Fire early warning method, device and equipment and storage medium
Through multi-sensor information fusion and deep learning technology, the severity of fire in the data center computer room is evaluated, and the fire alarm level is determined using fuzzy logic algorithms, which solves the problem of lack of intelligent fire alarms and achieves efficient fire early warning and loss reduction effects.
Patent Information
- Application Number
- CN202411730291.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-28
- Publication Date
- 2025-03-04
AI Technical Summary
Currently, there is a lack of intelligent alarms for fires in data centers, especially in the early stages of the fire, which makes it impossible to detect dangerous situations in a timely manner.
By fusion of multi-sensor information, we use a long-term memory network to evaluate the severity of fire by obtaining carbon monoxide concentration, smoke concentration and temperature data, and use a long-term memory network to determine the fire alarm level, and combine a fuzzy logic algorithm to achieve intelligent alarm.
It improves the ability to predict fires in advance, detect fire situations early, reduces disaster losses, and achieves accurate assessment of fires and intelligent alarms.
Smart Images
Figure CN119559742A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a fire early warning method, device, equipment and storage medium. Background Art
[0002] With the development of technologies such as cloud computing, the Internet of Things, and artificial intelligence, the amount of global data continues to grow. This requires data centers to be continuously expanded and upgraded to cope with the growing demand for data storage and processing. At home and abroad, the information centers of various industries and units have data centers for data storage and computing. For some financial data centers, due to the particularity of the financial industry and the requirements for data security and reliability, financial data centers must implement strict security measures to protect customers' sensitive information and financial security.
[0003] Once a fire occurs in a data center computer room, it will have immeasurable consequences for IT equipment, so it is necessary to quickly, accurately and effectively detect fires in data center computer rooms to ensure the safe and stable operation of the data center. However, current research on computer room fires mainly focuses on fire prevention and fire extinguishing measures and fire extinguishing systems after a fire occurs. There are still some deficiencies in intelligent alarms after a fire occurs in a computer room. For example, the lack of accuracy in the recognition of the early stage of a fire leads to the inability to detect the danger in time at the early stage of a fire. Summary of the invention
[0004] The present invention provides a fire early warning method, device, equipment and storage medium to solve the problem of intelligent fire alarm.
[0005] In a first aspect, the present invention provides a fire early warning method, comprising:
[0006] Acquiring sensor collected data, wherein the sensor collected data includes carbon monoxide concentration data, smoke concentration and temperature data;
[0007] Processing the sensor collected data using a long short-term memory network to obtain the severity of the fire;
[0008] The fire severity and fuzzy logic algorithm are used to determine the fire alarm level, and a fire warning is performed according to the fire alarm level.
[0009] In a second aspect, the present invention provides a fire warning device, comprising:
[0010] A data acquisition module, used to acquire sensor collected data, wherein the sensor collected data includes carbon monoxide concentration data, smoke concentration and temperature data;
[0011] A fire severity determination module, for processing the sensor collected data using a long short-term memory network to obtain the fire severity;
[0012] The fire warning module is used to determine the fire alarm level by using the fire severity and fuzzy logic algorithm, and to issue a fire warning according to the fire alarm level.
[0013] In a third aspect, the present invention provides an electronic device, the electronic device comprising:
[0014] at least one processor;
[0015] and a memory communicatively coupled to the at least one processor;
[0016] The memory stores a computer program executable by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the fire warning method of the first aspect.
[0017] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, which are used to implement the fire warning method of the first aspect when executed by a processor.
[0018] The fire warning scheme provided by the present invention collects three different types of environmental data, and uses the long short-term memory network to accurately assess the severity of the fire, and then uses the fuzzy logic algorithm to determine the fire alarm level under the current fire severity, and finally realizes intelligent alarm according to the level. This scheme adopts the multi-sensor information fusion method to accurately assess the fire situation, improve the ability to predict fire in advance, detect fire early, and reduce disaster losses.
