Fault detection method based on current break variable

Abstract

The invention discloses a fault detection method based on a current break variable, and relates to the technical field of power system fault detection, and the method comprises the steps: obtaining three-phase current data and relative ground potential data, calculating the three-phase current break variable and zero-sequence current, and constructing a fault detection model. And judging the three-phase current data and the relative ground potential data through a fault detection model, outputting a fault detection result, generating an alarm signal, and starting a protection mechanism. By acquiring the three-phase current data and the relative ground potential data and calculating the three-phase current break variable and the zero-sequence current, accurate monitoring of the current change when the fault occurs is realized, the fault detection model is constructed, and the fault detection result is accurately output by comprehensively judging the three-phase current data and the relative ground potential data, so that the fault detection accuracy is improved. The efficiency and the accuracy of fault identification are improved; an alarm signal is generated according to a detection result, a protection mechanism is started, a fault area is effectively isolated, fault diffusion is prevented, and stable operation of the power distribution network is guaranteed.

Description

Technical Field

[0001] The invention relates to the technical field of power system fault detection, in particular to a fault detection method based on current mutation. Background Art

[0002] Traditional fault detection methods mainly rely on direct measurement of sensors or prediction through models. These methods face problems such as low efficiency, high time cost and insufficient accuracy in practical applications. In addition, model-based fault identification methods have extremely high requirements for system modeling and parameter setting, and are easily affected by the external environment, resulting in errors in fault identification results.

[0003] To address this problem, a fault detection method based on current mutation is proposed, aiming to improve the efficiency of fault detection, reduce time cost, improve detection accuracy, and enhance its applicability. Summary of the invention

[0004] In view of the problems of low efficiency, high time cost and insufficient accuracy in existing fault detection methods, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to improve the efficiency of fault detection and reduce the time cost, and improve the accuracy and applicability of fault identification through a method for detecting a sudden change in current.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a fault detection method based on current mutation, which includes obtaining three-phase current data and relative ground potential data of the distribution network operation, and calculating the current mutation and zero-sequence current of the three phases; constructing a fault detection model based on the current mutation and the zero-sequence current, judging the three-phase current data and the relative ground potential data through the fault detection model, and outputting the fault detection result; generating an alarm signal according to the fault detection result, and starting a protection mechanism.

[0008] As a preferred solution of the fault detection method of the current mutation amount of the present invention, wherein: the fault detection model is constructed based on the support vector machine algorithm; the fault detection model includes a fault start criterion module and a fault type judgment module; the fault start criterion module includes a current start criterion and a voltage start criterion; the specific formula of the current start criterion is as follows:

[0009] |Δi K |=|i K -i K-N |>|ΔI s.set |;

[0010] Among them, ΔiK is the total current mutation of the Kth line, N is the number of sampling points in one power frequency cycle, ΔI s,set Current start criterion threshold setting value, i K is the current sampling value of the Kth circuit.

[0011] The specific formula of the voltage start criterion is as follows:

[0012] |u K -u K-N |>kU N ;

[0013] Among them, u K is the voltage sampling value of the Kth line, k is the voltage ratio before and after the fault line, U N is the total voltage sampling value of the sampling points N in the power frequency cycle, where N is the number of sampling points in one power frequency cycle.

[0014] As a preferred solution of the fault detection method of the current mutation quantity of the present invention, it also includes: when the sampling value of any phase meets the current start-up criterion and the voltage start-up criterion, and the fault start-up condition X meets the start-up number, the electrical quantity integrated sensor performs fault type diagnosis through the fault detection model, outputs the fault detection result, and introduces an auxiliary diagnosis criterion on the original fault start-up criterion module; if the fault start-up condition X does not meet the start-up number once, the fault start-up condition X is zero, and the number of fault start-up conditions X is re-determined; the specific formula of the auxiliary diagnosis criterion is as follows:

[0015] m|Δi B -Δi C |<|Δi B -Δi A | and m|Δi B -Δi C |<|Δi C -Δi A |;

[0016] Among them, m is the setting multiple, Δi B is the sudden change of the grounding phase B current, Δi C is the sudden change of the grounded phase C current, Δi A is the sudden change of grounding phase A current.

