Method and system for monitoring state of expressway power transmission ring network

Abstract

The invention relates to the technical field of expressway power grids, and particularly provides a state monitoring method and system for an expressway power transmission looped network, and the method comprises the steps: obtaining the state data of each node through sensors disposed at a plurality of nodes of the power transmission looped network; constructing a dynamic topology adjacency matrix of the nodes; calculating an evaluation index according to the state data, and mapping the evaluation index to a corresponding node in the dynamic topology adjacency matrix; and using the diagnosis model to diagnose the abnormal state of the power transmission ring network based on the structure of the dynamic topology adjacency matrix and the evaluation indexes of the nodes. The real-time performance and diagnosis accuracy of the monitoring system are remarkably improved, and innovative technical guarantee is provided for highway power supply safety.

Description

Technical Field

[0001] The present invention belongs to the technical field of highway power grids, and in particular relates to a method and system for monitoring the status of a highway power transmission ring network. Background Art

[0002] As a key component of the power system, the stable operation of highway transmission ring networks is crucial for ensuring transportation and power supply. Currently, common condition monitoring methods include centralized monitoring based on SCADA systems and distributed fiber optic sensing technology. While traditional SCADA systems can collect basic parameters such as voltage and current, they suffer from data update delays (typically in the order of seconds) and insufficient topological correlation analysis. Distributed fiber optic sensing technology, while capable of monitoring line temperature and deformation, struggles to reflect the dynamic interactions between electrical nodes. Summary of the Invention

[0003] In view of the above-mentioned deficiencies in the prior art, the present invention provides a method and system for monitoring the status of a highway power transmission ring network to solve the above-mentioned technical problems.

[0004] In a first aspect, the present invention provides a method for monitoring the status of a highway power transmission ring network, comprising: The status data of each node is obtained through sensors deployed at multiple nodes in the transmission ring network; Construct a dynamic topological adjacency matrix of nodes; Calculating evaluation indicators based on the state data and mapping the evaluation indicators to corresponding nodes in the dynamic topology adjacency matrix; The diagnosis model is used to diagnose abnormal conditions of the transmission ring network based on the structure of the dynamic topological adjacency matrix and the evaluation indicators of the nodes.

[0005] In an optional embodiment, acquiring status data of each node through sensors deployed at multiple nodes of the power transmission ring network includes: Deploy power detection sensors at nodes to collect voltage and current; Deploy a vibration sensor at the node, wherein the vibration sensor collects vibration acceleration; Distributed optical fibers are deployed to collect line temperature.

[0006] In an optional embodiment, constructing a dynamic topological adjacency matrix of nodes includes: Build the basic topology based on the physical connection relationship between nodes; Regularly verify whether the connection relationship of the connected nodes of the transmission ring network is normal by injecting characteristic frequency signals; The verification result is obtained and mapped to the basic topology to obtain a dynamic topology adjacency matrix.

[0007] In an optional implementation, mapping the verification result to the basic topology includes: If the verification result shows that the connection relationship is normal, the weight of the edge between the corresponding nodes in the basic topology is set to 1; If the verification result shows that the connection relationship is abnormal, the weight of the edge between the corresponding nodes in the basic topology is set to 0; In the display state, the edge with a weight of 0 adopts the preset alarm display color, and the edge with a weight of 1 adopts the preset default display color.

[0008] In an optional embodiment, calculating the evaluation index based on the state data and mapping the evaluation index to the corresponding node in the dynamic topology adjacency matrix includes: Calculate the impedance and load rate between connected nodes based on the voltage and current of the nodes; Correcting the impedance between DC nodes according to the line temperature; Correct the impedance between AC nodes according to the line length; The vibration acceleration is converted into a vibration level.

[0009] In an optional embodiment, the diagnosis model is used to diagnose abnormal conditions of the power transmission ring network based on the structure of the dynamic topological adjacency matrix and the evaluation index of the nodes, including: Use diagnostic rules to determine whether there are any abnormalities in the structure of the dynamic topology adjacency matrix and the evaluation indicators of the nodes currently obtained: If so, a corresponding alarm message is generated; If not, the impedance and the corresponding corrected temperature in the evaluation index are saved to the data sequence, and the LSTM network is used to predict the abnormal state based on the data sequence.

