Heavy rainfall disaster influence assessment method and system

Abstract

The invention is suitable for the technical field of disaster assessment, and particularly relates to a heavy rainfall disaster influence assessment method and system, and the method comprises the steps: S100: delimiting a disaster influence assessment region of a power system, positioning the deployment position of power equipment, selecting video monitoring equipment at the deployment position, and determining the disaster influence assessment region of the power system; collecting audio data at the deployment position, extracting frequency characteristics, comparing with an existing data set and judging whether rainfall occurs or not by using audio collection equipment pre-integrated in the video monitoring equipment, and if so, recording rainfall time and creating a time window; and S200, collecting the video monitoring data at the deployment position through the video monitoring equipment. By generating the evaluation report, the risk point location in the electric power system can be visually displayed, the response speed and the decision-making efficiency are greatly improved, so that targeted measures are taken for prevention and control, the probability of occurrence of disasters of the electric power system is reduced, and efficient and stable operation of the electric power system is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster assessment, and in particular to a method and system for assessing the impact of a heavy rainfall disaster. Background Art

[0002] Heavy rainfall disaster impact assessment refers to the process of analyzing the damage to the power system in a certain area after heavy rainfall occurs.

[0003] In the existing technology, the above analysis process relies on post-event data and lacks real-time monitoring and dynamic evaluation capabilities. When heavy rainfall occurs, the power system may suffer sudden, localized and severe damage in a short period of time, such as line breakage, water ingress to equipment or power outage. In these cases, data collection and loss assessment can only be carried out after the disaster.

[0004] It is precisely because of the lack of technical means to monitor the intensity of rainfall and the degree of impact in real time that the power production department is unable to take effective preventive measures in time; therefore, "how to dynamically monitor power equipment in real time when heavy rainfall comes" is the technical problem that the present invention needs to solve. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for evaluating the impact of heavy rainfall disasters, so as to solve the problem of "how to dynamically monitor power equipment in real time when heavy rainfall occurs" raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for assessing the impact of heavy rainfall disasters, the method comprising:

[0008] S100: Delineate a disaster impact assessment area for the power system, locate the deployment location of the power equipment, select a video surveillance device at the deployment location, use an audio acquisition device pre-integrated in the video surveillance device to collect audio data at the deployment location, extract frequency features, compare with existing data sets, determine whether rainfall occurs, and if so, record the rainfall time and create a time window;

[0009] S200: collecting video surveillance data at the deployment location via the video surveillance device, and taking out a number of snapshots at preset time intervals, and calculating the number and strength of edge features in the snapshots using an edge detection algorithm, querying a preset two-dimensional comparison table, and traversing the edge value of each snapshot, wherein the two-dimensional comparison table consists of a quantity item, an intensity item, and an edge value item;

[0010] S300: With time as the horizontal coordinate and the edge value as the vertical coordinate, a change trend graph is drawn, the change rate of the edge value is calculated, the change rate is compared with a preset threshold, a heavy rainfall period is defined, and the duration is determined, the power equipment is clustered into several risk levels, wherein the risk levels include at least high, medium and low, and the power equipment corresponding to the high risk level is defined as a hidden danger equipment;

[0011] S400: defining the snapshot corresponding to the potential danger device as a target snapshot, comparing the target snapshots at adjacent time intervals, determining the change items, integrating the change items and the potential danger device, generating an assessment report, and sending the assessment report to a preset terminal.

[0012] Furthermore, the S100 includes:

[0013] Configuring the corresponding relationship between the deployment location, video surveillance data and audio data;

[0014] Based on the corresponding relationship, the control authority of the audio acquisition device is obtained, and a trigger rule is constructed.

[0015] Furthermore, the S100 further includes:

[0016] Acquire weather data of the disaster impact assessment area, determine the type of weather data, and configure a monitoring frequency corresponding to the type;

[0017] An initial moment is selected from the time window, and when the initial moment arrives, the video monitoring device and the audio acquisition device are adjusted using the monitoring frequency.

[0018] Further, the S200 includes:

[0019] Creating a recognition model, inputting the snapshot into the recognition model, and determining whether there are risk features;

[0020] If so, the attributes of the risk feature are traversed, and based on the attributes, a pre-built emergency response strategy is initiated.