[0017] As a preferred solution of the fault detection method of current mutation amount described in the present invention, wherein: the fault detection result includes the fault type; the fault type includes single-phase grounding fault, two-phase grounding short circuit fault, two-phase short circuit fault and three-phase short circuit fault; the single-phase grounding fault includes, when the zero-sequence current is greater than the threshold value and the current mutation amount meets the auxiliary diagnosis criterion, a single-phase grounding fault occurs in the system, wherein the phase with the smallest current mutation amount is the fault phase; when only one phase voltage drops and the current mutation amount of two phases meets the auxiliary diagnosis criterion, a single-phase grounding fault occurs in the system, wherein the phase with reduced voltage is the fault phase; when the voltage of two phases decreases while the voltage of another phase increases, and two-phase grounding and two-phase short circuit do not meet the fault start criterion module, if the current mutation amount meets the auxiliary diagnosis criterion, a single-phase grounding fault occurs in the system, wherein the phase with the smallest current mutation amount is the fault phase.

[0018] As a preferred solution of the fault detection method of current mutation amount described in the present invention, wherein: the two-phase ground short circuit fault includes, when the two-phase voltage drops and the value of the maximum current mutation amount of the two-phase is 10 times the minimum value of the current mutation amount and is greater than 40A, then the system has a two-phase ground short circuit fault, wherein the phase with the minimum current mutation amount is a non-fault phase; the two-phase short circuit fault includes, when the two-phase voltage drops and the maximum current mutation amount of the two-phase current is 100 times that of the phase with the minimum current mutation amount and the zero-sequence current is less than a preset threshold, the system has a two-phase short circuit fault, wherein the phase with the minimum current mutation amount is a non-fault phase; the three-phase short circuit fault includes, when the difference of the three-phase current mutation amount is equal to zero, that is, the ratio of the absolute value of the maximum value of the difference of the two-phase current mutation amount to the absolute value of the minimum value is less than 10 and the zero-sequence current is less than the set threshold, then it is determined that the system has a three-phase short circuit fault.

[0019] As a preferred solution of the fault detection method of the current mutation amount of the present invention, wherein: the current mutation amount is calculated by high-frequency sampling of the current signal to calculate the instantaneous rate of current change; the current mutation amount includes single-phase current mutation amount, two-phase current mutation amount and three-phase current mutation amount; the specific formula of the current mutation amount is as follows:

[0020]

[0021] Among them, Δi K,A is the Kth phase current mutation of line A, Δi K,B is the Kth phase current mutation of line B, Δi K,C is the current mutation of phase C of the Kth line, i K A is the current value of phase A of the line after a fault occurs in the distribution network, is the current value of phase B of line after a fault occurs in the distribution network, is the current value of phase C of the line after a fault occurs in the distribution network, i0,K is the zero-sequence current sampling value of the Kth line, and N is the number of sampling points in one power frequency cycle.

[0022] As a preferred solution of the fault detection method for current mutation of the present invention, the protection mechanism is to determine the fault location according to the fault type, select the protection strategy, send fault information and execute protection instructions to the distribution network control system, and isolate the fault area; the protection operation includes but is not limited to circuit breaker tripping, fault isolation and load transfer.

[0023] In the second aspect, an embodiment of the present invention provides a fault detection system based on current mutation, which includes: a calculation module, which is used to obtain three-phase current data and relative ground potential data of the distribution network operation, and calculate the current mutation and zero-sequence current of the three phases; a construction module, which constructs a fault detection model based on the current mutation and the zero-sequence current, judges the three-phase current data and the relative ground potential data through the fault detection model, and outputs the fault detection result; a protection mechanism module, which is used to generate an alarm signal according to the fault detection result and start the protection mechanism.

[0024] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the current mutation fault detection method as described in the first aspect of the present invention are implemented.

[0025] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the current mutation fault detection method as described in the first aspect of the present invention are implemented.

[0026] The beneficial effects of the present invention are as follows: the present invention obtains three-phase current data and relative ground potential data, calculates the three-phase current mutation and zero-sequence current, realizes accurate monitoring of current changes when a fault occurs, builds a fault detection model, and accurately outputs fault detection results through comprehensive judgment of the three-phase current data and relative ground potential data, thereby improving the efficiency and accuracy of fault identification; generates an alarm signal according to the detection result, and starts a protection mechanism to effectively isolate the fault area, prevent the fault from spreading, and ensure the stable operation of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative work. Among them:

[0028] Figure 1 This is a fault judgment start-up flow chart of the fault detection method of current mutation quantity in Example 1.