[0010] In an optional embodiment, the diagnostic rules are used to determine whether the structure of the dynamic topology adjacency matrix and the evaluation indicators of the nodes currently obtained are abnormal, including: When the impedance value of the line between the nodes is detected to suddenly exceed the maximum threshold and the current on the line drops to zero, it is determined to be a line disconnection fault; If the fluctuation amplitude of the line impedance within 1 second exceeds 10% of its historical average value, and the vibration acceleration detected exceeds the set threshold, it is determined that the line has poor contact; When the actual line load rate exceeds 85% of the rated value and the cable temperature is continuously above 70°C, an overload warning is triggered; Traverse the dynamic topology adjacency matrix, count the edges with weight 0, and match the edges with weight 0 with the planned power outage areas. If the two do not match, it is determined that there is a topological anomaly.

[0011] In a second aspect, the present invention provides a state monitoring system for a highway power transmission ring network, comprising: A data acquisition module is used to obtain status data of each node through sensors deployed at multiple nodes of the transmission ring network; Topology building module, used to build the dynamic topological adjacency matrix of nodes; An indicator calculation module is used to calculate evaluation indicators based on state data and map the evaluation indicators to corresponding nodes in the dynamic topology adjacency matrix; The state diagnosis module is used to diagnose the abnormal state of the transmission ring network by using the diagnosis model based on the structure of the dynamic topology adjacency matrix and the evaluation index of the node.

[0012] In an optional embodiment, the data acquisition module includes: The first collection unit is used to collect voltage and current by deploying power detection sensors at the node; A second acquisition unit is configured to deploy a vibration sensor at the node, wherein the vibration sensor acquires vibration acceleration; The third collection unit is used to collect line temperature by deploying distributed optical fibers.

[0013] In an optional embodiment, the topology building module includes: Basic building unit, used to build basic topology based on the physical connection relationship between nodes; A status verification unit, used to verify whether the connection relationship of the connected nodes of the transmission ring network is normal by regularly injecting characteristic frequency signals; The state mapping unit is used to obtain the verification result and map the verification result to the basic topology to obtain a dynamic topology adjacency matrix.

[0014] According to a third aspect, a device is provided, comprising: A memory for storing a status monitoring program for a highway power transmission ring network; The processor is configured to implement the steps of the highway transmission ring network status monitoring method provided in the first aspect when executing the highway transmission ring network status monitoring program.

[0015] In a fourth aspect, a computer-readable storage medium is provided, on which a status monitoring program for a highway transmission ring network is stored. When the status monitoring program for the highway transmission ring network is executed by a processor, the steps of the method for monitoring the status of a highway transmission ring network provided in the first aspect are implemented.

[0016] The beneficial effects of the present invention lie in the fact that the state monitoring method and system for highway power transmission ring networks provided herein achieve real-time tracking of ring network structural changes through the construction of a dynamic topological adjacency matrix, resolving the technical pain point that traditional static models cannot adapt to network reconstruction. Multi-source sensor data and evaluation indicators are mapped to topological nodes, breaking through the data siloing limitations of existing methods and enabling collaborative analysis of the entire network status. Combined diagnosis based on matrix structure and node indicators can accurately locate abnormal nodes and identify potential fault propagation paths. This method significantly improves the real-time performance and diagnostic accuracy of the monitoring system, providing innovative technical support for highway power supply security.

[0017] In addition, the present invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0020] Figure 2 FIG. 4 is a schematic block diagram of a system according to an embodiment of the present invention.

[0021] Figure 3 A schematic structural diagram of a device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0024] The state monitoring method for a highway power transmission ring network provided by an embodiment of the present invention is executed by a computer device. Accordingly, the state monitoring system for a highway power transmission ring network runs in the computer device.

[0025] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject may be a state monitoring system of a highway power transmission ring network. According to different requirements, the order of the steps in the flow chart may be changed, and some steps may be omitted.

[0026] like Figure 1 As shown, the method includes: S1. Obtain status data of each node through sensors deployed at multiple nodes in the transmission ring network; S2. Construct a dynamic topological adjacency matrix of nodes; S3. Calculate the evaluation index based on the state data and map the evaluation index to the corresponding node in the dynamic topology adjacency matrix; S4. Use the diagnostic model based on the structure of the dynamic topological adjacency matrix and the evaluation indicators of the nodes to diagnose the abnormal status of the transmission ring network.

