Power transmission risk early warning method and device, equipment and medium

Abstract

The application relates to the technical field of artificial intelligence, and discloses a power transmission risk early warning method, device, equipment and medium, wherein the method comprises the following steps: an initial image is an image photographed by a monitoring device based on a first focal length configuration for a suspected forest fire point; a temperature difference between a first highest temperature and a first ambient temperature is calculated according to the initial image, and the temperature difference is taken as a first temperature difference; if the first temperature difference is greater than a first threshold value or the first highest temperature is greater than a second threshold value, the monitoring device is controlled to photograph the suspected forest fire point according to a preset time configuration, and a first image set is obtained; whether the suspected forest fire point is a fire point is judged according to the first image set, and a judgment result is obtained; if the judgment result is yes, a forest fire risk level of a fire source point corresponding to the first highest temperature or the first temperature difference is determined according to the first image set, a first level is obtained, and first power transmission risk early warning information is sent according to the first level and a preset sending configuration. The accuracy of power transmission risk early warning based on image recognition technology is improved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for early warning of power transmission risks. Background Technology

[0002] Wildfires are one of the adverse factors affecting the normal operation of power transmission lines. To mitigate the impact of wildfires on power transmission lines, manual inspections, aerial patrols, satellite remote sensing, and video surveillance are the main methods of wildfire monitoring. Manual inspections require significant investment of manpower, resources, and funds, and are inefficient. Aerial patrols, in addition to their high investment of manpower, resources, and funds, cannot achieve real-time, all-weather monitoring. Satellite remote sensing provides thermal infrared images with insufficient resolution and long scanning cycles. While video surveillance can address these issues, current image recognition technology is not accurate enough, resulting in numerous false alarms and missed alarms, leading to low accuracy in wildfire early warning systems. Summary of the Invention

[0003] Based on this, it is necessary to address the technical problem that the accuracy of image recognition technology is not high enough when using video monitoring of wildfires, resulting in a large number of false alarms and missed alarms, which leads to low accuracy of wildfire early warning. Therefore, a method, device, equipment and medium for power transmission risk early warning are proposed.

[0004] Firstly, a method for early warning of power transmission risks is provided, the method comprising:

[0005] Acquire an initial image, which is an image taken by the monitoring device based on a first focal length configuration of the suspected wildfire point;

[0006] The temperature difference between the first maximum temperature and the first ambient temperature is calculated based on the initial image and is taken as the first temperature difference;

[0007] If the first temperature difference is greater than the first threshold, or if the first highest temperature is greater than the second threshold, then according to the preset time configuration, the monitoring device is controlled to take pictures of the suspected wildfire point to obtain the first image set;

[0008] Based on the first image set, determine whether the suspected wildfire spot is a fire spot, and obtain the determination result;

[0009] If the judgment result is yes, then the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference is determined according to the first image set to obtain the first level, and the first power transmission risk warning information is sent according to the first level and the preset transmission configuration.

[0010] Furthermore, the step of determining whether a suspected wildfire spot is a fire spot based on the first image set and obtaining the determination result includes:

[0011] Based on the first image set, a temperature-time curve is generated for the fire source point corresponding to the first highest temperature.

[0012] If the slope of the temperature-time curve satisfies the first condition, then the judgment result is determined to be yes;

[0013] If the slope of the temperature-time curve does not meet the first condition, then the judgment result is determined to be negative.

[0014] Further, the step of determining the wildfire risk level of the fire source corresponding to the first highest temperature or first temperature difference based on the first image set, and obtaining the first level, includes:

[0015] The temperature rise rate is calculated based on the temperature-time curve to obtain the first rate.

[0016] The minimum distance between the fire source corresponding to the first highest temperature or the first temperature difference and the nearest transmission line tower is obtained as the danger distance;

[0017] Based on the first rate and the danger distance, the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference is determined, and the first level is obtained.

[0018] Further, after the step of calculating the temperature difference between the first maximum temperature and the first ambient temperature based on the initial image as the first temperature difference, the method further includes:

[0019] If the first temperature difference is less than or equal to the first threshold, or if the first highest temperature is less than or equal to the second threshold, then according to the second focal length configuration, the monitoring device is controlled to take pictures of the suspected wildfire point to obtain a target image, and the shooting range of the target image is greater than the shooting range of the initial image.

[0020] The second temperature difference is obtained by calculating the temperature difference between the second highest temperature and the second ambient temperature based on the target image;

[0021] If the second temperature difference is greater than the third threshold, then the fire source point corresponding to the second highest temperature corresponding to the second temperature difference that is greater than the third threshold is taken as the target fire source point, and the minimum distance between the target fire source point and the nearest transmission line tower is calculated to obtain the first distance;

[0022] The temperature rise rate of the target fire source point is calculated based on each of the target images to obtain the second rate;

[0023] Based on the first distance and the second rate, the wildfire risk level is determined to obtain the second level. Based on the second level and the preset transmission configuration, the first power transmission risk warning information is sent.

[0024] Furthermore, prior to the step of acquiring the initial image, the following steps are also included:

[0025] Obtain the monitoring data from the monitoring device;

[0026] The monitoring data is input into a pre-trained wildfire classification model for classification and prediction to obtain the first prediction result;

[0027] If the first prediction result indicates a suspected wildfire, the suspected wildfire point is determined based on the image in the monitoring data. Based on the first focal length configuration, the monitoring device is controlled to capture images of the suspected wildfire point to obtain the initial image.

