Fault alarm management method and device and storage medium

Abstract

The embodiment of the invention discloses a fault alarm management method and device and a storage medium. The fault alarm management method comprises the following steps: determining possible fault points according to an obtained infrared image of electrical equipment of a transformer substation; positioning the position of the electric signal for judging the fault in the secondary circuit of the electrical equipment of the transformer substation, and comparing the position with the possible fault point to determine an actual fault point; converting the actual fault points into a to-be-processed fault matrix, performing feature extraction on the to-be-processed fault matrix, and determining an actual fault point matrix; according to the actual fault point matrix, a predicted fault point is positioned based on a neural network model, and fault warning is carried out; and establishing a transformer substation electrical equipment secondary circuit database, and storing possible fault point data, actual fault point data, predicted fault point data and alarm data. According to the technical scheme of the embodiment of the invention, real-time fault detection and alarm are carried out on the secondary circuit of the electrical equipment of the transformer substation, the accuracy of fault detection is improved, and adverse effects on the secondary circuit of the electrical equipment of the transformer substation are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical circuit detection, and in particular to a fault alarm management method, device and storage medium. Background Art

[0002] Due to long-term operation, equipment aging, improper operation and other reasons, the secondary circuit of substation electrical equipment may have potential safety risks, posing serious safety hazards to power equipment and power systems. Therefore, it is necessary to perform fault detection on the secondary circuit of substation electrical equipment.

[0003] The method used in the prior art for defect detection of secondary circuits of electrical equipment in substations is: use data from power plants or substations to establish a model through an electrical simulation system, set the electrical secondary circuit to be checked to correspond to different fault types and fault points of the electrical primary equipment; simulate the fault waveform when a fault occurs in the electrical simulation system, and when the fault waveform is correct and complete, connect the electrical simulation system to the relevant voltage and current analog circuits at the secondary outlet of the voltage transformer / current transformer and check whether the setting of the protection device to be checked is consistent with the official setting; then check whether the collected input signal of the electrical simulation system is correct, so that the operating state of the electrical simulation system is consistent with normal operation; the electrical simulation system simulates different fault types and fault points to determine whether the different fault types and fault points are consistent with the actual situation. If they are not consistent, analyze the causes and test again. If they are consistent, perform the next test until all generators are tested.

[0004] However, the existing technology for electrical secondary circuit defect detection has the problems of low fault detection accuracy, inability to monitor in real time, and adverse effects on the electrical secondary circuit when the staff operates improperly. Summary of the invention

[0005] The present invention provides a fault alarm management method, device and storage medium, which perform real-time fault detection and alarm on the secondary circuit of substation electrical equipment, improve the accuracy of fault detection, and reduce adverse effects on the secondary circuit of substation electrical equipment.

[0006] According to one aspect of the present invention, a fault alarm management method is provided, which is used for a secondary circuit of an electrical device in a substation; the fault alarm management method comprises:

[0007] Obtain infrared images of electrical equipment in the substation, and determine possible fault points in the secondary circuit of the electrical equipment in the substation based on the infrared images;

[0008] Locate the position of the electrical signal that determines the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault points to determine the actual fault point;

[0009] Convert the actual fault point into a fault matrix to be processed, perform feature extraction on the fault matrix to be processed, and determine the actual fault point matrix;

[0010] According to the actual fault point matrix, the neural network model is used to locate and predict the fault point, and a fault alarm is issued for the secondary circuit of the substation electrical equipment;

[0011] Establish a secondary circuit database for substation electrical equipment to store possible fault point data, actual fault point data, predicted fault point data and alarm data.

[0012] Optionally, obtaining an infrared image of the electrical equipment of the substation, and determining a possible fault point in the secondary circuit of the electrical equipment of the substation according to the infrared image, includes:

[0013] Obtain infrared images of electrical equipment in substations, perform matrix conversion and angle correction on the infrared images, and obtain monitoring matrices;

[0014] Process the monitoring matrix to obtain the final infrared image of the substation electrical equipment;

[0015] The infrared images of the final substation electrical equipment are identified to determine possible fault points.

[0016] Optionally, an infrared image of the electrical equipment of the substation is obtained, and matrix conversion and angle correction are performed on the infrared image to obtain a monitoring matrix, including:

[0017] Acquire a first infrared image of the electrical equipment in the substation, and convert the first infrared image into a first monitoring matrix;

[0018] According to the first monitoring matrix, a second monitoring matrix is ​​obtained by calculating the saturation;

[0019] Performing angle correction on the second infrared image of the substation electrical equipment corresponding to the second monitoring matrix to obtain a monitoring matrix;

[0020] The monitoring matrix is ​​processed to obtain the final infrared image of the substation electrical equipment, including:

[0021] Grayscale processing is performed on the pixel points in the monitoring matrix to obtain a grayscale matrix;

[0022] The elements in the grayscale matrix are corroded to obtain the final infrared image of the substation electrical equipment.

[0023] Optionally, performing angle correction on the second infrared image of the substation electrical equipment corresponding to the second monitoring matrix to obtain the monitoring matrix includes:

[0024] The second monitoring matrix is ​​transformed according to the polar coordinate equation to obtain a third monitoring matrix;

[0025] Perform characteristic rotation processing on the third monitoring matrix to obtain a monitoring matrix.

