DC power distribution network line fault identification method, system, device, medium and product

Abstract

The invention relates to the technical field of power systems, and discloses a direct current power distribution network line fault identification method, system, device, medium and product, the method uses a plurality of similarity algorithms to carry out similarity calculation on current signals at two ends of a target line in a direct current power distribution network collected in real time, thereby avoiding the limitation of a single similarity algorithm, and improving the identification accuracy of the direct current power distribution network line fault. According to the method, the accuracy and robustness of comprehensive similarity calculation can be improved, meanwhile, by weighting the comprehensive similarity and the similarities, whether a redundancy check link is entered or not is judged, by introducing the redundancy check link, it is ensured that fault recognition is more accurate, misoperation is avoided, the fault condition of a target line is recognized through the redundancy check link, and the fault recognition efficiency is improved. Therefore, the line fault of the direct-current power distribution network can be quickly and accurately identified.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method, system, equipment, medium and product for identifying line faults in a DC distribution network. Background Art

[0002] Generally, protection strategies for DC distribution networks can be divided into two categories: local information-based methods and communication-based methods. The former includes overcurrent protection and current differential protection, while the latter includes differential protection and longitudinal directional protection. In DC distribution networks, due to the low system impedance and short transient fault duration, using overcurrent or current differential action as fault signatures often suffers from poor selectivity and significant influence from transient resistance.

[0003] Before protecting the DC distribution network, it is necessary to identify the DC distribution network line fault. However, the existing DC distribution network line fault identification method is prone to misjudgment in high-noise or interference environments, and it is difficult to effectively distinguish fault from non-fault signals, resulting in poor robustness of fault identification. Summary of the Invention

[0004] In view of this, the present invention provides a method, system, device, medium and product for identifying DC distribution network line faults, which solves the technical problems of existing DC distribution network line fault identification methods, which are prone to misjudgment in high-noise or interference environments, and have difficulty in effectively distinguishing fault from non-fault signals, resulting in poor robustness of fault identification.

[0005] A first aspect of the present invention provides a method for identifying a DC power distribution network line fault, comprising:

[0006] Real-time acquisition of current signals at both ends of the target line in the DC distribution network;

[0007] Using a plurality of preset similarity algorithms, determining the similarity between the current signals at the two ends corresponding to each of the preset similarity algorithms;

[0008] Performing dynamic weight fusion on the similarities between the current signals at both ends corresponding to the preset similarity algorithms to obtain a weighted comprehensive similarity;

[0009] Determining whether to enter a redundancy check phase based on the weighted comprehensive similarity and each of the similarities;

[0010] If the weighted comprehensive similarity is greater than a preset first similarity threshold, and any of the similarities is less than a preset second similarity threshold, then the redundancy check step is entered;

[0011] For the redundancy check link, the total energy of the current signal of the target line within a preset time window is obtained, and the transient energy ratio of the current signal is determined based on the total energy;

[0012] Determining whether the transient energy ratio is greater than a preset transient energy ratio threshold;

[0013] When it is determined that the transient energy ratio is greater than the preset transient energy ratio threshold, it is determined that an internal fault exists in the target line.

[0014] Preferably, the preset similarity algorithm includes a Pearson coefficient algorithm, a Tanimoto coefficient algorithm and a cosine similarity algorithm.

[0015] Preferably, the dynamic weight fusion of the similarities between the current signals at both ends corresponding to the preset similarity algorithms to obtain the weighted comprehensive similarity includes:

[0016] According to the environmental scene in which the target route is located, matching the weights of each of the preset similarity algorithms corresponding to the environmental scene in a preset environmental weight mapping library;

[0017] The similarities between the current signals at the two ends respectively corresponding to the preset similarity algorithms are dynamically weighted and fused according to the weights to obtain the weighted comprehensive similarity.

[0018] Preferably, the method further comprises:

[0019] When the weighted comprehensive similarity is greater than a preset first similarity threshold, and any of the similarities is not less than the preset second similarity threshold, it is determined that an external fault exists on the target line.

[0020] Preferably, the acquiring the total energy of the current signal of the target line within a preset time window and determining the transient energy ratio of the current signal according to the total energy includes:

[0021] Integrating the energy of the current signal of the target line within a preset time window to obtain the total energy;

[0022] The transient energy ratio of the current signal is determined according to the total energy and a preset reference energy.

[0023] Preferably, the method further comprises:

[0024] In the case where it is determined that the target line has an internal fault, a fault isolation operation is performed on the target line.