[0027] In an embodiment of the present invention, based on step S1, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0028] To achieve high-precision voltage and current acquisition, high-precision Hall-effect sensors are used. Based on the Hall-effect principle, these sensors enable contactless measurement without disrupting circuit integrity. They also feature wide bandwidth, high precision, and excellent linearity, meeting measurement requirements across diverse voltage levels and current ranges. For example, for a common 10kV distribution network, a range-adaptable Hall-effect voltage sensor can be selected, offering a measurement accuracy of up to 0.2%, ensuring accurate voltage data acquisition. Current sensors are selected based on the load current of the line. For example, for industrial power lines with large current fluctuations, a Hall-effect current sensor with a range of 0-2000A can be selected to ensure accurate and stable current measurement. Furthermore, to enhance interference resistance, the power detection sensor features a metal shielded housing that effectively blocks external electromagnetic interference, ensuring the reliability of the collected data. The sensor's signal output interface uses a standard RS-485 or CAN bus interface, facilitating connection to a data acquisition module and enabling long-distance, high-speed data transmission.

[0029] The vibration sensor uses a MEMS (micro-electromechanical system) vibration accelerometer, which offers advantages such as small size, light weight, low power consumption, and high sensitivity, making it suitable for installation at power equipment nodes. Based on the vibration frequency characteristics of power equipment, the sensor was selected with a frequency response range of 0.1Hz-10kHz, covering the vibration frequency range of power equipment under normal operation and fault conditions. Its sensitivity can reach 100mV / g, accurately capturing even the smallest vibration changes. The sensor features a digital output interface, such as I²C or SPI, facilitating direct connection to a microcontroller for rapid data acquisition and processing. Furthermore, the vibration sensor includes built-in temperature compensation circuitry to automatically compensate for the effects of ambient temperature fluctuations on measurement results, ensuring accurate measurement data under varying ambient temperatures.

[0030] The distributed fiber optic Raman scattering distributed fiber optic temperature measurement system utilizes the temperature effect of spontaneous Raman scattered light within the fiber, measuring temperature by detecting changes in the intensity of the backscattered light. The fiber utilizes specialized, high-temperature and bend-resistant optical fibers with an operating temperature range of -40°C to 200°C, making it suitable for a variety of complex power line environments. The fiber's spatial resolution reaches 1m, and its temperature measurement accuracy is ±0.5°C, enabling precise monitoring of temperature changes at various locations along the power line. The system utilizes optical time-domain reflectometry (OTDR) technology, enabling distributed temperature measurement over long distances (up to 20 km), meeting the needs of long-distance power line monitoring.

[0031] At power nodes, voltage sensors are connected in parallel to the power lines via dedicated voltage transformers (PTs) to ensure safe and accurate voltage signal acquisition. Current sensors, using either a through-hole or split-type structure, are directly attached to the power lines to measure current. During installation, strict compliance with electrical safety regulations is required to ensure a secure connection between the sensor and the line and good electrical insulation. Sensors should also be installed in a location that is easily accessible for maintenance and data collection, and be protected against water, dust, and corrosion.

[0032] Vibration sensors are installed in key locations on power equipment, such as transformer casings and circuit breaker operating mechanisms. During installation, use specialized adhesives or screws to ensure a tight fit between the sensor and the equipment surface to ensure effective transmission of vibration signals. To avoid external vibration interference, the sensor should be installed away from sources of mechanical vibration and electromagnetic interference. Additionally, damping pads should be installed between the sensor and the equipment to minimize the impact of normal equipment vibration on measurement results.

[0033] Distributed optical fiber is laid along power lines, either overhead, underground, or in ducts. In overhead lines, optical fiber can be installed on the same pole as the power cables. Dedicated fixtures secure the fiber to the power tower, ensuring a safe distance from the power lines to prevent electromagnetic interference. When laying underground or in ducts, protective measures must be taken to prevent damage. During fiber installation, avoid excessive bending and stretching to ensure that the optical transmission performance of the fiber is not affected.

[0034] A data acquisition module is installed at each monitoring node. This module integrates multiple sensor interfaces and can simultaneously connect to power detection sensors, vibration sensors, and the signal processing unit of the distributed fiber-optic temperature measurement system. The data acquisition module utilizes a high-performance microcontroller with high-speed data acquisition and processing capabilities. It performs high-precision A / D conversion on analog signals collected by sensors and directly reads and processes digital signals.

[0035] The data acquisition module supports multi-channel simultaneous acquisition, ensuring the time synchronization of data such as voltage, current, vibration acceleration, and temperature. Furthermore, a built-in data buffer allows for temporary storage of collected data to prevent data loss. Furthermore, the data acquisition module features data preprocessing, filtering, noise reduction, and other processes to improve data quality.

