Method and device for locating partial discharge fault of collector line

Abstract

This invention provides a method and apparatus for locating partial discharge faults in power collection lines. The method includes: acquiring a first high-frequency partial discharge pulse signal at the bus end and second high-frequency partial discharge pulse signals at the ends of each branch line when a fault occurs in the power collection line of a new energy power station; obtaining a suspected fault range corresponding to the power collection line of the new energy power station based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal, and a fault range location model of the power collection line; determining a target fault range corresponding to the power collection line of the new energy power station according to the structure type of the power collection line corresponding to each suspected fault range; and locating the fault within the target fault range based on the traveling wave method to obtain the partial discharge fault location result of the power collection line of the new energy power station. This invention can accurately determine the target fault range corresponding to the power collection line of a new energy power station without requiring excessive fault monitoring devices, and can also ensure the accuracy of partial discharge fault location in power collection lines.

Description

Technical Field

[0001] This invention relates to the field of power line monitoring technology, and in particular to a method and device for locating partial discharge faults in power lines. Background Technology

[0002] A collector line is a line in a power system used to collect and transmit electrical energy. It typically aggregates electrical energy from multiple generating units (such as wind turbines and solar panels) to a single point before transmitting it to the power grid or load center via transmission lines. To ensure the safe and stable operation of collector lines, condition monitoring and fault location are generally performed to promptly detect and address potential problems and faults. Among these, the accurate location of partial discharge faults in collector lines is crucial because they can lead to major power safety accidents within a short period.

[0003] Currently, the traveling wave method is mainly used to locate partial discharge faults in power collection lines. However, since most new energy power stations are located in mountainous areas and cover a large area, their power collection lines are radially distributed and have multiple branches and short T-connections. This means that traveling wave-based fault location for power collection lines requires a large number of fault monitoring devices and reasonable installation points to achieve accurate location of fault points along the entire power collection line. At the same time, the distributed power characteristics of the power collection lines in new energy power stations and the variability of fault points may make it impossible to accurately determine the fault range. Summary of the Invention

[0004] This invention provides a method and apparatus for locating partial discharge faults in power collection lines, in order to solve the problem that the current method for locating partial discharge faults in power collection lines of new energy power plants requires a large number of fault monitoring devices and has insufficient accuracy.

[0005] In a first aspect, embodiments of the present invention provide a method for locating partial discharge faults in a power line, comprising:

[0006] Acquire the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line when a fault occurs in the power collection line of a new energy power station.

[0007] Based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal and the fault interval location model of the collector line, the suspected fault interval of the collector line of the new energy power station is obtained.

[0008] The suspected fault interval is verified according to the collection line structure type corresponding to each suspected fault interval, and the target fault interval corresponding to the collection line of the new energy power station is determined according to the verification result.

[0009] Based on the traveling wave method, fault location is performed within the target fault range to obtain the partial discharge fault location results of the power collection lines of new energy power plants.

[0010] In one possible implementation, the training process of the fault location model for the power collection line is as follows:

[0011] The first historical high-frequency partial discharge pulse signal at the bus end and the second historical high-frequency partial discharge pulse signal at the end of each branch line when a historical fault occurs in the collection line of different new energy power stations are obtained, along with the corresponding historical fault location results. The branch line where the historical fault location results are located is recorded as the historical fault interval.

[0012] Using the first historical high-frequency partial discharge pulse signal and each of the second historical high-frequency partial discharge pulse signals as inputs, and the corresponding historical fault intervals as outputs, a preset neural network model is trained to obtain a fault interval location model for the power collection line.

[0013] In one possible implementation, the suspected fault interval is checked according to the collector line structure type corresponding to each suspected fault interval, and the target fault interval of the new energy power station collector line is determined based on the check result, including:

[0014] The probability that the collector line structure type corresponding to each suspected fault interval is identified as a fault interval is obtained, denoted as the fault probability;

[0015] The target fault range of the power collection line of the new energy power station is determined based on the fault probability corresponding to each suspected fault range.

