A method and system for panoramic monitoring of digital power distribution networks based on multidimensional data

Abstract

This invention relates to the field of power distribution network monitoring technology, and is a digital panoramic monitoring method and system for power distribution networks based on multi-dimensional data. The specific method includes: collecting working data from the working surfaces of high-voltage fuse contacts in the power distribution network; analyzing the working data, outputting abnormal feature identification tags and fault feature screening tags, filtering the abnormal feature identification tags based on the fault feature screening tags, quantifying the severity of faults on the working surfaces of the contacts using a fuzzy comprehensive evaluation model, obtaining a quantitative value of the fault severity, and simultaneously generating maintenance strategy suggestions. This invention solves the problems of low fault detection accuracy and the inability to timely and accurately identify and handle complex faults in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of power distribution network monitoring technology, and is a digital panoramic monitoring method and system for power distribution networks based on multidimensional data. Background Technology

[0002] In power systems, high-voltage fuses are critical protection devices, and their operational status directly affects the safety and stability of the power grid. The contact blade is one of the core components of a high-voltage fuse, and the condition of its working contact surface directly impacts the fuse's performance and lifespan. However, existing high-voltage fuse contact blade monitoring methods often suffer from the following problems: Monitoring methods primarily rely on single data sources, such as visual inspection or simple electrical parameter measurements, lacking comprehensive support from multi-dimensional data, leading to insufficient accuracy in fault identification. Simultaneously, fault identification strategies are mostly based on rule-based systems, making it difficult to adapt to complex fault modes, easily resulting in missed faults or false alarms. Furthermore, existing monitoring systems lack adaptability and cannot dynamically optimize monitoring strategies according to the actual operating environment. Traditional periodic maintenance strategies are inefficient, potentially leading to over-maintenance and increased costs, or even causing faults due to untimely maintenance. These problems severely restrict the safety and efficiency of power grid operation. Summary of the Invention

[0003] The technical problem to be solved by the present invention is that the fault detection accuracy is low and complex faults cannot be identified and processed in a timely and accurate manner in the existing technology. The present invention proposes a digital distribution network panoramic monitoring method and system based on multi-dimensional data.

[0004] To achieve the above objectives, the technical solution of the present invention, a digital distribution network panoramic monitoring method based on multi-dimensional data, includes the following steps:

[0005] The working data of the contact blade working surface of the high-voltage fuse in the power distribution network is collected using data acquisition equipment.

[0006] Analyze the working data, configure the abnormal feature identification strategy based on the analysis results, output abnormal feature identification tags, and identify abnormal features of high voltage fuses based on the abnormal feature identification tags.

[0007] Based on the historical surface state data of the non-working contact surface of the blade, a fault feature filtering strategy is configured synchronously, fault feature filtering labels are output, and abnormal feature identification labels are filtered according to the fault feature filtering labels.

[0008] A fuzzy comprehensive evaluation model is constructed, and the severity of the fault on the working contact surface of the contact knife is quantitatively calculated using the fuzzy comprehensive evaluation model to obtain a quantitative value of the fault severity.

[0009] Establish a digital maintenance strategy generation model, input the quantitative value of the fault severity into the digital maintenance strategy generation model, and generate maintenance strategy suggestions.

[0010] Specifically, the data acquisition includes: acquiring a microscopic image of the working contact surface of the high-voltage fuse blade using a high-resolution microscope camera; obtaining X-ray fluorescence spectral data of the working contact surface of the blade using a miniature X-ray fluorescence spectrometer; and obtaining local electric field spectral data of the working contact surface of the blade using a local electric field spectral analyzer.

[0011] Specifically, the anomaly feature identification strategy includes:

[0012] S21: Extract the surface microscopic image and convert it into a grayscale image. Normalize the image pixel values ​​to the range of [0,1] and use a bilateral filter to denoise the image.

[0013] S22: Calculate the local texture gradient G(a) of the surface surrounding image using the Sobel operator, and obtain the adjustment scale s(a) based on the local texture gradient;

[0014] Preferably, These represent the brightness gradients of the a-th pixel in the horizontal and vertical directions, respectively.

[0015] Preferably, s0 is the initial scale.

