Ground fault monitoring method and device for low-voltage direct-current system, computer equipment, readable storage medium and program product

Abstract

The invention relates to the technical field of low-voltage direct-current system monitoring, and provides a low-voltage direct-current system grounding fault monitoring method and device, computer equipment, a readable storage medium and a program product. The method comprises the steps that when it is monitored that the insulation resistance value of the low-voltage direct current system is smaller than a preset resistance threshold value, an initial branch set is obtained according to the air switch state of each branch, so that a candidate branch set is obtained; for any candidate branch, calculating the similarity between the candidate branch and any grounding type branch in the typical grounding test feature library according to the leakage current amplitude, the leakage current phase and the running current change rate; and when the similarity between the candidate branch and one of the grounding type branches is smaller than a first preset similarity threshold value and the operation current deviation between the candidate branch and one of the grounding type branches is smaller than a preset deviation threshold value, determining the candidate branch as a suspected grounding branch so as to determine a target grounding branch of which the grounding probability is greater than a preset grounding probability threshold value. The method can improve the monitoring precision.

Description

Technical Field

[0001] This application relates to the technical field of low-voltage DC system monitoring, and in particular to a method, device, computer device, computer-readable storage medium, and computer program product for monitoring grounding faults in a low-voltage DC system. Background Art

[0002] With the development of electrical equipment and automation systems, low-voltage DC systems have been widely used in fields such as industrial control, rail transit, power electronics, and new energy. Low-voltage DC systems have advantages such as high efficiency, convenient control, and high power density. However, the operating safety of low-voltage DC systems has very high requirements for the insulation state. Therefore, it is necessary to monitor grounding faults in low-voltage DC systems.

[0003] In traditional methods, the balance bridge method or the low-frequency injection method is used to monitor grounding faults in low-voltage DC systems. Among them, the balance bridge method determines whether there is a grounding fault in the low-voltage DC system by monitoring the balance of the positive and negative pole voltages to the ground, but this method cannot locate the specific fault branch; the low-frequency injection method injects a low-frequency signal into the low-voltage DC system and determines whether there is a grounding fault in the low-voltage DC system by monitoring the change in the signal loop current, but this method is easily affected by environmental interference and locates the specific fault branch. In summary, traditional methods for monitoring grounding faults in low-voltage DC systems only monitor the overall insulation resistance of the low-voltage DC system, making it difficult to locate the specific fault branch and resulting in low monitoring accuracy. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer device, computer-readable storage medium, and computer program product for monitoring grounding faults in a low-voltage DC system in view of the above technical problems.

[0005] In a first aspect, this application provides a method for monitoring grounding faults in a low-voltage DC system, including:

[0006] When it is detected that the insulation resistance value of the low-voltage DC system is less than a preset resistance threshold, an initial branch set in the operating state in the low-voltage DC system is obtained according to the on-off state of the air switch of each branch in the low-voltage DC system;

[0007] A candidate branch set is obtained according to whether the initial branches in the initial branch set meet the conditions for starting to determine suspected grounding branches;

[0008] For any candidate branch in the candidate branch set, the similarity between the candidate branch and any grounding type branch in the typical grounding test feature library is calculated according to the leakage current amplitude, leakage current phase, and operating current change rate;

[0009] When the similarity between the candidate branch and one of the grounded type branches is less than the first preset similarity threshold, and the deviation between the operating current of the candidate branch and the operating current of the one grounded type branch is less than the preset deviation threshold, the candidate branch is determined as a suspected grounded branch;

[0010] According to the suspected grounded branch and the branch-level topology relationship of the low-voltage DC system, a target grounded branch with a grounding probability greater than the preset grounding probability threshold is determined.

[0011] In one embodiment, the obtaining the candidate branch set according to whether the initial branch in the initial branch set meets the condition for starting the determination of the suspected grounded branch includes:

[0012] When the change rate of the operating current of the initial branch in the initial branch set is less than the preset change threshold, it is determined that the initial branch meets the condition for starting the determination of the suspected grounded branch;

[0013] The candidate branch set is obtained according to the initial branch that meets the condition for starting the determination of the suspected grounded branch.

[0014] In one embodiment, the calculating the similarity between the candidate branch and any grounded type branch in the typical grounding test feature library according to the leakage current amplitude, the leakage current phase, and the change rate of the operating current includes:

[0015] Obtain the weights corresponding to the leakage current amplitude, the leakage current phase, and the change rate of the operating current respectively;

[0016] According to the differences between the leakage current amplitude, the leakage current phase, and the change rate of the operating current of the candidate branch and the amplitude of the leakage current, the phase of the leakage current, and the operating current of any grounded type branch in the typical grounding test feature library, the differences corresponding to the leakage current amplitude, the leakage current phase, and the change rate of the operating current are obtained respectively;

[0017] Multiply the weights and the differences corresponding to the leakage current amplitude, the leakage current phase, and the change rate of the operating current respectively, and then perform an addition process to obtain the similarity between the candidate branch and any grounded type branch in the typical grounding test feature library.

[0018] In one embodiment, the determining a target grounded branch with a grounding probability greater than the preset grounding probability threshold according to the suspected grounded branch and the branch-level topology relationship of the low-voltage DC system includes:

[0019] Obtain the branch-level topology relationship of the low-voltage DC system;

[0020] According to the branch-level topological relationship of the low-voltage DC system, the downstream branches in the suspected grounding branch are determined as the target grounding branches with a grounding probability greater than the preset grounding probability threshold.