[0026] Optionally, locate the position of the electrical signal for determining the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault points to determine the actual fault point, including:

[0027] Obtain the electrical signals in the secondary circuit of the substation electrical equipment, and reconstruct the electrical signal matrix according to the electrical signals;

[0028] Performing wavelet transform on the reconstructed electrical signals in the reconstructed electrical signal matrix to obtain a high-frequency reconstructed electrical signal set and a low-frequency reconstructed electrical signal set;

[0029] The high-frequency reconstructed electrical signal set and the low-frequency reconstructed electrical signal set are differentially processed to obtain a high-frequency reconstructed electrical signal variance set and a low-frequency reconstructed electrical signal variance set.

[0030] Optionally, after performing differential processing on the high-frequency reconstructed electrical signal set and the low-frequency reconstructed electrical signal set to obtain the high-frequency reconstructed electrical signal variance set and the low-frequency reconstructed electrical signal variance set, the method further includes:

[0031] Superimposing the high-frequency reconstructed electrical signal variance set and the low-frequency reconstructed electrical signal variance set in sequence to obtain the reconstructed electrical signal variance set;

[0032] Compare the reconstructed electrical signal variance set with a preset threshold to determine the reconstructed electrical signal detection set;

[0033] Extract features from the reconstructed electrical signal detection set to obtain a reconstructed electrical signal set, and then determine the electrical signal for fault judgment;

[0034] When the difference between the position of the electrical signal determining the fault and the distance to the possible fault point is less than a preset difference, the possible fault point is determined to be the actual fault point.

[0035] Optionally, the actual fault point is converted into a fault matrix to be processed, and feature extraction is performed on the fault matrix to be processed to determine the actual fault point matrix, including:

[0036] Set the actual fault point set;

[0037] Obtain a fault matrix to be processed according to the actual fault point set;

[0038] The actual fault point features in the fault matrix to be processed are extracted to determine the actual fault point matrix.

[0039] Optionally, based on the actual fault point matrix, the fault point is located and predicted based on the neural network model, and a fault alarm is issued for the secondary circuit of the substation electrical equipment, including:

[0040] Determine an actual fault point training matrix and an actual fault point test matrix according to the actual fault point matrix;

[0041] Input the actual fault point training matrix into the neural network input layer, and obtain the trained neural network model through iteration;

[0042] Input the actual fault point test matrix into the trained neural network model and output the predicted fault point;

[0043] Locate the predicted fault point and issue a fault alarm.

[0044] According to another aspect of the present invention, a fault alarm management device is provided, the fault alarm management device comprising:

[0045] A possible fault point determination module is used to obtain infrared images of electrical equipment in the substation and determine possible fault points in the secondary circuit of the electrical equipment in the substation based on the infrared images;

[0046] The actual fault point determination module is used to locate the position of the electrical signal for determining the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault points to determine the actual fault point;

[0047] An actual fault point matrix determination module is used to convert the actual fault point into a fault matrix to be processed, perform feature extraction on the fault matrix to be processed, and determine the actual fault point matrix;

[0048] The predicted fault point location and alarm module is used to locate and predict the fault point based on the actual fault point matrix and the neural network model, and to issue fault alarms for the secondary circuits of the substation electrical equipment;

[0049] The data storage module is used to establish a secondary circuit database for substation electrical equipment, storing possible fault point data, actual fault point data, predicted fault point data and alarm data.

[0050] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the fault alarm management method of any embodiment of the present invention when executed.

[0051] The technical solution of the embodiment of the present invention is to set a fault alarm management method for the secondary circuit of the substation electrical equipment, determine the possible fault points in the secondary circuit of the substation electrical equipment by acquiring the infrared image of the substation electrical equipment; locate the position of the electrical signal for judging the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault point to verify whether the possible fault point is the point where the fault actually occurs, and then determine the actual fault point to improve the detection performance; then determine the actual fault point matrix according to the actual fault point, locate and predict the fault point based on the actual fault point matrix based on the neural network model, realize the prediction of the fault point, and perform fault alarm on the secondary circuit of the substation electrical equipment; establish a secondary circuit database of the substation electrical equipment to store possible fault point data, actual fault point data, predicted fault point data and alarm data, realize real-time fault detection and alarm on the secondary circuit of the substation electrical equipment, improve the accuracy of fault detection, and reduce the adverse effects on the secondary circuit of the substation electrical equipment.

[0052] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in 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 creative work.

[0054] Figure 1 is a flow chart of a fault alarm management method provided according to an embodiment of the present invention;

[0055] Figure 2 is a flow chart of another fault alarm management method provided according to an embodiment of the present invention;

[0056] Figure 3 is a flowchart of another fault alarm management method provided by an embodiment of the present invention;

[0057] Figure 4 is a flowchart of another fault alarm management method provided by an embodiment of the present invention;

[0058] Figure 5 is a flowchart of another fault alarm management method provided by an embodiment of the present invention;

[0059] Figure 6 is a flowchart of another fault alarm management method provided by an embodiment of the present invention;

[0060] Figure 7 is a structural diagram of a fault alarm management device provided according to an embodiment of the present invention;

[0061] Figure 8 It is a structural diagram of a fault alarm management device for implementing the fault alarm management method of the embodiment of the present invention provided according to the embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0063] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0064] Figure 1 This is a flow chart of a fault alarm management method provided according to an embodiment of the present invention. This embodiment can be applied to fault detection and alarm of secondary circuits of electrical equipment in substations. The fault alarm management method can be executed by a fault alarm management device, which can be implemented in the form of hardware and / or software. The fault alarm management method is used for secondary circuits of electrical equipment in substations. Figure 1 As shown, the fault alarm management method includes:

[0065] S110, acquiring an infrared image of the electrical equipment in the substation, and determining a possible fault point in a secondary circuit of the electrical equipment in the substation according to the infrared image.

