Cable joint fault prediction system and method based on partial discharge signal

Abstract

The embodiment of the invention discloses a cable joint fault prediction system and method based on a partial discharge signal, and the method comprises the steps: receiving and recording the partial discharge signal and a power frequency voltage phase angle of a to-be-detected cable joint in real time, detecting the amplitude of the partial discharge signal, and when the detected amplitude is greater than a preset value, performing fault prediction on the to-be-detected cable joint. Generating a phase resolution partial discharge diagram based on the power frequency voltage phase angle corresponding to the amplitude and a preset discharge diagram generation rule, and obtaining a plurality of pre-stored fault curve diagrams and corresponding associated feature information, and based on the multiple pre-stored fault curve graphs and the corresponding associated feature information, performing segmentation processing on the phase resolution partial discharge graph to obtain multiple to-be-compared sub-graph sets, and performing comparison processing based on the multiple to-be-compared sub-graph sets and the multiple pre-stored fault curve graphs to obtain a fault prediction result. According to the scheme, reasonable fault prediction can be carried out by detecting the partial discharge signal of the cable joint part, and the accuracy and efficiency of fault prediction are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of cable fault prediction, and in particular, to a cable joint fault prediction system and method based on partial discharge signals. Background Art

[0002] The cable joint is the connection point between the various sections of the cable line, which is used to ensure that the cable forms a continuous circuit. Its main function is to make the line unobstructed, keep the cable sealed, and ensure the insulation level at the cable joint to ensure the safe and reliable operation of the cable. Cable joint failure may cause damage or failure of the insulation layer, expose the live conductor, increase the risk of electric shock, and in severe cases may cause electric shock accidents or even death. In addition, cable joint failure may also cause a short circuit, generate a lot of heat, cause the cable sheath to burn, and cause a fire. Therefore, the quality of the cable joint directly affects the stability and safety of the power system, and accurate fault prediction is required.

[0003] In the related technologies, most of them determine whether the cable joint is faulty by detecting the operating parameters at the cable joint or manually perform fault detection on the cable joint regularly. There is a lack of reasonable fault prediction methods for cable joints, and safety hazards of cable joints cannot be discovered in time, which affects the operation of the power system. Summary of the invention

[0004] The embodiment of the present invention provides a cable joint fault prediction system and method based on partial discharge signals, which solves the problem that there is a lack of a reasonable fault prediction method for cable joints in the related art, and the safety hazards of cable joints cannot be discovered in time, which affects the operation of the power system. It can perform reasonable fault prediction by detecting partial discharge signals at the cable joints, thereby improving the accuracy and efficiency of fault prediction.

[0005] In a first aspect, an embodiment of the present invention provides a cable joint fault prediction method based on partial discharge signals, comprising:

[0006] Receive and record the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested in real time, detect the amplitude of the partial discharge signal, and generate a phase-resolved partial discharge map based on the power frequency voltage phase angle corresponding to the amplitude and a preset discharge map generation rule when detecting that the amplitude is greater than a preset value;

[0007] Acquire a plurality of pre-stored fault curve graphs and corresponding associated characteristic information, and segment the phase-resolved partial discharge graph based on the plurality of pre-stored fault curve graphs and corresponding associated characteristic information to obtain a plurality of sub-graph sets to be compared;

[0008] A fault prediction result is obtained by performing comparison processing based on the plurality of sub-graph sets to be compared and the plurality of pre-stored fault curve graphs.

[0009] Optionally, the generating of a phase-resolved partial discharge map based on the power frequency voltage phase angle corresponding to the amplitude and a preset discharge map generating rule includes:

[0010] The phase of the current voltage cycle is determined according to the power frequency voltage phase angle corresponding to the amplitude, whether the phase meets the preset partial discharge map generation condition is determined, and a phase-resolved partial discharge map is generated according to the determination result.

[0011] Optionally, the preset partial discharge map generation condition includes that the stage reaches the end stage of the cycle, and the generating of the phase-resolved partial discharge map according to the determination result includes:

[0012] When the current stage has not reached the end stage of the cycle, continuously receiving the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested until the current voltage cycle ends;

[0013] A phase-resolved partial discharge diagram is generated according to each of the amplitudes in the current voltage cycle and the corresponding power frequency voltage phase angle.

[0014] Optionally, the segmentation process of the phase-resolved partial discharge image based on the plurality of pre-stored fault curve images and the corresponding associated characteristic information to obtain a plurality of sub-image sets to be compared includes:

[0015] Counting the number of images of the pre-stored fault curve diagram, and copying the phase-resolved partial discharge diagram to obtain the number of discharge diagrams to be segmented;

[0016] The plurality of discharge graphs to be segmented are randomly assigned to one of the pre-stored fault curve graphs, and segmentation positions of the corresponding discharge graphs to be segmented are determined according to the associated characteristic information of the plurality of pre-stored fault curve graphs, and segmentation processing is performed to obtain a plurality of sub-graph sets to be compared.

[0017] Optionally, the associated characteristic information includes one or more characteristic phase angle ranges, and the segmentation positions of the corresponding discharge graphs to be segmented are determined according to the associated characteristic information of the plurality of pre-stored fault curve graphs, and segmentation processing is performed to obtain a plurality of sub-graph sets to be compared, including:

[0018] Determine two end point phase angles of the characteristic phase angle range of the pre-stored fault curve diagram, and determine the end point phase angles as corresponding segmentation positions of the discharge diagram to be segmented;

[0019] The discharge graph to be divided is divided at the division positions to obtain a plurality of sub-graphs to be compared, and the plurality of sub-graphs to be compared are combined into a sub-graph set to be compared, wherein the sub-graph to be compared between the two endpoint phase angles is a key comparison sub-graph.