[0021] In one embodiment, after determining the target grounding branch with a grounding probability greater than the preset grounding probability threshold, the method further includes:

[0022] When it is determined that the target grounding branch is a true grounding branch, the leakage current amplitude, leakage current phase, operating current, and operating current change rate of the target grounding branch are obtained as the target feature vector;

[0023] When the similarity between the target feature vector and the feature vector corresponding to one of the grounding type branches in the typical grounding test feature library is less than the second preset similarity threshold, the weights of the features in the feature vector are updated to update the typical grounding test feature library; the features include leakage current amplitude, leakage current phase, operating current, and operating current change rate;

[0024] When the similarity between the target feature vector and the feature vector corresponding to one of the grounding type branches in the typical grounding test feature library is greater than the second preset similarity threshold, the target feature vector is added to the typical grounding test feature library to update the typical grounding test feature library.

[0025] In one embodiment, the updating the weights of the features in the feature vector includes:

[0026] When one of the features in the target feature vector contributes more to the grounding fault monitoring than the preset contribution threshold, the weight of the one feature is increased;

[0027] When one of the features in the target feature vector contributes less to the grounding fault monitoring than the preset contribution threshold, the weight of the one feature is decreased.

[0028] In a second aspect, the present application also provides a low-voltage DC system grounding fault monitoring device, including:

[0029] An initial branch set acquisition module, configured to obtain an initial branch set in the operating state of the low-voltage DC system according to the on / off state of the air switches of each branch in the low-voltage DC system when it is monitored that the insulation resistance value of the low-voltage DC system is less than the preset resistance threshold;

[0030] A candidate branch set acquisition module, configured to obtain a candidate branch set according to whether the initial branches in the initial branch set meet the conditions for starting the determination of suspected grounding branches;

[0031] A similarity acquisition module, configured to calculate the similarity between any candidate branch in a candidate branch set and any grounding type branch in a typical grounding test feature library according to the leakage current amplitude, the leakage current phase, and the operating current change rate;

[0032] A suspected grounding branch determination module, configured to determine the candidate branch as a suspected grounding branch when the similarity between the candidate branch and one of the grounding type branches is less than a first preset similarity threshold, and the deviation between the operating current of the candidate branch and the operating current of the one of the grounding type branches is less than a preset deviation threshold;

[0033] A target grounding branch determination module, configured to determine a target grounding branch with a grounding probability greater than a preset grounding probability threshold according to the suspected grounding branch and the branch - level topological relationship of the low - voltage DC system.

[0034] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and the processor executes the above - mentioned method.

[0035] In a fourth aspect, the present application further provides a computer - readable storage medium. The computer - readable storage medium stores a computer program thereon, and the computer program is executed by a processor to execute the above - mentioned method.

[0036] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and the computer program is executed by a processor to execute the above - mentioned method.

[0037] The above-mentioned low-voltage DC system grounding fault monitoring method, device, computer equipment, computer-readable storage medium, and computer program product, when detecting that the insulation resistance value of the low-voltage DC system is less than the preset resistance threshold, obtain the initial branch set in the running state in the low-voltage DC system according to the on / off state of the air switches of each branch in the low-voltage DC system; obtain the candidate branch set according to whether the initial branches in the initial branch set meet the conditions for starting to determine the suspected grounding branches; for any candidate branch in the candidate branch set, calculate the similarity between the candidate branch and any grounding type branch in the typical grounding test feature library according to the leakage current amplitude, leakage current phase, and operating current change rate; when the similarity between the candidate branch and one of the grounding type branches is less than the first preset similarity threshold, and the deviation between the operating current of the candidate branch and the operating current of one of the grounding type branches is less than the preset deviation threshold, determine the candidate branch as a suspected grounding branch; determine the target grounding branch with a grounding probability greater than the preset grounding probability threshold according to the suspected grounding branch and the branch-level topology relationship of the low-voltage DC system. Through monitoring the on / off state of the air switches of each branch in the low-voltage DC system, this application determines the candidate branch set; in the candidate branch set, according to the leakage current amplitude, leakage current phase, and operating current change rate, it determines the suspected grounding branch; according to the suspected grounding branch and the branch-level topology relationship of the low-voltage DC system, it determines the target grounding branch with a grounding probability greater than the preset grounding probability threshold, which can locate the specific faulty branch under complex working conditions and improve the monitoring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0039] Figure 1 It is an application environment diagram of the low-voltage DC system grounding fault monitoring method in an embodiment;

[0040] Figure 2 It is a flowchart of the low-voltage DC system grounding fault monitoring method in an embodiment;

[0041] Figure 3 It is a flowchart of calculating the similarity between a candidate branch and any grounding type branch in the typical grounding test feature library in an embodiment;

[0042] Figure 4 It is a structural block diagram of the low-voltage DC system grounding fault monitoring device in an embodiment;

[0043] Figure 5 It is the internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0044] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] The grounding fault monitoring method for a low-voltage DC system provided by an embodiment of the present application can be applied to, for example Figure 1 the application environment shown in the figure. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or on other network servers. When the terminal 102 monitors that the insulation resistance value of the low-voltage DC system is less than a preset resistance threshold, it determines a target grounding branch whose grounding probability is greater than a preset grounding probability threshold according to the leakage current, operating current and on-off state of the air switch of each branch in the low-voltage DC system. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0046] In an exemplary embodiment, as Figure 2 shown in the figure, a grounding fault monitoring method for a low-voltage DC system is provided. Taking the method applied to the terminal 102 in Figure 1 as an example, the following steps S201 to S205 are included. Among them:

[0047] Step S201, when it is monitored that the insulation resistance value of the low-voltage DC system is less than a preset resistance threshold, obtain an initial branch set in the running state in the low-voltage DC system according to the on-off state of the air switch of each branch in the low-voltage DC system.

