Method for judging whether power distribution network line has single-phase earth fault

Abstract

The invention discloses a method for judging whether a power distribution network line has a single-phase earth fault, and the method comprises the following steps: S1, obtaining an optimal decomposition layer number and an optimal penalty factor of variational mode decomposition based on an improved dream optimization algorithm; s2, performing optimal variational mode decomposition on a zero-sequence current time sequence output by a power distribution network line to obtain IMF components; wherein the optimal variation mode decomposition adopts the optimal decomposition layer number and the optimal penalty factor; representing the optimal decomposition layer number; and S3, judging whether the power distribution network line has a single-phase earth fault or not based on the IMF components. The judgment accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution networks, and more particularly to a method for determining whether a power distribution network line has a single-phase grounding fault. Background Art

[0002] At present, single-phase grounding faults in distribution networks seriously affect power supply reliability. However, existing methods for determining single-phase grounding faults in distribution networks often suffer from misjudgment problems.

[0003] Therefore, how to provide a method for determining whether a single-phase grounding fault exists in a distribution network line, which can improve the accuracy of the determination, is an urgent problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] In view of this, an object of the present invention is to provide a method for determining whether a single-phase grounding fault exists in a power distribution network line.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, a method for determining whether a single-phase ground fault occurs in a distribution network line is provided, comprising the following steps:

[0007] S1: Based on the improved dream optimization algorithm, the optimal number of decomposition layers and the optimal penalty factor of variational mode decomposition are obtained;

[0008] S2: Perform optimal variational modal decomposition on the zero-sequence current time series output by the distribution network line to obtain IMF components; wherein the optimal variational mode decomposition adopts the optimal number of decomposition layers and the optimal penalty factor; represents the optimal decomposition level;

[0009] S3: Based on The IMF component is used to determine whether there is a single-phase grounding fault in the distribution network line.

[0010] Preferably, S1 specifically includes the following steps:

[0011] S11: Generate initial population ;in, ; M represents the number of individuals in the initial population; individual Includes elements of two dimensions: the number of decomposition layers and the penalty factor;

[0012] S12: Calculate the fitness of all individuals and retain a preset proportion of individuals based on fitness ranking;

[0013] S13: Divide the individuals retained in S12 into several groups, and randomly assign the number of forgetting dimensions to each group; wherein the number of forgetting dimensions is 1 or 2;

[0014] S14: Each group performs T1 grouping iterations on its individuals based on its own forgetting dimension number; where T1 is a positive integer;

[0015] S15: Perform T2 global iterations on the individuals after T1 grouping iterations to obtain the optimal number of decomposition layers and the optimal penalty factor; wherein T2 is a positive integer.

[0016] Preferably, in S11:

[0017] ;

[0018] Where, represents a randomly generated integer in the closed interval [3,15], which represents the number of decomposition levels; represents a random real number in the closed interval [0,1], Represents the penalty factor.

[0019] Preferably, in S12: rank the fitness from large to small, and retain the top 80% of the individuals.

[0020] Preferably, S14 is implemented based on the following formula:

[0021] ;

[0022] Where, ; Q represents the number of groups obtained by S13; ;

[0023] It represents the value of the j-th dimension element of the i-th individual in the q-th group after the t+1-th iteration. When j=1, it represents the number of decomposition levels, and when j=2, it represents the penalty factor.

[0024] It represents the value of the j-th dimension element of the individual with the highest fitness in the q-th group before the t+1-th iteration. When j=1, it represents the number of decomposition layers, and when j=2, it represents the penalty factor.

[0025] Represents a random number between the closed interval [0,1];

[0026] It represents the value of the j-th dimension element of the randomly selected individual in the q-th group after the t-th iteration. When j=1, it represents the number of decomposition levels, and when j=2, it represents the penalty factor.

[0027] It represents the value of the j-th dimension element of the i-th individual in the q-th group after the t-th iteration. When j=1, it represents the number of decomposition levels, and when j=2, it represents the penalty factor.

