Power distribution equipment fault identification method and system

Abstract

The invention relates to the technical field of fault identification, and particularly provides a power distribution equipment fault identification method and system, and the method comprises the following steps: obtaining the operation data of power distribution equipment, and carrying out the noise removal of the obtained data, and obtaining first data; performing fluctuation enhancement processing on the first data based on a CEEMD enhancement function to obtain second data; performing voltage, current and power dimension feature extraction on the second data, and calculating a feature entropy value; identifying a corresponding fault mode based on the size of the feature entropy; according to the method, frequency fluctuation enhancement processing is performed on the operation data of the power distribution equipment based on the CEEMD algorithm, then the features of the enhanced data are extracted, the feature entropy of the features is calculated, the fault features of the power distribution equipment are identified by identifying the range of the feature entropy, the transient features at the moment of fault occurrence can be prevented from being omitted, and the fault detection accuracy is improved. And the accuracy of a fault identification result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault identification, and particularly to a fault identification method and system for distribution equipment. Background Art

[0002] Due to factors such as random fluctuations of load, equipment aging, and improper maintenance, medium and low voltage distribution equipment often faces various fault risks. These faults may not only cause power supply interruption, but also lead to equipment damage and even safety accidents, bringing significant impacts on production, life, and economic development. Therefore, it is necessary to study effective fault control methods for medium and low voltage distribution equipment to reduce the failure rate.

[0003] When analyzing the faults of distribution equipment, the collected operation voltage, current and other data of the distribution equipment may be affected by factors such as low acquisition frequency and acquisition environment, missing some transient characteristics at the moment of fault occurrence, and unable to provide accurate data basis for subsequent fault feature extraction, resulting in a decrease in the accuracy of fault analysis results. Therefore, the present application proposes a fault identification method and system for distribution equipment. Summary of the Invention

[0004] The purpose of the present invention is to provide a fault identification method and system for distribution equipment to solve the problem of low accuracy of the current fault identification method for distribution equipment.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] A fault identification method for distribution equipment, the fault identification method includes the following steps:

[0007] Obtain the operation data of the distribution equipment, and remove the noise from the obtained data to obtain the first data;

[0008] Perform fluctuation enhancement processing on the first data based on the CEEMD enhancement function to obtain the second data;

[0009] Extract the features in the dimensions of voltage, current and power from the second data, and calculate the feature entropy value;

[0010] Identify the corresponding fault mode based on the magnitude of the feature entropy value.

[0011] Preferably, the noise of the operation data is removed based on formula (1):

[0012]

[0013] Wherein, R z represents the noise removal result of the operation data of the medium and low voltage distribution equipment, r z represents the attribute value of the operation data of the distribution equipment, and σ zRepresents the noise value of the operating data of the power distribution equipment, f z Represents the original operating data of the power distribution equipment.

[0014] Preferably, perform fluctuation enhancement processing on the first data based on formula (2) and formula (3):

[0015] P r = G a (C k - c k ) 2 ; Formula (2)

[0016] f r = O r (P r ) × R z ; Formula (3)

[0017] Among them, P r Represents the CEEMD frequency enhancement operator, C k Represents the initial frequency value of the data, c k Represents the frequency change rate of the operating data, G a Represents the data transformation parameter, f r Represents the fluctuation data enhancement capture result, O r () represents the CEEMD enhancement function.

[0018] Preferably, perform feature extraction based on formula (4), formula (5), and formula (6):

[0019]

[0020] Among them, g y Represents the voltage feature of the power distribution equipment, U max , U min Respectively represent the maximum and minimum values of the voltage of the power distribution equipment during operation, g l Represents the current feature of the power distribution equipment, I s Represents the actual current of the power distribution equipment, I e Represents the rated current of the power distribution equipment, g s Represents the power factor feature of the power distribution equipment, P s Represents the active power of the power distribution equipment during operation, P w Represents the reactive power of the power distribution equipment during operation.

[0021] Preferably, calculate the feature entropy value based on formula (7):

[0022] T s = -κ y ln g y - κ l ln g l-κ s ln g s ; Formula (7)

[0023] where, T s represents the calculated characteristic entropy value of the power distribution equipment, and κ y , κ l , κ s respectively represent the entropy value weights of different characteristics of the power distribution equipment.

