Data center fire prevention method and system combining the Internet of Things and artificial intelligence

Abstract

The present invention relates to a data center fire prevention and control method that combines the Internet of Things and artificial intelligence. First, static electricity is removed from users entering the entrance while monitoring whether they have flammable and explosive items on them, reducing fire hazards at the source. Then, the readings of the temperature sensors set by the fire alarm system are analyzed so that the temperature sensor readings can be used to alarm in a more sensitive situation. At this time, the administrator decides whether a fire is about to occur and whether it is necessary to activate the fire prevention and control equipment. The infrared image captured by the infrared camera can also be used to determine whether there is a fire, that is, whether a flame can be detected in the infrared image using artificial intelligence. If there is a fire, the fire prevention and control equipment is automatically activated, and the staff is informed to evacuate the relevant personnel. The entire process combines the Internet of Things and artificial intelligence to quickly and effectively respond to abnormal situations and prevent and control fires in the data center computer room.

Description

Technical Field

[0001] The present invention relates to the field of smart computer room technology, and in particular to a data center fire prevention and control method and system combining the Internet of Things and artificial intelligence. Background Art

[0002] Data centers are specialized, globally coordinated networks of devices used to transmit, accelerate, display, compute, and store data on the internet infrastructure. Data centers contain valuable data resources that need to be properly stored and protected.

[0003] Existing technologies for communication processing such as data backup are already relatively mature and can effectively protect the contents of data centers at the software level. However, data centers may also face problems such as damage to physical hardware due to fires in the central computer room or other disasters, which in turn may lead to data loss and cause immeasurable losses.

[0004] In existing technology, there are two main approaches to fire prevention in data center computer rooms. One approach involves in-house fire prevention hardware, which, upon activation, effectively eliminates fire factors and fire conditions. The other approach involves sensors deployed within the data center computer room. These sensors collaborate to collect data from the computer room and generate alarms when risk thresholds are reached, effectively preventing and controlling fires in the data center computer room. These two approaches are often handled separately, requiring personnel to activate and deactivate the fire prevention hardware as needed, set individual sensor thresholds, and generate alarms when these thresholds are reached. This reliance on manual labor can lead to delayed fire prevention and control, and requires extremely high levels of professional expertise. Summary of the Invention

[0005] The purpose of the present invention is to address at least one of the deficiencies of the prior art and to provide a data center fire prevention and control method and system that combines the Internet of Things and artificial intelligence.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] Specifically, a data center fire prevention and control method combining the Internet of Things and artificial intelligence is proposed, including the following:

[0008] When a user enters the data center room, the gate is used to eliminate static electricity on the user and to monitor whether the user is carrying flammable and explosive items, thereby obtaining a first monitoring result;

[0009] When the first monitoring result is abnormal, inform the on-duty personnel to conduct an investigation, and allow the user to enter the data center room after the investigation is completed;

[0010] Acquire a temperature data set collected by a temperature sensor group pre-deployed in the fire alarm system, analyze the temperature data set, and obtain a second monitoring result;

[0011] When the second monitoring result is abnormal, the sound and light alarm is controlled to operate, and then the start and stop signal of the fire extinguishing system is obtained, and the fire extinguishing system is controlled to operate accordingly according to the start and stop signal of the fire extinguishing system;

[0012] Obtaining an infrared image captured by an infrared camera pre-deployed in the fire alarm system, and analyzing the infrared image to obtain a third monitoring result;

[0013] When the third monitoring result is abnormal, the sound and light alarm is controlled to operate, the staff is informed to evacuate, and the fire extinguishing system and the smoke exhaust system are controlled to be turned on.

[0014] Further, specifically, the operation mode of the gate machine is as follows:

[0015] When the user triggers the gate switch, the electrostatic discharge device with electrostatic monitoring function performs the initial electrostatic discharge on the user and obtains the user's electrostatic voltage after the initial electrostatic discharge;

[0016] determining whether the electrostatic voltage is greater than a first threshold, and if so, triggering a secondary release of the electrostatic voltage, and turning on an ion blower to blow air toward the user when the secondary release is triggered;

[0017] The monitoring device monitors the items carried by the user to determine whether they are carrying flammable or explosive items. If so, the first monitoring result is displayed as abnormal.