[0028] represents the set of forgotten dimensions of the qth group;

[0029] When the number of forgotten dimensions of the qth group is equal to 1, or ;

[0030] When the number of forgotten dimensions of the qth group is equal to 2, .

[0031] Preferably, S15 is implemented based on the following formula:

[0032] ;

[0033] ;

[0034] ;

[0035] Where, Indicates the The value of the j-th dimension element of the i-th individual after the iteration;

[0036] Indicates the The value of the j-th dimension element of the individual with the highest fitness before the iteration;

[0037] represents the learning rate;

[0038] Indicates the The upper limit of the value of the j-th dimension element of all individuals after iterations;

[0039] Indicates the The lower limit of the value of the j-th dimension element of all individuals after iterations;

[0040] represents the spiral search term, b represents the curvature constant, and r~U(-1,1) represents the random direction factor obeying the uniform distribution U(-1,1);

[0041] Indicates the The upper limit of the value of the j-th dimension element of all individuals after iterations;

[0042] Represents a randomly generated real number in the closed interval [0,1];

[0043] Indicates the The lower limit of the value of the j-th dimension element of all individuals after iterations;

[0044] When j=1, it indicates the number of decomposition layers, and when j=2, it indicates the penalty factor; .

[0045] Preferably, the fitness is calculated based on the following formula:

[0046] ;

[0047] in, Indicates fitness; represents the envelope entropy; represents sample entropy; and Represents the weight coefficient; K represents the current number of decomposition layers; represents the Hilbert envelope amplitude of the kth IMF component; represents the sum of K IMF envelope amplitudes; n represents the embedding dimension, that is, the length of the subsequence intercepted from the zero-sequence current time series; s represents the similarity tolerance, that is, the tolerance parameter used to determine whether two subsequences are similar; It represents the probability that the distance between all subsequence pairs of length n+1 in the zero-sequence current time series is less than or equal to s under the conditions of embedding dimension n+1 and similarity tolerance s; It represents the probability that the distance between all subsequence pairs of length n in the zero-sequence current time series is less than or equal to s under the conditions of embedding dimension n and similarity tolerance s.

[0048] In a second aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for determining whether a single-phase grounding fault exists in a distribution network line as described in the first aspect is implemented.

[0049] In a third aspect, a non-transitory computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for determining whether a single-phase grounding fault exists in a distribution network line as described in the first aspect is implemented.

[0050] In a fourth aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the method for determining whether a single-phase grounding fault exists in a distribution network line as described in the first aspect.

[0051] It can be seen from the above technical solutions that, compared with the prior art, the present invention provides a method for determining whether a single-phase grounding fault exists in a distribution network line, and the present invention can improve the accuracy of the determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0053] Figure 1 A flow chart of a method for determining whether a single-phase grounding fault exists in a distribution network provided by the present invention;

[0054] Figure 2 A schematic diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0056] First, as Figure 1 As shown, an embodiment of the present invention discloses a method for determining whether a single-phase grounding fault exists in a distribution network line, comprising the following steps:

[0057] S1: Based on the improved dream optimization algorithm, the optimal number of decomposition layers and the optimal penalty factor of variational mode decomposition are obtained;

[0058] In one embodiment, S1 specifically includes the following steps:

[0059] S11: Generate initial population ;in, ; M represents the number of individuals in the initial population; individual Includes elements of two dimensions: the number of decomposition layers and the penalty factor;

[0060] In one embodiment, in S11:

[0061] ;

[0062] Where, represents a randomly generated integer in the closed interval [3,15], which represents the number of decomposition levels; represents a random real number in the closed interval [0,1], Represents the penalty factor.