[0066] Specifically, the secondary circuit of electrical equipment is a low-voltage electrical circuit required to monitor, control, regulate, and protect the operation of the primary electrical equipment and provide operating or production command signals to operation and maintenance personnel. The secondary circuit of electrical equipment includes control circuits, signal circuits, measurement circuits, regulation circuits, relay protection, and automatic device circuits. Possible fault points are points in the secondary circuit of substation electrical equipment that may fail, as determined through preliminary analysis.

[0067] Obtain infrared images of electrical equipment in the substation, analyze and identify the infrared images of the electrical equipment in the substation based on image recognition technology, and find possible fault points. For example, infrared images of electrical equipment in the substation can be obtained by computer vision technology or thermal imaging cameras.

[0068] S120, locate the position of the electrical signal for determining the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault points to determine the actual fault point.

[0069] Specifically, the electrical signal for judging the fault can be understood as the weak electrical signal in the secondary circuit of the electrical equipment. The weak electrical signal detection method is applied to detect the electrical signal in the secondary circuit of the electrical equipment in the substation, and the weak electrical signal is detected by filtering the noise, and the position of the weak electrical signal is located. The position of the located weak electrical signal is compared with the possible fault point obtained by analyzing and identifying the image recognition technology to determine the actual point of fault. Exemplarily, the distance between the position of the weak electrical signal and the position of the possible fault point is determined. If the distance between the position of the weak electrical signal and the position of the possible fault point is less than the preset distance, such as less than 1 mm, it is determined that the possible fault point is the point where the fault actually occurred.

[0070] S130, converting the actual fault points into a fault matrix to be processed, performing feature extraction on the fault matrix to be processed, and determining the actual fault point matrix.

[0071] Specifically, the determined actual fault points are collected and converted into a fault matrix to be processed, and features are extracted from the fault points in the fault matrix to be processed to obtain a final fault point matrix, which is determined to be the actual fault point matrix.

[0072] S140. According to the actual fault point matrix, the fault point is located and predicted based on the neural network model, and a fault alarm is issued for the secondary circuit of the substation electrical equipment.

[0073] Specifically, according to the actual fault point matrix and the trained neural network model, the possible fault points in the future are predicted and the predicted fault points are located to improve the accuracy of fault detection. When the predicted fault point is located, a fault alarm is issued for the secondary circuit of the substation electrical equipment to remind the operation and maintenance staff to carry out maintenance, improve the safety of the secondary circuit of the electrical equipment, and reduce the adverse effects on the secondary circuit of the substation electrical equipment.

[0074] S150, establishing a secondary circuit database of electrical equipment in a substation to store possible fault point data, actual fault point data, predicted fault point data, and alarm data.

[0075] Specifically, the secondary circuit of electrical equipment can be monitored in real time by establishing an electrical equipment secondary circuit detection platform, and timely alarms can be issued when the predicted fault point is located. By identifying the fault point, locating the fault point, and reminding maintenance personnel, full-link visual management of the secondary circuit of electrical equipment can be achieved. A secondary circuit database for substation electrical equipment is established, and possible fault point data, actual fault point data, predicted fault point data, and alarm data are stored in the database to facilitate staff to conduct research and analysis.

[0076] The technical solution of the embodiment of the present invention is to set a fault alarm management method for the secondary circuit of the substation electrical equipment, determine the possible fault points in the secondary circuit of the substation electrical equipment by acquiring the infrared image of the substation electrical equipment; locate the position of the electrical signal for judging the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault point to verify whether the possible fault point is the point where the fault actually occurs, and then determine the actual fault point to improve the detection performance; then determine the actual fault point matrix according to the actual fault point, locate and predict the fault point based on the actual fault point matrix based on the neural network model, realize the prediction of the fault point, and perform fault alarm on the secondary circuit of the substation electrical equipment; establish a secondary circuit database of the substation electrical equipment to store possible fault point data, actual fault point data, predicted fault point data and alarm data, realize real-time fault detection and alarm on the secondary circuit of the substation electrical equipment, improve the accuracy of fault detection, and reduce the adverse effects on the secondary circuit of the substation electrical equipment.

[0077] Figure 2 FIG. 1 is a flowchart of another fault alarm management method provided according to an embodiment of the present invention. This embodiment is a detailed description of some technical features of the above embodiment. Figure 2 As shown, the fault alarm management method includes:

[0078] S210, acquiring an infrared image of the electrical equipment in the substation, performing matrix conversion and angle correction on the infrared image, and obtaining a monitoring matrix.

[0079] In an optional embodiment of the present invention, an infrared image of the substation electrical equipment is obtained, and the infrared image is matrix converted and angle corrected to obtain a monitoring matrix, including: obtaining a first infrared image of the substation electrical equipment, and converting the first infrared image into a first monitoring matrix.

[0080] Specifically, the first infrared image of the substation electrical equipment is obtained, the horizontal dimension of the first infrared image of the substation electrical equipment is set to i, and the vertical dimension is set to j, and the first infrared image of the substation electrical equipment is converted into a first monitoring matrix, which is expressed as follows:

[0081]

[0082] Among them, a ij represents the pixel points of the horizontal i dimension and the vertical j dimension in the first infrared image of the electrical equipment of the substation. A represents the first monitoring matrix.

[0083] According to the first monitoring matrix, a second monitoring matrix is ​​obtained by calculating the saturation; and an angle correction is performed on a second infrared image of the substation electrical equipment corresponding to the second monitoring matrix to obtain a monitoring matrix.