[0048] The preset resistance threshold can be set according to the actual situation. For example, the preset resistance threshold can be set to 50 kΩ.

[0049] When it is detected that the insulation resistance value \(R_{alert}\) of the low-voltage DC system is less than the preset resistance threshold, it indicates that there may be a grounding fault in the low-voltage DC system. At this time, the initial branch set in the running state of the low-voltage DC system can be obtained according to the on-off state of the air switches of each branch in the low-voltage DC system. Specifically, the branches with the air switches in the closed state (\(S = 1\)) can be determined as the initial branches; based on the initial branches, the initial branch set in the running state of the low-voltage DC system can be obtained.

[0050] Step S202: Obtain the candidate branch set according to whether the initial branches in the initial branch set meet the conditions for starting the determination of suspected grounding branches.

[0051] Before starting the determination of suspected grounding branches, it is necessary to first determine whether the initial branches in the initial branch set meet the conditions for starting the determination of suspected grounding branches to obtain the candidate branch set to avoid misjudgment.

[0052] Step S203: For any candidate branch in the candidate branch set, calculate the similarity between the candidate branch and any grounding type branch in the typical grounding test feature library according to the leakage current amplitude, leakage current phase, and operating current change rate.

[0053] The leakage current amplitude of branches of different grounding types (grounding positions) can be obtained according to the typical grounding test scenario and the leakage current phase (relative to the system voltage) and the change rate of the operating current to form the feature vectors corresponding to branches of different grounding types ; the typical grounding test feature library can be obtained according to the feature vectors corresponding to branches of different grounding types. Among them, the actual application environment or experimental environment for simulating, detecting, and verifying the grounding condition of the low-voltage DC system is called the grounding test scenario; the grounding test scenario for simulating, detecting, and verifying the relatively common grounding conditions of the low-voltage DC system is called the typical grounding test scenario. The typical grounding test scenario includes the end grounding scenario and the midpoint grounding scenario. The end grounding scenario can connect a fixed resistor

[0054] (typical value 10 kΩ - 100 kΩ) at the end of the branch (such as the circuit breaker mechanism box); the midpoint grounding scenario can connect a fixed resistor in the middle of the branch (such as inside the switch cabinet) .

[0055] For any candidate branch in the candidate branch set, the similarity between the candidate branch and any branch of a grounding type in the typical grounding test feature library can be calculated based on the differences in the leakage current amplitude, leakage current phase, and operating current change rate of the candidate branch and those of any branch of a grounding type in the typical grounding test feature library. Among them, the leakage current phase can be analyzed through the Fast Fourier Transform (FFT) to eliminate the harmonic interference in the low-voltage DC system.

[0056] Step S204: When the similarity between the candidate branch and a branch of a certain grounding type is less than the first preset similarity threshold, and the deviation between the operating current of the candidate branch and the operating current of a branch of a certain grounding type is less than the preset deviation threshold, the candidate branch is determined as a suspected grounding branch.

[0057] The first preset similarity threshold and the preset deviation threshold can be set according to the actual situation. For example, the first preset similarity threshold can be set to 0.2, and the preset deviation threshold can be set to 10%.

[0058] When the similarity between the candidate branch and a branch of a certain grounding type is less than the first preset similarity threshold , and the deviation between the operating current of the candidate branch and the operating current of a branch of a certain grounding type is less than the preset deviation threshold, it indicates that there may be a grounding fault in the candidate branch. At this time, the candidate branch can be determined as a suspected grounding branch.

[0059] Step S205: According to the branch-level topological relationship between the suspected grounding branch and the low-voltage DC system, determine the target grounding branch whose grounding probability is greater than the preset grounding probability threshold.

[0060] Based on the branch-level topological relationship of the low-voltage DC system, the target grounding branch whose grounding probability is greater than the preset grounding probability threshold can be determined among the suspected grounding branches.

[0061] In the above-mentioned low-voltage DC system grounding fault monitoring method, by monitoring the on-off state of the air switches of each branch in the low-voltage DC system, the candidate branch set is determined; in the candidate branch set, the suspected grounding branch is determined according to the leakage current amplitude, leakage current phase, and operating current change rate; according to the branch-level topological relationship between the suspected grounding branch and the low-voltage DC system, the target grounding branch whose grounding probability is greater than the preset grounding probability threshold is determined, which can locate the specific fault branch under complex working conditions and improve the monitoring accuracy.

[0062] In one embodiment, a candidate branch set is obtained according to whether the initial branches in the initial branch set meet the conditions for starting the determination of suspected grounded branches. The specific steps are as follows: When the rate of change of the operating current of the initial branches in the initial branch set is less than a preset change threshold, it is determined that the initial branches meet the conditions for starting the determination of suspected grounded branches; according to the initial branches that meet the conditions for starting the determination of suspected grounded branches, a candidate branch set is obtained.

[0063] The preset change threshold can be set according to the actual situation. For example, the preset change threshold can be set to ±5% / s.

