Digital power distribution network panoramic monitoring method and system based on multi-dimensional data

Abstract

The invention relates to the technical field of power distribution network monitoring, in particular to a digital power distribution network panoramic monitoring method and system based on multi-dimensional data, and the method specifically comprises the steps: carrying out the working data collection of a working contact surface of a contact knife of a high-voltage fuse in a power distribution network; analyzing the working data, outputting an abnormal feature identification tag and a fault feature screening tag, screening the abnormal feature identification tag according to the fault feature screening tag, and performing quantitative calculation on the fault severity of the working contact surface of the contact knife through a fuzzy comprehensive evaluation model to obtain a fault severity quantized value. Meanwhile, generating a maintenance strategy suggestion; according to the invention, the problems of low fault detection precision and incapability of timely and accurately identifying and processing complex faults in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network monitoring, and is a method and system for panoramic monitoring of a digital distribution network based on multi-dimensional data. Background Art

[0002] In the power system, high-voltage fuses are key protective devices, and their operating status is directly related to the safety and stability of the power grid. The contact blade is one of the core components of the high-voltage fuse, and the condition of its working contact surface directly affects the performance and life of the fuse. However, existing high-voltage fuse contact blade monitoring methods often have the following problems, including: the monitoring method of high-voltage fuse contact blades mainly relies on a single data source, such as visual inspection or simple electrical parameter measurement, and lacks the comprehensive support of multi-dimensional data, resulting in insufficient fault identification accuracy; at the same time, the fault identification strategy is mostly based on a rule-based system, which is difficult to adapt to complex fault modes and easily leads to missed faults or false alarms. In addition, the existing monitoring system lacks adaptability and cannot dynamically optimize the monitoring strategy according to the actual operating environment. The traditional regular maintenance strategy is inefficient, which may lead to excessive maintenance and increased costs, and may also cause failures due to untimely maintenance. These problems seriously 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 to address the problems in the prior art of low fault detection accuracy and inability to timely and accurately identify and handle complex faults, and propose a digital distribution network panoramic monitoring method and system based on multidimensional data.

[0004] In order to achieve the above-mentioned object, the present invention provides a method for panoramic monitoring of a digital distribution network based on multi-dimensional data, which includes the following steps:

[0005] The working data of the contact surface of the high-voltage fuse in the distribution network is collected through the data acquisition equipment;

[0006] Analyze the working data, configure the abnormal feature recognition strategy based on the analysis results, output the abnormal feature recognition label, and perform abnormal feature recognition on the high-voltage fuse based on the abnormal feature recognition label;

[0007] Based on the historical surface status data of the non-working contact surface of the touch knife, a fault feature screening strategy is synchronously configured, a fault feature screening label is output, and the abnormal feature identification label is screened according to the fault feature screening label;

[0008] A fuzzy comprehensive evaluation model is constructed, and the fault severity of the contact surface of the contact knife is quantitatively calculated through the fuzzy comprehensive evaluation model to obtain the quantitative value of the fault severity;

[0009] A digital maintenance strategy generation model is established, the quantitative value of the fault severity is input into the digital maintenance strategy generation model, and maintenance strategy recommendations are generated at the same time.

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

[0011] Specifically, the abnormal feature recognition 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, Represent the brightness gradient of the a-th pixel in the horizontal and vertical directions respectively;

[0015] Preferably, s0 is the initial scale,

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

[0017] S23: Adaptively adjusting the shape of the basic wavelet basis function through the local texture gradient, wherein the adaptive adjustment includes: in, is the adaptively adjusted wavelet basis function, is the basic wavelet basis function;

[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, where NSW is a non-stationary wavelet transform;

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

[0021] Specifically, the abnormal feature recognition strategy also 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] With the center of the region as the center of the circle, fill each abnormal feature area with a circular area of ​​radius 1.5r, and set the part of the filled circular area that does not overlap with the abnormal feature area as the damage comparison area;

[0024] S27: Extract local X-ray fluorescence spectrum data of each abnormal feature area and damage contrast area, 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 ′ are the ratios of trace elements in the nth abnormal characteristic area and the damage contrast area; BO n ,BO n ′ are the micro-oxygen contents in the nth abnormal feature area and the damaged contrast area respectively;

