cable tray, and establish a multi-layer induction configuration module based on the multi-layer sensor network and embed it in the digital twin space. The multi-layer induction configuration module is used for multi-level sensing data identification and configuration.

[0020] Specifically, the multi-layer induction configuration module is an embedded configuration unit with the ability to manage hierarchical features and match fault labels, and is used to integrate the sensing node parameters and their configuration strategies required for each type of fault. Based on the three-dimensional structure, wiring method and actual operation status data of the cable tray, construct a virtual digital twin space, and map and embed the multi-layer sensor network constructed in step S2 in the digital twin space, that is, deploy sensor nodes with fault labels and hierarchical granularity in the digital twin model, and establish an induction configuration module for each layer of the sensor network to configure reading parameters, data parsing logic, trigger thresholds, etc., to achieve virtual deployment of the sensing network, real-time synchronization of status and dynamically adjustable configuration, provide a three-dimensional visualization support and a highly controllable monitoring platform for fault identification, and enable different levels of monitoring tasks to virtually run, predict, verify and update in the digital twin space.

[0021] Step S400: According to the sensing configuration parameters of the multi-layer induction configuration module, perform fault identification and location through the digital twin space to obtain fault location information.

[0022] Specifically, the sensing configuration parameters refer to the setting values such as the layout positions, sampling frequencies, threshold parameters, and recognition algorithms of each sensor. After the digital twin space is constructed and the sensing configuration is completed, a positioning request is received, including the specified fault type and the required positioning level. By matching the corresponding sensing configuration module, the sensor network data is called to analyze the current bridge state in real time. Combining historical data and model algorithms for state simulation, the specific fault location is identified, and the possible development trend and scope diffusion of the fault are further simulated, and comprehensive positioning information including the fault point position, severity, and warning range is output, realizing high-precision and predictable fault positioning.

[0023] Further, as Figure 2 shown, step S200 includes: Step S210: Match the compensation monitoring sensors according to the abnormal missing features in the fault evaluation list.

[0024] Step S220: According to the monitoring sensors and the compensation monitoring sensors, perform hierarchical division according to the range size of the compensation space to obtain the hierarchical granularity.

[0025] Step S230: Set the success probability compensation threshold, use the success probability compensation threshold as a constraint condition, and perform compensation strategy analysis on the compensation monitoring sensors based on the hierarchical granularity to determine the compensation sensors and sensing parameters for each hierarchical granularity.

[0026] Step S240: According to the hierarchical granularity and the corresponding compensation sensors and sensing parameters, establish hierarchical network blocks for each fault type.

[0027] Step S250: Integrate the hierarchical network blocks of all fault types to construct the multi-layer sensor network.

[0028] Specifically, based on the abnormal missing features marked in the fault evaluation list, the types of sensors that match this feature are searched, and a list of sensor types to be compensated, that is, compensation monitoring sensors, is generated to close the gap in sensor layout and enhance the ability to capture key fault signs in advance. This matching process can be intelligently recommended based on a pre-stored fault-sensor mapping rule library. Exemplarily, if the feature of uneven heat diffusion at the connection part is missing in the current deployment, an infrared point measurement sensor is compensated and deployed; if the feature of microstructural deformation is missing, a micro-displacement gauge or strain gauge is compensated and installed.

[0029] Obtain the information of currently deployed monitoring sensors and their coverage. Combine the abnormal missing features listed in the fault evaluation list to identify areas with monitoring blind spots or incomplete data, and then determine the spatial scope of compensatory monitoring. According to the distribution scope of the compensatory area, combined with the fault type and the requirement of recognition accuracy, introduce multiple types of compensatory monitoring sensors, including electrical, physical, chemical, and image sensors. After evaluating the coverage ability and monitoring resolution of various compensatory sensors, according to the difference in spatial scale, set the following granularity level division criteria: Micro granularity layer: applicable to areas where the compensatory spatial scope is less than 0.1 meters, select thermocouple sensors, micro pressure sensors, etc.; Medium granularity layer: applicable to areas where the compensatory spatial scope is between 0.1 meters and 1 meter, configure infrared image collectors, tension sensors, etc.; Macro granularity layer: applicable to areas where the compensatory spatial scope is greater than 1 meter, deploy distributed optical fiber temperature monitors, image recognition sensors, etc. During the granularity division process, based on the fusion analysis, evaluate the recognition accuracy and coverage of each sensor in the target compensatory area, and construct a recognition diffusion evaluation map. According to the diffusion trend and recognition ability gradient of this evaluation map, cluster and divide the compensatory space, and form monitoring areas with different granularity levels. Finally, output the monitoring granularity structure including micro, medium, and macro levels, as the basic basis for subsequent compensatory sensor configuration and multi-layer sensor network construction.

