KR102573300B1 - Method and apparatus for protecting battery module provided in electric vehicle - Google Patents

Abstract

Embodiments suggest a method and apparatus for protecting a battery module provided in an electric vehicle. The device according to an embodiment includes an electric vehicle battery protective cover composed of a plurality of layers and surrounding the battery module, a first fire extinguishing water inlet formed on one side of the electric vehicle battery protective cover and including a first check valve, one side The first fire hose connected to the first check valve and the other side connected to the first nozzle coupling part provided at the lower end of the charging port of the electric vehicle, formed on the other side of the electric vehicle battery protection cover, and the second check valve A second fire extinguishing water inlet including a second fire hose having one side connected to the second check valve and the other side connected to the second nozzle fastening part provided at the bottom of the rear trunk of the electric vehicle, the second fire extinguishing water inlet and An exhaust port spaced apart in the width direction of the electric vehicle and formed on the other side of the electric vehicle battery protection cover, one side of which is connected to the exhaust port, and the other side is spaced apart from the second check valve in the width direction of the electric vehicle and is located at the bottom of the rear trunk of the electric vehicle. It includes an exhaust pipe connected to the third check valve provided, the first nozzle fastening part and the second nozzle fastening part each have a cover installed, and after the cover is removed, a fire extinguishing water supply nozzle is fastened from the outside, and the plurality of The layer of is a first cover layer of polyimide material coated with a first heat-resistant coating agent, a second cover layer of flame-retardant silicone rubber material that protects the battery module from external impact and coated with a second heat-resistant coating material, and the first It may be located between the cover layer and the second cover layer and include a buffer layer made of polyurethane.

Description

Method and device for protecting a battery module provided in an electric vehicle {METHOD AND APPARATUS FOR PROTECTING BATTERY MODULE PROVIDED IN ELECTRIC VEHICLE}

Embodiments of the present disclosure relate to a technology for protecting a battery module included in an electric vehicle, and to a battery protection cover surrounding a battery module included in an electric vehicle and a device related to the cover.

Meanwhile, a battery module used in an electric vehicle has a structure in which a plurality of batteries such as lithium ion batteries are intensively packed. A lithium ion battery is a chemical energy storage device in which lithium ions are charged and discharged through an anode and a cathode, and is vulnerable to fire compared to other types of batteries.

In the event of a fire in an electric vehicle, a thermal runaway phenomenon mainly occurs in the battery module. When such a thermal runaway phenomenon occurs, the battery module releases stored energy very quickly. In particular, since a lithium ion battery has a higher energy density than other batteries, the thermal runaway phenomenon may occur very rapidly. Causes of thermal runaway include overcharge, overdischarge, internal short-circuit accident, terminal contact failure, charging failure, mechanical shock, and electrical shock. there is. In addition, when the lithium ion battery is in an environment suitable for generating heat even at a temperature of 60° C. or lower, thermal runaway may occur after 1 to 2 days. When thermal runaway occurs, the internal pressure of the lithium-ion battery increases and the electrolyte inside it vaporizes, and then the lithium-ion battery expands and the electrolyte is ejected, which causes toxic gases such as carbon monoxide and acetylene to be generated, resulting in an explosion. It can develop into a big fire.

In addition, in order to secure time for rescuing occupants in the event of a fire in a battery module included in an electric vehicle, a method of delaying the fire of the battery module until the fire spreads may be required.

Accordingly, as a device for protecting a battery module provided in an electric vehicle, a plurality of fire extinguishing water inlets are formed to directly supply water to the battery module in case of fire, an exhaust port for discharging toxic gas and heat are formed, and an external impact and an electric vehicle battery protection cover that protects the battery module from high heat generated inside.

Embodiments of the present disclosure may provide a method and apparatus for protecting a battery module included in an electric vehicle.

