A wiring monitoring method and system based on digital twin

Abstract

The present invention discloses a wiring monitoring method and system based on digital twins, which relate to the field of wiring monitoring technology, including: constructing a digital twin model of wiring based on the operation data of the wiring unit; dynamically updating the digital twin model in combination with the real-time operation data of the wiring unit; collecting multimodal data of the wiring unit through a multimodal sensor cluster, aligning the timestamps of the multimodal data, and integrating them into original monitoring data; utilizing multimodal fusion based on deep learning to extract the features of the original monitoring data and generate state parameters; generating a backup path based on a fault report, combining the digital twin model of the wiring and the logical topology structure of the wiring unit; the present invention realizes accurate mapping and real-time synchronization of structure and state by constructing and dynamically updating the digital twin model of the wiring.

Description

Technical Field

[0001] The present invention relates to the field of wiring monitoring technology, and in particular to a wiring monitoring method and system based on digital twins. Background Art

[0002] With the rapid development of information technology, modern wiring has become increasingly complex and large-scale, placing higher demands on the reliability and stability of wiring. Traditionally, wiring monitoring mainly relies on management systems (NMS) based on standard protocols such as SNMP (Simple Management Protocol) and LLDP (Link Layer Discovery Protocol). These systems can provide basic topology discovery, device status monitoring, and simple fault alarm functions.

[0003] In recent years, digital twin technology has gradually attracted attention as an emerging intelligent monitoring method. In the field, digital twin technology can be used to create virtual copies, allowing managers to simulate, optimize and maintain wiring in digital space. However, most existing technologies rely on static topological structures and cannot reflect the dynamic changes of wiring in real time. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a wiring monitoring method based on digital twins to solve the dynamic adaptability problem of existing wiring monitoring technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a wiring monitoring method based on digital twins, which comprises:

[0008] Build a digital twin model of wiring based on the operation data of the wiring unit;

[0009] Dynamically update the digital twin model by combining the real-time operation data of the wiring unit;

[0010] Through the multimodal sensor cluster, the multimodal data of the wiring unit is collected, and the multimodal data timestamps are aligned to integrate them into the original monitoring data;

[0011] Utilize multimodal fusion based on deep learning to extract features of original monitoring data and generate state parameters;

[0012] Based on status parameters, the wiring unit is monitored in real time, abnormal events are detected and identified, and fault reports are generated;

[0013] Based on the fault report, an alternative path is generated by combining the digital twin model of the wiring and the logical topology of the wiring unit.

[0014] 1. As a preferred solution of the wiring monitoring method based on digital twins of the present invention, wherein: the digital twin model of the wiring is constructed based on the operation data of the wiring unit, and the specific steps are as follows:

[0015] Collect the operation data of the wiring unit through monitoring sensors deployed at the nodes;

[0016] Use noise filtering algorithm to process the operation data;

[0017] Use SNMP and LLDP-based topology scanning tools to automatically scan the connection relationships of wiring devices;

[0018] Use the SNMP interface of switches and routers to obtain the MAC address, port status and connection information of the device to build the physical topology;

[0019] Match the connection relationship data in the scan results with the operation data;

[0020] Use graph theory-based methods to represent physical topology;

[0021] Construct the adjacency matrix A of the wiring unit and generate a logic graph describing the signal transmission path between nodes;

[0022] The output includes the logical topology of node locations, connection relationships and signal transmission paths;

[0023] Use 3D laser scanning equipment to scan the physical position of the wiring unit and obtain the spatial coordinates of the wiring;

[0024] Process the spatial coordinates into a standardized point cloud data format, and align and integrate the data of multiple scanning areas using the ICP algorithm;

[0025] Automatically generate the geometric 3D model of the wiring unit using 3D modeling tools;

[0026] Match the nodes in the geometric 3D model with the node IDs in the logical topology structure;

[0027] The lines in the geometric model correspond to the connection relationships defined in the logical topology structure;

[0028] The operating data of nodes and transmission paths are mapped into a geometric 3D model to obtain a digital twin model of the wiring.

[0029] As a preferred solution of the wiring monitoring method based on digital twins of the present invention, the digital twin model is dynamically updated in combination with the real-time operation data of the wiring unit. The specific steps are as follows:

[0030] By collecting real-time operating data, updating the node and line status, and mapping them to the corresponding nodes and lines of the digital twin model of the wiring;

[0031] When the logical topology changes, the adjacency matrix A is automatically updated.

