Power transmission channel visualization-based key hidden danger prediction method and system, and computer readable storage medium

Abstract

The invention belongs to the technical field of intelligent operation inspection of power transmission lines, and more specifically relates to a key hidden danger prediction method and system based on power transmission channel visualization, and a computer readable storage medium. The method comprises the following steps: preprocessing visual alarm data of a power transmission line; dividing the preprocessed data according to regions and calculating weights; constructing a time-space domain two-dimensional matrix model; performing chi-square test on the whole time-space domain two-dimensional matrix, matrix rows and matrix columns, and dividing hidden dangers into super-key hidden dangers, key hidden dangers and conventional hidden dangers based on comparison between calculated chi-square statistics and critical values; according to the method, a k-means algorithm is used to obtain areas where key hidden dangers and super-key hidden dangers are prone to occurrence, and a mean value comparison method is used to calculate a month where the key hidden dangers are prone to occurrence, so that the key hidden dangers which may occur are predicted in advance at a specific time or place. According to the method, the problems of low efficiency and accuracy of operation and maintenance management of the power transmission line and seasonal and regional key hidden danger prediction are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent operation and inspection of power transmission lines, and more specifically, relates to a method, system and computer-readable storage medium for predicting key hidden dangers based on visualization of power transmission channels. Background Art

[0002] The intelligent monitoring device for power transmission lines based on artificial intelligence has demonstrated excellent intelligent analysis capabilities and accurate identification effects for on-site hidden dangers. As society's requirements for the quality of electricity used in daily life continue to increase, the inspection of power transmission lines has begun to focus on more diversified types of hidden dangers to fully ensure the stable operation of the power grid. However, this move also brings challenges: the massive alarm images generated daily have greatly increased the workload of inspectors and reduced processing efficiency, making it easy for key hidden dangers to be submerged in a large number of ordinary hidden dangers or invalid alarms, making it difficult to be detected and properly handled in a timely manner, thereby potentially increasing power risks. In addition, the identification of key hidden dangers currently still relies on the experience and judgment of inspectors, and there is a lack of automatic identification and prediction methods for key hidden dangers. The automatic identification and early prediction of key hidden dangers will greatly help the operation and maintenance team to plan response strategies in advance, and effectively curb the occurrence of hidden dangers through scientific prevention and control measures, thereby ensuring the safe operation of transmission lines.

[0003] Chinese invention patent CN110399398A discloses a method for identifying high-incidence areas of visual alarms in power transmission line channels. The original data is weighted according to the latitude and longitude attribute values, and the improved k-means algorithm is used to cluster the weighted hidden danger data to realize the identification of high-incidence areas of alarms.

[0004] In summary, not all hidden dangers are regional. Relying solely on the k-means clustering algorithm has the problem of over-calculation, and the prediction is not accurate and reliable enough, and it is even more difficult to accurately capture the characteristics of seasonal and regional hidden dangers. How to provide an efficient and reliable method for visualizing key hidden dangers in transmission lines and provide data support for the prevention and treatment of hidden dangers in transmission lines is one of the problems that technicians in this field need to solve urgently. Summary of the invention

[0005] The present invention aims to overcome at least one defect of the above-mentioned prior art and provide a key hidden danger prediction method based on transmission channel visualization to solve the problems of low efficiency and accuracy in transmission line operation and maintenance management, as well as seasonal and regional key hidden danger prediction.

[0006] The detailed technical scheme of the present invention is as follows:

[0007] A method for predicting key hidden dangers based on visualization of power transmission channels, the method comprising:

[0008] S1. Obtain visual alarm data of transmission lines and pre-process all types of alarm data;

[0009] The preprocessing includes extracting attribute values ​​from the alarm data, retaining the alarm type, alarm time, longitude and latitude attributes, and deleting false alarm data;

[0010] S2, dividing the pre-processed data into regions according to longitude and latitude and setting regional weights;

[0011] S3. Count the number of occurrences of various hidden dangers with the region as the horizontal axis and the 12 months as the vertical axis, and weight the number of hidden dangers to construct a two-dimensional matrix model in the time and space domain;

[0012] S4. Perform chi-square test on the entire two-dimensional matrix, matrix rows, and matrix columns in the time-space domain, and classify the hidden dangers into super-key hidden dangers, key hidden dangers, and conventional hidden dangers based on the comparison between the calculated chi-square statistic and the critical value in the chi-square distribution table;

[0013] S5. When the number of hidden danger occurrences is associated with longitude and latitude and / or month, the k-means algorithm is used to obtain the areas prone to major hidden dangers and super major hidden dangers, and / or the prone month is calculated by the mean comparison method.