[0016] G max G min These are the minimum and maximum values ​​of the local texture gradient, respectively, and μ is the sensitivity coefficient;

[0017] S23: Adaptively adjust the shape of the basic wavelet basis function using local texture gradients, wherein the adaptive adjustment includes: in, For the adaptively adjusted wavelet basis functions, Based on wavelet basis functions;

[0018] Preferably, the basic wavelet basis functions include, but are not limited to: Symlet-8 wavelet basis functions and Daubechies wavelet basis functions;

[0019] S24: Select J=5 scales and K=4 directions to perform NSW multi-scale decomposition, extract multi-scale wavelet coefficients, and process the wavelet coefficients through an adaptive filter. NSW is a non-stationary wavelet transform.

[0020] S25: Use an autoregressive model to model the distribution of wavelet coefficients and set the standard range of model residuals. When the predicted residuals of wavelet coefficients deviate from the standard range of model residuals, mark the corresponding regions of wavelet coefficients in the surface micro-image as abnormal feature regions. The order of the autoregressive model is 3.

[0021] Specifically, the anomaly feature identification strategy further includes:

[0022] S26: Obtain the area and center of each abnormal feature region in the surface microscopic image, and calculate the equivalent circular radius r of each abnormal feature region based on the area.

[0023] Using the center of the region as the center, fill each abnormal feature region with a circular region with a radius of 1.5r, and set the part of the filled circular region that does not overlap with the abnormal feature region as the damage comparison region;

[0024] S27: Extract local X-ray fluorescence spectral data for each abnormal feature region and the damage contrast region, and calculate the damage assessment coefficient sh according to the damage assessment strategy. n The damage assessment strategy is specifically as follows:

[0025]

[0026] Among them, BL n BL n ′ represents the ratio of trace elements in the nth abnormal feature region and the damage comparison domain, respectively; BO n ,BO n ′ represents the micro-oxygen content in the nth abnormal feature region and the damage comparison region, respectively;

[0027] Preferably, the ratios of trace elements include, but are not limited to, the copper-zinc ratio and the iron-nickel ratio;

[0028] α1 and α2 are the area proportion coefficients of the nth abnormal feature region and the damaged comparison region, respectively.

[0029] Specifically, the anomaly feature identification strategy further includes:

[0030] S28: Identify the center of maximum electric field intensity in each anomalous feature region using local electric field spectrum data. Divide a circular region with a radius of 1.5r centered on the center of maximum electric field intensity. Set the part of the divided circular region that does not overlap with the anomalous feature region as the first electric field distortion comparison domain. Set the part of the anomalous feature region that does not overlap with the divided circular region as the second electric field distortion comparison domain. Set the part of the divided circular region that overlaps with the anomalous feature region as the distortion interest domain of the nth anomalous feature region.

[0031] S29: Calculate and obtain the distortion evaluation coefficient jb according to the electric field distortion evaluation strategy. n The electric field distortion assessment strategy is specifically as follows:

[0032]

[0033] Among them, DR n ,DR n ′,DR n "These are the capacitance values ​​of the distortion interest region, the first electric field distortion comparison region, and the second electric field distortion comparison region of the nth abnormal feature region, respectively;

[0034] β1 represents the area proportion coefficient of the nth abnormal feature region;

[0035] β2 represents the area ratio coefficient of the first electric field distortion comparison domain;

[0036] β3 represents the area ratio coefficient of the second electric field distortion contrast domain.

[0037] Specifically, the configuration of the fault feature screening strategy includes the following steps:

[0038] S31: After the contact blade of the high-voltage fuse completed the previous historical fuse failure, identify the obtained historical abnormal feature areas, wherein the total number of the historical abnormal feature areas is M;

[0039] S32: Extract the location of each historical abnormal feature region on the working contact surface of the stent and map it to the non-working contact surface of the stent. At the same time, mark the same location on the non-working contact surface of the stent to form a sequence of key observation locations.

[0040] S33: During the current fusing process of the contact blade of the high-voltage fuse, acquire historical surface state data of each key observation area in the key observation position sequence. The historical surface state data includes: surface temperature data and surface stress data.

[0041] S34: Based on historical surface state data of the non-working contact surface of the blade, synchronously configure the fault feature filtering strategy and output the fault feature filtering label gz. m The fault feature screening strategy includes:

[0042]

[0043] Among them, gz(1) m Filter sub-labels for the first fault characteristic;

[0044]

[0045] wd m This represents the temperature value of the m-th key observation area;

[0046] The average temperature of M key observation areas on the non-working contact surface of the blade;

[0047] wd max ,wd min These are the maximum and minimum temperature values ​​for M key observation areas on the non-working contact surface of the blade, respectively.

