An alarm method, device, equipment and medium for monitoring fire in a computer room

Abstract

The present application relates to an alarm method, device, equipment and medium for fire monitoring in a computer room, and to the field of fire alarm. The method includes obtaining a three-dimensional model of a computer room, multiple infrared images in the computer room, and airflow information corresponding to each of multiple preset positions in the computer room, drawing an air circulation diagram in the computer room based on the airflow information and the three-dimensional model, determining the circulation abnormality area and the circulation abnormality score of each circulation abnormality area from the air circulation diagram, segmenting a sub-infrared image of each circulation abnormality area from the infrared image, determining the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score, and alarming the target circulation abnormality area whose probability reaches a preset probability threshold. The present application has the effect of facilitating alarm and early warning of the initial area before the fire occurs in the computer room and timely discovering the location of the fire that is about to occur in the computer room.

Description

Technical Field

[0001] The present application relates to the field of fire alarm, and in particular to an alarm method, device, equipment and medium for fire monitoring in a computer room. Background Art

[0002] With the development and popularization of technologies such as cloud computing and the Internet of Things, the construction of servers and safe operation and maintenance such as heat dissipation have become an important issue. Currently, the main way to ensure the constant temperature and humidity in the computer room is to build a computer room and place multiple server devices in the computer room, and install equipment such as air conditioners in the computer room. Since the server generates a lot of heat when running, if the temperature rises due to equipment failure such as air conditioners, the risk of fire will increase.

[0003] At present, the main method is to install temperature sensors in the computer room to monitor temperature changes to determine whether a fire has occurred. However, this method has a certain hysteresis and is not convenient for alarming the initial abnormalities before a fire occurs in the computer room. Therefore, how to achieve early regional alarm and early warning before a fire occurs in the computer room and timely discover the location of a fire in the computer room has become a problem. Summary of the invention

[0004] In order to facilitate the alarm and early warning of the initial area before a fire occurs in a computer room and to promptly discover the location where a fire is about to occur in the computer room, the present application provides an alarm method, device, equipment and medium for computer room fire monitoring.

[0005] In a first aspect, the present application provides an alarm method for fire monitoring in a computer room, which adopts the following technical solution:

[0006] An alarm method for monitoring fire in a computer room, comprising:

[0007] Acquire a three-dimensional model of a computer room, a plurality of infrared images in the computer room, and airflow information corresponding to a plurality of preset positions in the computer room, wherein the airflow information includes wind speed and wind direction, and a plurality of server devices are installed in the computer room;

[0008] Drawing an air circulation diagram in the computer room based on the air flow information and the three-dimensional model, wherein the air circulation diagram records the air flow information at any position in the three-dimensional model;

[0009] Determine the abnormal circulation area and the abnormal circulation score of each abnormal circulation area from the air circulation map;

[0010] Segmenting a sub-infrared image of each circulation abnormality region from the infrared image;

[0011] Determine the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score;

[0012] Alarms are issued for target flow abnormal areas whose probability reaches the preset probability threshold.

[0013] By adopting the above technical solution, a three-dimensional model, an infrared image and airflow information of multiple preset positions of the computer room are obtained, so that an accurate air circulation map can be drawn according to the airflow information and the three-dimensional model. The air circulation map records the air circulation conditions at any position in the computer room, that is, the wind speed value and wind direction at any position, so that the circulation abnormality area and the circulation abnormality score of each circulation abnormality area with respect to air circulation can be accurately determined from the air circulation map. The infrared image records the temperature conditions in the computer room. After determining the infrared image, a sub-infrared image of each circulation abnormality area can be segmented according to the position of the circulation abnormality area. The probability of fire in each circulation abnormality area is determined based on the sub-infrared image and the circulation abnormality score, that is, it is more accurate to comprehensively determine the probability of fire in each circulation abnormality area based on the temperature and air circulation conditions. The preset probability threshold is used as the dividing point of whether the probability of fire is too high. Therefore, an alarm is issued for the target circulation abnormality area that reaches the preset probability threshold, so that the position where the fire is about to occur in the computer room can be discovered in time, and the probability of fire in the circulation abnormality area is determined based on the comprehensive analysis of air circulation and temperature, so as to achieve the effect of facilitating the alarm and early warning of the initial area before the fire occurs in the computer room.

[0014] In another possible implementation, drawing an air circulation diagram in the computer room based on the airflow information and the three-dimensional model includes:

[0015] Determine a first grayscale value corresponding to each preset position based on the wind speed value of each preset position;

[0016] Mapping the first grayscale value corresponding to each preset position to the corresponding preset position in the three-dimensional model;

[0017] and determining a flow arrow corresponding to the wind direction according to the wind direction, and mapping the flow arrow to a corresponding preset position;

[0018] Performing simulation based on the three-dimensional model and the airflow information of each preset position, obtaining the wind speed value and wind direction of the remaining positions in the three-dimensional model except the preset position, and determining the first gray value and flow arrow of each remaining position;

[0019] The first grayscale value and flow arrow of each preset position and the first grayscale value and flow arrow of each remaining position are mapped in the three-dimensional model to obtain the air circulation diagram.

[0020] In another possible implementation, determining the abnormal circulation area and the abnormal circulation score of each abnormal circulation area from the air circulation map includes:

[0021] Determine the pointing angle of each flow arrow in the air circulation diagram;

[0022] Scanning the air circulation diagram according to a preset range and a preset step length to obtain a plurality of areas to be tested, wherein the preset range is a three-dimensional area;

[0023] Determine an initial anomaly score for each area to be tested, where the initial anomaly score is determined by a pointing angle and a first grayscale value in each area to be tested;

[0024] Based on whether the server device exists in each area to be tested, the initial anomaly score of each area to be tested is corrected to obtain the circulation anomaly score;

[0025] The area to be tested whose circulation anomaly score reaches a preset score threshold is determined as the circulation anomaly area.

[0026] In another possible implementation, determining the initial anomaly score of each area to be tested includes any one of the following:

[0027] Determine the number of pointing angles and the first gray value average value in each area to be tested, and determine an initial abnormality score for each area to be tested based on the number of pointing angles and the first gray value average value;

[0028] The directional angles in each area to be tested are fitted to obtain the air circulation path in each area to be tested, the curvature of the air circulation path and the average first grayscale value in each area to be tested are determined, and the initial abnormality score of each area to be tested is determined based on the curvature and the average first grayscale value.

[0029] In another possible implementation, the step of correcting the initial anomaly score of each area to be tested based on whether the server device exists in each area to be tested to obtain the circulation anomaly score includes:

[0030] If there is no server device in any of the tested areas, determine the center position of any of the tested areas, calculate the distance from the center position to each server device, and determine the shortest distance, and correct the initial anomaly score based on the shortest distance to obtain the circulation anomaly score;

[0031] If there is a server device in any of the areas to be tested, the volume ratio of the server device in any of the areas to be tested is determined, and the initial anomaly score is corrected based on the volume ratio to obtain a circulation anomaly score.

[0032] In another possible implementation, determining the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score includes:

[0033] Determine the average temperature of each circulation abnormality area based on the sub-infrared image;

[0034] Converting the sub-infrared image into a grayscale image and obtaining a second grayscale value of each position in the sub-infrared image;

[0035] Mapping the grayscale image in a preset plane coordinate system to obtain a first coordinate point of each second grayscale value;

[0036] Mapping the abnormal circulation area in the preset plane coordinate system to obtain a second coordinate point of each first gray value;

[0037] Adding the first grayscale value and the second grayscale value that are the same at the first coordinate point and the second coordinate point to obtain a third grayscale value for each preset position and the remaining positions in each abnormal circulation area;

[0038] averaging the third grayscale values ​​of each preset position and the remaining positions to obtain an average third grayscale value;

[0039] Determine the temperature and heat anomaly score of each circulation anomaly area based on the temperature average value, the third gray value average value and the corresponding coefficients;

[0040] The probability of fire occurring in each circulation abnormality area is determined based on the temperature and heat abnormality score and the circulation abnormality score.