[0014] The data used by the k-means algorithm and the mean comparison method are the weighted number of hidden dangers described in S33:

[0015] After k-means clustering, the data values ​​within each cluster and the largest cluster are taken as areas prone to this type of hidden dangers, and the months with the number of hidden dangers higher than the mean by more than 20% are taken as months prone to this type of hidden dangers.

[0016] Specifically, when both the monthly and longitude and latitude conditions of the hidden danger meet the calculation results, the hidden danger will be marked as a super key hidden danger; when one of them is met, it will be marked as a key hidden danger; when neither of them is met, it will be marked as a common hidden danger.

[0017] Furthermore, the step of dividing the preprocessed data by regions and calculating weights in S2 includes the following steps:

[0018] S21: The longitude and latitude coordinates of the same type of hidden dangers are randomly divided into m areas (S1, S2, ..., S m );

[0019] S22: According to formula W i =1-(S i / S) calculates the weights of m regions (W1, W2, ..., W m ), where 1<=i<=m, S=S1+S2+…+S m

[0020] Furthermore, the S3 specifically includes:

[0021] S31, with m regions as the horizontal axis (S1, S2, ..., S m ), with 12 months as the vertical axis (D1, D2, D3, ..., D 12 ), construct a two-dimensional matrix of size m×12;

[0022] S32, traverse a certain type of hidden dangers, and count the hidden dangers that fall in (S i ,D j ) The number of times in the region (R 11 ,R 12 ,...,R ij ), where 1<=i<=m, 1<=j<=12;

[0023] S33, weighting the number of hidden dangers in each area according to the weight in S22 to obtain (0 11 ,O 12 ,...,O ij ). Repeat step S21 until all types are traversed.

[0024] The S4 specifically includes:

[0025] S41. Construct an expected frequency table for the same type of hidden dangers, according to formula E ij =(R i ×C j ) / N calculates the expected frequency of each cell, where R i represents the sum of the i-th row, C j represents the sum of the jth column, and N represents the observation frequency;

[0026] S42. Obtain the chi-square statistics of such hidden dangers based on month and longitude and latitude through chi-square test Calculate the degrees of freedom of the two-dimensional matrix in the time-space domain df = (m-1) × 11, and find the critical value T1 of the chi-square statistic of df at the significance level of 0.05 in the chi-square distribution table;

[0027] like It is believed that the probability of occurrence of this type of hidden danger is related to both the month and longitude and latitude, which means that the probability of occurrence of this type of hidden danger is high in a specific month and longitude and latitude.

[0028] S43, if The chi-square statistic is calculated by weighting the number of hidden dangers based on month and longitude and latitude:

[0029] Calculate (S i ,D j ) The expected frequency of hidden dangers in each month is E1=C j / 12, and then obtain the chi-square statistic Among them, O j =O 1j +O 2j +...+O mj , by finding the critical value T2 of the chi-square statistic with degrees of freedom df=11 at a significance level of 0.05 in the chi-square distribution table; if at this time It is believed that the number of occurrences of this type of hidden danger is related to the monthly period. There is no correlation;

[0030] Calculated in (S i ,D j ) i The expected frequency of hidden dangers in each area is E2=R i / m, and then obtain the chi-square statistic Among them, O i =O i1 +O i2 +...+O i12 , by finding the critical value T3 of the chi-square statistic at the significance level of 0.05 when df=m-1 in the chi-square distribution table, if at this time It is believed that the number of occurrences of this type of hidden danger is related to the longitude and latitude. There is no correlation;

[0031] When neither of them is related, it is marked as a general hidden danger.