[0021] Furthermore, the S200 further includes:

[0022] Generate a two-dimensional comparison table with the quantity items as rows, the intensity items as columns, and the edge value items as query results;

[0023] The serial number of the electric power equipment is obtained, and a mapping between the two-dimensional comparison table and the serial number is established.

[0024] Further, the S300 includes:

[0025] Sorting the snapshots in descending order of the change rate to generate a queue;

[0026] The queues are integrated to generate inspection routes, and the inspection routes are integrated into the evaluation report.

[0027] Furthermore, the S400 includes:

[0028] Traversing the influencing factors of the variable item, wherein the influencing factors at least include: wind speed and temperature;

[0029] The change item is marked in the inspection route via the hidden danger device.

[0030] Furthermore, the system comprises:

[0031] A creation module is used to delineate a disaster impact assessment area of ​​the power system, locate the deployment location of the power equipment, select the video surveillance equipment at the deployment location, use the audio acquisition equipment pre-integrated in the video surveillance equipment to collect audio data at the deployment location, extract frequency features, compare with existing data sets, determine whether rainfall occurs, and if so, record the rainfall time, and create a time window;

[0032] A traversal module, used to collect video surveillance data at the deployment location via the video surveillance device, and to intercept a number of snapshots at preset time intervals, and to calculate the number and strength of edge features in the snapshots using an edge detection algorithm, and to query a preset two-dimensional comparison table to traverse the edge value of each snapshot, wherein the two-dimensional comparison table consists of a quantity item, an intensity item, and an edge value item;

[0033] A definition module is used to draw a change trend graph with time as the horizontal coordinate and edge value as the vertical coordinate, calculate the change rate of the edge value, compare the change rate with a preset threshold, define the heavy rainfall period, and determine the duration, cluster the power equipment into several risk levels, wherein the risk levels include at least: high, medium and low, and define the power equipment corresponding to the high risk level as a hidden danger equipment;

[0034] The sending module is used to define the snapshot corresponding to the potential danger device as a target snapshot, compare the target snapshots at adjacent time intervals, determine the change items, integrate the change items and the potential danger device, generate an assessment report, and send the assessment report to a preset terminal.

[0035] Furthermore, the creation module includes:

[0036] A configuration unit, used to configure the corresponding relationship between the deployment position, the video surveillance data and the audio data;

[0037] A construction unit, used to obtain the control authority of the audio acquisition device based on the corresponding relationship and construct a trigger rule;

[0038] An acquisition unit, used to acquire weather data of the disaster impact assessment area, determine the type of weather data, and configure a monitoring frequency corresponding to the type;

[0039] The adjustment unit is used to select an initial moment from the time window, and when the initial moment arrives, use the monitoring frequency to adjust the video monitoring device and the audio acquisition device.

[0040] Furthermore, the traversal module includes:

[0041] A judgment unit, used for creating a recognition model, inputting the snapshot into the recognition model, judging whether there is a risk feature, and if so, traversing the attributes of the risk feature, and based on the attributes, starting a pre-built emergency response strategy;

[0042] A generating unit, used to generate a two-dimensional comparison table with the quantity items as rows, the intensity items as columns, and the edge value items as query results;

[0043] The mapping unit is used to obtain the serial number of the electric power equipment and establish a mapping between the two-dimensional comparison table and the serial number.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] By acquiring video surveillance data, power equipment can be monitored in real time, and data support can be provided for impact assessment. By collecting audio data, reliance on meteorological data can be reduced, the accuracy of assessment data can be improved, and early warning capabilities for disasters can be enhanced. By calculating edge values ​​and combining audio data, the start time of rainfall can be determined, which helps with early warning and emergency response. By determining edge values, rainfall intensity can be assessed in real time, greatly improving the timeliness of impact assessment, thereby providing decision support for preventive resource allocation. By generating assessment reports, risk points in the power system can be intuitively displayed, so that targeted measures can be taken in a timely manner for prevention and control, reducing the probability of disasters in the power system and ensuring efficient and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart of a heavy rainfall disaster impact assessment method provided by an embodiment of the present invention;

[0047] Figure 2 A first sub-flow chart of the heavy rainfall disaster impact assessment method provided by an embodiment of the present invention;

[0048] Figure 3A second sub-flow chart of the heavy rainfall disaster impact assessment method provided by an embodiment of the present invention;