[0048] gz(2) m Filter sub-labels for the second fault characteristics;

[0049]

[0050] yl m This represents the stress value of the m-th key observation area;

[0051] The average stress value of M key observation areas on the non-working contact surface of the blade;

[0052] yl max ,yl min These are the maximum and minimum stress values ​​for M key observation areas on the non-working contact surface of the blade, respectively.

[0053] S35: Filter the abnormal feature identification tags according to the fault feature filtering tags. The filtering strategy includes: assigning an initial distance weight q to the abnormal feature area identified by the contactor after the completion of this fuse breaking operation. n And calculate the weight adjustment factor by filtering labels based on fault characteristics. D n,m D0 is the straight-line distance between the centers of the nth abnormal feature region and the mth historical abnormal feature region; D0 is the preset standard fault masking distance.

[0054] S36: Based on S35, calculate the update distance weight q′ for each abnormal feature region after the contactor completes this fuse-breaking operation. n The updated distance weight is the product of the initial distance weight and the weight adjustment factor.

[0055] Specifically, the calculation strategy for the quantification value of the fault severity is as follows:

[0056]

[0057] LH represents the quantification of the fault severity of the contact blade of a high-voltage fuse in the distribution network.

[0058] Specifically, the maintenance strategy recommendation includes: setting the initial monitoring frequency to W times of fuse failure operation, and simultaneously setting a first alarm value and a second alarm value for the severity of the fault;

[0059] After W blows of the same contact of the high-voltage fuse, when the first detection of a fault severity quantification value greater than or equal to the first alarm value, an offline maintenance recommendation is output.

[0060] When the detected fault severity quantification value is greater than the second alarm value but less than the first alarm value, the corresponding sequence number of the fuse operation is extracted.

[0061] If the corresponding circuit breaker operation sequence numbers are all consecutive, increase the monitoring frequency and adjust the monitoring frequency to W-1 times.

[0062] If the sequence number of the corresponding meltdown operation is not consecutive, output a suggestion to perform periodic surface repair on the contact tool;

[0063] When the monitored fault severity quantification values ​​are all less than the second alarm value, a signal indicating that the distribution network is operating normally in this initial monitoring frequency is output.

[0064] In addition, the digital power distribution network panoramic monitoring system based on multi-dimensional data of the present invention includes the following modules:

[0065] The system includes a contact surface data acquisition module, an abnormal feature identification module, a fault feature screening module, a fault quantification module, and a maintenance strategy generation module.

[0066] The contact data acquisition module collects working data of the working contact surface of the high-voltage fuse in the power distribution network during the current fuse operation through data acquisition equipment.

[0067] The anomaly feature identification module is used to analyze working data, configure anomaly feature identification strategies based on the analysis results, output anomaly feature identification tags, and identify anomalies in high-voltage fuses based on these tags.

[0068] The fault feature screening module, based on historical surface state data of the non-working contact surface of the blade, synchronously configures a fault feature screening strategy, outputs fault feature screening tags, and filters abnormal feature identification tags according to the fault feature screening tags.

[0069] The fault quantification module is used to construct a fuzzy comprehensive evaluation model and to quantify the severity of faults on the working contact surface of the contact knife through the fuzzy comprehensive evaluation model, thereby obtaining a quantified value of the severity of the fault.

[0070] The maintenance strategy generation module is used to establish a digital maintenance strategy generation model, input the quantified value of the fault severity into the digital maintenance strategy generation model, and generate maintenance strategy suggestions.

[0071] A storage medium storing instructions, which, when read by a computer, cause the computer to execute the aforementioned method for panoramic monitoring of a digital power distribution network based on multidimensional data.

[0072] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for panoramic monitoring of a digital power distribution network based on multidimensional data.

[0073] Compared with the prior art, the technical effects of the present invention are as follows:

[0074] 1. This invention integrates multiple data acquisition devices such as a high-resolution microscope camera, a miniature X-ray fluorescence spectrometer, and a local electric field spectrum analyzer, enabling comprehensive acquisition of working data of high-voltage fuse contacts from multiple dimensions. This not only greatly enhances the richness and diversity of the data but also provides a more comprehensive reflection of the actual working status of the contacts, thereby improving the reliability of fault identification.