[0029] Figure 2 This is a fault judgment flow chart of the fault detection method of current mutation quantity in Example 1. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0031] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0032] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0033] Example 1

[0034] Reference Figure 1-2 , which is the first embodiment of the present invention, and provides a fault detection method based on current mutation, including:

[0035] S1: Obtain the three-phase current data and relative ground potential data of the distribution network, and calculate the current mutation and zero-sequence current of the three phases.

[0036] Specifically, the electrical quantity integrated sensor installed on the overhead line can collect limited line information, including the value of each phase current of the line before and after the distribution network fault occurs. The collected data information is mathematically processed to obtain the average value of the current mutation amount; the current mutation amount is calculated by high-frequency sampling of the current signal and the instantaneous rate of current change; the specific formula of the current mutation amount is as follows:

[0037]

[0038] Among them, Δi K,A is the Kth phase current mutation of line A, Δi K,B is the Kth current mutation of phase B of line, Δi K,C is the current mutation of phase C of the Kth line, is the current value of phase A of the line after a fault occurs in the distribution network, is the current value of phase B of line after a fault occurs in the distribution network, is the current value of phase C of the line after a fault occurs in the distribution network, i 0,K is the zero-sequence current sampling value of the Kth line, and N is the number of sampling points in one power frequency cycle.

[0039] It should be noted that the collected data information is mathematically processed to obtain the average value of the current mutation, which is represented by a, b and c respectively. The meanings of other variables are shown in Table 1.

[0040] Table 1 Variable name table

[0041]

[0042] Furthermore, when the system is operating normally, the mutation of the three-phase current is basically zero. When a fault occurs in the system, the current will change more than when it is operating normally. A ground fault will also cause a zero-sequence current. The fault can be detected based on the change in current. K,A , Δi K,B , Δi K,C The current mutation includes single-phase current mutation, two-phase current mutation and three-phase current mutation.

[0043] Furthermore, when a single-phase grounding fault occurs, the relevant formula for the single-phase current mutation is as follows:

[0044]

[0045] Among them, U f|0| is the voltage before the fault occurs, Z f is the total ground impedance, Z ∑(A) is the ground impedance of phase A before the fault occurs, Z ∑(B) is the ground impedance of phase B before the fault occurs, Z ∑(C) is the ground impedance of phase C before the fault occurs.

[0046] Specifically, when two phases are short-circuited to ground, the specific formula for the two-phase current mutation is as follows:

[0047]

[0048] Among them, α is the impedance value between the fault point and the ground.

[0049] Furthermore, when two phases are short-circuited, the specific formula for the two-phase current mutation is as follows:

[0050]

[0051] Among them, U f |0| is the voltage before the fault occurs.

[0052] Furthermore, when the three phases are short-circuited, the specific formula for the three-phase current mutation is as follows:

[0053]

[0054] Among them, U f |0| is the voltage before the fault occurs.

[0055] It should be noted that when a single-phase grounding fault occurs in the distribution network, the line current mutation of the fault phase is zero, while the current mutation of the non-grounded phase is almost equal to the absolute value of three times the zero-sequence current; in the case of a two-phase grounding short-circuit fault, the current mutation of the grounding fault phase changes significantly, while the current mutation of the healthy phase is close to the absolute value of the zero-sequence current; for a two-phase short-circuit fault, the current mutation of the fault phase is similar and almost equal, while the current mutation of the healthy phase is basically zero; in the case of a three-phase short-circuit fault, the current mutation of each phase is equal. Before diagnosing the fault type, the electrical quantity integrated sensor first needs to determine whether the distribution network has a fault, that is, to determine the starting criterion for fault diagnosis. Only after confirming that the distribution network has a fault can the fault type be further diagnosed and analyzed.

[0056] S2: A fault detection model is constructed based on the current mutation and zero-sequence current. The three-phase current data and relative ground potential data are judged by the fault detection model, and the fault detection result is output.

[0057] Specifically, the fault detection model is constructed based on the support vector machine algorithm; the fault detection model includes a fault start criterion module and a fault type judgment module; the fault start criterion module includes a current start criterion and a voltage start criterion; the specific formula of the current start criterion is as follows:

[0058] |Δi K |=|i K -i K-N |>|ΔI s.set |;

[0059] Among them, Δi K is the total current mutation of the Kth line, N is the number of sampling points in one power frequency cycle, ΔI s,set Current start criterion threshold setting value, i K is the current sampling value of the Kth circuit.

[0060] Furthermore, the specific formula for voltage start criterion is as follows:

[0061] |u K -u K-N |>kU N ;

[0062] Among them, u K is the voltage sampling value of the Kth line, k is the voltage ratio before and after the fault line, U N is the total voltage sampling value of the sampling points N in the power frequency cycle, where N is the number of sampling points in one power frequency cycle.

