Affinity propagation clustering high-voltage cable partial discharge positioning method and system

Abstract

The invention discloses an affinity propagation clustering high-voltage cable partial discharge positioning method and system, and relates to the technical field of high-voltage cable partial discharge detection, and the method comprises the following steps: installing an ultrahigh frequency sensor, and measuring the electromagnetic wave of partial discharge; a plurality of partial discharge power sources are arranged to simulate a discharge source; positioning calibration points are selected, two ultrahigh-frequency sensors collect ultrahigh-frequency electromagnetic wave amplitudes of the calibration points in the discharging process, and a calibration database is established; when partial discharge occurs, collecting a group of signal amplitudes, inputting the group of signal amplitudes into a calibration database, and analyzing by adopting an affinity propagation clustering algorithm; and the acquired data is compared with the coordinates of the calibration points of the same category in the database, and the obtained result is the positioning result of the partial discharge. According to the positioning algorithm, the influence of the discharge type on the positioning result is overcome, the robustness is high, the positioning precision is good, and the effectiveness of the positioning algorithm is verified.

Description

Technical Field

[0001] The invention relates to the technical field of local discharge detection of high-voltage cables, and in particular to a local discharge positioning method and system for high-voltage cables based on affinity propagation clustering. Background Art

[0002] Partial discharge location is an interdisciplinary research field worldwide, which involves the integration of multiple disciplines such as power systems, materials science, acoustics, signal processing and data analysis. With the development of smart grid technology and the increasing concern for environmental sustainability, partial discharge detection technology has become particularly important in improving the energy efficiency of power systems and reducing environmental impact. A series of international standards developed by organizations such as the International Electrotechnical Commission (IEC) and the International Organization for Standardization (ISO) provide a unified framework and guidance for the detection, evaluation and equipment certification of partial discharge. Research institutions and universities around the world are working in interdisciplinary collaboration to develop new detection technologies, such as ultra-high frequency (UHF) sensing technology and artificial intelligence algorithms, to improve the sensitivity and accuracy of partial discharge detection. At the same time, global cooperative projects and research programs, as well as the participation of power equipment manufacturers, are promoting the development and innovation of partial discharge detection technology. The popularization of education and training, as well as the investment of government and private funds, have further accelerated the advancement of technology in this field, making partial discharge location technology one of the key technologies to ensure the safe and stable operation of power systems.

[0003] Partial discharge is one of the common fault phenomena in power equipment, which usually occurs in the tip organ part of the equipment. The occurrence of partial discharge is not only a manifestation of the decline of the insulation performance of the equipment, but also has a significant impact on the insulation performance of the equipment. In severe cases, it may even cause insulation breakdown of the equipment, causing equipment damage and ultimately leading to power accidents. Therefore, the detection and location of partial discharge of power equipment is of great significance to ensure the safe and stable operation of power equipment.

[0004] With the development and progress of urban power grids, power cables are increasingly used and have become one of the most important power equipment. In the most commonly used cross-linked polyethylene insulated cables (XLPE cables), partial discharge often occurs due to factors such as burrs and equipment processes. This makes partial discharge detection and positioning one of the important means to discover XLPE cable defects, helping staff to quickly locate defective points, troubleshoot faults in a timely manner, and prevent the development and expansion of faults.

[0005] At present, the commonly used methods for detecting and locating partial discharge of cross-linked polyethylene cables are mainly ultrasonic method and arrival time method. Among them, the ultrasonic method is easily affected by attenuation in power cables and has poor positioning accuracy. The arrival time method realizes positioning through the arrival time of electromagnetic waves. During the positioning process, electromagnetic waves are prone to reflection and dispersion, resulting in inaccurate time measurement and inability to guarantee positioning accuracy. Therefore, it is necessary to propose new local positioning methods, such as: affinity propagation clustering local discharge positioning method for high-voltage cables. Summary of the invention

[0006] In view of the problems existing in the existing high-voltage cable partial discharge positioning and system based on affinity propagation clustering, the present invention is proposed.