[0020] Optionally, the sub-graph set to be compared includes one or more key comparison sub-graphs and one or more non-key comparison sub-graphs, and the fault prediction result is obtained by performing comparison processing based on the multiple sub-graph sets to be compared and the multiple pre-stored fault curve graphs, respectively, including:

[0021] Performing a similarity comparison between the key comparison sub-images and the non-key comparison sub-images in the plurality of sub-image sets to be compared and the corresponding image parts of the corresponding pre-stored fault curve graphs;

[0022] The fault prediction result is determined according to the similarities corresponding to the key comparison subgraphs and the non-key comparison subgraphs in the plurality of subgraph sets to be compared and the preset fault conditions.

[0023] Optionally, determining the fault prediction result according to the similarities corresponding to the key comparison subgraphs and the non-key comparison subgraphs in the plurality of subgraph sets to be compared and a preset fault condition includes:

[0024] Comparing the similarities corresponding to the key comparison subgraphs in the plurality of subgraph sets to be compared with the first preset similarity respectively, and comparing the similarities corresponding to the non-key comparison subgraphs in the plurality of subgraph sets to be compared with the second preset similarity, wherein the first preset similarity is greater than the second preset similarity;

[0025] When there exists in the set of sub-graphs to be compared a similarity corresponding to a key comparison sub-graph greater than the first preset similarity and a similarity corresponding to a non-key comparison sub-graph greater than the second preset similarity, the fault information associated with the pre-stored fault curve graph corresponding to the set of sub-graphs to be compared is determined as the fault prediction result.

[0026] In a second aspect, an embodiment of the present invention further provides a cable joint fault prediction system based on partial discharge signals, comprising:

[0027] A receiving module is used to receive and record the partial discharge signal and power frequency voltage phase angle of the cable joint to be tested in real time;

[0028] A detection module, used for detecting the amplitude of the partial discharge signal;

[0029] An image generation module, for generating a phase-resolved partial discharge image based on a power frequency voltage phase angle corresponding to the amplitude and a preset discharge image generation rule when it is detected that the amplitude is greater than a preset value;

[0030] An acquisition module, used to acquire a plurality of pre-stored fault curve graphs and corresponding associated characteristic information;

[0031] A segmentation processing module, used for segmenting the phase-resolved partial discharge image based on the plurality of pre-stored fault curve images and the corresponding associated characteristic information to obtain a plurality of sub-image sets to be compared;

[0032] The fault prediction module is used to perform comparison processing based on the multiple sub-graph sets to be compared and the multiple pre-stored fault curve graphs to obtain a fault prediction result.

[0033] In a third aspect, an embodiment of the present invention further provides a cable joint fault prediction device based on partial discharge signals, the device comprising:

[0034] one or more processors;

[0035] a storage device for storing one or more programs,

[0036] When the one or more programs are executed by the one or more processors, the one or more processors implement a cable joint fault prediction method based on partial discharge signals described in an embodiment of the present invention.

[0037] In a fourth aspect, an embodiment of the present invention further provides a storage medium storing computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to execute a cable joint fault prediction method based on partial discharge signals described in an embodiment of the present invention.

[0038] In the embodiment of the present invention, the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested are received in real time and recorded, the amplitude of the partial discharge signal is detected, and when the amplitude is detected to be greater than the preset value, a phase-resolved partial discharge map is generated based on the power frequency voltage phase angle corresponding to the amplitude and the preset discharge map generation rule, and multiple pre-stored fault curves and corresponding associated feature information are obtained. Based on the multiple pre-stored fault curves and the corresponding associated feature information, the phase-resolved partial discharge map is segmented to obtain multiple sub-image sets to be compared, and the multiple sub-image sets to be compared and the multiple pre-stored fault curves are respectively compared to obtain the fault prediction result. This solution solves the problem that there is a lack of reasonable fault prediction methods for cable joints in the related art, the safety hazards of cable joints cannot be discovered in time, and the operation of the power system is affected. It can perform reasonable fault prediction by detecting the partial discharge signal at the cable joint, thereby improving the accuracy and efficiency of fault prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flowchart of a cable joint fault prediction method based on partial discharge signals provided by an embodiment of the present invention;

[0040] Figure 2A flowchart of another cable joint fault prediction method based on partial discharge signals provided by an embodiment of the present invention;

[0041] Figure 3 A schematic diagram of a phase-resolved partial discharge image provided by an embodiment of the present invention;

[0042] Figure 4 A flowchart of another cable joint fault prediction method based on partial discharge signals provided by an embodiment of the present invention;

[0043] Figure 5 A flowchart of another cable joint fault prediction method based on partial discharge signals provided by an embodiment of the present invention;

[0044] Figure 6 A module structure block diagram of a cable joint fault prediction system based on partial discharge signals provided by an embodiment of the present invention;

[0045] Figure 7 A schematic structural diagram of a cable joint fault prediction device based on partial discharge signals provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention, rather than to limit the embodiments of the present invention. It is also necessary to explain that, for ease of description, only parts related to the embodiments of the present invention are shown in the accompanying drawings, rather than all structures.

[0047] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and or or" in the specification and claims represents at least one of the connected objects, and the character "or" generally indicates that the objects associated before and after are in an "or" relationship.

