KR20220164960A - System and method for fire prevention of vehicle based on artificial intelligence - Google Patents

Abstract

An artificial intelligence based vehicle fire prevention system and method are disclosed. The present invention provides a system for preventing a fire from occurring in a vehicle battery based on artificial intelligence, the system comprising a sensing unit for sensing state information of the vehicle battery, a fire suppression device for spraying fire extinguishing liquid to the vehicle battery based on the state information, and a control unit for executing a clustering-based algorithm that generates fire occurrence information of the vehicle battery based on the state information and controlling the fire suppression device based on the results of the clustering-based algorithm.

Description

AI-based vehicle fire prevention system and method {SYSTEM AND METHOD FOR FIRE PREVENTION OF VEHICLE BASED ON ARTIFICIAL INTELLIGENCE}

The present invention relates to an artificial intelligence-based vehicle fire prevention system and method. More specifically, when a fire occurs or there is a sign of a fire in a vehicle battery, it is detected in real time through artificial intelligence and fire extinguishing agent is sprayed so that the fire can be entered at an early stage. It is about.

An artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, machines learn, judge, and become smarter on their own. The more AI systems are used, the higher the recognition rate and the more accurate understanding of user preferences, so existing rule-based smart systems are gradually being replaced by deep learning-based AI systems.

Artificial intelligence technology consists of machine learning (deep learning) and element technologies using machine learning. Machine learning is an algorithm technology that classifies/learns the characteristics of input data by itself, and element technology is a technology that utilizes machine learning algorithms such as deep learning, such as linguistic understanding, visual understanding, inference/prediction, knowledge expression, motion control, etc. consists of the technical fields of

Recently, with the development of electric vehicle technology, vehicles are beginning to include high-capacity vehicle batteries. In particular, vehicle batteries have a structure in which a plurality of batteries such as lithium ion batteries are intensively packed, and thus generate high-temperature heat during operation and have a high possibility of fire due to the high-temperature heat.

Vehicle batteries not only have a high possibility of fire, but also have a problem of rapidly spreading at the same time as a fire occurs due to a chemical reaction caused by a moisture reaction of an alkali metal in the event of a fire.

Most of the existing prior art to solve this problem discloses the use of a general powder fire extinguishing agent as a fire extinguishing agent, but due to the rapid chemical reaction caused by the moisture reaction of alkali metals and structural damage in the event of a fire, general powder fire extinguishing agents are used to suppress fire. The effect is insignificant, and there is a limit to preventing fatal damage to the battery.

In addition, when a fire occurs in the battery, the operation of the solid aerosol fire extinguisher unit, the powder fire extinguisher unit, and the liquid fire extinguisher unit depends on the normal operation of the monitoring unit, so if a problem occurs in the monitoring unit, the fire cannot be extinguished appropriately at the beginning. there is a problem.

Therefore, in order to properly solve the above problems, even though one type of fire extinguishing agent is used, it is necessary to develop a fire extinguishing agent that not only has an excellent fire suppression effect on the battery, but also can minimize damage to the battery in contact with the fire extinguishing agent. to be.

In addition, the present applicant recognizes the above problems, and even though only a liquid type fire extinguishing agent is used, it is possible to suppress damage to the battery and maximize the fire suppression effect at the same time due to the effect of mixing between the components included therein, as well as to maximize the fire suppression effect, We have come to invent an artificial intelligence-based vehicle fire prevention system and method capable of detecting whether there is a fire in real time through artificial intelligence and extinguishing the fire according to the real-time detection result.

KR 10-2064416 B1

An object of the present invention is to provide an AI-based vehicle fire protection system and method.

In addition, an object of the present invention is to receive state information from a vehicle battery and apply a clustering technique based on the state information to detect a fire or fire risk of a battery in real time without smoke or flame.

In addition, an object of the present invention is to extinguish a fire early by detecting it in real time and injecting an extinguishing agent when fire occurrence information is generated in real time.

In addition, an object of the present invention is to prevent the occurrence of fire at an early stage through a coating layer on a battery cell included in a battery pack.

In order to solve the above problems, the present invention is an artificial intelligence-based system for preventing a fire occurring in a vehicle battery, a sensing unit for detecting state information of the vehicle battery, and the vehicle battery based on the state information. Performing a clustering-based algorithm for generating fire occurrence information for the vehicle battery based on a fire suppression device for spraying extinguishing fluid and the state information, and controlling the fire suppression device based on the result value of the clustering-based algorithm A control unit may be included, but the state information may include overcurrent occurrence information.

In addition, the fire extinguishing fluid includes a fire extinguishing agent, and the fire extinguishing agent contains 40 to 60 parts by weight of potassium nitrate, 40 to 60 parts by weight of ammonium phosphate, 40 to 60 parts by weight of sodium carbonate and 40 to 60 parts by weight of magnesium carbonate, based on 100 parts by weight of purified water. It may contain parts by weight.

The sensing unit may include an overcurrent detection sensor, and the control unit may input a measurement value received from the overcurrent detection sensor to the clustering-based algorithm.

In addition, the fire suppression device may include a tank for storing the extinguishing fluid, a spray nozzle for injecting the extinguishing fluid from the tank to the vehicle battery, and a valve for controlling the spray nozzle.

In addition, the tank includes a piston for applying pressure to the digestive fluid and a power generator for generating power for driving the piston, but the power generator may contain explosives.

In addition, in order to solve the above-described problems, the present invention provides a method for preventing fire in a vehicle based on artificial intelligence, comprising the steps of receiving state information of the vehicle battery and performing a clustering-based algorithm based on the state information. obtaining fire occurrence information of the vehicle battery based on a resultant value of the clustering-based algorithm, and controlling to spray a fire extinguishing liquid to the vehicle battery based on the fire occurrence information, including the state information may include overcurrent occurrence information.