[0075] 2. This invention employs a multi-stage anomaly feature recognition strategy, combined with the processing of surface microscopic images, analysis of X-ray fluorescence spectral data and local electric field spectrum data, to accurately identify abnormal feature regions on the surface of the contact blade. In particular, by utilizing the Sobel operator to calculate local texture gradients, adaptively adjusting wavelet basis functions, and multi-scale decomposition of the autoregressive model, the identification of subtle fault features becomes more accurate, effectively reducing the probability of missed fault detections and false alarms.

[0076] 3. This invention uses a synchronous configuration fault feature screening strategy and historical surface state data of the non-working contact surface of the contact blade to screen and evaluate currently identified abnormal features. Through comprehensive analysis of temperature and stress data of historical abnormal feature areas, the system can more accurately predict and identify potential fault areas, thus improving the accuracy of fault prediction. Attached Figure Description

[0077] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0078] in:

[0079] Figure 1This is a flowchart illustrating a digital power distribution network panoramic monitoring method based on multidimensional data according to the present invention.

[0080] Figure 2 This is a schematic diagram of the structure of a digital power distribution network panoramic monitoring system based on multidimensional data according to the present invention. Detailed Implementation

[0081] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0082] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0083] 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 phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0084] Example 1:

[0085] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for panoramic monitoring of a digital power distribution network based on multidimensional data, such as... Figure 1 As shown, the specific steps include the following:

[0086] The working data of the contact blade working surface of the high-voltage fuse in the power distribution network is collected using data acquisition equipment.

[0087] The data acquisition process includes: acquiring microscopic images of the working contact surface of the high-voltage fuse using a high-resolution microscope camera; obtaining X-ray fluorescence spectral data of the working contact surface using a miniature X-ray fluorescence spectrometer; and obtaining local electric field spectral data of the working contact surface using a local electric field spectral analyzer.

[0088] Analyze the working data, configure the abnormal feature identification strategy based on the analysis results, output abnormal feature identification tags, and identify abnormal features of high voltage fuses based on the abnormal feature identification tags.

[0089] The abnormal feature identification strategy includes:

[0090] S21: Extract the surface microscopic image and convert it into a grayscale image. Normalize the image pixel values ​​to the range of [0,1] and use a bilateral filter to denoise the image.

[0091] S22: Calculate the local texture gradient G(a) of the surface surrounding image using the Sobel operator, and obtain the adjustment scale s(a) based on the local texture gradient;

[0092] S23: Adaptively adjust the shape of the basic wavelet basis function using local texture gradients, wherein the adaptive adjustment includes: in, For the adaptively adjusted wavelet basis functions, Based on wavelet basis functions;

[0093] For example, in this embodiment, the basic wavelet basis function is the Symlet-8 wavelet basis function;

[0094] S24: Select J=5 scales and K=4 directions to perform NSW multi-scale decomposition, extract multi-scale wavelet coefficients, and process the wavelet coefficients through an adaptive filter;

[0095] S25: Use an autoregressive model to model the distribution of wavelet coefficients and set the standard range of model residuals. When the predicted residuals of wavelet coefficients deviate from the standard range of model residuals, mark the corresponding regions of wavelet coefficients in the surface micro-image as abnormal feature regions. The order of the autoregressive model is 3.

[0096] The anomaly feature identification strategy also includes:

[0097] S26: Obtain the area and center of each abnormal feature region in the surface microscopic image, and calculate the equivalent circular radius r of each abnormal feature region based on the area.

[0098] Using the center of the region as the center, fill each abnormal feature region with a circular region with a radius of 1.5r, and set the part of the filled circular region that does not overlap with the abnormal feature region as the damage comparison region;

[0099] S27: Extract local X-ray fluorescence spectral data for each abnormal feature region and the damage contrast region, and calculate the damage assessment coefficient sh according to the damage assessment strategy. n The damage assessment strategy is specifically as follows:

[0100]

[0101] Among them, BL n BL n ′ represents the ratio of trace elements in the nth abnormal feature region and the damage comparison domain, respectively; BO n ,BO n ′ represents the micro-oxygen content in the nth abnormal feature region and the damage comparison region, respectively;

[0102] For example, in this embodiment, the ratio of trace elements is the iron-nickel ratio;

[0103] α1 and α2 are the area proportion coefficients of the nth abnormal feature region and the damaged comparison region, respectively.

