Ground fault uploading method, device and equipment of power distribution network and medium

Abstract

The application discloses a power distribution network ground fault uploading method, device, equipment and medium. The method comprises the following steps: acquiring actual operation condition parameters of the power distribution network, generating actual condition combinations based on the correlation between the actual operation condition parameters, and querying matched ground fault characteristic data in a pre-constructed theoretical change information library based on the actual condition combinations; determining an activation strategy of a detection device based on the ground fault characteristic data, activating the detection device based on the activation strategy, and collecting actual ground fault characteristic data of the power distribution network; performing multi-feature fusion calculation on the actual ground fault characteristic data to obtain a ground fault recognition result; and determining a ground fault data uploading rule corresponding to the power distribution network according to the ground fault recognition result and the actual condition combinations, and uploading the actual ground fault characteristic data and the ground fault recognition result. The ground fault recognition accuracy is improved, and dynamic response and adaptive uploading of the whole fault detection process are realized.

Description

Technical Field

[0001] This invention relates to the technical field of ground fault detection and data transmission in power distribution networks, and particularly to methods, devices, equipment, and media for uploading ground fault data in power distribution networks. Background Technology

[0002] Multi-condition dynamic response grounding faults refer to grounding faults in power systems, industrial equipment, or electrical installations caused by dynamic changes in operating conditions (such as load fluctuations, operating mode switching, changes in environmental conditions, etc.), which lead to a decrease in the insulation performance of equipment or lines and changes in grounding circuit parameters, thereby causing grounding faults. The manifestation and development process of the fault will exhibit dynamic characteristics as the operating conditions change.

[0003] Existing power distribution network grounding fault detection technologies have the following problems: Relying on a single operating condition model results in poor adaptability. Complex system operating conditions, such as load fluctuations, arc grounding, and the activation or deactivation of compensation devices, can lead to drastic changes in zero-sequence quantities, which can easily cause misjudgments or missed judgments.

[0004] The data acquisition equipment lacks dynamic response capabilities. It typically employs a fixed sampling rate and a fixed upload strategy, making it unable to automatically adjust for different operating conditions.

[0005] There is a lack of comprehensive utilization of multidimensional grounding characteristic data. For example, nonlinear harmonics, waveform distortion, and HHT (Hilbert-Huang Transform) characteristics cannot be effectively integrated. Summary of the Invention

[0006] This invention provides a method, apparatus, equipment, and medium for uploading ground fault data in a power distribution network, so as to achieve dynamic and adaptive ground fault detection and data uploading under multiple operating conditions in the power distribution network.

[0007] According to one aspect of the present invention, a method for transmitting ground faults in a distribution network is provided, the method comprising: Obtain the actual operating condition parameters of the distribution network, generate actual operating condition combinations based on the correlation between the actual operating condition parameters, and query matching ground fault characteristic data in a pre-built theoretical change information database based on the actual operating condition combinations. Based on the ground fault characteristic data, an activation strategy for the detection equipment is determined, and the detection equipment is activated based on the activation strategy. The actual ground fault characteristic data of the distribution network is then collected through the activated detection equipment. Perform multi-feature fusion calculation on the actual ground fault feature data to obtain the ground fault identification result; Based on the ground fault identification result and the actual operating condition combination, a ground fault data upload rule corresponding to the distribution network is determined, and the actual ground fault characteristic data and the ground fault identification result are uploaded based on the data upload rule.

[0008] According to another aspect of the present invention, a ground fault uploading device for a distribution network is provided, characterized in that it comprises: The parameter acquisition module is used to acquire the actual operating condition parameters of the distribution network, generate actual operating condition combinations based on the correlation between the actual operating condition parameters, and query matching ground fault feature data in a pre-built theoretical change information database based on the actual operating condition combinations. The detection equipment activation module is used to determine the activation strategy of the detection equipment based on the ground fault feature data, activate the detection equipment based on the activation strategy, and collect the actual ground fault feature data of the distribution network through the activated detection equipment. The fault identification module is used to perform multi-feature fusion calculation on the actual ground fault feature data to obtain the ground fault identification result; The upload module is used to determine the ground fault data upload rules corresponding to the distribution network based on the ground fault identification results and the actual operating condition combination, and upload the actual ground fault feature data and the ground fault identification results based on the data upload rules.

[0009] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and memory that is communicatively connected to at least one processor; The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to execute the ground fault uploading method for a distribution network according to any embodiment of the present invention.

[0010] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the ground fault uploading method for a distribution network according to any embodiment of the present invention.