In addition, in order to solve the above problems, the present invention is a non-transitory computer readable medium storing instructions, wherein the instructions, when executed by a processor, cause the processor to perform the above-described method, a non-transitory computer readable medium It can be a possible medium.

The present invention provides an artificial intelligence-based vehicle fire prevention system and method, which can effectively prevent fire that may occur in a vehicle battery in the full-scale electric vehicle era.

In addition, the present invention can receive state information from a vehicle battery and apply a clustering technique based on the state information to detect a fire or fire risk of a battery in real time without smoke or flame.

In addition, when the fire occurrence information is generated in real time, the present invention can detect it in real time and extinguish the fire early by spraying an extinguishing agent.

In addition, an object of the present invention is to prevent the occurrence of fire at an early stage through a coating layer on a battery cell included in a battery pack.

Through this, the present invention can have an effect of significantly reducing damages, costs, human casualties, and the like due to fire by preventing a fire in a vehicle battery used in an electric vehicle.

Effects obtainable according to the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below. will be.

1 and 2 are views schematically showing a vehicle according to the present invention.
3 is a diagram showing a control unit according to the present invention.
4 is a view showing a sensing unit according to the present invention.
5 and 6 are views showing a battery pack according to the present invention.
7 is a view showing a fire suppression device according to the present invention.
8 is a view showing an example of applying a fire suppression device according to the present invention.
9 is a view showing a vehicle fire prevention method according to the present invention.
10 is a diagram showing a graph to which a clustering-based algorithm according to the present invention is applied.
The accompanying drawings, which are included as part of the detailed description to aid understanding of the present specification, provide examples of the present specification and describe technical features of the present specification together with the detailed description.

Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings, but the same or similar elements are given the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted.

In addition, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the embodiment disclosed in this specification, the detailed description thereof will be omitted.

In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in this specification, the technical idea disclosed in this specification is not limited by the accompanying drawings, and all changes included in the spirit and technical scope of the present invention , it should be understood to include equivalents or substitutes.

Terms including ordinal numbers, such as first and second, may be used to describe various components, but the components are not limited by the terms. These terms are only used for the purpose of distinguishing one component from another.

Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, terms such as "comprise" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Hereinafter, a vehicle fire prevention system according to a preferred embodiment of the present specification will be described in detail based on the above information.

1 and 2 are views schematically showing a vehicle according to the present invention.

According to FIG. 1 , a vehicle 10 according to the present invention may include a control unit 100, a sensing unit 200, a battery pack 300, and a fire suppression device 400.

The battery pack 300 according to the present invention may mean a vehicle battery. That is, the battery pack 300 according to the present invention is a battery package manufactured for a vehicle, and may be installed on a lower plate of the vehicle and sealed with a housing to prevent external impact. Hereinafter, the battery pack 300 and the vehicle battery may be used interchangeably.

The sensing unit 200 according to the present invention may include at least one sensor and detect state information of a vehicle battery. The sensing unit 200 according to the present invention may transmit detected state information to the control unit 100 .

The fire suppression device 400 sprays the extinguishing liquid to the vehicle battery based on the state information, and whether or not to spray the extinguishing liquid may be controlled by the controller 100.

The control unit 100 according to the present invention may generate fire occurrence information for a vehicle battery based on state information. In addition, the control unit 100 may control other elements in the vehicle fire prevention system according to the present invention.

The control unit 100 according to the present invention may perform a clustering-based algorithm for generating fire occurrence information for a vehicle battery based on state information, and control the fire suppression device 400 based on a result value of the clustering-based algorithm. have. In this case, the clustering-based algorithm will be described later in detail in FIG. 10 .

The fire occurrence information may refer to information or data generated when it is determined that a fire has occurred in the vehicle battery based on state information. When fire occurrence information is generated, the controller 100 may determine that a fire has occurred in the vehicle battery.

According to Figure 2, it is confirmed that the vehicle fire protection system according to the present invention is installed in the vehicle. Vehicle fire protection system according to the present invention can be installed in the lower part of the vehicle. Since an electric vehicle may include a vehicle battery in the lower portion or lower plate of the vehicle, the vehicle fire prevention system according to the present invention may be installed at the corresponding location.

According to FIG. 2 , the system according to the present invention may include a housing of a vehicle battery and a spray nozzle 430 formed through the housing. A detailed description of this will be given later.

3 is a diagram showing a control unit according to the present invention.

According to FIG. 3 , the controller 100 according to the present invention may include a processor 110, a memory 120 and a communication module 130.

The processor 110 may execute commands stored in the memory 120 to control other components. The processor 110 may execute instructions stored in the memory 120 .

The processor 110 is a component capable of performing calculations and controlling other devices. Mainly, it may mean a central processing unit (CPU), an application processor (AP), a graphics processing unit (GPU), and the like. Also, the CPU, AP, or GPU may include one or more cores therein, and the CPU, AP, or GPU may operate using an operating voltage and a clock signal. However, while a CPU or AP consists of a few cores optimized for serial processing, a GPU may consist of thousands of smaller and more efficient cores designed for parallel processing.

The processor 110 may provide or process appropriate information or functions to a user by processing signals, data, information, etc. input or output through the components described above or by running an application program stored in the memory 120.

The memory 120 stores data supporting various functions of the control unit 100 . The memory 120 may store a plurality of application programs (application programs or applications) driven by the controller 100, data for operation of the controller 100, and commands. At least some of these application programs may be downloaded from the external controller 100 through wireless communication. In addition, the application program may be stored in the memory 120, installed in the control unit 100, and driven by the processor 110 to perform the operation (or function) of the control unit 100.

The memory 120 may be a flash memory type, a hard disk type, a solid state disk type, a silicon disk drive type, or a multimedia card micro type. ), card-type memory (eg SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read -only memory), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. Also, the memory 120 may include a web storage performing a storage function on the Internet.

