Circuit online monitoring method, system and equipment for power transmission line

Abstract

The invention discloses a circuit on-line monitoring method, system and device for a power transmission line, and relates to the technical field of electric power, and the method comprises the steps: obtaining a target long-distance power transmission line, dividing the target long-distance power transmission line into N segments according to the environment heterogeneity and the electrical response difference, constructing corresponding intra-segment equivalent circuit models, and carrying out the combination to generate a whole-line combination equivalent model; respectively acquiring operation data of the N sections of circuits to form N groups of distributed monitoring data sets; and performing anomaly analysis on the monitoring data by using the combined equivalent model, obtaining an anomaly index of each section of circuit, and realizing accurate positioning and early warning reminding of an abnormal circuit according to the anomaly index. Therefore, the technical effects of environment adaptability enhancement, model precision improvement and monitoring and positioning accuracy improvement are achieved.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method, system and equipment for online monitoring of circuits of transmission lines. Background Art

[0002] With the continuous growth of electricity demand and the increasing length of transmission distances, higher requirements are being placed on the monitoring and fault warning of long-distance transmission lines. Traditional methods for modeling and monitoring transmission lines typically treat the entire transmission line as a single entity for modeling and analysis, using a single equivalent circuit model to characterize the electrical characteristics of the transmission line. However, long-distance transmission lines often traverse diverse geographical environments and climatic conditions, facing complex environmental heterogeneity. For example, different terrains, such as mountainous areas, plains, and deserts, lead to significant differences in environmental factors such as temperature, humidity, and wind speed. Furthermore, different sections of the line exhibit varying electrical responses, which are difficult to fully account for in traditional holistic modeling approaches. As a result, these approaches fail to accurately reflect the actual operating status of the transmission line under different environmental and electrical conditions, making it difficult to promptly detect potential fault hazards. Summary of the Invention

[0003] The present invention provides a method, system and equipment for online circuit monitoring of transmission lines to solve the technical problems in the prior art of ignoring environmental heterogeneity, insufficient model accuracy, and affecting the accuracy of monitoring and fault location, thereby achieving the technical effects of enhanced environmental adaptability, improved model accuracy, and improved monitoring and positioning accuracy.

[0004] In a first aspect, the present invention provides a method for online monitoring of a circuit of a power transmission line, wherein the method for online monitoring of a circuit of a power transmission line comprises: Acquire the target long-distance transmission line.

[0005] The long-distance transmission line is divided into N circuit segments according to environmental heterogeneity and electrical response differences, an intra-segment equivalent circuit model corresponding to each of the N circuit segments is constructed, and N intra-segment equivalent circuit models are output.

[0006] The N intra-segment equivalent circuit models are combined to construct a full-line combined equivalent model.

[0007] Circuit operation data are collected for each of the N sections of circuits, and corresponding N groups of distributed monitoring data sets are output.

[0008] The full-line combination equivalent model is called to perform an anomaly analysis on the N groups of distributed monitoring data sets, obtain N anomaly indicators corresponding to the N sections of circuits, and locate and remind abnormal circuits according to the N anomaly indicators.

[0009] In a feasible implementation, the long-distance transmission line is divided into N circuit sections according to environmental heterogeneity and electrical response differences, including: The long-distance power transmission line is initialized and divided into segments with equal intervals, and M segments of circuits are output.

[0010] M groups of line environment information and M groups of electrical operation response data corresponding to the M sections of circuits are collected.

[0011] An environmental heterogeneity score and an electrical response difference score of each of the M circuit segments are calculated based on the M groups of line environment information and the M groups of electrical operation response data.

[0012] Adaptively segmenting the M-segment circuit using the environmental heterogeneity score and the electrical response difference score as variables, and outputting a segmentation result, wherein the segmentation result is an N-segment circuit.

[0013] In a feasible implementation, the environmental heterogeneity score and the electrical response difference score are used as variables to adaptively segment the M-segment circuit, and output the segmentation result, including: A fusion scoring function is constructed to calculate M fusion scoring indicators corresponding to the M circuit segments according to the environmental heterogeneity score and the electrical response difference score.

[0014] The M fusion score indicators are traversed to calculate the fusion score indicator differences of adjacent segments, and M-1 fusion score indicator differences are output.

[0015] A segment fusion score threshold is set, and circuits whose M-1 fusion score indicator differences are greater than the segment fusion score threshold are output as candidate segment boundaries.

[0016] Adaptively cluster the candidate segment boundaries and output segment division results.

[0017] In a feasible implementation, constructing an intra-segment equivalent circuit model corresponding to each of the N segments of the circuit and outputting N intra-segment equivalent circuit models includes: The physical structure parameters and electrical connection characteristics corresponding to the N segments of the circuit are collected.

[0018] According to the physical structure parameters and the electrical connection characteristics, equivalent model parameters of each circuit segment are calculated, and N equivalent model parameters are output.

[0019] Equivalent circuit model processing is performed on the N circuit segments according to the N equivalent model parameters, and N intra-segment equivalent circuit models are output.

[0020] In a feasible implementation, before calculating the equivalent model parameters of each circuit segment, the following steps are also included: Get an equivalent model selector, the equivalent model selector pre-stores RL equivalent models, Type equivalent model and T-type equivalent model.

[0021] The equivalent model selector outputs N equivalent model types and N equivalent model parameters corresponding to the N circuit segments according to the physical structure parameters and the electrical connection characteristics.