[0030] The success probability compensation threshold is the set minimum lower limit of the successful monitoring probability, used to judge whether the current configuration meets the reliability requirements of fault monitoring. Set the minimum reliability for monitoring a certain target fault category (such as an 85% success probability), conduct combined simulation and analysis on the compensatory monitoring sensors at each level, select the sensor configuration scheme that meets or exceeds this threshold, and at the same time output its key configuration parameters, including sampling rate, power consumption, layout method, etc., to ensure that each fault type has a stable sensing ability after compensation.

[0031] The hierarchical network block refers to a sub-network with a sensor layout hierarchical structure constructed for a single fault type. According to the hierarchical granularity and the corresponding sensor types and configuration parameters at each level, form a perception block structure for a single fault type, that is, construct a hierarchical network block. Each block has its own self-consistent internal perception level, layout scheme, and feedback mechanism, realizing the construction of an independent, clear, and structured perception network for each type of fault, which is conducive to modular management and special fault diagnosis. For example, for the "short circuit" fault, establish a two-layer block for temperature perception and current monitoring; for the "deformation" type of fault, establish a three-layer block for stress perception, image perception, and displacement perception.

[0032] Perform a fusion operation on the hierarchical network blocks of each fault type, identify the shared areas, shared sensors, and adjacent block merging conditions, conduct topology optimization, form a unified sensor network structure that spans fault dimensions and has multiple granularities, and output a sensor deployment map and a network parameter configuration file to construct a multi-layer sensor network and achieve collaborative perception and data reuse capabilities.

[0033] Further, step S250 includes: Step S251: Identify the homologous sensors between the hierarchical network blocks of each fault type.

[0034] Step S252: Based on the homologous sensors, establish connections between the hierarchical network blocks of each fault type, combine the connections of the hierarchical network blocks of all fault types, and construct the multi-layer sensor network.

[0035] Specifically, homologous sensors refer to sensors with the same data source or shared sensing information in multiple fault monitoring blocks. For example, the same temperature sensor is used for both overload identification and poor contact monitoring. Conduct a cross-analysis of all the constructed hierarchical network blocks of fault types to identify sensor nodes with overlapping data sources or sampling areas. This process can be performed by comparing and matching information such as sensor ID, installation location code, and sampling variable type, and output a list of homologous sensors as the basis for subsequent integration.

[0036] Based on the identified homologous sensors, connect the originally independently operating fault identification sub-networks through these common nodes to form an overall structural network that can share data and decision-making resources. At the same time, conduct conflict coordination (such as data access priority, bandwidth allocation), function mapping (matching of multi-task sensing functions), and path optimization (rearrangement of node access sequences). Finally, form an integrated multi-layer sensor network topology, realize the integration of monitoring resources across fault types, reduce redundant deployment, construct an efficient collaborative data acquisition and processing platform, and support the complete data-driven input of the subsequent digital twin model.

[0037] Further, step S220 includes: Step S221: The compensation monitoring sensors include electrical, physical, chemical, and image monitoring types. Compensate the abnormal missing features according to the electrical, physical, chemical, and image monitoring types and their sensing parameters to obtain compensated features.

[0038] Step S222: Based on the monitoring sensors and the compensated features of each monitoring type, evaluate the fault fusion identification accuracy and identification range to obtain an identification diffusion evaluation map.

[0039] Step S223: According to the positioning hierarchical range of each fault type, perform hierarchical segmentation on the identification diffusion evaluation map to obtain the hierarchical granularity.

[0040] Specifically, the compensation monitoring sensor is a sensor device used to complement the missing or abnormal data in the original monitoring link. It can be classified into electrical types (such as current, voltage, impedance), physical types (such as temperature, vibration, displacement), chemical types (such as gas concentration, corrosion products), and image monitoring types (such as visual recognition, thermal image analysis) according to the detection object. Analyze the "abnormal missing feature" field marked in the fault evaluation list, and select the corresponding type of compensation sensor according to the type of missing content; at the same time, compensate for the missing features according to its sensing parameters (such as sampling frequency, sensitivity, sampling coverage radius, etc.) to obtain compensation features that can accurately reflect the fault features.