[0048] The cable joint fault prediction method based on partial discharge signal provided in the embodiment of the present application can be applied to the prediction scenario of cable joint fault. The cable joint fault prediction method based on partial discharge signal provided in the embodiment of the present application, the execution subject of each step can be a computer device, which refers to any electronic device with data calculation, processing and storage capabilities, such as mobile phones, PCs (Personal Computers), tablet computers and other terminal devices, and can also be servers and other devices, which are not limited in the embodiment of the present application.

[0049] Figure 1 A flowchart of a cable joint fault prediction method based on partial discharge signals provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, specifically including:

[0050] Step S101, receiving and recording the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested in real time, detecting the amplitude of the partial discharge signal, and generating a phase-resolved partial discharge map based on the power frequency voltage phase angle corresponding to the amplitude and a preset discharge map generation rule when detecting that the amplitude is greater than a preset value.

[0051] Among them, the cable joint to be tested is used to characterize the cable joint waiting for detection. The partial discharge signal can be a physical signal generated by the discharge phenomenon occurring in the local range of the insulation part of the cable joint. The partial discharge signal can be obtained by a partial discharge monitor. The power frequency voltage phase angle refers to the phase difference of the power frequency voltage relative to the reference point. The power frequency voltage phase angle can be calculated by the signal processing of the partial discharge signal by the partial discharge monitor. In one embodiment, when the amplitude of the partial discharge signal of the cable joint is detected to be greater than a preset value, a method for generating a phase-resolved partial discharge map can be to match the power frequency voltage phase angle corresponding to the amplitude greater than the preset value with the preset phase angle, and generate a phase-resolved partial discharge map based on the matching result. Optionally, a method for generating a phase-resolved partial discharge map can be to determine the stage of the current voltage cycle according to the power frequency voltage phase angle corresponding to the amplitude greater than the preset value, determine whether the stage meets the preset partial discharge map generation condition, and generate a phase-resolved partial discharge map according to the determination result. The voltage cycle is relative to the power frequency voltage phase angle. The stage of the current voltage cycle is determined by the power frequency voltage phase angle, and a phase-resolved partial discharge map is generated based on the stage of the current voltage cycle. This can improve the efficiency and accuracy of generating the phase-resolved partial discharge map.

[0052] Step S102: acquiring a plurality of pre-stored fault curve graphs and corresponding associated characteristic information, and segmenting the phase-resolved partial discharge graph based on the plurality of pre-stored fault curve graphs and corresponding associated characteristic information to obtain a plurality of sub-graph sets to be compared.

[0053] Among them, the pre-stored fault curve graph can be a phase-resolved partial discharge curve graph corresponding to different cable joint faults stored in advance. The associated characteristic information can be the curve characteristic data information of the pre-stored fault curve graph. The sub-graph set to be compared is used to characterize the combination of multiple sub-graphs to be compared obtained by segmenting the phase-resolved partial discharge graph. In one embodiment, after obtaining multiple pre-stored fault curve graphs and the corresponding associated characteristic information, the characteristic part curve in the corresponding pre-stored fault curve graph is determined according to the associated characteristic information, and the phase-resolved partial discharge graph is segmented according to the characteristic part curve to obtain multiple sub-graph sets to be compared. Optionally, a segmentation processing method for the phase-resolved partial discharge graph can be to count the number of images of the pre-stored fault curve graph, copy the phase-resolved partial discharge graph to obtain the number of discharge graphs to be segmented, randomly assign multiple discharge graphs to be segmented to a pre-stored fault curve graph, determine the segmentation positions of the corresponding discharge graphs to be segmented according to the associated characteristic information of the multiple pre-stored fault curve graphs, and perform segmentation processing to obtain multiple sub-graph sets to be compared. By allocating a replicated phase-resolved partial discharge graph to each pre-stored fault curve graph and determining the segmentation position of the phase-resolved partial discharge graph according to the characteristic information of the pre-stored fault curve graph, the rationality of the subsequent comparison processing of the sub-graph set to be compared with the pre-stored fault curve graph can be improved.

[0054] Step S103: performing comparison processing based on the plurality of sub-graph sets to be compared and the plurality of pre-stored fault curve graphs to obtain fault prediction results.

[0055] Among them, the fault prediction result can be the prediction information of the fault condition of the cable joint. In one embodiment, after the phase-resolved partial discharge image is segmented to obtain multiple sets of sub-images to be compared, each sub-image to be compared in the multiple sets of sub-images to be compared is respectively compared with the corresponding image part of the corresponding pre-stored fault curve map for similarity, the average similarity of each sub-image to be compared in the set of sub-images to be compared is calculated, and the average similarity of the multiple sets of sub-images to be compared is respectively compared with the preset similarity, and the fault prediction result of the cable joint to be tested is determined according to the comparison result. Optionally, the set of sub-images to be compared includes one or more key comparison sub-images and one or more non-key comparison sub-images. A method for determining the fault prediction result can be to compare the key comparison sub-images and non-key comparison sub-images in the multiple sets of sub-images to be compared with the corresponding image part of the corresponding pre-stored fault curve map for similarity, and determine the fault prediction result according to the similarity corresponding to the key comparison sub-images and non-key comparison sub-images in the multiple sets of sub-images to be compared and the preset fault condition. By comparing the similarities between the key comparison sub-images and non-key comparison sub-images in the sub-image set to be compared and the corresponding image parts of the pre-stored fault curve graph, and then determining the fault prediction results based on the similarities obtained from the comparison and the preset fault conditions, the accuracy and rationality of the fault prediction results can be improved.