[0084] Specifically, the saturation of the pixel points in the first infrared image of the substation electrical equipment is set, the saturation of the pixel points in the first infrared image of the substation electrical equipment is calculated, and the substation electrical equipment in the first infrared image of the substation electrical equipment is extracted. The calculation formula is as follows:

[0085]

[0086] Among them, min RGB represents the minimum RGB pixel value in the first infrared image of the substation electrical equipment, max RGB represents the maximum RGB pixel value in the first infrared image of the substation electrical equipment, and B represents the second monitoring matrix. The second monitoring matrix B corresponds to the second infrared image of the substation electrical equipment. The second infrared image is different from the first infrared image. The second infrared image is obtained by calculating the saturation of the pixels in the first infrared image to obtain the second monitoring matrix, and then converted by the second monitoring matrix.

[0087] The second monitoring matrix is ​​transformed according to the polar coordinate equation to obtain a third monitoring matrix; and the third monitoring matrix is ​​subjected to characteristic rotation processing to obtain a monitoring matrix.

[0088] Specifically, a straight line equation y=bx+b′ is set, wherein x and y represent elements in the second monitoring matrix, and b and b′ represent pixel peak values ​​of pixel points in the second monitoring matrix.

[0089] The polar coordinate equation is set to α=xcosθ+ysinθ, where θ represents the angular coordinate, and the pixel points in the second monitoring matrix are transformed according to the polar coordinate equation to obtain a third monitoring matrix.

[0090] The third monitoring matrix is ​​characterized by a rotation process. Exemplarily, original coordinates are set, and the third monitoring matrix is ​​rotated along the original coordinates in rows and columns to obtain a monitoring matrix.

[0091] S220, processing the monitoring matrix to obtain a final infrared image of the substation electrical equipment.

[0092] In an optional embodiment of the present invention, the monitoring matrix is ​​processed to obtain an infrared image of the final substation electrical equipment, including: graying the pixels in the monitoring matrix to obtain a grayed matrix; corroding the elements in the grayed matrix to obtain an infrared image of the final substation electrical equipment.

[0093] Specifically, the three primary colors are set to be β1, β2 and β3, and the gray value B′ is calculated as follows:

[0094] B′=0.30β1+0.59β2+0.12β3;

[0095] Assume that the frequency of pixels in the monitoring matrix is ​​c, and the grayscale histogram matrix is:

[0096]

[0097] Among them, c i1 Represents the pixel point in the monitoring matrix, i1=1,2,3,...,255; Set the number of elements in the grayscale histogram matrix to c′, normalize the grayscale histogram matrix, and obtain the normalized grayscale histogram matrix The normalized grayscale histogram matrix is ​​divided into background elements and target elements. The grayscale value threshold is set to ω. The grayscale values ​​of the elements in the normalized grayscale histogram matrix that are greater than ω are recorded as target elements, and the target element ratio c1 is calculated; the grayscale values ​​of the elements in the normalized grayscale histogram matrix that are less than or equal to ω are recorded as background elements, and the background element ratio c2 is calculated; the average grayscale value of the target element is set to c′1, the average grayscale value of the background element is set to c′2, and the average grayscale value of the elements in the normalized grayscale histogram matrix is ​​set to c″. The variance χ is calculated as follows:

[0098] χ=c1(c1′-c″) 2 +c2(c′2-c″) 2 ;

[0099] When the variance takes the maximum value, ω is the optimal gray value threshold, and the elements in the monitoring matrix are binarized to obtain the gray matrix A″′. The elements in the gray matrix are corroded, and the corrosion matrix is ​​set to A. The gray matrix A″′ and the corrosion matrix Satisfy the formula Where A′ represents the elements in the corrosion matrix, express After the above calculation, the infrared image of the electrical equipment of the final substation is obtained.

[0100] S230, identifying the infrared image of the electrical equipment of the final substation to determine the possible fault point.

[0101] Specifically, by acquiring the infrared image of the substation electrical equipment, the infrared image of the substation electrical equipment is converted into a matrix, and by screening the saturation of the pixel points in the matrix, the target area is extracted and the surrounding rectangular area is filled, and then angle correction and morphological processing are used to eliminate interference irrelevant to the target area, and the final infrared image of the substation electrical equipment is obtained to identify possible fault points, reduce image errors, and improve recognition effect.

[0102] S240, locate the position of the electrical signal for determining the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault points to determine the actual fault point.

[0103] S250, converting the actual fault point into a fault matrix to be processed, performing feature extraction on the fault matrix to be processed, and determining the actual fault point matrix.

[0104] S260. According to the actual fault point matrix, the fault point is located and predicted based on the neural network model, and a fault alarm is issued for the secondary circuit of the substation electrical equipment.

[0105] S270. Establish a secondary circuit database for substation electrical equipment to store possible fault point data, actual fault point data, predicted fault point data, and alarm data.

[0106] Figure 3 FIG. 1 is a flow chart of another fault alarm management method provided according to an embodiment of the present invention. Figure 3 As shown, the fault alarm management method includes:

[0107] S310, obtaining an infrared image of the electrical equipment in the substation, and determining possible fault points in the secondary circuit of the electrical equipment in the substation according to the infrared image.

[0108] S311. Acquire electrical signals in the secondary circuit of the substation electrical equipment, and reconstruct an electrical signal matrix according to the electrical signals.

[0109] Specifically, the electrical signals in the secondary circuit of the substation electrical equipment are obtained, which are recorded as the electrical signal set C = {a1, a2, a3, ..., a i′}, where a i′ represents the i′th electrical signal, and the electrical signal dimension in the electrical signal set C is set to j′. The reconstructed electrical signal matrix is ​​constructed according to the electrical signal set C as follows:

[0110]

[0111] Among them, A1 represents the reconstructed electrical signal matrix, a i ″ j′ Represents the reconstructed electrical signal of the j′th dimension of the i′th electrical signal in the reconstructed electrical signal matrix.