[0063] Furthermore, when the sampling value of any phase meets the current start criterion and the voltage start criterion, and the fault start condition X meets the start times, the electrical quantity integrated sensor performs fault type diagnosis through the fault detection model, outputs the fault detection result, and introduces an auxiliary diagnosis criterion on the original fault start criterion module; if the fault start condition X does not meet the start times at one time, the fault start condition X is zero, and the number of fault start conditions X is re-determined;

[0064] Specifically, the specific formula for auxiliary diagnosis criteria is as follows:

[0065] m|Δi B -Δi C |<|Δi B -Δi A | and m|Δi B -Δi C |<|Δi C -Δi A |;

[0066] Among them, m is the setting multiple, Δi B is the sudden change of the grounding phase B current, Δi C is the sudden change of the grounded phase C current, Δi A is the sudden change of grounding phase A current.

[0067] It should be noted that the fault detection result includes the fault type; the fault type includes a single-phase grounding fault, a two-phase grounding short-circuit fault, a two-phase short-circuit fault and a three-phase short-circuit fault.

[0068] Furthermore, the single-phase grounding fault includes: when the zero-sequence current is greater than the threshold value and the current mutation amount meets the auxiliary diagnosis criterion, the system has a single-phase grounding fault, wherein the phase with the smallest current mutation amount is the fault phase; when only one phase voltage drops and the current mutation amount of two phases meets the auxiliary diagnosis criterion, the system has a single-phase grounding fault, wherein the voltage reduction phase is the fault phase;

[0069] Furthermore, when the voltage of two phases decreases while the voltage of another phase increases, and the two-phase grounding and two-phase short circuit do not meet the fault start judgment module, if the current mutation meets the auxiliary diagnosis judgment, a single-phase grounding fault occurs in the system, and the phase with the smallest current mutation is the fault phase.

[0070] Specifically, a two-phase ground short circuit fault includes: when the two-phase voltage drops and the value of the maximum current mutation amount of the two phases is 10 times the minimum current mutation amount and is greater than 40A, a two-phase ground short circuit fault occurs in the system, where the phase with the minimum current mutation amount is the non-fault phase.

[0071] Furthermore, a two-phase short circuit fault includes that when the two-phase voltage drops, and the maximum current mutation amount of the two-phase current is 100 times that of the phase with the smallest current mutation amount and the zero-sequence current is less than a preset threshold, a two-phase short circuit fault occurs in the system, wherein the phase with the smallest current mutation amount is a non-fault phase;

[0072] Furthermore, a three-phase short circuit fault includes, when the difference in the three-phase current mutation amount is equal to zero, that is, the ratio of the absolute value of the maximum value to the absolute value of the minimum value of the difference in the two-phase current mutation amount is less than 10 and the zero-sequence current is less than the set threshold, then it is determined that the system has a three-phase short circuit fault.

[0073] S3: Generate an alarm signal based on the fault detection result and start the protection mechanism.

[0074] Specifically, the protection mechanism determines the fault location according to the fault type, selects the protection strategy, sends fault information and executes protection instructions to the distribution network control system, and isolates the fault area; protection operations include but are not limited to circuit breaker tripping, fault isolation and load transfer.

[0075] Furthermore, the present embodiment also provides a fault detection system based on current mutation, including: a calculation module, used to obtain three-phase current data and relative ground potential data of the distribution network operation, and calculate the three-phase current mutation and zero-sequence current; a construction module, which constructs a fault detection model based on the current mutation and zero-sequence current, judges the three-phase current data and relative ground potential data through the fault detection model, and outputs the fault detection result; a protection mechanism module, which is used to generate an alarm signal according to the fault detection result and start the protection mechanism.

[0076] This embodiment also provides a computer device, which is suitable for the current mutation fault detection method, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the current mutation fault detection method proposed in the above embodiment.

[0077] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0078] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the following steps are implemented: obtaining three-phase current data and relative ground potential data of the distribution network operation, and calculating the current mutation amount and zero-sequence current of the three phases; constructing a fault detection model based on the current mutation amount and the zero-sequence current, judging the three-phase current data and the relative ground potential data through the fault detection model, and outputting a fault detection result; generating an alarm signal according to the fault detection result, and starting a protection mechanism.