[0011] The technical solution of this invention involves acquiring actual operating condition parameters of the distribution network, generating actual operating condition combinations based on the correlation between these parameters, querying matching ground fault feature data in a pre-built theoretical change information database based on these actual operating condition combinations, determining an activation strategy for detection equipment based on the ground fault feature data, activating the detection equipment based on the activation strategy, and collecting actual ground fault feature data of the distribution network through the activated detection equipment, performing multi-feature fusion calculation on the actual ground fault feature data to obtain ground fault identification results, determining ground fault data upload rules corresponding to the distribution network based on the ground fault identification results and the actual operating condition combinations, and uploading the actual ground fault feature data and the ground fault identification results based on the data upload rules. This solves the technical problems of existing technologies, such as poor adaptability due to reliance on a single operating condition model, lack of dynamic response capability of acquisition equipment, failure to effectively integrate multi-dimensional fault feature data leading to false positives and false negatives, wasted computing power and bandwidth, and low identification accuracy. It achieves the technical effects of adapting to the dynamic changes of multiple operating conditions in the distribution network, significantly reducing the false positive and false negative rates of faults, activating equipment on demand to save computing power and bandwidth, improving ground fault identification accuracy, and realizing dynamic response and adaptive uploading throughout the fault detection process.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 A flowchart illustrating a method for uploading grounding faults in a power distribution network, provided as an embodiment of the present invention; Figure 2 A flowchart illustrating another method for uploading grounding faults in a power distribution network, provided by an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a grounding fault uploading device for a power distribution network provided in an embodiment of the present invention; Figure 4 A schematic diagram of the structure of an electronic device for implementing a ground fault uploading method for a power distribution network according to an embodiment of the present invention. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0017] Figure 1 This is a flowchart illustrating a ground fault uploading method for a distribution network according to an embodiment of the present invention. This embodiment is applicable to ground fault detection and adaptive uploading in distribution networks. The method can be executed by a ground fault uploading device for the distribution network, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method specifically includes the following steps: S110. Obtain the actual operating condition parameters of the distribution network, generate an actual operating condition combination based on the correlation between the actual operating condition parameters, and query the matching ground fault characteristic data in the pre-constructed theoretical change information database based on the actual operating condition combination.

[0018] Among them, actual operating condition parameters can be understood as various parameters reflecting the working status of the distribution network during real-time operation; actual operating condition combinations can be understood as operating status combinations formed by integrating the correlation relationships of actual operating condition parameters of the distribution network; theoretical change information database can be understood as a database that pre-stores the mapping relationship between different operating condition combinations of the distribution network and corresponding ground fault characteristic data; ground fault characteristic data can be understood as various characteristic data that can reflect the ground fault status of the distribution network.

[0019] Specifically, the actual operating condition parameters reflecting the current operating status of the power distribution network are collected in real time through the power distribution network monitoring link. Then, based on the inherent correlation between the parameters, the parameters are integrated to generate the corresponding actual operating condition combination. Using the actual operating condition combination as the retrieval basis, the ground fault characteristic data that is suitable for the actual operating condition combination is searched and matched in the pre-built theoretical change information database that stores the correspondence between the operating condition combination and the ground fault characteristic data, so as to provide data basis for subsequent equipment control.

[0020] Optionally, the actual operating condition parameters include at least one of the following: system wiring mode parameters, load fluctuation curve parameters, compensation device status parameters, distributed capacitance imbalance parameters, fault type, and disturbance parameters.

[0021] Among them, the system wiring mode parameter can be understood as a parameter reflecting the connection mode of the distribution network system lines; the load fluctuation curve parameter can be understood as a parameter reflecting the change law of the distribution network load over time; the compensation device status parameter can be understood as a parameter reflecting the operating status of the compensation device in the distribution network; the distributed capacitance imbalance parameter can be understood as a parameter reflecting the degree of distributed capacitance imbalance in the distribution network; and the fault type and disturbance parameter can be understood as a parameter reflecting the types of faults and various disturbances that may occur in the distribution network.

[0022] S120. Determine the activation strategy of the detection device based on the ground fault characteristic data, activate the detection device based on the activation strategy, and collect the actual ground fault characteristic data of the distribution network through the activated detection device.

[0023] The activation strategy can be understood as the rules that guide the start-up, shutdown, and mode adjustment of each functional module of the detection equipment; the detection equipment can be understood as various devices used to collect data related to grounding faults in the power distribution network; and the actual grounding fault characteristic data can be understood as the grounding fault characteristic data collected by the detection equipment based on the actual operating state of the power distribution network.

[0024] Specifically, based on the ground fault characteristic data matched from the theoretical change information database, and combined with the needs of data acquisition and analysis, activation rules, i.e. activation strategies, are formulated for each functional module of the detection equipment. The corresponding modules of the detection equipment are started and stopped according to the strategy to make the detection equipment in an adapted working state. Then, the activated detection equipment is used to collect the relevant characteristic data of the current ground fault in the distribution network on the field to obtain the actual ground fault characteristic data.