[0032] As a preferred solution of the wiring monitoring method based on digital twins described in the present invention, wherein: the multimodal data of the wiring unit is collected through a multimodal sensor cluster, and the multimodal data timestamps are aligned and integrated into the original monitoring data. The specific steps are as follows:

[0033] Deploy multimodal sensor clusters at the nodes of the wiring units and the branch points of the trunk lines;

[0034] Deploy fiber optic sensors on optical fiber lines and use distributed fiber optic sensing technology to monitor line stress changes and temperature;

[0035] Deploy electromagnetic sensors on cable lines and nodes to monitor cable current fluctuations and signal strength changes;

[0036] Deploy vibration sensors at physical nodes and line support locations to monitor mechanical vibrations;

[0037] The multimodal sensor cluster collects multimodal data at a unified frequency to generate time series data;

[0038] Providing unified timestamps for multimodal sensor clusters through time synchronization protocols;

[0039] Integrate time-synchronized multimodal data into raw monitoring data in a unified format;

[0040] The original monitoring data is denoised, missing values ​​are filled and standardized.

[0041] As a preferred solution of the wiring monitoring method based on digital twins of the present invention, wherein: the multimodal fusion based on deep learning is used to extract the original monitoring data features and generate state parameters. The specific steps are as follows:

[0042] Perform feature extraction on single-modal raw monitoring data through a separate neural network (e.g., convolutional neural network);

[0043] Using the attention mechanism, the feature vectors of the extracted unimodal original monitoring data are weighted and fused to generate a unified hidden feature representation;

[0044] Through the fully connected layer, the fused features are classified and regressed, and the output status parameters include node load status, signal transmission strength and line health status.

[0045] As a preferred solution of the wiring monitoring method based on digital twins of the present invention, wherein: based on the state parameters, the wiring unit is monitored in real time, abnormal events are detected and identified, and a fault report is generated. The specific steps are as follows:

[0046] Mapping state parameters into the digital twin model of wiring;

[0047] When the operating data is updated, the state parameters of the digital twin model are updated in real time;

[0048] Obtain a visual digital twin model that displays the status parameters of the wiring unit in real time, including node load status, signal transmission strength, and line health status;

[0049] According to the impact of state parameter failure on the wiring unit, abnormal events are defined as node failure, signal attenuation failure and line vibration failure;

[0050] Through experimental analysis, the node fault threshold k1, signal attenuation fault threshold k2 and line vibration fault threshold k3 are set;

[0051] When the value of the node load status exceeds the node fault threshold k1, it is determined to be a node fault. When the signal transmission strength is less than the signal attenuation fault threshold k2, it is determined to be a signal attenuation fault. When the value of the line health status is less than the line vibration fault threshold k3, it is determined to be a line vibration fault.

[0052] A time series classification model based on LSTM (Long Short-Term Memory Network) to capture the temporal variation pattern of operating status;

[0053] Use historical state parameter samples that are labeled with specific abnormal events (labeled as 1) and normal states (labeled as 0) and divide them into training sets and validation sets;

[0054] Input the training set into the classification model, output the predicted fault classification probability of the sample, and compare it with the actual label of the sample. When the maximum number of iterations is reached, the training ends;

[0055] Input the validation set, calculate the loss function of the classification model, and evaluate the performance of the classification model;

[0056] When the F1 score of the classification model (an indicator that comprehensively considers precision and recall) reaches the optimal value, the predicted probability of the abnormal event is the predicted probability threshold;

[0057] Input the state parameters obtained based on real-time multimodal data into the classification model and output abnormal events and their probabilities;

[0058] If the probability of a certain type of abnormal event exceeds the predicted probability threshold, the abnormal event is determined to be a fact;

[0059] For detected abnormal events, the specific location of the fault is determined by combining the topological structure of the digital twin model;

[0060] Based on the transmission paths of the logical topology structure, the adjacency matrix A is used to calculate and summarize the paths connected to the faulty nodes and lines, and analyze the impact of the fault on the wiring;

[0061] Obtain the abnormal event type, specific location and impact range, and integrate them into a fault report.