[0018] Furthermore, specifically, the process of obtaining the second monitoring result includes:

[0019] Analyze the data collected by each temperature sensor in the temperature sensor group, and determine whether there is an abnormal risk in the current temperature sensor reading based on the analysis results. If so, mark the current temperature sensor as an abnormal risk object;

[0020] Obtain all abnormal risk objects and determine whether there are abnormal risk objects adjacent to the monitoring location. If so, count the number N of abnormal risk objects adjacent to the monitoring location.

[0021] For abnormal risk objects that do not have adjacent monitoring positions, the second threshold is used as the safety threshold of their temperature data. When their temperature data exceeds the second threshold, it is determined that there is an abnormal second monitoring result. For abnormal risk objects that have adjacent monitoring positions, A / N times the second threshold is used as the safety threshold of their temperature data. When their temperature data exceeds A / N times the second threshold, it is determined that there is an abnormal second monitoring result. A is an adjustment parameter that is set in advance and is less than N.

[0022] Further, specifically, judging whether there is an abnormal risk in the current temperature sensor reading based on the analysis result includes:

[0023] The sampling period T is preset, and multiple real-time temperature values ​​within the period (t, t+NT) are collected in the form of random sampling, where t is an arbitrary starting time and N is a positive integer;

[0024] A two-dimensional coordinate system is constructed with the time axis as the horizontal axis, the real-time temperature value as the vertical axis, and (t, 0) as the coordinate origin. At this time, there are multiple discrete points in the two-dimensional coordinate system whose horizontal coordinates are within the range of (t, t+NT);

[0025] A first straight line can be obtained by fitting all discrete points, and the first straight line is defined as the temperature standard line of the current period;

[0026] The temperature standard line is used to judge abnormality of multiple real-time temperature values ​​in the next (t+NT, t+2NT) period. The judgment method is as follows:

[0027] Calculate the shortest distance between the discrete points formed by multiple real-time temperature values ​​within the time range (t+NT, t+2NT) and the temperature standard line, and count the number Q of discrete points whose shortest distance is greater than the third threshold.

[0028] If the number of discrete points Q accounts for more than a fourth ratio threshold of the total number of samples, it is determined that there is a risk of abnormality in the current temperature sensor reading.

[0029] Furthermore, specifically, the process of obtaining the third monitoring result includes:

[0030] The infrared image is pre-processed and then input into a pre-trained BP neural network. It is determined whether there is a flame in the infrared image based on the output result of the BP neural network. If so, it is determined that the third monitoring result is abnormal.

[0031] The present invention also proposes a data center fire prevention and control system that combines the Internet of Things and artificial intelligence, including:

[0032] A gate, provided at the entrance of the data center, for performing static elimination on the user and monitoring whether the user is carrying flammable and explosive items when the user enters the data center computer room, and obtaining a first monitoring result;

[0033] Fire alarm system, including,

[0034] A temperature sensor group is pre-arranged in the central computer room, and the temperature sensor group is used to collect temperature data sets.

[0035] Sound and light alarm, used for sound and light alarm during operation,

[0036] Multiple infrared cameras are pre-placed in the central computer room to collect infrared images;

[0037] A fire extinguishing system for extinguishing fires upon receiving corresponding control signals;

[0038] A smoke exhaust system, for exhausting smoke upon receiving a corresponding control signal;

[0039] The control system is in communication with the gate machine, fire alarm system, fire extinguishing system and smoke exhaust system, and is used to:

[0040] Obtain the first monitoring result. If the first monitoring result is abnormal, inform the on-duty personnel to conduct an investigation. After the investigation is completed, allow the user to enter the data center room.

[0041] Acquire a temperature data set collected by a temperature sensor group pre-arranged in the fire alarm system, analyze the temperature data set, and obtain a second monitoring result.

[0042] When the second monitoring result is abnormal, the sound and light alarm is controlled to operate, and then the start and stop signal of the fire extinguishing system is obtained, and the fire extinguishing system is controlled to operate accordingly according to the start and stop signal of the fire extinguishing system;

[0043] Obtain an infrared image captured by an infrared camera pre-arranged in the fire alarm system, analyze the infrared image, and obtain a third monitoring result.

[0044] When the third monitoring result is abnormal, the sound and light alarm is controlled to operate, the staff is informed to evacuate, and the fire extinguishing system and the smoke exhaust system are controlled to be turned on.