[0112] S312, performing wavelet transform on the reconstructed electrical signals in the reconstructed electrical signal matrix to obtain a high-frequency reconstructed electrical signal set and a low-frequency reconstructed electrical signal set.

[0113] Specifically, wavelet analysis is performed on the reconstructed electrical signals in the reconstructed electrical signal matrix, and a column in the reconstructed electrical signal matrix is ​​taken as the first reconstructed electrical signal set. in Indicates the i′th electrical signal dimension of the reconstructed electrical signal; calculating the average value of the reconstructed electrical signals in the first reconstructed electrical signal set, setting a first threshold value ω1, when the absolute value of the difference between the reconstructed electrical signals in the first reconstructed electrical signal set and the average value of the reconstructed electrical signals in the first reconstructed electrical signal set is greater than the first threshold value ω1, adding the corresponding reconstructed electrical signals in the first reconstructed electrical signal set to the high-frequency reconstructed electrical signal set; otherwise, adding the corresponding reconstructed electrical signals in the first reconstructed electrical signal set to the low-frequency reconstructed electrical signal set.

[0114] S313 , performing differential processing on the high-frequency reconstructed electrical signal set and the low-frequency reconstructed electrical signal set to obtain a high-frequency reconstructed electrical signal variance set and a low-frequency reconstructed electrical signal variance set.

[0115] Specifically, the optimal sliding window width is set to d, and the sliding kurtosis algorithm is used to process the high-frequency reconstructed electrical signal set and the low-frequency reconstructed electrical signal set; there are d′ high-frequency reconstructed electrical signals in the high-frequency reconstructed electrical signal set, and d′>d, the variance of the d-1 high-frequency reconstructed electrical signals after the first high-frequency reconstructed electrical signal in the high-frequency reconstructed electrical signal set is calculated, recorded as the first variance of the high-frequency reconstructed electrical signal set, and the first variance of the high-frequency reconstructed electrical signal set is added to the high-frequency reconstructed electrical signal variance set; then the variance of the d-2 high-frequency reconstructed electrical signals after the second high-frequency reconstructed electrical signal in the high-frequency reconstructed electrical signal set is calculated, recorded as the second variance of the high-frequency reconstructed electrical signal set, and the second variance of the high-frequency reconstructed electrical signal set is added to the high-frequency reconstructed electrical signal variance set, and the high-frequency reconstructed electrical signal variance set is obtained by calculating in sequence.

[0116] There are d″ low-frequency reconstructed electrical signals in the low-frequency reconstructed electrical signal set, and d″>d. The variance of the d-1 low-frequency reconstructed electrical signals after the first low-frequency reconstructed electrical signal in the low-frequency reconstructed electrical signal set is calculated, recorded as the first variance of the low-frequency reconstructed electrical signal set, and the first variance of the low-frequency reconstructed electrical signal set is added to the low-frequency reconstructed electrical signal variance set; then the variance of the d-2 low-frequency reconstructed electrical signals after the second low-frequency reconstructed electrical signal in the low-frequency reconstructed electrical signal set is calculated, recorded as the second variance of the low-frequency reconstructed electrical signal set, and the second variance of the low-frequency reconstructed electrical signal set is added to the low-frequency reconstructed electrical signal variance set, and the low-frequency reconstructed electrical signal variance set is obtained by calculation in sequence.

[0117] S314 , sequentially superimposing the high-frequency reconstructed electrical signal variance set and the low-frequency reconstructed electrical signal variance set to obtain a reconstructed electrical signal variance set.

[0118] S315: Compare the reconstructed electrical signal variance set with a preset threshold to determine the reconstructed electrical signal detection set.

[0119] Specifically, the preset threshold is set to ω2, and the reconstructed electric signal variance set with a value less than the preset threshold is added to the reconstructed electric signal detection set.

[0120] S316: extract features from the reconstructed electrical signal detection set to obtain a reconstructed electrical signal set, and then determine the electrical signal for fault judgment.

[0121] Specifically, feature extraction is performed on the reconstructed electrical signal detection set, and noise is filtered to obtain a processed reconstructed electrical signal set. The reconstructed electrical signals in the processed reconstructed electrical signal set are electrical signals for determining faults, that is, weak electrical signals.

[0122] S317: When the difference between the position of the electrical signal that determines the fault and the distance to the possible fault point is less than a preset difference, the possible fault point is determined to be the actual fault point.

[0123] Specifically, the position of the weak electric signal is located and compared with the position of the possible fault point, and the preset difference is set to ω3. When the difference between the position of the weak electric signal and the position of the possible fault point is less than ω3, the possible fault point is the actual fault point; otherwise, the possible fault point is not the actual fault point. Weak electric signals are detected by combining wavelet analysis with peak filtering algorithm, and high-frequency electric signals and low-frequency electric signals are distinguished by reconstructing electric signals. Then, sliding peak filtering is used to process high-frequency electric signals and low-frequency electric signals to obtain variance sets, and the variance sets are sequentially superimposed to verify whether the possible fault point is the actual fault point. It is suitable for extracting weak electric signals under noise interference, which greatly improves the detection capability of weak electric signals.

[0124] S318, converting the actual fault point into a fault matrix to be processed, performing feature extraction on the fault matrix to be processed, and determining the actual fault point matrix.