[0041] The fault fusion recognition accuracy refers to the correct rate index of the monitoring sensor network formed by the combination of multiple sensor types in actual fault detection. The recognition range refers to the area range where the monitoring sensor can effectively identify faults. The recognition diffusion evaluation graph is a graph structure representing the change trend of the fusion recognition ability with the spatial or type dimension, which can be used to evaluate the balance between coverage and accuracy. Fuse the characteristic data of the existing monitoring sensor and the compensation monitoring sensor, and use fault recognition algorithms (such as support vector machines, neural networks, etc.) to evaluate the accuracy and range of the fused data in fault recognition. Through simulation and actual testing, generate the recognition diffusion evaluation graph, intuitively display the gain under each type of compensation configuration and its "diffusion" boundary, provide objective data basis for the subsequent hierarchical granularity division, and make the sensor network more configuration-targeted.

[0042] The positioning hierarchy range refers to the positioning accuracy range required for a certain type of fault. According to the possible propagation range or safety response requirements of different fault types in the physical structure, set the target positioning resolution hierarchy. For example, it is required to be accurate to the node level for overload faults and accurate to the branch level for corrosion faults. Then, perform hierarchical partitioning on the recognition diffusion evaluation graph according to these requirements, and output the corresponding hierarchical granularity level for each layer, realizing precise and hierarchical monitoring design for different fault types, and improving the resource allocation efficiency and the dynamic adaptation ability of recognition response.

[0043] Further, step S230 includes: Constrained by the success probability compensation threshold, according to the recognition diffusion evaluation graph, search for the sensor layout distance and sensing adjustment parameters, and determine the compensation sensors and sensing parameters for each hierarchical granularity. The compensation sensors and sensing parameters for each hierarchical granularity are the types of compensation sensors that meet the success probability compensation threshold and the recognition range, their layout strategies, and adjustment parameters.

[0044] Specifically, the sensor layout distance refers to the layout distance between the compensation sensor and the target monitoring point or other sensors in space, which affects data synchronization and signal interference. The sensing control parameters refer to the parameters that affect the working performance of the sensor, such as sampling frequency, sensitivity, detection threshold, communication frequency band, etc. Based on the recognition diffusion evaluation map, the fusion recognition performance at each level is extracted. On the premise of meeting the success probability compensation threshold, optimize the sensor layout distance and search for matching control parameters: adjust the distance between the sensor layout points of the same layer or adjacent layers, and evaluate whether the redundant layout quantity can be reduced without reducing the accuracy; search for the parameter combination that can meet the recognition range requirement and success probability threshold in the existing candidate set of sensor types; consider constraints such as recognition coverage, available resources of the sensor, deployment space, energy consumption, etc. during the search process, and select the optimal configuration scheme in a multi-objective optimization manner. Finally, output the selected compensation sensor type, layout position distance, and its sensing parameters at each level granularity.

[0045] Further, step S300 includes: Step S310: Construct a three-dimensional geometric model according to the physical entity structure data of the cable tray.

[0046] Step S320: Collect the multi-physical field data of the cable tray, and couple and add the multi-physical field data to the three-dimensional geometric model.

[0047] Step S330: Combine the three-dimensional geometric model with the actual operation data of the cable tray to create a digital twin base and construct the digital twin space.

[0048] Further, the multi-physical field data includes: thermal field, stress field, and electromagnetic field.

[0049] Specifically, the physical entity structure data refers to information such as the size, shape, material properties, support structure, and interfaces of the bridge structure. Import the bridge structure drawings using BIM, CAD, or 3D modeling tools, identify geometric components (such as trays, support arms, and connecting plates), and establish a three-dimensional geometric model of the cable tray to provide a space carrier for digital simulation and mapping.