[0016] In one possible implementation, obtaining the probability that the collector line structure type corresponding to each of the suspected fault intervals is identified as a fault interval includes:

[0017] The probability of a collector line structure type being identified as a fault interval is obtained by looking up the data in the preset fault probability table; wherein, the preset fault probability table is a table showing the correspondence between each collector line structure type and the probability of each collector line structure type being identified as a fault interval.

[0018] In one possible implementation, the probability that the collector line structure type corresponding to each suspected fault interval is identified as a fault interval is obtained, denoted as the fault probability, including:

[0019] Obtain the proportion of each suspected fault section corresponding to the collector line structure type to the different collector line structure types in the new energy power station's collector lines;

[0020] The probability that the collector line structure type corresponding to each suspected fault interval is identified as a fault interval is obtained based on the ratio, and is denoted as the fault probability.

[0021] In one possible implementation, the probability that the collector line structure type corresponding to each suspected fault interval is identified as a fault interval is obtained according to the ratio, denoted as the fault probability, including:

[0022] The first correction factor is determined based on the stated ratio;

[0023] The initial probability that the collector line structure type corresponding to each suspected fault interval is determined to be a fault interval is corrected according to the first correction coefficient, and the probability that the collector line structure type corresponding to each suspected fault interval is determined to be a fault interval is obtained, which is denoted as the fault probability.

[0024] In one possible implementation, determining the target fault range of the power collection line at the new energy power station based on the fault probability corresponding to each suspected fault range includes:

[0025] If there is a suspected fault interval with a probability greater than a preset probability threshold among the fault probabilities corresponding to each suspected fault interval, then the suspected fault interval corresponding to the maximum value among the fault probabilities is determined as the target fault interval of the new energy power station's collection line.

[0026] One possible implementation also includes:

[0027] If there is no suspected fault interval with a probability greater than the preset probability threshold in the fault probability corresponding to each suspected fault interval, then the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line are obtained before and / or after the fault occurs in the new energy power station collection line. The steps of "obtaining the suspected fault interval corresponding to the new energy power station collection line based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal and the collection line fault interval location model" and subsequent steps are re-executed.

[0028] One possible implementation also includes: acquiring environmental information when a fault occurs in the power collection lines of a new energy power station;

[0029] The suspected fault interval is verified according to the structure type of the collector line corresponding to each suspected fault interval. Based on the verification results, the target fault interval corresponding to the collector line of the new energy power station is determined, including:

[0030] The suspected fault interval is verified based on the collection line structure type and environmental information corresponding to each suspected fault interval, and the target fault interval corresponding to the collection line of the new energy power station is determined based on the verification results.

[0031] Secondly, embodiments of the present invention provide a partial discharge fault location device for a power line, comprising:

[0032] The acquisition module is used to acquire the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line when a fault occurs in the power collection line of the new energy power station.

[0033] The first processing module is used to obtain the suspected fault range of the power collection line of the new energy power station based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal and the fault range location model of the power collection line.

[0034] The second processing module is used to verify the suspected fault section according to the collection line structure corresponding to each suspected fault section, and to determine the target fault section of the collection line of the new energy power station based on the verification result.

[0035] The fault location module is used to locate faults within the target fault range based on the traveling wave method, and obtain the partial discharge fault location results of the power collection lines of the new energy power station.

[0036] This invention provides a method and apparatus for locating partial discharge faults in a power collection line. The method involves acquiring a first high-frequency partial discharge pulse signal at the bus end and second high-frequency partial discharge pulse signals at the ends of each branch line when a fault occurs in the power collection line of a new energy power station. Then, based on the first and second high-frequency partial discharge pulse signals and a power collection line fault range location model, a suspected fault range corresponding to the power collection line of the new energy power station is obtained. Next, the suspected fault range is verified according to the power collection line structure type corresponding to each suspected fault range, and the target fault range corresponding to the power collection line of the new energy power station is determined based on the verification results. Finally, fault location is performed within the target fault range using the traveling wave method to obtain the partial discharge fault location result of the power collection line of the new energy power station. This method can accurately determine the target fault range corresponding to the power collection line of the new energy power station using the power collection line fault range location model and the power collection line structure type, without requiring excessive fault monitoring devices. Furthermore, the accuracy of partial discharge fault location is ensured by accurately obtaining the target fault range and then performing fault location based on the traveling wave method. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating the implementation of the partial discharge fault location method for power collection lines provided in this embodiment of the invention.