[0056] As can be seen from the above, the local discharge signal and the power frequency voltage phase angle of the cable joint to be tested are received in real time and recorded, the amplitude of the local discharge signal is detected, and when the amplitude is detected to be greater than the preset value, a phase-resolved local discharge map is generated based on the power frequency voltage phase angle corresponding to the amplitude and the preset discharge map generation rule, and multiple pre-stored fault curves and corresponding associated feature information are obtained. The phase-resolved local discharge map is segmented based on the multiple pre-stored fault curves and the corresponding associated feature information to obtain multiple sub-image sets to be compared, and the fault prediction results are obtained based on the multiple sub-image sets to be compared and the multiple pre-stored fault curves. This solution solves the problem of the lack of a reasonable fault prediction method for cable joints in the related art, the inability to timely discover the safety hazards of cable joints, and the impact on the operation of the power system. It can perform reasonable fault prediction by detecting the local discharge signal at the cable joint, thereby improving the accuracy and efficiency of fault prediction.

[0057] Figure 2 A flowchart of another cable joint fault prediction method based on partial discharge signals provided by an embodiment of the present invention provides an optional specific method for generating a phase-resolved partial discharge map, such as Figure 2 As shown, specifically including:

[0058] Step S201: receiving and recording the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested in real time, and detecting the amplitude of the partial discharge signal.

[0059] Step S202: when it is detected that the amplitude is greater than a preset value, determine the stage of the current voltage cycle according to the power frequency voltage phase angle corresponding to the amplitude, determine whether the stage meets the preset partial discharge map generation condition, and generate a phase-resolved partial discharge map according to the determination result.

[0060] Among them, the voltage cycle refers to the time interval of the alternating cycle of the positive and negative poles of the voltage in the AC power supply, which is relative to the power frequency voltage phase angle. The preset partial discharge map generation condition can be a pre-set condition that needs to be met to generate a phase-resolved partial discharge map. Optionally, the preset partial discharge map generation condition includes the stage of the current voltage cycle reaching the end stage of the cycle. A method for generating a phase-resolved partial discharge map can be, when the stage of the current voltage cycle has not reached the end stage of the cycle, continuously receiving the partial discharge signal and the power frequency voltage phase angle of the cable connector to be tested until the end of the current voltage cycle, and generating a phase-resolved partial discharge map according to the amplitude of each partial discharge signal in the current voltage cycle and the corresponding power frequency voltage phase angle. An exemplary example may be that the preset value is 8pC, the amplitude of the current partial discharge signal is 9pC, which is greater than the preset value, and the corresponding power frequency voltage phase angle is 60°. The power frequency voltage phase angle range corresponding to the early stage of the voltage cycle is [0°, 120°), the middle stage is [120°, 240°), the late stage is [240°, 360°), and the end stage of the cycle is 360°. Then the current voltage cycle is in the early stage and has not reached the end stage of the cycle. The partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested are continuously received until the end of the current voltage cycle. A phase-resolved partial discharge diagram is generated according to the amplitude of each partial discharge signal in the current voltage cycle and the corresponding power frequency voltage phase angle, such as Figure 3 As shown, Figure 3 A schematic diagram of a phase-resolved partial discharge diagram provided by an embodiment of the present invention, wherein the vertical axis is the amplitude of the partial discharge signal and the horizontal axis is the phase angle of the power frequency voltage. In another embodiment, when the current voltage cycle is in a stage that has not reached the end of the cycle, the phase-resolved partial discharge diagram is generated according to the amplitudes of each partial discharge signal of the previous cycle of the current voltage cycle and the corresponding power frequency voltage phase angle recorded; when the current voltage cycle is in a stage that has reached the end of the cycle, the phase-resolved partial discharge diagram is generated according to the amplitudes of each partial discharge signal of the current voltage cycle and the corresponding power frequency voltage phase angle recorded.

[0061] Step S203: acquiring a plurality of pre-stored fault curve graphs and corresponding associated characteristic information, and segmenting the phase-resolved partial discharge graph based on the plurality of pre-stored fault curve graphs and corresponding associated characteristic information to obtain a plurality of sub-graph sets to be compared.

[0062] Step S204: performing comparison processing based on the plurality of sub-graph sets to be compared and the plurality of pre-stored fault curve graphs to obtain fault prediction results.

[0063] From the above, it can be seen that the stage of the current voltage cycle is determined according to the power frequency voltage phase angle corresponding to the amplitude greater than the preset value, and whether the stage meets the preset partial discharge map generation condition is determined, and the phase-resolved partial discharge map is generated according to the determination result. This solution determines the stage of the current voltage cycle by the power frequency voltage phase angle, and then generates a phase-resolved partial discharge map based on the stage of the current voltage cycle, which can improve the efficiency and accuracy of generating phase-resolved partial discharge maps.

[0064] Figure 4 A flowchart of another cable joint fault prediction method based on partial discharge signals provided by an embodiment of the present invention provides a specific method for segmenting an optional phase-resolved partial discharge image, such as Figure 4 As shown, specifically including:

[0065] Step S301, receiving and recording the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested in real time, detecting the amplitude of the partial discharge signal, and generating a phase-resolved partial discharge map based on the power frequency voltage phase angle corresponding to the amplitude and a preset discharge map generation rule when detecting that the amplitude is greater than a preset value.