[0064] When the rate of change of the operating current of the initial branches in the initial branch set is less than the preset change threshold, it indicates that the false alarm probability of determining the suspected grounded branches for the initial branches is relatively low. At this time, it can be determined that the initial branches meet the conditions for starting the determination of suspected grounded branches. When the rate of change of the operating current of the initial branches in the initial branch set is greater than or equal to the preset change threshold, it indicates that the false alarm probability of determining the suspected grounded branches for the initial branches is relatively high. At this time, it can be determined that the initial branches do not meet the conditions for starting the determination of suspected grounded branches.

[0065] The initial branches that meet the conditions for starting the determination of suspected grounded branches can be used as candidate branches to obtain a candidate branch set.

[0066] In this embodiment, when the rate of change of the operating current of the initial branches in the initial branch set is less than the preset change threshold, it is determined that the initial branches meet the conditions for starting the determination of suspected grounded branches to obtain a candidate branch set, which can reduce the false alarm probability of determining the suspected grounded branches for the initial branches, thereby improving the monitoring accuracy.

[0067] In one embodiment, according to the leakage current amplitude, leakage current phase, and rate of change of the operating current, the similarity between the candidate branch and any grounded type branch in the typical grounding test feature library is calculated. Specifically, it can be as Figure 3 shown in the steps: Step S301, obtain the weights corresponding to the leakage current amplitude, leakage current phase, and rate of change of the operating current respectively; Step S302, according to the differences between the leakage current amplitude, leakage current phase, and rate of change of the operating current of the candidate branch and the leakage current amplitude, leakage current phase, and operating current of any grounded type branch in the typical grounding test feature library, obtain the differences corresponding to the leakage current amplitude, leakage current phase, and rate of change of the operating current respectively; Step S303, multiply the weights and differences corresponding to the leakage current amplitude, leakage current phase, and rate of change of the operating current respectively, and then perform an addition process to obtain the similarity between the candidate branch and any grounded type branch in the typical grounding test feature library.

[0068] The weights corresponding to the leakage current amplitude, the weights corresponding to the leakage current phase, and the weights corresponding to the operating current change rate can be optimized and set according to the test data of the low-voltage DC system. and the weights corresponding to the leakage current phase and the weights corresponding to the operating current change rate .

[0069] Based on the leakage current amplitude of the candidate branch detected in real time, the leakage current phase, and the operating current change rate , the differences between them and the leakage current amplitude , the leakage current phase , and the operating current of any grounding type branch in the typical grounding test feature library can be obtained, and the corresponding differences of the leakage current amplitude, the leakage current phase, and the operating current change rate can be obtained.

[0070] The weights and differences corresponding to the leakage current amplitude, the leakage current phase, and the operating current change rate can be multiplied and then added to obtain the similarity between the candidate branch and any grounding type branch in the typical grounding test feature library, as shown in Equation (1).

[0071] (1)

[0072] In this embodiment, based on the differences between the leakage current amplitude, the leakage current phase, and the operating current change rate of the candidate branch and the leakage current amplitude, the leakage current phase, and the operating current of any grounding type branch in the typical grounding test feature library, the corresponding differences of the leakage current amplitude, the leakage current phase, and the operating current change rate are obtained; by multiplying and then adding the weights and differences corresponding to the leakage current amplitude, the leakage current phase, and the operating current change rate, the relatively accurate similarity between the candidate branch and any grounding type branch in the typical grounding test feature library can be quickly obtained.

[0073] In one of the embodiments, according to the branch-level topological relationship between the suspected grounding branch and the low-voltage DC system, the target grounding branch with a grounding probability greater than the preset grounding probability threshold is determined. The specific steps are as follows: obtain the branch-level topological relationship of the low-voltage DC system; according to the branch-level topological relationship of the low-voltage DC system, determine the downstream branch in the suspected grounding branch as the target grounding branch with a grounding probability greater than the preset grounding probability threshold.

[0074] The branch-level topological relationship of the low-voltage DC system can be obtained based on the electrical wiring relationship of the low-voltage DC system and professional analysis tools.

[0075] According to the branch - level topological relationship of the low - voltage DC system, the downstream branches in the suspected grounding branch (such as the end - grounding branch with a lower similarity) can be determined as the target grounding branches with a grounding probability greater than the preset grounding probability threshold.

[0076] In this embodiment, according to the branch - level topological relationship of the low - voltage DC system, the downstream branches in the suspected grounding branch are determined as the target grounding branches with a grounding probability greater than the preset grounding probability threshold, and target grounding branches with a higher grounding probability can be obtained, which can improve the monitoring accuracy.

[0077] In one of the embodiments, after determining the target grounding branch with a grounding probability greater than the preset grounding probability threshold, the method provided in this application further includes: when it is determined that the target grounding branch is a real grounding branch, obtaining the leakage current amplitude, leakage current phase, operating current, and operating current change rate of the target grounding branch as the target feature vector; when the similarity between the target feature vector and the feature vector corresponding to one of the grounding - type branches in the typical grounding test feature library is less than the second preset similarity threshold, updating the weights of each feature in the feature vector to update the typical grounding test feature library; the features include leakage current amplitude, leakage current phase, operating current, and operating current change rate; when the similarity between the target feature vector and the feature vector corresponding to one of the grounding - type branches in the typical grounding test feature library is greater than the second preset similarity threshold, adding the target feature vector into the typical grounding test feature library to update the typical grounding test feature library.

[0078] In actual operation, when it is determined that the target grounding branch is a real grounding branch, the optimization process of the typical grounding test feature library can be automatically started to further improve the accuracy of subsequent low - voltage DC system grounding fault monitoring. Among them, the low - voltage DC system grounding fault monitoring can also be called low - voltage DC system insulation monitoring.