[0041] In another possible implementation, a plurality of sound and light alarm devices are provided in the machine room, and the alarm is given to the target flow abnormal area whose probability reaches a preset probability threshold, including:

[0042] Calculate the distance from any target abnormal circulation area to each sound and light alarm device, and determine the nearest sound and light alarm device corresponding to any target abnormal circulation area;

[0043] Controlling the nearest sound and light alarm device corresponding to any target abnormal circulation area to operate;

[0044] Acquire a monitoring image covering any target abnormal circulation area, and mark any target abnormal circulation area in the monitoring image to obtain a marked monitoring image;

[0045] The marked monitoring image is sent to the terminal device of the administrator.

[0046] In a second aspect, the present application provides an alarm device for monitoring fire in a computer room, which adopts the following technical solution:

[0047] An alarm device for monitoring fire in a machine room, comprising:

[0048] A data acquisition module, used to acquire a three-dimensional model of a computer room, a plurality of infrared images in the computer room, and airflow information corresponding to each of a plurality of preset positions in the computer room, wherein the airflow information includes wind speed and wind direction, and a plurality of server devices are installed in the computer room;

[0049] A circulation diagram drawing module, used for drawing an air circulation diagram in the computer room based on the air flow information and the three-dimensional model, wherein the air circulation diagram records the air flow information at any position in the three-dimensional model;

[0050] A score determination module, used to determine the circulation abnormality area and the circulation abnormality score of each circulation abnormality area from the air circulation map;

[0051] An image segmentation module, used for segmenting a sub-infrared image of each abnormal circulation area from the infrared image;

[0052] A probability determination module, used to determine the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score;

[0053] The alarm module is used to alarm the target flow abnormal area whose probability reaches a preset probability threshold.

[0054] By adopting the above technical solution, the data acquisition module obtains the three-dimensional model, infrared image and airflow information of multiple preset positions of the computer room, so that the circulation map drawing module can subsequently draw an accurate air circulation map based on the airflow information and the three-dimensional model. The air circulation map records the air circulation conditions at any position in the computer room, that is, the wind speed value and wind direction at any position. The score determination module can accurately determine the circulation abnormality area and the circulation abnormality score of each circulation abnormality area in terms of air circulation from the air circulation map. The infrared image records the temperature conditions in the computer room. After determining the infrared image, the image segmentation module can segment each circulation abnormality area according to the position of the circulation abnormality area. The probability determination module determines the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score. That is, it is more accurate to determine the probability of fire in each circulation abnormality area based on the temperature and air circulation conditions. The preset probability threshold is used as the dividing point whether the probability of fire is too high. The alarm module alarms the target circulation abnormality area whose probability reaches the preset probability threshold, so as to timely discover the location where the fire is about to occur in the computer room, and determine the probability of fire in the circulation abnormality area based on a comprehensive analysis of air circulation and temperature, so as to achieve the effect of facilitating the alarm and early warning of the initial area before the fire occurs in the computer room.

[0055] In another possible implementation, when the air flow diagram drawing module draws the air flow diagram in the computer room based on the air flow information and the three-dimensional model, it is specifically used to:

[0056] Determine a first grayscale value corresponding to each preset position based on the wind speed value of each preset position;

[0057] Mapping the first grayscale value corresponding to each preset position to the corresponding preset position in the three-dimensional model;

[0058] and determining a flow arrow corresponding to the wind direction according to the wind direction, and mapping the flow arrow to a corresponding preset position;

[0059] Performing simulation based on the three-dimensional model and the airflow information of each preset position, obtaining the wind speed value and wind direction of the remaining positions in the three-dimensional model except the preset position, and determining the first gray value and flow arrow of each remaining position;

[0060] The first grayscale value and flow arrow of each preset position and the first grayscale value and flow arrow of each remaining position are mapped in the three-dimensional model to obtain the air circulation diagram.

[0061] In another possible implementation, when the score determination module determines the abnormal circulation area and the abnormal circulation score of each abnormal circulation area from the air circulation map, it is specifically used to:

[0062] Determine the pointing angle of each flow arrow in the air circulation diagram;

[0063] Scanning the air circulation diagram according to a preset range and a preset step length to obtain a plurality of areas to be tested, wherein the preset range is a three-dimensional area;

[0064] Determine an initial anomaly score for each area to be tested, where the initial anomaly score is determined by a pointing angle and a first grayscale value in each area to be tested;

[0065] Based on whether the server device exists in each area to be tested, the initial anomaly score of each area to be tested is corrected to obtain the circulation anomaly score;

[0066] The area to be tested whose circulation anomaly score reaches a preset score threshold is determined as the circulation anomaly area.

[0067] In another possible implementation, the score determination module is specifically used for any of the following when determining the initial abnormality score of each area to be tested:

[0068] Determine the number of pointing angles and the first gray value average value in each area to be tested, and determine an initial abnormality score for each area to be tested based on the number of pointing angles and the first gray value average value;

[0069] The directional angles in each area to be tested are fitted to obtain the air circulation path in each area to be tested, the curvature of the air circulation path and the average first grayscale value in each area to be tested are determined, and the initial abnormality score of each area to be tested is determined based on the curvature and the average first grayscale value.

[0070] In another possible implementation, when the score determination module corrects the initial anomaly score of each area to be tested based on whether the server device exists in each area to be tested to obtain the circulation anomaly score, it is specifically used to:

[0071] If there is no server device in any of the tested areas, determine the center position of any of the tested areas, calculate the distance from the center position to each server device, and determine the shortest distance, and correct the initial anomaly score based on the shortest distance to obtain the circulation anomaly score;

[0072] If there is a server device in any of the areas to be tested, the volume ratio of the server device in any of the areas to be tested is determined, and the initial anomaly score is corrected based on the volume ratio to obtain a circulation anomaly score.

[0073] In another possible implementation, when determining the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score, the probability determination module is specifically used to:

[0074] Determine the average temperature of each circulation abnormality area based on the sub-infrared image;

[0075] Converting the sub-infrared image into a grayscale image and obtaining a second grayscale value of each position in the sub-infrared image;

[0076] Mapping the grayscale image in a preset plane coordinate system to obtain a first coordinate point of each second grayscale value;

[0077] Mapping the abnormal circulation area in the preset plane coordinate system to obtain a second coordinate point of each first gray value;

[0078] Adding the first grayscale value and the second grayscale value that are the same at the first coordinate point and the second coordinate point to obtain a third grayscale value for each preset position and the remaining positions in each abnormal circulation area;

[0079] averaging the third grayscale values ​​of each preset position and the remaining positions to obtain an average third grayscale value;

[0080] Determine the temperature and heat anomaly score of each circulation anomaly area based on the temperature average value, the third gray value average value and the corresponding coefficients;

[0081] The probability of fire occurring in each circulation abnormality area is determined based on the temperature and heat abnormality score and the circulation abnormality score.

[0082] In another possible implementation, a plurality of sound and light alarm devices are provided in the machine room, and when the alarm module alarms the target flow abnormal area whose probability reaches a preset probability threshold, it is specifically used to include:

[0083] Calculate the distance from any target abnormal circulation area to each sound and light alarm device, and determine the nearest sound and light alarm device corresponding to any target abnormal circulation area;

[0084] Controlling the nearest sound and light alarm device corresponding to any target abnormal circulation area to operate;

[0085] Acquire a monitoring image covering any target abnormal circulation area, and mark any target abnormal circulation area in the monitoring image to obtain a marked monitoring image;

[0086] The marked monitoring image is sent to the terminal device of the administrator.