[0025] Optionally, the activation strategy includes at least one of the following: high sampling rate mode start / stop determination result, harmonic submodule start / stop determination result, Hilbert-Huang transform calculation module start / stop determination result, noise reduction process execution determination result, and event-level upload trigger determination result; the step of determining the activation strategy of the detection device based on the ground fault characteristic data includes: integrating at least one determination result into a device activation matrix, and determining the activation strategy of the detection device based on the device activation matrix.

[0026] Among them, the high sampling rate mode start / stop determination result can be understood as the conclusion on whether to enable the high sampling rate mode of the detection equipment; the harmonic submodule start / stop determination result can be understood as the conclusion on whether to start the harmonic submodule of the detection equipment; the Hilbert-Huang transform calculation module start / stop determination result can be understood as the conclusion on whether to activate the Hilbert-Huang transform calculation module of the detection equipment; the noise reduction process execution determination result can be understood as the conclusion on whether to execute the noise reduction process on the detection data; the event-level upload trigger determination result can be understood as the conclusion on whether to trigger the event-level data upload; and the equipment activation matrix can be understood as the matrix form of the basis for integrating the start / stop and process execution determination results of various detection equipment modules.

[0027] Specifically, the start / stop / execution judgment results of at least one module or process, such as the high sampling rate mode and harmonic sub-module of the detection equipment, are first determined. Then, these judgment results are integrated into a matrix-form device activation matrix. Finally, this device activation matrix is ​​used as the activation strategy of the detection equipment, making the formulation of the activation strategy more systematic and operable.

[0028] S130. Perform multi-feature fusion calculation on the actual ground fault feature data to obtain the ground fault identification result.

[0029] Among them, multi-feature fusion calculation can be understood as a calculation method that integrates and analyzes multiple feature data reflecting ground faults; ground fault identification results can be understood as relevant judgment information about ground faults in the distribution network obtained by analyzing actual ground fault feature data.

[0030] Specifically, for the actual ground fault feature data collected by the detection equipment, fault features of different dimensions are extracted and integrated for analysis. The fused feature data is processed by a preset calculation model. Based on the calculation results, judgment information that can clearly reflect the specific situation of the ground fault in the distribution network is obtained, namely the ground fault identification result.

[0031] Optionally, the step of performing multi-feature fusion calculation on the actual ground fault feature data to obtain the ground fault identification result includes: extracting zero-sequence amplitude phasor features, harmonic energy features, time-frequency energy cluster features, principal component dimensionality reduction features, and short-time energy mutation features from the actual ground fault feature data; integrating all extracted features according to a preset fusion rule to obtain fused feature data; inputting the fused feature data into a preset fault identification model, and outputting the ground fault identification result through model calculation; wherein, the ground fault identification result includes fault type, fault phase, and fault confidence level.

[0032] Among them, zero-sequence amplitude phasor characteristics can be understood as reflecting the characteristics of zero-sequence current, voltage amplitude, and phase of the distribution network; harmonic energy characteristics can be understood as reflecting the characteristics of the magnitude of harmonic energy in the distribution network; time-frequency energy cluster characteristics can be understood as reflecting the characteristics of energy distribution of the fault signal in the time and frequency domains of the distribution network; principal component dimensionality reduction characteristics can be understood as the characteristics obtained after performing principal component analysis to reduce the dimensionality of the fault feature data of the distribution network; short-time energy mutation characteristics can be understood as reflecting the characteristics of sudden changes in the short-time energy of the fault signal of the distribution network; preset fusion rules can be understood as pre-set rules for integrating various fault feature data, which can be pre-set based on experience, and this embodiment does not impose specific restrictions on them; fused feature data can be understood as the data obtained after integrating multiple fault feature data according to preset rules; preset fault identification model can be understood as a pre-trained model for analyzing fused feature data and determining ground faults; fault type can be understood as the specific type of ground fault in the distribution network; fault phase can be understood as the line phase in the distribution network where a ground fault occurs; fault reliability level can be understood as the rating of the accuracy of the ground fault identification result.

[0033] Specifically, five types of features, including zero-sequence amplitude and phasor, and harmonic energy, are extracted from actual ground fault feature data. These feature data are then integrated into fused feature data according to pre-set rules. Finally, the fused feature data is input into a pre-trained fault identification model. Through the model's calculation and processing, a ground fault identification result containing fault type, fault phase, and fault confidence level is output, thereby improving the accuracy of fault identification.

[0034] Preferably, the preset fusion rules are multi-dimensional feature integration criteria pre-defined based on the characteristic data of distribution network grounding faults. The core rules include three specific categories: feature normalization, feature weight allocation, and feature dimension integration, adapting to the attribute differences of different features such as zero-sequence amplitude and phasor, and harmonic energy. First, each feature data is normalized to eliminate dimensional differences between different features such as zero-sequence quantities and time-frequency energy, ensuring data comparability. Then, weights are allocated according to the contribution of each feature to grounding fault identification; for example, higher weights are assigned to HHT time-frequency energy cluster features and zero-sequence amplitude and phasor features to enhance the identification impact of core features. Finally, through feature splicing or weighted summation, the normalized and weighted multi-dimensional features are integrated into unified-dimensional fused feature data, preparing for subsequent input into the fault identification model. All rules are calibrated based on historical fault data and operating condition characteristics of the distribution network and can be fine-tuned according to actual grid operation conditions.