The communication module 130 transmits and receives information with a base station or a camera having a communication function through an antenna. The communication module 130 may include a modulation unit, a demodulation unit, a signal processing unit, and the like.

Wireless communication may refer to communication using a wireless communication network using a communication facility previously installed by telecommunication companies and a frequency of the communication facility. At this time, the communication module 130 is CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), SC-FDMA (single carrier frequency division multiple access), and the like, as well as the communication module 130 can also be used for 3rd generation partnership project (3GPP) long term evolution (LTE). In addition, not only 5G communication, which is currently being commercialized, but also 6G, which is scheduled to be commercialized later, can be used. However, the present specification may utilize a pre-installed communication network without being bound by such a wireless communication method.

In addition, as a short range communication technology, Bluetooth, BLE (Bluetooth Low Energy), Beacon, RFID (Radio Frequency Identification), NFC (Near Field Communication), infrared communication (Infrared Data Association; IrDA) ), UWB (Ultra Wideband), ZigBee, etc. may be used.

4 is a view showing a sensing unit according to the present invention.

The sensing unit 200 according to the present invention may include at least one of a gas detection sensor 210, a temperature sensor 220, an acceleration sensor 230, a pressure sensor 240, and an overcurrent detection sensor 250. have. In addition, the control unit (100 in FIG. 1 ) measures measurements received from at least one of the gas detection sensor 210, the temperature sensor 220, the acceleration sensor 230, the pressure sensor 240, and the overcurrent detection sensor 250. Based on the value, fire occurrence information can be generated.

In this case, the state information according to the present invention may include at least one of gas generation information, temperature rise information, vehicle collision information, and overcurrent generation information.

For example, the sensing unit 200 may include a gas detection sensor 210 . When gas is sensed by the sensing unit 200, gas generation information may be generated. Also, the sensing unit 200 may include a temperature sensor 220 . When a temperature higher than a predetermined temperature value is sensed by the sensing unit 200, temperature rise information may be generated. Also, the sensing unit 200 may include an acceleration sensor 230 and a pressure sensor 240 . When predetermined acceleration values and pressure values are sensed by the sensing unit 200, vehicle collision information may be generated. Also, the sensing unit 200 may include an overcurrent detection sensor 250 . When a current greater than a predetermined current value is sensed by the sensing unit 200, overcurrent generation information may be generated.

In this way, when at least one of gas generation information, temperature rise information, vehicle collision information, and overcurrent generation information is generated, the control unit (100 in FIG. 1) according to the present invention determines that a fire has occurred in the vehicle battery or a state corresponding thereto And, the fire suppression device (400 in FIG. 1) can be driven. This has the effect of extinguishing a fire or preventing a fire.

5 and 6 are views showing a battery pack according to the present invention.

5 and 6 , a battery pack 300 according to the present invention may include a battery cell 310, a thermal pad 320, and a thermal management module 330. In addition, the battery pack 300 according to the present invention further includes a gas discharge pipe 340, as well as a housing 350 including a battery cell 310, a thermal pad 320, and a thermal management module 330. can include

The battery pack 300 according to the present invention includes a battery cell 310 in which a plurality of cell assemblies including a plurality of unit battery cells 310 are connected to obtain high output. Each unit battery cell 310 can be repeatedly charged and discharged by an electrochemical reaction between components including positive and negative current collectors, separators, active materials, electrolytes, and the like.

The battery pack 300 is used for controlling power supply to driving loads such as motors, measuring electrical characteristic values such as current or voltage, controlling charge/discharge, controlling voltage equalization, estimating SOC (State of Charge), and the like. A battery management system (BMS) that monitors and controls the state of a secondary battery by applying an algorithm may be additionally included.

Since the battery pack 300 including one or more battery cells 310 is manufactured in a form in which a plurality of secondary batteries (battery cells) are concentrated in a narrow space, it is important to easily dissipate heat generated from each secondary battery. do. To this end, the battery pack 300 may further include a thermal management module 330 mounted on the battery cell 310 having an air-cooled or water-cooled cooling passage to cool heat of the battery cell 310 .

The thermal management module 330 may cool heat generated from the battery cell 310 . The thermal management module 330 may be disposed under the battery cell 310 to support the battery cell 310 . The thermal management module 330 may be disposed in contact with the lower portion of the battery cell 310 .

The battery pack 300 may include a thermal pad 320 disposed between the battery cell 310 and the thermal management module 330 . The thermal pad 320 may be used as a medium for transferring heat generated in the battery cell 310 to the outside. The thermal pad 320 may be formed of a material having high thermal conductivity. The thermal pad 320 may be disposed between the battery cell 310 and the thermal management module 330 . In this case, the thermal pad 320 may transfer heat generated in the battery cell 310 to the thermal management module 330 .

In addition, the battery cell 310 according to the present invention may include a corrosion-resistant coating layer on the surface,

The coating layer is coated with an anti-corrosion coating composition, and the anti-corrosion coating composition may include a solvent, an epoxy resin, a curing agent and a dispersing agent.

Most of the fires occurring in the battery cell 310 are caused by overload due to high temperature heat generated during the operation of the battery cell 310, and furthermore, durability due to surface corrosion caused by long-term use of the battery cell 310. If this is weakened, there is a problem in that the possibility of fire increases.

Accordingly, the automatic fire extinguishing device of the present invention includes an anti-corrosion coating layer on the surface of the battery cell 310 to improve durability of the battery cell 310, thereby reducing the occurrence of fire itself in advance.

The solvent includes water (cold water, hot water), alcohol, anhydrous or hydrous lower alcohol having 1 to 4 carbon atoms (methanol, ethanol, alcohol, propanol, butanol, etc.), toluene, phenol, and a mixed solvent of the above alcohols and water. may be used, but is not limited thereto.