[0050] Multi-physical field data includes field information such as thermal fields (temperature distribution), stress fields (deformation and load), and electromagnetic fields (inductive interference) that can affect the health status of the cable tray. Use multi-physical field simulation tools to import the 3D model, add boundary conditions and material parameters, and input measured or simulated data to obtain the spatial distribution maps of each physical field, which are superimposed and mapped onto the 3D geometric model to achieve synchronous visualization and prediction of the effects of forces, electrothermal, and electromagnetic fields on the cable tray under complex working conditions. Among them, the thermal field collects the temperature distribution data of the cable tray through thermocouple sensors or infrared thermal imagers to reflect the heat generation of the cable; the stress field collects the mechanical stress distribution data of the cable tray using strain gauges or pressure sensors to reflect the stress on the structure; the electromagnetic field uses electromagnetic sensors to collect the electromagnetic field intensity data around the cable tray to reflect electromagnetic interference and electromagnetic compatibility issues.

[0051] Obtain the cable tray operation data (such as temperature, current, vibration, cracking signals, etc.) from the data acquisition system, edge sensing terminals, and historical databases, perform time-space mapping binding with the 3D geometric model, create a digital twin base as the starting state of the virtual twin body, and further construct a digital twin space on this basis to real-time simulate various state changes of the cable tray during actual operation, such as temperature changes, stress changes, electromagnetic field changes, etc.

[0052] Furthermore, step S300 further includes: Step S340: Obtain the hierarchical sensing configuration parameters for each fault type according to the fault type labels and hierarchical granularities of the multi-layer sensor network.

[0053] Step S350: Establish the multi-layer induction configuration module according to the hierarchical sensing configuration parameters of each fault type.

[0054] Step S360: Add the multi-layer induction configuration module as an internal sensing parameter configuration tool for the digital twin space to the digital twin space.

[0055] Specifically, after the multi-layer sensor network is constructed, extract the relevant configuration information of each fault type from the calibrated hierarchical network blocks, including hierarchical labels, data requirements, compensation strategies, etc., and organize a hierarchical sensing configuration parameter table for each fault to achieve an accurate mapping between the fault type and the multi-level sensing requirements, providing basic data support for the structure construction of the configuration module.

[0056] Generate a modular configuration unit structure based on the configuration parameters of each fault type at different granularity levels, including sensor selection logic, parameter setting templates, and data access specifications, and package it into a functional module that can be deployed in the twin space to form a configurable module unit that can be standardized and deployed, enhancing the automatic adaptation ability of sensing strategies in different scenarios.

[0057] Mount the multi - layer sensing configuration module to the digital twin platform in the form of a service interface or a dynamic component, supporting the invocation of corresponding - level sensing configurations at different fault evolution simulation stages, enabling the system to autonomously complete parameter activation and deployment, and providing real - time adaptation capabilities for the virtual - real mapping of the cable tray operating state.

[0058] Furthermore, step S400 includes: Step S410: Obtain a fault location request, including the fault type and the location level granularity.

[0059] Step S420: The multi - layer sensing configuration module performs sensing configuration matching according to the fault type and the location level granularity, obtains the monitoring data of the corresponding sensor network based on the matching sensing configuration parameters, conducts state simulation through the digital twin space, identifies the fault information and locates the fault. At the same time, based on the fault information, it conducts fault evolution simulation to obtain the fault prediction range and outputs the fault location information.

[0060] Specifically, the fault location request is a location task request proposed by the system user or the monitoring system, and the content includes the fault type to be analyzed and the desired monitoring accuracy level. Receive the request data including the fault type (such as overload, breakdown, corrosion, etc.) and the location level granularity as the input parameters for subsequent sensing configuration and identification simulation. When the specific level granularity parameter is not provided in the location request, automatically set the granularity classification based on the recognition diffusion evaluation map and the current monitoring coverage (for example, the micro - layer is used for detail confirmation, and the macro - layer is used for general range identification).

[0061] The multi - layer sensing configuration module invokes the matching mechanism, filters the sensing units that match the fault type and the level granularity from the database, inputs the cable tray monitoring data (temperature, current, image, etc.) collected in real - time according to the sensing parameters into the digital twin space, invokes the twin simulation model to conduct multi - physical - field simulation on the current state of the cable tray, and identifies the current fault point location and the specific fault type by comparing with the normal - state model. At the same time, based on the fault information, it conducts fault evolution simulation in the digital twin space, predicts the possible development range and trend of the fault, and finally outputs the detailed fault location information, including the fault type, the specific location, the granularity level, and the risk diffusion map.