[0104] The anomaly feature identification strategy also includes:

[0105] S28: Identify the center of maximum electric field intensity in each anomalous feature region using local electric field spectrum data. Divide a circular region with a radius of 1.5r centered on the center of maximum electric field intensity. Set the part of the divided circular region that does not overlap with the anomalous feature region as the first electric field distortion comparison domain. Set the part of the anomalous feature region that does not overlap with the divided circular region as the second electric field distortion comparison domain. Set the part of the divided circular region that overlaps with the anomalous feature region as the distortion interest domain of the nth anomalous feature region.

[0106] S29: Calculate and obtain the distortion evaluation coefficient jb according to the electric field distortion evaluation strategy. n The electric field distortion assessment strategy is specifically as follows:

[0107]

[0108] Among them, DR n ,DR n ′,DR n "These are the capacitance values ​​of the distortion interest region, the first electric field distortion comparison region, and the second electric field distortion comparison region of the nth abnormal feature region, respectively;

[0109] β1 represents the area proportion coefficient of the nth abnormal feature region;

[0110] β2 represents the area ratio coefficient of the first electric field distortion comparison domain;

[0111] β3 represents the area ratio coefficient of the second electric field distortion contrast domain.

[0112] Based on the historical surface state data of the non-working contact surface of the blade, a fault feature filtering strategy is configured synchronously, fault feature filtering labels are output, and abnormal feature identification labels are filtered according to the fault feature filtering labels.

[0113] The configuration of the fault feature filtering strategy includes the following steps:

[0114] S31: After the contact blade of the high-voltage fuse completed the previous historical fuse failure, identify the obtained historical abnormal feature areas, wherein the total number of the historical abnormal feature areas is M;

[0115] S32: Extract the location of each historical abnormal feature region on the working contact surface of the stent and map it to the non-working contact surface of the stent. At the same time, mark the same location on the non-working contact surface of the stent to form a sequence of key observation locations.

[0116] S33: During the current fusing process of the contact blade of the high-voltage fuse, acquire historical surface state data of each key observation area in the key observation position sequence. The historical surface state data includes: surface temperature data and surface stress data.

[0117] S34: Based on historical surface state data of the non-working contact surface of the blade, synchronously configure the fault feature filtering strategy and output the fault feature filtering label gz. m The fault feature screening strategy includes:

[0118]

[0119] Among them, gz(1) m Filter sub-labels for the first fault characteristic;

[0120]

[0121] wd m This represents the temperature value of the m-th key observation area;

[0122] The average temperature of M key observation areas on the non-working contact surface of the blade;

[0123] wd max ,wd min These are the maximum and minimum temperature values ​​for M key observation areas on the non-working contact surface of the blade, respectively.

[0124] gz(2) m Filter sub-labels for the second fault characteristics;

[0125]

[0126] yl m This represents the stress value of the m-th key observation area;

[0127] The average stress value of M key observation areas on the non-working contact surface of the blade;

[0128] yl max ,yl min These are the maximum and minimum stress values ​​for M key observation areas on the non-working contact surface of the blade, respectively.

[0129] S35: Filter the abnormal feature identification tags according to the fault feature filtering tags. The filtering strategy includes: assigning an initial distance weight q to the abnormal feature area identified by the contactor after the completion of this fuse breaking operation. n And calculate the weight adjustment factor by filtering labels based on fault characteristics. D n,m D0 is the straight-line distance between the centers of the nth abnormal feature region and the mth historical abnormal feature region; D0 is the preset standard fault masking distance.

[0130] S36: Based on S35, calculate the update distance weight q′ for each abnormal feature region after the contactor completes this fuse-breaking operation. n The updated distance weight is the product of the initial distance weight and the weight adjustment factor.

[0131] A fuzzy comprehensive evaluation model is constructed, and the severity of the fault on the working contact surface of the contact knife is quantitatively calculated using the fuzzy comprehensive evaluation model to obtain a quantitative value of the fault severity.

[0132] The specific strategy for calculating the severity quantification value of the fault is as follows:

[0133]

[0134] LH represents the quantification of the fault severity of the contact blade of a high-voltage fuse in the distribution network.

[0135] Establish a digital maintenance strategy generation model, input the quantitative value of the fault severity into the digital maintenance strategy generation model, and generate maintenance strategy suggestions.

[0136] The maintenance strategy recommendations include: setting the initial monitoring frequency to W times of fuse failure operation, and simultaneously setting a first alarm value and a second alarm value for the severity of the fault.