[0022] In a feasible implementation, equivalent model parameters of each equivalent model are defined in the equivalent model selector.

[0023] The equivalent model parameters of the RL equivalent model include series resistance and series inductance. The equivalent model parameters of the T-type equivalent model include series impedance and capacitance between both ends to ground, and the equivalent model parameters of the T-type equivalent model include series impedance between both ends and susceptance between the midpoint and ground.

[0024] In a feasible implementation, combining the N intra-segment equivalent circuit models to construct a full-line combined equivalent model further includes: Obtain abnormal event sample signals.

[0025] Equivalent error fitting is performed on the N intra-segment equivalent circuit models respectively according to the abnormal event sample signal, and N equivalent error indicators are output.

[0026] The N intra-segment equivalent circuit models are equivalently optimized with the goal of minimizing the N equivalent error indicators, and the optimized N intra-segment equivalent circuit models are output.

[0027] The N equivalent circuit models within the optimized segments are connected to construct the equivalent model of the entire line combination.

[0028] In a feasible implementation, calling the full-line combination equivalent model to perform anomaly analysis on the N groups of distributed monitoring data sets to obtain N anomaly indicators corresponding to the N sections of circuits includes: An equivalent training data set of the full-line combination equivalent model is established, including M groups of equivalent training data sets in a healthy state and M groups of equivalent training data sets under the abnormal event sample signal.

[0029] Model training is performed based on the equivalent training data set and labels representing the degree of abnormality, an abnormality monitoring model is output, and N abnormality indicators corresponding to the N sections of circuits are obtained based on the abnormality monitoring model.

[0030] In a second aspect, the present invention further provides an online circuit monitoring system for a power transmission line, wherein the online circuit monitoring system for a power transmission line comprises: The target transmission line acquisition module is used to acquire the target long-distance transmission line.

[0031] The equivalent circuit model construction module is used to divide the long-distance transmission line into N circuit segments according to environmental heterogeneity and electrical response differences, construct an intra-segment equivalent circuit model corresponding to each of the N circuit segments, and output N intra-segment equivalent circuit models.

[0032] The model combination module is used to combine the N intra-segment equivalent circuit models to construct a full-circuit combination equivalent model.

[0033] The monitoring and acquisition module is used to collect circuit operation data of the N sections of circuits respectively and output corresponding N groups of distributed monitoring data sets.

[0034] The analysis and positioning reminder module is used to call the full-line combination equivalent model to perform abnormal analysis on the N groups of distributed monitoring data sets, obtain N abnormal indicators corresponding to the N sections of circuits, and locate and remind abnormal circuits according to the N abnormal indicators.

[0035] In a third aspect, the present invention further provides an electronic device comprising: a memory for storing executable instructions; and a processor for implementing the method for online monitoring of circuits for transmission lines provided by the present invention when executing the executable instructions stored in the memory.

[0036] The present invention discloses a method, system and equipment for online circuit monitoring of transmission lines, comprising: obtaining basic information of a target long-distance transmission line; segmenting the transmission line based on environmental heterogeneity and electrical response differences, dividing the entire transmission line into N sub-circuits, and constructing an intra-segment equivalent circuit model corresponding to each sub-circuit, thereby obtaining N intra-segment equivalent circuit models; integrating and combining the N intra-segment equivalent circuit models to construct a combined equivalent model covering the entire transmission line; respectively collecting corresponding circuit operation data for the N sub-circuits to form N groups of distributed monitoring data sets; calling the combined equivalent model to jointly analyze the N groups of distributed monitoring data sets, identifying abnormal characteristic indicators of each sub-circuit, and then outputting N corresponding abnormal indicators; judging whether there is an abnormal circuit segment based on the abnormal indicator, and performing positioning and early warning reminder operations on the circuit segment with the abnormality. The method, system and equipment for online circuit monitoring of transmission lines disclosed by the present invention solve the technical problems of ignoring environmental heterogeneity, insufficient model accuracy, and affecting the accuracy of monitoring and fault location, and achieve the technical effects of enhanced environmental adaptability, improved model accuracy, and improved monitoring and positioning accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The figure is a flow chart of the method for online monitoring of a circuit of a power transmission line according to the present invention.

[0038] Figure 2 The figure is a schematic structural diagram of the circuit online monitoring system for power transmission lines according to the present invention.

[0039] Figure 3 Schematic diagram of the structure of an exemplary electronic device of the present invention.

[0040] Explanation of the reference numerals: target transmission line acquisition module 11 , equivalent circuit model construction module 12 , model combination module 13 , monitoring and acquisition module 14 , analysis and positioning reminder module 15 , processor 31 , memory 32 , input device 33 , output device 34 . DETAILED DESCRIPTION

[0041] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention, rather than all, are shown in the drawings.

[0042] Example 1, as Figure 1 The figure is a flow chart of a method for online monitoring of a circuit of a power transmission line according to the present invention, wherein the method for online monitoring of a circuit of a power transmission line comprises: S100: Acquire a target long-distance power transmission line.

[0043] Specifically, acquiring the target long-distance transmission line means determining the specific line that needs to be monitored from among many transmission lines, that is, identifying and locating the transmission line in the power grid system to ensure that subsequent monitoring and analysis can be carried out on the correct object.

[0044] The specific process includes retrieving relevant information about the target transmission line from the power grid's database or monitoring system, such as the line's starting and ending points, the geographical areas passed along the way, the line's voltage level and transmission capacity, etc., to provide clear objects for subsequent segmented modeling, data collection and anomaly analysis, ensuring that the entire monitoring process is targeted and purposeful.