[0035] Specifically, the preset fault identification model is an algorithmic model trained based on historical feature data of distribution network grounding faults, used to determine the specific circumstances of grounding faults. It supports two implementation forms: logical criterion model and machine learning model. The input of the model is the fused feature data integrated according to preset fusion rules; the output is a clear grounding fault identification result, including three core pieces of information: fault type, fault phase, and fault confidence level. The model is trained using grounding fault feature data corresponding to all operating conditions of the distribution network as the training set, with the training set and test set divided in a 7:3 ratio. The model is iteratively trained and validated, and the model parameters are continuously optimized through error feedback until the fault identification accuracy and confidence level determination accuracy of the model reach the preset threshold.

[0036] Specifically, ground fault identification is performed through multi-feature fusion using either a logical criterion model or a machine learning model, outputting the fault type, fault phase, and fault confidence level. If the model structure is a logical criterion model, it consists of multiple ground fault judgment logic formulas and threshold conditions, outputting the identification result through comparison of feature data with thresholds and logical formula calculations. If it is a machine learning model, it employs a lightweight classification network structure, including a feature input layer, a feature extraction layer, and a classification output layer, which can efficiently process fused feature data and complete fault classification and confidence rating. Both types of models are compatible with the computing power of detection equipment in the distribution network field, enabling rapid fault identification.

[0037] Preferably, the logic criterion model is based on the electrical characteristics and fault judgment criteria of distribution network grounding faults. It consists of multiple sets of grounding fault judgment logic formulas and multi-level characteristic threshold conditions. Each formula and threshold is calibrated based on distribution network industry standards, historical fault data, and grounding fault characteristic patterns under full operating conditions. The model is divided into independent criterion modules according to fault characteristic types, such as zero-sequence quantity criterion units, harmonic energy criterion units, and time-frequency energy criterion units. Each module presets judgment thresholds for corresponding characteristics (such as zero-sequence current mutation threshold, harmonic energy increment threshold, HHT time-frequency energy migration threshold, etc.), and simultaneously sets logical operation relationships (AND / OR / NOT) between modules. During runtime, the fused feature data is input into the corresponding criterion modules according to type. First, the fault judgment result of a single module is obtained by comparing the feature data with the preset threshold (such as exceeding the standard / not exceeding the standard, fault / non-fault). Then, the results of each module are comprehensively calculated by the preset logical formula, and finally the fault type and fault phase are output. The fault confidence level is calculated and output based on the consistency of the judgment results of each module. The entire model has no complex iterative calculations, low computing power consumption, and is suitable for the real-time computing needs of field detection equipment.

[0038] Preferably, the machine learning model adopts a lightweight classification network structure adapted to the computing power of power distribution network field detection equipment. The overall architecture is a three-layer serial structure: a feature input layer, a feature extraction layer, and a classification output layer. The feature input layer is a standardized data interface that receives unified-dimensional fused feature data processed according to preset fusion rules, performs data format conversion and normalization secondary verification to ensure the standardization of the input data. The feature extraction layer contains multiple lightweight convolutional kernels and pooling layers, specifically extracting core features such as zero-sequence quantities, harmonic energy, and HHT time-frequency energy from the fused feature data. It filters out feature factors strongly correlated with grounding faults, eliminates redundant data, and reduces subsequent computational load. The classification output layer uses a softmax classifier to map the extracted core feature factors to preset fault type and fault phase classification intervals. Simultaneously, it outputs the confidence level of each classification result through a probability calculation module, ultimately integrating them into a recognition result containing fault type, fault phase, and fault confidence level. The model uses ground fault feature data of the full range of operating conditions of the distribution network as the training set. After multiple iterations of training and parameter optimization, it is finalized and can adapt to the dynamic changes of multiple operating conditions of the distribution network, with higher accuracy in identifying complex fault features.

[0039] S140. Determine the ground fault data upload rules corresponding to the distribution network based on the ground fault identification results and the actual operating condition combination, and upload the actual ground fault feature data and the ground fault identification results based on the data upload rules.

[0040] Among them, the rules for uploading ground fault data can be understood as rules that guide the uploading method and content of data related to ground faults in the distribution network; ground fault data can be understood as data related to distribution network faults that includes actual ground fault characteristic data and ground fault identification results.

[0041] Specifically, by combining the ground fault identification results obtained through multi-feature fusion calculation with the actual operating conditions of the distribution network at present, and taking into account the fault situation and operating status, ground fault data upload rules adapted to the current situation of the distribution network are formulated. Then, in strict accordance with these rules, the collected actual ground fault feature data and the ground fault identification results obtained from the analysis are uploaded to the designated backend to complete the reporting of fault data.

