Substation fire detection method and device based on terminal power business edge computing

Abstract

The present application relates to a substation fire detection method and device based on edge computing of terminal power business, which is applied to an intelligent gateway, and the intelligent gateway includes an edge computing unit. The method includes: receiving a substation monitoring image sent by an image acquisition device; the substation monitoring image is an image obtained by the image acquisition device shooting the target substation in real time; sending the substation monitoring image to the edge computing unit; through the edge computing unit, inputting the substation monitoring image into a pre-trained flame detection model to obtain a flame detection result; the flame detection result is the result obtained by the pre-trained flame detection model marking the flame area in the substation monitoring image; based on the flame detection result, generating a fire detection result for the target substation. The use of this method can improve the efficiency of fire inspections.

Description

Technical Field

[0001] The present application relates to the field of power monitoring technology, and in particular to a substation fire detection method and device, computer equipment, and storage medium based on terminal power business edge computing. Background Art

[0002] Substations are important nodes in the power grid responsible for converting voltage and distributing electrical energy. Substation equipment inspection is a basic task to ensure the safe operation of substations and improve power supply reliability.

[0003] Traditionally, substation fire inspections are mostly conducted manually. Substation attendants enter the substation equipment area and inspect the operating equipment for fires using their senses, such as sight, hearing, smell, touch, or related detection equipment. While this manual inspection method is widely used, it is notoriously difficult to perform and requires a significant amount of manpower.

[0004] Therefore, there is a problem in the traditional technology that the fire inspection efficiency is low. Summary of the Invention

[0005] Based on this, it is necessary to provide a substation fire detection method, device, computer equipment and storage medium based on terminal power business edge computing that can improve the efficiency of fire inspections in response to the above technical problems.

[0006] A substation fire detection method based on terminal power business edge computing is applied to an intelligent gateway, wherein the intelligent gateway includes an edge computing unit. The method includes:

[0007] Receiving a substation monitoring image sent by an image acquisition device; the substation monitoring image is an image obtained by the image acquisition device shooting the target substation in real time;

[0008] Sending the substation monitoring image to the edge computing unit;

[0009] The substation monitoring image is input into a pre-trained flame detection model through the edge computing unit to obtain a flame detection result; the flame detection result is a result obtained by the pre-trained flame detection model marking the flame area in the substation monitoring image;

[0010] Based on the flame detection result, a fire detection result for the target substation is generated; the fire detection result includes at least one of the location of the fire point, the cause of the fire, and the fire level.

[0011] In one embodiment, the flame detection result includes a flame marked area, and generating a fire detection result for the target substation based on the flame detection result includes:

[0012] Acquiring first position information of the flame marked area in the substation monitoring image, and acquiring second position information of the target substation in the substation monitoring image;

[0013] The fire starting point location of the target substation is determined according to the first location information and the second location information.

[0014] In one embodiment, generating a fire detection result for the target substation based on the flame detection result includes:

[0015] Based on the flame marked area, determining a flame area image in the substation monitoring image;

[0016] Acquiring the flame region area in the flame region image, and acquiring the grayscale information of the flame region image;

[0017] The fire severity level of the target substation is determined according to the flame region area and the grayscale information.

[0018] In one embodiment, the grayscale information includes the grayscale value of each pixel of the flame area image, and determining the fire severity of the target substation based on the flame area and the grayscale information includes:

[0019] Obtaining a ratio between the area of the flame region and the image area of the substation monitoring image, and obtaining an average grayscale value of the grayscale values of each pixel;

[0020] A target fire severity level corresponding to the ratio and the average grayscale value is queried as the fire severity level of the target substation.

[0021] In one embodiment, obtaining the flame region area in the flame region image includes:

[0022] Inputting the flame region image into a flame semantic segmentation model to obtain a first flame region in the flame region image;

[0023] performing guided filtering on the first flame region based on the flame region image to obtain a flame region after guided filtering;

[0024] The area of the flame region after the guided filtering is determined in the flame region image to obtain the flame region area.

[0025] In one embodiment, generating a fire detection result for the target substation based on the flame detection result includes:

[0026] According to the location of the fire point of the target substation and the fire severity of the target substation, querying the corresponding target fire cause in a preset fire cause database;

[0027] The target fire cause is used as the fire cause of the target substation.