[0062] In summary, the cable tray fault location method based on multi - layer sensing data fusion provided by the embodiments of this application has the following beneficial effects: By analyzing the fault characteristics of the cable tray, a fault evaluation list is established, providing a structured reference standard for subsequent monitoring and identification. The introduction of success probability and abnormal missing characteristics provides the intelligent compensation ability to handle incomplete data and uncertain conditions. Fault monitoring feature compensation is carried out according to the fault evaluation list, and a multi-layer sensor network is constructed, realizing the refined perception of different fault types and different levels of data, improving the adaptability and perception ability of the sensor network to complex cable tray faults, and providing a more comprehensive and accurate data basis for subsequent fault identification and location. By transforming the physical structure and operation data of the cable tray into a digital twin space, a virtual mapping environment highly matching the physical entity is provided for fault identification and location. The embedded multi-layer induction configuration module can perform multi-level sensing data identification and configuration in the digital twin space, giving full play to the high fidelity and dynamic characteristics of the digital twin technology, further improving the accuracy and reliability of fault identification, realizing the effective integration and collaborative work of the physical entity and the virtual space, enabling subsequent fault identification to be efficiently simulated, verified and inferred in the virtual space, and improving the dynamic fault identification ability. According to the sensing configuration parameters of the multi-layer induction configuration module, fault identification and location are carried out through the digital twin space, so as to obtain a more accurate and stable fault location result.

[0063] Overall, the embodiment of the present application realizes the panoramic perception and high-precision positioning of the operating state of the cable tray by constructing an evaluation mechanism driven by fault characteristics, a multi-source sensing network deployed in layers, and a digital twin space integrating the cable tray structure and real-time data. Through the dynamic configuration and deduction of the digital twin environment, the accuracy of cable tray fault identification and the real-time response under complex working conditions are greatly improved, and the comprehensiveness and reliability of cable tray fault monitoring are overall enhanced.

[0064] Embodiment 2, as Figure 3 shown, based on the same inventive concept as the foregoing Embodiment 1, the embodiment of the present application provides a cable tray fault location system for multi-layer sensing data fusion, and the system includes: A fault feature analysis module 10, configured to analyze the fault characteristics of the cable tray and establish a fault evaluation list, where the fault evaluation list includes fault types, monitoring sensors, success probability, and abnormal missing characteristics.

[0065] A sensing construction module 20, configured to perform fault monitoring feature compensation according to the fault evaluation list and construct a multi-layer sensor network, where the multi-layer sensor network has fault type labels and hierarchical granularity.

[0066] The digital twin module 30 is used to construct a digital twin space according to the physical structure and operation data of the cable tray, and embed a multi-layer induction configuration module into the digital twin space based on the multi-layer sensor network. The multi-layer induction configuration module is used for multi-level sensing data identification configuration.

[0067] The fault location module 40 is used to identify and locate faults through the digital twin space according to the sensing configuration parameters of the multi-layer induction configuration module, and obtain fault location information.

[0068] Furthermore, the sensing construction module 20 of the embodiment of the present application is further used to execute the following steps: Match compensation monitoring sensors according to the abnormal missing features in the fault evaluation list; divide the levels according to the range of the compensation space based on the monitoring sensors and the compensation monitoring sensors to obtain level granularity; set a success probability compensation threshold, use the success probability compensation threshold as a constraint condition, and perform compensation strategy analysis on the compensation monitoring sensors based on the level granularity to determine the compensation sensors and sensing parameters for each level granularity; establish a hierarchical network block for each fault type according to the level granularity and the corresponding compensation sensors and sensing parameters; integrate the hierarchical network blocks of all fault types to construct the multi-layer sensor network.

[0069] Furthermore, the sensing construction module 20 of the embodiment of the present application is further used to execute the following steps: Identify the homologous sensors between the hierarchical network blocks of each fault type; establish connections between the hierarchical network blocks of each fault type based on the homologous sensors, and connect and combine the hierarchical network blocks of all fault types to construct the multi-layer sensor network.

[0070] Furthermore, the sensing construction module 20 of the embodiment of the present application is further used to execute the following steps: The compensation monitoring sensors include electrical, physical, chemical, and image monitoring types. Compensate the abnormal missing features according to the electrical, physical, chemical, and image monitoring types and their sensing parameters to obtain compensation features; evaluate the fault fusion recognition accuracy and recognition range based on the monitoring sensors and the compensation features of each monitoring type to obtain an identification diffusion evaluation map; perform hierarchical segmentation on the identification diffusion evaluation map according to the positioning level range of each fault type to obtain the level granularity.