[0087] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0088] An electronic device, comprising:

[0089] at least one processor;

[0090] Memory;

[0091] At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one is configured to: execute an alarm method for fire monitoring in a computer room as shown in any possible implementation of the first aspect.

[0092] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0093] A computer-readable storage medium, when the computer program is executed in a computer, causes the computer to execute an alarm method for fire monitoring in a computer room as described in any one of the first aspects.

[0094] In summary, the present application includes at least one of the following beneficial technical effects:

[0095] The three-dimensional model, infrared image and airflow information of multiple preset positions of the computer room are obtained, so that an accurate air circulation map can be drawn according to the airflow information and the three-dimensional model. The air circulation map records the air circulation conditions at any position in the computer room, that is, the wind speed value and wind direction at any position, so that the circulation abnormality area and the circulation abnormality score of each circulation abnormality area in terms of air circulation can be accurately determined from the air circulation map. The infrared image records the temperature conditions in the computer room. After determining the infrared image, the sub-infrared image of each circulation abnormality area can be segmented according to the position of the circulation abnormality area. The probability of fire in each circulation abnormality area is determined based on the sub-infrared image and the circulation abnormality score, that is, it is more accurate to comprehensively determine the probability of fire in each circulation abnormality area based on the temperature and air circulation conditions. The preset probability threshold is used as the dividing point of whether the probability of fire is too high. Therefore, an alarm is issued for the target circulation abnormality area that reaches the preset probability threshold, so that the location where the fire is about to occur in the computer room can be discovered in time, and the probability of fire in the circulation abnormality area is determined based on the comprehensive analysis of air circulation and temperature, so as to achieve the effect of facilitating the alarm and early warning of the initial area before the fire occurs in the computer room. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] Figure 1 It is a flow chart of an alarm method for fire monitoring in a computer room according to an embodiment of the present application.

[0097] Figure 2 It is a structural schematic diagram of an alarm device for fire monitoring in a computer room according to an embodiment of the present application.

[0098] Figure 3 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0099] The present application is further described in detail below in conjunction with the accompanying drawings.

[0100] After reading this specification, those skilled in the art may make modifications to this embodiment without any creative contribution as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0101] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0102] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0103] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0104] The embodiment of the present application provides an alarm method for fire monitoring in a computer room, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. Figure 1 As shown, the method includes step S101, step S102, step S103, step S104, step S105 and step S106, wherein:

[0105] S101, obtaining a three-dimensional model of a computer room, a plurality of infrared images in the computer room, and airflow information corresponding to a plurality of preset positions in the computer room.

[0106] The airflow information includes wind speed and wind direction. Multiple server devices are installed in the computer room.

[0107] For the embodiment of the present application, the three-dimensional model of the computer room can be modeled by the staff in advance through the modeling software according to the distribution of the server equipment, the distribution of the air conditioning equipment and other facilities in the computer room to obtain a three-dimensional model, and then stored in the local storage medium in the electronic device or in the cloud server, so as to facilitate the electronic device to obtain the three-dimensional model of the computer room. The staff can install multiple infrared temperature measurement cameras in the computer room in advance, so that the infrared images of various places in the computer room can be collected in all directions, and then it is convenient to determine the temperature of various places in the computer room according to the infrared images later. The infrared temperature measurement camera is connected to the electronic device through a wire, so that the electronic device can obtain the infrared image of the infrared temperature measurement camera. In order to facilitate the air circulation in the computer room, the staff can determine multiple preset positions in advance according to the distribution of other facilities such as server equipment in the computer room, and then install multiple high-sensitivity anemometers and wind speed and wind direction sensors at the preset positions, so as to collect the airflow information of multiple preset positions, that is, the wind speed value and wind direction of each preset position. The electronic device is connected to each anemometer and wind speed and wind direction sensor through a wire, so as to facilitate the acquisition of the airflow information of each preset position.

[0108] S102, drawing an air circulation diagram in the computer room based on the airflow information and the three-dimensional model.

[0109] Among them, the air circulation map records the airflow information at any position in the three-dimensional model.

[0110] For the embodiment of the present application, after the electronic device obtains the airflow information of each preset position, it can accurately draw an air circulation diagram in the computer room in combination with the three-dimensional model of the computer room, thereby facilitating subsequent analysis of the locations where fires may occur in the computer room based on the air circulation diagram.

[0111] S103, determining the abnormal circulation area and the abnormal circulation score of each abnormal circulation area from the air circulation map.

[0112] For the embodiment of the present application, after the electronic device determines the air circulation diagram, since the air circulation diagram records and displays the air circulation conditions at any location in the machine room, the electronic device can accurately determine the abnormal circulation area and the abnormal circulation score of each abnormal circulation area from the air circulation diagram.

[0113] S104, segmenting a sub-infrared image of each abnormal circulation area from the infrared image.

[0114] For the embodiment of the present application, after the electronic device obtains the infrared image covering all positions in the computer room, since the abnormal circulation area is determined, a preset three-dimensional coordinate system can be stored in the electronic device, and then the electronic device maps the three-dimensional model of the computer room in the preset three-dimensional coordinate system, and then determines the coordinate points of the abnormal circulation area. The range of the infrared image collected by each infrared temperature measuring camera is fixed, so the staff can set the coordinate points of the collection range of each infrared temperature measuring camera in the preset three-dimensional coordinate system in the electronic device in advance. The electronic device can determine the sub-infrared image of each abnormal circulation area by segmenting the infrared image according to the coordinate points of the abnormal circulation area and the coordinate points corresponding to each infrared image, thereby facilitating the subsequent analysis of the temperature in each abnormal circulation area.

[0115] S105: Determine the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score.

[0116] For the embodiment of the present application, after the electronic device determines the sub-infrared image, the sub-infrared image represents the temperature height in the circulation abnormality area. The temperature height represents the possibility of fire to a certain extent. The circulation abnormality score of the circulation abnormality area represents the air circulation in the area. The better the air circulation, the stronger the corresponding heat dissipation capacity, and the heat is not easy to accumulate in the area, and the smaller the possibility of fire, and vice versa. Therefore, the electronic device can accurately determine the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score.

[0117] S106, an alarm is issued for the target flow abnormality area whose probability reaches a preset probability threshold.

[0118] For the embodiment of the present application, the preset probability threshold is used as the dividing point for whether the possibility of fire is too high. After the electronic device determines each abnormal circulation area, the probability of each abnormal circulation area is compared with the preset probability, so as to determine the target abnormal circulation area whose probability reaches the preset probability threshold, that is, the area where the possibility of fire is relatively high. Then the electronic device alarms the target abnormal circulation area, so that the staff can know the location of the fire in the computer room in time, and by drawing the air circulation map, determining the abnormal circulation area, and determining the initial area before the fire occurs in the computer room according to the sub-infrared image and the abnormal circulation score, it is more convenient and accurate to make an alarm.

[0119] In a possible implementation of the embodiment of the present application, in step S102, an air circulation diagram in the computer room is drawn based on the airflow information and the three-dimensional model, specifically including step S1021 (not shown in the figure), step S1022 (not shown in the figure), step S1023 (not shown in the figure), step S1024 (not shown in the figure) and step S1025 (not shown in the figure), wherein:

[0120] S1021: Determine a first grayscale value corresponding to each preset position based on the wind speed value of each preset position.

[0121] For the embodiment of the present application, the larger the wind speed value, the stronger the air circulation capacity. Therefore, the electronic device determines the first grayscale value corresponding to each preset position according to the size of the wind speed value. To facilitate subsequent calculations, the staff can set a preset function based on the fact that the larger the wind speed value, the smaller the grayscale value, that is, the wind speed value is inversely proportional to the grayscale value. After the electronic device determines the wind speed value of each preset position, it can calculate the first grayscale value corresponding to each preset position according to the preset function.