[0036] The data acquisition module transmits processed data to the monitoring center via wireless or wired networks. For wired transmission, industrial Ethernet or fiber optic communication can be used. These offer high transmission rates and excellent stability, making them suitable for monitoring scenarios with short distances and relatively stable environments. For wireless transmission, 4G / 5G communication modules or LoRa wireless communication technology can be used. 4G / 5G communication modules offer fast transmission speeds and wide coverage, making them suitable for data transmission with high real-time requirements. LoRa wireless communication technology offers the advantages of low power consumption and long-distance transmission, making it suitable for monitoring nodes in remote areas or those with stringent power consumption requirements.

[0037] To ensure the security and reliability of data transmission, encryption technologies such as SSL / TLS are used during data transmission to prevent data theft and tampering. Furthermore, a data transmission redundancy mechanism is established. If the primary transmission channel fails, it automatically switches to the backup channel to ensure uninterrupted data transmission.

[0038] In an embodiment of the present invention, based on step S2, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0039] S201. Construct a basic topology based on the physical connection relationship between nodes.

[0040] The electrical parameters and physical connection information of nodes are acquired through the power SCADA (Supervisory Control and Data Acquisition) system, including the coordinate locations, equipment models, and voltage levels of nodes such as substations, switchyards, and line endpoints. Furthermore, geospatial data, such as the actual line directions and tower locations between nodes, is extracted from the power GIS (Geographic Information System), providing accurate foundational information for topology construction. The adjacency matrix method in graph theory is used to construct the basic topology structure. Each node is regarded as a vertex in the graph, and the physical connection between nodes is regarded as an edge. The matrix (n is the total number of nodes) is constructed such that if node i is physically connected to node j, the values ​​in row i, column j and row j, column i in the matrix are set to 1; if no connection exists, they are set to 0. During the construction process, the topology is optimized based on information such as node voltage levels and line capacity to ensure that the topology accurately reflects the physical connection relationships and electrical characteristics of the actual power grid. Professional power system analysis software, such as PSCAD / EMTDC and PowerWorld, can be used to graphically display the constructed basic topology. In this visualization interface, different node types are distinguished by distinct icons and colors. For example, substations are represented by specific icons, while transmission lines are represented by lines of varying colors and thicknesses. This allows operators to intuitively understand the grid topology.

[0041] S202. Regularly verify whether the connection relationship of the connected nodes of the transmission ring network is normal by injecting characteristic frequency signals.

[0042] Select an appropriate characteristic frequency signal based on the grid's frequency characteristics and the equipment's tolerance. Typically, frequencies that are integer or non-integer multiples of the power frequency (50Hz or 60Hz), such as 100Hz or 200Hz, are chosen to avoid interference with the grid's normal operating frequency. The signal amplitude should be appropriately set based on the line's voltage level and transmission capacity to ensure effective signal transmission on the transmission line without damaging the equipment. For example, for a 110kV transmission line, the characteristic frequency signal amplitude can be set to 1%-5% of the rated voltage.

[0043] Signal injection and detection devices are installed at nodes in the transmission ring network. The signal injection device uses a high-precision signal generator to produce a stable and accurate characteristic frequency signal, which is injected into the transmission line via a coupling transformer. The detection device uses a bandpass filter and high-precision voltage and current transformers to accurately extract the characteristic frequency signal components in the line. Perform signal injection and testing at regular intervals (e.g., every hour or half hour). Before injecting the signal, first assess the line's operating status to ensure it is operating normally and free of faults. After injecting the signal, check whether adjacent nodes can receive the characteristic frequency signal and record parameters such as the signal's amplitude and phase. By comparing the amplitude, phase, and other parameters of the injected and detected signals, the connection between nodes is determined to be normal. If adjacent nodes can receive the characteristic frequency signal, and the amplitude and phase variations are within a preset tolerance (e.g., amplitude error no more than 10%, phase error no more than 5°), the connection is considered normal. If no signal is received or the signal parameters are outside the tolerance range, the connection is considered abnormal.

[0044] S203. Obtain verification results, and map the verification results to the basic topology to obtain a dynamic topology adjacency matrix.

[0045] Based on the results of the connectivity verification, the adjacency matrix of the base topology is updated. If the verification result indicates a normal connectivity relationship, the weights of the edges between the corresponding nodes in the base topology adjacency matrix are set to 1. If the verification result indicates an abnormal connectivity relationship, the weights of the edges between the corresponding nodes are set to 0. A timestamp is also established to record the time of each verification and matrix update, allowing for subsequent tracing and analysis of topological changes. In the visualization interface, the edges in the topology map are colored according to the weights of the dynamic topology adjacency matrix. Edges with a weight of 0 are displayed in a striking red color as a default alarm, highlighting abnormal connections. Edges with a weight of 1 are displayed in blue as a default color, indicating normal connections. Furthermore, special effects such as flashing and bolding can be added to the topology map to further enhance the warning effect of abnormal connections. In addition, by setting up query and analysis functions in the visual interface, operation and maintenance personnel can view detailed connection relationship verification data, historical records and fault analysis reports by clicking on nodes or edges, which facilitates real-time monitoring and troubleshooting of the power grid topology.