[0025] In a second aspect, the present invention further provides a DC distribution network line fault identification system, comprising:

[0026] Signal acquisition module, used to collect current signals at both ends of the target line in the DC distribution network in real time;

[0027] A similarity calculation module, configured to use a plurality of preset similarity algorithms to determine the similarity between the current signals at the two ends corresponding to the preset similarity algorithms;

[0028] A similarity fusion module is used to perform dynamic weight fusion on the similarities between the current signals at both ends corresponding to the preset similarity algorithms to obtain a weighted comprehensive similarity;

[0029] A similarity judgment module, configured to judge whether to enter a redundancy check phase based on the weighted comprehensive similarity and each of the similarities;

[0030] a redundancy check judgment module, configured to enter the redundancy check step when the weighted comprehensive similarity is greater than a preset first similarity threshold and any of the similarities is less than a preset second similarity threshold;

[0031] a redundancy check module, configured to obtain, for the redundancy check link, a total energy of the current signal of the target line within a preset time window, and determine a transient energy ratio of the current signal based on the total energy;

[0032] An energy judgment module, configured to judge whether the transient energy ratio is greater than a preset transient energy ratio threshold;

[0033] The fault identification module is configured to determine that an internal fault exists in the target line when it is determined that the transient energy ratio is greater than the preset transient energy ratio threshold.

[0034] In a third aspect, the present invention further provides an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor performs the steps of the DC distribution network line fault identification method as described in the first aspect.

[0035] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the steps of the DC distribution network line fault identification method as described in the first aspect.

[0036] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program comprises program instructions, wherein when the program instructions are executed by a computer, the computer is caused to perform the steps of the DC distribution network line fault identification method as described in the first aspect.

[0037] As can be seen from the above technical solutions, the present invention uses multiple similarity algorithms to perform similarity calculation on the current signals at both ends of the target line in the real-time acquisition of the DC distribution network, thereby avoiding the limitations of a single similarity algorithm and improving the accuracy and robustness of the comprehensive similarity calculation. At the same time, by weighting the comprehensive similarity and each similarity, it is determined whether to enter the redundant verification link. By introducing the redundant verification link, fault identification is ensured to be more accurate and malfunction is avoided. The fault condition of the target line is identified through the redundant verification link, thereby achieving rapid and accurate identification of DC distribution network line faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 A diagram illustrating an application environment of a DC distribution network line fault identification method provided by an embodiment of the present invention;

[0040] Figure 2 A flow chart of a method for identifying a DC distribution network line fault provided by an embodiment of the present invention;

[0041] Figure 3 A schematic structural diagram of a DC distribution network line fault identification system provided by an embodiment of the present invention;

[0042] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0044] The DC distribution network line fault identification method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, the terminal 101 communicates with the server 102 via a network. The data storage system can store data that the server 102 needs to process. The data storage system can be integrated on the server 102 or placed on the cloud or other network servers. The terminal 101 or the server 102 collects the current signals at both ends of the target line in the DC distribution network in real time; uses multiple preset similarity algorithms to determine the similarity between the current signals at both ends corresponding to each preset similarity algorithm; performs dynamic weight fusion on the similarity between the current signals at both ends corresponding to each preset similarity algorithm to obtain a weighted comprehensive similarity; judges whether to enter the redundancy check link based on the weighted comprehensive similarity and each similarity; when the weighted comprehensive similarity is greater than a preset first similarity threshold and any similarity is less than a preset second similarity threshold, enters the redundancy check link; for the redundancy check link, obtains the total energy of the current signal of the target line within a preset time window, and determines the transient energy ratio of the current signal based on the total energy; judges whether the transient energy ratio is greater than a preset transient energy ratio threshold; when it is judged that the transient energy ratio is greater than the preset transient energy ratio threshold, it is determined that there is an internal fault in the target line.

[0045] The terminal 101 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and the like.

[0046] The server 102 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0047] like Figure 2 As shown, the embodiment of the present application provides a method for identifying a DC power distribution network line fault, which is applied to Figure 1 The terminal 101 or the server 102 in the embodiment is used as an example to illustrate the method, which includes the following steps S1 to S8.

[0048] Step S1: collecting current signals at both ends of a target line in a DC distribution network in real time.

[0049] The current signals at both ends of the target line are acquired in real time using current transformers or other current acquisition devices. Current transformers offer high precision and fast response, accurately reflecting current changes in the target line within the DC distribution network. They also eliminate high-frequency noise from the current signals through filtering and align the current signal timing using a synchronized clock.