[0028] In one embodiment, after the step of generating a fire detection result for the target substation based on the flame detection result, the method further includes:

[0029] The fire detection result is sent to a target master station; the target master station is used to display the fire detection result to a user.

[0030] A substation fire detection device based on terminal power business edge computing is applied to an intelligent gateway. The intelligent gateway includes an edge computing unit. The device includes:

[0031] A receiving module, configured to receive a substation monitoring image sent by an image acquisition device; the substation monitoring image is an image obtained by the image acquisition device shooting the target substation in real time;

[0032] A sending module, configured to send the substation monitoring image to the edge computing unit;

[0033] a labeling module, configured to input the substation monitoring image into a pre-trained flame detection model through the edge computing unit to obtain a flame detection result; the flame detection result is a result obtained by labeling the flame area in the substation monitoring image by the pre-trained flame detection model;

[0034] A generation module is used to generate a fire detection result for the target substation based on the flame detection result; the fire detection result includes at least one of the location of the fire point, the cause of the fire, and the fire level.

[0035] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0036] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0037] The above-mentioned substation fire detection method, device, computer equipment and storage medium based on edge computing of terminal power business use image acquisition equipment to collect substation monitoring images of the target substation in real time, and send the substation monitoring images to an intelligent gateway with edge computing capabilities; the intelligent gateway inputs the substation image into the edge computing module; the edge computing module is used to input the substation monitoring image into a pre-trained flame detection model to obtain a flame detection result; based on the flame detection result, a fire detection result for the target substation is generated; the fire detection result includes at least one of the fire location, fire cause, and fire level; automated fire inspection is realized, avoiding the consumption of a large amount of human resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a diagram of an application environment of a substation fire detection method in one embodiment;

[0039] Figure 2 1 is a flow chart of a substation fire detection method according to an embodiment;

[0040] Figure 3 is a flow chart of a substation fire detection method according to another embodiment;

[0041] Figure 4 is a structural block diagram of a substation fire detection device in one embodiment;

[0042] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0044] The substation fire detection method based on terminal power business edge computing provided in this application can be applied to Figure 1In the application environment shown, the image acquisition device 110 communicates with the intelligent gateway 120 via a network. The intelligent gateway 120 receives the substation monitoring image sent by the image acquisition device 110; the substation monitoring image is an image obtained by the image acquisition device in real time photographing the target substation; the substation monitoring image is sent to the edge computing unit; the intelligent gateway 120 inputs the substation monitoring image into a pre-trained flame detection model through the edge computing unit to obtain a flame detection result; the flame detection result is the result obtained by the pre-trained flame detection model by annotating the flame area in the substation monitoring image; based on the flame detection result, the intelligent gateway 120 generates a fire detection result for the target substation; the fire detection result includes at least one of the location of the fire point, the cause of the fire, and the fire level.

[0045] In one embodiment, Figure 2 As shown in the figure, a substation fire detection method based on terminal power business edge computing is provided. Figure 1 The intelligent gateway in the example is used as an example to illustrate that the intelligent gateway includes an edge computing unit, including the following steps:

[0046] Step S210: receiving a substation monitoring image sent by an image acquisition device; the substation monitoring image is an image obtained by the image acquisition device by photographing the target substation in real time.

[0047] The image acquisition device may be a video camera, a still camera, etc.

[0048] In the specific implementation, when a fire is detected in a target substation, an image acquisition device can be used to photograph the target substation in real time to obtain a substation monitoring image. Then, the image acquisition device sends the collected substation monitoring image to the intelligent gateway, and the intelligent gateway receives the substation monitoring image sent by the image acquisition device.

[0049] Step S220: Send the substation monitoring image to the edge computing unit.

[0050] Among them, the edge computing unit may refer to a computing unit that enables the intelligent gateway to realize edge computing functions.

[0051] In a specific implementation, after receiving the substation monitoring image, the smart gateway inputs the substation monitoring image into the edge computing unit.

[0052] In step S230, the substation monitoring image is input into the pre-trained flame detection model through the edge computing unit to obtain a flame detection result; the flame detection result is the result obtained by the pre-trained flame detection model marking the flame area in the substation monitoring image.

[0053] The pre-trained flame detection model may refer to a pre-trained yolov3 model.