[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0021] Figure 1 is a flow chart of a fire warning method provided according to Embodiment 1 of the present invention;
[0022] Figure 2is a flow chart of a fire warning method provided according to Embodiment 2 of the present invention;
[0023] Figure 3 This is a schematic diagram of a fire warning process provided according to Embodiment 2 of the present invention;
[0024] Figure 4 is a structural schematic diagram of a fire warning device provided according to Embodiment 3 of the present invention;
[0025] Figure 5 It is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. DETAILED DESCRIPTION
[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In the description of the present invention, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are an "or" relationship. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0028] Embodiment 1
[0029] Figure 1A flowchart of a fire warning method is provided for the first embodiment of the present invention. This embodiment is applicable to the situation of warning a fire in a computer room. The method can be executed by a fire warning device. The fire warning device can be implemented in the form of hardware and / or software. The fire warning device can be configured in an electronic device. The electronic device can be composed of two or more physical entities or one physical entity.
[0030] like Figure 1 As shown, a fire warning method provided in the first embodiment of the present invention specifically includes the following steps:
[0031] S101. Acquire sensor collected data, wherein the sensor collected data includes carbon monoxide concentration data, smoke concentration and temperature data.
[0032] In this embodiment, carbon monoxide sensors, smoke sensors and temperature sensors may be arranged in advance in the machine room, and these sensors are used to obtain fire characteristic parameters, namely, carbon monoxide concentration data, smoke concentration data and temperature data.
[0033] Specifically, fires in computer rooms can be roughly divided into two stages: smoldering fire and open fire. In different fire stages, the changing trends of characteristic parameters collected by various sensors are usually different. When the computer room is in the smoldering fire stage, flammable materials such as cable insulation begin to melt after being heated, and the heat released is relatively small. The temperature at this time is not much different from the surrounding environment. At the same time, due to the large proportion of incomplete combustion of combustibles, the CO concentration and smoke concentration continue to increase. When it develops to the open fire stage, the combustibles in the smoldering stage gradually burn fully and begin to release a large amount of heat, so the temperature will rise rapidly. The released smoke will change within a higher level, and the growth rate of CO concentration will slow down. In different computer room environments, the time for smoldering fire to evolve into open fire is also different.
[0034] S102: Process the sensor collected data using a long short-term memory network to obtain the severity of the fire.
[0035] In this embodiment, a pre-trained long short-term memory network can be used to process sensor collected data, and the model can evaluate the severity of the fire.
[0036] S103: Determine a fire alarm level using the fire severity and a fuzzy logic algorithm, and issue a fire warning according to the fire alarm level.
[0037] In this embodiment, the fuzzy logic algorithm can be used to calculate the severity of the fire, thereby obtaining the fire alarm level. Different fire warning methods can correspond to different fire alarm levels.
[0038] The technical solution of the embodiment of the present invention collects three different types of environmental data, and uses the long short-term memory network to accurately assess the severity of the fire, and then uses the fuzzy logic algorithm to determine the fire alarm level under the current fire severity, and realizes intelligent alarm according to the level. This solution uses a multi-sensor information fusion method to accurately assess the fire situation, improve the ability to predict fire in advance, detect fire conditions early, and reduce disaster losses.
[0039] Optionally, the sensor collected data also includes the collection time corresponding to the carbon monoxide concentration data, the collection time corresponding to the smoke concentration and the collection time corresponding to the temperature data.
[0040] Optionally, before using the fire severity and the fuzzy logic algorithm to determine the fire alarm level, it also includes: obtaining the design specification requirement information of the computer room, and determining the protection level of the computer room based on the design specification requirement information; wherein, using the fire severity and the fuzzy logic algorithm to determine the fire alarm level includes: using a fuzzy logic algorithm to perform fuzzy calculations on the fire severity and the protection level to obtain the fire alarm level.
[0041] For example, the design specification requirement information may be the electronic information system computer room design specification GB50174-2008. The protection level is determined according to the use nature, management requirements and economic and social importance of the computer room, which can be specifically divided into three levels: A, B and C.