Technical tasks to be achieved in the embodiments are not limited to those mentioned above, and other technical tasks not mentioned will be considered by those skilled in the art from various embodiments to be described below. can

An apparatus for protecting a battery module included in an electric vehicle according to an embodiment includes an electric vehicle battery protective cover composed of a plurality of layers and surrounding the battery module, formed on one side of the electric vehicle battery protective cover, and a first check valve. A first fire hose having one side connected to the first check valve and the other side connected to the first nozzle coupling part provided at the bottom of the charging port of the electric vehicle, and the other side of the electric vehicle battery protection cover. A second fire hose having a second fire extinguishing water inlet including a second check valve, one side connected to the second check valve, and the other side connected to the second nozzle fastening part provided at the bottom of the rear trunk of the electric vehicle. , An exhaust port spaced apart from the second fire extinguishing water inlet in the width direction of the electric vehicle and formed on the other side of the electric vehicle battery protection cover, one side connected to the exhaust port, and the other side extending from the second check valve to the width direction of the electric vehicle. It includes an exhaust pipe that is spaced apart and connected to a third check valve provided at the bottom of the rear trunk of the electric vehicle, and a cover is installed on the first nozzle fastening part and the second nozzle fastening part, respectively, so that after the cover is removed, fire extinguishing water is supplied from the outside. A supply nozzle is fastened, and the plurality of layers include a first cover layer made of polyimide material coated with a first heat-resistant coating agent, a flame retardant silicon rubber material coated with a second heat-resistant coating material to protect the battery module from external impact. It may include a second cover layer and a buffer layer made of a polyurethane material located between the first cover layer and the second cover layer.

According to one embodiment, the first heat-resistant coating agent may be applied to the exhaust pipe. The second heat-resistant coating agent may be applied to the first fire hose and the second fire hose. An extinguishing powder layer directly contacting the battery module may be further included in the plurality of layers. The extinguishing powder layer may be configured in a form in which a material melted at a temperature of 160 degrees to 180 degrees surrounds the first extinguishing powder and the second extinguishing powder. When the battery module fires, the extinguishing powder layer melts, so that the first extinguishing powder and the second extinguishing powder may be supplied to the battery module.

For example, the first heat-resistant coating agent may be a coating agent in which silicon carbide is added to a binder prepared by mixing a dispersion solution of silica sol containing 30 to 45 mass percent of solid components dispersed in water and an aluminum hydroxide solution. . For example, the second heat-resistant coating agent may be a coating agent composed of a solution containing polyurethane-urea. For example, the first digestion powder may be expanded vermiculite powder having a particle size of 160 ~ 200um. For example, the second extinguishing powder may include 75 parts by weight of ammonium monophosphate, 10 parts by weight of graphite, and 15 parts by weight of silica. For example, the mixing ratio of the first extinguishing powder and the second extinguishing powder may be 7:3 by weight.

According to an embodiment, a fire detection module is mounted on the battery module wrapped with the electric vehicle battery protection cover, and the fire detection module may include a control unit, a memory, a power supply unit, a sensor unit, and a communication unit. The control unit measures the temperature of the battery module and the amount of impact applied to the battery module in real time through the sensor unit, and generates a neural network based on basic information related to the electric vehicle, the temperature of the battery module, and the amount of impact applied to the battery module. Determines the fire risk of the battery module through a fire risk prediction model using, and sends a report message to an external server, surrounding vehicle terminals, and pre-connected terminals through the communication unit based on the fact that the fire risk is greater than or equal to a preset value. can transmit

For example, the report message may include information about the location of the electric vehicle, information about the location of the first fire extinguishing water inlet and the location of the second fire extinguishing water inlet, how to use the first nozzle coupling part, and the second nozzle It may contain information about how to use the fastening part. The basic information related to the electric vehicle may include information about the model year of the electric vehicle and information about the model of the electric vehicle. A basic vector for a battery module may be determined through data preprocessing of basic information related to the electric vehicle. The basic vector for the battery module may include a value related to the age of the electric vehicle, a value related to the type of the battery, a value related to the capacity of the battery, and a value related to the configuration of the battery. A state vector of the battery module may be determined through data preprocessing of the temperature of the battery module and the amount of impact applied to the battery module. The state vector may include a value for temperature per unit time and a value for impulse per unit time.