[0032] In another aspect of the present invention, a system for predicting key hidden dangers based on visualization of power transmission channels is provided, comprising:

[0033] at least one processor; and

[0034] A memory storing instructions, which, when executed by the at least one processor, enables the at least one processor to execute the above-mentioned method for predicting key hidden dangers based on visualization of power transmission channels.

[0035] In another aspect of the present invention, a machine-readable storage medium is provided, which stores executable instructions, and when the instructions are executed, the machine executes the above-mentioned method for predicting key hidden dangers based on visualization of power transmission channels.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] (1) The present invention provides a method, system and computer-readable storage medium for predicting key hidden dangers based on the visualization of power transmission channels. The method can deeply analyze historical alarm data, accurately capture the characteristics of seasonal and regional hidden dangers, and then scientifically predict key hidden dangers that may appear in the future. This groundbreaking data application not only provides a forward-looking perspective for operation and maintenance personnel, but also helps them prepare for the peak period of hidden dangers and formulate effective response strategies, thereby ensuring the safe and stable operation of transmission lines.

[0038] (2) The present invention provides a method, system and computer-readable storage medium for predicting key hidden dangers based on the visualization of transmission channels. A two-dimensional matrix model of the frequency of hidden danger occurrence in the spatiotemporal domain is carefully designed. In view of the challenge of ensuring uniformity in the spatial domain division in some scenarios, a data weighting strategy is cleverly adopted. This method effectively avoids the statistical deviation that may be caused by differences in regional sizes without changing the distribution characteristics of the original data, thereby ensuring the accuracy and reliability of the correlation data and providing a solid data foundation for subsequent hidden danger analysis.

[0039] (3) The present invention provides a method, system and computer-readable storage medium for predicting key hidden dangers based on transmission channel visualization. Before introducing the k-means clustering algorithm, a preliminary verification of the correlation between hidden dangers and longitude and latitude was carried out, which not only improves the pertinence of the algorithm application, but also significantly reduces unnecessary clustering calculations, greatly optimizes the data processing process, and improves the overall prediction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a method for predicting key hidden dangers based on visualization of power transmission channels described in the present invention. DETAILED DESCRIPTION

[0041] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0042] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0043] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0044] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0045] Example 1

[0046] Ginseng Figure 1 This embodiment provides a method for predicting key hidden dangers based on visualization of power transmission channels, the method comprising:

[0047] S1. Obtaining visual alarm data of power transmission lines; specifically, obtaining visual alarm data of power transmission lines for at least one year, and preprocessing all types of alarm data;

[0048] Preferably, the preprocessing includes extracting attribute values ​​from the alarm data, retaining the alarm type, alarm time, longitude and latitude attributes, and deleting false alarm data.

[0049] Preferably, there are 245,483 pieces of visual alarm data for a certain transmission line. The historical wildfire alarm data from 2022-9-9 to 2023-9-8 are queried. After excluding the continuous alarm data, there are a total of 249 wildfire alarms. The alarm data includes 29 fields such as alarm self-increment ID, alarm occurrence time, alarm type, alarm content, and equipment number. This example conducts a key hidden danger analysis on the wildfire alarm data in the visual alarm image of the transmission line based on the above data.

[0050] This example filters 249 wildfire alarm data, retains only the alarm occurrence time, longitude information and latitude information contained in the alarm content, and sorts them in ascending order according to the alarm occurrence time attribute. Some of the data are shown in Table 1:

[0051] Table 1 Alarm content data table

[0052]

[0053]

[0054] S2. Divide the preprocessed data by region and calculate weights, preferably, specifically including:

[0055] S21. Obtain the longitude and latitude ranges of wildfire hazards for the filtered data, where the longitude range is 103.90144-107.98210 and the latitude range is 25.08300-27.37741. Set the number of regions to 4, that is, divide it into 4 regions. Perform the following divisions on the filtered data:

[0056] Region S1: longitude [103.90144-105) and latitude [25.08300-26)

[0057] Region S2: longitude [103.90144-105), latitude [26-27.37741];

[0058] Region S3: longitude [105-107.98210], latitude [25.08300-26);

[0059] Region S4: longitude [105-107.98210], latitude [26-27.37741].

