Fire prediction method and system based on offshore platform fire alarm equipment

Abstract

The invention discloses a fire hazard prediction method and system based on an offshore platform fire alarm device, and the method comprises the steps: determining a temperature abnormal region in a target region through a preset region division strategy, and shortening a region needing to be predicted more accurately, thereby reducing the data size needed by the subsequent fire hazard prediction, and improving the prediction efficiency. And selecting at least one target fusion image from the fusion image sequence according to a preset image selection strategy, inputting the at least one target fusion image into a preset image anomaly recognition model, outputting a recognition result corresponding to the at least one target fusion image, and performing image anomaly recognition according to each recognition result. And adopting a preset prediction strategy to generate fire prediction information of the temperature abnormal region. According to the method, the subsequent fire risk can be estimated based on the number of articles with fire hazards in a continuous period of time, so that the convenience and efficiency of fire prediction are effectively improved, and the problem that existing fire prediction is easily interfered by the environment and misinformation is generated is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of fire prediction, and particularly relates to a fire prediction method and system based on fire alarm equipment on an offshore platform. Background Art

[0002] Offshore fires have always been a major threat in the safety field of wind power facilities due to their strong suddenness, fast spread speed, and great difficulty in extinguishing. With the increasing complexity of the construction of wind power facilities, the fire risk has increased significantly, but there are still many defects in the existing prediction technologies, making it difficult to meet the actual needs.

[0003] In the prior art, it mostly relies on the monitoring of single parameters such as smoke sensors and temperature sensors. However, in the initial stage of a fire, there is often a lack of obvious smoke or sudden temperature change, resulting in a high false negative rate. For example, a smoke sensor can only trigger an alarm when the fire develops to the thick smoke stage, missing the best opportunity for fire extinguishing; while a temperature sensor is greatly affected by the environment and is prone to false alarms. Therefore, there is an urgent need for a fire prediction method and system based on fire alarm equipment on an offshore platform. Summary of the Invention

[0004] The present invention provides a fire prediction method and system based on fire alarm equipment on an offshore platform to solve the technical problem that existing fire predictions are easily affected by the environment and generate false alarms.

[0005] In a first aspect, the present invention provides a fire prediction method based on fire alarm equipment on an offshore platform, including:

[0006] Obtaining real-time temperature data of each preset position in a target area based on the fire alarm equipment on the offshore platform;

[0007] According to each real-time temperature data, determining a temperature anomaly area in the target area by using a preset area division strategy, and obtaining an infrared image and a visible light image of the temperature anomaly area within a preset time period;

[0008] Fusing a certain infrared image and a certain visible light image at the same moment according to a preset adversarial network to obtain fused images at different moments, and sorting the fused images based on the time sequence to obtain a fused image sequence;

[0009] Selecting at least one target fused image from the fused image sequence according to a preset image selection strategy, and inputting the at least one target fused image into a preset image anomaly recognition model, and the image anomaly recognition model outputs a recognition result corresponding to the at least one target fused image;

[0010] Generating fire prediction information for the temperature anomaly area according to each recognition result by using a preset prediction strategy.

[0011] Second aspect, the present invention provides a fire prediction system based on a fire alarm device for an offshore platform, including:

[0012] An acquisition module configured to acquire real-time temperature data of each preset position in a target area based on a fire alarm device for an offshore platform;

[0013] A determination module configured to determine a temperature anomaly area in the target area according to each real-time temperature data by using a preset area division strategy, and acquire an infrared image and a visible light image of the temperature anomaly area within a preset time period;

[0014] A fusion module configured to fuse a certain infrared image and a certain visible light image at the same moment according to a preset adversarial network to obtain fusion images at different moments, and sort the fusion images based on the time sequence to obtain a fusion image sequence;

[0015] An output module configured to select at least one target fusion image from the fusion image sequence according to a preset image selection strategy, and input the at least one target fusion image into a preset image anomaly recognition model, and the image anomaly recognition model outputs a recognition result corresponding to the at least one target fusion image;

[0016] A generation module configured to generate fire prediction information of the temperature anomaly area according to each recognition result by using a preset prediction strategy.

[0017] Third aspect, there is provided an electronic device, which includes: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the steps of the fire prediction method based on a fire alarm device for an offshore platform according to any embodiment of the present invention.

[0018] Fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program instructions are executed by a processor, the processor is enabled to execute the steps of the fire prediction method based on a fire alarm device for an offshore platform according to any embodiment of the present invention.