[0122] S1022: Map the first grayscale value corresponding to each preset position to the corresponding preset position in the three-dimensional model.

[0123] For the embodiment of the present application, after the electronic device determines the first grayscale value of each preset position, it maps the first grayscale value of each preset position to the corresponding preset position in the three-dimensional model, so as to facilitate viewing the first grayscale value representing the wind speed at each preset position in the three-dimensional model, and facilitate subsequent drawing of an air circulation diagram based on the three-dimensional model. Furthermore, the electronic device can also determine the display area of ​​the grayscale value of each preset position according to the size of the first grayscale value. The smaller the first grayscale value, the larger the corresponding wind speed value, the stronger the heat dissipation capacity, and the larger the corresponding display area, indicating that the heat dissipation capacity in a certain area is greater.

[0124] S1023, and determine the flow arrow corresponding to the wind direction according to the wind direction, and map the flow arrow to the corresponding preset position.

[0125] For the embodiment of the present application, the electronic device determines a flow arrow with a consistent direction according to the wind direction of each preset position, and then the electronic device maps the flow arrow to the corresponding preset position in the three-dimensional model. The electronic device maps the first gray value and the flow arrow in the three-dimensional model so that the wind speed value and wind direction of each preset position are visualized, thereby facilitating the subsequent drawing of the air circulation diagram.

[0126] S1024, performing simulation based on the three-dimensional model and the airflow information of each preset position, obtaining the wind speed value and wind direction of the remaining positions in the three-dimensional model except the preset position, and determining the first gray value and flow arrow of each remaining position.

[0127] For the embodiment of the present application, the electronic device can input the three-dimensional model, the airflow information of each preset position, and other initial condition data into the trained network model for simulation, so as to obtain the wind speed value and wind direction of the remaining positions in the three-dimensional model except the preset position. Specifically, the network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models. Or the electronic device can upload the three-dimensional model to simulation software such as air flow or fluid analysis, set the required data and the airflow information of each preset position in the simulation software, so as to obtain the wind speed value and wind direction of the remaining positions in the three-dimensional model except the preset position. After the electronic device determines the wind speed value and wind direction of the remaining positions, the first grayscale value and flow arrow of each remaining position can be determined in the above manner. The remaining position can be any three-dimensional coordinate position except the preset position, that is, any position in the entire space of the three-dimensional model.

[0128] S1025, mapping the first grayscale value and flow arrow of each preset position and the first grayscale value and flow arrow of each remaining position in the three-dimensional model to obtain an air circulation diagram.

[0129] For the embodiment of the present application, after the electronic device determines the first grayscale value and flow arrow of each preset position, and the first grayscale value and flow arrow of the remaining positions, all of these first grayscale values ​​and flow arrows are mapped in the three-dimensional model, thereby obtaining an air circulation diagram in the computer room. It is more convenient and accurate to obtain an air circulation diagram by simulating the airflow information of multiple preset positions.

[0130] In a possible implementation of the embodiment of the present application, in step S103, the abnormal circulation area and the abnormal circulation score of each abnormal circulation area are determined from the air circulation map, specifically including step S1031 (not shown in the figure), step S1032 (not shown in the figure), step S1033 (not shown in the figure), step S1034 (not shown in the figure) and step S1035 (not shown in the figure), wherein:

[0131] S1031, determining the direction angle of each flow arrow in the air circulation diagram.

[0132] For the embodiment of the present application, after the electronic device determines the air circulation diagram, it can determine the pointing angle of each flow arrow from the air circulation diagram, for example, taking the horizontal plane or other plane as the reference plane, and then determine the angle between each flow arrow and the reference plane. Different flow arrows correspond to different wind directions, and different wind directions correspond to different reference planes. For example, in a three-dimensional coordinate system, if the flow arrow is parallel to the horizontal plane, the reference plane is a reference plane perpendicular to the horizontal plane; if the flow arrow is parallel to the vertical plane, the reference plane is a horizontal plane.

[0133] S1032, scanning the air circulation map according to a preset range and a preset step length to obtain a plurality of areas to be tested.

[0134] Among them, the preset range is a three-dimensional area.

[0135] For the embodiment of the present application, the preset range may be in the shape of a cube, and the staff may set the preset range formed by the length, width and height in advance, and the preset step length may be five centimeters, ten centimeters, etc. After the electronic device determines the preset range and the preset step length, it may perform window scanning in the air circulation map according to the preset range and the preset step length, thereby obtaining multiple areas to be tested.

[0136] S1033, determining an initial abnormality score for each area to be tested.

[0137] The initial abnormal score is determined by the pointing angle and the first grayscale value in each area to be tested.

[0138] For the embodiments of the present application, the pointing angle in each area to be tested characterizes the direction of air circulation, characterizes the air circulation capacity and heat dissipation capacity in the area to be tested, and further characterizes the degree of abnormality in the air circulation in the area to be tested. The first grayscale value characterizes the wind speed in the area to be tested. The greater the wind speed, the stronger the air circulation capacity and the heat dissipation capacity, which also characterizes the degree of abnormality in the air circulation in the area to be tested. In summary, the pointing angle and the first grayscale value are both key factors affecting the degree of abnormality in the area to be tested. Therefore, the electronic device accurately determines the initial abnormality score of each area to be tested based on the pointing angle and the first grayscale value.

[0139] S1034: Based on whether there is a server device in each area to be tested, the initial anomaly score of each area to be tested is corrected to obtain a circulation anomaly score.

[0140] For the embodiment of the present application, if there is a server device in a certain area to be tested, it means that the heat dissipated by the server device in the area to be tested is large, the possibility of fire in the area to be tested is large, and the more serious the loss when the fire occurs, the greater the corresponding degree of abnormality. If there is no server device in a certain area to be tested, it means that the possibility of fire in the area to be tested is small, the less the loss when the fire occurs, and the smaller the corresponding degree of abnormality. Therefore, the electronic device can correct the initial abnormality score according to whether there is a server device in the area to be tested, so as to obtain a more accurate and true circulation abnormality score.

[0141] S1035, determining the area to be tested whose circulation anomaly score reaches a preset score threshold as a circulation anomaly area.

[0142] For the embodiment of the present application, the larger the circulation anomaly score, the greater the probability of fire. The preset score threshold serves as the dividing point for whether the area to be tested belongs to the circulation anomaly area. Therefore, after the electronic device determines the circulation anomaly score of each area to be tested, the circulation anomaly score is compared with the preset score threshold, so as to determine the areas to be tested whose circulation anomaly scores reach the preset score threshold, and determine these areas as circulation anomaly areas. The initial anomaly value of the area to be tested is determined by the first gray value and the pointing angle, and the initial anomaly value is corrected according to the presence or absence of a server device to obtain the circulation anomaly value. Finally, it is more accurate to determine the circulation anomaly area based on the circulation anomaly value.

[0143] In a possible implementation of the embodiment of the present application, determining the initial abnormality score of each area to be tested in step S1033 specifically includes any one of step 1 and step 2:

[0144] Step 1: Determine the number of pointing angles and the average first grayscale value in each area to be tested, and determine the initial abnormality score of each area to be tested based on the number of pointing angles and the average first grayscale value.