[0039] Figure 2 This is a schematic diagram of the power collection line topology of a new energy power station provided in an embodiment of the present invention;

[0040] Figure 3 This is a schematic diagram of the structure of the partial discharge fault location device for power collection lines provided in an embodiment of the present invention. Detailed Implementation

[0041] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0042] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0043] Figure 1 The implementation flowchart of the partial discharge fault location method for collector lines provided in the embodiments of the present invention is described in detail below:

[0044] Step 101: Obtain the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line when a fault occurs in the power collection line of the new energy power station.

[0045] Combination Figure 2 As shown, the topology of the power collection line of a new energy power station generally includes a bus and several branches. In this embodiment, in order to minimize the number of fault monitoring devices, only the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch can be acquired when a fault occurs in the power collection line of the new energy power station.

[0046] Step 102: Based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal, and the fault interval location model of the collector line, obtain the suspected fault interval corresponding to the collector line of the new energy power station.

[0047] For example, the training process for a fault location model for a power line can be as follows:

[0048] The system acquires the first historical high-frequency partial discharge pulse signal at the bus end and the second historical high-frequency partial discharge pulse signal at the end of each branch line when a historical fault occurs in the collection line of different new energy power plants, as well as the corresponding historical fault location results, and records the branch line where the historical fault location results are located as the historical fault interval.

[0049] Using the first historical high-frequency partial discharge pulse signal and each of the second historical high-frequency partial discharge pulse signals as inputs, and the corresponding historical fault intervals as outputs, a preset neural network model is trained to obtain a fault interval location model for the collector line.

[0050] In this embodiment, in order to quickly and accurately locate the partial discharge fault of the collector line even when only the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line are acquired at the time of the fault, a collector line fault interval location model can be trained in advance.

[0051] Considering that there is generally little measured data for training the fault zone localization model of the power collection line, this embodiment uses the power collection line fault zone localization model to obtain the suspected fault zone corresponding to the power collection line of the new energy power station, and then verifies the suspected fault zone to more accurately determine the target fault zone corresponding to the power collection line of the new energy power station.

[0052] Step 103: Verify the suspected fault section according to the structure type of the collector line corresponding to each suspected fault section, and determine the target fault section corresponding to the collector line of the new energy power station based on the verification results.

[0053] In this embodiment, considering that the accuracy of the suspected fault interval is insufficient, we consider using the collector line structure type corresponding to each suspected fault interval for further verification.

[0054] For example, depending on the actual situation, the collector line structure type can be divided into cases with few or short branches, cases containing long branches, and cases where long branches contain multiple T-junction branches. When a suspected fault section corresponds to different collector line structure types, its probability of being the target fault section also varies. Therefore, the collector line structure type corresponding to each suspected fault section can be used for further verification.

[0055] Optionally, the suspected fault section can be verified based on the structure type of the collector line corresponding to each suspected fault section. The target fault section of the new energy power station's collector line can be determined based on the verification results, and may include:

[0056] The probability that the collector line structure type corresponding to each suspected fault section is identified as a fault section is denoted as the fault probability.

[0057] Based on the fault probability corresponding to each suspected fault range, the target fault range of the power collection lines of the new energy power station is determined.

[0058] For example, obtaining the probability that the collector line structure type corresponding to each suspected fault section is identified as a fault section can include:

[0059] By looking up the preset fault probability table, the probability that the collector line structure type corresponding to each suspected fault interval is identified as a fault interval is obtained.

[0060] The preset fault probability table is a table showing the correspondence between each type of collector line structure and the probability that each type of collector line structure is identified as a fault zone.