[0063] Understandably, too few decomposition levels may not effectively separate signal components, while too many will generate redundant components and increase computational complexity. A decomposition level of 15 or fewer covers 99% of fault characteristic components and avoids redundant IMFs caused by over-decomposition. The penalty factor controls the bandwidth. A larger penalty factor means stricter bandwidth restrictions. A value below 500 can lead to modal aliasing, while a value exceeding 5000 may overconstrain and cause signal distortion.

[0064] S12: Calculate the fitness of all individuals and retain a preset proportion of individuals based on fitness ranking;

[0065] In one embodiment, in S12: rank the fitness from large to small, and retain the top 80% of the individuals.

[0066] S13: Divide the individuals retained in S12 into several groups, and randomly assign the number of forgetting dimensions to each group; wherein the number of forgetting dimensions is 1 or 2;

[0067] In one embodiment, the individuals retained in S12 are divided into 5 groups.

[0068] S14: Each group performs T1 grouping iterations on its individuals based on its own forgetting dimension number; where T1 is a positive integer;

[0069] In one embodiment, S14 is implemented based on the following formula:

[0070] ;

[0071] Where, ; Q represents the number of groups obtained by S13; ;

[0072] It represents the value of the j-th dimension element of the i-th individual in the q-th group after the t+1-th iteration. When j=1, it represents the number of decomposition levels, and when j=2, it represents the penalty factor.

[0073] It represents the value of the j-th dimension element of the individual with the highest fitness in the q-th group before the t+1-th iteration. When j=1, it represents the number of decomposition layers, and when j=2, it represents the penalty factor.

[0074] Represents a random number between the closed interval [0,1];

[0075] It represents the value of the j-th dimension element of the randomly selected individual in the q-th group after the t-th iteration. When j=1, it represents the number of decomposition levels, and when j=2, it represents the penalty factor.

[0076] It represents the value of the j-th dimension element of the i-th individual in the q-th group after the t-th iteration. When j=1, it represents the number of decomposition levels, and when j=2, it represents the penalty factor.

[0077] represents the set of forgotten dimensions of the qth group;

[0078] When the number of forgotten dimensions of the qth group is equal to 1, or ;

[0079] It is understandable that: When , it means only the penalty factor is updated; when , it means only the number of decomposition levels is updated.

[0080] When the number of forgotten dimensions of the qth group is equal to 2, ;

[0081] It is understandable that: , it means that neither the penalty factor nor the number of decomposition levels are updated.

[0082] S15: Perform T2 global iterations on the individuals after T1 grouping iterations to obtain the optimal number of decomposition layers and the optimal penalty factor; wherein T2 is a positive integer.

[0083] In one embodiment, S15 is implemented based on the following formula:

[0084] ;

[0085] ;

[0086] ;

[0087] Where, Indicates the The value of the j-th dimension element of the i-th individual after the iteration;

[0088] Indicates the The value of the j-th dimension element of the individual with the highest fitness before the iteration;

[0089] represents the learning rate;

[0090] In one embodiment, The value is 0.6.

[0091] Indicates the The upper limit of the value of the j-th dimension element of all individuals after iterations;

[0092] Indicates the The lower limit of the value of the j-th dimension element of all individuals after iterations;

[0093] represents the spiral search term, b represents the curvature constant, and r~U(-1,1) represents the random direction factor obeying the uniform distribution U(-1,1);

[0094] In one embodiment, b takes the value of 1.

[0095] Indicates the The upper limit of the value of the j-th dimension element of all individuals after iterations;

[0096] Represents a randomly generated real number in the closed interval [0,1];

[0097] Indicates the The lower limit of the value of the j-th dimension element of all individuals after iterations;

[0098] When j=1, it indicates the number of decomposition layers, and when j=2, it indicates the penalty factor;

[0099] .