[0007] Therefore, the problem to be solved by the present invention is the rapid feature attenuation and significant positioning error existing in the traditional method.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, an embodiment of the present invention provides a method for locating partial discharge of a high-voltage cable based on affinity propagation clustering, which comprises the following steps:

[0010] Install ultra-high frequency sensors to measure electromagnetic waves of partial discharge;

[0011] Set up multiple partial discharge sources to simulate discharge sources;

[0012] Select the calibration points for positioning, use two UHF sensors to collect the UHF electromagnetic wave amplitude during the discharge process at each calibration point, and establish a calibration database;

[0013] When partial discharge occurs, a set of signal amplitudes is collected, input into the calibration database, and analyzed using affinity propagation clustering algorithm;

[0014] The collected data is compared with the coordinates of the calibration points of the same category in the database, and the result is the location result of the partial discharge.

[0015] As a preferred solution of the high-voltage cable partial discharge location method based on affinity propagation clustering described in the present invention, the step of establishing a calibration database includes:

[0016] A section of cable is selected and UHF sensors are installed at both ends of the cable to collect UHF electromagnetic waves generated by partial discharge;

[0017] Select N points in the cable as calibration points and record the coordinates of each calibration point;

[0018] The simulated partial discharge power is used to discharge at these calibration points, and the UHF sensors at both ends are used to collect the amplitude of the UHF electromagnetic waves generated by the discharge in real time to establish a calibration database;

[0019] Among them, after the calibration database is established, when local discharge occurs, the amplitudes of this group of signals are clustered and analyzed according to the amplitudes in the calibration database, and the coordinates of the calibration points that belong to the same category as the amplitudes of this group of signals are the positioning results of the local discharge.

[0020] As a preferred solution of the affinity propagation clustering method for localizing partial discharge of high-voltage cables described in the present invention, the affinity propagation clustering algorithm analysis step includes:

[0021] First, construct a similarity matrix. Suppose there are G clustering objects, represented by, i = 1, 2, ..., G, then the similarity between any two objects is represented by s(i, j);

[0022] The similarity between an object and itself is represented by a constant, so the similarity expression between objects is:

[0023]

[0024] Among them, W represents a constant, so the similarity matrix S between objects is constructed:

[0025]

[0026] After obtaining the similarity matrix, an iterative process can be performed to finally obtain the clustering result.

[0027] As a preferred solution of the high-voltage cable partial discharge location method based on affinity propagation clustering of the present invention, the iterative process of the affinity propagation clustering algorithm includes:

[0028]

[0029] In the iteration, the variable res(i,j) represents the responsiveness of object i to object j, indicating the confidence of object i in identifying object j as the center point. Similarly, the variable ava(i,j) represents the degree of utilization of object j to object i, indicating the confidence of object j in identifying itself as the center point of object i.

[0030] ″″

[0031] Where t represents the number of iterations, i∈(1,2,…,G), i≠i, j∈(1,2,…,G), j≠j.

[0032] As a preferred solution of the high-voltage cable partial discharge location method based on affinity propagation clustering of the present invention, the condition for any object k (k=(1, 2), G) to become the center point in the cluster objects is specifically expressed as:

[0033] res (t+1) (k,k)+ava (t+1) (k,k)>0;

[0034] Through iteration, a group of center points can be generated, and for an object, the center point in the group has the lowest similarity value;

[0035] The condition for the algorithm iteration process to end is: the number of iterations reaches the set maximum value, or the element composition of the center point group remains unchanged in M ​​consecutive iterations.

[0036] As a preferred solution of the high-voltage cable partial discharge location method based on affinity propagation clustering described in the present invention, in which: in each iteration process, the iteration factor λ is used to update res(i,j) and ava(i,j), which is specifically expressed as:

[0037] res (t+1) (i,j)=(1-λ)res (t+1) (i,j)+λres (t) (i,j);

[0038] ava (t+1) (i,j)=(1-λ)ava (t+1) (i,j)+λava (t) (i,j);

[0039] The iteration factor λ ranges from 0 to 1.

[0040] As a preferred solution of the affinity propagation clustering high-voltage cable partial discharge location method of the present invention, it also includes an adaptive feedback mechanism;

[0041] The adaptive feedback mechanism is: intelligently comparing the extracted features with the features of the calibration point coordinates pre-stored in the database, using a deep learning algorithm to improve the accuracy of the matching, thereby determining the precise location of the partial discharge.