[0062] As a preferred solution of the wiring monitoring method based on digital twins of the present invention, wherein: according to the fault report, the digital twin model of the wiring and the logical topology structure of the wiring unit are combined to generate an alternative path. The specific steps are as follows:

[0063] Extract identified abnormal event data based on the specific content of the fault report;

[0064] Mapping fault starting points (such as nodes and lines) to nodes and lines in the logical topology structure in the digital twin model;

[0065] Input fault data into the digital twin model of the wiring to simulate fault propagation;

[0066] Starting from the fault starting point (such as the faulty node and line), recursively traverse the directly connected nodes of the adjacency matrix A;

[0067] For each downstream node, the signal strength is calculated according to the signal attenuation model and updated;

[0068] For each connection line, check whether there is any interruption or vibration abnormality based on the line health score. If it is abnormal, the transmission is terminated; otherwise, the transmission continues;

[0069] During the propagation simulation, each affected node ID and line number is recorded and displayed in the 3D visualization interface of the digital twin model.

[0070] Remove faulty nodes and lines from the affected topology and update the adjacency matrix A;

[0071] The Dijkstra shortest path algorithm is used to calculate the shortest path from the source node to the target node, and the calculated alternative path is mapped into the digital twin model.

[0072] In a second aspect, the present invention provides a wiring monitoring system based on digital twins, comprising a model building module, a model updating module, a data acquisition module, a feature extraction module, a fault monitoring module, and a backup path module.

[0073] The model building module is used to build a digital twin model of the wiring based on the operation data of the wiring unit;

[0074] The model update module is used to dynamically update the digital twin model in combination with the real-time operation data of the wiring unit;

[0075] The data acquisition module is used to collect multimodal data of the wiring unit through a multimodal sensor cluster, align the timestamps of the multimodal data, and integrate them into original monitoring data;

[0076] The feature extraction module is used to extract the features of the original monitoring data and generate state parameters by using multimodal fusion based on deep learning;

[0077] The fault monitoring module is used to monitor the wiring unit in real time based on the status parameters, detect and identify abnormal events, and generate a fault condition report;

[0078] The backup path module is used to generate a backup path based on the fault report, combining the digital twin model of the wiring and the logical topology structure of the wiring unit.

[0079] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the wiring monitoring method based on digital twins as described in the first aspect of the present invention is implemented.

[0080] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the wiring monitoring method based on digital twins as described in the first aspect of the present invention.

[0081] The beneficial effects of the present invention are: by constructing and dynamically updating the digital twin model of the wiring, accurate mapping and real-time synchronization of the structure and status are achieved, which not only provides an intuitive visual management tool, but also significantly improves the fault location accuracy and maintenance efficiency. By deploying a multimodal sensor cluster, the operation data is collected and integrated, the system's perception ability is enhanced, the comprehensiveness and accuracy of the data are ensured, and a solid foundation is laid for subsequent analysis. By utilizing deep learning technology to fuse multimodal data features and generate comprehensive status parameters, the system can intelligently detect and predict anomalies, speed up diagnosis and improve accuracy. By comprehensively evaluating the health status of the wiring unit and quickly generating alternative paths when a fault occurs, the continuity and reliability of the wiring are guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0083] Figure 1 This is a flowchart of the wiring monitoring method based on digital twins in Example 1.

[0084] Figure 2 This is a module diagram of the wiring monitoring system based on digital twin in Example 1. DETAILED DESCRIPTION

[0085] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0086] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0087] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0088] Example 1, with reference to Figure 1 and Figure 2, which is the first embodiment of the present invention, provides a wiring monitoring method based on digital twins, comprising the following steps:

[0089] Build a digital twin model of wiring based on the operation data of the wiring unit;

[0090] Dynamically update the digital twin model by combining the real-time operation data of the wiring unit;

[0091] Through the multimodal sensor cluster, the multimodal data of the wiring unit is collected, and the multimodal data timestamps are aligned to integrate them into the original monitoring data;

[0092] Utilize multimodal fusion based on deep learning to extract features of original monitoring data and generate state parameters;

[0093] Based on status parameters, the wiring unit is monitored in real time, abnormal events are detected and identified, and fault reports are generated;

[0094] Based on the fault report, an alternative path is generated by combining the digital twin model of the wiring and the logical topology of the wiring unit.

[0095] S1. Build a digital twin model of the wiring based on the operating data of the wiring unit.