[0054] In a specific implementation, after the intelligent gateway inputs the substation monitoring image into the edge computing unit, the intelligent gateway, through the edge computing unit, inputs the substation monitoring image into a pre-trained flame detection model. This pre-trained flame detection model then annotates the flame areas in the substation monitoring image to obtain the flame detection results. In practical applications, the flame detection results can include information such as the flame annotated areas.

[0055] Step S240: Generate a fire detection result for the target substation based on the flame detection result; the fire detection result includes at least one of the location of the fire point, the cause of the fire, and the fire severity.

[0056] In a specific implementation, after obtaining the flame detection result, the intelligent gateway can determine at least one of the fire point location, fire cause, and fire level of the target substation based on the flame marked area in the flame detection result, and then generate a fire detection result for the target substation.

[0057] In the above-mentioned substation fire detection method based on edge computing of terminal power business, the substation monitoring image of the target substation is collected in real time by an image acquisition device, and the substation monitoring image is sent to an intelligent gateway with edge computing capabilities; the intelligent gateway inputs the substation image into the edge computing module; the edge computing module is used to input the substation monitoring image into a pre-trained flame detection model to obtain a flame detection result; based on the flame detection result, a fire detection result for the target substation is generated; the fire detection result includes at least one of the fire location, fire cause, and fire level; automated fire inspection is realized, avoiding the consumption of a large amount of human resources.

[0058] In another embodiment, the flame detection result includes a flame marked area. Based on the flame detection result, a fire detection result for a target substation is generated, including: obtaining first position information of the flame marked area in the substation monitoring image, and obtaining second position information of the target substation in the substation monitoring image; determining the fire starting point location of the target substation based on the first position information and the second position information.

[0059] In a specific implementation, when the intelligent gateway generates fire detection results for the target substation based on the flame detection results, the intelligent gateway can obtain the first position information of the flame marked area in the substation monitoring image, and obtain the second position information of the target substation in the substation monitoring image; finally, the intelligent gateway determines the location of the fire point in the target substation based on the relative position relationship between the first position information and the second position information.

[0060] The technical solution of this embodiment obtains the first position information of the flame marked area in the substation monitoring image, and obtains the second position information of the target substation in the substation monitoring image; based on the relative position relationship between the first position information and the second position information, the fire point position of the target substation is accurately located.

[0061] In another embodiment, a fire detection result for a target substation is generated based on the flame detection result, including: determining a flame area image in the substation monitoring image based on the flame marked area; obtaining the flame area in the flame area image, and obtaining grayscale information of the flame area image; and determining the fire level of the target substation based on the flame area and grayscale information.

[0062] In a specific implementation, when generating fire detection results for a target substation based on flame detection results, the intelligent gateway can identify a flame region image within the substation monitoring image based on the flame-annotated area. The intelligent gateway can then obtain the flame area and grayscale information from the flame region image. Finally, the intelligent gateway determines the fire severity at the target substation based on the flame area and grayscale information.

[0063] The technical solution of this embodiment determines the flame area image in the substation monitoring image based on the flame marked area, and obtains the flame area in the flame area image, thereby determining the ignition area of the current fire based on the flame area, and determining the flame intensity of the current fire based on the grayscale information of the flame area image, thereby accurately judging the fire level of the target substation.

[0064] In another embodiment, the fire severity level of the target substation is determined based on the flame area and grayscale information, including: obtaining the ratio between the flame area and the image area of the substation monitoring image, and obtaining the average grayscale value of the grayscale values of each pixel; querying the target fire severity level corresponding to the ratio and the average grayscale value as the fire severity level of the target substation.

[0065] The grayscale information includes the grayscale value of each pixel in the flame area image.

[0066] In a specific implementation, when determining the fire severity level of a target substation based on the flame area and grayscale information, the intelligent gateway can obtain the ratio between the flame area and the image area of the substation monitoring image. Furthermore, the intelligent gateway determines the grayscale value of each pixel in the flame area image from the grayscale information and calculates the average grayscale value of each pixel to obtain the average grayscale value. The intelligent gateway can then query a preset mapping table for the target fire severity level corresponding to this ratio and average grayscale value. Finally, the intelligent gateway uses this target fire severity level as the fire severity level of the target substation.

[0067] The technical solution of this embodiment is to obtain the ratio between the area of the flame area and the image area of the substation monitoring image, and to obtain the average grayscale value of the grayscale values of each pixel; and to query the target fire level corresponding to the ratio and the average grayscale value as the fire level of the target substation. In this way, the fire level of the target substation can be determined in a timely manner.