[0042] In a second aspect, an embodiment of the present invention provides a high-voltage cable partial discharge location system based on affinity propagation clustering, which includes a data acquisition module, a calibration module, a data analysis module, and a location module;

[0043] The data acquisition module is responsible for collecting the signal data detected by the sensor in real time, providing input for subsequent analysis and positioning;

[0044] The calibration module is the core of the positioning system and is used to store and compare data of actual discharge events for accurate positioning;

[0045] The data analysis module is responsible for processing and analyzing the collected signal data, using a specific algorithm to identify and classify signal features, and providing a basis for positioning;

[0046] The positioning module compares the collected data with the coordinates of the calibration points of the same category in the database to obtain the positioning result of the partial discharge.

[0047] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned affinity propagation clustering high-voltage cable partial discharge location method.

[0048] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned affinity propagation clustering method for localizing partial discharge of high-voltage cables is implemented.

[0049] The beneficial effects of the present invention are as follows: positioning is performed using the amplitude of ultra-high frequency electromagnetic waves generated by partial discharge. First, multiple cable positions are selected as positioning calibration points by simulating the partial discharge source, and discharge is performed at these points to record the amplitude of the discharge signal, thereby establishing a calibration database. When partial discharge actually occurs, these data are imported into the calibration database, cluster analysis is performed using the affinity propagation clustering algorithm, and the position of the partial discharge is calculated. Experimental verification shows that the average positioning error of this method is about 1 meter, showing high positioning accuracy and good robustness, and providing an effective solution for partial discharge positioning of power cables. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0051] Figure 1 Flowchart of the localization method for partial discharge in high-voltage cables based on affinity propagation clustering.

[0052] Figure 2 Diagram of partial discharge position calibration strategy for high voltage cable partial discharge location method based on affinity propagation clustering.

[0053] Figure 3Model diagram of partial discharge for high voltage cable partial discharge location method based on affinity propagation clustering.

[0054] Figure 4 This is a positioning result in the experiment. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0056] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0057] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0058] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0059] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0060] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0061] Example 1

[0062] Reference Figure 1 to Figure 3 , which is the first embodiment of the present invention, provides a method for locating local discharge of high-voltage cables based on affinity propagation clustering, comprising the following steps:

[0063] S2. Install ultra-high frequency sensors to measure the electromagnetic waves of partial discharge.

[0064] S3. Set up multiple partial discharge power sources to simulate the discharge source.

[0065] S4. Select and locate calibration points, and use two UHF sensors to collect the UHF electromagnetic wave amplitude during the discharge process of each calibration point to establish a calibration database.

[0066] The steps to establish a calibration database include:

[0067] A section of cable is selected and UHF sensors are installed at both ends of the cable to collect UHF electromagnetic waves generated by partial discharge;

[0068] Select N points in the cable as calibration points and record the coordinates of each calibration point;

[0069] The simulated partial discharge power is used to discharge at these calibration points, and the UHF sensors at both ends are used to collect the amplitude of the UHF electromagnetic waves generated by the discharge in real time to establish a calibration database;

[0070] Among them, after the calibration database is established, when local discharge occurs, the amplitudes of this group of signals are clustered and analyzed according to the amplitudes in the calibration database, and the coordinates of the calibration points that belong to the same category as the amplitudes of this group of signals are the positioning results of the local discharge.

[0071] S5. When partial discharge occurs, a group of signal amplitudes are collected, and the group of signal amplitudes are input into the calibration database, and analyzed using the affinity propagation clustering algorithm.

[0072] The analysis steps of affinity propagation clustering algorithm include:

[0073] First, construct a similarity matrix. Suppose there are G clustering objects, represented by, i = 1, 2, ..., G, then the similarity between any two objects is represented by s(i, j);

[0074] The similarity between an object and itself is represented by a constant, so the similarity expression between objects is:

[0075]

[0076] Among them, W represents a constant, so the similarity matrix S between objects is constructed:

[0077]

[0078] After obtaining the similarity matrix, an iterative process can be performed to finally obtain the clustering result.

[0079] The iterative process of the affinity propagation clustering algorithm includes:

[0080]

[0081] In the iteration, the variable res(i,j) represents the responsiveness of object i to object j, indicating the confidence of object i in identifying object j as the center point. Similarly, the variable ava(i,j) represents the degree of utilization of object j to object i, indicating the confidence of object j in identifying itself as the center point of object i.

[0082] ″″

[0083] Where t represents the number of iterations, i∈(1,2,…,G), i≠i, j∈(1,2,…,G), j≠j.