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

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

[0029] Specifically, the abnormal feature recognition strategy also includes:

[0030] S28: Identifying the center of maximum electric field intensity in each abnormal characteristic region through the local electric field spectrum data, dividing a circular region with a radius of 1.5r with the center of the maximum electric field intensity as the center, setting the portion of the divided circular region that does not overlap with the abnormal characteristic region as the first electric field distortion contrast domain, setting the portion of the abnormal characteristic region that does not overlap with the divided circular region as the second electric field distortion contrast domain, and setting the portion of the divided circular region that overlaps with the abnormal characteristic region as the distortion focus domain of the nth abnormal characteristic 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 ″ are the capacitance values ​​of the distortion focus 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 is the area ratio coefficient of the nth abnormal feature area;

[0035] β2 is the area ratio coefficient of the first electric field distortion contrast domain;

[0036] β3 are the area ratio coefficients of the second electric field distortion contrast domain.

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

[0038] S31: obtaining a historical abnormal characteristic region obtained after the contact blade of the high-voltage fuse is last blown, and identifying the historical abnormal characteristic region, wherein the total number of the historical abnormal characteristic regions is M;

[0039] S32: extracting the location of each historical abnormal feature area on the working contact surface of the touch knife and mapping it to the non-working contact surface of the touch knife, and marking the same location on the non-working contact surface of the touch knife to form a key observation position sequence;

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

[0041] S34: Based on the historical surface status data of the non-working contact surface of the contact knife, the fault feature screening strategy is configured synchronously and the fault feature screening label gz is output. m , the fault feature screening strategy includes:

[0042]

[0043] Among them, gz(1) m Filtering subtags for the first fault feature;

[0044]

[0045] wd m is the temperature value of the mth key observation area;

[0046] is the average temperature of M key observation areas on the non-working contact surface of the touch knife;

[0047] wd max ,wd min are the maximum temperature and minimum temperature of M key observation areas on the non-working contact surface of the touch knife;

[0048] gz(2) m Filter subtags for the second fault feature;

[0049]

[0050] yl m is the stress value of the mth key observation area;

[0051] is the stress mean of M key observation areas on the non-working contact surface of the contact knife;

[0052] yl max ,yl min are the maximum stress value and minimum stress value of M key observation areas on the non-working contact surface of the touch knife;

[0053] S35: Filter the abnormal feature identification tags according to the fault feature screening tags. The screening strategy includes: assigning an initial distance weight q to the abnormal feature area identified by the contact knife after the current fusing work is completed. n , and calculate the weight adjustment factor based on the fault characteristics screening label D n,m is the straight-line distance between the centers of the nth abnormal characteristic area and the mth historical abnormal characteristic area; D0 is the preset standard fault concealment distance;

[0054] S36: According to S35, calculate the updated distance weight q′ of each abnormal feature area after the contact knife completes the current fusing work n , wherein the updated distance weight is the product of the initial distance weight and the weight adjustment factor.

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

[0056]

[0057] Wherein, LH is the quantitative value of the fault severity of the contact of the high-voltage fuse in the distribution network.

[0058] Specifically, the maintenance strategy suggestion includes: presetting the initial monitoring frequency to W times of the fusing working process, and simultaneously presetting the first alarm value and the second alarm value of the fault severity;

[0059] After the same contact of the high-voltage fuse has been blown W times, when the fault severity quantization value is detected to be greater than or equal to the first alarm value for the first time, an offline maintenance suggestion is output;

[0060] When the fault severity quantization value is detected to be greater than the second alarm value and less than the first alarm value, the corresponding serial number of the fusing operation is extracted;

[0061] If the serial numbers of the corresponding fuse operations are all consecutive, the output increases the monitoring frequency and adjusts the monitoring frequency to W-1 times;

[0062] If the serial number of the corresponding fusing work is a discontinuous serial number, output a suggestion for regular surface repair of the contact knife;

[0063] When it is monitored that the quantitative values ​​of the fault severity are all less than the second alarm value, a signal that the distribution network is operating normally at the initial monitoring frequency is output.