For example, the fire risk of the battery module may be determined based on input of the basic vector and the state vector of the battery module to the neural network. The neural network may include an input layer, one or more hidden layers, and an output layer. Each learning data composed of a plurality of base vectors, a plurality of state vectors, and a plurality of answer fire risks is input to the input layer of the neural network, passes through the one or more hidden layers and the output layer, and is output as an output vector. An output vector is input to a loss function layer connected to the output layer, and the loss function layer outputs a loss value using a loss function that compares the output vector with the correct answer vector for each learning data, and outputs a loss value of the neural network. Parameters may be learned in a direction in which the loss value becomes smaller.

According to embodiments, the device forms a plurality of fire extinguishing water inlets in an electric vehicle battery protective cover so that fire extinguishing water can be directly supplied to the battery module when the battery module is on fire, thereby enabling the fire to be extinguished more quickly.

According to embodiments, the device may secure time to rescue occupants by discharging toxic gas or heat to the outside of the electric vehicle in the event of a battery module fire by forming an exhaust hole in the battery protection cover of the electric vehicle.

According to embodiments, the device adds an extinguishing powder layer containing a plurality of extinguishing powders to the battery protective cover, thereby delaying the spread of fire for a certain period of time through two types of extinguishing powders in the event of a battery module fire, thereby protecting the occupants. You can secure time to rescue. In addition, the EV battery protective cover is relatively easy to mold compared to other protective covers, and weight increase can be minimized by applying a minimum amount of heat-resistant coating.

Effects obtainable from the embodiments are not limited to the effects mentioned above, and other effects not mentioned are clearly derived and understood by those skilled in the art based on the detailed description below. It can be.

BRIEF DESCRIPTION OF THE DRAWINGS Included as part of the detailed description to aid understanding of the embodiments, the accompanying drawings provide various embodiments and, together with the detailed description, describe technical features of the various embodiments.
1 is a diagram illustrating a state in which a device for protecting a battery module included in an electric vehicle according to an embodiment is installed.
2 is a view for explaining a first fire hose in a device for protecting a battery module included in an electric vehicle according to an embodiment.
3 is a view for explaining a second fire hose and an exhaust pipe in a device for protecting a battery module included in an electric vehicle according to an embodiment.
4 is a diagram showing the configuration of an electric vehicle battery protection cover according to an embodiment.
5 is a diagram showing a configuration of an electric vehicle battery protection cover including an extinguishing powder layer according to an embodiment.
6 is a flowchart of a method for a device for protecting a battery module included in an electric vehicle to determine a fire risk level and transmit a message according to the fire risk level according to an embodiment.

The following embodiments combine elements and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form not combined with other components or features. In addition, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may be changed. Some components or features of one embodiment may be included in another embodiment, or may be replaced with corresponding components or features of another embodiment.

In the description of the drawings, procedures or steps that may obscure the gist of various embodiments are not described, and procedures or steps that can be understood by those skilled in the art are not described. did

Throughout the specification, when a part is said to "comprising" or "including" a certain element, it means that it may further include other elements, not excluding other elements, unless otherwise stated. do. In addition, terms such as “… unit”, “… unit”, and “module” described in the specification mean a unit that processes at least one function or operation, which is hardware or software or a combination of hardware and software. can be implemented as Also, “a or an”, “one”, “the” and like terms are used herein in the context of describing various embodiments (particularly in the context of the claims below). Unless otherwise indicated or clearly contradicted by context, both the singular and the plural can be used.

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The detailed description set forth below in conjunction with the accompanying drawings is intended to describe exemplary embodiments of various embodiments, and is not intended to represent a single embodiment.