[0060] S22. Then, the proportion of each area in the entire area is calculated based on the latitude and longitude information. After calculation, the proportions of S1-S4 are 10.76%, 16.16%, 29.21%, and 43.87%, respectively. The weights of the four areas are marked by 1-the proportion of each area, and the final weights are:

[0061] W=(0.8924 0.8384 0.7079 0.5613).

[0063] S3, count the number of occurrences of various hidden dangers to build a two-dimensional matrix model in the time and space domain;

[0064] The number of occurrences of various hidden dangers is counted with 4 regions as the horizontal axis and 12 months as the vertical axis, and the number of hidden dangers is weighted to construct a 4×12 two-dimensional matrix model in the space-time domain.

[0065] Preferably, the S3 specifically includes:

[0066] S31. Taking the number of wildfires in each region in each month as an example, according to the alarm occurrence time and longitude and latitude, the m×12 two-dimensional matrix A can be obtained. In this embodiment, m=4:

[0067]

[0068] S32, taking the traversal of forest fire hazards as an example, the number of times falling in areas S1 to S4 is counted in turn (R 11 ,R 12 ,...,R ij ), where 1<=i<=m, 1<=j<=12.

[0069] S33, weighting the number of hidden dangers in each area according to the weight in S22 to obtain (0 11 ,O 12 ,...,O ij ), in the matrix S, the columns represent months and the rows represent regions. The content of the two-dimensional matrix A' after weighting the A matrix is:

[0070]

[0071] S4. Perform chi-square test on the model of the two-dimensional matrix in the time-space domain and classify the hidden danger types;

[0072] The chi-square test is performed on the two-dimensional matrix, matrix rows, and matrix columns in the entire space-time domain. Based on the comparison between the calculated chi-square statistic and the critical value in the chi-square distribution table, the hidden dangers are divided into super-key hidden dangers, key hidden dangers, and conventional hidden dangers.

[0073] Preferably, the S4 specifically includes:

[0074] S41. Construct an expected frequency table for the same type of hidden dangers, according to formula E ij =(R i ×C j ) / N calculates the expected frequency of each cell, where R i represents the sum of the i-th row, C j represents the sum of the jth column, and N represents the observation frequency;

[0075] The expected frequency table is as follows:

[0076]

[0077] S42, according to the formula The chi-square statistic value of the correlation between wildfire hazard and month and longitude and latitude can be calculated to be 20.525. In this case, the degree of freedom df = (4-1) × 11 = 33. The critical value of the chi-square distribution corresponding to the degree of freedom 33 is shown in Table 2:

[0078] Table 2 Chi-square distribution critical value table corresponding to 33 degrees of freedom

[0079]

[0080] because It is less than the critical value of 47.3999 at the significance level of 0.05, so the wildfire hazard is not simultaneously correlated with the month and longitude and latitude.

[0081] S43. Calculate the correlation between month and region and wildfire hazard respectively. It should be noted that a two-dimensional cross table cannot be formed when calculating the correlation between month and region and wildfire hazard respectively. In this case, the expected frequency = the sum of observed frequencies / number of rows (or columns);

[0082] Calculate (S i ,D j ), and then obtain the chi-square statistic and degrees of freedom. By looking up the chi-square distribution table, we can determine the expected frequency of hidden dangers at a significance level of 0.05. The critical value T2 (19.6751), if at this time It is believed that the number of occurrences of this type of hidden danger is related to the monthly period. There is no correlation;

[0083] Specifically, the degrees of freedom for the chi-square test of month and wildfire hazard are 11, and the calculated chi-square test statistic for month and wildfire hazard is 138.64.

[0084] Calculate (S i ,D j ) i The expected frequency of hidden dangers in the area, and then obtain the chi-square statistic and degrees of freedom, and determine the probability of hidden dangers at a significance level of 0.05 by looking up the chi-square distribution table. The critical value T3 (7.8147), if at this time It is believed that the number of occurrences of this type of hidden danger is related to the longitude and latitude. There is no correlation;

[0085] Specifically, the degrees of freedom for the chi-square test of longitude and latitude and wildfire hazard is 3, and the calculated chi-square test statistic for region and wildfire hazard is 1.73.