[0079] When it is determined that the target grounding branch is a real grounding branch, the leakage current amplitude, leakage current phase, operating current, and operating current change rate of the target grounding branch can be obtained as the target feature vector.

[0080] When the similarity between the target feature vector and the feature vector corresponding to one of the grounding - type branches in the typical grounding test feature library is less than the second preset similarity threshold, update the weights of each feature in the feature vector to update the typical grounding test feature library, reflecting the contribution of the target feature vector; the features include leakage current amplitude, leakage current phase, operating current, and operating current change rate. Among them, the second preset similarity threshold can be set according to the actual situation.

[0081] When the similarity between the target feature vector and the feature vector corresponding to one of the grounding type branches in the typical grounding test feature library is greater than the second preset similarity threshold, add the target feature vector to the typical grounding test feature library to use the target feature vector as new reference data and update the typical grounding test feature library.

[0082] In this embodiment, after determining that the target grounding branch is a true grounding branch, obtain the leakage current amplitude, leakage current phase, operating current, and operating current change rate of the target grounding branch as the target feature vector; update the typical grounding test feature library according to the similarity between the target feature vector and the feature vector corresponding to the grounding type branch in the typical grounding test feature library, so as to further improve the accuracy of subsequent grounding fault monitoring of the low-voltage DC system.

[0083] In one of the embodiments, update the weights of the features in the feature vector. The specific steps are as follows: when the contribution of one of the features in the target feature vector to grounding fault monitoring is greater than the preset contribution threshold, increase the weight of one of the features; when the contribution of one of the features in the target feature vector to grounding fault monitoring is less than the preset contribution threshold, decrease the weight of one of the features.

[0084] The preset contribution threshold can be set according to the actual situation.

[0085] When the contribution of one of the features in the target feature vector to grounding fault monitoring is greater than the preset contribution threshold, it indicates that the importance of this feature is relatively high during the grounding fault monitoring process. At this time, the weight of this feature can be increased.

[0086] When the contribution of one of the features in the target feature vector to grounding fault monitoring is less than the preset contribution threshold, it indicates that the importance of this feature is relatively low during the grounding fault monitoring process. At this time, the weight of this feature can be decreased.

[0087] In this embodiment, dynamically adjust the weights of the features according to the size relationship between the contribution of each feature in the target feature vector to grounding fault monitoring and the preset contribution threshold, which can improve the adaptability and accuracy of grounding fault monitoring of the low-voltage DC system.

[0088] To better understand the above method, the following details an application embodiment of the grounding fault monitoring method for the low-voltage DC system of this application.

[0089] Traditional grounding fault monitoring (insulation monitoring of low-voltage DC systems) mainly uses the following three methods:

[0090] (1) Balanced bridge method: By detecting the balance of the positive and negative pole voltages to the ground, judge the insulation state of the low-voltage DC system, but this method cannot locate the specific fault branch.

[0091] (2) Low-frequency injection method: Inject low-frequency signals into the low-voltage DC system. By detecting the current change in the signal loop, the grounding location is judged, but it is vulnerable to environmental interference and requires additional hardware support.

[0092] (3) Through voltage change and zero-sequence current detection, grounding fault detection is realized, but the detection accuracy is insufficient under complex grounding faults, and the detection logic cannot be dynamically optimized.

[0093] In summary, the traditional grounding fault monitoring method for low-voltage DC systems only monitors the overall system insulation resistance of the low-voltage DC system grounding fault monitoring. It relies on manual inspection of each branch one by one. Under complex working conditions (such as multi-point grounding, high-resistance grounding), the monitoring accuracy is low, and it is easy to misjudge or miss judgment. Moreover, it does not monitor in combination with the branch operation status (such as the on / off position of the air switch), has poor adaptability to the parameter changes of the low-voltage DC system, and is difficult to dynamically adjust the monitoring logic.

[0094] The technical solution provided in this embodiment aims to solve the problems of insufficient accuracy, poor adaptability, and lack of real-time performance existing in the traditional technology for grounding fault monitoring in low-voltage DC systems. By means of big data analysis and dynamic optimization of the fault determination algorithm, the accuracy and real-time performance of grounding fault monitoring are improved. Among them, the fault determination logic used in the grounding fault monitoring process of the low-voltage DC system can be called the fault determination algorithm.

[0095] Step 1: Real-time acquisition and storage of multi-dimensional data:

[0096] Data source:

[0097] The real-time leakage current of each branch in the low-voltage DC system ( );

[0098] The operating current of each branch in the low-voltage DC system ( ) and the on / off position status (Boolean quantity S) of the air switch.

[0099] Storage method:

[0100] Record data in a time series database with a time resolution ≤ 100 ms.

[0101] Step 2: Construction of a typical grounding test feature library:

[0102] Typical grounding test scenarios can include end grounding scenarios and midpoint grounding scenarios. The end grounding scenario can connect a fixed resistor at the end of the branch (such as the breaker mechanism box) (typical value 10 kΩ - 100 kΩ); the midpoint grounding scenario can connect a fixed resistor in the middle of the branch (such as inside the switch cabinet) .

[0103] Feature extraction:

[0104] Leakage current amplitudes of branches with different grounding types (grounding positions) , leakage current phases (relative to the system voltage) and the change rate of the operating current to form eigenvectors corresponding to branches of different grounding types ; The typical grounding test feature library can be obtained according to the eigenvectors corresponding to branches of different grounding types.