[0028] Further, after the step of acquiring the monitoring data of the monitoring device, the following steps are included:

[0029] The monitoring data is input into a pre-trained external force damage classification model for classification and prediction to obtain a second prediction result.

[0030] If the second prediction result indicates suspected external force damage, the image from the monitoring data is input into a pre-trained target segmentation model to segment the external force damage points and obtain the suspected external force damage points.

[0031] Obtain a second distance and a third distance, where the second distance is the minimum distance between the suspected external force damage point and the transmission line, and the third distance is the minimum distance between the suspected external force damage point and the transmission line tower.

[0032] If the second distance is greater than the fourth threshold and each of the third distances is greater than the fifth threshold, then the suspected external force damage point is determined to be a non-external force damage point.

[0033] If the second distance is less than or equal to the fourth threshold, or if any of the third distances is less than or equal to the fifth threshold, then the suspected external force damage point is determined as the external force damage point to be analyzed.

[0034] Obtain the direction of motion of the external force failure point to be analyzed, and determine whether the direction of motion, the second distance, and the third distance corresponding to the external force failure point to be analyzed satisfy the second condition;

[0035] If satisfied, calculate the distance reduction rate for the second distance corresponding to the point of external force damage to be analyzed, and obtain the third rate. Calculate the distance reduction rate for the third distance corresponding to the point of external force damage to be analyzed, and obtain the fourth rate. Determine the external force damage risk level based on the third rate and the fourth rate, and obtain the third level. Send the second power transmission risk warning information based on the third level and the preset transmission configuration.

[0036] Furthermore, the second condition is that the second distance decreases, the third distance decreases, and the direction of movement intersects with the transmission line.

[0037] Secondly, a power transmission risk early warning device is provided, the device comprising:

[0038] The data acquisition module is used to acquire an initial image, which is an image taken by the monitoring device based on a first focal length configuration of the suspected wildfire point;

[0039] The temperature difference calculation module is used to calculate the temperature difference between the first maximum temperature and the first ambient temperature based on the initial image, as the first temperature difference;

[0040] The first image set determination module is used to control the monitoring device to take pictures of the suspected wildfire point according to a preset time configuration if the first temperature difference is greater than the first threshold, or if the first highest temperature is greater than the second threshold, thereby obtaining the first image set.

[0041] The judgment result determination module is used to determine whether a suspected wildfire point is a fire point based on the first image set, and obtain the judgment result.

[0042] The first early warning module is used to determine the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference based on the first image set if the judgment result is yes, obtain the first level, and send the first power transmission risk early warning information according to the first level and the preset transmission configuration.

[0043] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described power transmission risk warning method.

[0044] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described power transmission risk warning method.

[0045] The power transmission risk early warning method, apparatus, equipment, and medium of this application improve the accuracy of power transmission risk early warning based on image recognition technology by acquiring an initial image, which is an image taken by a monitoring device based on a first focal length configuration of a suspected wildfire point. The initial image is used to calculate the temperature difference between a first maximum temperature and a first ambient temperature, which is taken as a first temperature difference. If the first temperature difference is greater than a first threshold, or if the first maximum temperature is greater than a second threshold, the monitoring device is controlled to take pictures of the suspected wildfire point according to a preset time configuration, resulting in a first image set. The first image set is used to determine whether the suspected wildfire point is a fire point, and a judgment result is obtained. If the judgment result is yes, the wildfire risk level of the fire source corresponding to the first maximum temperature or the first temperature difference is determined based on the first image set, resulting in a first level. Based on the first level and a preset transmission configuration, a first power transmission risk early warning information is sent. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] in:

[0048] Figure 1 Here is a flowchart of a power transmission risk early warning method in one embodiment;

[0049] Figure 2 Here is another flowchart of the power transmission risk early warning method in one embodiment;

[0050] Figure 3 This is a structural block diagram of a power transmission risk early warning device in one embodiment;

[0051] Figure 4 This is a structural block diagram of a computer device in one embodiment. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] Please see Figure 1 As shown, Figure 1A flowchart illustrating the power transmission risk early warning method provided in this embodiment of the invention includes the following steps:

[0054] S1: Acquire an initial image, which is an image taken by the monitoring device based on a first focal length configuration of the suspected wildfire point;

[0055] Specifically, it can obtain initial images sent by monitoring equipment, initial images from preset storage space, or initial images from third-party applications.

[0056] The initial image is a digital image.

[0057] Surveillance equipment includes cameras.

[0058] Optionally, the monitoring equipment, based on the first focal length configuration, captures video of suspected wildfire sites and extracts image frames from the video as initial images at preset time intervals.

[0059] Optionally, the monitoring equipment, based on a first focal length configuration, takes images of suspected wildfire sites at preset time intervals, and uses the captured images as initial images.

[0060] S2: Calculate the temperature difference between the first maximum temperature and the first ambient temperature based on the initial image, and use it as the first temperature difference;

[0061] Specifically, temperature is identified for each pixel in the initial image, the highest identified temperature is taken as the first highest temperature, the lowest identified temperature is taken as the first ambient temperature, and the first highest temperature is subtracted from the first ambient temperature to obtain the first temperature difference.