[0045] The beneficial effects of the present invention are:

[0046] The present invention proposes a data center fire prevention and control method that combines the Internet of Things and artificial intelligence. First, static electricity is removed from users entering the entrance while monitoring whether they have flammable and explosive items on them, reducing fire hazards at the source. Then, by analyzing the readings of the temperature sensors set by the fire alarm system, the temperature sensor readings can be used to alarm in a more sensitive situation. That is, when there is a fire hazard, the administrator can be reminded to investigate the relevant issues. At this time, the administrator decides whether a fire is about to occur and whether fire prevention equipment needs to be activated. The infrared image captured by the infrared camera can also be used to determine whether there is a fire. In other words, whether flames can be detected in the infrared image using artificial intelligence. If there is a fire, fire prevention measures are immediately initiated, the fire prevention equipment is automatically activated, and the staff are informed to evacuate the relevant personnel. The entire process combines the Internet of Things and artificial intelligence to quickly and effectively respond to abnormal situations and prevent fires in data center computer rooms. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other features of the present disclosure will become more apparent through a detailed description of the embodiments shown in conjunction with the accompanying drawings. The same reference numerals in the drawings of the present disclosure represent the same or similar elements. Obviously, the drawings described below are only some embodiments of the present disclosure. It is possible for a person skilled in the art to derive other drawings based on these drawings without inventive effort. In the drawings:

[0048] Figure 1 Shown is a flow chart of the data center fire prevention method combined with the Internet of Things and artificial intelligence of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other unless there is a conflict. The same reference numerals used throughout the drawings indicate the same or similar parts.

[0050] Reference Figure 1 In Example 1, the present invention proposes a data center fire prevention method combining the Internet of Things and artificial intelligence, including the following:

[0051] Step 110: When a user enters the data center room, the gate is used to eliminate static electricity from the user and to monitor whether the user is carrying flammable or explosive items, thereby obtaining a first monitoring result.

[0052] Step 120: When the first monitoring result is abnormal, inform the on-duty personnel to conduct an investigation, and allow the user to enter the data center room after the investigation is completed;

[0053] Step 130: Acquire a temperature data set collected by a temperature sensor group pre-deployed in the fire alarm system, analyze the temperature data set, and obtain a second monitoring result;

[0054] Step 140: When the second monitoring result is abnormal, control the sound and light alarm to operate, then obtain the start and stop signal of the fire extinguishing system, and control the corresponding operation of the fire extinguishing system according to the start and stop signal of the fire extinguishing system;

[0055] Step 150: Obtain an infrared image captured by an infrared camera pre-deployed in the fire alarm system, analyze the infrared image, and obtain a third monitoring result;

[0056] Step 160: When the third monitoring result is abnormal, control the sound and light alarm to operate, inform the staff to evacuate, and control the fire extinguishing system to start, and control the smoke exhaust system to start.

[0057] In this embodiment, static electricity is first removed from incoming users at the entrance while monitoring for flammable and explosive materials, mitigating fire hazards at the source. The fire alarm system then analyzes the temperature sensor readings, enabling a more sensitive alarm. This alerts administrators to investigate potential fire hazards, alerting them to the impending fire and determining whether fire prevention equipment should be activated. Infrared images captured by infrared cameras can also be used to determine whether a fire is present. This involves identifying flames in the infrared images using artificial intelligence. If a fire is present, fire prevention measures are immediately initiated, automatically activating fire prevention equipment and notifying staff to evacuate relevant personnel. This entire process, combining the Internet of Things (IoT) with artificial intelligence, enables a quick and effective response to abnormal situations and fire prevention in data center rooms.

[0058] As a preferred embodiment of the present invention, specifically, the gate machine operates as follows:

[0059] When the user triggers the gate switch, the electrostatic discharge device with electrostatic monitoring function performs the initial electrostatic discharge on the user and obtains the user's electrostatic voltage after the initial electrostatic discharge;

[0060] determining whether the electrostatic voltage is greater than a first threshold, and if so, triggering a secondary release of the electrostatic voltage, and turning on an ion blower to blow air toward the user when the secondary release is triggered;

[0061] The monitoring device monitors the items carried by the user to determine whether they are carrying flammable or explosive items. If so, the first monitoring result is displayed as abnormal.