[0105] Step 3, Fault determination algorithm logic:

[0106] When the insulation resistance value of the low-voltage DC system is monitored to be less than the preset resistance threshold (e.g., R_alert < 50 kΩ), the following process is triggered:

[0107] ① Candidate branch screening:

[0108] Branches with the air switch in the closed state (S = 1) can be determined as initial branches; based on the initial branches, the set of initial branches in the operating state in the low-voltage DC system can be obtained.

[0109] When the change rate of the operating current of the initial branches in the set of initial branches is less than the preset change threshold, it indicates that the false alarm probability of determining the initial branches as suspected grounding branches is relatively low. At this time, it can be determined that the initial branches meet the conditions for starting the determination of suspected grounding branches. The initial branches that meet the conditions for starting the determination of suspected grounding branches can be used as candidate branches to obtain the candidate branch set .

[0110] ② Similarity (also called feature matching degree) calculation:

[0111] For any candidate branch in the candidate branch set , the similarity between the candidate branch and any grounding type branch in the typical grounding test feature library can be calculated based on the differences between the leakage current amplitude, leakage current phase, and the change rate of the operating current of the candidate branch monitored in real time and those of any grounding type branch in the typical grounding test feature library.

[0112] Specifically, the weights corresponding to the leakage current amplitude , the weight corresponding to the leakage current phase and the weight corresponding to the change rate of the operating current can be optimized and set according to the test data of the low-voltage DC system.

[0113] Based on the leakage current amplitude of the candidate branch monitored in real time , leakage current phase And the rate of change of operating current , the amplitude of the leakage current of any grounding type branch in the typical grounding test feature library , the phase of the leakage current and the operating current to obtain the corresponding differences of the leakage current amplitude, the leakage current phase, and the rate of change of operating current respectively.

[0114] The weights and differences corresponding to the leakage current amplitude, the leakage current phase, and the rate of change of operating current can be multiplied and then added to obtain the similarity between the candidate branch and any grounding type branch in the typical grounding test feature library , as shown in Equation (1).

[0115] (1)

[0116] ③ Dynamic threshold determination:

[0117] According to the actual situation, a first preset similarity threshold and a preset deviation threshold can be set. For example, the first preset similarity threshold can be set to 0.2, and the preset deviation threshold can be set to 10%.

[0118] When the similarity between the candidate branch and one of the grounding type branches is less than the first preset similarity threshold , and the deviation between the operating current of the candidate branch and the operating current of one of the grounding type branches is less than the preset deviation threshold, it indicates that the candidate branch may have a grounding fault. At this time, the candidate branch can be determined as a suspected grounding branch.

[0119] ③ Topology verification:

[0120] According to the branch-level topology relationship of the low-voltage DC system, the downstream branch in the suspected grounding branch (such as the similarity of the end grounding branch is lower) can be determined as the target grounding branch with a grounding probability greater than the preset grounding probability threshold.

[0121] Step 4. Anti-interference optimization:

[0122] Phase synchronization correction: The phase of the leakage current can be analyzed by the Fast Fourier Transform (FFT) to eliminate the harmonic interference of the low-voltage DC system.

[0123] Load fluctuation filtering: If the rate of change of operating current exceeds the change threshold (such as ±5% / s), the determination of the suspected grounding branch is postponed to avoid false alarms.

[0124] Step 5. Optimization of the fault determination algorithm after the target grounding branch is located:

[0125] During actual operation, after determining that the target grounding branch (which can also be called the fault branch) is a real grounding branch, the optimization process of the typical grounding test feature library can be automatically started to further improve the accuracy and efficiency of subsequent grounding fault monitoring in the low-voltage DC system.

[0126] Step 5.1. Fault data recording and analysis:

[0127] Data recording:

[0128] ① Record the real-time leakage current ( ), operating current ( ), breaker status ( ), and fault occurrence time ( ) of the target grounding branch.

[0129] ② Record the grounding resistance value ( ) and grounding location (end or middle) of the target grounding branch.

[0130] Data analysis:

[0131] Extract the features of the fault data of the target grounding branch to form a target feature vector . The target feature vector can also be called the new feature vector.

[0132] Compare the target feature vector with the feature vectors corresponding to each grounding type branch in the typical grounding test feature library and analyze the differences.

[0133] Step 5.2. Dynamic update of the feature library:

[0134] Feature library update rules:

[0135] When the similarity between the target feature vector and the feature vector corresponding to one of the grounding type branches in the typical grounding test feature library is less than the second preset similarity threshold, update the weights ( ) of each feature in the feature vector to update the typical grounding test feature library and reflect the contribution of the target feature vector.

[0136] ② When the similarity between the target feature vector and the feature vector corresponding to one of the grounding type branches in the typical grounding test feature library is greater than the second preset similarity threshold, add the target feature vector to the typical grounding test feature library to use the target feature vector as new reference data to update the typical grounding test feature library.

[0137] Weight optimization:

[0138] Dynamically adjust the weights in the similarity calculation according to the contributions of each feature in the target feature vector to the grounding fault monitoring ( ) to improve the adaptability of the grounding fault monitoring in the low-voltage DC system.

[0139] ② Machine learning algorithms (such as the gradient descent method) can be used to optimize the weights of each feature to make the similarity calculation more accurate.