[0062] S3: If the first temperature difference is greater than the first threshold, or the first highest temperature is greater than the second threshold, then according to the preset time configuration, control the monitoring device to take pictures of the suspected wildfire point to obtain the first image set;

[0063] Optionally, the interval length of the preset time configuration is shorter than the interval length of the preset time interval.

[0064] Specifically, if the first temperature difference is greater than the first threshold, or the first highest temperature is greater than the second threshold, it means that the suspected wildfire point is likely to be a fire point and further analysis is needed. Therefore, according to the preset time configuration, the monitoring device is controlled to take pictures of the suspected wildfire point and the pictures are used as the first image set. Alternatively, the monitoring device is controlled to take videos of the suspected wildfire point and the pictures are extracted from the videos according to the preset time configuration. All the extracted pictures are used as the first image set.

[0065] S4: Determine whether the suspected wildfire point is a fire point based on the first image set, and obtain the determination result;

[0066] Specifically, the temperature of each image in the first image set is calculated for suspected wildfire points. Based on each temperature, it is determined whether the temperature of the suspected wildfire point is continuously rising. If the temperature of the suspected wildfire point is continuously rising, it means that the suspected wildfire point is a fire point, and the determination result is yes. If the temperature of the suspected wildfire point is not continuously rising, it means that the suspected wildfire point is not a fire point, and the determination result is no.

[0067] Because wildfires can shift, the total area of ​​suspected wildfire sites across all images in the first image set is smaller than a preset area. In other words, the location of suspected wildfire sites within the images of the first image set may change.

[0068] S5: If the judgment result is yes, then determine the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference based on the first image set, obtain the first level, and send the first power transmission risk warning information according to the first level and the preset transmission configuration.

[0069] Specifically, if the judgment result is yes, it means that the suspected wildfire point is a fire point and an early warning needs to be issued. The temperature index of the suspected wildfire point is calculated based on the first image set. Based on the calculated data, the wildfire risk level of the fire source point corresponding to the first highest temperature or the first temperature difference is determined by a lookup table method. The determined wildfire risk level is taken as the first level. The sub-configuration corresponding to the first level is determined from the preset transmission configuration, and the first power transmission risk early warning information is generated based on the sub-configuration.

[0070] This embodiment acquires an initial image, which is an image taken by a monitoring device based on a first focal length configuration of a suspected wildfire point. Based on the initial image, the temperature difference between a first maximum temperature and a first ambient temperature is calculated as the first temperature difference. If the first temperature difference is greater than a first threshold, or if the first maximum temperature is greater than a second threshold, then according to a preset time configuration, the monitoring device is controlled to take pictures of the suspected wildfire point, obtaining a first image set. Based on the first image set, it is determined whether the suspected wildfire point is a fire point, obtaining a judgment result. If the judgment result is yes, then based on the first image set, the wildfire risk level of the fire source point corresponding to the first maximum temperature or the first temperature difference is determined, obtaining a first level. Based on the first level and a preset transmission configuration, a first power transmission risk warning information is sent, thereby improving the accuracy of power transmission risk warning based on image recognition technology.

[0071] In one embodiment, the step of determining whether a suspected wildfire spot is a fire spot based on the first image set and obtaining a determination result includes:

[0072] S41: Generate a temperature-time curve for the fire source point corresponding to the first highest temperature based on the first image set;

[0073] Specifically, based on the first image set, the temperature of the fire source corresponding to the first highest temperature is calculated, and a temperature-time curve is generated based on the calculated temperature (as the y-axis coordinate) and the image capture time (as the x-axis coordinate).

[0074] The rate of temperature rise, which is the slope of the temperature-time curve.

[0075] S42: If the slope of the temperature-time curve satisfies the first condition, then the judgment result is determined to be yes;

[0076] The first condition is the slope range.

[0077] Specifically, if the slope of the temperature-time curve is within the slope range of the first condition, then the judgment result is determined to be yes.

[0078] S43: If the slope of the temperature-time curve does not meet the first condition, then the judgment result is determined to be no.

[0079] Specifically, if the slope of the temperature-time curve is not within the slope range of the first condition, then the judgment result is determined to be negative.

[0080] This embodiment accurately determines the judgment result by comparing the slope of the temperature-time curve of the fire source point corresponding to the first highest temperature with the first condition, thus providing a foundation for improving the accuracy of power transmission risk early warning based on image recognition technology.

[0081] In one embodiment, the step of determining the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference based on the first image set, and obtaining the first level, includes:

[0082] S51: Calculate the temperature rise rate based on the temperature-time curve to obtain the first rate;

[0083] Specifically, the temperature rise rate (i.e., the heating rate) is calculated based on the temperature-time curve of the fire source point corresponding to the first highest temperature, and the calculated data is used as the first rate.

[0084] S52: Obtain the minimum distance between the fire source point corresponding to the first highest temperature or the first temperature difference and the nearest transmission line tower, as the danger distance;

[0085] Specifically, the distance between the fire source point corresponding to the first highest temperature or the first temperature difference and each tower within a preset range is calculated. The transmission line corresponding to the minimum calculated distance is the nearest transmission line, and the minimum calculated distance is taken as the minimum distance and the danger distance.