[0084] For any object k (k = (1, 2), G) in the cluster object, the condition for becoming the center point is specifically expressed as:

[0085] res (t+1) (k,k)+ava (t+1) (k,k)>0;

[0086] Through iteration, a group of center points can be generated, and for an object, the center point in the group has the lowest similarity value;

[0087] The condition for the algorithm iteration process to end is: the number of iterations reaches the set maximum value, or the element composition of the center point group remains unchanged in M ​​consecutive iterations.

[0088] In each iteration, the iteration factor λ is used to update res(i,j) and ava(i,j), which can be expressed as follows:

[0089] res (t+1) (i,j)=(1-λ)res (t+1) (i,j)+λres (t) (i,j);

[0090] ava(t+1) (i,j)=(1-λ)ava (t+1) (i,j)+λava (t) (i,j);

[0091] The iteration factor λ ranges from 0 to 1.

[0092] S6. The collected data is compared with the coordinates of the calibration points of the same category in the database, and the result obtained is the location result of the partial discharge.

[0093] It also includes adaptive feedback mechanisms;

[0094] The adaptive feedback mechanism is: intelligently comparing the extracted features with the features of the calibration point coordinates pre-stored in the database, using a deep learning algorithm to improve the accuracy of the matching, thereby determining the precise location of the partial discharge.

[0095] In summary, the amplitude of the ultra-high frequency electromagnetic waves generated by partial discharge is used for positioning. First, multiple cable positions are selected as positioning calibration points by simulating the partial discharge source, and discharge is performed at these points to record the amplitude of the discharge signal, thereby establishing a calibration database. When partial discharge actually occurs, these data are imported into the calibration database, and cluster analysis is performed using the affinity propagation clustering algorithm to calculate the location of the partial discharge. Experimental verification shows that the average positioning error of this method is about 1 meter, showing high positioning accuracy and good robustness, and providing an effective solution for the positioning of partial discharge of power cables.

[0096] Example 2

[0097] On the basis of the first embodiment, this embodiment further provides a high-voltage cable partial discharge location system based on affinity propagation clustering, comprising a data acquisition module, a calibration module, a data analysis module, and a location module;

[0098] The data acquisition module is responsible for collecting the signal data detected by the sensor in real time, providing input for subsequent analysis and positioning;

[0099] The calibration module is the core of the positioning system and is used to store and compare data of actual discharge events for accurate positioning;

[0100] The data analysis module is responsible for processing and analyzing the collected signal data, using a specific algorithm to identify and classify signal features, and providing a basis for positioning;

[0101] The positioning module compares the collected data with the coordinates of the calibration points of the same category in the database to obtain the positioning result of the partial discharge.

[0102] This embodiment also provides a computer device, which is suitable for the high-voltage cable partial discharge positioning method based on affinity propagation clustering, and includes a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the high-voltage cable partial discharge positioning method based on affinity propagation clustering as proposed in the above embodiment.

[0103] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0104] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for locating partial discharge of a high-voltage cable by implementing affinity propagation clustering as proposed in the above embodiment is implemented.

[0105] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0106] Example 3

[0107] On the basis of the previous two embodiments, this embodiment provides a method for locating partial discharge of high-voltage cables based on affinity propagation clustering. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0108] like Figure 4 As described above, the blue dots in the figure represent the amplitude of the calibration point, and the orange dots represent the amplitude of the partial discharge. It can be seen from the figure that the positioning matches the sixth calibration point, so the positioning result is the coordinate of the calibration point.

[0109] The experimental positioning results are shown in Table 1:

[0110] Table 1: Experimental results

[0111]

[0112] As can be seen from Table 1, the positioning results of the four discharge models are relatively close, indicating that the positioning algorithm proposed in this paper overcomes the influence of the discharge type on the positioning results and has high robustness. From the positioning accuracy, it can be seen that the average positioning error is about 1 meter and the maximum error is about 4 meters, indicating that the positioning accuracy is good. It can meet the requirements of maintenance personnel to quickly reach the vicinity of the defect location, verifying the effectiveness of the positioning algorithm in this paper.

[0113] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for locating partial discharge of high-voltage cables based on affinity propagation clustering, characterized by: The following steps are included: Install ultra-high frequency sensors to measure electromagnetic waves of partial discharge; Set up multiple partial discharge sources to simulate discharge sources; Select the calibration points for positioning, use two UHF sensors to collect the UHF electromagnetic wave amplitude during the discharge process at each calibration point, and establish a calibration database; When partial discharge occurs, a set of signal amplitudes is collected, input into the calibration database, and analyzed using affinity propagation clustering algorithm; The collected data is compared with the coordinates of the calibration points of the same category in the database, and the result is the location result of the partial discharge.