[0061] In this embodiment, a preset fault probability table can be formed by statistically analyzing historical fault location results. This table represents the correspondence between the probability of each type of collector line structure being identified as a fault zone. After obtaining a suspected fault zone, the preset fault probability table can be used to verify whether the suspected fault zone can be identified as the target fault zone.

[0062] For example, suppose the suspected fault range has few or short branches. Since the probability of a range with few or short branches being identified as a fault range is low, the suspected fault range is likely not the target fault range.

[0063] Optionally, the probability that the collector line structure type corresponding to each suspected fault section is identified as a fault section is obtained, denoted as the fault probability, which may include:

[0064] Obtain the proportion of the collector line structure type corresponding to each suspected fault section to the different collector line structure types in the new energy power station.

[0065] The probability that the collector line structure type corresponding to each suspected fault section is identified as a fault section is obtained based on the proportion, and is denoted as the fault probability.

[0066] For example, the probability that the collector line structure type corresponding to each suspected fault section is identified as a fault section can be obtained according to the proportion, denoted as the fault probability, and may include:

[0067] The first correction factor is determined based on the proportion.

[0068] The initial probability of the collector line structure type corresponding to each suspected fault interval being identified as a fault interval is corrected according to the first correction coefficient, and the probability of the collector line structure type corresponding to each suspected fault interval being identified as a fault interval is obtained, which is denoted as the fault probability.

[0069] In this embodiment, considering the differences in the topology of the collection lines of various new energy power plants, when a certain collection line structure type accounts for a high or low proportion in the entire collection line topology of the new energy power plant, the probability of it being identified as a fault section may also be high or low. Therefore, the proportion of the collection line structure type corresponding to each suspected fault section to the different collection line structure types in the collection lines of the new energy power plant is obtained, and a targeted first correction coefficient is determined for each suspected fault section based on this proportion, so as to more accurately measure the probability of the suspected fault section being identified as a fault section, and thus more accurately determine the target fault section.

[0070] For example, determining the target fault range of the power collection lines of a new energy power station based on the fault probability corresponding to each suspected fault range may include:

[0071] If there is a suspected fault interval with a probability greater than a preset probability threshold in the fault probability corresponding to each suspected fault interval, then the suspected fault interval corresponding to the maximum value of each fault probability is determined as the target fault interval of the new energy power station's collection line.

[0072] If there is no suspected fault interval with a probability greater than the preset probability threshold in the fault probability corresponding to each suspected fault interval, then the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line are obtained before and / or after the fault occurs in the new energy power station collection line. The steps of "obtaining the suspected fault interval corresponding to the new energy power station collection line based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal and the collection line fault interval location model" and subsequent steps are re-executed.

[0073] In this embodiment, after obtaining the fault probability corresponding to each suspected fault interval, considering the case where the fault probabilities corresponding to each suspected fault interval are all low, that is, the confidence of each suspected fault interval is not high, at this time, the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line before and / or after the fault of the new energy power station collection line are re-acquired, so as to re-execute the step of "obtaining the suspected fault interval corresponding to the new energy power station collection line based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal and the collection line fault interval location model" and subsequent steps, and then re-search for a more reliable target fault interval when the confidence of each suspected fault interval is not high.

[0074] For example, environmental information can also be obtained when a fault occurs in the power collection line of a new energy power station.

[0075] Accordingly, the suspected fault section can be verified based on the structure type of the collection line and environmental information corresponding to each suspected fault section, and the target fault section corresponding to the collection line of the new energy power station can be determined based on the verification results.

[0076] In this embodiment, the environmental information when a fault occurs in the power collection line of a new energy power station may also affect the target fault section in the power collection line of the new energy power station. Based on the power collection line structure type and environmental information corresponding to each suspected fault section, the suspected fault section is checked together to further improve the accuracy of the target fault section.

[0077] Step 104: Based on the traveling wave method, perform fault location within the target fault range to obtain the partial discharge fault location result of the power collection line of the new energy power station.