[0086] S53: Determine the wildfire risk level of the fire source corresponding to the first highest temperature or first temperature difference based on the first rate and the danger distance, and obtain the first level.

[0087] Specifically, based on the first rate and the danger distance, a lookup table method is used to determine the wildfire risk level of the fire source corresponding to the first highest temperature, and the determined wildfire risk level is taken as the first level.

[0088] This embodiment determines the wildfire risk level of the fire source corresponding to the first highest temperature by measuring the rate of temperature rise, thus accurately determining the wildfire risk level and improving the accuracy of power transmission risk early warning based on image recognition technology.

[0089] In one embodiment, after the step of calculating the temperature difference between the first maximum temperature and the first ambient temperature based on the initial image as the first temperature difference, the method further includes:

[0090] S61: If the first temperature difference is less than or equal to the first threshold, or the first highest temperature is less than or equal to the second threshold, then according to the second focal length configuration, the monitoring device is controlled to take pictures of the suspected wildfire point to obtain a target image, and the shooting range of the target image is greater than the shooting range of the initial image.

[0091] Specifically, if the first temperature difference is less than or equal to the first threshold, or if the first highest temperature is less than or equal to the second threshold, it means that the possibility of the suspected wildfire point being a fire point is generally low. In order to improve accuracy, further analysis is needed. According to the second focal length configuration, the monitoring equipment is controlled to take pictures of the suspected wildfire point, and each picture taken is taken as a target image.

[0092] S62: Calculate the temperature difference between the second highest temperature and the second ambient temperature based on the target image to obtain the second temperature difference;

[0093] Specifically, temperature is identified for each pixel in the target image, the highest identified temperature is taken as the second highest temperature, the lowest identified temperature is taken as the second ambient temperature, and the second highest temperature is subtracted from the second ambient temperature to obtain the second temperature difference.

[0094] S63: If the second temperature difference is greater than the third threshold, then the fire source point corresponding to the second highest temperature corresponding to the second temperature difference that is greater than the third threshold is taken as the target fire source point, and the minimum distance between the target fire source point and the nearest transmission line tower is calculated to obtain the first distance;

[0095] Specifically, if the second temperature difference is greater than the third threshold, it means that the suspected wildfire point is a fire point. The fire point corresponding to the second highest temperature of the second temperature difference greater than the third threshold will affect the normal operation of the transmission line. Therefore, the fire point corresponding to the second highest temperature of the second temperature difference greater than the third threshold will be taken as the target fire point.

[0096] The minimum distance between the target fire source and the nearest transmission line tower is calculated, thereby identifying the transmission line tower that the target fire source is most likely to affect most quickly. Specifically, the distances between the target fire source and each tower within a preset range are calculated, and the transmission line corresponding to the minimum calculated distance is the nearest transmission line. This minimum calculated distance is used as the first distance.

[0097] S64: Calculate the temperature rise rate of the target fire source point based on each of the target images to obtain the second rate;

[0098] Specifically, the temperature rise rate (heating rate) of the target fire source is calculated based on each target image, and the calculated data is used as the second rate.

[0099] S65: Determine the wildfire risk level based on each of the first distances and the second rate to obtain the second level, and send the first power transmission risk warning information according to the second level and the preset transmission configuration.

[0100] Specifically, based on each of the first distances and the second rates, a lookup table method is used to determine the wildfire risk level, and the determined wildfire risk level is taken as the second level; from the preset transmission configuration, the sub-configuration corresponding to the second level is determined, and the first power transmission risk warning information is generated based on the sub-configuration.

[0101] In this embodiment, when the first temperature difference is less than or equal to the first threshold, or when the first highest temperature is less than or equal to the second threshold, the analysis is performed by expanding the shooting range, which avoids missing risks and thus improves the accuracy of power transmission risk warning based on image recognition technology.

[0102] In one embodiment, prior to the step of acquiring the initial image, the method further includes:

[0103] S11: Obtain the monitoring data from the monitoring device;

[0104] Specifically, it can acquire monitoring data sent by monitoring devices, monitoring data from preset storage space, or monitoring data from third-party applications.

[0105] The monitoring data includes: images. Monitoring data may also include: data from various sensors.

[0106] S12: Input the monitoring data into the pre-trained wildfire classification model for classification and prediction to obtain the first prediction result;

[0107] Specifically, the monitoring data is input into a pre-trained wildfire classification model for classification prediction. The vector element with the largest value is selected from the predicted vectors, and the classification category corresponding to the selected vector element is taken as the first prediction result.

[0108] The pre-trained wildfire classification model is a pre-trained binary classification model. It is used to perform binary classification of suspected wildfires and non-existent wildfires.

[0109] S13: If the first prediction result is that a wildfire is suspected, then the suspected wildfire point is determined according to the image in the monitoring data, and the monitoring device is controlled to capture the image of the suspected wildfire point based on the first focal length configuration to obtain the initial image.

[0110] Specifically, if the first prediction result indicates a suspected wildfire, further analysis is required. Therefore, the shooting area corresponding to the image in the monitoring data is taken as the suspected wildfire point. Based on the first focal length configuration, the monitoring device is controlled to shoot images of the suspected wildfire point, and the captured images are used as the initial images.