[0046] In an embodiment of the present invention, based on step S3, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0047] S301. Calculate the impedance and load ratio between connected nodes based on the voltage and current of the nodes.

[0048] Calculate the DC system node impedance using direct measurement based on Ohm's law: Apply a known DC voltage V between nodes i and j. inj . Measure the current I flowing through the line ij .

[0049] Calculate the resistance:

[0050] V i ,V j is the node voltage.

[0051] Synchronized Phasor Measurement Unit (PMU) uses PMU to synchronously measure node voltages 、 and current , calculate the complex impedance:

[0052] Perform Fourier transform (FFT) on the 1kHz sampling data to extract the fundamental component (50 / 60Hz).

[0053] Separating resistance and reactance: Resistance component:

[0054] θ i ,θ j is the voltage phase angle, ϕ ij is the current phase angle.

[0055] Reactive component:

[0056] The load rate reflects the load level of a node or line, and the calculation formula is: η=S actual / S rated ×100%, Among them S actual is the actual apparent power. For AC systems, (U is the line voltage, I is the line current); for DC systems, S actual =UI (U is DC voltage, I is DC current). rated is the rated apparent power of the node or line. This data can be obtained from the equipment nameplate or power system design documents. After the calculation is completed, the load factor is compared with the threshold specified in the power system operation standard to evaluate the system operation status.

[0057] S302. Correct the impedance between DC nodes according to the line temperature.

[0058] The impedance of the DC line is closely related to temperature. According to the temperature characteristic formula of resistance: R t =R0(1+α(t−t0)), where R tR is the resistance at temperature t, R0 is the resistance at the reference temperature t0, and α is the resistance temperature coefficient (the value of α is different for different materials of the line, such as copper and aluminum). The line temperature t collected by the distributed optical fiber, combined with the resistance temperature coefficient α of the line material and the resistance R0 at the reference temperature (which can be obtained through the line design parameters), is used to calculate the resistance at the current temperature, and then the impedance between the DC nodes is corrected.

[0059] When new line temperature data is obtained, first determine whether the temperature change exceeds the preset threshold. If it exceeds the threshold, start the impedance correction program. Recalculate the DC line resistance according to the temperature-impedance relationship formula and update the impedance value between the DC nodes. At the same time, record the timestamps of the temperature change and impedance correction for subsequent analysis of the change trend of the line impedance with temperature.

[0060] S303. Correct the impedance between the AC nodes according to the line length.

[0061] The AC line has the characteristics of distributed parameters, and the line length has a significant impact on the impedance. For a short line (generally with a length less than 100 km), a lumped parameter model is adopted, and the line impedance Z = R + jX, where the resistance R = r0l (r0 is the resistance per unit length, which can be obtained from the line material and specification parameters, and l is the line length), and the reactance X = x0l (x0 is the reactance per unit length).

[0062] For a long line (with a length greater than 100 km), a distributed parameter model is adopted, and calculations are carried out using the Bergeron model or wave process theory, considering the influence of the distributed capacitance and inductance of the line on the impedance. By accurately calculating the line length and combining parameters such as the line material and specification, the impedance between the AC nodes is corrected.

[0063] A line parameter table is established in the power system database to record information such as the length, material, and specification of each line. When calculating the impedance between the AC nodes, the system automatically retrieves parameters such as the line length from the database, selects an appropriate calculation model according to the line length, and corrects the impedance. Regularly (such as annually) verify and update parameters such as the line length to ensure the accuracy of the correction results.

[0064] S304. Convert the vibration acceleration to a vibration level.

[0065] The vibration acceleration a is divided into: a < 0.28 is excellent, 0.28 < a < 0.71 is good, 0.71 < a < 1.8 is qualified, and a > 1.8 is unqualified.

[0066] The vibration acceleration data collected by the vibration sensor is first filtered to remove high-frequency noise and outliers. The processed data is then compared with the vibration classification standard to determine the corresponding vibration level. The power equipment monitoring system interface displays vibration levels in an intuitive manner (e.g., using different colors and icons), and also generates a vibration level trend chart, making it easier for operators to understand the vibration status of the equipment.