[0049] Figure 4 A third sub-flow chart of the heavy rainfall disaster impact assessment method provided by an embodiment of the present invention;

[0050] Figure 5 A fourth sub-flow chart of the heavy rainfall disaster impact assessment method provided by an embodiment of the present invention;

[0051] Figure 6 A block diagram of a heavy rainfall disaster impact assessment system provided by an embodiment of the present invention;

[0052] Figure 7 A block diagram of the composition of a creation module in a heavy rainfall disaster impact assessment system provided by an embodiment of the present invention;

[0053] Figure 8 A block diagram of the composition of a traversal module in a heavy rainfall disaster impact assessment system provided in an embodiment of the present invention;

[0054] Fig. 9 A block diagram of the components of the definition module in the heavy rainfall disaster impact assessment system provided by an embodiment of the present invention;

[0055] Fig.10 This is a block diagram of the composition of the sending module in the heavy rainfall disaster impact assessment system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0057] In Example 1, Figure 1 The implementation process of the heavy rainfall disaster impact assessment method provided by the embodiment of the present invention is shown and described in detail below:

[0058] S100: Delineate the disaster impact assessment area of ​​the power system, locate the deployment location of the power equipment, select the video surveillance equipment at the deployment location, use the audio acquisition equipment pre-integrated in the video surveillance equipment to collect audio data at the deployment location, extract frequency features, compare with existing data sets, determine whether rainfall occurs, and if so, record the rainfall time and create a time window.

[0059] Determine the areas in the power system that require disaster impact assessment, draw a plan distribution map of the power equipment, where the power equipment includes substations, transmission lines, and distribution equipment; in the plan distribution map, mark the location and type of the power equipment and other data, find the video surveillance equipment at the power equipment, and collect video surveillance data, where the video surveillance equipment can be a surveillance camera specifically used to monitor power equipment, or it can be surveillance equipment of residents and businesses near the power equipment. However, when obtaining video surveillance data from residents and businesses, the corresponding usage permissions should be obtained, and the video surveillance equipment should also be pre-integrated with an audio acquisition device to obtain audio data at the power equipment.

[0060] Frequency features are extracted from audio data and compared with existing data sets to determine whether rainfall has occurred. In actual rainfall, raindrops hitting the ground or equipment surface will produce specific acoustic features. These features are usually manifested as fluctuations in a specific frequency range. By performing frequency analysis on the collected audio data, the characteristic spectrum of the raindrop impact sound is extracted and compared with the pre-built rainfall audio feature database to determine whether rainfall has occurred and estimate the rainfall amount. If the judgment result is that rainfall has occurred, the current moment is recorded and determined as the rainfall time. The time window is recorded, where the starting point of the time window is the rainfall time and the end point is the end time of the rainfall.

[0061] S200: Collect video surveillance data at the deployment location via the video surveillance device, and take out a number of snapshots at preset time intervals, and use an edge detection algorithm to calculate the number and intensity of edge features in the snapshots, query a preset two-dimensional comparison table, and traverse the edge value of each snapshot, wherein the two-dimensional comparison table consists of a quantity item, an intensity item, and an edge value item.

[0062] At preset time intervals, several snapshots are taken from the video surveillance data, and the edge detection algorithm is used to identify areas in the snapshots where the brightness changes significantly. Under rainfall conditions, the number and intensity of edge features will change significantly due to the blurring effect of raindrops. Therefore, the rainfall intensity can be determined by monitoring the number and intensity of edge features in the snapshots. In real life, as the rainfall intensity increases, the number of edge features in the snapshots will decrease, and the edge intensity will also weaken, which provides a quantitative basis for judging the rainfall intensity. Using the number and intensity of edge features, a two-dimensional comparison table is constructed, in which the number of edge features is the row and the intensity of edge features is the column, and the edge value is written to the intersection of the row and the column.

[0063] S300: With time as the horizontal axis and edge value as the vertical axis, draw a change trend graph, calculate the change rate of the edge value, compare the change rate with the preset threshold, define the heavy rainfall period, and determine the duration, cluster the power equipment into several risk levels, where the risk levels include at least: high, medium and low, and define the power equipment corresponding to the high risk level as hidden danger equipment.