[0111] In this embodiment, a binary classification prediction is first performed, indicating whether there is a suspected wildfire or not. Step S13 and subsequent steps are only executed when there is a suspected wildfire. This reduces computational resources and avoids missing power transmission risk warnings.

[0112] Please see Figure 2 As shown, in one embodiment, after the step of acquiring the monitoring data of the monitoring device, the following steps are included:

[0113] S141: Input the monitoring data into a pre-trained external force damage classification model for classification and prediction to obtain a second prediction result;

[0114] Specifically, the monitoring data is input into a pre-trained external force damage classification model for classification prediction. The vector element with the largest value is selected from the predicted vectors, and the classification category corresponding to the selected vector element is used as the second prediction result.

[0115] The pre-trained external force damage classification model is a pre-trained binary classification model.

[0116] The second prediction result is either suspected external damage or no external damage.

[0117] S142: If the second prediction result is suspected external force damage, then the image in the monitoring data is input into the pre-trained target segmentation model to segment the external force damage points and obtain the suspected external force damage points;

[0118] Specifically, if the second prediction result indicates suspected external force damage, it means that external force damage exists. External force damage is one of the adverse factors affecting the normal operation of transmission lines. Therefore, the image in the monitoring data is input into the pre-trained target segmentation model to segment the external force damage points, thereby obtaining a mask of the suspected external force damage points. The mask is a binarized mask. The location data of the suspected external force damage points in the image is determined based on the binarized mask. The geographical location of the suspected external force damage points is determined based on the location data in the image and the geographical location of the image capturing device.

[0119] S143: Obtain a second distance and a third distance, wherein the second distance is the minimum distance between the suspected external force damage point and the transmission line, and the third distance is the minimum distance between the suspected external force damage point and the transmission line tower;

[0120] Specifically, it can obtain the second and third distances, or it can obtain the second and third distances from a preset storage space, or it can obtain the second and third distances from a third-party application.

[0121] Specifically, based on the geographical location of the suspected external force damage point and the geographical location of the transmission line, the minimum distance between the suspected external force damage point and the transmission line is calculated.

[0122] Specifically, based on the geographical location of the suspected external force damage point and the geographical location of each tower of the transmission line, the minimum distance between the suspected external force damage point and the tower of the transmission line is calculated.

[0123] S144: If the second distance is greater than the fourth threshold and each of the third distances is greater than the fifth threshold, then the suspected external force damage point is determined to be a non-external force damage point;

[0124] Specifically, if the second distance is greater than the fourth threshold and each of the third distances is greater than the fifth threshold, then the suspected external force damage point is relatively far from the transmission line and each of the transmission line towers, and will not affect the normal operation of the transmission line. Therefore, the suspected external force damage point is determined to be a non-external force damage point.

[0125] S145: If the second distance is less than or equal to the fourth threshold, or if any of the third distances is less than or equal to the fifth threshold, then the suspected external force damage point is determined as the external force damage point to be analyzed.

[0126] Specifically, if the second distance is less than or equal to the fourth threshold, or if any of the third distances is less than or equal to the fifth threshold, then the suspected external force damage point is close to the transmission line or at least one tower of the transmission line, which may affect the normal operation of the transmission line. Therefore, the suspected external force damage point is determined as the external force damage point to be analyzed.

[0127] S146: Obtain the direction of motion of the external force failure point to be analyzed, and determine whether the direction of motion, the second distance and the third distance corresponding to the external force failure point to be analyzed satisfy the second condition;

[0128] Specifically, the direction of movement of the point of external force damage to be analyzed is determined based on the various images in the monitoring data.

[0129] S147: If satisfied, calculate the distance reduction rate for the second distance corresponding to the external force damage point to be analyzed, and obtain the third rate; calculate the distance reduction rate for the third distance corresponding to the external force damage point to be analyzed, and obtain the fourth rate; determine the external force damage risk level based on the third rate and the fourth rate, and obtain the third level; and send the second power transmission risk warning information based on the third level and the preset transmission configuration.

[0130] Specifically, if the following conditions are met, that is, the direction of movement, the second distance, and the third distance corresponding to the point of external force damage to be analyzed satisfy the second condition, then it is determined that the point of external force damage to be analyzed will affect the normal operation of the transmission line and an early warning is required. Therefore, firstly, the distance reduction rate is calculated for the second distance corresponding to the point of external force damage to be analyzed to obtain the third rate, and the distance reduction rate is calculated for the third distance corresponding to the point of external force damage to be analyzed to obtain the fourth rate. Then, the risk level of the point of external force damage to be analyzed is determined by a lookup table method based on the third rate and the fourth rate, and the determined risk level is taken as the third level. From the preset transmission configuration, the sub-configuration corresponding to the first level is determined, and the first transmission risk early warning information is generated based on the sub-configuration.

[0131] This embodiment enables early warning of the risk of external force damage to the operation of transmission lines, thereby improving the accuracy of transmission risk early warning based on image recognition technology.

[0132] In one embodiment, the second condition is that the second distance decreases, the third distance decreases, and the direction of movement intersects with the transmission line.