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

[0065] Contact surface data acquisition module, abnormal feature recognition module, fault feature screening module, fault quantification module and maintenance strategy generation module;

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

[0067] The abnormal feature recognition module is used to analyze the working data, configure the abnormal feature recognition strategy according to the analysis results, output the abnormal feature recognition label, and perform abnormal feature recognition on the high-voltage fuse according to the abnormal feature recognition label.

[0068] The fault feature screening module is based on the historical surface state data of the non-working contact surface of the stylus, synchronously configures the fault feature screening strategy, outputs the fault feature screening label, and screens the abnormal feature identification label according to the fault feature screening label

[0069] The fault quantification module is used to construct a fuzzy comprehensive evaluation model, and to quantify the severity of the fault of the working contact surface of the stylus by using the fuzzy comprehensive evaluation model to obtain a quantitative 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 fault severity quantization value into the digital maintenance strategy generation model, and generate maintenance strategy recommendations.

[0071] A storage medium stores instructions, and when a computer reads the instructions, the computer is caused to execute the method for panoramic monitoring of a digital distribution network based on multi-dimensional data.

[0072] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for panoramic monitoring of a digital distribution network based on multi-dimensional data is implemented.

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

[0074] 1. By integrating multiple data acquisition devices such as a high-resolution microscope camera, a miniature X-ray fluorescence spectrometer, and a local electric field spectrum analyzer, the present invention can comprehensively collect the operating data of the high-voltage fuse contact blade from multiple dimensions. This not only greatly improves the richness and diversity of the data, but also can more comprehensively reflect the actual working status of the contact blade, thereby improving the reliability of fault identification.

[0075] 2. The present invention uses a multi-stage abnormal feature recognition strategy, combined with surface microscopic image processing, X-ray fluorescence spectrum data and local electric field spectrum data analysis, to accurately identify abnormal feature areas on the touch tool surface. In particular, the use of the Sobel operator to calculate local texture gradients, adaptive adjustment of wavelet basis functions and multi-scale decomposition of the autoregressive model makes the identification of subtle fault features more accurate, effectively reducing the probability of missed fault detection and false alarms.

[0076] 3. The present invention synchronously configures a fault feature screening strategy and utilizes historical surface state data of the non-working contact surface of the touch knife to screen and evaluate the 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, thereby improving the accuracy of fault prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0078] in:

[0079] Figure 1Schematic diagram of a flow chart of a method for panoramic monitoring of a digital distribution network based on multi-dimensional data according to the present invention;

[0080] Figure 2 The figure is a structural diagram of a digital distribution network panoramic monitoring system based on multi-dimensional data according to the present invention. DETAILED DESCRIPTION

[0081] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0082] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0083] Secondly, the term "one embodiment" or "embodiment" 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 various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0084] Example 1:

[0085] like Figure 1 As shown, a method for panoramic monitoring of a digital distribution network based on multi-dimensional data according to an embodiment of the present invention is as follows: Figure 1 As shown, the specific steps are as follows:

[0086] The working data of the contact surface of the high-voltage fuse in the distribution network is collected through the data acquisition equipment;

[0087] The working data acquisition includes: obtaining a surface microscopic image of the working contact surface of the high-voltage fuse contact blade through a high-resolution microscope camera; obtaining X-ray fluorescence spectrum data of the working contact surface of the contact blade through a micro X-ray fluorescence spectrometer; and obtaining local electric field spectrum data of the working contact surface of the contact blade through a local electric field spectrum analyzer.

[0088] Analyze the working data, configure the abnormal feature recognition strategy based on the analysis results, output the abnormal feature recognition label, and perform abnormal feature recognition on the high-voltage fuse based on the abnormal feature recognition label;

[0089] The abnormal feature recognition 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 adjusting the shape of the basic wavelet basis function through the local texture gradient, wherein the adaptive adjustment includes: in, is the adaptively adjusted wavelet basis function, is the basic wavelet basis function;

[0093] Exemplarily, 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 a standard range of model residuals. When the predicted residuals of the wavelet coefficients deviate from the standard range of the model residuals, mark the corresponding area of ​​the wavelet coefficients in the surface microscopic image as an abnormal feature area, where the order of the autoregressive model is 3.