[0042] Among them, according to the above specifications, it can be determined that the computer room that meets one of the following conditions can be Class A:
[0043] (1) The interruption of the operation of the electronic information system will cause significant economic losses;
[0044] (2) The interruption of the operation of electronic information systems will cause serious disorder in public places.
[0045] A computer room that meets any of the following conditions can be considered Class B:
[0046] (1) The interruption of the operation of the electronic information system will cause great economic losses;
[0047] (2) Interruption of the operation of electronic information systems will cause disorder in public places.
[0048] The remaining computer rooms that are not in Class A or Class B are Class C. Different levels require different firefighting resources, so the protection level can be included in the reference factors for determining the fire alarm level. Therefore, the fuzzy logic algorithm can be used to perform fuzzy calculations on the severity of the fire and the protection level, so as to obtain the fire alarm level.
[0049] Optionally, network equipment and power equipment are installed in the computer room.
[0050] Specifically, the computer room described in this embodiment may be a computer room of a data center. A large number of high-density devices such as servers and network devices are usually arranged in the computer room of a data center. These devices are concentrated in a relatively small space. Once a fire occurs, the fire will spread easily. In addition, there are a large number of power equipment in the computer room, which will intensify the fire and increase the risk of fire spread. Since the computer room of a data center stores a large amount of important data, the data center has high fire extinguishing requirements and needs to avoid secondary damage.
[0051] There are various fire risks in the computer room, mainly the risk of electrical equipment failure. The main reasons for the risk of electrical failure include: 1) Due to the particularity of the computer room layout, a large number of cables for AC and DC power supply and data exchange will be laid under the anti-static floor of the computer room. These cables are piled together, which is easy to cause various electrical failures. 2) There are many types of electrical equipment in the computer room. Since there are a large number of power supply and power consumption equipment such as UPS equipment, air conditioners and power distribution equipment in the computer room, most of these equipment are low-voltage DC power supply and are in a 24-hour working state, it is easy to cause the aging of the insulation material in the equipment, resulting in short circuits or poor contact and other failures, which are easy to cause computer room fires. 3) The equipment in the computer room is densely arranged, and the equipment generates a lot of heat when running, and the heat dissipation in the space is uneven. When the equipment position is not reasonably distributed, it is easy to cause the hot and cold channels in the computer room to conflict with each other, resulting in local overtemperature in the computer room, which is easy to cause electrical failures and fires in the computer room. In summary, the fire in the computer room of the data center is more complex and risky than traditional fires. Therefore, more professional and comprehensive preventive measures need to be taken to ensure the safety and stable operation of the data center.
[0052] Embodiment 2
[0053] Figure 2 This is a flow chart of a fire warning method provided in the second embodiment of the present invention. The technical solution of the embodiment of the present invention is further optimized on the basis of the above-mentioned optional technical solutions, and provides a specific method for warning a fire in a computer room.
[0054] Optionally, the processing of the sensor collected data using the long short-term memory network to obtain the severity of the fire includes: inputting the carbon monoxide concentration data and the corresponding collection time, the smoke concentration and the corresponding collection time, and the temperature data and the corresponding collection time into the long short-term memory network to obtain the severity of the fire. The advantage of this setting is that it fully utilizes the time accumulation effect of the sensor collected data, uses the long short-term memory network to accurately determine the severity of the fire, reduces the false alarm rate, and achieves rapid fire identification.
[0055] Optionally, before the fuzzy calculation of the fire severity and the protection level using a fuzzy logic algorithm to obtain the fire alarm level is performed, it also includes: determining abnormal data from the sensor collected data, and determining the duration of the abnormal data according to the collection time corresponding to the abnormal data; wherein, the fuzzy calculation of the fire severity and the protection level using a fuzzy logic algorithm to obtain the fire alarm level includes: fuzzy calculation of the fire severity, the protection level and the duration of the abnormal data using a fuzzy logic algorithm to obtain the fire alarm level. The advantage of this setting is that by integrating the fire severity represented by CO concentration, temperature and smoke, the protection level of the computer room and the duration of the abnormal data, the recognition accuracy and early warning capability of computer room fires are improved.