[0140] Step 5.3, Fault determination optimization:

[0141] Optimization rules:

[0142] Optimize the dynamic threshold determination rule in the fault determination process according to the data of the target feature vector.

[0143] When the contribution of one of the features in the target feature vector to the grounding fault monitoring is greater than the preset contribution threshold, the weight of this feature can be increased. For example, when the contribution of the phase feature in the target feature vector to the grounding fault monitoring is greater than the preset contribution threshold, then increase the weight of this feature ( ) )

[0144] When the contribution of one of the features in the target feature vector to the grounding fault monitoring is less than the preset contribution threshold, the weight of this feature can be decreased. For example, when the contribution of the operating current change rate feature in the target feature vector to the grounding fault monitoring is less than the preset contribution threshold, then decrease the weight of this feature ( ) )

[0145] Anti-interference optimization:

[0146] Optimize the parameters of the anti-interference algorithms (such as phase synchronization correction and load fluctuation filtering) according to the interference features in the target feature vector to improve the anti-interference ability during the grounding fault monitoring of the low-voltage DC system.

[0147] The technical solution provided in this embodiment realizes high-precision, strong real-time performance, and good dynamic adaptability of grounding fault monitoring and grounding fault location by real-time monitoring the leakage current, operating current, and air switch status of each branch in the low-voltage DC system, and combining big data analysis and dynamic optimization of the fault determination algorithm.

[0148] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0149] Based on the same inventive concept, an embodiment of the present application also provides a low-voltage DC system grounding fault monitoring device for implementing the above-mentioned low-voltage DC system grounding fault monitoring method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the low-voltage DC system grounding fault monitoring device provided below can refer to the limitations on the low-voltage DC system grounding fault monitoring method in the above text, and will not be repeated here.

[0150] In an exemplary embodiment, as Figure 4 shown, a low-voltage DC system grounding fault monitoring device is provided, where:

[0151] An initial branch set acquisition module 401, configured to obtain an initial branch set in the running state in the low-voltage DC system according to the on-off state of the air switches of each branch in the low-voltage DC system when it is detected that the insulation resistance value of the low-voltage DC system is less than a preset resistance threshold;

[0152] A candidate branch set acquisition module 402, configured to obtain a candidate branch set according to whether the initial branches in the initial branch set meet the conditions for starting to determine suspected grounding branches;

[0153] A similarity acquisition module 403, configured to calculate the similarity between any candidate branch in the candidate branch set and any grounding type branch in the typical grounding test feature library according to the leakage current amplitude, leakage current phase, and operating current change rate;

[0154] A suspected grounding branch determination module 404, configured to determine the candidate branch as a suspected grounding branch when the similarity between the candidate branch and one of the grounding type branches is less than a first preset similarity threshold, and the deviation between the operating current of the candidate branch and the operating current of the one of the grounding type branches is less than a preset deviation threshold;

[0155] A target grounding branch determination module 405, configured to determine a target grounding branch with a grounding probability greater than a preset grounding probability threshold according to the suspected grounding branch and the branch - level topology relationship of the low - voltage DC system.

[0156] In one embodiment, the candidate branch set acquisition module 402 is further configured to: when the change rate of the operating current of an initial branch in the initial branch set is less than a preset change threshold, determine that the initial branch meets the condition for starting the determination of the suspected grounding branch; and obtain a candidate branch set according to the initial branches that meet the condition for starting the determination of the suspected grounding branch.

[0157] In one embodiment, the similarity acquisition module 403 is further configured to: obtain the weights corresponding to the leakage current amplitude, leakage current phase, and operating current change rate respectively; according to the differences between the leakage current amplitude, leakage current phase, and operating current change rate of the candidate branch and the leakage current amplitude, leakage current phase, and operating current of any grounding - type branch in the typical grounding test feature library, obtain the differences corresponding to the leakage current amplitude, leakage current phase, and operating current change rate respectively; multiply the weights corresponding to the leakage current amplitude, leakage current phase, and operating current change rate respectively by the differences and then perform an addition process to obtain the similarity between the candidate branch and any grounding - type branch in the typical grounding test feature library.

[0158] In one embodiment, the target grounding branch determination module 405 is further configured to: obtain the branch - level topology relationship of the low - voltage DC system; according to the branch - level topology relationship of the low - voltage DC system, determine the downstream branches in the suspected grounding branches as target grounding branches with a grounding probability greater than a preset grounding probability threshold.

[0159] In one embodiment, the device further includes a feature library update module, configured to: when it is determined that the target grounding branch is a true grounding branch, obtain the leakage current amplitude, leakage current phase, operating current, and operating current change rate of the target grounding branch as a target feature vector; when the similarity between the target feature vector and the feature vector corresponding to any grounding - type branch in the typical grounding test feature library is less than a second preset similarity threshold, update the weights of the features in the feature vector to update the typical grounding test feature library; the features include leakage current amplitude, leakage current phase, operating current, and operating current change rate; when the similarity between the target feature vector and the feature vector corresponding to any grounding - type branch in the typical grounding test feature library is greater than the second preset similarity threshold, add the target feature vector to the typical grounding test feature library to update the typical grounding test feature library.

[0160] In one embodiment, the feature library update module is further configured to: when the contribution of one of the features in the target feature vector to the grounding fault monitoring is greater than a preset contribution threshold, increase the weight of the one feature; when the contribution of one of the features in the target feature vector to the grounding fault monitoring is less than the preset contribution threshold, decrease the weight of the one feature.