[0064] With time as the horizontal axis and the edge value of the power equipment as the vertical axis, a change trend graph is drawn, in which each power equipment corresponds to a change trend graph; in the change trend graph, a number of points are selected according to the preset step size, and the slope of two adjacent points is calculated and determined as the change rate; in the change trend graph, the time period in which the change rate is greater than the preset threshold is determined as the heavy rainfall period, and the duration of the heavy rainfall is determined according to the two endpoint values ​​of the heavy rainfall period.

[0065] Based on the geographical location, waterproof level and real-time monitoring data of the power equipment (such as equipment temperature, current, and voltage changes), the risk level of each power equipment is determined, and the power equipment is divided into three risk levels: high, medium, and low. The power equipment corresponding to the high risk level is defined as hidden danger equipment; in addition, different maintenance strategies should be set for different risk levels. For example, hidden danger equipment should be monitored and emergency measures should be formulated as a priority, while power equipment corresponding to the low risk level should be included in the scope of routine maintenance.

[0066] S400: defining the snapshot corresponding to the potential danger device as a target snapshot, comparing the target snapshots at adjacent time intervals, determining the change items, integrating the change items and the potential danger device, generating an assessment report, and sending the assessment report to a preset terminal.

[0067] Find the snapshot corresponding to the hidden danger equipment and define it as the target snapshot. Store the target snapshot in chronological order, compare two adjacent target snapshots, determine the changed area, and define it as the change item. The change item can determine whether the power equipment has changed during heavy rainfall, where the change item may be collapsed equipment or waterlogged area, etc. Fill the change item and the hidden danger equipment into the template pre-prepared by the power equipment maintenance personnel, generate an assessment report, and send the assessment report to the preset terminal, where the preset terminal is the power equipment maintenance personnel terminal.

[0068] In Example 2, Figure 2 The implementation process of the heavy rainfall disaster impact assessment method provided by the embodiment of the present invention is shown, and S100 is described in detail below:

[0069] S101: configuring the corresponding relationship between the deployment position, video surveillance data and audio data.

[0070] Each power equipment corresponds to at least one video surveillance device and one audio acquisition device, and a corresponding relationship is established between the deployment location, video surveillance data and audio data.

[0071] In this embodiment, by constructing a corresponding relationship, the hidden danger equipment and the snapshots and audio data corresponding to the hidden danger equipment can be quickly located, so as to monitor the hidden danger equipment in real time and provide data support for the disaster impact assessment of the hidden danger equipment.

[0072] S102: Based on the corresponding relationship, the control authority of the audio acquisition device is obtained, and a trigger rule is constructed.

[0073] Obtain control authority for the audio acquisition device and construct trigger rules; the trigger rules are: when the change rate of the edge value calculated through the snapshot is greater than the preset setting value, start the audio acquisition device; the change rate of the edge value greater than the preset setting value means that it is raining in the disaster impact assessment area at the current moment.

[0074] In Example 3, Figure 2 The implementation process of the heavy rainfall disaster impact assessment method provided by the embodiment of the present invention is shown, and S100 is further described in detail below, as follows:

[0075] S103: Acquire weather data of the disaster impact assessment area, determine the type of weather data, and configure a monitoring frequency corresponding to the type.

[0076] The weather data of the disaster impact assessment area is read from the public meteorological data to determine the type of weather data, where the type is sunny, cloudy, light rain, moderate rain and heavy rain, etc. Under different types, different monitoring frequencies are configured for video surveillance equipment and audio acquisition equipment, where the correspondence between the type and the monitoring frequency is stored in a pre-built query table.

[0077] S104: Selecting an initial moment from the time window, and adjusting the video surveillance device and the audio acquisition device using the monitoring frequency when the initial moment arrives.

[0078] When the time window arrives, it means it has started to rain, and the monitoring frequency of the video surveillance equipment and audio acquisition equipment is adjusted at this time.

[0079] In Example 4, Figure 3 The implementation process of the heavy rainfall disaster impact assessment method provided by the embodiment of the present invention is shown, and S200 is described in detail below, as follows:

[0080] S201: Create an identification model, input the snapshot into the identification model, determine whether there is a risk feature, and if so, traverse the attributes of the risk feature, and based on the attributes, initiate a pre-built emergency response strategy.

[0081] Based on the deep learning algorithm, a recognition model is created and trained using risk scenarios in existing data, so that the recognition model can accurately identify risk features in the snapshot, where risk features may be fallen cables, trees, lightning, accumulated water, etc.