[0125] S319. According to the actual fault point matrix, the fault point is located and predicted based on the neural network model, and a fault alarm is issued for the secondary circuit of the substation electrical equipment.

[0126] S320. Establish a secondary circuit database for substation electrical equipment to store possible fault point data, actual fault point data, predicted fault point data, and alarm data.

[0127] Figure 4 FIG. 1 is a flow chart of another fault alarm management method provided according to an embodiment of the present invention. Figure 4 As shown, the fault alarm management method includes:

[0128] S410, obtaining an infrared image of the electrical equipment in the substation, and determining a possible fault point in the secondary circuit of the electrical equipment in the substation according to the infrared image.

[0129] S420, locate the position of the electrical signal for determining the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault points to determine the actual fault point.

[0130] S430: Set an actual fault point set.

[0131] Specifically, the actual fault point set is set to C″={a″1,a″2,a″3,...,a″ i″}.

[0132] S440: Obtain a fault matrix to be processed according to the actual fault point set.

[0133] Specifically, the characteristic dimension of each fault point in the actual fault point set is j″, and the fault matrix to be processed is as follows:

[0134]

[0135] Among them, a″ i″j″ It represents the fault point to be processed whose feature dimension is j″ in the fault matrix to be processed.

[0136] Set the output average current value to e, the power consumption parameter to ε, the fault point characteristic value of the secondary circuit of the electrical equipment to e, and build a fault point acquisition model. The calculation formula is as follows:

[0137]

[0138] in, represents the power consumption parameter of the i2th fault point, D represents the fault point acquisition function, and i2=1,2,3,...,i″.

[0139] The power conversion coefficient of the secondary circuit of the electrical equipment is set to δ, and the fault signal distribution characteristics of the fault point to be processed are set to The calculation formula for the upper limit D′ of the secondary circuit power of electrical equipment is as follows:

[0140]

[0141] The power distribution of the fault points in the fault point set is obtained by calculating the upper limit of the secondary circuit power of the electrical equipment, and the power distribution set of the fault points D″={e1,e2,e3,...,e i″}, where e i″ represents the power of the i″th fault point; select the minimum value of the fault point power in the fault point power distribution set, denoted as e min , and then calculate the average value of the fault point power in the fault point power distribution set, recorded as ; The calculation formula of the secondary circuit distribution parameter φ of electrical equipment is as follows:

[0142]

[0143] The fusion parameter method is used to calculate the fusion parameter of the fault point, which is recorded as , the characteristic function of the fault point is set to The extraction parameters of the fault point are: , the characteristic interval length of the fault point is e′, then the characteristic function calculation formula of the fault point is as follows:

[0144]

[0145] in, represents the fusion parameter of the i3th fault point, i3=1,2,3,...,i″.

[0146] S450: extracting actual fault point features in the fault matrix to be processed, and determining an actual fault point matrix.

[0147] Specifically, the feature function of the fault point in the actual fault point set is used to extract the feature of the actual fault point, and the actual fault point set C″′={a″′1,a″′2,a″′3,...,a″′ i″}, set the fault point feature dimension in the actual fault point set to j″′, and the actual fault point matrix A3 is as follows:

[0148]

[0149] Among them, a″′ i″′j″′It represents the actual fault point with the feature dimension of j″′ of the i″′th fault point in the actual fault point matrix.

[0150] The technical solution of the embodiment of the present invention realizes data collection of actual fault points of the secondary circuit of the electrical equipment by modeling and processing the data information collected in real time from the fault of the secondary circuit of the electrical equipment, provides reliable and accurate data for subsequent feature extraction of the actual fault point, and then reduces the data dimension and the amount of subsequent processing calculation by extracting the fault features of the data information collected in real time from the fault of the secondary circuit of the electrical equipment.

[0151] S460. According to the actual fault point matrix, the fault point is located and predicted based on the neural network model, and a fault alarm is issued for the secondary circuit of the substation electrical equipment.

[0152] S470. Establish a secondary circuit database for substation electrical equipment to store possible fault point data, actual fault point data, predicted fault point data, and alarm data.

[0153] Figure 5 FIG. 1 is a flow chart of another fault alarm management method provided according to an embodiment of the present invention. Figure 5 As shown, the fault alarm management method includes:

[0154] S510: Acquire an infrared image of the electrical equipment in the substation, and determine a possible fault point in the secondary circuit of the electrical equipment in the substation according to the infrared image.

[0155] S520, locate the position of the electrical signal for determining the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault points to determine the actual fault point.

[0156] S530: Convert the actual fault point into a fault matrix to be processed, perform feature extraction on the fault matrix to be processed, and determine the actual fault point matrix.

[0157] S540: Determine an actual fault point training matrix and an actual fault point test matrix according to the actual fault point matrix.

[0158] Specifically, the j1 column is selected from the actual fault point matrix as the actual fault point training matrix, and the remaining j2 columns are selected from the actual fault point matrix as the actual fault point test matrix.

[0159] S550, input the actual fault point training matrix into the neural network input layer, and obtain the trained neural network model through iteration.

[0160] Specifically, the actual fault point training matrix is ​​input into the input layer of the back propagation (BP) neural network, the number of neurons is set to g, the hidden layer activation function is set to f, the actual fault point training matrix is ​​processed by the hidden layer activation function, and the output layer outputs the processing result; the error function is set to f′, and the calculation formula is as follows:

[0161] f′=||E out -E′ out || 2 ;

[0162] Among them, E out Represents the output processing result of the output layer, E′ out Indicates the expected output processing result.