[0024] Preferably, the entropy value weight is obtained by the following method:

[0025] Obtain the historical operation data of the power distribution equipment and the fault types of the power distribution equipment;

[0026] Invert the entropy value weight based on the above power distribution equipment fault identification method.

[0027] Preferably, the method for identifying the fault mode specifically includes:

[0028] Obtain the value ranges of different fault modes;

[0029] Compare the characteristic entropy value with the value range to obtain the value range where the characteristic entropy value is located;

[0030] Take the fault mode corresponding to the value range where the characteristic entropy value is located as the output fault mode.

[0031] The present invention also discloses a power distribution equipment fault identification system for implementing the above power distribution equipment fault identification method, and the system includes:

[0032] An acquisition unit for acquiring the operation data of the power distribution equipment;

[0033] A calculation unit for performing noise elimination, fluctuation enhancement processing, feature extraction, and characteristic entropy value calculation operations on the operation data;

[0034] A fault identification unit for identifying the faults of the power distribution equipment based on the output result of the calculation unit and outputting the fault types..

[0035] In summary, the present invention has the following beneficial effects compared with the prior art:

[0036] The power distribution equipment fault identification method disclosed in the embodiments of the present invention performs frequency fluctuation enhancement processing on the operation data of the power distribution equipment based on the CEEMD algorithm, then extracts the features of the enhanced data, and then calculates the characteristic entropy value of the features. By identifying the range where the characteristic entropy value is located, the fault characteristics of the power distribution equipment are identified, which can prevent the omission of transient characteristics at the moment of fault occurrence and improve the accuracy of the fault identification result. Description of the Drawings

[0037] Figure 1Schematic structural diagram of the power distribution equipment fault identification method disclosed in the embodiments of the present invention. Detailed implementation manners

[0038] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0039] Embodiment 1

[0040] As Figure 1 shown, a power distribution equipment fault identification method provided by an embodiment of the present invention includes the following steps:

[0041] Step S100: Obtain the operation data of the power distribution equipment, and perform noise removal on the obtained data to obtain the first data;

[0042] Specifically, in this step, data such as voltage, current, and power during the operation of the power distribution equipment are obtained as the operation data of the power distribution equipment.

[0043] Based on formula (1), noise is removed from the operation data:

[0044]

[0045] Among them, R z represents the noise removal result of the operation data z of the medium and low voltage power distribution equipment; r z represents the attribute value of the operation data z of the power distribution equipment, which is determined by the staff according to the parameters of the power distribution equipment and the type of the operation data; σ z represents the noise value of the operation data z of the power distribution equipment, which is determined by the staff according to the operation environment of the power distribution equipment and the type of the operation data z; f z represents the original operation data of the power distribution equipment; formula (1) is used to remove the data of the equipment during normal operation from the original data.

[0046] In this step, denoising the operation data can effectively remove the high-frequency data in the signal while retaining the low-frequency data containing important signal features. Since the voltage, current, and power of the power distribution equipment are at a stable value during operation, when the operation environment of the power distribution equipment changes or a fault occurs, the operation data of the power distribution equipment, such as voltage, current, and power, will all fluctuate.

[0047] Step S200: Perform fluctuation enhancement processing on the first data based on the CEEMD enhancement function to obtain the second data;

[0048] Specifically, in this embodiment, the first data is processed by fluctuation enhancement based on formula (2) and formula (3):

[0049] P r = G a (C k - c k ) 2 ; Formula (2)

[0050] f r = O r (P r ) × R z ; Formula (3)

[0051] Among them, P r represents the CEEMD frequency enhancement operator, which is determined by the staff; C k represents the initial frequency value of the data, which is statistically obtained by the staff based on historical data; c k represents the frequency change rate of the operation data; G a represents the data transformation parameter, f r represents the capture result of the fluctuation data enhancement, and O r () represents the CEEMD enhancement function.

[0052] In this step, formula (2) and formula (3) are used to enhance the data to obtain the transient fluctuation result of the operating frequency, providing data support for subsequent identification of the fault mode of the distribution equipment.