[0096] Monitoring sensors (such as voltage sensors, current sensors, and temperature sensors) deployed at nodes (such as switches and routers) collect operating data of the wiring unit, including node signal strength, line electrical impedance, temperature, and humidity.

[0097] Use noise filtering algorithms (such as denoising algorithms based on wavelet transform) to process operating data to eliminate noise caused by environmental factors or equipment interference;

[0098] Furthermore, a topology scanning tool based on SNMP (Simple Management Protocol) and LLDP (Link Layer Discovery Protocol) is used to automatically scan the connection relationship of wiring devices;

[0099] Use the SNMP interface of switches and routers to obtain the MAC address, port status and connection information of the device to build the physical topology;

[0100] Match the connection relationship data in the scan results (such as port mapping and transmission paths between devices) with the operation data to ensure that the topology information can reflect the actual transmission status of the wiring;

[0101] Use graph theory-based methods (such as adjacency matrix representation) to represent physical topology structures;

[0102] Construct the adjacency matrix A of the wiring unit and generate a logic graph describing the signal transmission path between nodes;

[0103] Specifically, the adjacency matrix A is an N×N matrix (N is the total number of nodes). Each element in the matrix indicates whether two nodes are directly connected. If the two nodes are directly connected, the element is 1, and if not, the element is 0.

[0104] For two nodes that are not directly connected, the path is calculated through matrix power operation (matrix multiplication) to find a transmission path of any length;

[0105] The output includes the logical topology of node locations, connection relationships and signal transmission paths;

[0106] Furthermore, a three-dimensional laser scanning device is used to scan the physical position of the wiring unit to obtain the spatial coordinates of the wiring;

[0107] Process the spatial coordinates into a standardized point cloud data format, and align and integrate the data of multiple scanning areas using the ICP algorithm;

[0108] Use 3D modeling tools (such as Autodesk Revit or Open 3D) to automatically generate a geometric 3D model of the wiring unit, including the physical location of the wiring, node locations, and line structure;

[0109] Match the nodes in the geometric 3D model with the node IDs in the logical topology structure;

[0110] The lines in the geometric model (e.g., fiber connections) correspond to the connection relationships defined in the logical topology;

[0111] The operation data of nodes and transmission paths are mapped into a geometric three-dimensional model, so that the geometric model can dynamically display the operation of the wiring unit and obtain a digital twin model of the wiring.

[0112] S2. Dynamically update the digital twin model based on the real-time operation data of the wiring unit.

[0113] By collecting real-time operating data, updating the node and line status, and mapping them to the corresponding nodes and lines of the digital twin model of the wiring;

[0114] When the logical topology changes (e.g., adding a new node or disconnecting a connection), the adjacency matrix A is automatically updated;

[0115] For example, assign a unique ID to a newly added node and map its location and operating status to the digital twin model of the wiring;

[0116] If the direct connection between two nodes is disconnected, the value of the corresponding position in the adjacency matrix is ​​changed from 1 to 0.

[0117] S3. Collect multimodal data of the wiring unit through a multimodal sensor cluster, align the multimodal data timestamps, and integrate them into the original monitoring data.

[0118] Deploy multimodal sensor clusters at the nodes of the wiring unit and the branch points of the trunk line to ensure that the monitoring range covers the entire wiring unit;

[0119] Deploy fiber optic sensors on optical fiber lines and use distributed fiber optic sensing technology (such as OTDR-based optical time domain reflectometry) to monitor line stress changes and temperature.

[0120] Deploy electromagnetic sensors on cable lines and nodes (such as switch ports) to monitor cable current fluctuations and signal strength changes;

[0121] Deploy vibration sensors at physical nodes (such as terminal equipment) and line support locations to monitor mechanical vibrations (such as when the line is disturbed by external forces or environmental factors);

[0122] The multimodal sensor cluster collects multimodal data at a unified frequency to generate time series data;

[0123] Providing a unified timestamp for the multimodal sensor cluster through a time synchronization protocol (based on the IEEE 1588 Precision Time Protocol (PTP) synchronization method) to ensure time alignment of different data sources;

[0124] Integrate time-synchronized multimodal data into raw monitoring data in a unified format;

[0125] De-noising, filling missing values ​​and standardizing the original monitoring data;

[0126] Specifically, the wavelet denoising algorithm is used to denoise the original monitoring data, the missing time points of the original monitoring data are filled using linear interpolation, and the data of each modality are normalized to eliminate dimensional differences.