[0066] Step S302, obtaining a plurality of pre-stored fault curve graphs and corresponding associated characteristic information, counting the number of images of the pre-stored fault curve graphs, and duplicating the phase-resolved partial discharge graphs to obtain the number of discharge graphs to be segmented.

[0067] The number of images may be the total number of pre-stored fault curve images. The discharge image to be segmented is used to characterize the phase-resolved partial discharge image to be segmented. An exemplary example may be that the plurality of pre-stored fault curve images are respectively pre-stored fault curve images. Figure 1 , Pre-stored fault curve Figure 2 And the stored fault curve Figure 3 , the number of images of the pre-stored fault curve diagram is obtained by counting to be 3, then the phase-resolved partial discharge diagram is copied to obtain 3 phase-resolved partial discharge diagrams, and the 3 phase-resolved partial discharge diagrams are determined as the discharge diagrams to be segmented.

[0068] Step S303: randomly assign the plurality of discharge graphs to be segmented to one of the pre-stored fault curve graphs, determine the segmentation positions of the corresponding discharge graphs to be segmented according to the associated characteristic information of the plurality of pre-stored fault curve graphs, and perform segmentation processing to obtain a plurality of sub-graph sets to be compared.

[0069] Among them, the cutting position is used to characterize the position where the cutting process is performed in the discharge graph to be cut. Optionally, the associated characteristic information includes one or more characteristic phase angle ranges, and the characteristic phase angle range can be the power frequency voltage phase angle range where the fault characteristic part curve in the pre-stored fault curve graph is located. For example, when the cable joint is in poor contact, the increase in the amplitude of the local discharge signal generally occurs in the phase angle range between 0° and 90°. One cutting processing method can be to determine the two end point phase angles of the characteristic phase angle range of the pre-stored fault curve graph, determine the end point phase angle as the corresponding cutting position of the discharge graph to be cut, cut at the cutting position of the discharge graph to be cut to obtain multiple sub-graphs to be compared, and combine the multiple sub-graphs to be compared into a set of sub-graphs to be compared, wherein the sub-graph to be compared between the two end point phase angles is the key comparison sub-graph. An exemplary example can be that the pre-stored fault curve Figure 1 If the characteristic phase angle range is 90° to 180°, the positions of the 90° phase angle and the 180° phase angle in the corresponding discharge graph to be segmented are determined as the segmentation positions, and segmentation is performed to obtain three sub-graphs to be compared, namely, the sub-graph of 0° to 90°, the sub-graph of 90° to 180°, and the sub-graph of 180° to 360° in the discharge graph to be segmented, wherein the sub-graph to be compared from 90° to 180° is the key comparison sub-graph. In another embodiment, the associated characteristic information includes a characteristic amplitude range, a continuous curve within the characteristic amplitude range in a pre-stored fault curve graph is identified, the two endpoint phase angles of the continuous curve are determined, the endpoint phase angles are determined as the segmentation position of the corresponding discharge graph to be segmented, the discharge graph to be segmented is segmented at the segmentation position to obtain multiple sub-graphs to be compared, and the multiple sub-graphs to be compared are combined into a set of sub-graphs to be compared.

[0070] Step S304: performing comparison processing based on the plurality of sub-graph sets to be compared and the plurality of pre-stored fault curve graphs to obtain fault prediction results.

[0071] As can be seen from the above, the number of images of the pre-stored fault curve graph is counted, the phase-resolved partial discharge graph is copied to obtain the discharge graphs to be segmented of the number of images, and the multiple discharge graphs to be segmented are randomly assigned to a pre-stored fault curve graph, and the segmentation positions of the corresponding discharge graphs to be segmented are determined according to the associated characteristic information of the multiple pre-stored fault curve graphs, and segmentation processing is performed to obtain multiple sub-graph sets to be compared. This scheme can improve the rationality of the subsequent comparison processing of the sub-graph set to be compared with the pre-stored fault curve graph by assigning a copied phase-resolved partial discharge graph to each pre-stored fault curve graph, and determining the segmentation position of the phase-resolved partial discharge graph according to the characteristic information of the pre-stored fault curve graph for segmentation.

[0072] Figure 5A flowchart of another cable joint fault prediction method based on partial discharge signals provided by an embodiment of the present invention provides an optional specific method for determining a fault prediction result, such as Figure 5 As shown, specifically including:

[0073] Step S401, receiving and recording the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested in real time, detecting the amplitude of the partial discharge signal, and generating a phase-resolved partial discharge map based on the power frequency voltage phase angle corresponding to the amplitude and a preset discharge map generation rule when detecting that the amplitude is greater than a preset value.

[0074] Step S402: acquiring a plurality of pre-stored fault curve graphs and corresponding associated characteristic information, and segmenting the phase-resolved partial discharge graph based on the plurality of pre-stored fault curve graphs and corresponding associated characteristic information to obtain a plurality of sub-graph sets to be compared.

[0075] Step S403: perform a similarity comparison between the key comparison sub-images and the non-key comparison sub-images in the plurality of sub-image sets to be compared and the corresponding image parts of the corresponding pre-stored fault curve graphs, and determine the fault prediction result according to the corresponding similarities of the key comparison sub-images and the non-key comparison sub-images in the plurality of sub-image sets to be compared and the preset fault conditions.