[0082] If there are risk features in the snapshot, the attributes of the risk features are determined, which may be natural factors, environmental factors, or operating status, etc. Based on the attributes, a pre-built emergency response strategy is initiated, where the emergency response strategy may be to increase the frequency of electronic inspections and to start backup lines, etc.

[0083] In Example 5, Figure 3 The implementation process of the heavy rainfall disaster impact assessment method provided by the embodiment of the present invention is shown, and S200 is further described in detail below, as follows:

[0084] S202: Generate a two-dimensional comparison table with the quantity items as rows, the intensity items as columns, and the edge value items as query results.

[0085] S203: Obtain the serial number of the electric power equipment, and establish a mapping between the two-dimensional comparison table and the serial number.

[0086] A two-dimensional comparison table is created for each power equipment, where the two-dimensional comparison table is mainly used to quantify the rainfall and determine the risk level based on the duration of rainfall. However, weights can be added to the two-dimensional comparison table for key equipment in the power system. In other words, if the rainfall at the key equipment is less than that at the non-key equipment, the key equipment can be defined as a high-risk level and the non-key equipment as a low-risk level by weighting the rainfall. The advantage of this is that higher attention can be paid to key equipment and key monitoring can be performed.

[0087] In Example 6, Figure 4 The implementation process of the heavy rainfall disaster impact assessment method provided by the embodiment of the present invention is shown, and S300 is further described in detail below, as follows:

[0088] S301: Sort the snapshots in descending order of the change rate to generate a queue.

[0089] Sort all snapshots in descending order of change rate.

[0090] S302: Integrate the queues, generate inspection routes, and integrate the inspection routes into an evaluation report.

[0091] According to the existing inspection resources, the snapshots that need to be inspected are selected from the front of the queue, and the inspection routes are integrated and generated according to the corresponding deployment locations. The inspection routes are integrated into the evaluation report and sent to the terminal of the power equipment maintenance personnel.

[0092] In Example 7, Figure 5 The implementation process of the heavy rainfall disaster impact assessment method provided by the embodiment of the present invention is shown, and S400 is further described in detail below, as follows:

[0093] S401: Traverse the influencing factors of the variable item, wherein the influencing factors at least include: wind speed and temperature.

[0094] After traversing the variable items, determine the possible causes of the variable items, that is, the influencing factors.

[0095] S402: Mark the change item into the inspection route via the hidden danger device.

[0096] Mark the changed items in the inspection route and inspect them first.

[0097] Figure 6 The structure diagram of the heavy rainfall disaster impact assessment system provided by an embodiment of the present invention is shown. The heavy rainfall disaster impact assessment system 1 includes:

[0098] Creating module 11, used to delineate the disaster impact assessment area of ​​the power system, locate the deployment location of the power equipment, select the video surveillance equipment at the deployment location, use the audio equipment pre-integrated in the video surveillance equipment to collect audio data at the deployment location, extract frequency features, compare with existing data sets, determine whether rainfall occurs, if so, record the rainfall time, and create a time window;

[0099] A traversal module 12 is used to collect video surveillance data at the deployment location via the video surveillance device, and to capture a number of snapshots at preset time intervals, and to calculate the number and strength of edge features in the snapshots using an edge detection algorithm, and to query a preset two-dimensional comparison table to traverse the edge value of each snapshot, wherein the two-dimensional comparison table is composed of a quantity item, an intensity item, and an edge value item;

[0100] The definition module 13 is used to draw a change trend diagram with time as the horizontal coordinate and the edge value as the vertical coordinate, calculate the change rate of the edge value, compare the change rate with a preset threshold, define the heavy rainfall period, and determine the duration, cluster the power equipment into several risk levels, wherein the risk levels include at least: high, medium and low, and define the power equipment corresponding to the high risk level as a hidden danger equipment;

[0101] The sending module 14 is used to define the snapshot corresponding to the potential danger device as a target snapshot, compare the target snapshots at adjacent time intervals, determine the change items, integrate the change items and the potential danger device, generate an assessment report, and send the assessment report to a preset terminal.