[0045] S200: Divide the long-distance transmission line into N circuit segments according to environmental heterogeneity and electrical response differences, construct an intra-segment equivalent circuit model corresponding to each of the N circuit segments, and output N intra-segment equivalent circuit models.

[0046] Specifically, environmental heterogeneity refers to differences in environmental conditions along a transmission line due to factors such as geography and climate. For example, temperature, humidity, and wind speed vary across terrains like mountainous areas, plains, and deserts. Electrical response variability refers to the varying electrical characteristics (such as voltage, current, and impedance) across different sections of a transmission line. Based on these differences, the entire line can be segmented into sections with similar environmental and electrical characteristics.

[0047] Specifically, the intra-segment equivalent circuit model is a simplified circuit model established for each segment, which is used to characterize the electrical behavior of the segment. The output N intra-segment equivalent circuit models are the models corresponding to the N segments.

[0048] The segmented modeling approach described above enables the equivalent circuit model within each segment to more closely reflect the operating characteristics of the actual line under varying environmental and electrical conditions. Compared to traditional, holistic modeling, this significantly improves model accuracy and enhances adaptability to complex environments. Furthermore, the segmented model facilitates targeted monitoring and analysis, helping to improve the accuracy of monitoring and positioning, and more effectively identify potential fault hazards.

[0049] In some embodiments, dividing the long-distance power transmission line into N circuit segments according to environmental heterogeneity and electrical response differences includes: The long-distance transmission line is initialized and divided into equally spaced segments, and M circuit segments are output; M groups of line environment information and M groups of electrical operation response data corresponding to the M circuit segments are collected; an environmental heterogeneity score and an electrical response difference score of each circuit segment in the M circuit segments are calculated based on the M groups of line environment information and the M groups of electrical operation response data; the M circuit segments are adaptively segmented using the environmental heterogeneity scores and the electrical response difference scores as variables, and a segmentation result is output, wherein the segmentation result is N circuit segments.

[0050] Specifically, long-distance transmission lines are first preliminarily divided into M segments according to a preset equidistant standard. For example, a 100-kilometer line is divided into 10-kilometer segments, where M = 10. Then, for each segment (a total of M segments), corresponding environmental information (such as terrain type, meteorological parameters, and vegetation coverage) and electrical operation response data (such as historical current, voltage, and failure rate for that segment) are collected. Next, feature extraction and quantification are performed on each segment of environmental information to generate an environmental heterogeneity score (e.g., calculated according to preset evaluation rules). Simultaneously, the electrical operation response data for each segment is analyzed to calculate an electrical response difference score (e.g., by calculating the standard deviation or coefficient of variation between the electrical operation response data and a preset value).

[0051] Furthermore, using the environmental heterogeneity score and the electrical response difference score as input variables, a clustering algorithm (such as K-means, hierarchical clustering, etc.) or an adaptive segmentation algorithm is used to reorganize the M-segment circuit into segments, outputting a final N-segment circuit (N ≤ M). For example, if some consecutive initial segments are highly similar in environmental and electrical characteristics, they can be merged into one segment; if the characteristics of some segments suddenly change, they are separately divided into new segments.

[0052] Through the above process, the intelligent and refined segmentation of long-distance transmission lines is achieved, so that each section has a high degree of consistency in environmental and electrical characteristics, which is conducive to subsequent zoning operation and maintenance, differentiated management and risk warning.

[0053] In some implementations, adaptively segmenting the M-segment circuit using the environmental heterogeneity score and the electrical response difference score as variables and outputting the segmentation result includes: A fusion scoring function is constructed to calculate M fusion scoring indicators corresponding to the M segments of circuits based on the environmental heterogeneity score and the electrical response difference score; the M fusion scoring indicators are traversed to calculate the fusion scoring indicator differences of adjacent segments, and M-1 fusion scoring indicator differences are output; a segmented fusion scoring threshold is set, and circuits with M-1 fusion scoring indicator differences greater than the segmented fusion scoring threshold are output as candidate segment boundaries; the candidate segment boundaries are adaptively clustered, and a segment division result is output.

[0054] Specifically, the fusion scoring function is used to weight or otherwise combine the environmental heterogeneity score and the electrical response difference score to obtain a scoring index that comprehensively reflects the heterogeneity of each circuit segment. This fusion scoring function can be constructed using linear weighting, nonlinear combination, and other methods.

[0055] Specifically, the fusion score difference is used to reflect the degree of mutation in the comprehensive characteristics between segments. The segment fusion score threshold is used to determine whether the fusion score difference is significant. If it exceeds this threshold, it is considered that there is a clear segment boundary.

[0056] Specifically, the fusion scoring function is constructed and the environmental heterogeneity score of each circuit is set as , the electrical response difference score is , then the fusion scoring function can be defined as: ; Among them, α and β are weight parameters, which can be set according to actual needs or optimized through data-driven methods.

[0057] Then, based on the constructed fusion scoring function, the M fusion scoring indicators of the M-segment circuit are calculated, and the fusion scoring indicator difference of all adjacent segments is calculated. ,get The score difference is used to reflect the changes in comprehensive characteristics between segments.

[0058] Furthermore, we set a threshold T and The positions of the segments are used as candidate segment boundaries, and adaptive clustering (such as density clustering, hierarchical clustering, etc.) is performed on the candidate segment boundaries to avoid excessive segmentation due to occasional anomalies, and the final N-segment circuit partitioning result is output. For example, segment boundaries that are too close to each other are merged or expert rules are combined to further optimize the number and position of segments.