[0076] Among them, the sub-graph set to be compared includes one or more key comparison sub-graphs and one or more non-key comparison sub-graphs, the key comparison sub-graphs may be sub-graphs to be compared with higher importance, and the non-key comparison sub-graphs may be sub-graphs to be compared with lower importance. Optionally, a method for determining a fault prediction result may be to compare the similarities corresponding to the key comparison sub-graphs in the multiple sub-graph sets to be compared with a first preset similarity, respectively, and to compare the similarities corresponding to the non-key comparison sub-graphs in the multiple sub-graph sets to be compared with a second preset similarity, the first preset similarity being greater than the second preset similarity, and in the case that the similarity corresponding to the key comparison sub-graph in the sub-graph set to be compared is greater than the first preset similarity and the similarity corresponding to the non-key comparison sub-graph is greater than the second preset similarity, the fault information associated with the pre-stored fault curve graph corresponding to the sub-graph set to be compared is determined as the fault prediction result. An exemplary example may be that the sub-graph set a to be compared is compared with a pre-stored fault curve graph. Figure 1 Corresponding, pre-stored fault curve Figure 1 The associated fault information is poor contact, the first preset similarity is 95%, the second preset similarity is 90%, and the key comparison sub-graph in the sub-graph set a to be compared is compared with the pre-stored fault curve Figure 1 The similarity of the corresponding image part is 99%, which is greater than the first preset similarity. Figure 1 and non-key pairs Figure 2With the stored fault curve Figure 1 The similarities of the corresponding image parts are 92% and 94% respectively, which are both greater than the second preset similarity. The similarities corresponding to the key comparison sub-graphs and non-key comparison sub-graphs in the other sub-graph sets to be compared do not meet the preset fault conditions, and the poor contact is determined as the fault prediction result of the cable joint to be tested. In another embodiment, the corresponding weights are calculated according to the number of key comparison sub-graphs and non-key comparison sub-graphs in the sub-graph set to be compared, wherein the weight of the key comparison sub-graph is greater than the weight of the non-key sub-graph, and all weights are equal to one, and the similarities corresponding to the key comparison sub-graphs and non-key comparison sub-graphs in the sub-graph set to be compared are multiplied by the corresponding weights and superimposed to obtain a comprehensive similarity, and the comprehensive similarity is compared with the preset similarity. When it is greater than the preset similarity, the fault information associated with the pre-stored fault curve graph corresponding to the sub-graph set to be compared is determined as the fault prediction result.

[0077] From the above, it can be seen that the key comparison sub-images and non-key comparison sub-images in the multiple sub-image sets to be compared are respectively compared with the corresponding image parts of the corresponding pre-stored fault curve graphs for similarity, and the fault prediction results are determined according to the similarities corresponding to the key comparison sub-images and non-key comparison sub-images in the multiple sub-image sets to be compared and the preset fault conditions. This scheme can improve the accuracy and rationality of the fault prediction results by comparing the key comparison sub-images and non-key comparison sub-images in the sub-image sets to be compared with the corresponding image parts of the pre-stored fault curve graphs for similarity, and then determining the fault prediction results according to the various similarities obtained by the comparison and the preset fault conditions.

[0078] Figure 6 This is a module structure block diagram of a cable joint fault prediction system based on partial discharge signals provided by an embodiment of the present invention. The system is used to execute a cable joint fault prediction method based on partial discharge signals provided by the above embodiment, and has functional modules and beneficial effects corresponding to the execution method. Figure 6 As shown, the system specifically includes:

[0079] The receiving module 101 is used to receive and record the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested in real time;

[0080] A detection module 102, configured to detect the amplitude of the partial discharge signal;

[0081] An image generation module 103 is used to generate a phase-resolved partial discharge image based on a power frequency voltage phase angle corresponding to the amplitude and a preset discharge image generation rule when it is detected that the amplitude is greater than a preset value;

[0082] An acquisition module 104 is used to acquire a plurality of pre-stored fault curve graphs and corresponding associated characteristic information;

[0083] A segmentation processing module 105 is used to segment the phase-resolved partial discharge image based on the plurality of pre-stored fault curve graphs and the corresponding associated characteristic information to obtain a plurality of sub-image sets to be compared;

[0084] The fault prediction module 106 is used to perform comparison processing based on the multiple sub-graph sets to be compared and the multiple pre-stored fault curve graphs to obtain a fault prediction result.

[0085] It can be seen from the above scheme that the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested are received in real time and recorded, the amplitude of the partial discharge signal is detected, and when the amplitude is detected to be greater than the preset value, a phase-resolved partial discharge map is generated based on the power frequency voltage phase angle corresponding to the amplitude and the preset discharge map generation rule, and multiple pre-stored fault curves and corresponding associated feature information are obtained. The phase-resolved partial discharge map is segmented based on the multiple pre-stored fault curves and the corresponding associated feature information to obtain multiple sub-image sets to be compared, and the multiple sub-image sets to be compared and the multiple pre-stored fault curves are respectively compared to obtain the fault prediction result. This scheme solves the problem of the lack of reasonable fault prediction methods for cable joints in the related art, the inability to timely discover the safety hazards of cable joints, and the impact on the operation of the power system. It can perform reasonable fault prediction by detecting the partial discharge signal at the cable joint, thereby improving the accuracy and efficiency of fault prediction.

[0086] In a possible embodiment, the image generation module 103 is specifically configured to:

[0087] The phase of the current voltage cycle is determined according to the power frequency voltage phase angle corresponding to the amplitude, whether the phase meets the preset partial discharge map generation condition is determined, and a phase-resolved partial discharge map is generated according to the determination result.