1 is a diagram illustrating a state in which a device for protecting a battery module included in an electric vehicle according to an embodiment is installed. 2 is a view for explaining a first fire hose in a device for protecting a battery module included in an electric vehicle according to an embodiment. 3 is a view for explaining a second fire hose and an exhaust pipe in a device for protecting a battery module included in an electric vehicle according to an embodiment. The embodiments of FIGS. 1 to 3 may be combined with various embodiments of the present disclosure.

In addition, specific terms used in various embodiments are provided to help understanding of various embodiments, and the use of these specific terms may be changed into other forms without departing from the technical spirit of various embodiments. .

1 to 3, the device for protecting the battery module provided in the electric vehicle 10 includes an electric vehicle battery protection cover 100 surrounding the battery module provided in the electric vehicle 10, and a first fire extinguishing water inlet 111 And the first fire hose 110 connecting the first nozzle fastening part 113, the second fire hose 120 connecting the second fire extinguishing water inlet 121 and the second nozzle fastening part 123, and the exhaust port ( 131) and an exhaust pipe 130 connecting the outside of the electric vehicle 10 and a fire detection module 140.

The electric vehicle 10 is a vehicle driven by electricity as a power source, and may use electric energy of a battery charged from an electricity supply source as a power source instead of an internal combustion engine. For example, a vehicle may refer to various means such as a car, a two-wheeled vehicle, and a bicycle.

The electric vehicle battery protection cover 100 protects the battery module provided in the electric vehicle 10 from external impact and at the same time protects the user riding the electric vehicle 10 in the event of a fire in the battery module provided in the electric vehicle 10. It is a cover. For example, the electric vehicle battery protection cover 100 may include fire extinguishing water inlets 111 and 121 for directly supplying fire extinguishing water to the battery module and an exhaust port 131 for discharging pressure and smoke generated by a fire. can For example, the electric vehicle battery protection cover 100 may be made of a material that withstands heat and pressure generated during a battery module fire for a certain period of time. In addition, the electric vehicle battery protective cover 100 is relatively easy to mold compared to other protective covers, and the weight increase can be minimized by applying a minimum amount of heat-resistant coating. For example, the electric vehicle battery protection cover 100 is composed of a plurality of layers and may cover the battery module. For example, the plurality of layers may include a first cover layer coated with a first heat resistant coating, a second cover layer coated with a second heat resistant coating, and a buffer layer positioned between the first cover layer and the second cover layer. there is.

The first extinguishing water inlet 111 and the second extinguishing water inlet 121 are inlets for directly supplying extinguishing water to the battery module from the outside of the electric vehicle 10 when a fire occurs in the battery module provided in the electric vehicle 10. .

For example, the first fire extinguishing water inlet 111 may be formed on one side of the electric vehicle battery protection cover 100. For example, the first fire extinguishing water inlet 111 may include a first check valve 112. The first check valve 112 may operate so that fire extinguishing water flows from the outside of the electric vehicle 10 to the inside of the battery module. For example, the first check valve 112 may perform an opening/closing operation when the pressure according to injection of fire extinguishing water exceeds a certain pressure. For example, the second fire extinguishing water inlet 121 may be formed on the other side of the electric vehicle battery protection cover 100. For example, the second fire extinguishing water inlet 121 may include a second check valve 122 . The second check valve 122 may operate so that fire extinguishing water flows from the outside of the electric vehicle 10 to the inside of the battery module. For example, the second check valve 122 may perform an opening/closing operation when the pressure according to injection of fire extinguishing water is higher than a certain pressure. In this way, the fire of the battery module can be extinguished faster than when one fire extinguishing water inlet is formed in the electric vehicle battery protective cover, and even if one fire extinguishing water inlet is broken, stable fire suppression is possible by using the remaining fire extinguishing water inlet.