[0102] Figure 7 The structural block diagram of the heavy rainfall disaster impact assessment system provided by the embodiment of the present invention is shown, and the creation module 11 includes:

[0103] A configuration unit 111, configured to configure a correspondence between the deployment location, the video surveillance data, and the audio data;

[0104] A construction unit 112, configured to obtain the control authority of the audio device based on the corresponding relationship and construct a trigger rule;

[0105] An acquisition unit 113 is used to acquire weather data of the disaster impact assessment area, determine the type of weather data, and configure a monitoring frequency corresponding to the type;

[0106] The adjustment unit 114 is used to select an initial moment from the time window, and when the initial moment arrives, adjust the video surveillance device and the audio device using the monitoring frequency.

[0107] Figure 8 The structural block diagram of the heavy rainfall disaster impact assessment system provided by the embodiment of the present invention is shown, and the traversal module 12 includes:

[0108] A judgment unit 121 is used to create a recognition model, input the snapshot into the recognition model, judge whether there is a risk feature, and if so, traverse the attributes of the risk feature, and based on the attributes, start a pre-built emergency response strategy;

[0109] A generating unit 122, configured to generate a two-dimensional comparison table with the quantity items as rows, the intensity items as columns, and the edge value items as query results;

[0110] The mapping unit 123 is used to obtain the serial number of the power equipment and establish a mapping between the two-dimensional comparison table and the serial number.

[0111] Fig. 9 The structural block diagram of the heavy rainfall disaster impact assessment system provided by the embodiment of the present invention is shown, and the definition module 13 includes:

[0112] A sorting unit 131, configured to sort the snapshots in descending order of the change rate, and adjust the sorting result by using the edge value to generate a queue;

[0113] The integration unit 132 is used to generate an inspection route according to the queue and integrate the inspection route into the evaluation report.

[0114] Fig.10 The structure diagram of the heavy rainfall disaster impact assessment system provided by the embodiment of the present invention is shown, and the sending module 14 includes:

[0115] A correction unit 141, configured to traverse the influencing factors of the variable item, wherein the influencing factors at least include: wind speed and temperature, and correct the variable item;

[0116] The marking unit 142 is used to mark the change item into the inspection route via the hidden danger device.

[0117] The creation module 11 is mainly used to complete step S100, the traversal module 12 is mainly used to complete step S200, the definition module 13 is mainly used to complete step S300, and the sending module 14 is mainly used to complete step S400;

[0118] The configuration unit 111 is mainly used to complete step S101, the construction unit 112 is mainly used to complete step S102, the acquisition unit 113 is mainly used to complete step S103, and the adjustment unit 114 is mainly used to complete step S104;

[0119] The judging unit 121 is mainly used to complete step S201, the generating unit 122 is mainly used to complete step S202, and the mapping unit 123 is mainly used to complete step S203;

[0120] The sorting unit 131 is mainly used to complete step S301, and the integration unit 132 is mainly used to complete step S302;

[0121] The correction unit 141 is mainly used to complete step S401, and the marking unit 142 is mainly used to complete step S402.

[0122] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0123] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0124] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for assessing the impact of heavy rainfall disasters, characterized in that: The method comprises: S100: Delineate a disaster impact assessment area for the power system, locate the deployment location of the power equipment, select a video surveillance device at the deployment location, use an audio acquisition device pre-integrated in the video surveillance device to collect audio data at the deployment location, extract frequency features, compare with existing data sets, determine whether rainfall occurs, and if so, record the rainfall time and create a time window; S200: collecting video surveillance data at the deployment location via the video surveillance device, and taking out a number of snapshots at preset time intervals, and calculating the number and strength of edge features in the snapshots using an edge detection algorithm, querying a preset two-dimensional comparison table, and traversing the edge value of each snapshot, wherein the two-dimensional comparison table consists of a quantity item, an intensity item, and an edge value item; S300: With time as the horizontal coordinate and the edge value as the vertical coordinate, a change trend graph is drawn, the change rate of the edge value is calculated, the change rate is compared with a preset threshold, a heavy rainfall period is defined, and the duration is determined, the power equipment is clustered into several risk levels, wherein the risk levels include at least high, medium and low, and the power equipment corresponding to the high risk level is defined as a hidden danger equipment; S400: defining the snapshot corresponding to the potential danger device as a target snapshot, comparing the target snapshots at adjacent time intervals, determining the change items, integrating the change items and the potential danger device, generating an assessment report, and sending the assessment report to a preset terminal.