[0088] In a possible embodiment, the image generation module 103 is further configured to:

[0089] When the current stage has not reached the end stage of the cycle, continuously receiving the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested until the current voltage cycle ends;

[0090] A phase-resolved partial discharge diagram is generated according to each of the amplitudes in the current voltage cycle and the corresponding power frequency voltage phase angle.

[0091] In a possible embodiment, the segmentation processing module 105 is specifically used to:

[0092] Counting the number of images of the pre-stored fault curve diagram, and copying the phase-resolved partial discharge diagram to obtain the number of discharge diagrams to be segmented;

[0093] The plurality of discharge graphs to be segmented are randomly assigned to one of the pre-stored fault curve graphs, and segmentation positions of the corresponding discharge graphs to be segmented are determined according to the associated characteristic information of the plurality of pre-stored fault curve graphs, and segmentation processing is performed to obtain a plurality of sub-graph sets to be compared.

[0094] In a possible embodiment, the segmentation processing module 105 is further used to:

[0095] Determine two end point phase angles of the characteristic phase angle range of the pre-stored fault curve diagram, and determine the end point phase angles as corresponding segmentation positions of the discharge diagram to be segmented;

[0096] The discharge graph to be divided is divided at the division positions to obtain a plurality of sub-graphs to be compared, and the plurality of sub-graphs to be compared are combined into a sub-graph set to be compared, wherein the sub-graph to be compared between the two endpoint phase angles is a key comparison sub-graph.

[0097] In a possible embodiment, the fault prediction module 106 is specifically configured to:

[0098] Performing a similarity comparison between the key comparison sub-images and the non-key comparison sub-images in the plurality of sub-image sets to be compared and the corresponding image parts of the corresponding pre-stored fault curve graphs;

[0099] The fault prediction result is determined according to the similarities corresponding to the key comparison subgraphs and the non-key comparison subgraphs in the plurality of subgraph sets to be compared and the preset fault conditions.

[0100] In a possible embodiment, the fault prediction module 106 is further configured to:

[0101] Comparing the similarities corresponding to the key comparison subgraphs in the plurality of subgraph sets to be compared with the first preset similarity respectively, and comparing the similarities corresponding to the non-key comparison subgraphs in the plurality of subgraph sets to be compared with the second preset similarity, wherein the first preset similarity is greater than the second preset similarity;

[0102] When there exists in the set of sub-graphs to be compared a similarity corresponding to a key comparison sub-graph greater than the first preset similarity and a similarity corresponding to a non-key comparison sub-graph greater than the second preset similarity, the fault information associated with the pre-stored fault curve graph corresponding to the set of sub-graphs to be compared is determined as the fault prediction result.

[0103] Figure 7A schematic diagram of the structure of a cable joint fault prediction device based on partial discharge signals provided by an embodiment of the present invention is shown in FIG. Figure 7 As shown, the device includes a processor 201, a memory 202, an input device 203 and an output device 204; the number of processors 201 in the device can be one or more. Figure 7 A processor 201 is taken as an example; the processor 201, memory 202, input device 203 and output device 204 in the device can be connected by a bus or other means. Figure 7 The example of the connection via bus is taken. The memory 202, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions or modules corresponding to a cable joint fault prediction method based on partial discharge signals in an embodiment of the present invention. The processor 201 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 202, that is, realizes the above-mentioned cable joint fault prediction method based on partial discharge signals. The input device 203 can be used to receive input digital or character information, and generate key signal input related to user settings and function control of the device. The output device 204 may include a display device such as a display screen.

[0104] An embodiment of the present invention further provides a storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute a cable joint fault prediction method based on partial discharge signals when executed by a computer processor, the method comprising:

[0105] Receive and record the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested in real time, detect the amplitude of the partial discharge signal, and generate a phase-resolved partial discharge map based on the power frequency voltage phase angle corresponding to the amplitude and a preset discharge map generation rule when detecting that the amplitude is greater than a preset value;

[0106] Acquire a plurality of pre-stored fault curve graphs and corresponding associated characteristic information, and segment the phase-resolved partial discharge graph based on the plurality of pre-stored fault curve graphs and corresponding associated characteristic information to obtain a plurality of sub-graph sets to be compared;

[0107] A fault prediction result is obtained by performing comparison processing based on the plurality of sub-graph sets to be compared and the plurality of pre-stored fault curve graphs.

[0108] It is worth noting that in the above-mentioned embodiment of a cable joint fault prediction method system based on partial discharge signals, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present invention.

[0109] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the embodiments of the present invention are not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the embodiments of the present invention. Therefore, although the embodiments of the present invention are described in more detail through the above embodiments, the embodiments of the present invention are not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the embodiments of the present invention, and the scope of the embodiments of the present invention is determined by the scope of the appended claims.

Claims

1. A cable joint fault prediction method based on partial discharge signals, applied to a server, characterized in that: include: Receive and record the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested in real time, detect the amplitude of the partial discharge signal, and generate a phase-resolved partial discharge map based on the power frequency voltage phase angle corresponding to the amplitude and a preset discharge map generation rule when detecting that the amplitude is greater than a preset value; Acquire a plurality of pre-stored fault curve graphs and corresponding associated characteristic information, and segment the phase-resolved partial discharge graph based on the plurality of pre-stored fault curve graphs and corresponding associated characteristic information to obtain a plurality of sub-graph sets to be compared; A fault prediction result is obtained by performing comparison processing based on the plurality of sub-graph sets to be compared and the plurality of pre-stored fault curve graphs.