The epoxy resin serves to increase storage stability and protects the surface of the battery cell 310, bisphenol A type epoxy resin, bisphenol F type epoxy resin, novolac type epoxy resin, brominated flame retardant Epoxy resin, cycloaliphatic epoxy resin, rubber modified epoxy resin, aliphatic polyglycidyl type epoxy resin, etc. can be applied. As an example, a bisphenol F-type epoxy resin may be applied. In particular, the bisphenol F-type epoxy resin has a high content of phenol groups among functional groups and thus has high hardness and thus excellent chemical resistance.

The curing agent serves to improve film properties of the coating layer by shortening the reaction time, and may be an isocyanate-based compound, but is not limited thereto.

Preferably, the curing agent is an isocyanate-based compound, and more specifically, the curing agent may be a compound represented by Formula 1 below:

[Formula 1]

On the other hand, the dispersant serves to improve the storage stability of the coating agent by improving the interfacial area by increasing the dispersibility of various mixtures, and may be selected from alkali metal silicate and magnesium silicate, but preferably magnesium silicate It is preferable to use

More preferably, the anticorrosion coating composition may include 40 to 60 parts by weight of an epoxy resin, 10 to 30 parts by weight of a curing agent, and 10 to 30 parts by weight of a dispersant, based on 100 parts by weight of a solvent.

In the case of the above weight range, not only can the corrosion prevention effect of the surface of the battery cell 310 be maximized due to the synergistic effect of mixing each component, but also the durability of the battery cell 310 by maximizing the adhesion of the coating layer By improving the , there is an advantage in preventing a fire that may occur in the battery cell 310 in advance.

However, if it is less than the above weight range or exceeds the above weight range, the effect may be insignificant.

[Preparation Example 1: Preparation of anti-corrosion coating layer]

Preparation of coating composition

An anticorrosive coating composition was prepared by mixing an epoxy resin, a curing agent represented by Formula 1 below, and magnesium silicate as a dispersing agent in toluene as a solvent:

[Formula 1]

Specific weight ranges of the composition are shown in Table 1 below.

BT1 BT2 BT3 BT4 BT5 toluene 100 100 100 100 100 epoxy resin 35 40 50 60 65 curing agent 8 10 20 30 32 dispersant 8 10 20 30 32

(Unit: parts by weight) Preparation of coating layer

An anti-corrosion coating layer was formed by applying the compositions of BT1 to BT5 on the surface of the lithium-based battery cell 310 and thermally curing them.

[Experimental Example 1: Test of adhesion and anti-corrosion effect of anti-corrosion coating layer]

A coating layer was prepared by thermally curing the coating composition of Preparation Example 1 on an aluminum steel sheet test piece.

Adhesion test

Regarding the adhesion of the coating layer, the adhesion is measured according to KS D 6711 aluminum and aluminum alloy painted plates and baths, and the case where the coating surface is completely peeled off is set as 0, and the case where the coated surface is not peeled off at all is set as 10. The degree of adhesion was evaluated by an index. The results are shown in Table 5 below.

BT1 BT2 BT3 BT4 BT5 adhesiveness 5 8 9 8 5

(Unit: index) According to Table 2 above, when the surface of the battery cell 310 is coated with the anti-corrosion coating composition of the present invention, it can be confirmed that it exhibits relatively excellent adhesion. In particular, by BT2 to BT4 In this case, it can be seen that the adhesion is maximized.

Anti-corrosion effect test

After 200 hours of testing with a salt spray tester of KS D 9502, discoloration and deterioration were tested.

As a comparative example, it was set to a case where the coating layer was not formed, and the experimental results are shown in Table 3 below.

[Evaluation table]

○: Discoloration and discoloration do not occur.

△: Discoloration and deterioration occurred within 5%.

Χ: Discoloration and deterioration of 5% or more occurred.

comparative example BT1 BT2 BT3 BT4 BT5 corrosion resistance Χ △ ○ ○ ○ △

According to Table 3, when the coating layer is included on the surface of the battery cell 310 of the present invention, it can be seen that the corrosion prevention effect is superior to that of the comparative example, and in particular, the effect is maximized in the case of BT2 to BT4 it can be known that

That is, when the above range is satisfied, corrosion of the surface of the battery cell 310 is effectively prevented and durability is improved, thereby preventing a fire caused by high heat or the like in advance.

7 is a view showing a fire suppression device according to the present invention, and FIG. 8 is a view showing an example of applying the fire suppression device according to the present invention.

According to FIG. 7, the fire suppression device 400 according to the present invention may include a fire extinguishing agent 411 storage tank 410, a power generator 420, a spray nozzle 430 and a valve 440. The fire extinguishing agent 411 storage tank 410 may store the fire extinguishing agent 411 therein, and may include a piston part 412. Fire extinguishing agent 411 may be discharged to the outside of the tank by the piston movement of the piston unit 412. The piston unit 412 may receive power from the power generating unit 420 and perform a piston movement.

According to FIG. 8 , the power generation unit 420 according to the present invention may include explosive materials such as explosives and gunpowder. In the case of an urgent situation such as a traffic accident, since the movement of the piston part 412 may be impossible due to power supply being cut off, the system according to the present invention can drive the piston part 412 using the power of an explosive material. The power generation unit 420 may be operated by the control unit (100 in FIG. 1), and may be controlled to ignite the explosive material by the control unit (100 in FIG. 1).

According to FIG. 8, the fire extinguishing agent 411 according to the present invention may be ejected into the connecting pipe 413 by the piston part 412. The connection pipe 413 is a pipe formed by extending from the fire suppression device 400, and can inject the fire extinguishing agent 411 into the housing 350 of the battery pack (300 in FIG. 1). An injection nozzle 430 is installed at one end of the connection pipe 413, and the injection nozzle 430 may inject the fire extinguishing agent 411 toward the inside of the housing 350. The injection nozzle 430 is opened and closed by the valve 440, and the valve 440 may be controlled by the controller (100 in FIG. 1). In addition, gas generated by a fire inside the housing 350 may be discharged to the outside through the gas discharge pipe 340 .