[0137] After W blows of the same contact of the high-voltage fuse, when the first detection of a fault severity quantification value greater than or equal to the first alarm value, an offline maintenance recommendation is output.

[0138] When the detected fault severity quantification value is greater than the second alarm value but less than the first alarm value, the corresponding sequence number of the fuse operation is extracted.

[0139] If the corresponding circuit breaker operation sequence numbers are all consecutive, increase the monitoring frequency and adjust the monitoring frequency to W-1 times.

[0140] If the sequence number of the corresponding meltdown operation is not consecutive, output a suggestion to perform periodic surface repair on the contact tool;

[0141] When the monitored fault severity quantification values ​​are all less than the second alarm value, a signal indicating that the distribution network is operating normally in this initial monitoring frequency is output.

[0142] Example 2:

[0143] like Figure 2 As shown in the figure, an embodiment of the present invention provides a digital power distribution network panoramic monitoring system based on multi-dimensional data, such as... Figure 2 As shown, it includes the following modules:

[0144] The system includes a contact surface data acquisition module, an abnormal feature identification module, a fault feature screening module, a fault quantification module, and a maintenance strategy generation module.

[0145] The contact data acquisition module collects working data of the working contact surface of the high-voltage fuse in the power distribution network during the current fuse operation through data acquisition equipment.

[0146] The anomaly feature identification module is used to analyze working data, configure anomaly feature identification strategies based on the analysis results, output anomaly feature identification tags, and identify anomalies in high-voltage fuses based on these tags.

[0147] The fault feature screening module, based on historical surface state data of the non-working contact surface of the blade, synchronously configures a fault feature screening strategy, outputs fault feature screening tags, and filters abnormal feature identification tags according to the fault feature screening tags.

[0148] The fault quantification module is used to construct a fuzzy comprehensive evaluation model and to quantify the severity of faults on the working contact surface of the contact knife through the fuzzy comprehensive evaluation model, thereby obtaining a quantified value of the severity of the fault.

[0149] The maintenance strategy generation module is used to establish a digital maintenance strategy generation model, input the quantified value of the fault severity into the digital maintenance strategy generation model, and generate maintenance strategy suggestions.

[0150] Example 3:

[0151] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0152] The processor executes the aforementioned method for panoramic monitoring of digital power distribution networks based on multidimensional data by calling computer programs stored in memory.

[0153] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the digital power distribution network panoramic monitoring method based on multi-dimensional data provided in the above-described embodiment. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Details will not be elaborated upon in this embodiment.

[0154] Example 4:

[0155] This embodiment proposes a computer-readable storage medium on which an erasable and rewritable computer program is stored.

[0156] When a computer program runs on a computer device, it causes the computer device to execute the aforementioned method for panoramic monitoring of a digital power distribution network based on multidimensional data.

[0157] For example, a computer-readable storage medium can be a read-only memory (ROM).

[0158] Memory (ROM) and Random Access Memory (RAM)

[0159] Memory (RAM) and Compact Disc (CD-ROM)

[0160] Memory (CD-ROM), magnetic tape, floppy disk, and optical data storage devices, etc.

[0161] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0162] It should be understood that determining B based on A does not mean determining B solely based on A; it also means determining B based on A and / or other information.

[0163] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network and / or wireless network. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0164] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0165] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0166] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0167] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0168] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0169] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0170] In summary, compared with the prior art, the technical effects of the present invention are as follows:

[0171] 1. This invention integrates multiple data acquisition devices such as a high-resolution microscope camera, a miniature X-ray fluorescence spectrometer, and a local electric field spectrum analyzer, enabling comprehensive acquisition of working data of high-voltage fuse contacts from multiple dimensions. This not only greatly enhances the richness and diversity of the data but also provides a more comprehensive reflection of the actual working status of the contacts, thereby improving the reliability of fault identification.

[0172] 2. This invention employs a multi-stage anomaly feature recognition strategy, combined with the processing of surface microscopic images, analysis of X-ray fluorescence spectral data and local electric field spectrum data, to accurately identify abnormal feature regions on the surface of the contact blade. In particular, by utilizing the Sobel operator to calculate local texture gradients, adaptively adjusting wavelet basis functions, and multi-scale decomposition of the autoregressive model, the identification of subtle fault features becomes more accurate, effectively reducing the probability of missed fault detections and false alarms.