[0059] Through the above process, adaptive segmentation is achieved by integrating environmental and electrical characteristics in multiple dimensions, more accurately reflecting the actual heterogeneity and operational differences of the line. This helps avoid the limitations of subjective or equidistant segmentation, improving the scientific nature and engineering applicability of the segmentation. The threshold and clustering mechanisms ensure the stability and robustness of the segmentation, avoiding overfitting and over-segmentation, and facilitating targeted deployment of subsequent operations, maintenance, monitoring, and risk management.

[0060] In some embodiments, constructing an intra-segment equivalent circuit model corresponding to each of the N segments of the circuit and outputting N intra-segment equivalent circuit models includes: Collect physical structure parameters and electrical connection characteristics corresponding to the N circuit segments; calculate equivalent model parameters of each circuit segment based on the physical structure parameters and the electrical connection characteristics, and output N equivalent model parameters; perform equivalent circuit model processing on the N circuit segments according to the N equivalent model parameters, and output N equivalent circuit models within the segments.

[0061] Specifically, the equivalent circuit model is a mathematical model that uses the electrical components (such as resistors, inductors, capacitors, etc.) and parameters to comprehensively reflect the main electrical characteristics (such as impedance, admittance, mutual inductance, etc.) of the actual circuit segment. It has the function of simplifying the circuit and facilitates subsequent analysis, simulation and optimization.

[0062] Specifically, physical structural parameters refer to the actual geometric and physical information of the transmission line, such as conductor length, cross-sectional area, conductor spacing, tower type, etc. Electrical connection characteristics refer to the electrical properties of the circuit segment, including parameters such as resistance, inductance, capacitance, grounding method, and connection method.

[0063] Specifically, the physical structural parameters (such as length, conductor type, cross-section, and tower spacing) and electrical connection characteristics (such as resistance, inductance, capacitance, and grounding method) of the N circuit segments obtained through adaptive partitioning are first collected. Then, based on the collected parameters, electrical theory formulas or simulation tools are used to calculate the equivalent parameters of each circuit segment. For example: equivalent resistance: ; Equivalent inductance: calculated based on the arrangement and length of the wires; Equivalent capacitance: calculated based on the distance between the wires and the ground and between phases.

[0064] Furthermore, according to the equivalent parameters of each segment, N intra-segment equivalent circuit models (such as π-type, T-type or lumped parameter models) are constructed and output for subsequent analysis, simulation or operation and maintenance decision-making.

[0065] Through this process, complex transmission lines can be segmented to form accurate equivalent circuit models, which in turn helps improve the accuracy and efficiency of subsequent simulation, analysis, and control. At the same time, it reduces model complexity, facilitates rapid modeling and dynamic adjustment of large-scale lines, and supports differentiated operating status assessment, fault diagnosis, and optimization strategy formulation for different sections, helping to improve the safety and economic efficiency of transmission lines. In some embodiments, before calculating the equivalent model parameters of each circuit segment, the method further includes: Get an equivalent model selector, the equivalent model selector pre-stores RL equivalent models, type equivalent model and T-type equivalent model; the equivalent model selector outputs N equivalent model types and N equivalent model parameters corresponding to the N-segment circuit according to the physical structure parameters and the electrical connection characteristics.

[0066] Specifically, the equivalent model selector is used to automatically select the most appropriate equivalent circuit model type (such as RL, π-type, or T-type models) and its parameters based on the circuit's physical structure parameters and electrical connection characteristics. The RL equivalent model uses series resistance and inductance to reflect the primary electrical characteristics of the circuit and is suitable for short-distance or low-complexity circuit segments. The π-type equivalent model, consisting of capacitance to ground at both ends and series resistance and inductance in the middle, is suitable for circuit segments with medium distances and significant distributed parameters. The T-type equivalent model, primarily based on capacitance to ground in the middle and series resistance and inductance at both ends, is suitable for long-distance or line segments with more significant distributed effects.

[0067] Specifically, the equivalent model selector is retrieved and initialized. The equivalent model selector stores a variety of standardized equivalent models (such as RL, π-type, and T-type) and their parameter calculation formulas or templates. The physical structural parameters (such as length, conductor cross-section, and tower type) and electrical connection characteristics (such as resistance, inductance, capacitance, and grounding type) of each circuit segment are then input into the equivalent model selector. The equivalent model selector automatically selects the appropriate equivalent model type for each circuit segment based on preset rules (such as line length thresholds and distribution parameter significance).

[0068] For example, if the line length is short and the distribution parameters have little impact, the RL model is selected; if the line length is moderate and the distribution parameters have a certain impact, the π-type model is selected; if the line length is long and the distribution parameters have a significant impact, the T-type model is selected.

[0069] Furthermore, based on the selected model type, the corresponding parameter calculation formula is automatically called to calculate the equivalent model parameters corresponding to each circuit segment, and the equivalent model type and equivalent model parameters are associated and output. For example, if the i-th segment is selected as a π-type model, the calculated output is: i , series inductor L i 、Capacitance C i1 with C i2 The parameters of are used as equivalent model parameters.

[0070] The above process uses an equivalent model selector to dynamically select the most appropriate equivalent model type based on the physical and electrical characteristics of different circuit segments. This not only ensures the physical meaning and simulation accuracy of the model, but also improves modeling efficiency, reduces human subjectivity and operational complexity, and helps ensure the accuracy of subsequent analysis.