[0019] The fire prediction method and system based on the fire alarm equipment of an offshore platform according to the present application determine the temperature abnormal area in the target area through a preset area division strategy, can relatively accurately shorten the area to be predicted, thereby reducing the amount of data required for subsequent fire prediction, and select at least one target fusion image from the fused image sequence according to a preset image selection strategy, and input the at least one target fusion image into a preset image abnormality recognition model, output the recognition result corresponding to the at least one target fusion image, and generate fire prediction information for the temperature abnormal area by using a preset prediction strategy according to each recognition result, can estimate the risk of subsequent fire based on the number of items with potential fire hazards for a continuous period of time, thereby effectively improving the convenience and efficiency of fire prediction, and solving the problem that the existing fire prediction is easily interfered by the environment and generates false alarms. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 It is a flowchart of a fire prediction method based on the fire alarm equipment of an offshore platform provided by an embodiment of the present invention;

[0022] Figure 2 It is a structural block diagram of a fire prediction system based on the fire alarm equipment of an offshore platform provided by an embodiment of the present invention;

[0023] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following clearly and completely describes the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] Please refer to Figure 1 , which shows a flowchart of a fire prediction method based on the fire alarm equipment of an offshore platform according to the present application.

[0026] As Figure 1As shown in the figure, the fire prediction method based on the fire alarm equipment on the offshore platform specifically includes the following steps:

[0027] Step S101, obtaining the real-time temperature data of each preset position in the target area based on the fire alarm equipment on the offshore platform.

[0028] Step S102, according to each real-time temperature data, determining the temperature anomaly area in the target area by using a preset area division strategy, and obtaining the infrared image and visible light image of the temperature anomaly area within a preset time period.

[0029] In this step, a position distribution map is constructed according to the coordinate information of each preset position on the electronic map, and at least one real-time temperature data is marked on the position distribution map to generate a real-time temperature distribution map;

[0030] In the real-time temperature distribution map, at least one target real-time temperature greater than the preset temperature threshold is screened out, and at least one target real-time temperature is connected end to end to obtain a temperature anomaly area.

[0031] Step S103, fusing a certain infrared image and a certain visible light image at the same moment according to a preset adversarial network to obtain fused images at different moments, and sorting the fused images based on the time sequence to obtain a fused image sequence.

[0032] In this step, a certain infrared image and a certain visible light image at the same moment are input into the generation model together in the cascade channel, and the generation model creates a fused image as the output; the discriminant model distinguishes the real visible light, infrared image and fused image, and continuously updates the fused image.

[0033] Step S104, selecting at least one target fused image from the fused image sequence according to a preset image selection strategy, and inputting the at least one target fused image into a preset image anomaly recognition model, and the image anomaly recognition model outputs a recognition result corresponding to the at least one target fused image.

[0034] In this step, the first fused image in the fused image sequence is defined as the first fused image, and the second fused image corresponding to the first fused image is sequentially searched in the fused image sequence based on the time sequence, where the similarity between the second fused image and the first fused image is less than the preset threshold;

[0035] And the third fused image corresponding to the second fused image is searched in the fused image sequence until all searches of the fused image sequence are completed to obtain at least one target fused image, where the similarity between the second fused image and the third fused image is less than the preset threshold.

[0036] It should be noted that each historical fusion image is subjected to an overlapping cropping operation to obtain multiple historical target fusion images. Among them, the cropping step size is set to 14, and the size of the uniformly cropped image block is 120*120;

[0037] The labeling software labelImg labels the first object without fire hazards and the second object with fire hazards in multiple historical target fusion images through rectangular frames to obtain labeling information;

[0038] Multiple historical target fusion images and corresponding labeling information are input into a preset neural network model for iterative training to obtain an image anomaly recognition model. At least one target fusion image is input into the preset image anomaly recognition model, and the image anomaly recognition model outputs a recognition result corresponding to at least one target fusion image.

[0039] Step S105, according to each recognition result, use a preset prediction strategy to generate fire prediction information for the temperature anomaly area.

[0040] In this step, the recognition results are sorted according to the acquisition time corresponding to at least one target fusion image to obtain a recognition result sequence;

[0041] Judge the recognition result sequence to determine whether the number of second items with fire hazards in each recognition result is decreasing based on the acquisition time order;

[0042] If not, generate prediction information that there is a fire in the temperature anomaly area, otherwise generate prediction information that there is no fire in the temperature anomaly area.

[0043] In summary, the method of the present application determines the temperature anomaly area in the target area through a preset area division strategy, can more accurately shorten the area to be predicted, thereby reducing the amount of data required for subsequent fire prediction, and selects at least one target fusion image from the fusion image sequence according to the preset image selection strategy, and inputs at least one target fusion image into the preset image anomaly recognition model, outputs a recognition result corresponding to at least one target fusion image, and according to each recognition result, uses a preset prediction strategy to generate fire prediction information for the temperature anomaly area, and can estimate the risk of subsequent fires based on the number of items with fire hazards over a continuous period of time, thereby effectively improving the convenience and efficiency of fire prediction.