[0133] Specifically, the second condition is that the second distance decreases and the third distance decreases, which means that the fire approaches the power transmission line and at least one of the towers on the power transmission line, and the direction of movement intersects the power transmission line, that is, when approaching the power transmission line and at least one of the towers on the power transmission line, the direction of the wildfire will cross the power transmission line.

[0134] Please see Figure 3 As shown, in one embodiment, a power transmission risk early warning device is provided, the device comprising:

[0135] Data acquisition module 801 is used to acquire an initial image, which is an image taken by the monitoring device based on a first focal length configuration of the suspected wildfire point;

[0136] Temperature difference calculation module 802 is used to calculate the temperature difference between the first maximum temperature and the first ambient temperature based on the initial image, as the first temperature difference;

[0137] The first image set determination module 803 is used to control the monitoring device to take pictures of the suspected wildfire point according to a preset time configuration if the first temperature difference is greater than the first threshold, or if the first highest temperature is greater than the second threshold, thereby obtaining the first image set.

[0138] The judgment result determination module 804 is used to determine whether a suspected wildfire point is a fire point based on the first image set, and obtain a judgment result.

[0139] The first early warning module 805 is used to determine the wildfire risk level of the fire source corresponding to the first highest temperature or first temperature difference based on the first image set if the judgment result is yes, obtain a first level, and send a first power transmission risk early warning information according to the first level and a preset transmission configuration.

[0140] This embodiment acquires an initial image, which is an image taken by a monitoring device based on a first focal length configuration of a suspected wildfire point. Based on the initial image, the temperature difference between a first maximum temperature and a first ambient temperature is calculated as a first temperature difference. If the first temperature difference is greater than a first threshold, or if the first maximum temperature is greater than a second threshold, then according to a preset time configuration, the monitoring device is controlled to take pictures of the suspected wildfire point, obtaining a first image set. Based on the first image set, it is determined whether the suspected wildfire point is a fire point, obtaining a judgment result. If the judgment result is yes, then based on the first image set, the wildfire risk level of the fire source point corresponding to the first maximum temperature or the first temperature difference is determined, obtaining a first level. Based on the first level and a preset transmission configuration, a first power transmission risk warning information is sent, thereby improving the accuracy of power transmission risk warning based on image recognition technology.

[0141] In one embodiment, the step of the judgment result determination module 804 determining whether a suspected wildfire point is a fire point based on the first image set and obtaining a judgment result includes:

[0142] Based on the first image set, a temperature-time curve is generated for the fire source point corresponding to the first highest temperature.

[0143] If the slope of the temperature-time curve satisfies the first condition, then the judgment result is determined to be yes;

[0144] If the slope of the temperature-time curve does not meet the first condition, then the judgment result is determined to be negative.

[0145] In one embodiment, the step of the first early warning module 805 determining the wildfire risk level of the fire source corresponding to the first highest temperature or first temperature difference based on the first image set, and obtaining the first level, includes:

[0146] The temperature rise rate is calculated based on the temperature-time curve to obtain the first rate.

[0147] The minimum distance between the fire source corresponding to the first highest temperature or the first temperature difference and the nearest transmission line tower is obtained as the danger distance;

[0148] Based on the first rate and the danger distance, the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference is determined, and the first level is obtained.

[0149] In one embodiment, the device further includes: a second early warning module, the second early warning module being used for:

[0150] If the first temperature difference is less than or equal to the first threshold, or if the first highest temperature is less than or equal to the second threshold, then according to the second focal length configuration, the monitoring device is controlled to take pictures of the suspected wildfire point to obtain a target image, and the shooting range of the target image is greater than the shooting range of the initial image.

[0151] The second temperature difference is obtained by calculating the temperature difference between the second highest temperature and the second ambient temperature based on the target image;

[0152] If the second temperature difference is greater than the third threshold, then the fire source point corresponding to the second highest temperature corresponding to the second temperature difference that is greater than the third threshold is taken as the target fire source point, and the minimum distance between the target fire source point and the nearest transmission line tower is calculated to obtain the first distance;

[0153] The temperature rise rate of the target fire source point is calculated based on each of the target images to obtain the second rate;

[0154] Based on the first distance and the second rate, the wildfire risk level is determined to obtain the second level. Based on the second level and the preset transmission configuration, the first power transmission risk warning information is sent.

[0155] In one embodiment, the apparatus further includes a preprocessing module, the preprocessing module being used for:

[0156] Obtain the monitoring data from the monitoring device;

[0157] The monitoring data is input into a pre-trained wildfire classification model for classification and prediction to obtain the first prediction result;

[0158] If the first prediction result indicates a suspected wildfire, the suspected wildfire point is determined based on the image in the monitoring data. Based on the first focal length configuration, the monitoring device is controlled to capture images of the suspected wildfire point to obtain the initial image.

[0159] In one embodiment, the device further includes: a third early warning module, the third early warning module being used for:

[0160] The monitoring data is input into a pre-trained external force damage classification model for classification and prediction to obtain a second prediction result.

[0161] If the second prediction result indicates suspected external force damage, the image from the monitoring data is input into a pre-trained target segmentation model to segment the external force damage points and obtain the suspected external force damage points.