[0096] The abnormal feature recognition 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] With the center of the region as the center of the circle, fill each abnormal feature area with a circular area of ​​radius 1.5r, and set the part of the filled circular area that does not overlap with the abnormal feature area as the damage comparison area;

[0099] S27: Extract local X-ray fluorescence spectrum data of each abnormal feature area and damage contrast area, 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 ′ are the ratios of trace elements in the nth abnormal characteristic area and the damage contrast area; BO n ,BO n ′ are the micro-oxygen contents in the nth abnormal feature area and the damaged contrast area respectively;

[0102] Exemplarily, in this embodiment, the ratio of trace elements is the ratio of iron to nickel;

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

[0104] The abnormal feature recognition strategy also includes:

[0105] S28: Identifying the center of maximum electric field intensity in each abnormal characteristic region through the local electric field spectrum data, dividing a circular region with a radius of 1.5r with the center of the maximum electric field intensity as the center, setting the portion of the divided circular region that does not overlap with the abnormal characteristic region as the first electric field distortion contrast domain, setting the portion of the abnormal characteristic region that does not overlap with the divided circular region as the second electric field distortion contrast domain, and setting the portion of the divided circular region that overlaps with the abnormal characteristic region as the distortion focus domain of the nth abnormal characteristic 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 ″ are the capacitance values ​​of the distortion focus 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 is the area ratio coefficient of the nth abnormal feature area;

[0110] β2 is the area ratio coefficient of the first electric field distortion contrast domain;

[0111] β3 are the area ratio coefficients of the second electric field distortion contrast domain.

[0112] Based on the historical surface status data of the non-working contact surface of the touch knife, a fault feature screening strategy is synchronously configured, a fault feature screening label is output, and the abnormal feature identification label is screened according to the fault feature screening label;

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

[0114] S31: obtaining a historical abnormal characteristic region obtained after the contact blade of the high-voltage fuse is last blown, and identifying the historical abnormal characteristic region, wherein the total number of the historical abnormal characteristic regions is M;

[0115] S32: extracting the location of each historical abnormal feature area on the working contact surface of the touch knife and mapping it to the non-working contact surface of the touch knife, and marking the same location on the non-working contact surface of the touch knife to form a key observation position sequence;

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

[0117] S34: Based on the historical surface status data of the non-working contact surface of the contact knife, the fault feature screening strategy is configured synchronously and the fault feature screening label gz is output. m , the fault feature screening strategy includes:

[0118]

[0119] Among them, gz(1) m Filtering subtags for the first fault feature;

[0120]

[0121] wd m is the temperature value of the mth key observation area;

[0122] is the average temperature of M key observation areas on the non-working contact surface of the touch knife;

[0123] wd max ,wd min are the maximum temperature and minimum temperature of M key observation areas on the non-working contact surface of the touch knife;

[0124] gz(2) m Filter subtags for the second fault feature;

[0125]

[0126] yl m is the stress value of the mth key observation area;

[0127] is the stress mean of M key observation areas on the non-working contact surface of the contact knife;

[0128] yl max ,yl min are the maximum stress value and minimum stress value of M key observation areas on the non-working contact surface of the touch knife;

[0129] S35: Filter the abnormal feature identification tags according to the fault feature screening tags. The screening strategy includes: assigning an initial distance weight q to the abnormal feature area identified by the contact knife after the current fusing work is completed. n , and calculate the weight adjustment factor based on the fault characteristics screening label D n,m is the straight-line distance between the centers of the nth abnormal characteristic area and the mth historical abnormal characteristic area; D0 is the preset standard fault concealment distance;

[0130] S36: According to S35, calculate the updated distance weight q′ of each abnormal feature area after the contact knife completes the current fusing work n , wherein 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 fault severity of the contact surface of the contact knife is quantitatively calculated through the fuzzy comprehensive evaluation model to obtain the quantitative value of the fault severity;

[0132] The calculation strategy of the fault severity quantitative value is specifically as follows:

[0133]

[0134] Wherein, LH is the quantitative value of the fault severity of the contact of the high-voltage fuse in the distribution network.

[0135] A digital maintenance strategy generation model is established, the quantitative value of the fault severity is input into the digital maintenance strategy generation model, and maintenance strategy recommendations are generated at the same time.