[0078] The traveling wave method is based on the characteristics of traveling waves propagating on transmission lines. When a fault occurs on a line, one or more traveling waves are generated at the fault point, and these waves propagate along the line to both sides. The basic principle of traveling wave localization is to detect and analyze the time difference between the arrival times of these traveling waves at the two ends of the line, and combine this with the line length and wave velocity to calculate the location of the fault point. In this embodiment, after determining the target fault range, precise fault localization is performed within the target fault range based on the traveling wave method.

[0079] This invention acquires a first high-frequency partial discharge pulse signal at the bus end and a second high-frequency partial discharge pulse signal at the end of each branch line when a fault occurs in the power collection line of a new energy power station. Then, based on the first and second high-frequency partial discharge pulse signals and the power collection line fault area location model, a suspected fault area corresponding to the power collection line of the new energy power station is obtained. Next, the suspected fault area is verified according to the power collection line structure type corresponding to each suspected fault area, and the target fault area corresponding to the power collection line of the new energy power station is determined based on the verification results. Finally, fault location is performed within the target fault area using the traveling wave method to obtain the partial discharge fault location result of the power collection line of the new energy power station. This method can accurately determine the target fault area corresponding to the power collection line of the new energy power station using the power collection line fault area location model and the power collection line structure type, without requiring excessive fault monitoring devices. Furthermore, the accuracy of partial discharge fault location is ensured by accurately obtaining the target fault area and then performing fault location based on the traveling wave method.

[0080] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0081] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0082] Figure 3 A schematic diagram of the structure of the partial discharge fault location device for a collector line provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0083] like Figure 3 As shown, the partial discharge fault location device for a collector line includes: an acquisition module 31, a first processing module 32, a second processing module 33, and a fault location module 34.

[0084] The acquisition module 31 is used to acquire the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line when a fault occurs in the power collection line of the new energy power station.

[0085] The first processing module 32 is used to obtain the suspected fault range of the power collection line of the new energy power station based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal and the fault range location model of the power collection line.

[0086] The second processing module 33 is used to verify the suspected fault interval according to the collection line structure corresponding to each suspected fault interval, and determine the target fault interval of the collection line of the new energy power station according to the verification result.

[0087] The fault location module 34 is used to locate the fault within the target fault range based on the traveling wave method, and obtain the partial discharge fault location result of the power collection line of the new energy power station.

[0088] This invention acquires a first high-frequency partial discharge pulse signal at the bus end and a second high-frequency partial discharge pulse signal at the end of each branch line when a fault occurs in the power collection line of a new energy power station. Then, based on the first and second high-frequency partial discharge pulse signals and the power collection line fault area location model, a suspected fault area corresponding to the power collection line of the new energy power station is obtained. Next, the suspected fault area is verified according to the power collection line structure type corresponding to each suspected fault area, and the target fault area corresponding to the power collection line of the new energy power station is determined based on the verification results. Finally, fault location is performed within the target fault area using the traveling wave method to obtain the partial discharge fault location result of the power collection line of the new energy power station. This method can accurately determine the target fault area corresponding to the power collection line of the new energy power station using the power collection line fault area location model and the power collection line structure type, without requiring excessive fault monitoring devices. Furthermore, the accuracy of partial discharge fault location is ensured by accurately obtaining the target fault area and then performing fault location based on the traveling wave method.

[0089] In one possible implementation, the training process of the fault location model for the power collection line is as follows:

[0090] The system acquires the first historical high-frequency partial discharge pulse signal at the bus end and the second historical high-frequency partial discharge pulse signal at the end of each branch line when a historical fault occurs in the collection lines of different new energy power plants, as well as the corresponding historical fault location results. The branch line where the historical fault location result is located is recorded as the historical fault interval. The system uses the first historical high-frequency partial discharge pulse signal and each of the second historical high-frequency partial discharge pulse signals as inputs and the corresponding historical fault intervals as outputs to train a preset neural network model, thereby obtaining a collection line fault interval location model.