[0056] Optionally, the fire warning according to the fire alarm level includes: when the fire alarm level is greater than a preset level, sending fire prompt information to the mobile terminal through the network, and performing a fire alarm operation through the network; when the fire alarm level is less than or equal to the preset level, sending fire warning prompt information to the mobile terminal through the network. The advantage of this setting is that by setting the preset level, the severity of the fire is accurately divided, avoiding the waste of police force.
[0057] like Figure 2 As shown, a fire warning method provided by Embodiment 2 of the present invention specifically includes the following steps:
[0058] S201. Acquire sensor collected data, wherein the sensor collected data includes carbon monoxide concentration data and corresponding collection time, smoke concentration and corresponding collection time, and temperature data and corresponding collection time.
[0059] For example, Figure 3 Figure 1 is a schematic diagram of a fire warning process. Figure 3 As shown, the sensor (i.e. Figure 3 The three types of detectors in the example (a) collect environmental (such as computer room) data and normalize the data.
[0060] S202: input the carbon monoxide concentration data and the corresponding collection time, the smoke concentration and the corresponding collection time, and the temperature data and the corresponding collection time into a long short-term memory network to obtain the severity of the fire.
[0061] Specifically, when a fire occurs in the computer room, the data collected by each sensor will begin to show abnormalities. As time goes by, the abnormality may be a transition from smoldering fire to open flame, and the sensor data collection has a certain time accumulation effect. The abnormality may also be affected by some interference signals or noise, and there is actually no fire in the computer room. Therefore, in order to make full use of the time accumulation effect of sensor data collection, reduce the false alarm rate, and achieve rapid fire identification. Figure 3 As shown in the figure, after normalizing the collected data, fire characteristics can be identified, hidden characteristics of fire characteristics can be discovered, and long short-term memory networks can be used to process sensor data with time characteristics to obtain the severity of the fire. Figure 3 The severity of a fire is characterized by the probability of open flames and the probability of smoldering fire shown in .
[0062] S203: Acquire design specification requirement information of the computer room, and determine the protection level of the computer room according to the design specification requirement information.
[0063] S204: Determine abnormal data from the sensor collected data, and determine the duration of the abnormal data according to the collection time corresponding to the abnormal data.
[0064] Specifically, the duration of abnormal data is closely related to the duration of the fire, and the duration of the fire is related to the fire alarm level. If the fire lasts longer, it means that the fire is more serious and the corresponding fire alarm level will be higher. The safety thresholds of the data collected by the three types of sensors can be set in advance, and the sensor collected data greater than the corresponding safety thresholds can be determined as abnormal data. According to the collection time corresponding to each abnormal data, the duration of the abnormal data can be determined.
[0065] S205. Perform fuzzy calculation on the fire severity, the protection level and the abnormal data duration using a fuzzy logic algorithm to obtain a fire alarm level.
[0066] Specifically, Figure 3 As shown, the fire severity, protection level and abnormal data duration (i.e., fire duration) are fuzzily calculated using fuzzy logic algorithm (i.e., fuzzy reasoning decision), so that the fire (alarm) level can be obtained.
[0067] S206: Determine whether the fire alarm level is greater than a preset level. If so, execute step 207; if not, execute step 208.
[0068] S207. Send fire warning information to the mobile terminal through the network, and perform fire alarm operation through the network.
[0069] Specifically, if the fire alarm level is greater than the preset level, it means that the current fire in the computer room is more serious. It is necessary to send a fire warning message to the mobile terminal equipped by the operation and maintenance personnel through the network, and dial the fire alarm number through the network, that is, to perform the fire alarm operation. Among them, the fire warning information can include the fire alarm level, the location of the computer room where the fire occurred, and the duration of abnormal data.
[0070] S208. Send fire warning information to the mobile terminal via the network.