[0162] Obtain a second distance and a third distance, where the second distance is the minimum distance between the suspected external force damage point and the transmission line, and the third distance is the minimum distance between the suspected external force damage point and the transmission line tower.

[0163] If the second distance is greater than the fourth threshold and each of the third distances is greater than the fifth threshold, then the suspected external force damage point is determined to be a non-external force damage point.

[0164] If the second distance is less than or equal to the fourth threshold, or if any of the third distances is less than or equal to the fifth threshold, then the suspected external force damage point is determined as the external force damage point to be analyzed.

[0165] Obtain the direction of motion of the external force failure point to be analyzed, and determine whether the direction of motion, the second distance, and the third distance corresponding to the external force failure point to be analyzed satisfy the second condition;

[0166] If satisfied, calculate the distance reduction rate for the second distance corresponding to the point of external force damage to be analyzed, and obtain the third rate. Calculate the distance reduction rate for the third distance corresponding to the point of external force damage to be analyzed, and obtain the fourth rate. Determine the external force damage risk level based on the third rate and the fourth rate, and obtain the third level. Send the second power transmission risk warning information based on the third level and the preset transmission configuration.

[0167] In one embodiment, the second condition is that the second distance decreases, the third distance decreases, and the direction of movement intersects with the transmission line.

[0168] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a power transmission risk early warning method on the server side.

[0169] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the following steps:

[0170] Acquire an initial image, which is an image taken by the monitoring device based on a first focal length configuration of the suspected wildfire point;

[0171] The temperature difference between the first maximum temperature and the first ambient temperature is calculated based on the initial image and is taken as the first temperature difference;

[0172] If the first temperature difference is greater than the first threshold, or if the first highest temperature is greater than the second threshold, then according to the preset time configuration, the monitoring device is controlled to take pictures of the suspected wildfire point to obtain the first image set;

[0173] Based on the first image set, determine whether the suspected wildfire spot is a fire spot, and obtain the determination result;

[0174] If the judgment result is yes, then the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference is determined according to the first image set to obtain the first level, and the first power transmission risk warning information is sent according to the first level and the preset transmission configuration.

[0175] This embodiment acquires an initial image, which is an image taken by a monitoring device based on a first focal length configuration of a suspected wildfire point. Based on the initial image, the temperature difference between a first maximum temperature and a first ambient temperature is calculated as the first temperature difference. If the first temperature difference is greater than a first threshold, or if the first maximum temperature is greater than a second threshold, then according to a preset time configuration, the monitoring device is controlled to take pictures of the suspected wildfire point, obtaining a first image set. Based on the first image set, it is determined whether the suspected wildfire point is a fire point, obtaining a judgment result. If the judgment result is yes, then based on the first image set, the wildfire risk level of the fire source point corresponding to the first maximum temperature or the first temperature difference is determined, obtaining a first level. Based on the first level and a preset transmission configuration, a first power transmission risk warning information is sent, thereby improving the accuracy of power transmission risk warning based on image recognition technology.

[0176] In one embodiment, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, performs the following steps:

[0177] Acquire an initial image, which is an image taken by the monitoring device based on a first focal length configuration of the suspected wildfire point;

[0178] The temperature difference between the first maximum temperature and the first ambient temperature is calculated based on the initial image and is taken as the first temperature difference.

[0179] If the first temperature difference is greater than the first threshold, or if the first highest temperature is greater than the second threshold, then according to the preset time configuration, the monitoring device is controlled to take pictures of the suspected wildfire point to obtain the first image set;

[0180] Based on the first image set, determine whether the suspected wildfire spot is a fire spot, and obtain the determination result;

[0181] If the judgment result is yes, then the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference is determined according to the first image set to obtain the first level, and the first power transmission risk warning information is sent according to the first level and the preset transmission configuration.

[0182] This embodiment acquires an initial image, which is an image taken by a monitoring device based on a first focal length configuration of a suspected wildfire point. Based on the initial image, the temperature difference between a first maximum temperature and a first ambient temperature is calculated as a first temperature difference. If the first temperature difference is greater than a first threshold, or if the first maximum temperature is greater than a second threshold, then according to a preset time configuration, the monitoring device is controlled to take pictures of the suspected wildfire point, obtaining a first image set. Based on the first image set, it is determined whether the suspected wildfire point is a fire point, obtaining a judgment result. If the judgment result is yes, then based on the first image set, the wildfire risk level of the fire source point corresponding to the first maximum temperature or the first temperature difference is determined, obtaining a first level. Based on the first level and a preset transmission configuration, a first power transmission risk warning information is sent, thereby improving the accuracy of power transmission risk warning based on image recognition technology.