[0044] Please refer to Figure 2 , which shows a structural block diagram of a fire prediction system based on a fire alarm device on an offshore platform of the present application.

[0045] As Figure 2As shown in the figure, the fire prediction system 200 includes an acquisition module 210, a determination module 220, a fusion module 230, an output module 240, and a generation module 250.

[0046] Among them, the acquisition module 210 is configured to obtain real-time temperature data of each preset position in the target area based on the fire alarm equipment of the offshore platform; the determination module 220 is configured to determine the temperature anomaly area in the target area according to each real-time temperature data by using a preset area division strategy, and obtain the infrared image and visible light image of the temperature anomaly area within a preset time period; the fusion module 230 is configured to fuse a certain infrared image and a certain visible light image at the same moment according to a preset adversarial network to obtain fusion images at different moments, and sort the fusion images based on the time sequence to obtain a fusion image sequence; the output module 240 is configured to select at least one target fusion image from the fusion image sequence according to a preset image selection strategy, and input the at least one target fusion image into a preset image anomaly recognition model, and the image anomaly recognition model outputs a recognition result corresponding to the at least one target fusion image; the generation module 250 is configured to generate fire prediction information of the temperature anomaly area according to each recognition result by using a preset prediction strategy.

[0047] It should be understood that Figure 2 The modules described in Figure 1 correspond to the respective steps in the method described in the reference Figure 2 Therefore, the operations, features, and corresponding technical effects described above for the method also apply to

[0048] In some other embodiments, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored. When the program instructions are executed by a processor, the processor executes the fire prediction method based on the fire alarm equipment of the offshore platform in any of the above method embodiments;

[0049] As an implementation manner, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are set as:

[0050] Obtain real-time temperature data of each preset position in the target area based on the fire alarm equipment of the offshore platform;

[0051] According to each real-time temperature data, use a preset area division strategy to determine the temperature anomaly area in the target area, and obtain the infrared image and visible light image of the temperature anomaly area within a preset time period;

[0052] Fuse a certain infrared image and a certain visible light image at the same moment according to a preset adversarial network to obtain fused images at different moments, and sort the fused images based on the time sequence to obtain a fused image sequence;

[0053] Select at least one target fused image from the fused image sequence according to a preset image selection strategy, and input the at least one target fused image into a preset image anomaly recognition model, and the image anomaly recognition model outputs a recognition result corresponding to the at least one target fused image;

[0054] Generate fire prediction information for the temperature anomaly area according to each recognition result by using a preset prediction strategy.

[0055] A computer-readable storage medium may include a storage program area and a storage data area. Among them, the storage program area can store an operating system and application programs required for at least one function; the storage data area can store data created according to the use of the fire prediction system based on the fire alarm equipment of the offshore platform. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the computer-readable storage medium may optionally include a memory remotely provided with respect to the processor, and these remote memories may be connected to the fire prediction system based on the fire alarm equipment of the offshore platform through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0056] Figure 3 It is a schematic structural diagram of the electronic device provided by the embodiment of the present invention, as Figure 3 shown. The device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330, and the output device 340 may be connected through a bus or other means, Figure 3 and taking the connection through the bus as an example. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running non-volatile software programs, instructions, and modules stored in the memory 320, that is, implements the fire prediction method based on the fire alarm equipment of the offshore platform in the above method embodiment. The input device 330 can receive input digital or character information, and generate key signal inputs related to user settings and function controls of the fire prediction system based on the fire alarm equipment of the offshore platform. The output device 340 may include a display device such as a display screen.

[0057] The above electronic device can execute the method provided by the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference may be made to the method provided by the embodiments of the present invention.

[0058] As an implementation manner, the above electronic device is applied to a fire prediction system based on a fire alarm device on an offshore platform, and is used for a client, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0059] Obtain real-time temperature data of each preset position in the target area based on the fire alarm device on the offshore platform;

[0060] According to each real-time temperature data, determine the temperature anomaly area in the target area by using a preset area division strategy, and obtain the infrared image and visible light image of the temperature anomaly area within a preset time period;

[0061] Fuse a certain infrared image and a certain visible light image at the same moment according to a preset adversarial network to obtain fused images at different moments, and sort the fused images based on the time sequence to obtain a fused image sequence;

[0062] Select at least one target fused image from the fused image sequence according to a preset image selection strategy, and input the at least one target fused image into a preset image anomaly recognition model, and the image anomaly recognition model outputs a recognition result corresponding to the at least one target fused image;

[0063] Generate fire prediction information for the temperature anomaly area according to each recognition result by using a preset prediction strategy.