[0145] For the embodiment of the present application, the more pointing angles there are in the area to be tested, the more it means that the air in the area to be tested is blocked by obstacles, thereby changing the direction of air flow. After the air flow is blocked, it continues to flow in multiple directions, thereby generating multiple pointing angles, which further indicates that the more chaotic the air circulation is, the easier it is for heat to accumulate at the obstacle, and the corresponding air circulation capacity is worse, the greater the probability of fire, and the greater the degree of abnormality. Therefore, the electronic device counts the pointing angles in each area to be tested to obtain the number of different angles that appear. In the air circulation diagram, each area to be tested has a first grayscale value at at least one preset position and a first grayscale value at at least one remaining position. Therefore, the electronic device calculates the average value of the first grayscale value for all the first grayscale values ​​in the area to be tested through the average value calculation formula. The larger the average value of the first grayscale value is, the smaller the wind speed value in the area to be tested is, the worse the air circulation capacity is, the worse the heat dissipation capacity is, the greater the probability of fire, and the greater the degree of abnormality. In summary, the number of pointing angles and the average first grayscale value are important factors that affect the probability of fire and the degree of abnormality in the area to be tested. The staff can set different coefficients for the number of pointing angles and the average first grayscale value in advance. After the electronic device determines the number of pointing angles and the average first grayscale value, it calls the corresponding coefficients for weighted calculation to obtain the initial abnormality score of each area to be tested. It is more accurate to determine the initial abnormality score by the number of pointing angles and the average first grayscale value.

[0146] Step 2: Fit the pointing angles in each area to be tested to obtain the air circulation path in each area to be tested, determine the curvature of the air circulation path and the average first grayscale value in each area to be tested, and determine the initial abnormality score of each area to be tested based on the curvature and the average first grayscale value.

[0147] For the embodiment of the present application, after the electronic device determines the pointing angle in each area to be tested, it can be fitted in combination with the flow arrow and the pointing angle, that is, the flow arrow is extended and connected to obtain the air flow path in the area to be tested, and then the electronic device can fit the parameter equation of the air flow path, and then calculate the curvature of the air flow path through the curvature calculation formula. The parameter equation for fitting the air flow path and the curvature calculation are both prior art and will not be repeated here. The greater the curvature, the greater the curvature of the air flow path, the greater the obstruction to the air flow, the weaker the corresponding flow capacity and heat dissipation capacity, the more serious the heat accumulation, the greater the probability of fire, and the greater the degree of abnormality. The electronic device calculates the average value of the first gray value for all the first gray values ​​in the area to be tested through the average value calculation formula. The greater the average value of the first gray value, the smaller the wind speed value in the area to be tested, the worse the air flow capacity, the worse the heat dissipation capacity, the greater the probability of fire, and the greater the degree of abnormality. In summary, the curvature of the air circulation path and the average value of the first grayscale value are important factors that affect the probability of fire and the degree of abnormality in the test area. The staff can set different coefficients for the curvature and the average value of the first grayscale value in advance. After the electronic device determines the curvature and the average value of the first grayscale value, it calls the corresponding coefficients for weighted calculation to obtain the initial abnormality score of each test area. It is also more accurate to determine the initial abnormality score by the curvature and the average value of the first grayscale value.

[0148] In other implementations, the electronic device may also determine the initial abnormality score by combining the curvature of the air circulation path, the number of directional angles, and the average value of the first grayscale value.

[0149] In a possible implementation of the embodiment of the present application, in step S1034, the initial anomaly score of each tested area is corrected based on whether there is a server device in each tested area to obtain a circulation anomaly score, which specifically includes step Sa (not shown in the figure) and step Sb (not shown in the figure), wherein:

[0150] Sa, if there is no server device in any area to be tested, then determine the center position of any area to be tested, calculate the distance from the center position to each server device, and determine the shortest distance. Based on the shortest distance, correct the initial anomaly score to obtain the circulation anomaly score.

[0151] For the embodiment of the present application, the electronic device determines whether there is a server device in any area to be tested based on the range coordinates of the server device and the range coordinates corresponding to the area to be tested. If there is no server device, the electronic device calculates the center position of the area to be tested based on the coordinates of the boundary points of the area to be tested. The center point coordinates of the cube are the average value of the vertex coordinates. There are corresponding calculation methods for calculating the center position of areas to be tested of other shapes. The center position of each server device can be set in advance in the three-dimensional model by the staff, or it can be calculated based on the coordinates of each vertex of the server device, that is, the center position of the server device and the center position of the area to be tested are used to represent the position of the server and the position of the area to be tested. The electronic device can calculate the distance from the area to be tested to each server device through the distance formula between two points in three-dimensional space. The farther the distance, the smaller the probability of a fire in the area to be tested, and the smaller the corresponding degree of abnormality. Therefore, the electronic device determines the closest distance from the test area to the nearest server device from multiple distances. The smaller the closest distance, the greater the impact and damage of the test area on the nearest server device in the event of a fire. Therefore, the electronic device corrects the initial abnormality score according to the closest distance. Specifically, the electronic device can store a function related to the distance and the correction value. The function can be inversely proportional. By inputting the closest distance into the function to obtain the correction value, and then adding the initial abnormality score to the correction value, the flow abnormality value of any test area can be obtained. The electronic device corrects each test area in the above manner to obtain the flow abnormality value.

[0152] Sb, if there is a server device in any area to be tested, the volume proportion of the server device in any area to be tested is determined, and the initial anomaly score is corrected based on the volume proportion to obtain the circulation anomaly score.

[0153] For the embodiment of the present application, the electronic device determines whether there is a server device in any area to be tested based on the range coordinates of the server device and the range coordinates corresponding to the area to be tested. If there is a server device, the electronic device divides the server device according to the boundary of the area to be tested to obtain the volume of the server device invading the area to be tested. The volume of the area to be tested is fixed, so the electronic device calculates the ratio of the volume invading the server device to the volume of the area to be tested, that is, the volume ratio. The larger the volume ratio, the greater the probability of a fire in the area to be tested, and the greater the corresponding degree of abnormality, and vice versa. Therefore, the electronic device corrects the initial abnormality score according to the volume ratio. Specifically, a function related to the volume ratio and the correction value can be stored in the electronic device. The function can be directly proportional. The correction value is obtained by inputting the volume ratio into the function, and then the initial abnormality score is added to the correction value to obtain the circulation abnormality value of any area to be tested. The electronic device corrects each area to be tested in the above manner to obtain the circulation abnormality value.

[0154] In other implementations, different locations on the server correspond to different correction scores, and the electronic device determines the location where the server device intrudes into the area to be tested, determines different correction values, and then performs correction.

[0155] In a possible implementation of the embodiment of the present application, the probability of fire in each circulation abnormality area is determined based on the sub-infrared image and the circulation abnormality score in step S105, which specifically includes step S1051 (not shown in the figure), step S1052 (not shown in the figure), step S1053 (not shown in the figure), step S1054 (not shown in the figure), step S1055 (not shown in the figure), step S1056 (not shown in the figure), step S1057 (not shown in the figure) and step S1058 (not shown in the figure), wherein:

[0156] S1051, determining the average temperature of each abnormal circulation area based on the sub-infrared image.

[0157] For the embodiment of the present application, different color depths in the sub-infrared image represent different temperatures. Therefore, after the electronic device determines multiple temperature values ​​in the sub-infrared image, the average temperature value of each circulation abnormality area can be determined by the average value calculation formula. It is more accurate to use the temperature average value to characterize the temperature in the circulation abnormality area. The larger the temperature average value, the greater the probability of fire, and vice versa.

[0158] S1052, converting the sub-infrared image into a grayscale image and obtaining a second grayscale value of each position in the sub-infrared image.

[0159] For the embodiment of the present application, the electronic device first performs denoising on the sub-infrared image, then performs grayscale transformation on the denoised sub-infrared image to obtain a grayscale image, and then determines the second grayscale value of each position in the sub-infrared image. The larger the second grayscale value, the higher the temperature and the greater the probability of fire.

[0160] S1053, mapping the grayscale image in a preset plane coordinate system to obtain a first coordinate point of each second grayscale value.

[0161] For the embodiment of the present application, since the infrared image is two-dimensional and lacks a depth of field direction (i.e., a coordinate axis perpendicular to the two-dimensional plane), the electronic device maps the grayscale image in a preset plane coordinate system, thereby being able to obtain the coordinate point of any position in the grayscale image, i.e., the first coordinate point of each second grayscale value.