[0071] Specifically, if the fire alarm level is less than or equal to the preset level, it means that the current fire in the computer room is still in the early stages, and the fire extinguishing equipment in the computer room can be used to extinguish the fire without calling the fire alarm. Fire warning information can be sent to the mobile terminal equipped by the operation and maintenance personnel through the network. Among them, the fire warning information may include information such as the fire alarm level, the location of the computer room where the fire occurred, the duration of abnormal data, and the location of the fire extinguisher in the computer room.
[0072] The fire warning method provided by the embodiment of the present invention makes full use of the time accumulation effect of sensor data collection, uses the long short-term memory network to accurately determine the severity of the fire, reduces the false alarm rate, and achieves rapid fire identification. By integrating the fire severity represented by CO concentration, temperature and smoke, the computer room protection level and the duration of abnormal data, the recognition accuracy and warning capability of the computer room fire are improved. By setting preset levels, the severity of the fire is accurately divided, avoiding the waste of police force.
[0073] Embodiment 3
[0074] Figure 4 This is a schematic diagram of the structure of a fire warning device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: a data acquisition module 301, a fire severity determination module 302 and a fire warning module 303, wherein:
[0075] A data acquisition module, used to acquire sensor collected data, wherein the sensor collected data includes carbon monoxide concentration data, smoke concentration and temperature data;
[0076] A fire severity determination module, for processing the sensor collected data using a long short-term memory network to obtain the fire severity;
[0077] The fire warning module is used to determine the fire alarm level by using the fire severity and fuzzy logic algorithm, and to issue a fire warning according to the fire alarm level.
[0078] The fire warning device provided by the embodiment of the present invention collects three different types of environmental data, and uses the long short-term memory network to accurately evaluate the severity of the fire, and then uses the fuzzy logic algorithm to determine the fire alarm level under the current fire severity, and realizes intelligent alarm according to the level. This device uses a multi-sensor information fusion method to accurately evaluate the fire situation, improve the ability to predict fire in advance, detect fire conditions early, and reduce disaster losses.
[0079] Optionally, the sensor collected data also includes the collection time corresponding to the carbon monoxide concentration data, the collection time corresponding to the smoke concentration and the collection time corresponding to the temperature data.
[0080] Optionally, the fire severity determination module is specifically used to input the carbon monoxide concentration data and the corresponding collection time, the smoke concentration and the corresponding collection time, and the temperature data and the corresponding collection time into a long short-term memory network to obtain the fire severity.
[0081] Optionally, the device further comprises:
[0082] The protection level determination module is used to obtain the design specification requirement information of the computer room before determining the fire alarm level using the fire severity and fuzzy logic algorithm, and determine the protection level of the computer room according to the design specification requirement information.
[0083] Optionally, the fire severity determination module is specifically used to perform fuzzy calculation on the fire severity and the protection level using a fuzzy logic algorithm to obtain a fire alarm level.
[0084] Optionally, the device further comprises:
[0085] The duration module is used to determine abnormal data from the sensor collected data before using the fuzzy logic algorithm to perform fuzzy calculation on the fire severity and the protection level to obtain the fire alarm level, and determine the abnormal data duration according to the collection time corresponding to the abnormal data.
[0086] Optionally, the fire severity determination module is specifically used to perform fuzzy calculation on the fire severity, the protection level and the abnormal data duration using a fuzzy logic algorithm to obtain a fire alarm level.
[0087] Optionally, the fire warning module includes:
[0088] A fire alarm unit, used to send fire warning information to the mobile terminal through the network when the fire alarm level is greater than a preset level, and perform fire alarm operations through the network;
[0089] The fire warning unit is used to send fire warning prompt information to the mobile terminal through the network when the fire alarm level is less than or equal to the preset level.
[0090] Optionally, network equipment and power equipment are installed in the computer room.
[0091] The fire warning device provided in the embodiment of the present invention can execute the fire warning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0092] Embodiment 4
[0093] Figure 5 A schematic diagram of the structure of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0094] like Figure 5 As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.
[0095] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0096] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as a fire warning method.