[0042] Optionally, determining the ground fault data upload rule corresponding to the distribution network based on the ground fault identification result and the actual operating condition combination includes: determining the complexity level of the actual operating condition combination based on the types, number, and fluctuation amplitude of the actual operating condition parameters included in the actual operating condition combination; retrieving matching ground fault data upload rules from a pre-built upload rule library based on the fault confidence level in the ground fault identification result and the complexity level; wherein the upload rule library pre-stores the correspondence between the fault confidence level, the complexity level of the operating condition combination, and the upload rules.

[0043] Among them, the complexity level can be understood as a level that reflects the complexity of the operating state, based on the parameter characteristics of the actual working condition combination; the upload rule base can be understood as a database that pre-stores the correspondence between the fault credibility level, the working condition combination complexity level and the upload rule.

[0044] Specifically, based on the types, number, and fluctuation amplitude of actual operating parameters included in the actual operating condition combination, the complexity of the operating state of the actual operating condition combination is determined and classified into complexity levels. Then, using the fault confidence level in the ground fault identification results and the classified complexity level as dual retrieval criteria, the matching ground fault data upload rules are searched and retrieved from the pre-built upload rule library that stores the correspondence between the three, so that the formulation of upload rules is more in line with the actual operating conditions.

[0045] Specifically, the complexity of operating condition combinations is divided into three levels: low, medium, and high. The core basis for level determination is two dimensions: the number of types of actual operating condition parameters included in the actual operating condition combination and the fluctuation amplitude of each parameter. First, the two dimensions are quantified and scored separately, and then the level is determined based on the comprehensive score. For example, the parameter number scoring is as follows: ≤2 types of actual operating condition parameters, 1 point; 3-4 types of actual operating condition parameters, 2 points; ≥5 types of actual operating condition parameters, 3 points. The parameter fluctuation amplitude scoring is as follows: all parameter fluctuation amplitudes ≤10% (normal stable fluctuation range), 1 point; 10% < some parameter fluctuation amplitudes ≤30%, 2 points; some parameter fluctuation amplitudes >30% (large fluctuations) or there are sudden changes in operating conditions such as compensation device activation / deactivation or wiring mode switching, 3 points. The comprehensive level is determined by adding the two scores together: a total score of 2 points is low level; a total score of 3-4 points is medium level; and a total score of 5-6 points is high level.

[0046] Specifically, the reliability level of distribution network grounding faults is divided into three levels: low, medium, and high. This is based on a comprehensive calculation of multi-feature fusion identification matching degree (40% weight), feature data and fault template fit degree (30% weight), and model judgment confidence degree (30% weight). The logical criteria and machine learning model judgment standards are unified, and the level is determined by a total score from 0 to 100. Matching degree refers to the matching percentage of the five core fault features; fit degree refers to the similarity between actual data and theoretical templates; and confidence degree is the consistency rate of judgment modules in the logical criterion model and the fault judgment probability in the machine learning model. The better the performance of these three indicators, the higher the corresponding score. For example, a total score < 60 indicates low reliability, with low reference value; 60 ≤ total score < 85 indicates medium reliability, with some reference value; and a total score ≥ 85 indicates high reliability, with high accuracy. This level, along with the complexity level of the working condition combination, serves as the retrieval basis for the upload rule base and determines the data upload priority. Low confidence level only transmits feature-extracted data, medium confidence level matches the regular upload rules, and high confidence level prioritizes the use of advanced upload rules such as real-time and full waveform.

[0047] Optionally, uploading the actual ground fault feature data and the ground fault identification result based on the data upload rules includes: encapsulating the actual ground fault feature data and the ground fault identification result based on the ground fault data upload rules to generate a ground fault upload data packet; and uploading the ground fault upload data packet to a preset background monitoring system through a power distribution network communication link.

[0048] Among them, the ground fault upload data packet can be understood as a data packet formed by encapsulating the actual ground fault characteristic data and the ground fault identification result; the distribution network communication link can be understood as a communication channel used to transmit distribution network fault data; and the background monitoring system can be understood as a background system used to receive, monitor and analyze distribution network fault data.

[0049] Specifically, according to the established rules for uploading ground fault data, the collected actual ground fault characteristic data and the analyzed ground fault identification results are encapsulated and processed to generate a ground fault upload data packet with a standardized structure. Then, the data packet is uploaded to a pre-set background monitoring system for monitoring the operation status of the distribution network through a dedicated communication channel of the distribution network, ensuring that the fault data is reported safely and in a standardized manner.