[0162] S1054, mapping the abnormal circulation area in a preset plane coordinate system to obtain a second coordinate point of each first gray value.

[0163] For the embodiment of the present application, the electronic device maps the missing coordinate axis of the sub-infrared image corresponding to the circulation abnormality area according to the missing coordinate axis and the depth of field direction, and maps it in a preset plane coordinate system, converting the three-dimensional coordinates of the first grayscale value in the circulation abnormality area into two-dimensional coordinates, that is, the second coordinate point of each first grayscale value.

[0164] S1055, adding the first grayscale value and the second grayscale value that are the same at the first coordinate point and the second coordinate point to obtain a third grayscale value of each preset position and the remaining positions in each abnormal circulation area.

[0165] For the embodiment of the present application, the electronic device determines the first grayscale value and the second grayscale value at the same position according to the first coordinate point and the second coordinate point, and then superimposes the first grayscale value and the second grayscale value at the same position to obtain the third grayscale value of each preset position and the remaining positions. The larger the third grayscale value at a position in the abnormal circulation area, the smaller the wind speed value and the higher the temperature, the more serious the heat accumulation, and the greater the probability of fire.

[0166] S1056, averaging the third grayscale values ​​of each preset position and the remaining positions to obtain an average third grayscale value.

[0167] For the embodiment of the present application, the electronic device averages all the third grayscale values ​​in the abnormal circulation area to obtain the third grayscale value average, and uses the third grayscale value to represent the third grayscale value in the entire abnormal circulation area, that is, the probability of fire.

[0168] S1057, determining the temperature and heat anomaly score of each circulation anomaly area based on the temperature average value, the third gray value average value, and the corresponding coefficients.

[0169] For the embodiment of the present application, the average temperature is a factor that affects the probability of fire in the circulation abnormality area in terms of temperature height, and the average third gray value is a factor that affects the probability of fire in the circulation abnormality area obtained by combining the temperature and wind speed, that is, a factor that affects the probability of fire in terms of heat accumulation and heat dissipation. The staff can set different coefficients for the average temperature and the third gray value and store them in the electronic device. After the electronic device determines the average temperature and the third gray value, it calls the corresponding coefficients for weighted calculation to accurately determine the temperature and heat abnormality score.

[0170] S1058: Determine the probability of fire in each circulation abnormality area based on the temperature and heat abnormality score and the circulation abnormality score.

[0171] For the embodiment of the present application, after the electronic device determines the temperature and heat abnormality score and the circulation abnormality score, it can directly sum the temperature and heat abnormality score and the circulation abnormality score to obtain a total score, and use the total score to represent the probability of fire in each circulation abnormality area. Or set the coefficients corresponding to the temperature and heat abnormality score and the circulation abnormality score in advance, and then the electronic device calls the corresponding coefficients to perform weighted calculation on the temperature and heat abnormality score and the circulation abnormality score to obtain a total score, and use the total score to represent the probability of fire. By determining the temperature and heat abnormality score and the circulation abnormality score in terms of air circulation, and comprehensively calculating the probability of fire in each circulation abnormality area, it is more accurate.

[0172] In a possible implementation of the embodiment of the present application, a plurality of sound and light alarm devices are arranged in the machine room, and an alarm is given to the target flow abnormal area whose probability reaches a preset probability threshold in step S106, which specifically includes step S1061 (not shown in the figure), step S1062 (not shown in the figure), step S1063 (not shown in the figure) and step S1064 (not shown in the figure), wherein:

[0173] S1061, calculating the distance from any target abnormal circulation area to each sound and light alarm device, and determining the nearest sound and light alarm device corresponding to any target abnormal circulation area.

[0174] For the embodiment of the present application, the staff can draw each sound and light alarm device in the three-dimensional model in advance and determine the three-dimensional coordinates of each sound and light alarm device. In the machine room, each sound and light alarm device is connected to the electronic equipment through a wire. The electronic equipment uses the three-dimensional coordinates of the center position of each target abnormal circulation area to characterize the position of each target abnormal circulation area, and then the electronic equipment calculates the distance from each target abnormal circulation area to each sound and light alarm device through the distance formula between two points in three-dimensional space, and then compares and sorts the distances corresponding to each target abnormal circulation area to determine the corresponding nearest sound and light alarm device.

[0175] S1062, controlling the nearest sound and light alarm device corresponding to any target abnormal circulation area to operate.

[0176] For the embodiment of the present application, after the electronic device determines the nearest sound and light alarm device for each target abnormal circulation area, it sends a control signal to the nearest sound and light alarm device corresponding to each target abnormal circulation area. The nearest sound and light alarm device works after receiving the control signal, thereby achieving an alarm effect.

[0177] S1063, obtaining a monitoring image covering any target abnormal circulation area, and marking any target abnormal circulation area in the monitoring image to obtain a marked monitoring image.

[0178] For the embodiment of the present application, a plurality of camera devices are also provided in the computer room, and each camera device corresponds to a different collection range. Therefore, the electronic device can determine the camera device corresponding to each target abnormal circulation area, and then obtain the monitoring image of the camera device. The electronic device marks the target abnormal circulation area in the monitoring image according to the range of the target abnormal circulation area, and obtains the marked monitoring image.

[0179] S1064, sending the marked surveillance image to the terminal device of the administrator.

[0180] For the embodiment of the present application, the electronic device can send the marked monitoring image to the terminal device of the manager through APP push, so that the manager can find the target abnormal circulation area in time.

[0181] The above embodiment introduces an alarm method for monitoring fire in a computer room from the perspective of a method flow, and the following embodiment introduces an alarm device for monitoring fire in a computer room from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0182] The present application embodiment provides an alarm device 20 for monitoring fire in a computer room, such as Figure 2 As shown, the alarm device 20 for monitoring fire in a machine room may specifically include:

[0183] The data acquisition module 201 is used to acquire a three-dimensional model of the computer room, multiple infrared images in the computer room, and airflow information corresponding to each of multiple preset positions in the computer room, the airflow information including wind speed and wind direction, and multiple server devices are installed in the computer room;

[0184] A circulation diagram drawing module 202 is used to draw an air circulation diagram in the computer room based on the air flow information and the three-dimensional model, wherein the air circulation diagram records the air flow information at any position in the three-dimensional model;

[0185] A score determination module 203, for determining the circulation abnormality area and the circulation abnormality score of each circulation abnormality area from the air circulation map;

[0186] An image segmentation module 204 is used to segment the infrared image into a sub-infrared image of each abnormal circulation area;

[0187] The probability determination module 205 is used to determine the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score;

[0188] The alarm module 206 is used to alarm the target flow abnormal area whose probability reaches a preset probability threshold.

[0189] The embodiment of the present application discloses an alarm device 20 for fire monitoring in a computer room. The data acquisition module 201 acquires a three-dimensional model of the computer room, an infrared image, and airflow information at multiple preset positions, so that the circulation map drawing module 202 can subsequently draw an accurate air circulation map based on the airflow information and the three-dimensional model. The air circulation map records the air circulation conditions at any position in the computer room, that is, the wind speed value and wind direction at any position. The score determination module 203 can accurately determine the circulation abnormality area and the circulation abnormality score of each circulation abnormality area with respect to air circulation from the air circulation map. The infrared image records the temperature conditions in the computer room. After the infrared image is determined, the image segmentation module 204 determines the position of the circulation abnormality area, that is, A sub-infrared image of each abnormal circulation area can be segmented, and the probability determination module 205 determines the probability of fire in each abnormal circulation area based on the sub-infrared image and the abnormal circulation score. That is, it is more accurate to comprehensively determine the probability of fire in each abnormal circulation area based on temperature and air circulation conditions. The preset probability threshold is used as the dividing point for whether the probability of fire is too high. The alarm module 206 alarms the target abnormal circulation area whose probability reaches the preset probability threshold, so that the location where the fire is about to occur in the computer room can be discovered in time, and the probability of fire in the abnormal circulation area is determined based on a comprehensive analysis of air circulation and temperature, thereby achieving the effect of facilitating alarm and early warning of the initial area before the fire occurs in the computer room.