[0062] As a preferred embodiment of the present invention, specifically, the process of obtaining the second monitoring result includes:

[0063] Analyze the data collected by each temperature sensor in the temperature sensor group, and determine whether there is an abnormal risk in the current temperature sensor reading based on the analysis results. If so, mark the current temperature sensor as an abnormal risk object;

[0064] Obtain all abnormal risk objects and determine whether there are abnormal risk objects adjacent to the monitoring location. If so, count the number N of abnormal risk objects adjacent to the monitoring location.

[0065] For abnormal risk objects that do not have adjacent monitoring positions, the second threshold is used as the safety threshold of their temperature data. When their temperature data exceeds the second threshold, it is determined that there is an abnormal second monitoring result. For abnormal risk objects that have adjacent monitoring positions, A / N times the second threshold is used as the safety threshold of their temperature data. When their temperature data exceeds A / N times the second threshold, it is determined that there is an abnormal second monitoring result. A is an adjustment parameter that is set in advance and is less than N.

[0066] In this preferred embodiment, considering that it may be too late for a general temperature sensor to sound an alarm when the temperature limit is reached, and the relevant machinery and equipment may have been damaged, it is necessary to arrange personnel to check for hidden dangers as soon as possible in the event of suspected hidden dangers and prevent them in advance. Therefore, the readings of the temperature sensors are analyzed for abnormal risks. If there are abnormal risks in adjacent temperature sensors, this is defined as a cluster risk phenomenon. In this case, we should respond sensitively and lower the reading thresholds of these temperature sensors according to the number of temperature sensors with abnormal risks to make the relevant data more sensitive. After that, relevant staff will be arranged to check the monitoring areas of the problematic temperature sensors, and judge whether it is necessary to start the linkage equipment to prevent and control the fire based on the inspection results.

[0067] As a preferred embodiment of the present invention, specifically, judging whether the current temperature sensor reading has an abnormal risk based on the analysis result includes:

[0068] The sampling period T is preset, and multiple real-time temperature values ​​within the period (t, t+NT) are collected in the form of random sampling, where t is an arbitrary starting time and N is a positive integer;

[0069] A two-dimensional coordinate system is constructed with the time axis as the horizontal axis, the real-time temperature value as the vertical axis, and (t, 0) as the coordinate origin. At this time, there are multiple discrete points in the two-dimensional coordinate system whose horizontal coordinates are within the range of (t, t+NT);

[0070] A first straight line can be obtained by fitting all discrete points, and the first straight line is defined as the temperature standard line of the current period;

[0071] The temperature standard line is used to judge abnormality of multiple real-time temperature values ​​in the next (t+NT, t+2NT) period. The judgment method is as follows:

[0072] Calculate the shortest distance between the discrete points formed by multiple real-time temperature values ​​within the time range (t+NT, t+2NT) and the temperature standard line, and count the number Q of discrete points whose shortest distance is greater than the third threshold.

[0073] If the number of discrete points Q accounts for more than a fourth ratio threshold of the total number of samples, it is determined that there is a risk of abnormality in the current temperature sensor reading.

[0074] In this preferred embodiment, considering that the temperature of the data center room is stable even with seasonal climate changes, the temperature analysis of the periodic time period is used to check whether the corresponding temperature sensor has any abnormal hidden dangers. When there are abnormal hidden dangers, the administrator can be informed as soon as possible for prevention and control.

[0075] As a preferred embodiment of the present invention, specifically, the process of obtaining the third monitoring result includes:

[0076] The infrared image is pre-processed and then input into a pre-trained BP neural network. It is determined whether there is a flame in the infrared image based on the output result of the BP neural network. If so, it is determined that the third monitoring result is abnormal.

[0077] The present invention also proposes a data center fire prevention and control system that combines the Internet of Things and artificial intelligence, including:

[0078] A gate, provided at the entrance of the data center, for performing static elimination on the user and monitoring whether the user is carrying flammable and explosive items when the user enters the data center computer room, and obtaining a first monitoring result;

[0079] Fire alarm system, including,

[0080] A temperature sensor group is pre-arranged in the central computer room, and the temperature sensor group is used to collect temperature data sets.