[0064] Through the description of the above implementation manners, those skilled in the art can clearly understand that each implementation manner can be realized by means of software plus a necessary general hardware platform, and of course, it can also be realized by hardware. Based on such an understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A fire prediction method based on offshore platform fire alarm equipment, characterized in that: include: Based on the offshore platform fire alarm equipment, real-time temperature data of each preset location in the target area is obtained; According to each real-time temperature data, a preset area division strategy is adopted to determine the temperature abnormal area in the target area, and an infrared image and a visible light image of the temperature abnormal area within a preset time period are obtained; According to the preset adversarial network, an infrared image and a visible light image at the same time are fused to obtain fused images at different times, and each fused image is sorted based on the time sequence to obtain a fused image sequence; Selecting at least one target fused image from the fused image sequence according to a preset image selection strategy, and inputting the at least one target fused image into a preset image anomaly recognition model, wherein the image anomaly recognition model outputs a recognition result corresponding to the at least one target fused image; According to each recognition result, a preset prediction strategy is adopted to generate fire prediction information of the temperature abnormality area.

2. A fire prediction method based on offshore platform fire alarm equipment according to claim 1, characterized in that: The method of determining the abnormal temperature area in the target area by using a preset area division strategy according to each real-time temperature data includes: Constructing a location distribution map according to the coordinate information of each preset location on the electronic map, and marking the at least one real-time temperature data on the location distribution map to generate a real-time temperature distribution map; At least one target real-time temperature greater than a preset temperature threshold is screened out in the real-time temperature distribution map, and the at least one target real-time temperature is connected end to end to obtain a temperature abnormality area.

3. A fire prediction method based on offshore platform fire alarm equipment according to claim 1, characterized in that: The method of fusing an infrared image and a visible light image at the same time according to a preset adversarial network to obtain fused images at different times includes: An infrared image and a visible light image at the same time are input into the generative model together in a cascade channel, and the generative model creates a fused image as output; The discriminant model distinguishes the real visible light and infrared images and the fused images, and continuously updates the fused images.

4. A fire prediction method based on offshore platform fire alarm equipment according to claim 1, characterized in that: The selecting at least one target fused image from the fused image sequence according to a preset image selection strategy comprises: The first fused image in the fused image sequence is defined as a first fused image, and a second fused image corresponding to the first fused image is sequentially searched in the fused image sequence based on a time-selected order, wherein the similarity between the second fused image and the first fused image is less than a preset threshold; And searching for a third fused image corresponding to the second fused image in the fused image sequence until all searches for the fused image sequence are completed to obtain at least one target fused image, wherein the similarity between the second fused image and the third fused image is less than a preset threshold.

5. A fire prediction method based on offshore platform fire alarm equipment according to claim 1, characterized in that: Before inputting the at least one target fused image into a preset image anomaly recognition model, the method further includes: Each historical fusion image is overlapped and cropped to obtain multiple historical target fusion images. The cropping step size is set to 14, and the image block size after uniform cropping is 120*120; The labeling software labelImg labels the first object without fire hazard and the second object with fire hazard in the fusion images of multiple historical targets through rectangular frames to obtain labeling information; Multiple historical target fusion images and corresponding annotation information are input into the preset neural network model for iterative training to obtain an image anomaly recognition model.

6. A fire prediction method based on offshore platform fire alarm equipment according to claim 1, characterized in that: The method of generating fire prediction information of the abnormal temperature area by using a preset prediction strategy according to each recognition result includes: Sorting the recognition results according to the acquisition time corresponding to the at least one target fused image to obtain a recognition result sequence; Determining the sequence of identification results whether the number of second objects with fire hazards in each identification result is decreasing based on the order of collection time; If not, prediction information indicating that a fire exists in the abnormal temperature region is generated; otherwise, prediction information indicating that a fire does not exist in the abnormal temperature region is generated.

7. A fire prediction system based on offshore platform fire alarm equipment, characterized in that: include: An acquisition module configured to acquire real-time temperature data of each preset location in the target area based on the offshore platform fire alarm equipment; A determination module is configured to determine the temperature abnormality area in the target area according to each real-time temperature data by adopting a preset area division strategy, and obtain an infrared image and a visible light image of the temperature abnormality area within a preset time period; A fusion module is configured to fuse an infrared image and a visible light image at the same time according to a preset adversarial network to obtain fused images at different times, and to sort the fused images based on a time sequence to obtain a fused image sequence; an output module, configured to select at least one target fused image from the fused image sequence according to a preset image selection strategy, and input the at least one target fused image into a preset image anomaly recognition model, wherein the image anomaly recognition model outputs a recognition result corresponding to the at least one target fused image; The generation module is configured to generate fire prediction information of the temperature abnormality area according to each recognition result and using a preset prediction strategy.

8. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images