[0136] The maintenance strategy suggestion includes: presetting the initial monitoring frequency to W times of the fusing working process, and simultaneously presetting the first alarm value and the second alarm value of the fault severity;

[0137] After the same contact of the high-voltage fuse has been blown W times, when the fault severity quantization value is detected to be greater than or equal to the first alarm value for the first time, an offline maintenance suggestion is output;

[0138] When the fault severity quantization value is detected to be greater than the second alarm value and less than the first alarm value, the corresponding serial number of the fusing operation is extracted;

[0139] If the serial numbers of the corresponding fuse operations are all consecutive, the output increases the monitoring frequency and adjusts the monitoring frequency to W-1 times;

[0140] If the serial number of the corresponding fusing work is a discontinuous serial number, output a suggestion for regular surface repair of the contact knife;

[0141] When it is monitored that the quantitative values ​​of the fault severity are all less than the second alarm value, a signal that the distribution network is operating normally at the initial monitoring frequency is output.

[0142] Example 2:

[0143] like Figure 2 As shown, a digital distribution network panoramic monitoring system based on multi-dimensional data according to an embodiment of the present invention is Figure 2 As shown, it includes the following modules:

[0144] Contact surface data acquisition module, abnormal feature recognition module, fault feature screening module, fault quantification module and maintenance strategy generation module;

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

[0146] The abnormal feature recognition module is used to analyze the working data, configure the abnormal feature recognition strategy according to the analysis results, output the abnormal feature recognition label, and perform abnormal feature recognition on the high-voltage fuse according to the abnormal feature recognition label.

[0147] The fault feature screening module is based on the historical surface state data of the non-working contact surface of the stylus, synchronously configures the fault feature screening strategy, outputs the fault feature screening label, and screens the abnormal feature identification label according to the fault feature screening label

[0148] The fault quantification module is used to construct a fuzzy comprehensive evaluation model, and to quantify the severity of the fault of the working contact surface of the stylus by using the fuzzy comprehensive evaluation model to obtain a quantitative 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 fault severity quantization value into the digital maintenance strategy generation model, and generate maintenance strategy recommendations.

[0150] Example 3:

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

[0152] The processor executes the above-mentioned method for panoramic monitoring of a digital distribution network based on multi-dimensional data by calling a computer program stored in the memory.

[0153] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a digital distribution network panoramic monitoring method based on multi-dimensional data provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device. For example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0154] Example 4:

[0155] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0156] When the computer program runs on a computer device, the computer device is enabled to execute the above-mentioned method for panoramic monitoring of a digital distribution network based on multi-dimensional data.

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

[0158] Memory, referred to as ROM), Random Access Memory (Random Access

[0159] Memory, referred to as RAM), Compact Disc Read-Only

[0160] Memory, referred to as: CD-ROM), magnetic tapes, floppy disks and optical data storage devices, etc.

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

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

[0163] The above embodiments can be implemented in whole or in part through software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the 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 or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

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

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

[0166] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0167] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

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

[0169] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these 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 any 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. By integrating multiple data acquisition devices such as a high-resolution microscope camera, a miniature X-ray fluorescence spectrometer, and a local electric field spectrum analyzer, the present invention can comprehensively collect the operating data of the high-voltage fuse contact blade from multiple dimensions. This not only greatly improves the richness and diversity of the data, but also can more comprehensively reflect the actual working status of the contact blade, thereby improving the reliability of fault identification.

[0172] 2. The present invention uses a multi-stage abnormal feature recognition strategy, combined with surface microscopic image processing, X-ray fluorescence spectrum data and local electric field spectrum data analysis, to accurately identify abnormal feature areas on the touch tool surface. In particular, the use of the Sobel operator to calculate local texture gradients, adaptive adjustment of wavelet basis functions and multi-scale decomposition of the autoregressive model makes the identification of subtle fault features more accurate, effectively reducing the probability of missed fault detection and false alarms.

[0173] 3. The present invention synchronously configures a fault feature screening strategy and utilizes historical surface state data of the non-working contact surface of the touch knife to screen and evaluate the 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, thereby improving the accuracy of fault prediction.