[0050] The technical solution of this invention involves acquiring actual operating condition parameters of the distribution network, generating actual operating condition combinations based on the correlation between these parameters, querying matching ground fault feature data in a pre-built theoretical change information database based on these actual operating condition combinations, determining an activation strategy for detection equipment based on the ground fault feature data, activating the detection equipment based on the activation strategy, and collecting actual ground fault feature data of the distribution network through the activated detection equipment, performing multi-feature fusion calculation on the actual ground fault feature data to obtain ground fault identification results, determining ground fault data upload rules corresponding to the distribution network based on the ground fault identification results and the actual operating condition combinations, and uploading the actual ground fault feature data and the ground fault identification results based on the data upload rules. This solves the technical problems of existing technologies, such as poor adaptability due to reliance on a single operating condition model, lack of dynamic response capability of acquisition equipment, failure to effectively integrate multi-dimensional fault feature data leading to false positives and false negatives, wasted computing power and bandwidth, and low identification accuracy. It achieves the technical effects of adapting to the dynamic changes of multiple operating conditions in the distribution network, significantly reducing the false positive and false negative rates of faults, activating equipment on demand to save computing power and bandwidth, improving ground fault identification accuracy, and realizing dynamic response and adaptive uploading throughout the fault detection process.

[0051] Figure 2 This is a flowchart of another method for uploading ground fault information in a distribution network, provided as an embodiment of the present invention. Based on the above embodiments, this embodiment further refines how to construct a theoretical change information database. For specific implementation details, please refer to the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here. Figure 2 As shown, the method specifically includes the following steps: S101. Collect all operating condition parameters of the distribution network and generate multiple full operating condition combinations based on the correlation between the parameters in the full operating condition parameters.

[0052] Among them, the full range of operating condition parameters can be understood as the various operating condition parameters under all possible operating states of the distribution network; the full range of operating condition combinations can be understood as all possible combinations of operating states formed by integrating the correlation relationships of the full range of operating condition parameters.

[0053] Specifically, all operating parameters that reflect the working status of the distribution network under various operating conditions are collected, namely, full-scale operating parameters. Then, the inherent correlation between the various full-scale operating parameters is analyzed. Based on the correlation, the parameters are integrated in different ways to generate all possible combinations of operating states of the distribution network, namely, multiple full-scale operating condition combinations, covering all operating scenarios of the distribution network.

[0054] S102. Match a corresponding ground fault acquisition strategy for each full-condition combination. For each full-condition combination, determine the ground fault characteristic data corresponding to the full-condition combination based on the acquisition strategy.

[0055] Among them, the ground fault acquisition strategy can be understood as the rules formulated for different combinations of operating conditions to collect ground fault characteristic data.

[0056] Specifically, based on the operating characteristics and fault detection requirements of different full-condition combinations of the distribution network, a suitable ground fault data acquisition rule, i.e., a ground fault acquisition strategy, is matched for each full-condition combination. Then, according to the acquisition strategy matched for each full-condition combination, the acquisition type, calculation method, etc. of the ground fault characteristic data corresponding to each full-condition combination are determined, and the fault characteristic data corresponding to each condition combination is clarified.

[0057] S103. Establish mapping relationships between the full range of operating conditions and their corresponding ground fault characteristic data, and construct the theoretical change information database based on multiple sets of the mapping relationships.

[0058] The mapping relationship can be understood as a one-to-one correspondence between the full range of operating conditions and the corresponding ground fault characteristic data.

[0059] Specifically, each full-scale operating condition combination is associated with its corresponding ground fault characteristic data determined by the acquisition strategy to establish a one-to-one mapping relationship. Then, the mapping relationship between all full-scale operating condition combinations and ground fault characteristic data is integrated and stored to build a theoretical change information database that can provide a basis for matching fault characteristic data with actual operating condition combinations, thereby realizing a systematic correspondence between operating condition combinations and fault characteristic data.

[0060] The technical solution of this invention, by pre-collecting all operating condition parameters of the distribution network and generating all operating condition combinations, matching collection strategies for each combination and determining corresponding ground fault characteristic data, and then establishing a mapping relationship to construct a theoretical change information database, not only provides systematic and comprehensive preset data support for quickly matching fault characteristic data for actual operating condition combinations, but also allows the formulation of subsequent detection equipment activation strategies to be more in line with different operating conditions of the distribution network, effectively improving the pertinence and adaptability of distribution network ground fault detection, and laying a solid data foundation for the efficient implementation of the entire ground fault uploading method.

[0061] Figure 3 This is a schematic diagram of a ground fault uploading device for a power distribution network, provided as an embodiment of the present invention. Figure 3 As shown, the device includes: a parameter acquisition module 310, a detection equipment activation module 320, a fault identification module 330, and an upload module 340.