[0086] Specifically, the critical values ​​of the chi-square distribution of month and wildfire hazard, longitude and latitude and wildfire hazard are based on 11 degrees of freedom and 3 degrees of freedom, respectively, as shown in Table 3:

[0087] Table 3 Chi-square distribution critical values ​​corresponding to degrees of freedom 11 and 3

[0088]

[0089]

[0090] When both the monthly and longitude and latitude conditions of the hidden danger meet the calculation results, the hidden danger will be marked as a super-key hidden danger. When one of them is met, it will be marked as a key hidden danger. When neither of them is met, it will be marked as a common hidden danger.

[0091] In summary, by comparing the critical value table, it can be seen that the occurrence of wildfire hazards has a high correlation with the month, but a small correlation with the region. This wildfire hazard is a key hazard.

[0092] S5. Use k-means algorithm and mean comparison method to determine the areas and times where hidden dangers are most likely to occur;

[0093] After clustering using the k-means algorithm, the data values ​​within each cluster and the largest cluster are the areas prone to hidden dangers of this type. Then, the number of hidden dangers is compared with the mean to determine the prone month.

[0094] Preferably, when the number of hidden danger occurrences is associated with longitude and latitude and / or month, the k-means algorithm is used to obtain key hidden dangers and super key hidden danger prone areas, and / or the prone month is calculated by the mean comparison method; that is, when the number of hidden danger occurrences is associated with longitude and latitude, the k-means algorithm is used to obtain key hidden dangers and super key hidden danger prone areas; when the number of hidden danger occurrences is associated with month, the prone month is calculated by the mean comparison method.

[0095] The data used by the k-means algorithm and the mean comparison method are the weighted number of hidden dangers described in S33:

[0096] The data values ​​in each cluster after k-means clustering and the largest cluster are taken as the areas prone to this type of hidden dangers, and the months with the number of hidden dangers higher than the mean by more than 20% are taken as the months prone to this type of hidden dangers;

[0097] Specifically, the number of wildfires in February, March and May exceeded the average by more than 20%. Therefore, wildfire hazards are major hazards in the above months.

[0098] Repeat step S1 until all hidden dangers are traversed.

[0099] Example 2

[0100] This embodiment provides a system for implementing a method for predicting key hidden dangers based on visualization of power transmission channels:

[0101] at least one processor; and

[0102] A memory storing instructions, which, when executed by the at least one processor, enables the at least one processor to execute the above-mentioned method for predicting key hidden dangers based on visualization of power transmission channels.

[0103] In this embodiment, electronic devices include but are not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile computing devices, smart phones, tablet computers, cellular phones, personal digital assistants (PDAs), handheld devices, messaging devices, wearable computing devices, consumer electronic devices, etc.

[0104] Example 3

[0105] This embodiment also provides a computer-readable storage medium storing executable instructions, which, when executed, enable the machine to execute the above-mentioned method for predicting key hidden dangers based on visualization of power transmission channels.

[0106] Specifically, a system or device equipped with a readable storage medium can be provided, on which software program codes that implement the functions of any of the above-mentioned embodiments are stored, and a computer or processor of the system or device can read and execute instructions stored in the readable storage medium.

[0107] In this case, the program code itself read from the machine-readable medium can realize the function of any one of the above embodiments, and thus the machine-readable code and the machine-readable storage medium storing the machine-readable code constitute part of this specification.

[0108] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or a cloud via a communication network.

[0109] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0110] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the technical solution of the present invention, and are not intended to limit the specific implementation methods of the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the claims of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. A method for predicting key hidden dangers based on visualization of power transmission channels, characterized in that: The method comprises: S1. Obtain visual alarm data of transmission lines and pre-process all types of alarm data; S2, dividing the pre-processed data into regions according to longitude and latitude and setting regional weights; S3. Count the number of occurrences of various hidden dangers with the region as the horizontal axis and the 12 months as the vertical axis, and weight the number of hidden dangers to construct a two-dimensional matrix model in the time and space domain; S4. Perform chi-square test on the entire two-dimensional matrix, matrix rows, and matrix columns in the time-space domain, and classify the hidden dangers into super-key hidden dangers, key hidden dangers, and conventional hidden dangers based on the comparison between the calculated chi-square statistic and the critical value in the chi-square distribution table; S5. When the number of hidden danger occurrences is associated with longitude and latitude and / or month, the k-means algorithm is used to obtain the areas prone to major hidden dangers and super major hidden dangers, and / or the prone month is calculated by the mean comparison method.