[0067] In an embodiment of the present invention, based on step S4, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0068] The diagnostic rules are used to determine whether there are any abnormalities in the structure of the dynamic topological adjacency matrix and the evaluation indicators of the nodes currently obtained. If so, a corresponding alarm message is generated; if not, the impedance and the corresponding corrected temperature in the evaluation indicators are saved to the data sequence, and the LSTM network is used to predict the abnormal state based on the data sequence.

[0069] The diagnostic rules include: When the impedance value of the line between the nodes is detected to suddenly exceed the maximum threshold and the current on the line drops to zero, it is determined to be a line disconnection fault; If the fluctuation amplitude of the line impedance within 1 second exceeds 10% of its historical average value, and the vibration acceleration detected exceeds the set threshold, it is determined that the line has poor contact; When the actual line load rate exceeds 85% of the rated value and the cable temperature is continuously above 70°C, an overload warning is triggered; Traverse the dynamic topology adjacency matrix, count the edges with weight 0, and match the edges with weight 0 with the planned power outage areas. If the two do not match, it is determined that there is a topological anomaly.

[0070] The following is an example of a diagnosis: To enhance the accuracy of diagnosis and prediction, feature extraction and derivation are performed on the raw data. Time series features of line impedance, including mean, standard deviation, and slope, are calculated. For vibration acceleration data, peak values, RMS values, and frequency characteristics are extracted. Furthermore, composite features, such as impedance fluctuation (the rate of impedance change per unit time) and the coupling coefficient between load factor and temperature, are constructed to provide rich information for subsequent diagnosis and prediction.

[0071] (1) Line disconnection fault diagnosis Line disconnection fault diagnosis is based on the dual criteria of impedance and current. The maximum threshold is set using a dynamic adaptive method based on the 99.5% quantile of historical data. The specific calculation is as follows: Z max =Q uantile (Z history,0.995) Among them, Z history is the historical impedance data sequence of the line. When the line impedance value Z is monitored current Satisfy Z current >Z max If the corresponding line current I is less than 5% of the rated current (i.e., I < 0.05Irated), a line disconnection fault is detected. This diagnostic process uses a sliding time window mechanism with a window length of 10 sampling cycles (sampling frequency of 10 Hz, i.e., a window length of 1 second) to avoid misjudgment caused by instantaneous fluctuations. (2) Diagnosis of poor line contact The diagnosis of poor line contact integrates impedance fluctuation and vibration acceleration characteristics. The historical average value is calculated using the exponentially weighted moving average (EWMA) algorithm, with the weight coefficient α set to 0.2. The calculation formula is:

[0072] in, is the impedance value at the current moment, When the fluctuation amplitude ΔZ of line impedance within 1 second (10 sampling points) exceeds 10% of the historical average value (i.e. ΔZ>0.1 ), and when the vibration acceleration A is greater than the set threshold, it is determined that there is a poor contact fault in the circuit. (3) Overload warning diagnosis The overload warning is based on a combination of load factor and cable temperature. When the actual line load factor η exceeds 85% of the rated value and the cable temperature T remains above 70°C for a continuous period (five consecutive sampling periods, or 0.5 seconds), the overload warning is triggered. To more accurately reflect the cable's thermal state, a thermal balance equation is introduced to correct the temperature: Where I is the line current, R is the line resistance, m is the cable mass, c p is the specific heat capacity, h is the convection heat transfer coefficient, A is the heat dissipation area, T amb is the ambient temperature. (4) Topological anomaly diagnosis The dynamic topological adjacency matrix is ​​traversed and edges with a weight of 0 are counted, representing lines with possible connectivity anomalies. These lines are then matched against the planned outage area data. A string similarity algorithm (such as the Levenshtein distance) is used to calculate the similarity of line names or numbers. When the similarity falls below a set threshold (typically 0.8), a topological anomaly is determined. Planned outage area data is obtained in real time through the power system dispatch and management system to ensure timeliness and accuracy.