[0050] Step S2: using a plurality of preset similarity algorithms, determining the similarity between the current signals at both ends corresponding to the respective preset similarity algorithms.

[0051] Among them, the preset similarity algorithms include Pearson coefficient algorithm, Tanimoto coefficient algorithm and cosine similarity algorithm.

[0052] It is understandable that in transient fault scenarios, a single similarity algorithm is susceptible to high-impedance faults or noise interference. Cosine similarity is based on the comparison of signal morphological characteristics and mainly relies on the trend of amplitude changes. When the signal experiences a sudden change in amplitude, cosine similarity fails and it is difficult to accurately identify high-impedance faults or rapidly changing signals. The Pearson coefficient mainly reflects the linear correlation between signals, but in the face of nonlinear interference, it may lead to misjudgment and fail to accurately distinguish between normal signals and fault signals. The Tanimoto coefficient calculates the similarity between signals by measuring the amplitude difference. However, in the case of high-impedance faults, the amplitude of the fault signal may change significantly, resulting in a decrease in the Tanimoto coefficient similarity, which helps to identify high-impedance faults and avoid false operations.

[0053] Therefore, the present embodiment uses multiple similarity algorithms to jointly calculate the similarity of current signals at both ends of a target line in a DC distribution network to improve the accuracy and robustness of fault identification. These algorithms can evaluate the similarity of current signals from different perspectives, comprehensively considering factors such as linear correlation, morphological characteristics, and amplitude differences, thereby more comprehensively capturing fault characteristics.

[0054] Among them, cosine similarity is used to describe the directional relationship of the collected current signal vectors, which can analyze the morphological changes of the current waveform and reflect the similarity between the signals based on the calculation results of cosine similarity. The calculation formula is:

[0055]

[0056] Where, and is the vector of current signal, and are their models respectively.

[0057] By analyzing the linear relationship between current signals, the Pearson correlation coefficient provides a measure of the correlation between signals, helping to determine whether the changing trends of the signals are consistent. Its calculation formula is:

[0058]

[0059] Where, and is the current signal vector and The standard deviation of .

[0060] The correlation between current signals is analyzed by Tanimoto similarity. The calculation formula of Tanimoto similarity is:

[0061]

[0062] Step S3: Dynamically weight the similarities between the current signals at both ends corresponding to the preset similarity algorithms to obtain a weighted comprehensive similarity.

[0063] In order to overcome the limitations of a single algorithm, a dynamic weight fusion strategy is adopted. Specifically, it includes:

[0064] Step S301: According to the environment scene where the target route is located, the weights of each preset similarity algorithm corresponding to the environment scene are matched in a preset environment weight mapping library.

[0065] Among them, environmental scenarios include clean state, strong noise state and high harmonic state. Different environmental scenarios may have different effects on the transmission and acquisition of current signals, thereby affecting the effect of the similarity algorithm. Among them, identifying environmental scenarios is to monitor the environmental parameters around the target line in real time through environmental sensors, such as noise level, harmonic content, etc., and compare and analyze these parameters with historical data or preset standards to determine the current environmental scenario. The preset environmental weight mapping library is established based on a large amount of experimental data and expert experience, and stores the recommended weights of each preset similarity algorithm under different environmental scenarios. By matching the current environmental scenario with the preset environmental weight mapping library, the weights of each similarity algorithm applicable to the current environment can be obtained to ensure the accuracy and reliability of the weighted comprehensive similarity. The preset environmental weight mapping library is shown in Table 1.

[0066] Table 1

[0067]

[0068] According to the environment weight mapping library, the current scene type can be matched. According to the environment type, the system will automatically generate a dynamic weight vector. ,in, 、 and are the dynamic weights of cosine similarity, Pearson correlation coefficient and Tanimoto similarity respectively, and T is the matrix transpose.

[0069] The size of each weight determines the influence of the corresponding similarity algorithm in the comprehensive judgment. By dynamically adjusting the weights, the system can automatically select the most appropriate similarity algorithm based on environmental changes, thereby maintaining a high fault recognition rate in a changing environment.

[0070] Step S302 : Dynamically weight fusion is performed on the similarities between the current signals at both ends corresponding to the preset similarity algorithms according to the weights to obtain a weighted comprehensive similarity.