The fire extinguishing agent 411 according to the present invention includes a fire extinguishing agent, and the fire extinguishing agent may contain a material selected from the group consisting of purified water, potassium nitrate, ammonium phosphate, sodium carbonate, magnesium carbonate and a mixture thereof as an active ingredient have.

The potassium nitrate is an inorganic compound having a chemical formula of KNO ₃ , a salt made of potassium ion K ⁺ and nitrate ion NO ₃ ^- , and is also called a saltpeter. Harmful by inhalation and skin contact. In case of eye contact, flush with plenty of boric acid and water.

Ammonium phosphate is a compound obtained by reacting phosphorus with ammonium, and there are three types of monoammonium phosphate, diammonium phosphate and triammonium phosphate. It is in the form of a fine powder like wheat flour, and can show a cooling effect, so it is also used as a component of powder fire extinguishers. Specifically, when spraying on a fire generating part, it sinks and prevents contact with oxygen so that the flame does not rise again.

The sodium carbonate is a compound of the formula Na ₂ CO ₃ and is a sodium salt of carbonic acid. In general, it is also called soda or soda carbonate, and anhydride is soda ash of white powder with strong hygroscopicity, and monohydrate, heptahydrate, and decahydrate are known. Specifically, it is used as a raw material for manufacturing glass and soap, and is also used as an alkali in paper manufacturing. Anhydrous is called soda ash, and decahydrate is called laundry soda or crystal soda.

The magnesium carbonate is a magnesium salt of carbonate, which is naturally produced as magnesite, and is a colorless crystal or powder. Anhydrous, monohydrate, trihydrate and pentahydrate are known. It is industrially produced and used as a raw material for manufacturing magnesium compounds or as an admixture for vulcanized rubber. Furthermore, it is used for flooring, fire prevention, fire extinguishing compositions, cosmetics, powdered toothpaste, etc., and is also used to maintain the color of food.

In the existing literature that discloses a fire extinguishing agent for suppressing a fire in a lithium-based battery, in order to minimize damage to the battery due to the reaction of alkali metal to moisture in the event of a fire. It discloses sequentially spraying solid aerosol fire extinguishing agent, powder fire extinguishing agent, and liquid fire extinguishing agent, and adding natural extracts in a certain weight range to components generally included in fire extinguishing agents to improve fire extinguishing ability. Prior literature on fire extinguishing agents is also disclosed.

However, the above existing prior literature had a problem of insignificant digestion or the hassle of using various types of fire extinguishing agents.

Therefore, despite the use of a liquid type fire extinguishing agent containing purified water, the synergistic effect of mixing the components constituting the fire extinguishing agent can maximize the fire extinguishing ability against the occurrence of fire while preventing damage to the battery. There are advantages to being

Furthermore, even if the fire extinguishing agent is stored for a long period of time, there is an advantage of improving the storage property by minimizing the change in the properties or physical properties of the fire extinguishing agent itself.

More specifically, the fire extinguishing agent preferably includes 40 to 60 parts by weight of potassium nitrate, 40 to 60 parts by weight of ammonium phosphate, 40 to 60 parts by weight of sodium carbonate and 40 to 60 parts by weight of magnesium carbonate, based on 100 parts by weight of purified water. .

In the case of the above weight range, the fire suppression effect can be maximized by the mixing action of each component, and storage stability can be improved by minimizing the change in the characteristics or physical properties of each component even when stored for a long time.

However, when it is less than or exceeds the above range, there is a problem that the effect is insignificant.

Preferably, the fire extinguishing agent may further include a compound represented by Formula 2 and a compound represented by Formula 3 as active ingredients:

[Formula 2]

[Formula 3]

here,

m is an integer from 0 to 4;

L ₁ and L ₂ are the same as or different from each other, and each independently represents a single bond or a substituted or unsubstituted alkylene group having 1 to 10 carbon atoms;

Ar ₁ and Ar ₂ are the same as or different from each other, and each independently represents a substituted or unsubstituted aryl group having 6 to 30 carbon atoms, a substituted or unsubstituted heteroaryl group having 3 to 30 carbon atoms, or a substituted or unsubstituted alkyl group having 1 to 20 carbon atoms. , A substituted or unsubstituted cycloalkyl group having 1 to 20 carbon atoms, a substituted or unsubstituted heteroalkyl group having 1 to 20 carbon atoms, a substituted or unsubstituted heterocycloalkyl group having 1 to 20 carbon atoms, a substituted or unsubstituted alkenyl group having 1 to 20 carbon atoms, It is selected from the group consisting of a substituted or unsubstituted cycloalkenyl group having 1 to 20 carbon atoms and a substituted or unsubstituted heteroalkenyl group having 1 to 20 carbon atoms,

R ₁ to R ₃ are the same as or different from each other, and each independently represents hydrogen, heavy hydrogen, halogen, a cyano group, a hydroxy group, a substituted or unsubstituted alkyl group having 1 to 30 carbon atoms, a substituted or unsubstituted alkenyl group having 2 to 30 carbon atoms, A substituted or unsubstituted alkynyl group having 2 to 24 carbon atoms, a substituted or unsubstituted heteroalkyl group having 2 to 30 carbon atoms, a substituted or unsubstituted aralkyl group having 6 to 30 carbon atoms, a substituted or unsubstituted aryl group having 5 to 30 carbon atoms, a substituted or Unsubstituted heteroaryl group having 2 to 30 carbon atoms, substituted or unsubstituted heteroarylalkyl group having 3 to 30 carbon atoms, substituted or unsubstituted cycloalkyl group having 3 to 20 carbon atoms, substituted or unsubstituted heterocycloalkyl group having 3 to 20 carbon atoms , It is selected from the group consisting of a substituted or unsubstituted cycloalkenyl group having 3 to 20 carbon atoms, a substituted or unsubstituted heteroaralkyl group having 3 to 30 carbon atoms, and a substituted or unsubstituted heteroalkenyl group having 1 to 20 carbon atoms,