[0079] In summary, the present invention obtains three-phase current data and relative ground potential data, calculates the current mutation amount and zero-sequence current of the three phases, realizes accurate monitoring of current changes when a fault occurs, constructs a fault detection model, and accurately outputs the fault detection result through comprehensive judgment of the three-phase current data and relative ground potential data, thereby improving the efficiency and accuracy of fault identification; generates an alarm signal according to the detection result, and starts a protection mechanism to effectively isolate the fault area, prevent the fault from spreading, and ensure the stable operation of the distribution network.

[0080] Example 2

[0081] Referring to Table 2, which is the second embodiment of the present invention, this embodiment provides a fault detection method based on current mutation. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0082] Specifically, the experimental equipment was arranged, including three-phase current sensors, relative ground potential measuring instruments and data acquisition systems; 10 lines with different load levels and fault characteristics were selected for monitoring, with a data sampling frequency of 1kHz and a sampling period of 0.02 seconds. The experiment simulated multiple fault types (including single-phase ground fault, two-phase ground short-circuit fault, two-phase short-circuit fault and three-phase short-circuit fault) to record current and voltage data under different fault conditions.

[0083] Furthermore, during the experiment, the three-phase current data and relative ground potential data of each line in normal operation and fault state were obtained, and the current mutation and zero-sequence current of each phase were calculated. Subsequently, the fault detection model constructed by the support vector machine algorithm was used to analyze these data. The fault detection model judgment results include fault type identification and corresponding alarm signal generation, and the corresponding protection mechanism (such as circuit breaker tripping and load transfer) is activated.

[0084] Furthermore, for comparative experiments, the traditional fault detection technology based on single current criterion was selected and applied under the same experimental conditions to verify the advantages of the new fault detection model. During the experiment, the data such as the accuracy, response time, false alarm rate and missed alarm rate of fault detection were recorded to comprehensively evaluate the performance of the invention.

[0085] Specifically, the experimental results are shown in Table 2. The new method shows significant advantages in both accuracy and response time. Specifically, in the detection of single-phase ground fault, the accuracy of the traditional method is 85%, while the new method reaches 98%, and the response time is shortened from 30 milliseconds of the traditional method to 20 milliseconds. In the detection of two-phase ground short-circuit fault, the accuracy of the traditional method is 82%, and the new method is improved to 96%, and the response time is reduced from 35 milliseconds to 22 milliseconds.

[0086] Table 2 Comparison table between the present invention and the prior art

[0087]

[0088] Furthermore, in the detection of two-phase short-circuit faults, the accuracy of the traditional method was 80%, while the new method increased to 94%, and the response time was shortened from 40 milliseconds to 25 milliseconds. For three-phase short-circuit faults, the accuracy of the traditional method was 88%, while the new method reached 99%, and the response time was further shortened from 28 milliseconds to 18 milliseconds. From the above data, it can be seen that the new method is not only significantly better than the traditional method in terms of accuracy, especially in the detection of key fault types, but also has a significant improvement effect. At the same time, it also shows a faster response speed, thereby better ensuring the stability and safety of the distribution network.

[0089] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A fault detection method based on current mutation, characterized in that: include, Obtain the three-phase current data and relative ground potential data of the distribution network operation, and calculate the three-phase current mutation and zero-sequence current; Building a fault detection model based on the current mutation amount and the zero-sequence current, judging the three-phase current data and the relative ground potential data through the fault detection model, and outputting the fault detection result; An alarm signal is generated according to the fault detection result, and a protection mechanism is started.

2. The fault detection method of current mutation according to claim 1, characterized in that: The fault detection model is constructed based on the support vector machine algorithm; the fault detection model includes a fault start criterion module and a fault type judgment module; the fault start criterion module includes a current start criterion and a voltage start criterion; the specific formula of the current start criterion is as follows: |Δi K |=|i K -i K-N |>|ΔI s.set |; Among them, Δi K is the total current mutation of the Kth line, N is the number of sampling points in one power frequency cycle, ΔI s,set Current start criterion threshold setting value, i K is the current sampling value of the Kth circuit; The specific formula of the voltage start criterion is as follows: u K -u K-N |>kU N ; Among them, u K is the voltage sampling value of the Kth line, k is the voltage ratio before and after the fault line, U N is the total voltage sampling value of the sampling points N in the power frequency cycle, where N is the number of sampling points in one power frequency cycle.