[0071] Based on the dynamic weight of the environment, calculate the weighted comprehensive similarity:

[0072]

[0073] Where S total is a weighted composite similarity. By weighting these similarities, a comprehensive judgment index is obtained, which the system uses to make a fault judgment. The purpose of weighted calculation is to combine the advantages of each similarity algorithm, so that the comprehensive judgment can maintain high robustness in various situations. For example, in a noisy environment, the characteristics of sudden amplitude changes will be more prominent, so the Tanimoto similarity will have a greater impact on the comprehensive result.

[0074] Step S4: Determine whether to enter the redundancy check phase based on the weighted comprehensive similarity and each similarity.

[0075] After obtaining the weighted comprehensive similarity and each similarity, a threshold determination is performed to determine whether a redundancy check step needs to be further performed.

[0076] Specifically, if the weighted combined similarity is greater than a preset first similarity threshold, and any individual similarity is less than a preset second similarity threshold, this indicates a possible anomaly or that a single algorithm is significantly affected by a specific environment. At this point, the system enters a redundancy check phase for more rigorous fault determination to ensure accurate identification. This redundancy check further enhances the reliability of fault identification through in-depth analysis of current signals, such as by utilizing characteristic quantities like transient energy ratios.

[0077] Step S5: When the weighted comprehensive similarity is greater than the preset first similarity threshold, and any similarity is less than the preset second similarity threshold, the redundancy check step is entered.

[0078] The first similarity threshold is a standard value set based on historical data and experiments, and is intended to classify different fault types. For example, it is set to 0.85.

[0079] To enhance system robustness, the comprehensive similarity determination relies not only on a single sampling result but also on the comprehensive similarity of three consecutive samples. This multiple determination mechanism ensures that abnormal signal fluctuations over a short period of time will not lead to misjudgment. If any similarity falls below the second similarity threshold of 0.7, a redundant check mechanism is initiated. This additional check step ensures that the system is more rigorous in handling transient faults. This is intended to prevent false positives and negatives, which can cause malfunctions due to factors such as transient interference and signal noise, leading to equipment damage or unnecessary downtime.

[0080] When the weighted comprehensive similarity is greater than a preset first similarity threshold, and any similarity is not less than a preset second similarity threshold, it is determined that an external fault exists on the target line.

[0081] Step S6: For the redundancy check link, the total energy of the current signal of the target line within the preset time window is obtained, and the transient energy ratio of the current signal is determined based on the total energy.

[0082] Among them, the redundancy check link mainly checks whether the similarity has dropped sharply. If the similarity drops sharply within the lookback window, it means that the signal amplitude has changed suddenly, which may be caused by noise or other transient factors. Therefore, the system will not make a fault judgment immediately, but trigger further redundancy check. The system will introduce a transient energy ratio , as an auxiliary basis for judgment. The role of this feature is to help the system confirm through other means when the amplitude change is not obvious.

[0083] Specifically, the total energy of the current signal of the target line within a preset time window is obtained, and the transient energy ratio of the current signal is determined based on the total energy, including:

[0084] Step S601: Integrate the energy of the current signal of the target line within a preset time window to obtain the total energy.

[0085] The calculation process of total energy is:

[0086]

[0087] Where, is the current signal amplitude. By integrating the current signal amplitude within the time window, the total energy E(t) within the period can be calculated.

[0088] Step S602: Determine the transient energy ratio of the current signal according to the total energy and the preset reference energy.

[0089] Among them, the transient energy ratio is:

[0090]

[0091] Where, is the total energy E(t), It is the baseline energy during normal operation.

[0092] Step S7: Determine whether the transient energy ratio is greater than a preset transient energy ratio threshold.

[0093] Wherein, according to the calculated transient energy ratio, it is determined whether it is greater than a preset transient energy ratio threshold. If it is greater than the threshold, it is determined to be an internal fault. When it is determined that the target line has an internal fault, a fault isolation operation is performed on the target line.

[0094] The transient energy ratio threshold is an empirical threshold derived through experiments and data analysis. This threshold takes into account the energy characteristics of high-impedance faults and avoids misjudgments caused by inaccurate judgments based on a single similarity algorithm. This mechanism enables the system to make accurate and rapid decisions when high-impedance faults occur, thereby enhancing the reliability and safety of fault diagnosis.

[0095] If it is determined that the transient energy ratio is not greater than a preset transient energy ratio threshold, it is determined to be an external fault and no fault isolation operation is performed on the target line.