[0190] In a possible implementation of the embodiment of the present application, the air flow diagram drawing module 202 is specifically used to draw the air flow diagram in the computer room based on the air flow information and the three-dimensional model:

[0191] Determine a first grayscale value corresponding to each preset position based on the wind speed value of each preset position;

[0192] Mapping the first grayscale value corresponding to each preset position to the corresponding preset position in the three-dimensional model;

[0193] And determine the flow arrow corresponding to the wind direction according to the wind direction, and map the flow arrow to the corresponding preset position;

[0194] Performing simulation based on the three-dimensional model and the airflow information of each preset position, obtaining the wind speed value and wind direction of the remaining positions in the three-dimensional model except the preset position, and determining the first gray value and flow arrow of each remaining position;

[0195] The first grayscale value and flow arrow of each preset position and the first grayscale value and flow arrow of each remaining position are mapped in the three-dimensional model to obtain an air circulation diagram.

[0196] In a possible implementation of the embodiment of the present application, when the score determination module 203 determines the abnormal circulation area and the abnormal circulation score of each abnormal circulation area from the air circulation map, it is specifically used to:

[0197] Determine the angle at which each flow arrow in the air flow diagram points;

[0198] Scanning the air circulation diagram according to a preset range and a preset step length to obtain multiple areas to be tested, wherein the preset range is a three-dimensional area;

[0199] Determine an initial anomaly score for each area to be tested, where the initial anomaly score is determined by a pointing angle and a first grayscale value in each area to be tested;

[0200] Based on whether there is a server device in each area to be tested, the initial anomaly score of each area to be tested is corrected to obtain a circulation anomaly score;

[0201] The area to be tested whose circulation anomaly score reaches the preset score threshold is determined as the circulation anomaly area.

[0202] In a possible implementation of the embodiment of the present application, the score determination module 203 is specifically used for any of the following when determining the initial abnormality score of each area to be tested:

[0203] Determine the number of pointing angles and the first gray value average value in each area to be tested, and determine an initial abnormality score for each area to be tested based on the number of pointing angles and the first gray value average value;

[0204] The directional angles in each area to be tested are fitted to obtain the air circulation path in each area to be tested, the curvature of the air circulation path and the average first grayscale value in each area to be tested are determined, and the initial abnormal score of each area to be tested is determined based on the curvature and the average first grayscale value.

[0205] In a possible implementation of the embodiment of the present application, when the score determination module 203 corrects the initial abnormal score of each tested area based on whether there is a server device in each tested area to obtain the circulation abnormal score, it is specifically used to:

[0206] If there is no server device in any of the tested areas, the center position of any of the tested areas is determined, the distance from the center position to each server device is calculated, and the shortest distance is determined. The initial anomaly score is corrected based on the shortest distance to obtain the circulation anomaly score;

[0207] If there is a server device in any of the areas to be tested, the volume ratio of the server device in any of the areas to be tested is determined, and the initial anomaly score is corrected based on the volume ratio to obtain a circulation anomaly score.

[0208] In a possible implementation of the embodiment of the present application, when the probability determination module 205 determines the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score, it is specifically used to:

[0209] Determine the average temperature of each circulation anomaly area based on the sub-infrared image;

[0210] Converting the sub-infrared image into a grayscale image and obtaining a second grayscale value at each position in the sub-infrared image;

[0211] Mapping the grayscale image in a preset plane coordinate system to obtain a first coordinate point of each second grayscale value;

[0212] Mapping the circulation abnormality area in a preset plane coordinate system to obtain a second coordinate point of each first gray value;

[0213] Adding the first grayscale value and the second grayscale value that are the same at the first coordinate point and the second coordinate point to obtain a third grayscale value for each preset position and the remaining positions in each abnormal circulation area;

[0214] averaging the third grayscale values ​​of each preset position and the remaining positions to obtain an average third grayscale value;

[0215] Determine the temperature and heat anomaly score of each circulation anomaly area based on the temperature average value, the third gray value average value and the corresponding coefficients;

[0216] The probability of fire in each circulation abnormality area is determined based on the temperature and heat abnormality scores and the circulation abnormality scores.

[0217] In a possible implementation of the embodiment of the present application, a plurality of sound and light alarm devices are arranged in the machine room, and when the alarm module 206 alarms the target flow abnormal area with a probability reaching a preset probability threshold, it is specifically used to include:

[0218] Calculate the distance from any target abnormal circulation area to each sound and light alarm device, and determine the nearest sound and light alarm device corresponding to any target abnormal circulation area;

[0219] Control the operation of the nearest sound and light alarm equipment corresponding to any target abnormal circulation area;

[0220] Acquire a monitoring image covering any target abnormal circulation area, and mark any target abnormal circulation area in the monitoring image to obtain a marked monitoring image;

[0221] Send the marked surveillance images to the terminal device of the manager.

[0222] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the alarm device 20 for fire monitoring in a computer room described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0223] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0224] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0225] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0226] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0227] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0228] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0229] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment. Compared with the related art, in the embodiment of the present application, a three-dimensional model of the computer room, an infrared image and airflow information of multiple preset positions are obtained, so that an accurate air circulation map can be drawn according to the airflow information and the three-dimensional model. The air circulation map records the air circulation conditions at any position in the computer room, that is, the wind speed value and wind direction at any position, so that the abnormal circulation area and the abnormal circulation score of each abnormal circulation area with respect to air circulation can be accurately determined from the air circulation map. The infrared image records the temperature conditions in the computer room. After determining the infrared image, a sub-infrared image of each abnormal circulation area can be segmented according to the position of the abnormal circulation area. The probability of fire in each abnormal circulation area is determined based on the sub-infrared image and the abnormal circulation score, that is, the probability of fire in each abnormal circulation area is more accurately determined based on the temperature and air circulation conditions. The preset probability threshold is used as the dividing point of whether the probability of fire is too high. Therefore, an alarm is issued for the target abnormal circulation area that reaches the preset probability threshold, so that the location where the fire is about to occur in the computer room can be discovered in time, and the probability of fire in the abnormal circulation area is determined based on the comprehensive analysis of air circulation and temperature, so as to achieve the effect of facilitating the alarm and early warning of the initial area before the fire occurs in the computer room.