[0073] LSTM network anomaly prediction: If no abnormality is found in the current diagnosis, the impedance and corresponding corrected temperature data in the evaluation index are saved to the data sequence. The data sequence is arranged in chronological order, and each sample contains impedance and temperature data of a fixed time length (set to 10 minutes, corresponding to 600 sampling points), forming a two-dimensional data matrix X∈R 600×2 In order to enhance the model’s ability to capture long-term dependencies, a sliding window method is used to generate training samples, and the window step size is set to 10 sampling points. The LSTM network consists of three LSTM layers, with 64, 32, and 16 neurons in each layer, respectively. These layers are then connected to a fully connected layer and an output layer. The input layer receives the normalized data sequence. The LSTM layer effectively models the long-term and short-term dependencies in the time series through the synergistic effect of the forget gate, input gate, and output gate. The fully connected layer transforms the feature vector output by the LSTM layer. The output layer uses a sigmoid activation function to output the probability of an anomaly (ranging from 0 to 1). A probability greater than 0.5 indicates an anomaly. The Adam optimizer is used for model training. The initial value of the learning rate is set to 0.001, and the cosine annealing learning rate adjustment strategy is used to dynamically adjust the learning rate.

[0074] In some embodiments, the highway power transmission ring network status monitoring system may include multiple functional modules composed of computer program segments. The computer program of each program segment in the highway power transmission ring network status monitoring system may be stored in a memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Function of monitoring the status of highway transmission ring network.

[0075] In this embodiment, the highway power transmission ring network status monitoring system can be divided into multiple functional modules according to the functions it performs, such as Figure 2 As shown. The functional modules of system 200 may include: module 210. A module as referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can perform fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0076] A data acquisition module is used to obtain status data of each node through sensors deployed at multiple nodes of the transmission ring network; Topology building module, used to build the dynamic topological adjacency matrix of nodes; An indicator calculation module is used to calculate evaluation indicators based on state data and map the evaluation indicators to corresponding nodes in the dynamic topology adjacency matrix; The state diagnosis module is used to diagnose the abnormal state of the transmission ring network by using the diagnosis model based on the structure of the dynamic topology adjacency matrix and the evaluation index of the node.

[0077] Optionally, as an embodiment of the present invention, the data acquisition module includes: The first collection unit is used to collect voltage and current by deploying power detection sensors at the node; A second acquisition unit is configured to deploy a vibration sensor at the node, wherein the vibration sensor acquires vibration acceleration; The third collection unit is used to collect line temperature by deploying distributed optical fibers.

[0078] Optionally, as an embodiment of the present invention, the topology building module includes: Basic building unit, used to build basic topology based on the physical connection relationship between nodes; A status verification unit, used to verify whether the connection relationship of the connected nodes of the transmission ring network is normal by regularly injecting characteristic frequency signals; The state mapping unit is used to obtain the verification result and map the verification result to the basic topology to obtain a dynamic topology adjacency matrix.

[0079] Figure 3 The state monitoring method for the highway power transmission ring network provided in the embodiment of the present application can be applied to equipment. Those skilled in the art will understand that the equipment structure involved in the embodiment of the present invention does not constitute a limitation of the equipment, and the equipment may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. In the embodiment of the present invention, the equipment includes but is not limited to laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The equipment can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0080] The device 300 may include a processor 310, a memory 320, and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention. The server structure may be a bus structure or a star structure, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0081] The memory 320 can be used to store execution instructions of the processor 310. The memory 320 can be implemented by any type of volatile or non-volatile memory 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, magnetic disk, or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the device 300 can perform some or all of the steps in the above-described method embodiments.

[0082] The processor 310 is the control center of the storage device, which uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device and / or processes data by running or executing software programs and / or modules stored in the memory 320, and calling data stored in the memory. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 310 can only include a central processing unit (CPU). In an embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0083] The communication unit 330 is configured to establish a communication channel so that the storage device can communicate with other devices, receive user data sent by other devices, or send user data to other devices.

[0084] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program that, when executed, may include some or all of the steps of each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0085] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software and a necessary general-purpose hardware platform. Based on this understanding, the technical solutions in the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, among other media capable of storing program code, and includes instructions for causing a computer device (which can be a personal computer, a server, or a second device, a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention.

[0086] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

[0087] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, and can be electrical, mechanical or other forms.

[0088] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of the present embodiment according to actual needs.

[0089] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0090] Although the present invention has been described in detail with reference to the accompanying drawings and in conjunction with preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, persons of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and such modifications or substitutions shall be within the scope of the present invention. Any changes or substitutions that can be easily conceived by persons skilled in the art within the technical scope disclosed in the present invention shall be within the scope of protection of the present invention.