The substituents of L ₁ , L ₂ , Ar ₁ , Ar ₂ and R ₁ to R ₃ are hydrogen, deuterium, cyano group, nitro group, halogen group, hydroxyl group, an alkyl group having 1 to 30 carbon atoms, and an alkenyl group having 2 to 30 carbon atoms. , C2-24 alkynyl group, C1-30 heteroalkyl group, C6-30 aralkyl group, C3-20 cycloalkyl group, C3-20 heterocycloalkyl group, C5-30 aryl group, Heteroaryl group having 2 to 30 carbon atoms, heteroarylalkyl group having 3 to 30 carbon atoms, alkoxy group having 1 to 30 carbon atoms, alkylsilyl group having 1 to 30 carbon atoms, arylsilyl group having 6 to 30 carbon atoms, and aryl having 6 to 30 carbon atoms It is substituted with a substituent selected from the group consisting of oxy groups, and when substituted with a plurality of substituents, they are the same as or different from each other.

More preferably, the compound represented by Formula 2 may be a compound represented by Formula 3 below:

[Formula 4]

More preferably, the compound represented by Formula 3 may be a compound represented by Formula 5 below:

[Formula 5]

On the other hand, preferably, the fire extinguishing agent is 40 to 60 parts by weight of potassium nitrate, 40 to 60 parts by weight of ammonium phosphate, 40 to 60 parts by weight of sodium carbonate, 40 to 60 parts by weight of magnesium carbonate, based on 100 parts by weight of purified water, Formula 2 It may include 10 to 30 parts by weight of the compound represented by Formula 2 and 10 to 30 parts by weight of the compound represented by Formula 2.

In the case of the above weight range, not only can the fire extinguishing ability for the fire occurring in the battery cell (310 in FIG. It has the advantage of maintaining the digestibility for a long time without changing its physical properties or characteristics.

However, if it is less than the above weight range or exceeds the above weight range, the effect may be insignificant.

[Production Example 2: Production of fire extinguishing agent of the present invention]

Potassium nitrate, ammonium phosphate, sodium carbonate, magnesium carbonate, a compound represented by Formula 3 and a compound represented by Formula 4 were mixed with purified water, maintained at 75° C., and stirred for 2 hours to prepare the fire extinguishing agent:

[Formula 4]

[Formula 5]

Specific parts by weight of the components constituting the fire extinguishing agent are shown in Table 4 below.

T1 T2 T3 T4 T5 T6 T7 T8 T9 T10 T11 T12 Purified water 100 100 100 100 100 100 100 100 100 100 100 100 potassium nitrate 35 40 50 60 65 50 50 50 50 50 50 50 Ammonium Phosphate 35 40 50 60 65 50 50 50 50 50 50 50 sodium carbonate 35 40 50 60 65 50 50 50 50 50 50 50 magnesium carbonate 35 40 50 60 65 50 50 50 50 50 50 50 Compound represented by Formula 3 - - - - - 20 - 8 10 20 30 32 Compound represented by Formula 4 - - - - - - 20 8 10 20 30 32

(Unit: parts by weight) [Experimental Example 2: Extinguishing effect test of the fire extinguishing agent of the present invention]

In order to test the extinguishing effect of the extinguishing agents of T1 to T12, a battery in which 60 lithium-based battery cells (310 in FIG. The time required for complete digestion was measured using a fire extinguisher.

The experiment was repeated 10 times and the result was expressed as an average value.

The results are shown in Table 5 below, and as a comparative example, the same experiment was performed with a fire extinguisher containing a dry chemical made of 70% by weight of ammonium phosphate, 10% by weight of graphite, and 20% by weight of silica.

On the other hand, 50 male and female test subjects in their 30s to 50s were recruited, and after the lithium-based battery was completely digested according to the above experiment, the degree of toxic gas odor such as carbon monoxide due to fire was evaluated.

The evaluation index is represented by an index of 1 to 10, and the higher the number, the less the smell of toxic gas.

minute (min) Indices T1 35 5 T2 27 7 T3 29 7 T4 28 7 T5 35 5 T6 25 6 T7 27 6 T8 29 6 T9 11 9 T10 9 9 T11 12 9 T12 27 6 comparative example 40 5

Looking at the results of Table 5, it can be seen that in the case of T1 to T12, there is an equal or higher extinguishing effect and toxic gas deodorizing effect than the comparative example.

In particular, in the case of T9 to T11, it can be confirmed that the effect is maximized.

[Experimental Example 3: Long-term storage test of the fire extinguishing agent of the present invention]

In order to test the long-term storage of the fire extinguishing agent of the present invention, the fire extinguishing agent of T1 to T12 was injected into the fire extinguisher and stored for one year. Then, in the same way as in Experimental Example 2, a fire is ignited in a battery in which 60 lithium-based battery cells (310 in FIG. 5) are stacked, and then a fire extinguisher containing T1 to T12 fire extinguishing agents stored for one year is sprayed. The experiment was conducted to extinguish the fire.

On the other hand, the same experiment was conducted with a fire extinguisher containing a powder fire extinguishing agent used as a comparative example in Experimental Example 2.

The experiment was repeated 10 times, and the results were shown as average values, as shown in Table 6 below.

[Evaluation table]

○: The fire that occurred was completely burned within 30 to 40 minutes.

△: The fire that occurred was completely burned within 50 to 60 minutes.

Χ: Fire extinguishing agent is not sprayed due to the change in physical properties of each composition.

evaluation T1 Χ T2 △ T3 △ T4 △ T5 Χ T6 △ T7 △ T8 △ T9 ○ T10 ○ T11 ○ T12 △ comparative example Χ

Looking at the results of Table 6, in the case of T1 to T12, it was confirmed that the long-term storage was equal or higher than that of Comparative Examples.