[0183] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0184] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0185] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0186] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for early warning of power transmission risks, the method comprising: Acquire an initial image, which is an image taken by the monitoring device based on a first focal length configuration of the suspected wildfire point; The temperature difference between the first maximum temperature and the first ambient temperature is calculated based on the initial image and is taken as the first temperature difference. If the first temperature difference is greater than the first threshold, or if the first highest temperature is greater than the second threshold, then according to the preset time configuration, the monitoring device is controlled to take pictures of the suspected wildfire point to obtain the first image set; Based on the first image set, determine whether the suspected wildfire spot is a fire spot, and obtain the determination result; If the judgment result is yes, then the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference is determined according to the first image set to obtain the first level, and the first power transmission risk warning information is sent according to the first level and the preset transmission configuration. Before the step of obtaining the initial image, the method further includes: Obtain the monitoring data from the monitoring device; The monitoring data is input into a pre-trained wildfire classification model for classification and prediction to obtain the first prediction result; If the first prediction result indicates a suspected wildfire, then the suspected wildfire point is determined based on the image in the monitoring data. Based on the first focal length configuration, the monitoring device is controlled to capture images of the suspected wildfire point to obtain the initial image. After the step of acquiring the monitoring data of the monitoring device, the following steps are included: The monitoring data is input into a pre-trained external force damage classification model for classification and prediction to obtain a second prediction result. If the second prediction result indicates suspected external force damage, the image from the monitoring data is input into a pre-trained target segmentation model to segment the external force damage points and obtain the suspected external force damage points. Obtain a second distance and a third distance, where the second distance is the minimum distance between the suspected external force damage point and the transmission line, and the third distance is the minimum distance between the suspected external force damage point and the transmission line tower. If the second distance is greater than the fourth threshold and each of the third distances is greater than the fifth threshold, then the suspected external force damage point is determined to be a non-external force damage point; If the second distance is less than or equal to the fourth threshold, or if any of the third distances is less than or equal to the fifth threshold, then the suspected external force damage point is determined as the external force damage point to be analyzed. Obtain the direction of motion of the external force failure point to be analyzed, and determine whether the direction of motion, the second distance, and the third distance corresponding to the external force failure point to be analyzed satisfy the second condition; If satisfied, calculate the distance reduction rate for the second distance corresponding to the point of external force damage to be analyzed, and obtain the third rate. Calculate the distance reduction rate for the third distance corresponding to the point of external force damage to be analyzed, and obtain the fourth rate. Determine the external force damage risk level based on the third rate and the fourth rate, and obtain the third level. Send the second power transmission risk warning information based on the third level and the preset transmission configuration.

2. The power transmission risk early warning method according to claim 1, characterized in that, The step of determining whether a suspected wildfire spot is a fire spot based on the first image set and obtaining the determination result includes: Based on the first image set, a temperature-time curve is generated for the fire source point corresponding to the first highest temperature. If the slope of the temperature-time curve satisfies the first condition, then the judgment result is determined to be yes; If the slope of the temperature-time curve does not meet the first condition, then the judgment result is determined to be negative.

3. The power transmission risk early warning method according to claim 2, characterized in that, The step of determining the wildfire risk level of the fire source corresponding to the first highest temperature or first temperature difference based on the first image set, and obtaining the first level, includes: The temperature rise rate is calculated based on the temperature-time curve to obtain the first rate. The minimum distance between the fire source corresponding to the first highest temperature or the first temperature difference and the nearest transmission line tower is obtained as the danger distance; Based on the first rate and the danger distance, the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference is determined, and the first level is obtained.

4. The power transmission risk early warning method according to claim 1, characterized in that, After the step of calculating the temperature difference between the first maximum temperature and the first ambient temperature based on the initial image as the first temperature difference, the method further includes: If the first temperature difference is less than or equal to the first threshold, or if the first highest temperature is less than or equal to the second threshold, then according to the second focal length configuration, the monitoring device is controlled to take pictures of the suspected wildfire point to obtain a target image, and the shooting range of the target image is greater than the shooting range of the initial image. The second temperature difference is obtained by calculating the temperature difference between the second highest temperature and the second ambient temperature based on the target image; If the second temperature difference is greater than the third threshold, then the fire source point corresponding to the second highest temperature corresponding to the second temperature difference that is greater than the third threshold is taken as the target fire source point, and the minimum distance between the target fire source point and the nearest transmission line tower is calculated to obtain the first distance; The temperature rise rate of the target fire source point is calculated based on each of the target images to obtain the second rate; Based on the first distance and the second rate, the wildfire risk level is determined to obtain the second level. Based on the second level and the preset transmission configuration, the first power transmission risk warning information is sent.

5. The power transmission risk early warning method according to claim 1, characterized in that, The second condition is that the second distance decreases, the third distance decreases, and the direction of movement intersects with the transmission line.

6. A power transmission risk early warning device, applied to the power transmission risk early warning method as described in claim 1, characterized in that, The device includes: The data acquisition module is used to acquire an initial image, which is an image taken by the monitoring device based on a first focal length configuration of the suspected wildfire point; The temperature difference calculation module is used to calculate the temperature difference between the first maximum temperature and the first ambient temperature based on the initial image, as the first temperature difference; The first image set determination module is used to control the monitoring device to take pictures of the suspected wildfire point according to a preset time configuration if the first temperature difference is greater than the first threshold, or if the first highest temperature is greater than the second threshold, thereby obtaining the first image set. The judgment result determination module is used to determine whether a suspected wildfire point is a fire point based on the first image set, and obtain the judgment result. The first early warning module is used to determine the wildfire risk level of the fire source corresponding to the first highest temperature or the first temperature difference based on the first image set if the judgment result is yes, obtain the first level, and send the first power transmission risk early warning information according to the first level and the preset transmission configuration.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the power transmission risk early warning method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the power transmission risk early warning method as described in any one of claims 1 to 5.

Images