3. The fault detection method of current sudden change according to claim 2, characterized in that: Also includes, When the sampling value of any phase meets the current start criterion and the voltage start criterion, and the fault start condition X meets the start times, the electrical quantity integrated sensor performs fault type diagnosis through the fault detection model, outputs the fault detection result, and introduces auxiliary diagnosis criteria on the original fault start criterion module; If the fault start condition X does not meet the start times at one time, the fault start condition X is zero, and the number of fault start condition X is re-determined; The specific formula of the auxiliary diagnosis criterion is as follows: m|Δi B -Δi C |<|Δi B -Δi A | and m|Δi B -Δi C |<|Δi C -Δi A |; Among them, m is the setting multiple, Δi B is the sudden change of the grounding phase B current, Δi C is the sudden change of the grounded phase C current, Δi A is the sudden change of grounding phase A current.

4. The fault detection method of current sudden change according to claim 3, characterized in that: The fault detection result includes the fault type; the fault type includes a single-phase grounding fault, a two-phase grounding short circuit fault, a two-phase short circuit fault and a three-phase short circuit fault; the single-phase grounding fault includes, When the zero-sequence current is greater than the threshold value and the current mutation quantity meets the auxiliary diagnosis criterion, a single-phase grounding fault occurs in the system, and the phase with the smallest current mutation quantity is the fault phase; When only one phase voltage drops, and the current mutation of two phases meets the auxiliary diagnosis criteria, a single-phase grounding fault occurs in the system, and the phase with reduced voltage is the fault phase; When the voltage of two phases decreases while the voltage of another phase increases, and the two-phase grounding and two-phase short circuit do not meet the fault start judgment module, if the current mutation meets the auxiliary diagnosis judgment, a single-phase grounding fault occurs in the system, and the phase with the smallest current mutation is the fault phase.

5. The fault detection method of current sudden change according to claim 4, characterized in that: The two-phase ground short circuit fault includes: When the two-phase voltage drops and the maximum current mutation value of the two-phase is 10 times the minimum current mutation value and is greater than 40A, a two-phase ground short circuit fault occurs in the system, and the phase with the minimum current mutation value is the non-fault phase; The two-phase short circuit fault includes: When the two-phase voltage drops, and the maximum current mutation of the two-phase current is 100 times that of the phase with the smallest current mutation, and the zero-sequence current is less than the preset threshold, a two-phase short circuit fault occurs in the system, in which the phase with the smallest current mutation is the non-fault phase; The three-phase short circuit fault includes: When the difference in the three-phase current mutation amount is equal to zero, that is, the ratio of the absolute value of the maximum value to the absolute value of the minimum value of the difference in the two-phase current mutation amount is less than 10 and the zero-sequence current is less than the set threshold, it is determined that a three-phase short circuit fault occurs in the system.

6. The fault detection method of current sudden change according to claim 1, characterized in that: The current mutation amount is calculated by high-frequency sampling of the current signal to calculate the instantaneous rate of current change; the current mutation amount includes single-phase current mutation amount, two-phase current mutation amount and three-phase current mutation amount; the specific formula of the current mutation amount is as follows: Among them, Δi K,A is the Kth phase current mutation of line A, Δi K,B is the Kth current mutation of phase B of line, Δi K,C is the current mutation of phase C of the Kth line, is the current value of phase A of the line after a fault occurs in the distribution network, is the current value of phase B of line after a fault occurs in the distribution network, is the current value of phase C of the line after a fault occurs in the distribution network, i 0,K is the zero-sequence current sampling value of the Kth line, and N is the number of sampling points in one power frequency cycle.

7. The fault detection method of current sudden change according to claim 1, characterized in that: The protection mechanism determines the fault location according to the fault type, selects the protection strategy, sends fault information and executes protection instructions to the distribution network control system, and isolates the fault area; the protection operation includes but is not limited to circuit breaker tripping, fault isolation and load transfer.

8. A fault detection system based on current mutation, based on the fault detection method of current mutation according to any one of claims 1 to 7, characterized in that: Also includes, A calculation module is used to obtain the three-phase current data and relative ground potential data of the distribution network operation, and calculate the three-phase current mutation and zero-sequence current; A construction module is used to construct a fault detection model based on the current mutation amount and the zero-sequence current, judge the three-phase current data and the relative ground potential data through the fault detection model, and output the fault detection result; The protection mechanism module is used to generate an alarm signal according to the fault detection result and start the protection mechanism.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the fault detection method for current sudden change amount according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the fault detection method for current mutation amount according to any one of claims 1 to 7 are implemented.

Images