In particular, in the case of T9 to T11, it can be confirmed that the long-term storage effect of the fire extinguishing agent is maximized.

Hereinafter, a vehicle fire prevention method according to another preferred embodiment of the present specification will be described in detail based on the above information. In this case, the subject performing the vehicle fire prevention method may be the above-described system or a control unit (100 in FIG. 1) of the system.

9 is a view showing a vehicle fire prevention method according to the present invention.

According to FIG. 9 , a method for preventing fire in a vehicle including a vehicle battery according to the present invention includes receiving state information of the vehicle battery (S110), performing a clustering-based algorithm based on the state information (S120), Acquisition of fire occurrence information of the vehicle battery based on the resultant value of the clustering-based algorithm (S130) and controlling to spray a fire extinguishing liquid to the vehicle battery based on the fire occurrence information (S140), The information may include overcurrent occurrence information.

Receiving state information of the vehicle battery ( S110 ) may be a step of receiving state information sensed by the sensing unit ( 200 in FIG. 1 ). ), performing a clustering-based algorithm based on state information (S120) may be a step of performing the K-means clustering technique according to FIG. 10 described above. Obtaining fire occurrence information of the vehicle battery based on the resultant value of the clustering-based algorithm (S130) generates overcurrent occurrence information based on the distance information of the center values of clustering 1 and clustering 2 according to FIG. 10 described above, It may be a step of obtaining fire occurrence information based on overcurrent occurrence information. In the step of controlling to spray the fire extinguishing liquid to the vehicle battery based on the fire occurrence information (S140), the piston unit (412 in FIG. 7) is driven by controlling the power generator (420 in FIG. 7), and the piston unit (FIG. It may be a step of injecting the fire extinguishing agent (411 in FIG. 7) into the housing (350 in FIG. 8) of the battery pack (300 in FIG. 1) through the driving of 412 in 7).

At this time, the fire extinguishing agent (411 in FIG. 7) may include the fire extinguishing agent as described above, and since the fire extinguishing agent is the same as the above, detailed description thereof will be omitted. In addition, the vehicle battery according to the present invention may include a plurality of battery cells (310 in FIG. 5), and the plurality of battery cells (310 in FIG. 5) may include a coating layer of the anti-corrosion coating composition as described above. can At this time, since the anti-corrosion coating composition is the same as the above, a detailed description thereof will be omitted.

10 is a diagram showing a graph to which a clustering-based algorithm according to the present invention is applied.

According to FIG. 10 , the clustering-based algorithm according to the present invention is performed in the controller (100 in FIG. 1 ) and may be performed by commands stored in the memory of the controller ( 100 in FIG. 1 ). The clustering-based algorithm according to the present invention may classify each cluster based on the current value measured by the overcurrent detection sensor 250 .

According to FIG. 10 , based on features 1 and 2, the control unit ( 100 in FIG. 1 ) may cluster measurement values detected by the overcurrent detection sensor 250 . The control unit (100 in FIG. 1 ) may perform a step of clustering on the basis of each cluster, calculate evaluation indexes for features in the formed clusters, and use the evaluation indexes to generate fire or short circuits in battery cells in real time. It can be determined whether this occurs or not.

The control unit (100 in FIG. 1 ) extracts a feature based on the value detected by the sensing unit or the overcurrent detection sensor, forms a cluster from the extracted feature, calculates an evaluation index for the formed cluster, and uses the calculated evaluation index Based on this, by determining the number of clusters, it is possible to recognize in real time whether there is a fire or short circuit in the vehicle battery.

The controller ( 100 in FIG. 1 ) may calculate an average value for features in the formed cluster and calculate an evaluation index through the average value. At this time, the clustering technique used may use K-means clustering among clustering techniques. K-means clustering refers to clustering given data into K clusters. In this K-means clustering, after randomly selecting one sample value from a given data sample, the distance from the sample value to other sample data is measured. At this time, the nearest centroid is selected from each data sample, and the distance from the corresponding sample to another data sample value is calculated again. By repeating this process, clustering is achieved. That is, a plurality of clusters are created. This clustering technique can be mainly implemented in Python.

According to FIG. 10 , feature 1 and feature 2 may be the size of voltage (V) and current (A) of a battery cell. In this case, the control unit ( 100 in FIG. 1 ) may receive, from the sensing unit, magnitudes of voltages (V) and currents (A) of each of the plurality of battery cells, and cluster them.

The controller (100 in FIG. 1 ) may classify measurement values into clustering 1 and clustering 2 as a clustering result. The control unit (100 in FIG. 1 ) may calculate the first central value of clustering 1 through an average calculation method, and calculate the second central value of clustering 2 through an average calculation method.

The controller (100 in FIG. 1 ) calculates the distance between the first center value and the second center value, and when the size of the calculated distance is greater than a predetermined value, it is determined that a fire or short circuit has occurred in the corresponding battery cell. can That is, the control unit (100 in FIG. 1 ) may classify the information classified as cluster 2 as overcurrent occurrence information. The controller (100 in FIG. 1 ) may generate fire occurrence information based on the overcurrent occurrence information and control the fire suppression device 400 to be driven based on the fire occurrence information.

Specifically, the clustering technique according to the present invention may be as follows.

The clustering technique according to the present invention is an algorithm for performing K-means clustering, and may refer to an algorithm performed in the step of performing a clustering-based algorithm based on state information (S120). The step of performing the clustering-based algorithm based on the state information according to the present invention (S120) is the step of extracting random K pieces of data with respect to the electrical characteristic signal (S121), generating a plurality of clusters around the K pieces of data Step (S122), step of extracting the central value of each of the plurality of clusters (S123), step of extracting the median distance value between the respective center values (S123), data to the cluster with the shortest distance based on the median distance value It may include allocating (S124) and updating the center of the cluster including the allocated data (S125).