[0091] In one possible implementation, the second processing module 33 can be used to obtain the probability that the collection line structure type corresponding to each suspected fault interval is determined to be a fault interval, denoted as the fault probability; and determine the target fault interval of the collection line of the new energy power station based on the fault probability corresponding to each suspected fault interval.

[0092] In one possible implementation, the second processing module 33 can be used to look up a preset fault probability table to obtain the probability that the collector line structure type corresponding to each suspected fault interval is determined to be a fault interval; wherein, the preset fault probability table is a correspondence table between each collector line structure type and the probability that each collector line structure type is determined to be a fault interval.

[0093] In one possible implementation, the second processing module 33 can be used to obtain the proportion of the collection line structure type corresponding to each suspected fault interval to the different collection line structure types in the collection line of the new energy power station; and obtain the probability that the collection line structure type corresponding to each suspected fault interval is determined to be a fault interval based on the proportion, denoted as the fault probability.

[0094] In one possible implementation, the second processing module 33 can be used to determine a first correction coefficient according to the ratio; and to correct the initial probability that the collector line structure type corresponding to each suspected fault interval is determined to be a fault interval according to the first correction coefficient, so as to obtain the probability that the collector line structure type corresponding to each suspected fault interval is determined to be a fault interval, denoted as the fault probability.

[0095] In one possible implementation, the second processing module 33 can be used to determine the suspected fault interval corresponding to the maximum value of each of the suspected fault intervals as the target fault interval of the new energy power station collection line if there is a suspected fault interval with a fault probability greater than a preset probability threshold.

[0096] In one possible implementation, the second processing module 33 can also be used to, if there is no suspected fault interval with a probability greater than the preset probability threshold in the fault probability corresponding to each suspected fault interval, acquire the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line before and / or after the fault of the new energy power station collection line, and re-execute the step of "obtaining the suspected fault interval corresponding to the new energy power station collection line based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal and the collection line fault interval location model" and subsequent steps.

[0097] In one possible implementation, the acquisition module 31 can be used to acquire environmental information when a fault occurs in the power collection line of a new energy power station; the second processing module 33 can be used to verify the suspected fault interval according to the power collection line structure type and the environmental information corresponding to each suspected fault interval, and determine the target fault interval corresponding to the power collection line of the new energy power station according to the verification result.

[0098] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0099] Those skilled in the art will recognize that the templates, units, and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0100] If the module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above embodiments of the partial discharge fault location method for power lines. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0101] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for locating partial discharge faults in a current collector line, characterized in that, include: Acquire the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line when a fault occurs in the power collection line of a new energy power station. Based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal and the fault interval location model of the collector line, the suspected fault interval of the collector line of the new energy power station is obtained. The suspected fault interval is verified according to the collection line structure type corresponding to each suspected fault interval, and the target fault interval corresponding to the collection line of the new energy power station is determined according to the verification result. Based on the traveling wave method, the fault location within the target fault range is performed to obtain the partial discharge fault location result of the power collection line of the new energy power station; The suspected fault interval is verified according to the corresponding collector line structure type. Based on the verification results, the target fault interval of the new energy power station collector line is determined, including: The probability that the collector line structure type corresponding to each suspected fault interval is identified as a fault interval is obtained, denoted as the fault probability; The target fault range of the power collection line of the new energy power station is determined based on the fault probability corresponding to each suspected fault range.

2. The method for locating partial discharge faults in a collector line according to claim 1, characterized in that, The training process of the fault location model for the power collection line is as follows: The first historical high-frequency partial discharge pulse signal at the bus end and the second historical high-frequency partial discharge pulse signal at the end of each branch line when a historical fault occurs in the collection line of different new energy power stations are obtained, along with the corresponding historical fault location results. The branch line where the historical fault location results are located is recorded as the historical fault interval. Using the first historical high-frequency partial discharge pulse signal and each of the second historical high-frequency partial discharge pulse signals as inputs, and the corresponding historical fault intervals as outputs, a preset neural network model is trained to obtain a fault interval location model for the power collection line.