[0127] S4. Utilize multimodal fusion based on deep learning to extract the features of original monitoring data and generate state parameters.

[0128] The feature extraction of single-modal raw monitoring data is performed through a separate neural network (such as a convolutional neural network), and the expression is as follows:

[0129] h i =f Conv (W i *X i +b i );

[0130] Among them, h i is the feature vector of the original monitoring data of the i-th modality, i is the index of the modality number, fConv is the activation function (ReLU) after the convolution operation, W i is the convolution kernel weight of the original monitoring data of the i-th modality, X i is the original monitoring data of the i-th modality, b i is the bias term of the original monitoring data of the i-th modality, * represents the convolution operation;

[0131] Using the attention mechanism, the extracted unimodal original monitoring data feature vectors are weighted and fused to generate a unified hidden layer feature representation, which is expressed as follows:

[0132]

[0133] Among them, α i is the attention weight of the original monitoring data of the i-th modality, which is used to measure the importance of the modality, N is the total number of modalities; ω is the parameter weight of the attention mechanism, and H is the feature vector of the original monitoring data after fusion;

[0134] Through the fully connected layer, the fused features are classified and regressed, and the output status parameters include node load status, signal transmission strength and line health status.

[0135] S5. Based on the status parameters, the wiring unit is monitored in real time, abnormal events are detected and identified, and a fault report is generated.

[0136] Mapping state parameters into the digital twin model of wiring;

[0137] Specifically, the node load status is mapped to the nodes of the digital twin model, and the node color changes dynamically to indicate the load condition (e.g., green for normal and red for overload);

[0138] The signal transmission strength is mapped to the line, and the thickness of the line indicates the signal strength (for example, a thicker line indicates a high signal strength, and a thinner line indicates a weakened signal);

[0139] The line health status is mapped to the line health score, and the line color changes to reflect the health level (for example, green indicates healthy, yellow indicates sub-healthy, and red indicates fault);

[0140] When the operating data is updated, the state parameters of the digital twin model are updated in real time to ensure that the model is consistent with the actual operating status;

[0141] Obtain a visual digital twin model that displays the status parameters of the wiring unit in real time, including node load status, signal transmission strength, and line health status;

[0142] According to the impact of state parameter failure on the wiring unit, abnormal events are defined as node failure, signal attenuation failure and line vibration failure;

[0143] Through experimental analysis, the node fault threshold k1, signal attenuation fault threshold k2 and line vibration fault threshold k3 are set;

[0144] Specifically, the node load state value is equal to the ratio of the node's current load to the node's maximum load. Experiments were conducted to simulate the node's operating state under different load conditions. The results showed that when the node load is 0, the node will disconnect the connection line, resulting in a failure. When the node load exceeds 90% of the maximum processing value, the node response time is too long, resulting in task accumulation and even processing failure. Therefore, k1 is set to 0.9;

[0145] Signal strength is negatively correlated with path loss. Experimental simulations compared the signal reception quality under different signal transmission strengths. The results showed that when the signal transmission strength is less than 0.3, wiring will be interrupted, resulting in signal reception quality far below working requirements. Therefore, k2 is set to 0.3.

[0146] The line health value can be defined as the ratio of the actual signal transmission quality to the theoretical maximum signal transmission quality. When a line vibration fault occurs, it indicates that the line may be subject to physical interference (such as vibration, bending, or breakage). According to optical fiber transmission theory, when the line health value is less than 0.5, the signal attenuation caused by vibration can no longer meet the requirements. Therefore, k3 is set to 0.5.

[0147] When the value of the node load status exceeds the node fault threshold k1, it is determined to be a node fault. When the signal transmission strength is less than the signal attenuation fault threshold k2, it is determined to be a signal attenuation fault. When the value of the line health status is less than the line vibration fault threshold k3, it is determined to be a line vibration fault.