[0071] In some embodiments, equivalent model parameters of each equivalent model are defined in the equivalent model selector; wherein the equivalent model parameters of the RL equivalent model include a series resistance and a series inductance, The equivalent model parameters of the T-type equivalent model include series impedance and capacitance between both ends to ground, and the equivalent model parameters of the T-type equivalent model include series impedance between both ends and susceptance between the midpoint and ground.

[0072] Specifically, equivalent model parameters are a set of parameters used to describe the electrical characteristics of the equivalent circuit model. Different types of equivalent models correspond to different parameter definitions. These include: Series resistance: The resistance component in a circuit connected in series with the direction of current flow, used to reflect the active power loss characteristics of the line. Series inductance: The inductance component in a circuit connected in series with the direction of current flow, reflecting the electromagnetic energy storage and impedance characteristics of the line. Series impedance: The total impedance composed of series resistance and series inductance. Ground capacitance: The capacitance formed between the conductor and the ground, reflecting the electric field distribution and energy storage characteristics of the line. Ground susceptance: The admittance of the ground capacitance, commonly used in T-type models.

[0073] S300: Combining the N intra-segment equivalent circuit models to construct a full-line combined equivalent model.

[0074] Specifically, by combining multiple intra-segment equivalent circuit models in series or in parallel according to actual electrical connection methods, an overall equivalent circuit model that can overall reflect the electrical characteristics of the complete line is formed.

[0075] Specifically, first, according to the aforementioned steps, the equivalent circuit models and their parameters for N line segments are obtained. Then, based on the actual electrical connection of the line (e.g., series, parallel, or mixed), the combination of the equivalent models for each segment is determined. For example, for typical transmission lines, series connection is often used. Next, the parameters of the individual segment models are synthesized according to circuit theory to obtain the overall parameters of the combined equivalent model. For example, in a series connection, the total resistance is the sum of the resistances of each segment, the total inductance is the sum of the inductances of each segment, and the total capacitance is synthesized using the series formula. In a parallel connection, the parameters are synthesized using the parallel formula. Finally, the synthesized parameters and structure are output as a combined equivalent model of the entire line for subsequent simulation, analysis, or operation and maintenance decision-making.

[0076] Through the organic combination of the models of each section, the above process allows the overall model to more realistically reflect the electrical characteristics of the entire line, thereby improving the overall modeling accuracy. At the same time, the segment model and the combined model can be flexibly decoupled according to the situation, facilitating the rapid updating and maintenance of the model during subsequent local line modifications.

[0077] In some embodiments, combining the N intra-segment equivalent circuit models to construct a full-circuit combined equivalent model further includes: Acquire an abnormal event sample signal; perform equivalent error fitting on the N in-segment equivalent circuit models according to the abnormal event sample signal, and output N equivalent error indicators; perform equivalent optimization on the N in-segment equivalent circuit models with the goal of minimizing the N equivalent error indicators, and output the optimized N in-segment equivalent circuit models; connect the optimized N in-segment equivalent circuit models to construct a full-line combination equivalent model.

[0078] Specifically, abnormal event sample signals refer to typical power signal samples collected during power system operation that reflect abnormal or faulty conditions, such as voltage sags, current surges, and short-circuit waveforms. Equivalent error fitting evaluates model accuracy by comparing the output of the equivalent circuit model with the actual abnormal event sample signals. This accuracy is typically quantified using error metrics such as mean square error (MSE) and maximum deviation.

[0079] Specifically, the monitoring system or historical database is used to obtain waveforms of voltage, current, and other signals that represent abnormal line behavior as sample inputs. The abnormal event sample signals are then fed into the equivalent circuit model within each segment. The error between the model output and the actual signal is calculated to obtain N equivalent error metrics (such as the mean square error (MSE) for each segment).

[0080] Furthermore, with the goal of minimizing N equivalent error indicators, a parameter optimization algorithm (such as least squares or genetic algorithms) is used to adjust the parameters of each segment model and output the optimized N segment equivalent circuit models. Furthermore, these N optimized segment equivalent circuit models are combined according to the actual electrical connection method (series, parallel, etc.) to construct a combined equivalent model of the entire line, achieving high-precision modeling of the electrical behavior of the entire line.

[0081] The above process uses error fitting and parameter optimization driven by abnormal event sample signals to enable the equivalent model to better reflect the actual behavior of the line under abnormal operating conditions, improve the reliability and practicality of the model, and thus provide a solid data and model foundation for subsequent intelligent applications such as anomaly detection, fault location, and operation and maintenance optimization.

[0082] S400: Collect circuit operation data for each of the N circuits, and output corresponding N groups of distributed monitoring data sets.

[0083] Specifically, a monitoring device or acquisition module is deployed on each section of the power line (N sections in total) to collect key electrical parameters such as voltage, current, phase, and frequency in real time or periodically during operation, generating N sets of distributed monitoring data sets. Each set corresponds to a section of the circuit and includes operating status information for that section at different points in time.

[0084] Through the above process, it is possible to achieve refined distributed monitoring of the operating status of each section of the entire line, providing a high-quality data basis for subsequent abnormal event analysis and equivalent error fitting.

[0085] S500: Calling the full-line combination equivalent model to perform anomaly analysis on the N groups of distributed monitoring data sets, obtaining N abnormal indicators corresponding to the N sections of circuits, and locating and prompting abnormal circuits according to the N abnormal indicators.