2. The high voltage cable partial discharge location method based on affinity propagation clustering as claimed in claim 1, characterized in that: The steps to establish a calibration database include: A section of cable is selected and UHF sensors are installed at both ends of the cable to collect UHF electromagnetic waves generated by partial discharge; Select N points in the cable as calibration points and record the coordinates of each calibration point; The simulated partial discharge power is used to discharge at these calibration points, and the UHF sensors at both ends are used to collect the amplitude of the UHF electromagnetic waves generated by the discharge in real time to establish a calibration database; Among them, after the calibration database is established, when local discharge occurs, the amplitudes of this group of signals are clustered and analyzed according to the amplitudes in the calibration database, and the coordinates of the calibration points that belong to the same category as the amplitudes of this group of signals are the positioning results of the local discharge.

3. The high voltage cable partial discharge location method based on affinity propagation clustering as claimed in claim 2, characterized in that: The analysis steps of affinity propagation clustering algorithm include: First, construct a similarity matrix. Suppose there are G clustering objects, represented by, i = 1, 2, ..., G, then the similarity between any two objects is represented by s(i, j); The similarity between an object and itself is represented by a constant, so the similarity expression between objects is: Among them, W represents a constant, so the similarity matrix S between objects is constructed: After obtaining the similarity matrix, an iterative process can be performed to finally obtain the clustering result.

4. The high voltage cable partial discharge location method based on affinity propagation clustering as claimed in claim 3, characterized in that: The iterative process of the affinity propagation clustering algorithm includes: In the iteration, the variable res(i,j) represents the responsiveness of object i to object j, indicating the confidence of object i in identifying object j as the center point. Similarly, the variable ava(i,j) represents the degree of utilization of object j to object i, indicating the confidence of object j in identifying itself as the center point of object i. ″″ Where t represents the number of iterations, i∈(1,2,…,G), i≠i, j∈(1,2,…,G), j≠j.

5. The high voltage cable partial discharge location method based on affinity propagation clustering as claimed in claim 4, characterized in that: For any object k (k = (1, 2), G) in the cluster object, the condition for becoming the center point is specifically expressed as: res (t+1) (k,k)+ava (t+1) (k,k)>0; Through iteration, a group of center points can be generated, and for an object, the center point in the group has the lowest similarity value; The condition for the algorithm iteration process to end is: the number of iterations reaches the set maximum value, or the element composition of the center point group remains unchanged in M ​​consecutive iterations.

6. The high voltage cable partial discharge location method based on affinity propagation clustering as claimed in claim 5, characterized in that: In each iteration, the iteration factor λ is used to update res(i,j) and ava(i,j), which can be expressed as follows: res (t+1) (i,j)=(1-λ)res (t+1) (i,j)+λres (t) (i,j); ava (t+1) (i,j)=(1-λ)ave (t+1) (i,j)+λleft (t) (i,j); The iteration factor λ ranges from 0 to 1.

7. The high voltage cable partial discharge location method based on affinity propagation clustering as claimed in claim 6, characterized in that: It also includes adaptive feedback mechanisms; The adaptive feedback mechanism is: intelligently comparing the extracted features with the features of the calibration point coordinates pre-stored in the database, using a deep learning algorithm to improve the accuracy of the matching, thereby determining the precise location of the partial discharge.

8. A high-voltage cable partial discharge location system based on affinity propagation clustering, based on the high-voltage cable partial discharge location method based on affinity propagation clustering according to any one of claims 1 to 7, characterized in that: It includes a data acquisition module, a calibration module, a data analysis module, and a positioning module; The data acquisition module is responsible for collecting the signal data detected by the sensor in real time, providing input for subsequent analysis and positioning; The calibration module is the core of the positioning system and is used to store and compare data of actual discharge events for accurate positioning; The data analysis module is responsible for processing and analyzing the collected signal data, using a specific algorithm to identify and classify signal features, and providing a basis for positioning; The positioning module compares the collected data with the coordinates of the calibration points of the same category in the database to obtain the positioning result of the partial discharge.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the high-voltage cable partial discharge location method based on affinity propagation clustering according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the high-voltage cable partial discharge location method based on affinity propagation clustering according to any one of claims 1 to 7 are implemented.

Images