[0068] In another embodiment, obtaining the flame region area in the flame region image includes: inputting the flame region image into a flame semantic segmentation model to obtain a first flame region in the flame region image; performing guided filtering on the first flame region based on the flame region image to obtain a flame region after guided filtering; and determining the area of the flame region after guided filtering in the flame region image to obtain the flame region area.

[0069] In a specific implementation, when obtaining the flame area from a flame region image, the intelligent gateway may input the flame region image into a pre-trained flame semantic segmentation model. Using this model, the first flame region in the flame region image is determined. The intelligent gateway then performs guided filtering on the first flame region based on the flame region image to obtain a flame region after guided filtering. In practical applications, the intelligent gateway may adjust the contrast of the flame region image to increase the contrast. The intelligent gateway then uses the adjusted flame region image to perform guided filtering on the first flame region to obtain a flame region after guided filtering.

[0070] Finally, the intelligent gateway determines the area of the flame region after the guided filtering in the flame region image to obtain the flame region area.

[0071] The technical solution of this embodiment is to input the flame region image into the flame semantic segmentation model to obtain a first flame region in the flame region image; perform guided filtering on the first flame region based on the flame region image to obtain a flame region after guided filtering, so that the edges of the flame region after guided filtering are sharper, and use the area of the flame region after guided filtering in the flame region image as the flame region area, thereby achieving more accurate determination of the area of the flame region in the flame region image.

[0072] In another embodiment, based on the flame detection result, a fire detection result for the target substation is generated, including: according to the fire point location of the target substation and the fire level of the target substation, searching for the corresponding target fire cause in a preset fire cause database; and using the target fire cause as the fire cause of the target substation.

[0073] In the specific implementation, when the intelligent gateway generates the fire detection results for the target substation based on the flame detection results, after determining the fire point location and the fire level of the target substation, the intelligent gateway can query the corresponding target fire cause in the preset fire cause database according to the fire point location and the fire level of the target substation; finally, the intelligent gateway uses the target fire cause as the fire cause of the target substation.

[0074] The technical solution of this embodiment is to query the corresponding target fire cause in the preset fire cause database according to the fire point location and fire intensity of the target substation, and use the target fire cause as the fire cause of the target substation, so as to quickly determine the fire cause of the target substation based on the fire point location and fire intensity, and thus provide timely reference for users.

[0075] In another embodiment, after the step of generating a fire detection result for a target substation based on the flame detection result, the method further includes: sending the fire detection result to a target master station; the target master station is used to display the fire detection result to a user.

[0076] In a specific implementation, after the intelligent gateway generates a fire detection result for the target substation based on the flame detection results, it can also send the fire detection result to the target master station. In actual applications, the intelligent gateway can send the fire detection result to the target master station via a message queue telemetry transmission protocol for reception by the target master station. After the target master station receives the fire detection result, the target master station can display the fire detection result on a display screen. For example, the target master station can display information such as the current fire point location, fire cause, and fire severity on the display screen, thereby promptly notifying the user of the current fire situation in the target substation.

[0077] The technical solution of this embodiment sends the fire detection results to the target master station for display to the user, thereby promptly notifying the user of the current fire situation in the target substation and allowing the user to go to the scene to perform fire extinguishing operations in a timely manner.

[0078] In another embodiment, Figure 3 As shown in the figure, a substation fire detection method based on terminal power business edge computing is provided. Figure 1 Taking the intelligent gateway in

[15] as an example, the intelligent gateway includes an edge computing unit and the following steps: Step S310: Receive a substation monitoring image sent by an image acquisition device; the substation monitoring image is an image obtained by the image acquisition device taking real-time photos of the target substation. Step S320: Send the substation monitoring image to the edge computing unit. Step S330: Input the substation monitoring image into a pre-trained flame detection model via the edge computing unit to obtain a flame detection result; the flame detection result is the result obtained by the pre-trained flame detection model labeling the flame area in the substation monitoring image; the flame detection result includes the labeled flame area. Step S340: Based on the labeled flame area, determine a flame area image in the substation monitoring image. Step S350: Input the flame area image into a flame semantic segmentation model to obtain a first flame area in the flame area image. Step S360: Perform guided filtering on the first flame area based on the flame area image to obtain a flame area after guided filtering. Step S370: Determine the area of the flame region after the guided filtering in the flame region image to obtain the flame region area, and obtain the grayscale information of the flame region image. Step S380: Determine the fire level of the target substation based on the flame region area and the grayscale information to obtain the fire detection result. Step S390: Send the fire detection result to the target master station; the target master station is used to display the fire detection result to the user. It should be noted that the specific definitions of the above steps can be found in the specific definitions of a substation fire detection method based on terminal power business edge computing above.