[0163] Set the error threshold to ξ, the current number of iterations to F′, and the maximum number of iterations to F. When the error function value is less than ξ or the current number of iterations is equal to the maximum number of iterations, stop the iteration and get the trained BP neural network model; otherwise, update the network connection weights and continue iterating until the error function value is less than ξ or the current number of iterations is equal to the maximum number of iterations.

[0164] S560, input the actual fault point test matrix into the trained neural network model, and output the predicted fault point.

[0165] Specifically, the actual fault point test matrix is ​​input into the trained BP neural network model, and the error accuracy threshold is set to ψ. When the error accuracy between the fault point result output by the trained BP neural network model and the actual fault point is less than ψ, the trained BP neural network model is the final BP neural network model; otherwise, the trained BP neural network model is not the final BP neural network model; repeat S550 to retrain the BP neural network model; input possible future fault points into the final BP neural network model, output the prediction results of possible future fault points, and realize fault point prediction.

[0166] S570: Locate the predicted fault point and issue a fault alarm.

[0167] Specifically, the predicted fault point is located, and a fault alarm is issued, and the location of the fault point in the secondary circuit of the electrical equipment is uploaded to the electrical equipment secondary circuit monitoring platform to remind maintenance personnel to carry out maintenance at the fault location.

[0168] The embodiment of the present invention divides the actual fault point matrix into an actual fault point training matrix and an actual fault point test matrix, inputs the actual fault point training matrix into a BP neural network, trains the BP neural network to obtain a trained BP neural network model, then inputs the actual fault point test matrix into the trained BP neural network model for verification to obtain a final BP neural network model, and finally inputs the predicted fault point data into the final BP neural network model to predict the fault point and improve the prediction accuracy.

[0169] S580. Establish a secondary circuit database for substation electrical equipment to store possible fault point data, actual fault point data, predicted fault point data, and alarm data.

[0170] Figure 6 The present invention provides a flowchart of another fault alarm management method according to an embodiment of the present invention.

[0171] like Figure 6 As shown, the fault alarm management method includes:

[0172] S610, perform image recognition on infrared images of electrical equipment in the substation; S620, determine possible fault points; S630, locate the position of weak electrical signals through wavelet decomposition and peak filtering algorithm; S640, verify whether the possible fault point is the actual fault point; if not, execute S650, abandon and return to execute S610; if so, execute S660, extract features of the actual fault point; S670, train the neural network model to realize the prediction of fault points; S680, electrical equipment secondary circuit fault alarm; S690, establish a monitoring platform and database.

[0173] Figure 7 Schematic diagram of a fault alarm management device provided according to an embodiment of the present invention. Figure 7 As shown, the fault alarm management device includes:

[0174] The possible fault point determination module 100 is used to obtain an infrared image of the electrical equipment in the substation and determine the possible fault point in the secondary circuit of the electrical equipment in the substation according to the infrared image.

[0175] The actual fault point determination module 200 is used to locate the position of the electrical signal for determining the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault points to determine the actual fault point.

[0176] The actual fault point matrix determination module 300 is used to convert the actual fault points into a fault matrix to be processed, perform feature extraction on the fault matrix to be processed, and determine the actual fault point matrix.

[0177] The predicted fault point location and alarm module 400 is used to locate and predict the fault point based on the actual fault point matrix and the neural network model, and to issue a fault alarm for the secondary circuit of the substation electrical equipment.

[0178] The data storage module 500 is used to establish a secondary circuit database of the substation electrical equipment, and store possible fault point data, actual fault point data, predicted fault point data and alarm data.

[0179] The technical solution of the embodiment of the present invention is to set a fault alarm management device for the secondary circuit of the substation electrical equipment, determine the possible fault point in the secondary circuit of the substation electrical equipment by acquiring the infrared image of the substation electrical equipment; locate the position of the electrical signal for judging the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault point to verify whether the possible fault point is the point where the fault actually occurs, and then determine the actual fault point to improve the detection performance; then determine the actual fault point matrix according to the actual fault point, locate and predict the fault point based on the actual fault point matrix based on the neural network model, realize the prediction of the fault point, and perform fault alarm on the secondary circuit of the substation electrical equipment; establish a secondary circuit database of the substation electrical equipment to store possible fault point data, actual fault point data, predicted fault point data and alarm data, realize real-time fault detection and alarm on the secondary circuit of the substation electrical equipment, improve the accuracy of fault detection, and reduce the adverse effects on the secondary circuit of the substation electrical equipment.

[0180] The fault alarm management device provided in the embodiment of the present invention can execute the fault alarm management method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0181] Figure 8 1 is a schematic diagram of the structure of a fault alarm management device for implementing the fault alarm management method of the embodiment of the present invention provided by the embodiment of the present invention. Figure 8 As shown, the fault alarm management device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the fault alarm management device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0182] Multiple components in the fault alarm management device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the fault alarm management device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0183] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a fault alarm management method.

[0184] In some embodiments, the fault alarm management method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the fault alarm management device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the fault alarm management method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the fault alarm management method in any other appropriate manner (e.g., by means of firmware).

[0185] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0186] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0187] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0188] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0189] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0190] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0191] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0192] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A fault alarm management method, characterized in that: Used for the secondary circuit of electrical equipment in a substation; the fault alarm management method comprises: Acquire an infrared image of the electrical equipment in the substation, and determine a possible fault point in the secondary circuit of the electrical equipment in the substation according to the infrared image; Locating the position of the electrical signal for determining the fault in the secondary circuit of the electrical equipment of the substation, and comparing it with the possible fault point to determine the actual fault point; Converting the actual fault point into a fault matrix to be processed, performing feature extraction on the fault matrix to be processed, and determining an actual fault point matrix; According to the actual fault point matrix, the fault point is located and predicted based on the neural network model, and a fault alarm is issued for the secondary circuit of the substation electrical equipment; A secondary circuit database of the substation electrical equipment is established to store the possible fault point data, the actual fault point data, the predicted fault point data and the alarm data.