[0100] In one embodiment, the fitness is calculated based on the following formula:

[0101] ;

[0102] in, Indicates fitness; represents the envelope entropy; represents sample entropy; and Represents the weight coefficient; K represents the current decomposition layer number (i.e., the fitness of which individual is calculated, and the decomposition layer number obtained by its latest iteration is used); represents the Hilbert envelope amplitude of the kth IMF component (variational modal decomposition is performed on the zero-sequence current time series, and a total of K IMF components are obtained); represents the sum of K IMF envelope amplitudes; n represents the embedding dimension, that is, the length of the subsequence intercepted from the zero-sequence current time series; s represents the similarity tolerance, that is, the tolerance parameter used to determine whether two subsequences are similar; It represents the probability that the distance between all subsequence pairs of length n+1 in the zero-sequence current time series is less than or equal to s under the conditions of embedding dimension n+1 and similarity tolerance s; It represents the probability that the distance between all subsequence pairs of length n in the zero-sequence current time series is less than or equal to s under the conditions of embedding dimension n and similarity tolerance s.

[0103] S2: Perform optimal variational modal decomposition on the zero-sequence current time series output by the distribution network line to obtain IMF components; wherein the optimal variational mode decomposition adopts the optimal number of decomposition layers and the optimal penalty factor; represents the optimal decomposition level;

[0104] S3: Based on The IMF component is used to determine whether there is a single-phase grounding fault in the distribution network line.

[0105] In one embodiment, S3 specifically includes the following steps:

[0106] S31: Yes IMF components are used for feature extraction;

[0107] S32: Compare the features extracted in S31 with the features of the distribution network line without a single-phase grounding fault. If the features extracted in S31 change, it indicates that a single-phase grounding fault exists in the distribution network line.

[0108] In one embodiment, the extracted features include frequency features and energy features.

[0109] In one embodiment, the feature extraction method uses a machine learning or deep learning model (such as a support vector machine or a neural network).

[0110] It is understandable that a single-phase grounding fault usually causes an increase in energy in certain frequency bands or a change in frequency components. Therefore, based on the frequency characteristics and energy characteristics, it can be determined whether a single-phase grounding fault exists in the distribution network line.

[0111] In a second aspect, the present invention further provides an electronic device, such as Figure 2 As shown, the electronic device may include: a processor 201, a communications interface 202, a memory 203, and a communication bus 204. The processor 201, the communications interface 202, and the memory 203 communicate with each other via the communication bus 204. The processor 201 may invoke logic instructions in the memory 203 to execute a method for determining whether a single-phase grounding fault exists in a power distribution network line.

[0112] Furthermore, the logic instructions in the aforementioned memory 203 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0113] In a third aspect, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the methods provided by the above methods to determine whether there is a single-phase grounding fault in the distribution network line.

[0114] In a fourth aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the method provided by the above-mentioned methods for determining whether there is a single-phase grounding fault in the distribution network line.

[0115] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0116] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0117] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0118] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining whether a single-phase grounding fault exists in a distribution network line, characterized in that: The following steps are involved: S1: Based on the improved dream optimization algorithm, the optimal number of decomposition layers and the optimal penalty factor of variational mode decomposition are obtained; S2: Perform optimal variational modal decomposition on the zero-sequence current time series output by the distribution network line to obtain IMF components; wherein the optimal variational mode decomposition adopts the optimal number of decomposition layers and the optimal penalty factor; represents the optimal decomposition level; S3: Based on The IMF component is used to determine whether there is a single-phase grounding fault in the distribution network line.

2. A method for determining whether a single-phase grounding fault exists in a distribution network according to claim 1, characterized in that: S1 specifically includes the following steps: S11: Generate initial population ;in, ; M represents the number of individuals in the initial population; individual Includes elements of two dimensions: the number of decomposition layers and the penalty factor; S12: Calculate the fitness of all individuals and retain a preset proportion of individuals based on fitness ranking; S13: Divide the individuals retained in S12 into several groups, and randomly assign the number of forgetting dimensions to each group; wherein the number of forgetting dimensions is 1 or 2; S14: Each group performs T1 grouping iterations on its individuals based on its own forgetting dimension number; where T1 is a positive integer; S15: Perform T2 global iterations on the individuals after T1 grouping iterations to obtain the optimal number of decomposition layers and the optimal penalty factor; wherein T2 is a positive integer.