[0062] The system includes the following modules: a parameter acquisition module 310, which acquires actual operating condition parameters of the distribution network, generates actual operating condition combinations based on the correlation between these parameters, and queries a pre-built theoretical change information database for matching ground fault feature data based on these actual operating condition combinations; a detection device activation module 320, which determines an activation strategy for the detection device based on the ground fault feature data, activates the detection device based on the activation strategy, and collects actual ground fault feature data of the distribution network through the activated detection device; a fault identification module 330, which performs multi-feature fusion calculation on the actual ground fault feature data to obtain a ground fault identification result; and an upload module 340, which determines a ground fault data upload rule corresponding to the distribution network based on the ground fault identification result and the actual operating condition combination, and uploads the actual ground fault feature data and the ground fault identification result based on the data upload rule.

[0063] The technical solution of this invention involves acquiring actual operating condition parameters of the distribution network, generating actual operating condition combinations based on the correlation between these parameters, querying matching ground fault feature data in a pre-built theoretical change information database based on these actual operating condition combinations, determining an activation strategy for detection equipment based on the ground fault feature data, activating the detection equipment based on the activation strategy, and collecting actual ground fault feature data of the distribution network through the activated detection equipment, performing multi-feature fusion calculation on the actual ground fault feature data to obtain ground fault identification results, determining ground fault data upload rules corresponding to the distribution network based on the ground fault identification results and the actual operating condition combinations, and uploading the actual ground fault feature data and the ground fault identification results based on the data upload rules. This solves the technical problems of existing technologies, such as poor adaptability due to reliance on a single operating condition model, lack of dynamic response capability of acquisition equipment, failure to effectively integrate multi-dimensional fault feature data leading to false positives and false negatives, wasted computing power and bandwidth, and low identification accuracy. It achieves the technical effects of adapting to the dynamic changes of multiple operating conditions in the distribution network, significantly reducing the false positive and false negative rates of faults, activating equipment on demand to save computing power and bandwidth, improving ground fault identification accuracy, and realizing dynamic response and adaptive uploading throughout the fault detection process.

[0064] Optionally, the actual operating condition parameters include at least one of the following: system wiring mode parameters, load fluctuation curve parameters, compensation device status parameters, distributed capacitance imbalance parameters, fault type, and disturbance parameters.

[0065] Optionally, the device further includes: The full combination generation module is used to collect full operating condition parameters of the distribution network before querying matching ground fault feature data in the pre-built theoretical change information database based on the actual operating condition combination, and to generate multiple full operating condition combinations based on the correlation between the parameters in the full operating condition parameters. The fault feature determination module is used to match a corresponding ground fault acquisition strategy for each full-condition combination, and for each full-condition combination, determine the ground fault feature data corresponding to the full-condition combination based on the acquisition strategy. The information database construction module is used to establish mapping relationships between the full range of operating conditions and their corresponding ground fault characteristic data, and to construct the theoretical change information database based on multiple sets of such mapping relationships.

[0066] Optionally, the activation strategy includes at least one of the following: high sampling rate mode start / stop determination result, harmonic submodule start / stop determination result, Hilbert-Huang transform calculation module start / stop determination result, noise reduction process execution determination result, and event-level upload trigger determination result; correspondingly, the detection device activation module is specifically used for: At least one determination result is integrated into a device activation matrix, and the activation strategy of the detection device is determined based on the device activation matrix.

[0067] Optionally, the fault identification module includes: The feature extraction unit is used to extract the zero-sequence amplitude phasor features, harmonic energy features, time-frequency energy cluster features, principal component dimensionality reduction features, and short-time energy mutation features from the actual grounding fault feature data. The feature integration unit is used to integrate all extracted features according to a preset fusion rule to obtain fused feature data. The identification result output unit is used to input the fused feature data into a preset fault identification model and output the ground fault identification result through model calculation; wherein, the ground fault identification result includes fault type, fault phase and fault confidence level.

[0068] Optionally, the upload module includes: The complexity level determination unit is used to determine the complexity level of the actual operating condition combination based on the types and quantities of actual operating condition parameters included in the actual operating condition combination and the amplitude of parameter fluctuations. The upload rule determination unit is used to retrieve matching ground fault data upload rules from a pre-built upload rule library based on the fault confidence level and the complexity level in the ground fault identification result; wherein, the upload rule library pre-stores the correspondence between fault confidence level, complexity level of operating condition combination and upload rules.

[0069] Optionally, the upload module includes: The data encapsulation unit is used to encapsulate the actual ground fault feature data and the ground fault identification result based on the ground fault data upload rules, and generate a ground fault upload data packet. The uploading unit is used to upload the ground fault data packet to a preset background monitoring system via the power distribution network communication link.

[0070] The ground fault uploading device for power distribution networks provided in this embodiment of the invention can execute the ground fault uploading method for power distribution networks provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0071] Figure 4This is a schematic diagram of an electronic device for implementing the ground fault uploading method for a power distribution network according to embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0072] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0073] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0074] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method of uploading ground faults in a power distribution network.