2. The fault alarm management method according to claim 1, characterized in that: The step of acquiring an infrared image of the electrical equipment in the substation and determining a possible fault point in a secondary circuit of the electrical equipment in the substation according to the infrared image comprises: Acquire an infrared image of the electrical equipment in the substation, perform matrix conversion and angle correction on the infrared image, and obtain a monitoring matrix; Processing the monitoring matrix to obtain an infrared image of the electrical equipment of the final substation; The infrared image of the final substation electrical equipment is identified to determine the possible fault point.

3. The fault alarm management method according to claim 2, characterized in that: The step of acquiring an infrared image of the electrical equipment in the substation, performing matrix conversion and angle correction on the infrared image, and obtaining a monitoring matrix includes: Acquire a first infrared image of the electrical equipment of the substation, and convert the first infrared image into a first monitoring matrix; According to the first monitoring matrix, obtaining a second monitoring matrix by calculating saturation; Performing angle correction on the second infrared image of the substation electrical equipment corresponding to the second monitoring matrix to obtain a monitoring matrix; The processing of the monitoring matrix to obtain the final infrared image of the substation electrical equipment includes: Performing grayscale processing on the pixel points in the monitoring matrix to obtain a grayscale matrix; The elements in the grayscale matrix are corroded to obtain the final infrared image of the electrical equipment in the substation.

4. The fault alarm management method according to claim 3, characterized in that: The step of performing angle correction on the second infrared image of the substation electrical equipment corresponding to the second monitoring matrix to obtain a monitoring matrix includes: Converting the second monitoring matrix according to the polar coordinate equation to obtain a third monitoring matrix; Performing characteristic rotation processing on the third monitoring matrix to obtain the monitoring matrix.

5. The fault alarm management method according to claim 1, characterized in that: The step of locating the position of the electrical signal for determining the fault in the secondary circuit of the substation electrical equipment and comparing it with the possible fault point to determine the actual fault point includes: Acquire electrical signals in the secondary circuit of the substation electrical equipment, and construct a reconstructed electrical signal matrix based on the electrical signals; Performing wavelet transform on the reconstructed electrical signals in the reconstructed electrical signal matrix to obtain a high-frequency reconstructed electrical signal set and a low-frequency reconstructed electrical signal set; The high-frequency reconstructed electrical signal set and the low-frequency reconstructed electrical signal set are differentially processed to obtain a high-frequency reconstructed electrical signal variance set and a low-frequency reconstructed electrical signal variance set.

6. The fault alarm management method according to claim 5, characterized in that: After performing differential processing on the high-frequency reconstructed electrical signal set and the low-frequency reconstructed electrical signal set to obtain a high-frequency reconstructed electrical signal variance set and a low-frequency reconstructed electrical signal variance set, the method further includes: Sequentially superimposing the high-frequency reconstructed electrical signal variance set and the low-frequency reconstructed electrical signal variance set to obtain a reconstructed electrical signal variance set; Comparing the reconstructed electrical signal variance set with a preset threshold to determine a reconstructed electrical signal detection set; Performing feature extraction on the reconstructed electrical signal detection set to obtain a reconstructed electrical signal set, and then determining an electrical signal for determining a fault; When the difference between the position of the fault-determining electrical signal and the distance to the possible fault point is less than a preset difference, the possible fault point is determined to be the actual fault point.

7. The fault alarm management method according to claim 1, characterized in that: The converting the actual fault point into a fault matrix to be processed, performing feature extraction on the fault matrix to be processed, and determining the actual fault point matrix includes: Set the actual fault point set; Obtaining a fault matrix to be processed according to the actual fault point set; The actual fault point features in the fault matrix to be processed are extracted to determine the actual fault point matrix.

8. The fault alarm management method according to claim 1, characterized in that: The method of locating and predicting the fault point based on the actual fault point matrix and issuing a fault alarm for the secondary circuit of the substation electrical equipment based on the neural network model includes: Determine an actual fault point training matrix and an actual fault point test matrix according to the actual fault point matrix; Inputting the actual fault point training matrix into the neural network input layer, and obtaining the trained neural network model through iteration; Inputting the actual fault point test matrix into the trained neural network model and outputting the predicted fault point; The predicted fault point is located and a fault alarm is issued.

9. A fault alarm management device, characterized in that: include: A possible fault point determination module is used to obtain an infrared image of the substation electrical equipment and determine a possible fault point in the secondary circuit of the substation electrical equipment according to the infrared image; An actual fault point determination module is used to locate the position of the electrical signal for determining the fault in the secondary circuit of the substation electrical equipment, and compare it with the possible fault point to determine the actual fault point; An actual fault point matrix determination module is used to convert the actual fault points into a fault matrix to be processed, perform feature extraction on the fault matrix to be processed, and determine the actual fault point matrix; A predicted fault point location and alarm module, used to locate and predict the fault point based on the actual fault point matrix and the neural network model, and to issue a fault alarm for the secondary circuit of the substation electrical equipment; The data storage module is used to establish the secondary circuit database of the substation electrical equipment, and store the possible fault point data, the actual fault point data, the predicted fault point data and the alarm data.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the fault alarm management method according to any one of claims 1 to 8 when executed.

Images