3. The method for locating partial discharge faults in a collector line according to claim 1, characterized in that, Obtaining the probability that the collector line structure type corresponding to each of the suspected fault intervals is identified as a fault interval includes: The probability of a collector line structure type being identified as a fault interval is obtained by looking up the data in the preset fault probability table; wherein, the preset fault probability table is a table showing the correspondence between each collector line structure type and the probability of each collector line structure type being identified as a fault interval.

4. The method for locating partial discharge faults in a collector line according to claim 1, characterized in that, The probability that the collector line structure type corresponding to each suspected fault interval is identified as a fault interval is obtained, denoted as the fault probability, including: Obtain the proportion of each suspected fault section corresponding to the collector line structure type to the different collector line structure types in the new energy power station's collector lines; The probability that the collector line structure type corresponding to each suspected fault interval is identified as a fault interval is obtained based on the ratio, and is denoted as the fault probability.

5. The method for locating partial discharge faults in a collector line according to claim 4, characterized in that, The probability that the collector line structure type corresponding to each suspected fault interval is identified as a fault interval is obtained based on the aforementioned ratio, denoted as the fault probability, including: The first correction factor is determined based on the stated ratio; The initial probability that the collector line structure type corresponding to each suspected fault interval is determined to be a fault interval is corrected according to the first correction coefficient, and the probability that the collector line structure type corresponding to each suspected fault interval is determined to be a fault interval is obtained, which is denoted as the fault probability.

6. The method for locating partial discharge faults in a collector line according to claim 1, characterized in that, Based on the fault probability corresponding to each suspected fault interval, the target fault interval of the power collection line of the new energy power station is determined, including: If there is a suspected fault interval with a probability greater than a preset probability threshold among the fault probabilities corresponding to each suspected fault interval, then the suspected fault interval corresponding to the maximum value among the fault probabilities is determined as the target fault interval of the new energy power station's collection line.

7. The method for locating partial discharge faults in a collector line according to claim 6, characterized in that, Also includes: If there is no suspected fault interval with a probability greater than the preset probability threshold in the fault probability corresponding to each suspected fault interval, then the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line are obtained before and / or after the fault occurs in the new energy power station collection line, and the steps of "obtaining the suspected fault interval corresponding to the new energy power station collection line based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal and the collection line fault interval location model" and subsequent steps are re-executed.

8. The method for locating partial discharge faults in a collector line according to claim 1, characterized in that, Also includes: Obtain environmental information when a fault occurs in the power collection lines of a new energy power station; The suspected fault interval is verified according to the structure type of the collector line corresponding to each suspected fault interval. Based on the verification results, the target fault interval corresponding to the collector line of the new energy power station is determined, including: The suspected fault interval is verified based on the collection line structure type and environmental information corresponding to each suspected fault interval, and the target fault interval corresponding to the collection line of the new energy power station is determined based on the verification results.

9. A device for locating partial discharge faults in a current collector line, characterized in that, include: The acquisition module is used to acquire the first high-frequency partial discharge pulse signal at the bus end and the second high-frequency partial discharge pulse signal at the end of each branch line when a fault occurs in the power collection line of the new energy power station. The first processing module is used to obtain the suspected fault range of the power collection line of the new energy power station based on the first high-frequency partial discharge pulse signal, the second high-frequency partial discharge pulse signal and the fault range location model of the power collection line. The second processing module is used to verify the suspected fault section according to the collection line structure corresponding to each suspected fault section, and to determine the target fault section of the collection line of the new energy power station based on the verification result. The fault location module is used to locate faults within the target fault range based on the traveling wave method, and to obtain the partial discharge fault location results of the power collection lines of the new energy power station. The second processing module is specifically used for: The probability that the collector line structure type corresponding to each suspected fault interval is identified as a fault interval is obtained, denoted as the fault probability; The target fault range of the power collection line of the new energy power station is determined based on the fault probability corresponding to each suspected fault range.

Images