[0230] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0231] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An alarm method for fire monitoring in a computer room, characterized in that: include: Acquire a three-dimensional model of a computer room, a plurality of infrared images in the computer room, and airflow information corresponding to a plurality of preset positions in the computer room, wherein the airflow information includes wind speed and wind direction, and a plurality of server devices are installed in the computer room; Drawing an air circulation diagram in the computer room based on the air flow information and the three-dimensional model, wherein the air circulation diagram records the air flow information at any position in the three-dimensional model; Determine the abnormal circulation area and the abnormal circulation score of each abnormal circulation area from the air circulation map; Segmenting a sub-infrared image of each circulation abnormality region from the infrared image; Determine the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score; Alarm the target flow abnormal area whose probability reaches the preset probability threshold; Wherein, drawing the air circulation diagram in the computer room based on the airflow information and the three-dimensional model includes: Determine a first grayscale value corresponding to each preset position based on the wind speed value of each preset position; Mapping the first grayscale value corresponding to each preset position to the corresponding preset position in the three-dimensional model; and determining a flow arrow corresponding to the wind direction according to the wind direction, and mapping the flow arrow to a corresponding preset position; Performing simulation based on the three-dimensional model and the airflow information of each preset position, obtaining the wind speed value and wind direction of the remaining positions in the three-dimensional model except the preset position, and determining the first gray value and flow arrow of each remaining position; Mapping the first grayscale value and flow arrow of each preset position and the first grayscale value and flow arrow of each remaining position in the three-dimensional model to obtain the air circulation diagram; Wherein, determining the abnormal circulation area and the abnormal circulation score of each abnormal circulation area from the air circulation map includes: Determine the pointing angle of each flow arrow in the air circulation diagram; Scanning the air circulation diagram according to a preset range and a preset step length to obtain a plurality of areas to be tested, wherein the preset range is a three-dimensional area; Determine an initial anomaly score for each area to be tested, where the initial anomaly score is determined by a pointing angle and a first grayscale value in each area to be tested; Based on whether the server device exists in each area to be tested, the initial anomaly score of each area to be tested is corrected to obtain the circulation anomaly score; Determine the area to be tested whose circulation anomaly score reaches a preset score threshold as the circulation anomaly area; The step of determining the initial abnormality score of each area to be tested includes any one of the following: Determine the number of pointing angles and the first gray value average value in each area to be tested, and determine an initial abnormality score for each area to be tested based on the number of pointing angles and the first gray value average value; The directional angles in each area to be tested are fitted to obtain the air circulation path in each area to be tested, the curvature of the air circulation path and the average first grayscale value in each area to be tested are determined, and the initial abnormality score of each area to be tested is determined based on the curvature and the average first grayscale value.

2. The alarm method for fire monitoring in a computer room according to claim 1, characterized in that: The step of correcting the initial anomaly score of each area to be tested based on whether the server device exists in each area to be tested to obtain the circulation anomaly score comprises: If there is no server device in any of the tested areas, determine the center position of any of the tested areas, calculate the distance from the center position to each server device, and determine the shortest distance, and correct the initial anomaly score based on the shortest distance to obtain the circulation anomaly score; If there is a server device in any of the areas to be tested, the volume ratio of the server device in any of the areas to be tested is determined, and the initial anomaly score is corrected based on the volume ratio to obtain a circulation anomaly score.

3. The alarm method for fire monitoring in a computer room according to claim 1, characterized in that: The determining the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score includes: Determine the average temperature of each abnormal circulation area based on the sub-infrared image; Converting the sub-infrared image into a grayscale image and obtaining a second grayscale value of each position in the sub-infrared image; Mapping the grayscale image in a preset plane coordinate system to obtain a first coordinate point of each second grayscale value; Mapping the abnormal circulation area in the preset plane coordinate system to obtain a second coordinate point of each first gray value; Adding the first grayscale value and the second grayscale value that are the same at the first coordinate point and the second coordinate point to obtain a third grayscale value for each preset position and the remaining positions in each abnormal circulation area; averaging the third grayscale values ​​of each preset position and the remaining positions to obtain an average third grayscale value; Determine the temperature and heat anomaly score of each circulation anomaly area based on the temperature average value, the third gray value average value and the corresponding coefficients; The probability of fire occurring in each circulation abnormality area is determined based on the temperature and heat abnormality score and the circulation abnormality score.

4. The alarm method for fire monitoring in a computer room according to claim 1, characterized in that: The machine room is provided with a plurality of sound and light alarm devices, which alarm the target flow abnormal area whose probability reaches a preset probability threshold, including: Calculate the distance from any target abnormal circulation area to each sound and light alarm device, and determine the nearest sound and light alarm device corresponding to any target abnormal circulation area; Controlling the nearest sound and light alarm device corresponding to any target abnormal circulation area to operate; Acquire a monitoring image covering any target abnormal circulation area, and mark any target abnormal circulation area in the monitoring image to obtain a marked monitoring image; The marked monitoring image is sent to the terminal device of the administrator.

5. An alarm device for monitoring fire in a machine room, characterized in that: include: A data acquisition module, used to acquire a three-dimensional model of a computer room, a plurality of infrared images in the computer room, and airflow information corresponding to each of a plurality of preset positions in the computer room, wherein the airflow information includes wind speed and wind direction, and a plurality of server devices are installed in the computer room; A circulation diagram drawing module, used for drawing an air circulation diagram in the computer room based on the air flow information and the three-dimensional model, wherein the air circulation diagram records the air flow information at any position in the three-dimensional model; A score determination module, used to determine the circulation abnormality area and the circulation abnormality score of each circulation abnormality area from the air circulation map; An image segmentation module, used for segmenting a sub-infrared image of each abnormal circulation area from the infrared image; A probability determination module, used to determine the probability of fire in each circulation abnormality area based on the sub-infrared image and the circulation abnormality score; An alarm module is used to alarm the target flow abnormal area whose probability reaches a preset probability threshold; When the air flow diagram drawing module draws the air flow diagram in the computer room based on the air flow information and the three-dimensional model, it is specifically used to: Determine a first grayscale value corresponding to each preset position based on the wind speed value of each preset position; Mapping the first grayscale value corresponding to each preset position to the corresponding preset position in the three-dimensional model; and determining a flow arrow corresponding to the wind direction according to the wind direction, and mapping the flow arrow to a corresponding preset position; Performing simulation based on the three-dimensional model and the airflow information of each preset position, obtaining the wind speed value and wind direction of the remaining positions in the three-dimensional model except the preset position, and determining the first gray value and flow arrow of each remaining position; Mapping the first grayscale value and flow arrow of each preset position and the first grayscale value and flow arrow of each remaining position in the three-dimensional model to obtain the air circulation diagram; When the score determination module determines the abnormal circulation area and the abnormal circulation score of each abnormal circulation area from the air circulation map, the score determination module is specifically used to: Determine the pointing angle of each flow arrow in the air circulation diagram; Scanning the air circulation diagram according to a preset range and a preset step length to obtain a plurality of areas to be tested, wherein the preset range is a three-dimensional area; Determine an initial anomaly score for each area to be tested, where the initial anomaly score is determined by a pointing angle and a first grayscale value in each area to be tested; Based on whether the server device exists in each area to be tested, the initial anomaly score of each area to be tested is corrected to obtain the circulation anomaly score; Determine the area to be tested whose circulation anomaly score reaches a preset score threshold as the circulation anomaly area; When the score determination module determines the abnormal circulation area and the abnormal circulation score of each abnormal circulation area from the air circulation map, the score determination module is specifically used to: Determine the pointing angle of each flow arrow in the air circulation diagram; Scanning the air circulation diagram according to a preset range and a preset step length to obtain a plurality of areas to be tested, wherein the preset range is a three-dimensional area; Determine an initial anomaly score for each area to be tested, where the initial anomaly score is determined by a pointing angle and a first grayscale value in each area to be tested; Based on whether the server device exists in each area to be tested, the initial anomaly score of each area to be tested is corrected to obtain the circulation anomaly score; Determine the area to be tested whose circulation anomaly score reaches a preset score threshold as the circulation anomaly area; Determining the initial anomaly score of each area to be tested includes any one of the following: Determine the number of pointing angles and the first gray value average value in each area to be tested, and determine an initial abnormality score for each area to be tested based on the number of pointing angles and the first gray value average value; The directional angles in each area to be tested are fitted to obtain the air circulation path in each area to be tested, the curvature of the air circulation path and the average first grayscale value in each area to be tested are determined, and the initial abnormality score of each area to be tested is determined based on the curvature and the average first grayscale value.

6. An electronic device, characterized in that: It includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and is configured to be executed by the at least one processor, and the at least one application is used to execute an alarm method for fire monitoring in a computer room according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the alarm method for fire monitoring in a computer room as described in any one of claims 1 to 4.

Images