The first fire hose 110 is a passage for delivering fire extinguishing water supplied from the outside of the electric vehicle 10 to the first fire extinguishing water inlet 110. For example, one side of the first fire hose 110 is connected to the first check valve 112, and the other side of the first fire hose 110 is coupled to the first nozzle provided at the lower end of the charging port of the electric vehicle 10. It can be connected to part 113. Through this, when fire extinguishing water is injected from the outside of the electric vehicle 10, the first fire hose 110 can directly supply the injected fire extinguishing water to one side of the battery module. The second fire hose 120 is a passage for delivering fire extinguishing water supplied from the outside of the electric vehicle 10 to the second fire extinguishing water inlet 120. For example, the other side of the second fire hose 120 is connected to the second check valve 122, and the other side of the second fire hose 120 is coupled to the second nozzle provided at the bottom of the rear trunk of the electric vehicle 10. It can be connected to part 123. Through this, when fire extinguishing water is injected from the outside of the electric vehicle 10, the second fire hose 120 can directly supply the injected fire extinguishing water to the other side of the battery module.

The first nozzle fastening part 113 is connected to the first fire hose 110 inside the electric vehicle 10, and a nozzle supplying fire extinguishing water from the outside of the electric vehicle 10 (hereinafter referred to as a fire extinguishing water supply nozzle) is fastened. It can be. For example, the first nozzle fastening part 113 may be located at the lower end of the charging port of the electric vehicle 10. The location of the charging port of the electric vehicle 10 may be different, such as a front grill, a front fender, a front lamp, a middle side, a rear lamp, etc., for each vehicle type of the electric vehicle 10 . Embodiments of the present disclosure are not limited to the location of the charging port of the electric vehicle 10 on the front fender and can be applied to various locations. The second nozzle fastening part 123 is connected to the second fire hose 120 inside the electric vehicle 10, and the fire extinguishing water supply nozzle can be fastened from the outside of the electric vehicle 10. For example, the second nozzle fastening part 123 may be located at the bottom of the rear trunk of the electric vehicle 10. For example, the first nozzle fastening part 113 and the second nozzle fastening part 123 may be configured in various shapes and structures to which the fire extinguishing water supply nozzle can be fastened outside the electric vehicle 10. For example, covers may be installed on each of the first nozzle fastening part 113 and the second nozzle fastening part 123 . After the cover is removed, the fire extinguishing water supply nozzle may be fastened to the first nozzle fastening part 113 and the second nozzle fastening part 123 from the outside.

The exhaust port 131 discharges air generated from the battery module included in the electric vehicle 10 to the outside, and, for example, discharges toxic gas and heat generated in the event of a fire in the battery module included in the electric vehicle 10 to the outside. can do. For example, the exhaust port 131 may be spaced apart from the second fire extinguishing water inlet 121 in the width direction of the electric vehicle 10 and formed on the other side of the electric vehicle battery protection cover 100. The exhaust pipe 130 is a passage for discharging air generated from the battery module included in the electric vehicle 10 to the outside. For example, the exhaust pipe 130 may have one side connected to the exhaust port 131 and the other side connected to the third check valve 132 spaced apart from the second check valve 121 in the width direction of the electric vehicle 10. . For example, the exhaust pipe 130 may have a cylindrical structure and may be configured in various shapes and structures for discharging air generated from the battery module to the outside of the electric vehicle 10 . The third check valve 132 may operate so that air generated inside the battery module included in the electric vehicle 10 is discharged to the outside of the electric vehicle 10 through the exhaust pipe 130 . For example, the third check valve 132 may perform an opening/closing operation when the pressure of the air generated from the battery module included in the electric vehicle 10 exceeds a predetermined pressure. In this way, by forming the exhaust port 131 in the electric vehicle battery protection cover 100, it is possible to secure time for rescuing occupants by discharging toxic gas or heat generated in the event of a battery module fire to the outside of the electric vehicle 10. . Additionally, for example, a cooling fan may be installed in the exhaust port 131 to operate according to the temperature of the battery module.