[0081] Sound and light alarm, used for sound and light alarm during operation,

[0082] Multiple infrared cameras are pre-placed in the central computer room to collect infrared images;

[0083] The fire extinguishing system is used to extinguish fires upon receiving corresponding control signals. The fire extinguishing system is installed using a domestic standard gas fire extinguishing system;

[0084] The smoke exhaust system is used to exhaust smoke when it receives the corresponding control signal. The smoke generated when a fire occurs is mainly composed of carbon monoxide. This gas has a strong asphyxiating effect and poses a great threat to people's lives. In addition, the smoke generated by the fire blocks people's vision. It makes it impossible for people to distinguish the direction when evacuating. Especially in high-rise buildings, due to their own "chimney effect", the smoke rises very quickly, and the harm is obvious. The smoke exhaust system should be activated immediately after a fire occurs. In addition, the machine room is a relatively closed environment. When gas jet fire extinguishing occurs, the gas fire extinguishing agent is not easy to discharge. The smoke exhaust system can assist in discharging the residual fire extinguishing agent.

[0085] The control system is in communication with the gate machine, fire alarm system, fire extinguishing system and smoke exhaust system, and is used to:

[0086] Obtain the first monitoring result. If the first monitoring result is abnormal, inform the on-duty personnel to conduct an investigation. After the investigation is completed, allow the user to enter the data center room.

[0087] Acquire a temperature data set collected by a temperature sensor group pre-arranged in the fire alarm system, analyze the temperature data set, and obtain a second monitoring result.

[0088] When the second monitoring result is abnormal, the sound and light alarm is controlled to operate, and then the start and stop signal of the fire extinguishing system is obtained, and the fire extinguishing system is controlled to operate accordingly according to the start and stop signal of the fire extinguishing system;

[0089] Obtain an infrared image captured by an infrared camera pre-arranged in the fire alarm system, analyze the infrared image, and obtain a third monitoring result.

[0090] When the third monitoring result is abnormal, the sound and light alarm is controlled to operate, the staff is informed to evacuate, and the fire extinguishing system and the smoke exhaust system are controlled to be turned on.

[0091] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

[0092] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.

[0093] If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or system that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0094] Although the present invention has been described in considerable detail and with particularity with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but rather should be construed as providing a broad possible interpretation of these claims in view of the prior art by reference to the appended claims, thereby effectively encompassing the intended scope of the invention. In addition, the invention has been described above in terms of embodiments foreseen by the inventors for the purpose of providing a useful description, and those insubstantial modifications of the invention that are not currently foreseen may still represent equivalent modifications of the invention.

[0095] The above description is merely a preferred embodiment of the present invention. The present invention is not limited to the above-described embodiments. As long as the technical effects of the present invention are achieved by the same means, they shall fall within the scope of protection of the present invention. Within the scope of protection of the present invention, various modifications and variations of the technical solutions and / or implementation methods may be made.

Claims

1. A data center fire prevention method combining the Internet of Things and artificial intelligence, characterized in that: These include: When a user enters the data center room, the gate is used to eliminate static electricity on the user and to monitor whether the user is carrying flammable and explosive items, thereby obtaining a first monitoring result; When the first monitoring result is abnormal, inform the on-duty personnel to conduct an investigation, and allow the user to enter the data center room after the investigation is completed; Acquire a temperature data set collected by a temperature sensor group pre-deployed in the fire alarm system, analyze the temperature data set, and obtain a second monitoring result; When the second monitoring result is abnormal, the sound and light alarm is controlled to operate, and then the start and stop signal of the fire extinguishing system is obtained, and the fire extinguishing system is controlled to operate accordingly according to the start and stop signal of the fire extinguishing system; Obtaining an infrared image captured by an infrared camera pre-deployed in the fire alarm system, and analyzing the infrared image to obtain a third monitoring result; When the third monitoring result is abnormal, the sound and light alarm is controlled to operate, the staff is informed to evacuate, and the fire extinguishing system and the smoke exhaust system are controlled to be turned on; Specifically, the process of obtaining the second monitoring result is: include, Analyze the data collected by each temperature sensor in the temperature sensor group, and determine whether there is an abnormal risk in the current temperature sensor reading based on the analysis results. If so, mark the current temperature sensor as an abnormal risk object; Obtain all abnormal risk objects and determine whether there are abnormal risk objects adjacent to the monitoring location. If so, count the number N of abnormal risk objects adjacent to the monitoring location. For abnormal risk objects that do not have adjacent monitoring positions, the second threshold is used as the safety threshold of their temperature data. When their temperature data exceeds the second threshold, it is determined that there is an abnormal second monitoring result. For abnormal risk objects that have adjacent monitoring positions, A / N times the second threshold is used as the safety threshold of their temperature data. When their temperature data exceeds A / N times the second threshold, it is determined that there is an abnormal second monitoring result. A is an adjustment parameter that is set in advance and is less than N.