[0173] 3. This invention uses a synchronous configuration fault feature screening strategy and historical surface state data of the non-working contact surface of the contact blade to screen and evaluate currently identified abnormal features. Through comprehensive analysis of temperature and stress data of historical abnormal feature areas, the system can more accurately predict and identify potential fault areas, thus improving the accuracy of fault prediction.

[0174] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for panoramic monitoring of digital power distribution networks based on multidimensional data, characterized in that, The method includes the following specific steps: The working data of the contact blade working surface of the high-voltage fuse in the power distribution network is collected using data acquisition equipment. The data acquisition process includes: acquiring microscopic images of the working contact surface of the high-voltage fuse blade using a high-resolution microscope camera; obtaining X-ray fluorescence spectral data of the working contact surface using a miniature X-ray fluorescence spectrometer; and obtaining local electric field spectral data of the working contact surface using a local electric field spectral analyzer. Analyze the working data, configure the abnormal feature identification strategy based on the analysis results, output abnormal feature identification tags, and identify abnormal features of high voltage fuses based on the abnormal feature identification tags. The abnormal feature identification strategy includes: S21: Extract the surface microscopic image and convert it into a grayscale image. Normalize the image pixel values ​​to the range of [0,1] and use a bilateral filter to denoise the image. S22: Calculate the local texture gradient of a surface messenger image using the Sobel operator. Adjust the scale based on the local texture gradient. ; S23: Adaptively adjust the shape of the basic wavelet basis function using local texture gradients, wherein the adaptive adjustment includes: ,in, For the adaptively adjusted wavelet basis functions, Basic wavelet basis functions; S24: Select J=5 scales and K=4 directions to perform NSW multi-scale decomposition, extract multi-scale wavelet coefficients, and process the wavelet coefficients through an adaptive filter; S25: Use an autoregressive model to model the distribution of wavelet coefficients and set the standard range of model residuals. When the predicted residuals of wavelet coefficients deviate from the standard range of model residuals, mark the corresponding regions of wavelet coefficients in the surface micro-image as abnormal feature regions. The order of the autoregressive model is 3. Based on the historical surface state data of the non-working contact surface of the blade, a fault feature filtering strategy is configured synchronously, fault feature filtering labels are output, and abnormal feature identification labels are filtered according to the fault feature filtering labels. A fuzzy comprehensive evaluation model is constructed, and the severity of the fault on the working contact surface of the contact knife is quantitatively calculated using the fuzzy comprehensive evaluation model to obtain a quantitative value of the fault severity. Establish a digital maintenance strategy generation model, input the quantitative value of the fault severity into the digital maintenance strategy generation model, and generate maintenance strategy suggestions.

2. The method for panoramic monitoring of digital power distribution networks based on multidimensional data according to claim 1, characterized in that, The anomaly feature identification strategy also includes: S26: Obtain the area and center of each anomalous feature region in the surface microscopic image, and calculate the equivalent circular radius of each anomalous feature region based on the area. ; Using the center of the region as the center, fill each abnormal feature region with a radius of [missing information]. In the circular area, the portion of the filled circular area that does not overlap with the abnormal feature area is set as the damage contrast region; S27: Extract local X-ray fluorescence spectral data for each abnormal feature region and the damage contrast region, and calculate the damage assessment coefficient according to the damage assessment strategy. The damage assessment strategy is specifically as follows: ； in, These are the ratios of trace elements in the nth abnormal feature region and the damage comparison region, respectively; These represent the micro-oxygen content in the nth abnormal feature region and the damage comparison region, respectively. These are the area proportion coefficients of the nth abnormal feature region and the damaged comparison region, respectively.

3. The method for panoramic monitoring of digital power distribution networks based on multidimensional data according to claim 2, characterized in that, The anomaly feature identification strategy also includes: S28: Identify the center of maximum electric field intensity in each anomalous region using local electric field spectrum data, and divide the region into circles with a radius of [missing information]. The circular region is defined as follows: the part of the circular region that does not overlap with the abnormal feature region is defined as the first electric field distortion comparison domain; the part of the abnormal feature region that does not overlap with the circular region is defined as the second electric field distortion comparison domain; and the part of the circular region that overlaps with the abnormal feature region is defined as the distortion interest domain of the nth abnormal feature region. S29: Calculate and obtain the distortion evaluation coefficients according to the electric field distortion evaluation strategy. The electric field distortion assessment strategy is specifically as follows: ； in, These are the capacitance values ​​of the distortion interest region, the first electric field distortion comparison region, and the second electric field distortion comparison region of the nth abnormal feature region, respectively. These are the area proportion coefficients of the nth abnormal feature region; These are the area proportion coefficients of the first electric field distortion comparison domain, respectively; These are the area ratio coefficients of the second electric field distortion contrast domain, respectively.