[0086] Optionally, the model can analyze the operating data of each circuit segment for anomalies, outputting N anomaly indicators corresponding to each of the N circuit segments. All anomaly indicators are then compared and thresholded to locate circuit segments where anomaly indicators exceed preset thresholds. Furthermore, the system automatically generates location results for the detected anomaly segments, providing reminders and alerts via the system interface, text messages, emails, and other means.

[0087] In some embodiments, calling the full-circuit combination equivalent model to perform anomaly analysis on the N groups of distributed monitoring data sets to obtain N anomaly indicators corresponding to the N sections of circuits includes: An equivalent training data set for the full-circuit combination equivalent model is established, including M groups of equivalent training data sets in a healthy state and M groups of equivalent training data sets under the abnormal event sample signals; model training is performed based on the equivalent training data sets and labels representing the degree of abnormality, and an abnormality monitoring model is output. N abnormality indicators corresponding to the N sections of the circuit are obtained based on the abnormality monitoring model.

[0088] Specifically, equivalent training datasets refer to multiple sets of circuit operating data collected or simulated in both healthy and abnormal states, used to train equivalent models for the entire circuit. Anomaly monitoring models, trained using equivalent training datasets based on machine learning and other methods, are used to identify and quantify the severity of circuit anomalies.

[0089] Specifically, based on the full circuit combination equivalent model, M sets of equivalent training data sets are collected or simulated under healthy (normal) conditions and abnormal event sample signals. Each set of data sets contains the key operating parameters of each circuit segment (such as voltage, current, and phase), along with labels indicating the degree of health or abnormality.

[0090] Next, using the equivalent training dataset as input and labels representing the health or abnormality level as the corresponding supervisory signals, the anomaly monitoring model is trained using machine learning methods (such as support vector machines, neural networks, and decision trees). This allows the model to accurately distinguish between healthy and abnormal states and quantify the degree of abnormality. Specifically, the anomaly monitoring model's performance is tested using the validation dataset. If the performance is satisfactory, the training process is terminated.

[0091] Furthermore, the N sets of distributed monitoring data sets collected are fed into the trained anomaly monitoring model, which then outputs N anomaly indicators corresponding to the N circuit segments. These anomaly indicators can be probability values, scores, or status classifications, which are then used for subsequent anomaly location and alarming.

[0092] Through model training and indicator output in the above process, abnormal sections in the line can be automatically and accurately identified and located, thereby reducing the burden of manual inspections and realizing data-driven intelligent operation and maintenance and early warning.

[0093] In summary, the method for online monitoring of power transmission lines provided by the present invention has the following technical effects: By obtaining basic information of the target long-distance transmission line; segmenting the transmission line based on environmental heterogeneity and electrical response differences, dividing the entire transmission line into N sub-circuits, and constructing an intra-segment equivalent circuit model corresponding to each sub-circuit, thereby obtaining N intra-segment equivalent circuit models; integrating and combining the N intra-segment equivalent circuit models to construct a combined equivalent model covering the entire transmission line; for the N sub-circuits, respectively collect corresponding circuit operation data to form N groups of distributed monitoring data sets; calling the combined equivalent model to jointly analyze the N groups of distributed monitoring data sets, identify the abnormal characteristic indicators of each sub-circuit, and then output N corresponding abnormal indicators; judging whether there is an abnormal circuit segment based on the abnormal indicators, and performing positioning and early warning reminder operations on the circuit segment with the abnormality, thereby achieving the technical effects of enhanced environmental adaptability, improved model accuracy, and improved monitoring and positioning accuracy.

[0094] Example 2, as Figure 2 This is a schematic diagram of the structure of the circuit online monitoring system for transmission lines of the present invention. For example, Figure 1 The flow chart of the method for online monitoring of a circuit of a transmission line according to the present invention can be shown as follows: Figure 2 The structure shown is implemented.

[0095] Based on the same concept as the online circuit monitoring method for a transmission line in the above embodiment, the present invention also provides an online circuit monitoring system for a transmission line, comprising: A target transmission line acquisition module 11 is used to acquire a target long-distance transmission line; an equivalent circuit model construction module 12, configured to divide the long-distance transmission line into N circuit segments according to environmental heterogeneity and electrical response differences, construct an intra-segment equivalent circuit model corresponding to each of the N circuit segments, and output N intra-segment equivalent circuit models; A model combination module 13 is used to combine the N intra-segment equivalent circuit models to construct a full-circuit combined equivalent model; A monitoring and collection module 14 is configured to collect circuit operation data for each of the N circuit segments and output corresponding N sets of distributed monitoring data sets; The analysis and positioning reminder module 15 is used to call the full-line combination equivalent model to perform abnormal analysis on the N groups of distributed monitoring data sets, obtain N abnormal indicators corresponding to the N sections of circuits, and locate and remind abnormal circuits according to the N abnormal indicators.

[0096] In some embodiments, the equivalent circuit model building module 12 includes: The equally spaced segmentation unit is used to initialize the long-distance transmission line into equally spaced segments and output M-segment circuits.

[0097] The line environment information and electrical operation response data acquisition unit is used to acquire M groups of line environment information and M groups of electrical operation response data corresponding to the M sections of circuits.

[0098] The environmental heterogeneity and electrical response difference score calculation unit is used to calculate the environmental heterogeneity score and electrical response difference score of each circuit in the M circuit segments according to the M groups of line environment information and the M groups of electrical operation response data.