[0071] Furthermore, the sensing construction module 20 of the embodiment of the present application is further used to execute the following steps: Constrained by the success probability compensation threshold, based on the recognition diffusion evaluation diagram, search for the sensor layout distance and sensing control parameters, and determine the compensation sensors and sensing parameters at each hierarchical granularity. The compensation sensors and sensing parameters at each hierarchical granularity are the types of compensation sensors that meet the success probability compensation threshold and the recognition range, as well as their layout strategies and control parameters.

[0072] Further, the digital twin module 30 in the embodiment of the present application is further configured to perform the following steps: Construct a three-dimensional geometric model according to the physical entity structure data of the cable tray; collect multi-physical field data of the cable tray, and couple and add the multi-physical field data to the three-dimensional geometric model; combine the three-dimensional geometric model with the actual operation data of the cable tray to create a digital twin base and construct the digital twin space.

[0073] Further, the multi-physical field data includes: thermal field, stress field, and electromagnetic field.

[0074] Further, the digital twin module 30 in the embodiment of the present application is further configured to perform the following steps: Obtain the hierarchical sensing configuration parameters of each fault type according to the fault type labels and hierarchical granularities of the multi-layer sensor network; establish the multi-layer induction configuration module according to the hierarchical sensing configuration parameters of each fault type; use the multi-layer induction configuration module as an internal sensing parameter configuration tool for the digital twin space and add it to the digital twin space.

[0075] Further, the fault location module 40 in the embodiment of the present application is further configured to perform the following steps: Obtain a fault location request, including the fault type and the location hierarchical granularity; the multi-layer induction configuration module performs sensing configuration matching according to the fault type and the location hierarchical granularity, obtains the monitoring data of the corresponding sensor network based on the matched sensing configuration parameters, performs state simulation through the digital twin space, identifies the fault information and locates the fault, and at the same time performs fault evolution simulation based on the fault information to obtain the fault prediction range, and outputs the fault location information.

[0076] Through the foregoing detailed description of the cable tray fault location method based on multi-layer sensing data fusion in this specification, those skilled in the art can clearly know the cable tray fault location system based on multi-layer sensing data fusion in this embodiment. For the system disclosed in Embodiment 2, since it corresponds to the method disclosed in Embodiment 1, it has corresponding functional modules and beneficial effects. For the related parts, refer to the description in the method part.

[0077] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A cable tray fault location method based on multi-layer sensing data fusion, characterized in that, Including: Analyze the fault characteristics of the cable tray, establish a fault evaluation list, including fault types, monitoring sensors, success probabilities, and abnormal missing characteristics; Perform fault monitoring feature compensation according to the fault evaluation list, and construct a multi-layer sensor network, where the multi-layer sensor network has fault type labels and hierarchical granularities; Construct a digital twin space based on the physical structure and operation data of the cable tray, and establish a multi-layer induction configuration module based on the multi-layer sensor network and embed it into the digital twin space. The multi-layer induction configuration module is used for multi-level sensing data identification configuration; According to the sensing configuration parameters of the multi-layer induction configuration module, perform fault identification and positioning through the digital twin space to obtain fault positioning information.

2. The method for cable tray fault location with multi-layer sensing data fusion according to claim 1, characterized in that Perform fault monitoring feature compensation according to the fault evaluation list, and construct a multi-layer sensor network, including: Match and compensate the monitoring sensors according to the abnormal missing characteristics in the fault evaluation list; Perform hierarchical division according to the monitoring sensors and the compensated monitoring sensors according to the range of the compensation space to obtain hierarchical granularities; Set a success probability compensation threshold, use the success probability compensation threshold as a constraint condition, and perform compensation strategy analysis on the compensated monitoring sensors based on the hierarchical granularities to determine the compensated sensors and sensing parameters for each hierarchical granularity; Establish hierarchical network blocks for each fault type according to the hierarchical granularities and the corresponding compensated sensors and sensing parameters; Integrate the hierarchical network blocks of all fault types to construct the multi-layer sensor network.

3. The cable tray fault location method for multi-layer sensing data fusion according to claim 2, characterized in that, Integrate the hierarchical network blocks of all fault types to construct the multi-layer sensor network, including: Identify the homologous sensors between the hierarchical network blocks of each fault type; Establish connections between the hierarchical network blocks of each fault type based on the homologous sensors, and connect and combine the hierarchical network blocks of all fault types to construct the multi-layer sensor network.