2. The method for predicting key hidden dangers based on transmission channel visualization according to claim 1 is characterized in that: The S2 includes: S21: The longitude and latitude coordinates of the same type of hidden dangers are randomly divided into m areas (S1, S2, ..., S m ); S22: According to formula W i =1-(S i / S) calculates the weights of m regions (W1, W2, ..., W m ), where 1<=i<=m, S=S1+S2+…+S m .

3. The method for predicting key hidden dangers based on transmission channel visualization according to claim 2 is characterized in that: The constructing of a two-dimensional matrix in the spatiotemporal domain comprises: S31, with m regions as the horizontal axis (S1, S2, ..., S m ), with 12 months as the vertical axis (D1, D2, D3, ..., D 12 ), construct a two-dimensional matrix of size m×12; S32, traverse all types of hidden danger data, and count the hidden danger data that fall in (S i ,D j ) The number of times in the region (R 11 ,R 12 ,...,R ij ), where 1<=i<=m, 1<=j<=12; S33, weighting the number of hidden dangers in each area according to the weight in S22 to obtain (0 11 ,O 12 ,...,O ij ). Repeat step S21 until all types are traversed.

4. The method for predicting key hidden dangers based on transmission channel visualization according to claim 3 is characterized in that: The S4 specifically includes: S41. Construct an expected frequency table for the same type of hidden dangers, according to formula E ij =(R i ×C j ) / N is calculated in (S i ,D j ) in each region, where R i represents the sum of the i-th row, C j represents the sum of the jth column, and N represents the observation frequency; S42. Obtain the chi-square statistics of such hidden dangers based on month and longitude and latitude through chi-square test Calculate the degrees of freedom of the two-dimensional matrix in the time-space domain df = (m-1) × 11, and find the critical value T1 of the chi-square statistic of df at the significance level of 0.05 in the chi-square distribution table; like It is believed that the probability of occurrence of this type of hidden danger is related to both the month and longitude and latitude, which means that the probability of occurrence of this type of hidden danger is high in a specific month and longitude and latitude, and it is a super-key hidden danger; S43, if The chi-square statistic is calculated by weighting the number of hidden dangers based on month and longitude and latitude: Calculate (S i ,D j ) The expected frequency of hidden dangers in each month is E1=C j / 12, and then obtain the chi-square statistic Among them, O j =O 1j +O 2j +...+O mj , by finding the critical value T2 of the chi-square statistic with degrees of freedom df = 11 at a significance level of 0.05 in the chi-square distribution table, if at this time It is considered that the number of occurrences of this type of hidden danger is related to the monthly level and is a key hidden danger; Calculated in (S i ,D j ) i The expected frequency of hidden dangers in each area is E2=R i / m, and then obtain the chi-square statistic Among them, O i =O i1 +O i2 +...+O i12 , by finding the critical value T3 of the chi-square statistic at the significance level of 0.05 when df=m-1 in the chi-square distribution table, if at this time It is considered that the number of occurrences of this type of hidden danger is related to the longitude and latitude, and it is a key hidden danger; When neither of them is related, it is marked as a general hidden danger.

5. The method for predicting key hidden dangers based on visualization of power transmission channels according to claim 3 is characterized in that: The data used by the k-means algorithm and the mean comparison method are the weighted number of hidden dangers described in S33: After k-means clustering, the data values ​​within each cluster and the largest cluster are taken as areas prone to this type of hidden dangers, and the months with the number of hidden dangers higher than the mean by more than 20% are taken as months prone to this type of hidden dangers.

6. A key hidden danger prediction system based on transmission channel visualization, characterized in that: The device comprises: processor; a memory having stored thereon a computer program executable on the processor; Wherein, when the computer program is executed by the processor, the steps of a method for predicting key hidden dangers based on visualization of power transmission channels as described in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images