2. The data center fire prevention method combining the Internet of Things and artificial intelligence according to claim 1 is characterized in that: Specifically, the gate machine operates as follows: When the user triggers the gate switch, the electrostatic discharge device with electrostatic monitoring function performs the initial electrostatic discharge on the user and obtains the user's electrostatic voltage after the initial electrostatic discharge; determining whether the electrostatic voltage is greater than a first threshold, and if so, triggering a secondary release of the electrostatic voltage, and turning on an ion blower to blow air toward the user when the secondary release is triggered; The monitoring device monitors the items carried by the user to determine whether they are carrying flammable or explosive items. If so, the first monitoring result is displayed as abnormal.

3. The data center fire prevention method combining the Internet of Things and artificial intelligence according to claim 1 is characterized in that: Specifically, judging whether there is an abnormal risk in the current temperature sensor reading based on the analysis results includes: The sampling period T is preset and collected in the form of random sampling Multiple real-time temperature values ​​within a time period, where t is an arbitrary start time and N is a positive integer; The time axis is the horizontal axis, and the real-time temperature value is the vertical axis. Construct a two-dimensional coordinate system for the coordinate origin. At this time, there are multiple horizontal coordinates in the two-dimensional coordinate system. Discrete points within a range; A first straight line can be obtained by fitting all discrete points, and the first straight line is defined as the temperature standard line of the current period; Use the temperature standard line to compare the next Multiple real-time temperature values ​​within a time period are used to determine abnormalities. The judgment method is as follows: Calculate the shortest distance between the discrete points formed by multiple real-time temperature values ​​within the time range of (t+NT, t+2NT) and the temperature standard line, and count the number Q of discrete points whose shortest distance is greater than the third threshold. If the number of discrete points Q accounts for more than a fourth ratio threshold of the total number of samples, it is determined that there is a risk of abnormality in the current temperature sensor reading.

4. The data center fire prevention method combining the Internet of Things and artificial intelligence according to claim 1 is characterized in that: Specifically, the process of obtaining the third monitoring result includes: The infrared image is pre-processed and then input into a pre-trained BP neural network. It is determined whether there is a flame in the infrared image based on the output result of the BP neural network. If so, it is determined that the third monitoring result is abnormal.

5. The data center fire prevention system that combines the Internet of Things and artificial intelligence is characterized by: The steps of the data center fire prevention method combining the Internet of Things and artificial intelligence as described in any one of claims 1 to 4 above are applied, and the system includes: A gate, provided at the entrance of the data center, for performing static elimination on the user and monitoring whether the user is carrying flammable and explosive items when the user enters the data center computer room, and obtaining a first monitoring result; Fire alarm system, including, A temperature sensor group is pre-arranged in the central computer room, and the temperature sensor group is used to collect temperature data sets. Sound and light alarm, used for sound and light alarm during operation, Multiple infrared cameras are pre-placed in the central computer room to collect infrared images; A fire extinguishing system for extinguishing fires upon receiving corresponding control signals; A smoke exhaust system, for exhausting smoke upon receiving a corresponding control signal; The control system is in communication with the gate machine, fire alarm system, fire extinguishing system and smoke exhaust system, and is used to: Obtain the first monitoring result. If the first monitoring result is abnormal, inform the on-duty personnel to conduct an investigation. After the investigation is completed, allow the user to enter the data center room. Acquire a temperature data set collected by a temperature sensor group pre-arranged in the fire alarm system, analyze the temperature data set, and obtain a second monitoring result. When the second monitoring result is abnormal, the sound and light alarm is controlled to operate, and then the start and stop signal of the fire extinguishing system is obtained, and the fire extinguishing system is controlled to operate accordingly according to the start and stop signal of the fire extinguishing system; Obtain an infrared image captured by an infrared camera pre-arranged in the fire alarm system, analyze the infrared image, and obtain a third monitoring result. When the third monitoring result is abnormal, the sound and light alarm is controlled to operate, the staff is informed to evacuate, and the fire extinguishing system and the smoke exhaust system are controlled to be turned on.

Images