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

Claims

1. A panoramic monitoring method for a digital distribution network based on multi-dimensional data, characterized in that: The method comprises the following specific steps: The working data of the contact surface of the high-voltage fuse in the distribution network is collected through the data acquisition equipment; Analyze the working data, configure the abnormal feature recognition strategy based on the analysis results, output the abnormal feature recognition label, and perform abnormal feature recognition on the high-voltage fuse based on the abnormal feature recognition label; Based on the historical surface status data of the non-working contact surface of the touch knife, a fault feature screening strategy is synchronously configured, a fault feature screening label is output, and the abnormal feature identification label is screened according to the fault feature screening label; A fuzzy comprehensive evaluation model is constructed, and the fault severity of the contact surface of the contact knife is quantitatively calculated through the fuzzy comprehensive evaluation model to obtain the quantitative value of the fault severity; A digital maintenance strategy generation model is established, the quantitative value of the fault severity is input into the digital maintenance strategy generation model, and maintenance strategy recommendations are generated at the same time.

2. A method for panoramic monitoring of a digital distribution network based on multidimensional data according to claim 1, characterized in that: The working data acquisition includes: obtaining a surface microscopic image of the working contact surface of the high-voltage fuse contact blade through a high-resolution microscope camera; obtaining X-ray fluorescence spectrum data of the working contact surface of the contact blade through a micro X-ray fluorescence spectrometer; and obtaining local electric field spectrum data of the working contact surface of the contact blade through a local electric field spectrum analyzer.

3. The method for panoramic monitoring of a digital distribution network based on multidimensional data according to claim 2, characterized in that: The abnormal feature recognition 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 G(a) of the surface surrounding image using the Sobel operator, and obtain the adjustment scale s(a) based on the local texture gradient; S23: Adaptively adjusting the shape of the basic wavelet basis function through the local texture gradient, wherein the adaptive adjustment includes: in, is the adaptively adjusted wavelet basis function, is the basic wavelet basis function; 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 a standard range of model residuals. When the predicted residuals of the wavelet coefficients deviate from the standard range of the model residuals, mark the corresponding area of ​​the wavelet coefficients in the surface microscopic image as an abnormal feature area, where the order of the autoregressive model is 3.

4. The method for panoramic monitoring of a digital distribution network based on multidimensional data according to claim 3, characterized in that: The abnormal feature recognition strategy also includes: 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; With the center of the region as the center of the circle, fill each abnormal feature area with a circular area of ​​radius 1.5r, and set the part of the filled circular area that does not overlap with the abnormal feature area as the damage comparison area; S27: Extract local X-ray fluorescence spectrum data of each abnormal feature area and damage contrast area, and calculate the damage assessment coefficient sh according to the damage assessment strategy n , the damage assessment strategy is specifically as follows: Among them, BL n ,BL n ′ are the ratios of trace elements in the nth abnormal characteristic area and the damage contrast area; BO n ,BO n ′ are the micro-oxygen contents in the nth abnormal feature area and the damaged contrast area respectively; α1 and α2 are the area ratio coefficients of the nth abnormal feature region and the damaged contrast region, respectively.

5. The method for panoramic monitoring of a digital distribution network based on multidimensional data according to claim 4, characterized in that: The abnormal feature recognition strategy also includes: S28: Identifying the center of maximum electric field intensity in each abnormal characteristic region through the local electric field spectrum data, dividing a circular region with a radius of 1.5r with the center of the maximum electric field intensity as the center, setting the portion of the divided circular region that does not overlap with the abnormal characteristic region as the first electric field distortion contrast domain, setting the portion of the abnormal characteristic region that does not overlap with the divided circular region as the second electric field distortion contrast domain, and setting the portion of the divided circular region that overlaps with the abnormal characteristic region as the distortion focus domain of the nth abnormal characteristic region; 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: Among them, DR n ,DR n ′,DR n ″ are the capacitance values ​​of the distortion focus region, the first electric field distortion comparison region, and the second electric field distortion comparison region of the nth abnormal feature region respectively; β1 is the area ratio coefficient of the nth abnormal feature area; β2 is the area ratio coefficient of the first electric field distortion contrast domain; β3 are the area ratio coefficients of the second electric field distortion contrast domain.