[0096] Step S8: If it is determined that the transient energy ratio is greater than the preset transient energy ratio threshold, it is determined that an internal fault exists in the target line.

[0097] It should be noted that the embodiment of the present application uses multiple similarity algorithms to perform similarity calculation on the current signals at both ends of the target line in the real-time acquisition of the DC distribution network, thereby avoiding the limitations of a single similarity algorithm and improving the accuracy and robustness of the comprehensive similarity calculation. At the same time, by weighting the comprehensive similarity and each similarity, it is determined whether to enter the redundant verification link. By introducing the redundant verification link, fault identification is ensured to be more accurate and false operations are avoided. The fault condition of the target line is identified through the redundant verification link, thereby achieving rapid and accurate identification of DC distribution network line faults.

[0098] After confirming an internal fault on the target line during redundancy verification, the system will further perform fault isolation operations to ensure safe and stable grid operation. Specific implementations of fault isolation operations include, but are not limited to, disconnecting the faulty line and activating backup lines. These operations will be intelligently determined based on the actual grid situation and fault type to achieve the optimal fault recovery strategy.

[0099] Based on the same inventive concept, an embodiment of the present application further provides a DC distribution network line fault identification system for implementing the above-mentioned DC distribution network line fault identification method.

[0100] The implementation solution provided by the system to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in the embodiments of one or more DC distribution network line fault identification systems provided below can refer to the limitations of the DC distribution network line fault identification method above, and will not be repeated here.

[0101] like Figure 3As shown, the present invention also provides a DC distribution network line fault identification system, comprising:

[0102] The signal acquisition module 100 is used to collect the current signals at both ends of the target line in the DC distribution network in real time;

[0103] The similarity calculation module 200 is used to use a plurality of preset similarity algorithms to determine the similarity between the current signals at both ends corresponding to each preset similarity algorithm;

[0104] The similarity fusion module 300 is used to perform dynamic weight fusion on the similarities between the current signals at both ends corresponding to the preset similarity algorithms to obtain a weighted comprehensive similarity;

[0105] A similarity determination module 400 is used to determine whether to enter the redundancy check phase based on the weighted comprehensive similarity and each similarity;

[0106] The redundancy check judgment module 500 is used to enter the redundancy check phase when the weighted comprehensive similarity is greater than a preset first similarity threshold and any similarity is less than a preset second similarity threshold;

[0107] The redundancy check module 600 is used to obtain the total energy of the current signal of the target line within a preset time window for the redundancy check link, and determine the transient energy ratio of the current signal based on the total energy;

[0108] An energy determination module 700 is configured to determine whether the transient energy ratio is greater than a preset transient energy ratio threshold;

[0109] The fault identification module 800 is configured to determine that an internal fault exists in the target line when it is determined that the transient energy ratio is greater than a preset transient energy ratio threshold.

[0110] In some embodiments, the preset similarity algorithms include a Pearson coefficient algorithm, a Tanimoto coefficient algorithm, and a cosine similarity algorithm.

[0111] In some embodiments, the similarity fusion module 300 is configured to:

[0112] According to the environmental scene where the target route is located, the weights of each preset similarity algorithm corresponding to the environmental scene are matched in the preset environmental weight mapping library;

[0113] The similarities between the current signals at both ends corresponding to the preset similarity algorithms are dynamically weighted and fused according to the weights to obtain a weighted comprehensive similarity.

[0114] In some embodiments, the system further includes an external fault identification module for:

[0115] When the weighted comprehensive similarity is greater than a preset first similarity threshold, and any similarity is not less than a preset second similarity threshold, it is determined that an external fault exists on the target line.

[0116] In some embodiments, the redundancy check module 600 is configured to:

[0117] Integrate the energy of the current signal of the target line within a preset time window to obtain the total energy;

[0118] The transient energy ratio of the current signal is determined according to the total energy and the preset reference energy.

[0119] In some embodiments, the device further comprises an isolation module configured to:

[0120] When it is determined that an internal fault exists in the target line, a fault isolation operation is performed on the target line.

[0121] like Figure 4 As shown, an embodiment of the present application provides an electronic device, the electronic device 10 includes a memory 20 and a processor 30, the memory 20 stores a computer program, and when the computer program is executed by the processor 30, the processor 30 performs the steps of the DC distribution network line fault identification method in the above embodiment.

[0122] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, the steps of the method for identifying a line fault in a DC distribution network as described in the above embodiment are implemented.