[0148] A time series classification model based on LSTM (Long Short-Term Memory Network) to capture the temporal variation pattern of operating status;

[0149] Use historical state parameter samples that are labeled with specific abnormal events (labeled as 1) and normal states (labeled as 0) and divide them into training sets and validation sets;

[0150] Input the training set into the classification model, output the predicted fault classification probability of the sample, and compare it with the actual label of the sample. When the maximum number of iterations is reached, the training ends;

[0151] Input the validation set, calculate the loss function of the classification model, and evaluate the performance of the classification model. The expression is as follows:

[0152]

[0153] Among them, L is the cross entropy loss value of the classification model, M is the total number of samples in the validation set, m is the sample number index, C is the number of abnormal event categories, c is the abnormal event category number index, and y m is the true label of the mth sample, is the predicted probability of the mth sample;

[0154] When the F1 score of the classification model (an indicator that comprehensively considers precision and recall) reaches the optimal value, the predicted probability of the abnormal event is the predicted probability threshold;

[0155] Input the state parameters obtained based on real-time multimodal data into the classification model and output abnormal events and their probabilities;

[0156] If the probability of a certain type of abnormal event exceeds the predicted probability threshold, the abnormal event is determined to be a fact;

[0157] For detected abnormal events, the specific location of the fault is determined by combining the topological structure of the digital twin model;

[0158] Specifically, we trace the signal transmission path in reverse to determine the starting node where the signal strength drops. We then directly locate the faulty node and confirm its connected nodes through the adjacency matrix A. This locates the line with the vibration fault and confirms the fault point by combining the vibration data from the multimodal sensor.

[0159] Based on the transmission paths of the logical topology structure, the adjacency matrix A is used to calculate and summarize the paths connected to the faulty nodes and lines, and analyze the impact of the fault on the wiring;

[0160] Obtain the abnormal event type, specific location and impact range, and integrate them into a fault report.

[0161] S6. Based on the fault report, a backup path is generated by combining the digital twin model of the wiring and the logical topology of the wiring unit.

[0162] Extract identified abnormal event data based on the specific content of the fault report, including fault node ID, signal attenuation strength, and line health score;

[0163] Mapping fault starting points (such as nodes and lines) to nodes and lines in the logical topology structure in the digital twin model;

[0164] Input fault data into the digital twin model of the wiring to simulate fault propagation;

[0165] Starting from the fault starting point (such as the faulty node and line), recursively traverse the directly connected nodes of the adjacency matrix A;

[0166] For each downstream node, the signal strength is calculated according to the signal attenuation model and updated;

[0167] For each connection line, check whether there is any interruption or vibration abnormality based on the line health score. If it is abnormal, the transmission is terminated; otherwise, the transmission continues;

[0168] The core logic of fault propagation is based on the following three characteristics:

[0169] Node dependency: Fault propagation follows the direct connection relationship between nodes. If a node fails, its directly connected downstream nodes will be affected.

[0170] Signal attenuation characteristics: During fault propagation, the signal strength gradually decreases along the path;

[0171] Propagation delay: There is a time delay for a fault to propagate from one node to another, which is calculated based on the physical distance between nodes and the signal propagation speed;

[0172] During the propagation simulation, each affected node ID and line number is recorded and displayed in the 3D visualization interface of the digital twin model.

[0173] Remove faulty nodes and lines from the affected topology and update the adjacency matrix A;

[0174] The shortest path from the source node to the target node is calculated using the Dijkstra shortest path algorithm. The calculated alternative path is mapped into the digital twin model and highlighted in green.

[0175] This embodiment also provides a wiring monitoring system based on digital twins, including: a model construction module, a model update module, a data acquisition module, a feature extraction module, a fault monitoring module and a backup path module. The model construction module is used to construct a digital twin model of the wiring based on the operation data of the wiring unit; the model update module is used to dynamically update the digital twin model in combination with the real-time operation data of the wiring unit; the data acquisition module is used to collect multimodal data of the wiring unit through a multimodal sensor cluster, and align the multimodal data timestamps to integrate them into original monitoring data; the feature extraction module is used to use multimodal fusion based on deep learning to extract the features of the original monitoring data and generate status parameters; the fault monitoring module is used to monitor the wiring unit in real time based on the status parameters, detect and identify abnormal events, and generate a fault situation report; the backup path module is used to generate a backup path based on the fault situation report, combined with the digital twin model of the wiring and the logical topology structure of the wiring unit.

[0176] This embodiment also provides a computer device, which is suitable for the monitoring method of wiring based on digital twins, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the monitoring method of wiring based on digital twins proposed in the above embodiment.