[0053] Step S300: Extract features in the voltage, current, and power dimensions of the second data, and calculate the feature entropy value;

[0054] Specifically, in this embodiment, feature extraction is performed based on formula (4), formula (5), and formula (6):

[0055]

[0056] Among them, g y represents the voltage feature of the distribution equipment, and U max , U min respectively represent the maximum and minimum values of the voltage of the distribution equipment during operation. g l represents the current feature of the distribution equipment, I s represents the actual current of the distribution equipment, and I e represents the rated current of the distribution equipment. g s represents the power factor feature of the distribution equipment, P s represents the active power of the distribution equipment during operation, and P w represents the reactive power of the distribution equipment during operation.

[0057] As a preferred implementation in this embodiment, the characteristic entropy value is calculated based on formula (7):

[0058] T s =-κ y ln g y -κ l ln g l -κ s ln g s ; Formula (7)

[0059] wherein, T s represents the characteristic entropy value of the distribution equipment calculated, and κ y , κ l , κ s respectively represent the entropy value weights of different characteristics of the distribution equipment.

[0060] Step S400: Identify the corresponding fault mode based on the magnitude of the characteristic entropy value;

[0061] Specifically, in this embodiment, different fault modes are set with different interval ranges. As shown in Table 1, after obtaining the characteristic entropy value, it is compared with the fault range in Table 1 to identify the fault mode:

[0062] Table 1 Distribution Equipment Fault Modes

[0063]

[0064] After obtaining the characteristic entropy value through formula (7), compare with the numerical range in Table 1, and determine the corresponding fault according to the numerical range where the characteristic entropy value is located.

[0065] As a preferred implementation in this embodiment, in step S300, the entropy value weight is calculated by an inversion method. The specific calculation method is to perform the operations in steps S100 to S400 through the historical operation data of the distribution equipment and the fault types of the distribution equipment to invert the entropy value weight.

[0066] The distribution equipment fault identification method disclosed in the embodiment of the present invention performs frequency fluctuation enhancement processing on the operation data of the distribution equipment based on the CEEMD algorithm, then extracts the characteristics of the enhanced data, and then calculates the characteristic entropy value of the characteristics. By identifying the range where the characteristic entropy value is located, the fault characteristics of the distribution equipment are identified, which can prevent the omission of transient characteristics at the moment of fault occurrence and improve the accuracy of the fault identification result.

[0067] Embodiment 2

[0068] The present invention also discloses a system for implementing the distribution equipment fault identification method described in Embodiment 1. The system includes:

[0069] An acquisition unit for acquiring the operation data of the power distribution equipment;

[0070] A calculation unit for performing operations such as noise removal, fluctuation enhancement processing, feature extraction, and feature entropy value calculation on the operation data;

[0071] A fault identification unit for identifying the faults of the power distribution equipment based on the output result of the calculation unit and outputting the fault type.

[0072] Specifically, in this embodiment, the acquisition unit can be connected to the hardware device of the power distribution equipment, such as a detection circuit, for real-time acquisition of the voltage, current, and power of the power distribution equipment, or can also be software, such as the acquisition port of the software for implementing the power distribution equipment fault identification method described in Embodiment 1;

[0073] When the calculation unit and the fault identification unit are hardware, they are computers capable of performing operations such as noise removal, fluctuation enhancement processing, feature extraction, and feature entropy value calculation, identifying the faults of the power distribution equipment, and outputting the fault type; when the calculation unit and the fault identification unit are software, the calculation unit and the fault identification unit are the calculation module and the comparison module of the software for implementing the power distribution equipment fault identification method described in Embodiment 1.

[0074] Embodiment 3

[0075] The present invention also discloses an electronic device, which includes a processor, and the processor implements the power distribution equipment fault identification method as described in Embodiment 1 when executing a computer program stored in a memory.

[0076] Embodiment 4

[0077] The present invention also discloses a readable storage medium storing a computer program, and when the computer program is executed by a processor, it enables the processor to implement the power distribution equipment fault identification method as described in Embodiment 1 when running the computer program.

[0078] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in electrical, mechanical or other forms.