2. The cable joint fault prediction method based on partial discharge signal according to claim 1 is characterized in that: The generating of a phase-resolved partial discharge map based on the power frequency voltage phase angle corresponding to the amplitude and a preset discharge map generating rule comprises: The phase of the current voltage cycle is determined according to the power frequency voltage phase angle corresponding to the amplitude, whether the phase meets the preset partial discharge map generation condition is determined, and a phase-resolved partial discharge map is generated according to the determination result.

3. The cable joint fault prediction method based on partial discharge signal according to claim 2 is characterized in that: The preset partial discharge map generation condition includes that the stage reaches the end stage of the cycle, and the phase-resolved partial discharge map is generated according to the determination result, including: When the current stage has not reached the end stage of the cycle, continuously receiving the partial discharge signal and the power frequency voltage phase angle of the cable joint to be tested until the current voltage cycle ends; A phase-resolved partial discharge diagram is generated according to each of the amplitudes in the current voltage cycle and the corresponding power frequency voltage phase angle.

4. The cable joint fault prediction method based on partial discharge signal according to any one of claims 1 to 3, characterized in that: The method of segmenting the phase-resolved partial discharge graph based on the plurality of pre-stored fault curve graphs and the corresponding associated characteristic information to obtain a plurality of sub-graph sets to be compared includes: Counting the number of images of the pre-stored fault curve diagram, and copying the phase-resolved partial discharge diagram to obtain the number of discharge diagrams to be segmented; The plurality of discharge graphs to be segmented are randomly assigned to one of the pre-stored fault curve graphs, and segmentation positions of the corresponding discharge graphs to be segmented are determined according to the associated characteristic information of the plurality of pre-stored fault curve graphs, and segmentation processing is performed to obtain a plurality of sub-graph sets to be compared.

5. The cable joint fault prediction method based on partial discharge signal according to claim 4 is characterized in that: The associated characteristic information includes one or more characteristic phase angle ranges, and the segmentation positions of the corresponding discharge graphs to be segmented are determined according to the associated characteristic information of the plurality of pre-stored fault curve graphs, and segmentation processing is performed to obtain a plurality of sub-graph sets to be compared, including: Determine two end point phase angles of the characteristic phase angle range of the pre-stored fault curve diagram, and determine the end point phase angles as corresponding segmentation positions of the discharge diagram to be segmented; The discharge graph to be divided is divided at the division positions to obtain a plurality of sub-graphs to be compared, and the plurality of sub-graphs to be compared are combined into a sub-graph set to be compared, wherein the sub-graph to be compared between the two endpoint phase angles is a key comparison sub-graph.

6. The cable joint fault prediction method based on partial discharge signal according to any one of claims 1 to 3, characterized in that: The sub-graph set to be compared includes one or more key comparison sub-graphs and one or more non-key comparison sub-graphs, and the fault prediction result is obtained by performing comparison processing based on the multiple sub-graph sets to be compared and the multiple pre-stored fault curve graphs, including: Performing a similarity comparison between the key comparison sub-images and the non-key comparison sub-images in the plurality of sub-image sets to be compared and the corresponding image parts of the corresponding pre-stored fault curve graphs; The fault prediction result is determined according to the similarities corresponding to the key comparison subgraphs and the non-key comparison subgraphs in the plurality of subgraph sets to be compared and the preset fault conditions.

7. The cable joint fault prediction method based on partial discharge signal according to claim 6 is characterized in that: The determining of the fault prediction result according to the similarities corresponding to the key comparison subgraphs and the non-key comparison subgraphs in the plurality of subgraph sets to be compared and the preset fault conditions includes: Comparing the similarities corresponding to the key comparison subgraphs in the plurality of subgraph sets to be compared with the first preset similarity respectively, and comparing the similarities corresponding to the non-key comparison subgraphs in the plurality of subgraph sets to be compared with the second preset similarity, wherein the first preset similarity is greater than the second preset similarity; When there exists in the set of sub-graphs to be compared a similarity corresponding to a key comparison sub-graph greater than the first preset similarity and a similarity corresponding to a non-key comparison sub-graph greater than the second preset similarity, the fault information associated with the pre-stored fault curve graph corresponding to the set of sub-graphs to be compared is determined as the fault prediction result.

8. A cable joint fault prediction system based on partial discharge signals, characterized in that: include: A receiving module is used to receive and record the partial discharge signal and power frequency voltage phase angle of the cable joint to be tested in real time; A detection module, used for detecting the amplitude of the partial discharge signal; An image generation module, for generating a phase-resolved partial discharge image based on a power frequency voltage phase angle corresponding to the amplitude and a preset discharge image generation rule when it is detected that the amplitude is greater than a preset value; An acquisition module, used to acquire a plurality of pre-stored fault curve graphs and corresponding associated characteristic information; A segmentation processing module, used for segmenting the phase-resolved partial discharge image based on the plurality of pre-stored fault curve images and the corresponding associated characteristic information to obtain a plurality of sub-image sets to be compared; The fault prediction module is used to perform comparison processing based on the multiple sub-graph sets to be compared and the multiple pre-stored fault curve graphs to obtain a fault prediction result.

9. A cable joint fault prediction device based on partial discharge signals, the device comprising: one or more processors; A storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the cable joint fault prediction method based on partial discharge signals as described in any one of claims 1 to 7.

10. A storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the cable joint fault prediction method based on partial discharge signals as claimed in any one of claims 1 to 7 when executed by a computer processor.

Images