2. The heavy rainfall disaster impact assessment method according to claim 1, characterized in that: The S100 includes: Configuring the corresponding relationship between the deployment location, video surveillance data and audio data; Based on the corresponding relationship, the control authority of the audio acquisition device is obtained, and a trigger rule is constructed.

3. The heavy rainfall disaster impact assessment method according to claim 1, characterized in that: The S100 further includes: Acquire weather data of the disaster impact assessment area, determine the type of weather data, and configure a monitoring frequency corresponding to the type; An initial moment is selected from the time window, and when the initial moment arrives, the video monitoring device and the audio acquisition device are adjusted using the monitoring frequency.

4. The heavy rainfall disaster impact assessment method according to claim 1, characterized in that: The S200 includes: Creating a recognition model, inputting the snapshot into the recognition model, and determining whether there are risk features; If so, the attributes of the risk feature are traversed, and based on the attributes, a pre-built emergency response strategy is initiated.

5. The heavy rainfall disaster impact assessment method according to claim 1, characterized in that: The S200 further includes: Generate a two-dimensional comparison table with the quantity items as rows, the intensity items as columns, and the edge value items as query results; The serial number of the electric power equipment is obtained, and a mapping between the two-dimensional comparison table and the serial number is established.

6. The heavy rainfall disaster impact assessment method according to claim 1, characterized in that: The S300 includes: Sorting the snapshots in descending order of the change rate to generate a queue; The queues are integrated to generate inspection routes, and the inspection routes are integrated into the evaluation report.

7. The heavy rainfall disaster impact assessment method according to claim 1, characterized in that: The S400 includes: Traversing the influencing factors of the variable item, wherein the influencing factors at least include: wind speed and temperature; The change item is marked in the inspection route via the hidden danger device.

8. A heavy rainfall disaster impact assessment system, characterized in that: The system comprises: A creation module is used to delineate a disaster impact assessment area of ​​the power system, locate the deployment location of the power equipment, select the video surveillance equipment at the deployment location, use the audio acquisition equipment pre-integrated in the video surveillance equipment to collect audio data at the deployment location, extract frequency features, compare with existing data sets, determine whether rainfall occurs, and if so, record the rainfall time, and create a time window; A traversal module, used to collect video surveillance data at the deployment location via the video surveillance device, and to intercept a number of snapshots at preset time intervals, and to calculate the number and strength of edge features in the snapshots using an edge detection algorithm, and to query a preset two-dimensional comparison table to traverse the edge value of each snapshot, wherein the two-dimensional comparison table consists of a quantity item, an intensity item, and an edge value item; A definition module is used to draw a change trend graph with time as the horizontal coordinate and edge value as the vertical coordinate, calculate the change rate of the edge value, compare the change rate with a preset threshold, define the heavy rainfall period, and determine the duration, cluster the power equipment into several risk levels, wherein the risk levels include at least: high, medium and low, and define the power equipment corresponding to the high risk level as a hidden danger equipment; The sending module is used to define the snapshot corresponding to the potential danger device as a target snapshot, compare the target snapshots at adjacent time intervals, determine the change items, integrate the change items and the potential danger device, generate an assessment report, and send the assessment report to a preset terminal.

9. The heavy rainfall disaster impact assessment system according to claim 8, characterized in that: The creation module includes: A configuration unit, used to configure the corresponding relationship between the deployment position, the video surveillance data and the audio data; A construction unit, used to obtain the control authority of the audio acquisition device based on the corresponding relationship and construct a trigger rule; An acquisition unit, used to acquire weather data of the disaster impact assessment area, determine the type of weather data, and configure a monitoring frequency corresponding to the type; The adjustment unit is used to select an initial moment from the time window, and when the initial moment arrives, use the monitoring frequency to adjust the video monitoring device and the audio acquisition device.

10. The heavy rainfall disaster impact assessment system according to claim 8, characterized in that: The traversal module includes: A judgment unit, used for creating a recognition model, inputting the snapshot into the recognition model, judging whether there is a risk feature, and if so, traversing the attributes of the risk feature, and based on the attributes, starting a pre-built emergency response strategy; A generating unit, used to generate a two-dimensional comparison table with the quantity items as rows, the intensity items as columns, and the edge value items as query results; The mapping unit is used to obtain the serial number of the electric power equipment and establish a mapping between the two-dimensional comparison table and the serial number.

Images