3. A method for determining whether a single-phase grounding fault exists in a distribution network according to claim 2, characterized in that: In S11: ； Where, represents a randomly generated integer in the closed interval [3,15], which represents the number of decomposition levels; represents a random real number in the closed interval [0,1], Represents the penalty factor.

4. A method for determining whether a single-phase grounding fault exists in a distribution network according to claim 2, characterized in that: In S12: Rank the fitness from large to small and retain the top 80% of individuals.

5. The method for determining whether a single-phase grounding fault exists in a distribution network according to claim 2, wherein: S14 is implemented based on the following formula: ； Where, ; Q represents the number of groups obtained by S13; ; It represents the value of the j-th dimension element of the i-th individual in the q-th group after the t+1-th iteration. When j=1, it represents the number of decomposition levels, and when j=2, it represents the penalty factor. It represents the value of the j-th dimension element of the individual with the highest fitness in the q-th group before the t+1-th iteration. When j=1, it represents the number of decomposition layers, and when j=2, it represents the penalty factor. Represents a random number between the closed interval [0,1]; It represents the value of the j-th dimension element of the randomly selected individual in the q-th group after the t-th iteration. When j=1, it represents the number of decomposition levels, and when j=2, it represents the penalty factor. It represents the value of the j-th dimension element of the i-th individual in the q-th group after the t-th iteration. When j=1, it represents the number of decomposition levels, and when j=2, it represents the penalty factor. represents the set of forgotten dimensions of the qth group; When the number of forgotten dimensions of the qth group is equal to 1, or ; When the number of forgotten dimensions of the qth group is equal to 2, .

6. A method for determining whether a single-phase grounding fault exists in a distribution network according to claim 2, characterized in that: S15 is implemented based on the following formula: ； ； ； Where, Indicates the The value of the j-th dimension element of the i-th individual after the iteration; Indicates the The value of the j-th dimension element of the individual with the highest fitness before the iteration; represents the learning rate; Indicates the The upper limit of the value of the j-th dimension element of all individuals after iterations; Indicates the The lower limit of the value of the j-th dimension element of all individuals after iterations; represents the spiral search term, b represents the curvature constant, and r~U(-1,1) represents the random direction factor obeying the uniform distribution U(-1,1); Indicates the The upper limit of the value of the j-th dimension element of all individuals after iterations; Represents a randomly generated real number in the closed interval [0,1]; Indicates the The lower limit of the value of the j-th dimension element of all individuals after iterations; When j=1, it indicates the number of decomposition layers, and when j=2, it indicates the penalty factor; .

7. A method for determining whether a single-phase grounding fault exists in a distribution network according to any one of claims 2 to 6, characterized in that: Fitness is calculated based on the following formula: ； in, Indicates fitness; represents the envelope entropy; represents sample entropy; and Represents the weight coefficient; K represents the current number of decomposition layers; represents the Hilbert envelope amplitude of the kth IMF component; represents the sum of K IMF envelope amplitudes; n represents the embedding dimension, that is, the length of the subsequence intercepted from the zero-sequence current time series; s represents the similarity tolerance, that is, the tolerance parameter used to determine whether two subsequences are similar; It represents the probability that the distance between all subsequence pairs of length n+1 in the zero-sequence current time series is less than or equal to s under the conditions of embedding dimension n+1 and similarity tolerance s; It represents the probability that the distance between all subsequence pairs of length n in the zero-sequence current time series is less than or equal to s under the conditions of embedding dimension n and similarity tolerance s.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for determining whether a single-phase grounding fault exists in a distribution network line according to any one of claims 1 to 7 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining whether a single-phase grounding fault exists in a power distribution network line according to any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for determining whether a single-phase grounding fault exists in a power distribution network line according to any one of claims 1 to 7 is implemented.

Images