Claims

1. A method for monitoring the status of a highway power transmission ring network, characterized in that: include: The status data of each node is obtained through sensors deployed at multiple nodes in the transmission ring network; Construct a dynamic topological adjacency matrix of nodes; Calculating evaluation indicators based on the state data and mapping the evaluation indicators to corresponding nodes in the dynamic topology adjacency matrix; The diagnosis model is used to diagnose abnormal conditions of the transmission ring network based on the structure of the dynamic topological adjacency matrix and the evaluation indicators of the nodes.

2. The method according to claim 1, characterized in that Sensors deployed at multiple nodes in the transmission ring network acquire status data for each node, including: Deploy power detection sensors at nodes to collect voltage and current; Deploy a vibration sensor at the node, wherein the vibration sensor collects vibration acceleration; Distributed optical fibers are deployed to collect line temperature.

3. The method according to claim 1, characterized in that Construct a dynamic topological adjacency matrix of nodes, including: Build the basic topology based on the physical connection relationship between nodes; Regularly verify whether the connection relationship of the connected nodes of the transmission ring network is normal by injecting characteristic frequency signals; The verification result is obtained and mapped to the basic topology to obtain a dynamic topology adjacency matrix.

4. The method according to claim 3, characterized in that Mapping the verification results to the underlying topology includes: If the verification result shows that the connection relationship is normal, the weight of the edge between the corresponding nodes in the basic topology is set to 1; If the verification result shows that the connection relationship is abnormal, the weight of the edge between the corresponding nodes in the basic topology is set to 0; In the display state, the edge with a weight of 0 adopts the preset alarm display color, and the edge with a weight of 1 adopts the preset default display color.

5. The method according to claim 2, characterized in that Calculating evaluation indicators based on state data and mapping the evaluation indicators to corresponding nodes in a dynamic topology adjacency matrix, including: Calculate the impedance and load rate between connected nodes based on the voltage and current of the nodes; Correcting the impedance between DC nodes according to the line temperature; Correct the impedance between AC nodes according to the line length; The vibration acceleration is converted into a vibration level.

6. The method according to claim 5, characterized in that The diagnostic model is based on the structure of the dynamic topological adjacency matrix and the evaluation indicators of the nodes to diagnose abnormal conditions of the transmission ring network, including: Use diagnostic rules to determine whether there are any abnormalities in the structure of the dynamic topology adjacency matrix and the evaluation indicators of the nodes currently obtained: If so, a corresponding alarm message is generated; If not, the impedance and the corresponding corrected temperature in the evaluation index are saved to the data sequence, and the LSTM network is used to predict the abnormal state based on the data sequence.

7. The method according to claim 6, characterized in that Use diagnostic rules to determine whether there are any abnormalities in the structure of the dynamic topology adjacency matrix and the evaluation indicators of the nodes currently obtained, including: When the impedance value of the line between the nodes is detected to suddenly exceed the maximum threshold and the current on the line drops to zero, it is determined to be a line disconnection fault; If the fluctuation amplitude of the line impedance within 1 second exceeds 10% of its historical average value, and the vibration acceleration detected exceeds the set threshold, it is determined that the line has poor contact; When the actual line load rate exceeds 85% of the rated value and the cable temperature is continuously above 70°C, an overload warning is triggered; Traverse the dynamic topology adjacency matrix, count the edges with weight 0, and match the edges with weight 0 with the planned power outage areas. If the two do not match, it is determined that there is a topological anomaly.

8. A highway power transmission ring network status monitoring system, characterized in that: include: A data acquisition module is used to obtain status data of each node through sensors deployed at multiple nodes of the transmission ring network; Topology building module, used to build the dynamic topological adjacency matrix of nodes; An indicator calculation module is used to calculate evaluation indicators based on state data and map the evaluation indicators to corresponding nodes in the dynamic topology adjacency matrix; The state diagnosis module is used to diagnose the abnormal state of the transmission ring network by using the diagnosis model based on the structure of the dynamic topology adjacency matrix and the evaluation index of the node.

9. The system according to claim 8, characterized in that The data acquisition module includes: The first collection unit is used to collect voltage and current by deploying power detection sensors at the node; A second acquisition unit is configured to deploy a vibration sensor at the node, wherein the vibration sensor acquires vibration acceleration; The third collection unit is used to collect line temperature by deploying distributed optical fibers.

10. The system according to claim 8, wherein: The topology building module includes: Basic building unit, used to build basic topology based on the physical connection relationship between nodes; A status verification unit, used to verify whether the connection relationship of the connected nodes of the transmission ring network is normal by regularly injecting characteristic frequency signals; The state mapping unit is used to obtain the verification result and map the verification result to the basic topology to obtain a dynamic topology adjacency matrix.

Images