6. A method for panoramic monitoring of a digital distribution network based on multidimensional data according to claim 5, characterized in that: The configuration of the fault feature screening strategy includes the following steps: S31: obtaining a historical abnormal characteristic region obtained after the contact blade of the high-voltage fuse is last blown, and identifying the historical abnormal characteristic region, wherein the total number of the historical abnormal characteristic regions is M; S32: extracting the location of each historical abnormal feature area on the working contact surface of the touch knife and mapping it to the non-working contact surface of the touch knife, and marking the same location on the non-working contact surface of the touch knife to form a key observation position sequence; S33: during the current fusing process of the contact blade of the high-voltage fuse, obtaining historical surface state data of each key observation area in the key observation position sequence, wherein the historical surface state data includes surface temperature data and surface stress data; S34: Based on the historical surface status data of the non-working contact surface of the contact knife, the fault feature screening strategy is configured synchronously and the fault feature screening label gz is output. m ; S35: Filter the abnormal feature identification tags according to the fault feature screening tags. The screening strategy includes: assigning an initial distance weight q to the abnormal feature area identified by the contact knife after the current fusing work is completed. n , and calculate the weight adjustment factor based on the fault characteristics screening label D n,m is the straight-line distance between the centers of the nth abnormal characteristic area and the mth historical abnormal characteristic area; D0 is the preset standard fault concealment distance; S36: According to S35, calculate the updated distance weight q′ of each abnormal feature area after the contact knife completes the current fusing work n , wherein the updated distance weight is the product of the initial distance weight and the weight adjustment factor.

7. A method for panoramic monitoring of a digital distribution network based on multi-dimensional data according to claim 6, characterized in that: The calculation strategy of the fault severity quantitative value is specifically as follows: Wherein, LH is the quantitative value of the fault severity of the contact of the high-voltage fuse in the distribution network.

8. The method for panoramic monitoring of a digital distribution network based on multi-dimensional data according to claim 7, characterized in that: The maintenance strategy suggestion includes: presetting the initial monitoring frequency to W times of the fusing working process, and simultaneously presetting the first alarm value and the second alarm value of the fault severity; After the same contact of the high-voltage fuse has been blown W times, when the fault severity quantization value is detected to be greater than or equal to the first alarm value for the first time, an offline maintenance suggestion is output; When the fault severity quantization value is detected to be greater than the second alarm value and less than the first alarm value, the corresponding serial number of the fusing operation is extracted; If the serial numbers of the corresponding fuse operations are all consecutive, the output increases the monitoring frequency and adjusts the monitoring frequency to W-1 times; If the serial number of the corresponding fusing work is a discontinuous serial number, output a suggestion for regular surface repair of the contact knife; When it is monitored that the quantitative values ​​of the fault severity are all less than the second alarm value, a signal that the distribution network is operating normally at the initial monitoring frequency is output.

9. A digital distribution network panoramic monitoring system based on multidimensional data, which is implemented based on a digital distribution network panoramic monitoring method based on multidimensional data according to any one of claims 1 to 8, characterized in that: The system includes the following modules: Contact surface data acquisition module, abnormal feature recognition module, fault feature screening module, fault quantification module and maintenance strategy generation module; The contact surface data acquisition module collects working data of the current fusing operation on the contact surface of the high-voltage fuse in the distribution network through the data acquisition device. The abnormal feature recognition module is used to analyze the working data, configure the abnormal feature recognition strategy according to the analysis results, output the abnormal feature recognition label, and perform abnormal feature recognition on the high-voltage fuse according to the abnormal feature recognition label. The fault feature screening module is based on the historical surface state data of the non-working contact surface of the stylus, synchronously configures the fault feature screening strategy, outputs the fault feature screening label, and screens the abnormal feature identification label according to the fault feature screening label The fault quantification module is used to construct a fuzzy comprehensive evaluation model, and to quantify the severity of the fault of the working contact surface of the touch knife through the fuzzy comprehensive evaluation model to obtain a quantitative value of the severity of the fault; The maintenance strategy generation module is used to establish a digital maintenance strategy generation model, input the fault severity quantization value into the digital maintenance strategy generation model, and generate maintenance strategy recommendations.

Images