[0177] The computer device may be a terminal, comprising a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to establish a wired or wireless network with an external terminal, and the wireless mode may be achieved through WIFI, an operator network, NFC (near field network) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0178] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the wiring monitoring method based on digital twins as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0179] In summary, the present invention achieves accurate mapping and real-time synchronization of structure and status by: constructing and dynamically updating a digital twin model of wiring, which not only provides an intuitive visual management tool, but also significantly improves fault location accuracy and maintenance efficiency. By deploying a multimodal sensor cluster to collect and integrate operating data, the system's perception capability is enhanced, ensuring the comprehensiveness and accuracy of the data, laying a solid foundation for subsequent analysis. By utilizing deep learning technology to fuse multimodal data features and generate comprehensive status parameters, the system can intelligently detect and predict anomalies, speed up diagnosis and improve accuracy. By comprehensively evaluating the health status of the wiring unit and quickly generating alternative paths when a fault occurs, continuity and reliability are guaranteed.

[0180] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A wiring monitoring method based on digital twins, characterized by: include, Build a digital twin model of wiring based on the operation data of the wiring unit; Dynamically update the digital twin model by combining the real-time operation data of the wiring unit; Through the multimodal sensor cluster, the multimodal data of the wiring unit is collected, and the multimodal data timestamps are aligned to integrate them into the original monitoring data; Utilize multimodal fusion based on deep learning to extract features of original monitoring data and generate state parameters; Based on status parameters, the wiring unit is monitored in real time, abnormal events are detected and identified, and fault reports are generated; Based on the fault report, the digital twin model of the wiring and the logical topology of the wiring unit are combined to generate an alternative path. The specific steps are as follows: Extract identified abnormal event data based on the specific content of the fault report; Map the fault starting point to the nodes and lines in the logical topology structure in the digital twin model; Input fault data into the digital twin model of the wiring to simulate fault propagation; Starting from the fault starting point, recursively traverse the directly connected nodes of the adjacency matrix A; For each downstream node, the signal strength is calculated according to the signal attenuation model and updated; For each connection line, check whether there is any interruption or vibration abnormality based on the line health score. If it is abnormal, the transmission is terminated; otherwise, the transmission continues; During the propagation simulation, each affected node ID and line number is recorded and displayed in the 3D visualization interface of the digital twin model. Remove faulty nodes and lines from the affected topology and update the adjacency matrix A; The Dijkstra shortest path algorithm is used to calculate the shortest path from the source node to the target node, and the calculated alternative path is mapped into the digital twin model.

2. The wiring monitoring method based on digital twin according to claim 1, characterized in that: The specific steps of building a digital twin model of wiring based on the operation data of the wiring unit are as follows: Collect the operation data of the wiring unit through monitoring sensors deployed at the nodes; Use noise filtering algorithm to process the operation data; Use SNMP and LLDP-based topology scanning tools to automatically scan the connection relationships of wiring devices; Use the SNMP interface of switches and routers to obtain the MAC address, port status and connection information of the device to build the physical topology; Match the connection relationship data in the scan results with the operation data; Use graph theory-based methods to represent physical topology; Construct the adjacency matrix A of the wiring unit and generate a logic graph describing the signal transmission path between nodes; The output includes the logical topology of node locations, connection relationships and signal transmission paths; Use 3D laser scanning equipment to scan the physical position of the wiring unit and obtain the spatial coordinates of the wiring; Process the spatial coordinates into a standardized point cloud data format, and align and integrate the data of multiple scanning areas using the ICP algorithm; Automatically generate the geometric 3D model of the wiring unit using 3D modeling tools; Match the nodes in the geometric 3D model with the node IDs in the logical topology structure; The lines in the geometric model correspond to the connection relationships defined in the logical topology structure; The operating data of nodes and transmission paths are mapped into a geometric 3D model to obtain a digital twin model of the wiring.

3. The wiring monitoring method based on digital twin according to claim 2, characterized in that: The digital twin model is dynamically updated by combining the real-time operation data of the wiring unit. The specific steps are as follows: By collecting real-time operating data, updating the node and line status, and mapping them to the corresponding nodes and lines of the digital twin model of the wiring; When the logical topology changes, the adjacency matrix A is automatically updated.