[0099] The adaptive segment division unit is used to adaptively segment the M-segment circuit using the environmental heterogeneity score and the electrical response difference score as variables, and output a segment division result, wherein the segment division result is an N-segment circuit.

[0100] In some implementations, the adaptive segment division unit in the equivalent circuit model construction module 12 includes: The fusion scoring function construction and fusion scoring index calculation unit is used to construct a fusion scoring function and calculate M fusion scoring indicators corresponding to the M circuit segments according to the environmental heterogeneity score and the electrical response difference score.

[0101] The fusion score index difference calculation unit is used to traverse the M fusion score indexes to calculate the fusion score index differences of adjacent segments and output M-1 fusion score index differences.

[0102] The candidate segment boundary determination unit is configured to set a segment fusion score threshold, and output the circuits whose M-1 fusion score indicator differences are greater than the segment fusion score threshold as candidate segment boundaries.

[0103] The segment division result output unit is used to adaptively cluster the candidate segment boundaries and output the segment division result.

[0104] In some embodiments, the equivalent circuit model building module 12 further includes: The physical structure parameter and electrical connection characteristic collecting unit is used to collect the physical structure parameters and electrical connection characteristics corresponding to the N sections of circuits.

[0105] The equivalent model parameter calculation unit is used to calculate the equivalent model parameters of each circuit segment according to the physical structure parameters and the electrical connection characteristics, and output N equivalent model parameters.

[0106] The intra-segment equivalent circuit model processing unit is used to perform equivalent circuit model processing on the N-segment circuits according to the N equivalent model parameters and output N intra-segment equivalent circuit models.

[0107] In some implementations, the equivalent model parameter calculation unit in the equivalent circuit model construction module 12 includes: The equivalent model selector acquisition unit is used to acquire an equivalent model selector, wherein the equivalent model selector pre-stores an RL equivalent model, a π-type equivalent model, and a T-type equivalent model.

[0108] The equivalent model type and parameter output unit is used for the equivalent model selector to output N equivalent model types and N equivalent model parameters corresponding to the N-segment circuit according to the physical structure parameters and the electrical connection characteristics.

[0109] Furthermore, the execution step of the equivalent model type and parameter output unit further includes: defining equivalent model parameters of each equivalent model in the equivalent model selector; wherein the equivalent model parameters of the RL equivalent model include series resistance and series inductance, The equivalent model parameters of the T-type equivalent model include series impedance and capacitance between both ends to ground, and the equivalent model parameters of the T-type equivalent model include series impedance between both ends and susceptance between the midpoint and ground.

[0110] In some embodiments, the model combination module 13 includes: The abnormal event sample signal acquisition unit is used to acquire the abnormal event sample signal.

[0111] The equivalent error fitting and index output unit is used to perform equivalent error fitting on the N intra-segment equivalent circuit models according to the abnormal event sample signal, and output N equivalent error indices.

[0112] The equivalent optimization and optimization model output unit is used to perform equivalent optimization on the N intra-segment equivalent circuit models with the goal of minimizing the N equivalent error indicators, and output the optimized N intra-segment equivalent circuit models.

[0113] The full-line combination equivalent model construction unit is used to connect the optimized N segment equivalent circuit models to construct the full-line combination equivalent model.

[0114] In some embodiments, the analysis and positioning reminder module 15 includes: The equivalent training data set construction unit is used to establish an equivalent training data set of the full-line combination equivalent model, including M groups of equivalent training data sets in a healthy state and M groups of equivalent training data sets under the abnormal event sample signal.

[0115] The abnormality monitoring model training and abnormality indicator acquisition unit is used to perform model training based on the equivalent training data set and the label representing the degree of abnormality, output the abnormality monitoring model, and obtain N abnormality indicators corresponding to the N sections of circuit based on the abnormality monitoring model.

[0116] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment one are also applicable to the online circuit monitoring system for transmission lines described in embodiment two. For the sake of brevity of the specification, they will not be further elaborated here.

[0117] Example 3, as Figure 3 The schematic structural diagram of an exemplary electronic device provided for the present invention shows a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present invention. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 3 As shown, the electronic device includes a processor 31, a memory 32, an input device 33 and an output device 34; the number of processors 31 in the electronic device can be one or more. Figure 3 Taking a processor 31 as an example, the processor 31, memory 32, input device 33 and output device 34 in the electronic device can be connected through a bus or other means. Figure 3 The bus connection is taken as an example.

[0118] Memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the online circuit monitoring method for power transmission lines in the embodiments of the present invention. Processor 31 executes the software programs, instructions, and modules stored in memory 32 to perform various computer functions and data processing, thereby implementing the online circuit monitoring method for power transmission lines.

[0119] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the embodiments mentioned above. It should be understood that those skilled in the art can still modify the technical solutions described in the above embodiments or replace some of the technical features therein with equivalents; and such modifications or replacements do not deviate from the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention and are all included in the scope of protection of the present invention.

Claims

1. A method for online monitoring of a circuit of a transmission line, characterized in that: include: Acquire target long-distance transmission lines; Dividing the long-distance transmission line into N circuit segments according to environmental heterogeneity and electrical response differences, constructing an intra-segment equivalent circuit model corresponding to each of the N circuit segments, and outputting N intra-segment equivalent circuit models; Combining the N intra-segment equivalent circuit models to construct a full-line combined equivalent model; Collect circuit operation data for each of the N circuit segments, and output corresponding N groups of distributed monitoring data sets; The full-line combination equivalent model is called to perform an anomaly analysis on the N groups of distributed monitoring data sets, obtain N anomaly indicators corresponding to the N sections of circuits, and locate and remind abnormal circuits according to the N anomaly indicators.