[0075] In some embodiments, the method for uploading ground faults in the distribution network can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for uploading ground faults in the distribution network described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method for uploading ground faults in the distribution network by any other suitable means (e.g., by means of firmware).

[0076] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0077] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0078] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0079] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0080] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0081] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0082] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0083] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for transmitting ground fault information in a power distribution network, characterized in that, include: Obtain the actual operating condition parameters of the distribution network, generate actual operating condition combinations based on the correlation between the actual operating condition parameters, and query matching ground fault characteristic data in a pre-built theoretical change information database based on the actual operating condition combinations. Based on the ground fault characteristic data, an activation strategy for the detection equipment is determined, and the detection equipment is activated based on the activation strategy. The actual ground fault characteristic data of the distribution network is then collected through the activated detection equipment. Perform multi-feature fusion calculation on the actual ground fault feature data to obtain the ground fault identification result; Based on the ground fault identification result and the actual operating condition combination, a ground fault data upload rule corresponding to the distribution network is determined, and the actual ground fault characteristic data and the ground fault identification result are uploaded based on the data upload rule.

2. The method according to claim 1, characterized in that, The actual operating condition parameters include at least one of the following: system wiring mode parameters, load fluctuation curve parameters, compensation device status parameters, distributed capacitance imbalance parameters, fault type, and disturbance parameters.

3. The method according to claim 1, characterized in that, Before querying matching ground fault characteristic data in a pre-built theoretical variation information database based on the actual operating condition combination, the method further includes: Collect all operating condition parameters of the distribution network and generate multiple full operating condition combinations based on the correlation between the parameters in the full operating condition parameters; For each full-condition combination, a corresponding ground fault acquisition strategy is matched. For each full-condition combination, ground fault characteristic data corresponding to the full-condition combination is determined based on the acquisition strategy. A mapping relationship is established between the full range of operating conditions and their corresponding ground fault characteristic data, and the theoretical change information database is constructed based on multiple sets of the mapping relationship.

4. The method according to claim 1, characterized in that, The activation strategy includes at least one of the following: high sampling rate mode start / stop determination result, harmonic submodule start / stop determination result, Hilbert-Huang transform calculation module start / stop determination result, noise reduction process execution determination result, and event-level upload trigger determination result; The activation strategy for determining the detection device based on the ground fault characteristic data includes: At least one determination result is integrated into a device activation matrix, and the activation strategy of the detection device is determined based on the device activation matrix.

5. The method according to claim 1, characterized in that, The step of performing multi-feature fusion calculation on the actual ground fault feature data to obtain the ground fault identification result includes: Extract the zero-sequence amplitude phasor characteristics, harmonic energy characteristics, time-frequency energy cluster characteristics, principal component dimensionality reduction characteristics, and short-time energy mutation characteristics from the actual grounding fault characteristic data; All extracted features are integrated according to preset fusion rules to obtain fused feature data; The fused feature data is input into a preset fault identification model, and the ground fault identification result is output through model calculation; wherein, the ground fault identification result includes fault type, fault phase and fault confidence level.

6. The method according to claim 1, characterized in that, The step of determining the ground fault data upload rules corresponding to the distribution network based on the ground fault identification results and the actual operating condition combination includes: The complexity level of the actual operating condition combination is determined based on the types, number, and fluctuation amplitude of the actual operating condition parameters included in the actual operating condition combination. Based on the fault confidence level and complexity level in the ground fault identification result, the matching ground fault data upload rule is retrieved from the pre-built upload rule library; wherein, the upload rule library pre-stores the correspondence between fault confidence level, complexity level of working condition combination and upload rule.

7. The method according to claim 1, characterized in that, The uploading of the actual ground fault characteristic data and the ground fault identification result based on the data upload rules includes: Based on the ground fault data upload rules, the actual ground fault feature data and the ground fault identification result are encapsulated to generate a ground fault upload data packet; The ground fault data packet is uploaded to the preset background monitoring system via the power distribution network communication link.

8. A ground fault uploading device for a power distribution network, characterized in that, include: The parameter acquisition module is used to acquire the actual operating condition parameters of the distribution network, generate actual operating condition combinations based on the correlation between the actual operating condition parameters, and query matching ground fault feature data in a pre-built theoretical change information database based on the actual operating condition combinations. The detection equipment activation module is used to determine the activation strategy of the detection equipment based on the ground fault feature data, activate the detection equipment based on the activation strategy, and collect the actual ground fault feature data of the distribution network through the activated detection equipment. The fault identification module is used to perform multi-feature fusion calculation on the actual ground fault feature data to obtain the ground fault identification result; The upload module is used to determine the ground fault data upload rules corresponding to the distribution network based on the ground fault identification results and the actual operating condition combination, and upload the actual ground fault feature data and the ground fault identification results based on the data upload rules.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the ground fault uploading method for the distribution network as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the ground fault uploading method for the distribution network as described in any one of claims 1-7.

Images