4. The method for panoramic monitoring of digital power distribution networks based on multidimensional data according to claim 3, characterized in that, The configuration of the fault feature filtering strategy includes the following steps: S31: After the contact blade of the high-voltage fuse completed the previous historical fuse failure, identify the obtained historical abnormal feature areas, wherein the total number of the historical abnormal feature areas is M; S32: Extract the location of each historical abnormal feature region on the working contact surface of the stent and map it to the non-working contact surface of the stent. At the same time, mark the same location on the non-working contact surface of the stent to form a sequence of key observation locations. S33: During the current fusing process of the contact blade of the high-voltage fuse, acquire historical surface state data of each key observation area in the key observation position sequence. The historical surface state data includes: surface temperature data and surface stress data. S34: Based on historical surface state data of the non-working contact surface of the blade, simultaneously configure the fault feature filtering strategy and output fault feature filtering labels. ; S35: Filter the abnormal feature identification labels according to the fault feature filtering labels. The filtering strategy includes: assigning an initial distance weight to the abnormal feature area identified by the contactor after the completion of this fuse breaking operation. And calculate the weight adjustment factor by filtering labels based on fault characteristics. , , The straight-line distance between the centers of the nth anomalous feature region and the mth historical anomalous feature region; The preset standard fault masking distance; S36: Based on S35, calculate the update distance weight of each abnormal feature region after the contact blade completes this melting operation. The updated distance weight is the product of the initial distance weight and the weight adjustment factor.

5. The method for panoramic monitoring of digital power distribution networks based on multidimensional data according to claim 4, characterized in that, The specific strategy for calculating the severity quantification value of the fault is as follows: ； LH represents the quantification of the fault severity of the contact blade of a high-voltage fuse in the distribution network.

6. The method for panoramic monitoring of digital power distribution networks based on multidimensional data according to claim 5, characterized in that, The maintenance strategy recommendations include: setting the initial monitoring frequency to W times of fuse failure operation, and simultaneously setting a first alarm value and a second alarm value for the severity of the fault. After W blows of the same contact of the high-voltage fuse, when the first detection of a fault severity quantification value greater than or equal to the first alarm value, an offline maintenance recommendation is output. When the detected fault severity quantification value is greater than the second alarm value but less than the first alarm value, the corresponding sequence number of the fuse operation is extracted. If the corresponding circuit breaker operation sequence numbers are all consecutive, increase the monitoring frequency and adjust the monitoring frequency to W-1 times. If the sequence number of the corresponding meltdown operation is not consecutive, output a suggestion to perform periodic surface repair on the contact tool; When the monitored fault severity quantification values ​​are all less than the second alarm value, a signal indicating that the distribution network is operating normally in this initial monitoring frequency is output.

7. A digital distribution network panoramic monitoring system based on multidimensional data, implemented based on the digital distribution network panoramic monitoring method based on multidimensional data as described in any one of claims 1-6, characterized in that, The system includes the following modules: The system includes a contact surface data acquisition module, an abnormal feature identification module, a fault feature screening module, a fault quantification module, and a maintenance strategy generation module. The contact data acquisition module collects working data of the working contact surface of the high-voltage fuse in the power distribution network for this fuse operation through the data acquisition device. The abnormal feature identification module is used to analyze the working data, configure the abnormal feature identification strategy according to the analysis results, output the abnormal feature identification label, and identify the abnormal features of the high voltage fuse according to the abnormal feature identification label. The fault feature screening module is based on the historical surface state data of the non-working contact surface of the contact knife, synchronously configures the fault feature screening strategy, outputs fault feature screening labels, and filters the abnormal feature identification labels according to the fault feature screening labels. The fault quantification module is used to construct a fuzzy comprehensive evaluation model and to quantify the severity of faults on the working contact surface of the contact knife through the fuzzy comprehensive evaluation model, thereby obtaining a quantified value of the severity of the fault. The maintenance strategy generation module is used to establish a digital maintenance strategy generation model, input the quantified value of the fault severity into the digital maintenance strategy generation model, and generate maintenance strategy suggestions.

Images