2. The method for online monitoring of a circuit of a power transmission line according to claim 1, wherein: The long-distance transmission line is divided into N sections according to environmental heterogeneity and electrical response differences, including: Initializing the long-distance power transmission line into equally spaced segments, and outputting M segments of circuits; Collecting M groups of line environment information and M groups of electrical operation response data corresponding to the M sections of circuits; Calculating an environmental heterogeneity score and an electrical response difference score for each of the M circuit segments based on the M groups of line environment information and the M groups of electrical operation response data; Adaptively segmenting the M-segment circuit using the environmental heterogeneity score and the electrical response difference score as variables, and outputting a segmentation result, wherein the segmentation result is an N-segment circuit.

3. The method for online monitoring of a circuit of a power transmission line according to claim 2, wherein: Adaptively segmenting the M-segment circuit using the environmental heterogeneity score and the electrical response difference score as variables, and outputting a segmentation result, including: Constructing a fusion scoring function to calculate M fusion scoring indicators corresponding to the M circuit segments according to the environmental heterogeneity score and the electrical response difference score; Traversing the M fusion score indicators to calculate the fusion score indicator differences of adjacent segments, and outputting M-1 fusion score indicator differences; Setting a segment fusion score threshold, and outputting circuits whose M-1 fusion score indicator differences are greater than the segment fusion score threshold as candidate segment boundaries; Adaptively cluster the candidate segment boundaries and output segment division results.

4. The method for online monitoring of a circuit of a power transmission line according to claim 1, wherein: Constructing an intra-segment equivalent circuit model corresponding to each of the N segments of the circuit, and outputting N intra-segment equivalent circuit models, including: Collecting physical structure parameters and electrical connection characteristics corresponding to the N segments of the circuit; Calculating equivalent model parameters of each circuit segment according to the physical structure parameters and the electrical connection characteristics, and outputting N equivalent model parameters; Equivalent circuit model processing is performed on the N circuit segments according to the N equivalent model parameters, and N intra-segment equivalent circuit models are output.

5. The method for online monitoring of a circuit of a power transmission line according to claim 4, wherein: Before calculating the equivalent model parameters of each circuit, it also includes: Get an equivalent model selector, the equivalent model selector pre-stores RL equivalent models, Type equivalent model and T-type equivalent model; The equivalent model selector outputs N equivalent model types and N equivalent model parameters corresponding to the N circuit segments according to the physical structure parameters and the electrical connection characteristics.

6. The method for online monitoring of a circuit of a power transmission line according to claim 5, wherein: defining equivalent model parameters of each equivalent model in the equivalent model selector; The equivalent model parameters of the RL equivalent model include series resistance and series inductance. The equivalent model parameters of the T-type equivalent model include series impedance and capacitance between both ends to ground, and the equivalent model parameters of the T-type equivalent model include series impedance between both ends and susceptance between the midpoint and ground.

7. The method for online monitoring of a circuit of a power transmission line according to claim 1, wherein: Combining the N intra-segment equivalent circuit models to construct a full-line combined equivalent model further includes: Obtaining abnormal event sample signals; Performing equivalent error fitting on the N intra-segment equivalent circuit models according to the abnormal event sample signal, and outputting N equivalent error indicators; performing equivalent optimization on the N intra-segment equivalent circuit models with the goal of minimizing the N equivalent error indicators, and outputting the optimized N intra-segment equivalent circuit models; The N equivalent circuit models within the optimized segments are connected to construct the equivalent model of the entire line combination.

8. The method for online monitoring of a circuit of a power transmission line according to claim 7, wherein: Calling the full-line combination equivalent model to perform anomaly analysis on the N groups of distributed monitoring data sets to obtain N anomaly indicators corresponding to the N sections of circuits, including: Establishing an equivalent training data set for the full-line combination equivalent model, including M groups of equivalent training data sets in a healthy state and M groups of equivalent training data sets under the abnormal event sample signal; Model training is performed based on the equivalent training data set and labels representing the degree of abnormality, an abnormality monitoring model is output, and N abnormality indicators corresponding to the N sections of circuits are obtained based on the abnormality monitoring model.

9. A circuit online monitoring system for a transmission line, characterized in that: The method for online monitoring of a circuit for a power transmission line according to any one of claims 1 to 8 comprises: A target transmission line acquisition module is used to acquire a target long-distance transmission line; an equivalent circuit model construction module, configured to divide the long-distance transmission line into N circuit segments according to environmental heterogeneity and electrical response differences, construct an intra-segment equivalent circuit model corresponding to each of the N circuit segments, and output the N intra-segment equivalent circuit models; A model combination module, used for combining the N intra-segment equivalent circuit models to construct a full-circuit combination equivalent model; A monitoring and acquisition module, configured to collect circuit operation data for each of the N circuit segments and output corresponding N sets of distributed monitoring data sets; The analysis and positioning reminder module is used to call the full-line combination equivalent model to perform abnormal analysis on the N groups of distributed monitoring data sets, obtain N abnormal indicators corresponding to the N sections of circuits, and locate and remind abnormal circuits according to the N abnormal indicators.

10. An electronic device, characterized in that: The electronic device comprises: a memory for storing executable instructions; The processor is configured to implement the method for online monitoring of a circuit for a transmission line according to any one of claims 1 to 8 when executing the executable instructions stored in the memory.

Images