[0079] It should be understood that although Figure 2 and Figure 3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 2 and Figure 3At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0080] In one embodiment, Figure 4 As shown, a substation fire detection device based on terminal power business edge computing is provided, which is applied to an intelligent gateway. The intelligent gateway includes an edge computing unit. The device includes:

[0081] The receiving module 410 is configured to receive a substation monitoring image sent by an image acquisition device; the substation monitoring image is an image obtained by the image acquisition device shooting the target substation in real time;

[0082] A sending module 420 is configured to send the substation monitoring image to the edge computing unit;

[0083] a labeling module 430 configured to input the substation monitoring image into a pre-trained flame detection model via the edge computing unit to obtain a flame detection result; the flame detection result is a result obtained by labeling the flame area in the substation monitoring image using the pre-trained flame detection model;

[0084] The generation module 440 is configured to generate a fire detection result for the target substation based on the flame detection result; the fire detection result includes at least one of the location of the fire, the cause of the fire, and the fire severity.

[0085] In one embodiment, the flame detection result includes a flame marked area, and the generation module is specifically used to obtain first position information of the flame marked area in the substation monitoring image, and to obtain second position information of the target substation in the substation monitoring image; based on the first position information and the second position information, determine the fire point location of the target substation.

[0086] In one embodiment, the generation module 440 is specifically used to determine a flame area image in the substation monitoring image based on the flame marked area; obtain the flame area in the flame area image, and obtain grayscale information of the flame area image; and determine the fire level of the target substation based on the flame area and the grayscale information.

[0087] In one embodiment, the grayscale information includes the average grayscale value of each pixel of the flame area image, and the generation module 440 is specifically used to obtain the ratio between the area of the flame area and the image area of the substation monitoring image; query the target fire level corresponding to the ratio and the average grayscale value as the fire level of the target substation.

[0088] In one embodiment, the generation module 440 is specifically configured to input the flame region image into a flame semantic segmentation model to obtain a first flame region in the flame region image; perform guided filtering on the first flame region based on the flame region image to obtain a flame region after guided filtering; and determine the area of the flame region after guided filtering in the flame region image to obtain the flame region area.

[0089] In one embodiment, the generation module 440 is specifically used to query the corresponding target fire cause in a preset fire cause database according to the location of the fire point of the target substation and the fire level of the target substation; and use the target fire cause as the fire cause of the target substation.

[0090] In one embodiment, the device includes: a return module, configured to send the fire detection result to a target host station; the target host station is configured to display the fire detection result to a user.

[0091] For the specific definition of the substation fire detection device based on the terminal power business edge computing, please refer to the definition of the substation fire detection method based on the terminal power business edge computing above, which will not be repeated here. The various modules in the above-mentioned substation fire detection device based on the terminal power business edge computing can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0092] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store substation fire detection data based on terminal power business edge computing. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a substation fire detection method based on terminal power business edge computing is implemented.

[0093] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0094] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program. When executed by the processor, the computer program causes the processor to perform the steps of the aforementioned method for detecting substation fires based on edge computing for terminal power services. The steps of the method for detecting substation fires based on edge computing for terminal power services may be the steps of the method for detecting substation fires based on edge computing for terminal power services in each of the aforementioned embodiments.

[0095] In one embodiment, a computer-readable storage medium is provided, storing a computer program. When executed by a processor, the computer program causes the processor to perform the steps of the aforementioned method for detecting substation fires based on edge computing for terminal power services. The steps of the method for detecting substation fires based on edge computing for terminal power services may be the steps of the method for detecting substation fires based on edge computing for terminal power services in each of the aforementioned embodiments.

[0096] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0097] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above 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.