[0079] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] In addition, each functional unit in various embodiments of the present invention may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of a combination of hardware and software functional units.

[0081] In a typical configuration of an embodiment of the present invention, an electronic device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0082] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory in the form of, for example, read-only memory (ROM) or flash memory (flash-RAM). The memory is an example of a computer-readable medium.

[0083] The readable storage medium includes permanent and non-permanent, removable and non-removable media and can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data.

[0084] Examples of the storage medium of the electronic device include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette tapes, magnetic disk storage, or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory media such as modulated data signals and carrier waves.

[0085] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. For the specific working process of the device described above, reference can be made to the corresponding process in the foregoing method embodiments, which will not be elaborated here.

Claims

1. A method for identifying a fault in a power distribution device, characterized in that: The fault identification method comprises the following steps: Acquire operation data of the power distribution equipment, and remove noise from the acquired data to obtain first data; Performing fluctuation enhancement processing on the first data based on the CEEMD enhancement function to obtain second data; Extracting features of the second data in terms of voltage, current and power, and calculating a feature entropy value; Based on the size of the characteristic entropy value, the corresponding fault mode is identified.

2. The method for identifying a fault in a power distribution device according to claim 1, characterized in that: Based on formula (1), the noise of the running data is removed: Among them, R z represents the noise removal result of the operation data of medium and low voltage power distribution equipment, r z Represents the attribute value of the power distribution equipment operation data, σ z Indicates the noise value of the distribution equipment operation data, f z Indicates the original operation data of the power distribution equipment.

3. The method for identifying a fault in a power distribution device according to claim 1, characterized in that: Based on formula (2) and formula (3), the first data is subjected to fluctuation enhancement processing: P r =G a (C k -c k ) 2 ; Formula (2) f r =O r (P r )×R z ; Formula (3) Among them, P r represents the CEEMD frequency enhancement operator, C k represents the initial frequency value of the data, c k Indicates the frequency change rate of the operating data, G a represents the data transformation parameter, f r represents the result of enhanced capture of fluctuation data, O r () represents the CEEMD enhancement function.

4. The method for identifying a fault in a power distribution device according to claim 3, characterized in that: Feature extraction is performed based on formula (4), formula (5) and formula (6): Among them, g y Indicates the voltage characteristics of the power distribution equipment, U max , U min Respectively represent the maximum and minimum voltage of the distribution equipment during operation, g l Indicates the current characteristics of the power distribution equipment, I s Indicates the actual current of the power distribution equipment, I e Indicates the rated current of the power distribution equipment, g s Indicates the power factor characteristics of the power distribution equipment, P s Indicates the active power of the distribution equipment, P w Indicates the reactive power of the power distribution equipment.

5. The method for identifying a fault in a power distribution device according to claim 4, characterized in that: The characteristic entropy value is calculated based on formula (7): T s = -K y ln g y -K l ln g l -K s ln g s ; Formula (7) Among them, T s Represents the calculated characteristic entropy value of the power distribution equipment, K y , K l , K s They respectively represent the entropy weights of different characteristics of power distribution equipment.

6. The method for identifying a fault in a power distribution device according to any one of claims 1 to 5, characterized in that: The entropy weight is obtained by the following method: Obtain historical operation data of power distribution equipment and fault types of power distribution equipment; The entropy value weight is inverted based on the distribution equipment fault identification method described in claim 5.

7. The method for identifying a fault in a power distribution device according to any one of claims 1 to 5, characterized in that: Methods for identifying failure modes include: Get the value range of different failure modes; Compare the characteristic entropy value with the value range to obtain the value range where the characteristic entropy value lies; The fault mode corresponding to the range of characteristic entropy values ​​is output as the fault mode.

8. A power distribution equipment fault identification system, characterized in that: For implementing the method for identifying a fault of a power distribution device described in Example 1, the system includes: An acquisition unit, used for acquiring operation data of the power distribution equipment; A computing unit, used for performing noise elimination, fluctuation enhancement processing, feature extraction and feature entropy value calculation operations on the operating data; The fault identification unit identifies the fault of the power distribution equipment based on the output result of the calculation unit and outputs the fault type.

Images