[0097] In some embodiments, the fire warning method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the fire warning method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the fire warning method in any other appropriate manner (e.g., by means of firmware).
[0098] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0099] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0100] The computer device provided above can be used to execute the fire warning method provided in any of the above embodiments, and has corresponding functions and beneficial effects.
[0101] Embodiment 5
[0102] In the context of the present invention, a computer-readable storage medium may be a tangible medium, wherein the computer-executable instructions, when executed by a computer processor, are used to perform a fire warning method, the method comprising:
[0103] Acquiring sensor collected data, wherein the sensor collected data includes carbon monoxide concentration data, smoke concentration and temperature data;
[0104] Processing the sensor collected data using a long short-term memory network to obtain the severity of the fire;
[0105] The fire severity and fuzzy logic algorithm are used to determine the fire alarm level, and a fire warning is performed according to the fire alarm level.
[0106] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by an instruction execution system, device or equipment or used with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0107] The computer device provided above can be used to execute the fire warning method provided in any of the above embodiments, and has corresponding functions and beneficial effects.
[0108] It is worth noting that in the embodiment of the above-mentioned fire warning device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0109] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A fire warning method, applied to a computer room, characterized in that: include: Acquiring sensor collected data, wherein the sensor collected data includes carbon monoxide concentration data, smoke concentration and temperature data; Processing the sensor collected data using a long short-term memory network to obtain the severity of the fire; The fire severity and fuzzy logic algorithm are used to determine the fire alarm level, and a fire warning is performed according to the fire alarm level.
2. The method according to claim 1, characterized in that The sensor collected data also includes the collection time corresponding to the carbon monoxide concentration data, the collection time corresponding to the smoke concentration and the collection time corresponding to the temperature data.
3. The method according to claim 2, characterized in that The method of processing the sensor collected data using a long short-term memory network to obtain the severity of the fire includes: The carbon monoxide concentration data and the corresponding collection time, the smoke concentration and the corresponding collection time, and the temperature data and the corresponding collection time are input into a long short-term memory network to obtain the severity of the fire.
4. The method according to any one of claims 1 to 3, characterized in that Before determining the fire alarm level by using the fire severity and the fuzzy logic algorithm, the method further includes: Obtaining design specification requirement information of the computer room, and determining the protection level of the computer room according to the design specification requirement information; Wherein, the method of determining the fire alarm level by using the fire severity and fuzzy logic algorithm includes: The fire severity and the protection level are fuzzily calculated using a fuzzy logic algorithm to obtain a fire alarm level.
5. The method according to claim 4, characterized in that Before the fuzzy calculation of the fire severity and the protection level by using the fuzzy logic algorithm to obtain the fire alarm level, the method further includes: Determine abnormal data from the sensor collected data, and determine the duration of the abnormal data according to the collection time corresponding to the abnormal data; The method of using a fuzzy logic algorithm to perform fuzzy calculation on the fire severity and the protection level to obtain a fire alarm level includes: The fire severity, the protection level and the duration of the abnormal data are fuzzily calculated using a fuzzy logic algorithm to obtain a fire alarm level.
6. The method according to claim 1, characterized in that The fire warning according to the fire alarm level includes: When the fire alarm level is greater than a preset level, a fire prompt message is sent to the mobile terminal through the network, and a fire alarm operation is performed through the network; When the fire alarm level is less than or equal to the preset level, a fire warning prompt message is sent to the mobile terminal through the network.
7. The method according to claim 1, characterized in that Network equipment and power equipment are installed in the computer room.
8. A fire warning device, characterized in that: include: A data acquisition module, used to acquire sensor collected data, wherein the sensor collected data includes carbon monoxide concentration data, smoke concentration and temperature data; A fire severity determination module, for processing the sensor collected data using a long short-term memory network to obtain the fire severity; The fire warning module is used to determine the fire alarm level by using the fire severity and fuzzy logic algorithm, and to issue a fire warning according to the fire alarm level.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the fire warning method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the fire warning method according to any one of claims 1 to 7 when executed.