4. The method for cable tray fault location with multi-layer sensing data fusion according to claim 2, characterized in that, Perform hierarchical division according to the monitoring sensors and the compensated monitoring sensors according to the range of the compensation space to obtain hierarchical granularities, including: The compensated monitoring sensors include electrical, physical, chemical, and image monitoring types. Compensate the abnormal missing characteristics according to the electrical, physical, chemical, and image monitoring types and their sensing parameters to obtain compensated characteristics; Evaluate the fault fusion recognition accuracy and recognition range based on the monitoring sensors and the compensated characteristics of each monitoring type to obtain an identification diffusion evaluation map; Perform hierarchical segmentation on the identification diffusion evaluation map according to the positioning hierarchical range of each fault type to obtain the hierarchical granularities.

5. The method for cable tray fault location with multi-layer sensing data fusion according to claim 1, characterized in that Construct a digital twin space based on the physical structure and operation data of the cable tray, including: Construct a three-dimensional geometric model according to the physical entity structure data of the cable tray; Collect multi-physical field data of the cable tray, and couple and add the multi-physical field data to the three-dimensional geometric model; Combine the three-dimensional geometric model with the actual operation data of the cable tray to create a digital twin base and construct the digital twin space.

6. The method for cable tray fault location by multi-layer sensing data fusion according to claim 5, characterized in that The multi-physical field data includes: thermal field, stress field, and electromagnetic field.

7. The method for cable tray fault location by multi-layer sensing data fusion according to claim 4, characterized in that Based on the hierarchical granularity, perform compensation strategy analysis on the compensation monitoring sensors to determine the compensation sensors and sensing parameters for each hierarchical granularity, including: Constrained by the success probability compensation threshold, according to the recognition diffusion evaluation graph, search for the sensor layout distance and sensing regulation parameters, and determine the compensation sensors and sensing parameters for each hierarchical granularity. The compensation sensors and sensing parameters for each hierarchical granularity are the types of compensation sensors that meet the success probability compensation threshold and the recognition range, as well as their layout strategies and regulation parameters.

8. The method for cable tray fault location with multi-layer sensing data fusion according to claim 1, characterized in that, Based on the multi-layer sensor network, establish a multi-layer induction configuration module and embed it into the digital twin space, including: According to the fault type labels and hierarchical granularity of the multi-layer sensor network, obtain the hierarchical sensing configuration parameters for each fault type; Establish the multi-layer induction configuration module according to the hierarchical sensing configuration parameters of each fault type; Take the multi-layer induction configuration module as an in-built sensing parameter configuration tool for the digital twin space and add it to the digital twin space.

9. The method for fault location of cable tray with multi-layer sensing data fusion according to claim 8, characterized in that According to the sensing configuration parameters of the multi-layer induction configuration module, perform fault identification and location through the digital twin space to obtain fault location information, including: Obtain a fault location request, including the fault type and the location hierarchical granularity; The multi-layer induction configuration module performs sensing configuration matching according to the fault type and the location hierarchical granularity, obtains the monitoring data of the corresponding sensor network based on the matching sensing configuration parameters, performs state simulation through the digital twin space, identifies the fault information and locates the fault, and at the same time performs fault evolution simulation based on the fault information to obtain the fault prediction range, and outputs the fault location information.

10. A cable tray fault location system for multi-layer sensing data fusion, characterized in that, The system is used to execute the cable tray fault location method for multi-layer sensing data fusion according to any one of claims 1-9, including: A fault feature analysis module, which is used to analyze the fault features of the cable tray and establish a fault evaluation list, including fault type, monitoring sensor, success probability, and abnormal missing features; A sensing construction module, which is used to perform fault monitoring feature compensation according to the fault evaluation list and construct a multi-layer sensor network, where the multi-layer sensor network has fault type labels and hierarchical granularity; A digital twin module, which is used to construct a digital twin space according to the physical structure and operation data of the cable tray, establish a multi-layer induction configuration module based on the multi-layer sensor network and embed it into the digital twin space, and the multi-layer induction configuration module is used to perform multi-level sensing data identification and configuration; A fault location module, which is used to perform fault identification and location through the digital twin space according to the sensing configuration parameters of the multi-layer induction configuration module to obtain fault location information.

Images