In the present invention, the median distance value may mean a distance value between clusters in a clustering process for generating two final clusters.

In this case, the electrical characteristic signal may include voltage (V) and current (A) signals for each of a plurality of battery cells included in the electric vehicle battery. Voltage (V) and current (A) signals for each battery cell will be described later.

In this case, the algorithm for performing the K-center clustering process based on the electrical characteristic signal may perform the clustering process according to Equation 1 representing the following Euclidean distance.

[Equation 1]

(However, d is a distance value, (x, y) is a coordinate value, x corresponds to voltage (V), and y corresponds to current (A))

According to FIG. 10 , the x-axis may correspond to voltage (V) as feature 1, and the y-axis may correspond to current (A) as feature 2. Cluster 1 is for a lower voltage (V) and current (A) and may mean a stable battery state. Cluster 2 is for a higher voltage (V) and current (A) and may mean an unstable battery state. Each dot represents the size of the voltage (V) and current (A) of each battery cell as coordinates, and may mean the size at a specific point in time.

The electric signal analysis method according to the present invention extracts the final distance values of cluster 1 and cluster 2, and obtains/generates fire occurrence information for the battery for the electric vehicle based on the final distance values.

At this time, the final distance value according to the present invention can be extracted in the following order.

(1) Extracting the first average value (x1, y1) of cluster 1 and the second average value (x2, y2) of cluster 2

(2) The first average value and the second average value are coordinate values, respectively, and the final distance value (L) between the first average value and the second average value is extracted based on Equation 2 below.

[Equation 2]

In the present invention, when the extracted final distance value (L) is greater than the preset distance value, it is determined that a fire or short circuit has occurred in the corresponding battery cell, and fire occurrence information can be obtained/generated based on this.

In addition, the electric signal analysis method according to the present invention may extract a different final distance value (L) according to the type of battery. In the case of a lithium ion battery, which is generally used as a battery for an electric vehicle, it is more efficient to multiply the final distance value (L) by a correction coefficient and compare it with a preset distance value based on this. This is referred to as the corrected final distance value (L') and can be extracted based on Equations 3 and 4 below.

[Equation 3]

(However, (x1, y1) is a coordinate value generated based on the average value of cluster 1, and (x2, y2) is a coordinate value generated based on the average value of cluster 2)

[Equation 4]

α is a constant for correction so that the final distance value is calculated to increase as the temperature of the battery cell increases, so that fire occurrence information is derived more accurately. In addition, α is a constant for correction so that the fire occurrence information is derived more accurately by making the final distance value calculated to be larger as the battery cell is short-circuited and the magnitude of the current change is higher. In addition, α is a constant for correcting fire occurrence information to be derived more accurately by considering the capacity of the battery cell. α is a constant and its unit can be neglected.

As such, when the fire occurrence information is generated based on the corrected final distance value L' using Equations 3 and 4, there is an effect that the fire occurrence information for the electric vehicle battery can be more accurately derived.

The above-described present invention can be modeled as a computer readable code on a medium on which a program is recorded. The computer-readable medium includes all types of recording devices in which data readable by a computer system is stored. Examples of computer-readable media include Hard Disk Drive (HDD), Solid State Disk (SSD), Silicon Disk Drive (SDD), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. , and also includes those modeled in the form of carrier waves (eg, transmission over the Internet). Accordingly, the above detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of this specification should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of this specification are included in the scope of this specification.

Any or other embodiments of the present invention described above are not mutually exclusive or distinct. Certain or other embodiments of the present invention described above may be used in combination or combination of respective configurations or functions.

The above detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

10: vehicle
100: control unit
200: sensing unit
300: battery pack
400: fire suppression device

Claims (7)

In a system for preventing fire in an artificial intelligence-based vehicle battery,
a sensing unit sensing state information of the vehicle battery;
A fire suppression device for injecting a fire extinguishing solution to the vehicle battery based on the state information; and
A controller that performs a clustering-based algorithm for generating fire occurrence information for the vehicle battery based on the state information and controls the fire suppression device based on a result value of the clustering-based algorithm;
The state information includes overcurrent occurrence information,
AI-based vehicle fire prevention system.
According to claim 1,
The digestive fluid contains a fire extinguishing agent,
The fire extinguishing agent comprises 40 to 60 parts by weight of potassium nitrate, 40 to 60 parts by weight of ammonium phosphate, 40 to 60 parts by weight of sodium carbonate and 40 to 60 parts by weight of magnesium carbonate, based on 100 parts by weight of purified water.
AI-based vehicle fire prevention system.
According to claim 1,
The sensing unit,
Including an overcurrent detection sensor,
The control unit,
Inputting the measurement value received from the overcurrent detection sensor to the clustering-based algorithm,
AI-based vehicle fire prevention system.
According to claim 1,
The fire suppression device,
a tank for storing the digestive fluid;
a spray nozzle for spraying the extinguishing liquid from the tank to the vehicle battery; and
To include a; valve for controlling the spray nozzle;
AI-based vehicle fire prevention system.
According to claim 4,
the tank,
a piston unit for applying pressure to the digestive fluid; and
Including; power generating unit for generating power for driving the piston unit,
The power generating unit includes explosives,
AI-based vehicle fire prevention system.
In the method of preventing fire in a vehicle based on artificial intelligence,
Receiving state information of the vehicle battery;
performing a clustering-based algorithm based on the state information;
obtaining fire occurrence information of the vehicle battery based on a result value of the clustering-based algorithm; and
Controlling to spray a fire extinguishing liquid to the vehicle battery based on the fire occurrence information; including,
The status information is
Including overcurrent generation information,
AI-based vehicle fire prevention method.
A non-transitory computer readable medium storing instructions,
The instructions, when executed by a processor, cause the processor to perform the method of claim 6.

Images