[0123] An embodiment of the present application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the steps of the DC distribution network line fault identification method described in the above embodiment.

[0124] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, electronic devices, computer storage media, and computer program products can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0125] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or apparatuses.

[0126] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0127] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, electronic devices, computer storage media, computer program products and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0129] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0130] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the method described in each embodiment of the present invention via a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0131] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for identifying line faults in a DC distribution network, characterized in that: include: Real-time acquisition of current signals at both ends of the target line in the DC distribution network; Using a plurality of preset similarity algorithms, determining the similarity between the current signals at the two ends corresponding to each of the preset similarity algorithms; Performing dynamic weight fusion on the similarities between the current signals at both ends corresponding to the preset similarity algorithms to obtain a weighted comprehensive similarity; Determining whether to enter a redundancy check phase based on the weighted comprehensive similarity and each of the similarities; If the weighted comprehensive similarity is greater than a preset first similarity threshold, and any of the similarities is less than a preset second similarity threshold, then the redundancy check step is entered; For the redundancy check link, the total energy of the current signal of the target line within a preset time window is obtained, and the transient energy ratio of the current signal is determined based on the total energy; Determining whether the transient energy ratio is greater than a preset transient energy ratio threshold; When it is determined that the transient energy ratio is greater than the preset transient energy ratio threshold, it is determined that an internal fault exists in the target line.

2. The DC distribution network line fault identification method according to claim 1, characterized in that: The preset similarity algorithms include a Pearson coefficient algorithm, a Tanimoto coefficient algorithm, and a cosine similarity algorithm.

3. The DC distribution network line fault identification method according to claim 1 or 2, characterized in that: The dynamic weight fusion of the similarities between the current signals at both ends corresponding to the preset similarity algorithms to obtain a weighted comprehensive similarity includes: According to the environmental scene in which the target route is located, matching the weights of each of the preset similarity algorithms corresponding to the environmental scene in a preset environmental weight mapping library; The similarities between the current signals at the two ends respectively corresponding to the preset similarity algorithms are dynamically weighted and fused according to the weights to obtain the weighted comprehensive similarity.

4. The DC distribution network line fault identification method according to claim 1, characterized in that: Also includes: When the weighted comprehensive similarity is greater than a preset first similarity threshold, and any of the similarities is not less than the preset second similarity threshold, it is determined that an external fault exists on the target line.

5. The DC distribution network line fault identification method according to claim 1, characterized in that: The acquiring the total energy of the current signal of the target line within a preset time window and determining the transient energy ratio of the current signal according to the total energy includes: Integrating the energy of the current signal of the target line within a preset time window to obtain the total energy; The transient energy ratio of the current signal is determined according to the total energy and a preset reference energy.

6. The DC distribution network line fault identification method according to claim 1, characterized in that: Also includes: In the case where it is determined that the target line has an internal fault, a fault isolation operation is performed on the target line.

7. A DC distribution network line fault identification system, characterized in that: include: Signal acquisition module, used to collect current signals at both ends of the target line in the DC distribution network in real time; A similarity calculation module, configured to use a plurality of preset similarity algorithms to determine the similarity between the current signals at the two ends corresponding to the preset similarity algorithms; A similarity fusion module is used to perform dynamic weight fusion on the similarities between the current signals at both ends corresponding to the preset similarity algorithms to obtain a weighted comprehensive similarity; A similarity judgment module, configured to judge whether to enter a redundancy check phase based on the weighted comprehensive similarity and each of the similarities; a redundancy check judgment module, configured to enter the redundancy check step when the weighted comprehensive similarity is greater than a preset first similarity threshold and any of the similarities is less than a preset second similarity threshold; a redundancy check module, configured to obtain, for the redundancy check link, a total energy of the current signal of the target line within a preset time window, and determine a transient energy ratio of the current signal based on the total energy; An energy judgment module, configured to judge whether the transient energy ratio is greater than a preset transient energy ratio threshold; The fault identification module is configured to determine that an internal fault exists in the target line when it is determined that the transient energy ratio is greater than the preset transient energy ratio threshold.

8. An electronic device, characterized in that: The electronic device includes a memory and a processor, wherein a computer program is stored in the memory. When the computer program is executed by the processor, the processor performs the steps of the DC distribution network line fault identification method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the steps of the method for identifying a DC distribution network line fault are implemented as claimed in any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer is caused to perform the steps of the method for identifying a line fault in a DC distribution network according to any one of claims 1 to 6.

Images