[0098] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A substation fire detection method based on terminal power business edge computing, characterized in that: Applied to an intelligent gateway, the intelligent gateway including an edge computing unit, the method comprising: Receiving a substation monitoring image sent by an image acquisition device; the substation monitoring image is an image obtained by the image acquisition device shooting the target substation in real time; Sending the substation monitoring image to the edge computing unit; The substation monitoring image is input into a pre-trained flame detection model through the edge computing unit to obtain a flame detection result; the flame detection result is a flame marked area obtained by marking the flame area in the substation monitoring image by the pre-trained flame detection model; Based on the flame detection result, a fire detection result for the target substation is generated, including: determining a flame area image in the substation monitoring image based on the flame marked area; inputting the flame area image into a flame semantic segmentation model to obtain a first flame area in the flame area image; improving the image contrast of the flame area image to obtain an adjusted flame area image; performing guided filtering on the first flame area based on the adjusted flame area image to obtain a flame area after guided filtering; determining the area of the flame area after guided filtering in the flame area image to obtain the flame area area, and obtaining grayscale information of the flame area image; the grayscale information includes the grayscale value of each pixel in the flame area image; obtaining a ratio between the flame area area and the image area of the substation monitoring image, and obtaining an average grayscale value of the grayscale values of each pixel; querying a target fire intensity level corresponding to the ratio and the average grayscale value as the fire intensity level of the target substation; the fire detection result includes at least one of the location of the fire point, the cause of the fire, and the fire intensity level.

2. The method according to claim 1, characterized in that The flame detection result includes a flame marked area, and generating a fire detection result for the target substation based on the flame detection result includes: Acquiring first position information of the flame marked area in the substation monitoring image, and acquiring second position information of the target substation in the substation monitoring image; The fire starting point location of the target substation is determined according to the first location information and the second location information.

3. The method according to claim 1, characterized in that The generating a fire detection result for the target substation based on the flame detection result includes: According to the location of the fire point of the target substation and the fire severity of the target substation, querying the corresponding target fire cause in a preset fire cause database; The target fire cause is used as the fire cause of the target substation.

4. The method according to claim 1, wherein After the step of generating a fire detection result for the target substation based on the flame detection result, the method further includes: The fire detection result is sent to a target master station; the target master station is used to display the fire detection result to a user.

5. A substation fire detection device based on terminal power business edge computing, characterized in that: Applied to an intelligent gateway, the intelligent gateway includes an edge computing unit, and the device includes: A receiving module, configured to receive a substation monitoring image sent by an image acquisition device; the substation monitoring image is an image obtained by the image acquisition device shooting the target substation in real time; A sending module, configured to send the substation monitoring image to the edge computing unit; a labeling module, configured to input the substation monitoring image into a pre-trained flame detection model through the edge computing unit to obtain a flame detection result; the flame detection result is a flame labeled area obtained by labeling the flame area in the substation monitoring image by the pre-trained flame detection model; A generation module, configured to generate a fire detection result for the target substation based on the flame detection result, comprising: determining a flame region image in the substation monitoring image based on the flame marked area; obtaining a flame region area in the flame region image, and obtaining grayscale information of the flame region image; the grayscale information comprising a grayscale value of each pixel in the flame region image; obtaining a ratio between the flame region area and the image area of the substation monitoring image, and obtaining an average grayscale value of the grayscale values of each pixel; querying a target fire severity level corresponding to the ratio and the average grayscale value as the fire severity level of the target substation; the fire detection result comprising at least one of a location of a fire point, a cause of the fire, and a fire severity level; The generation module is specifically configured to input the flame region image into a flame semantic segmentation model to obtain a first flame region in the flame region image; improve the image contrast of the flame region image to obtain an adjusted flame region image; perform guided filtering on the first flame region based on the adjusted flame region image to obtain a flame region after guided filtering; and determine the area of the flame region after guided filtering in the flame region image to obtain the flame region area.

6. The device according to claim 5, characterized in that The flame detection result includes a flame marked area, and the generation module is specifically used to obtain first position information of the flame marked area in the substation monitoring image, and obtain second position information of the target substation in the substation monitoring image; and determine the fire point location of the target substation based on the first position information and the second position information.

7. The device according to claim 5, characterized in that The generation module is specifically configured to query a preset fire cause database for a corresponding target fire cause according to the fire point location of the target substation and the fire severity of the target substation; and use the target fire cause as the fire cause of the target substation.

8. The device according to claim 5, characterized in that The device further includes: a return module, configured to send the fire detection result to a target master station; the target master station is configured to display the fire detection result to a user.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images