[0161] Each module in the above-mentioned grounding fault monitoring device for low-voltage DC systems can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0162] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data of the embodiments of the grounding fault monitoring method for low-voltage DC systems. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a grounding fault monitoring method for low-voltage DC systems.

[0163] Those skilled in the art can understand that Figure 5 the structure shown in

[0164] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0165] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

[0166] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

[0167] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0168] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0169] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.

[0170] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for monitoring grounding faults in a low-voltage DC system, characterized in that, The method includes: When it is detected that the insulation resistance value of the low-voltage DC system is less than a preset resistance threshold, an initial branch set in the running state in the low-voltage DC system is obtained according to the on-off state of the air switch of each branch in the low-voltage DC system; A candidate branch set is obtained according to whether the initial branches in the initial branch set meet the conditions for starting the determination of suspected grounding branches; For any candidate branch in the candidate branch set, the similarity between the candidate branch and any grounding type branch in the typical grounding test feature library is calculated according to the leakage current amplitude, leakage current phase, and operating current change rate; When the similarity between the candidate branch and one of the grounding type branches is less than a first preset similarity threshold, and the deviation between the operating current of the candidate branch and the operating current of the one of the grounding type branches is less than a preset deviation threshold, the candidate branch is determined as a suspected grounding branch; According to the suspected grounding branch and the branch-level topological relationship of the low-voltage DC system, a target grounding branch with a grounding probability greater than a preset grounding probability threshold is determined.

2. The method according to claim 1, wherein The obtaining of the candidate branch set according to whether the initial branches in the initial branch set meet the conditions for starting the determination of suspected grounding branches includes: When the operating current change rate of the initial branches in the initial branch set is less than a preset change threshold, it is determined that the initial branches meet the conditions for starting the determination of suspected grounding branches; A candidate branch set is obtained according to the initial branches that meet the conditions for starting the determination of suspected grounding branches.

3. The method according to claim 1, characterized in that The calculating of the similarity between the candidate branch and any grounding type branch in the typical grounding test feature library according to the leakage current amplitude, leakage current phase, and operating current change rate includes: Obtaining the respective weights corresponding to the leakage current amplitude, leakage current phase, and operating current change rate; According to the differences between the leakage current amplitude, leakage current phase, and operating current change rate of the candidate branch and the amplitude of the leakage current, phase of the leakage current, and operating current of any grounding type branch in the typical grounding test feature library, the respective differences corresponding to the leakage current amplitude, leakage current phase, and operating current change rate are obtained; The respective weights and differences corresponding to the leakage current amplitude, leakage current phase, and operating current change rate are multiplied and then added to obtain the similarity between the candidate branch and any grounding type branch in the typical grounding test feature library.

4. The method according to claim 1, characterized in that, The determining of a target grounding branch with a grounding probability greater than a preset grounding probability threshold according to the suspected grounding branch and the branch-level topological relationship of the low-voltage DC system includes: Obtaining the branch-level topological relationship of the low-voltage DC system; According to the branch-level topological relationship of the low-voltage DC system, the downstream branches in the suspected grounding branches are determined as target grounding branches with a grounding probability greater than a preset grounding probability threshold.

5. The method according to claim 1, characterized in that, After determining the target grounding branch with a grounding probability greater than a preset grounding probability threshold, the method further includes: When it is determined that the target grounding branch is a real grounding branch, the leakage current amplitude, leakage current phase, operating current, and operating current change rate of the target grounding branch are obtained as a target feature vector; When the similarity between the target feature vector and the feature vector corresponding to one of the grounding type branches in the typical grounding test feature library is less than the second preset similarity threshold, update the weights of the features in the feature vector to update the typical grounding test feature library; the features include leakage current amplitude, leakage current phase, operating current, and operating current change rate. When the similarity between the target feature vector and the feature vector corresponding to one of the grounding type branches in the typical grounding test feature library is greater than the second preset similarity threshold, add the target feature vector to the typical grounding test feature library to update the typical grounding test feature library.

6. The method according to claim 5, wherein The updating the weights of the features in the feature vector includes: When the contribution of one of the features in the target feature vector to the grounding fault monitoring is greater than the preset contribution threshold, increase the weight of the one feature. When the contribution of one of the features in the target feature vector to the grounding fault monitoring is less than the preset contribution threshold, decrease the weight of the one feature.

7. A grounding fault monitoring device for a low-voltage DC system, characterized in that, The device includes: An initial branch set acquisition module, configured to obtain an initial branch set in the operating state in the low-voltage DC system according to the on / off state of the air switches of each branch in the low-voltage DC system when it is detected that the insulation resistance value of the low-voltage DC system is less than the preset resistance threshold. A candidate branch set acquisition module, configured to obtain a candidate branch set according to whether the initial branches in the initial branch set meet the conditions for starting the determination of suspected grounding branches. A similarity acquisition module, configured to calculate the similarity between any candidate branch in the candidate branch set and any grounding type branch in the typical grounding test feature library according to the leakage current amplitude, leakage current phase, and operating current change rate. A suspected grounding branch determination module, configured to determine the candidate branch as a suspected grounding branch when the similarity between the candidate branch and one of the grounding type branches is less than the first preset similarity threshold and the deviation between the operating current of the candidate branch and the operating current of the one grounding type branch is less than the preset deviation threshold. A target grounding branch determination module, configured to determine a target grounding branch with a grounding probability greater than the preset grounding probability threshold according to the suspected grounding branch and the branch-level topology relationship of the low-voltage DC system.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the 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 by the processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.

Images