4. The wiring monitoring method based on digital twin according to claim 3, characterized in that: The multimodal sensor cluster is used to collect multimodal data of the wiring unit, align the multimodal data timestamps, and integrate them into the original monitoring data. The specific steps are as follows: Deploy multimodal sensor clusters at the nodes of the wiring units and the branch points of the trunk lines; Deploy fiber optic sensors on optical fiber lines and use distributed fiber optic sensing technology to monitor line stress changes and temperature; Deploy electromagnetic sensors on cable lines and nodes to monitor cable current fluctuations and signal strength changes; Deploy vibration sensors at physical nodes and line support locations to monitor mechanical vibrations; The multimodal sensor cluster collects multimodal data at a unified frequency to generate time series data; Providing unified timestamps for multimodal sensor clusters through time synchronization protocols; Integrate time-synchronized multimodal data into raw monitoring data in a unified format; The original monitoring data is denoised, missing values ​​are filled and standardized.

5. The wiring monitoring method based on digital twin according to claim 4, characterized in that: The method uses multimodal fusion based on deep learning to extract the features of original monitoring data and generate state parameters. The specific steps are as follows: Feature extraction of single-modal raw monitoring data through a separate neural network; Using the attention mechanism, the feature vectors of the extracted unimodal original monitoring data are weighted and fused to generate a unified hidden feature representation; Through the fully connected layer, the fused features are classified and regressed, and the output status parameters include node load status, signal transmission strength and line health status.

6. The wiring monitoring method based on digital twin according to claim 5, characterized in that: The method of monitoring the wiring unit in real time based on the status parameters, detecting and identifying abnormal events, and generating a fault report is as follows: Mapping state parameters into the digital twin model of wiring; When the operating data is updated, the state parameters of the digital twin model are updated in real time; Obtain a visual digital twin model that displays the status parameters of the wiring unit in real time, including node load status, signal transmission strength, and line health status; According to the impact of state parameter failure on the wiring unit, abnormal events are defined as node failure, signal attenuation failure and line vibration failure; Through experimental analysis, the node fault threshold k1, signal attenuation fault threshold k2 and line vibration fault threshold k3 are set; When the value of the node load status exceeds the node fault threshold k1, it is determined to be a node fault. When the signal transmission strength is less than the signal attenuation fault threshold k2, it is determined to be a signal attenuation fault. When the value of the line health status is less than the line vibration fault threshold k3, it is determined to be a line vibration fault. LSTM-based time series classification model to capture the temporal variation pattern of operating status; Use historical state parameter samples that mark specific abnormal events and normal states and divide them into training sets and validation sets; Input the training set into the classification model, output the predicted fault classification probability of the sample, and compare it with the actual label of the sample. When the maximum number of iterations is reached, the training ends; Input the validation set, calculate the loss function of the classification model, and evaluate the performance of the classification model; When the F1 score of the classification model reaches the optimal value, the predicted probability of the abnormal event is the predicted probability threshold; Input the state parameters obtained based on real-time multimodal data into the classification model and output abnormal events and their probabilities; If the probability of a certain type of abnormal event exceeds the predicted probability threshold, the abnormal event is determined to be a fact; For detected abnormal events, the specific location of the fault is determined by combining the topological structure of the digital twin model; Based on the transmission paths of the logical topology structure, the adjacency matrix A is used to calculate and summarize the paths connected to the faulty nodes and lines, and analyze the impact of the fault on the wiring; Obtain the abnormal event type, specific location and impact range, and integrate them into a fault report.

7. A wiring monitoring system based on digital twins, based on the wiring monitoring method based on digital twins according to any one of claims 1 to 6, characterized in that: Including model building module, model updating module, data acquisition module, feature extraction module, fault monitoring module and backup path module, The model building module is used to build a digital twin model of the wiring based on the operation data of the wiring unit; The model update module is used to dynamically update the digital twin model in combination with the real-time operation data of the wiring unit; The data acquisition module is used to collect multimodal data of the wiring unit through a multimodal sensor cluster, align the timestamps of the multimodal data, and integrate them into original monitoring data; The feature extraction module is used to extract the features of the original monitoring data and generate state parameters by using multimodal fusion based on deep learning; The fault monitoring module is used to monitor the wiring unit in real time based on the status parameters, detect and identify abnormal events, and generate a fault condition report; The backup path module is used to generate a backup path based on the fault report, combining the digital twin model of the wiring and the logical topology structure of the wiring unit.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the wiring monitoring method based on digital twins according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the wiring monitoring method based on digital twins according to any one of claims 1 to 6 are implemented.

Images