The fire detection module 140 is a module for detecting a fire in the battery module of the electric vehicle 10 . The fire detection module 140 may determine the fire risk level of the battery module in advance independently of the vehicle terminal inside the electric vehicle 10, and notify the state of the electric vehicle 10 to an external server and surrounding vehicle terminals according to the fire risk level. . For example, the fire detection module 140 may include a control unit, a memory, a power supply unit, a sensor unit, and a communication unit. The fire detection module 140 may operate even in case of a fire in the battery module by using a separate power supply. At this time, the electric vehicle battery protection cover 100 may be in the form of surrounding the battery module to form a space spaced apart from the battery module, and the fire detection module 140 is in the space where the electric vehicle battery protection cover 100 and the battery module are spaced apart. It can be attached to the battery module.

The control unit of the fire detection module 140 controls the overall operation of the fire detection module 140 in general. The control unit may include one or more processors to control other components included in the management fire detection module 140 . For example, the control unit may generally control the communication unit and the memory by executing programs stored in the memory. In addition, the controller may perform the function of the fire detection module 140 by executing programs stored in the memory. For example, the control unit may include a hardware structure specialized for processing an artificial intelligence model.

AI models can be created through machine learning. Such learning may be performed, for example, in the fire detection module 140 itself where the artificial intelligence model is performed, or may be performed through a separate server. The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning or reinforcement learning, but in the above example Not limited. The artificial intelligence model may include a plurality of artificial neural network layers. Artificial neural networks include deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), restricted boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), It may be one of deep Q-networks or a combination of two or more of the foregoing, but is not limited to the foregoing examples. The artificial intelligence model may include, in addition or alternatively, software structures in addition to hardware structures.

The communication unit of the fire detection module 140 may include one or more components that allow the fire detection module 140 to communicate with other devices (not shown) and servers (not shown). Another device (not shown) may be a computing device such as the fire detection module 140 or a sensing device, but is not limited thereto. The communication unit may receive a user input from another electronic device or data stored in the external device from an external device through a network. For example, the communication unit may transmit/receive a message for establishing a connection with at least one device. The communication unit may transmit information generated by the control unit to at least one device connected to the management server. The communication unit may receive information from at least one device connected to the fire detection module 140 . The communication unit may transmit information related to the received information in response to information received from at least one device.

The memory of the fire detection module 140 may store programs for processing and control by the control unit. For example, the memory may store information input to the fire detection module 140 or information received from other devices through a network. Also, the memory may store data generated by the controller. The memory may store information input to or output from the controller. Memory includes flash memory type, hard disk type, multimedia card micro type, card type memory (eg SD or XD memory, etc.), RAM (RAM, Among Random Access Memory) SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk It may include at least one type of storage medium.

The power supply unit of the fire detection module 140 may supply power to at least one component of the fire detection module 140 . For example, the power supply may include a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

The sensor unit of the fire detection module 140 may detect an operating state (eg, temperature or amount of impact) of the battery module of the electric vehicle 10 and generate an electrical signal or data value corresponding to the detected state. For example, the sensor unit may use at least one of an impact sensor, a color sensor, an infrared (IR) sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

For example, a vehicle terminal may be included, embedded, or installed inside the electric vehicle 10, and may be used in a smartphone, mobile phone, smart TV, set-top box, tablet PC, wearable device, etc. It can be implemented in a variety of devices including.

In the present specification, a vehicle terminal, a base station, an external vehicle terminal, and a road side unit (RSU) may communicate with each other through a communication network. The communication network may be, for example, a wireless communication network or a wired communication network. The wireless communication network may be, for example, a communication network based on Long Term Evolution (LTE) Radio Access Technology (RAT), New Radio (NR) RAT, WiFi, and the like. A base station may include a next generation-Node B (gNB) and/or an evolved-NodeB (eNB). For example, a base station may be a fixed station or a network entity that communicates with a vehicle terminal, and may be referred to as a base transceiver system (BTS) or access point (AP). The external vehicle terminal may be included, embedded, or installed in an external vehicle, and represents an external terminal that provides various information by communicating with the base station and/or the vehicle terminal. The RSU is a device installed next to a road or highway to support wireless communication between a vehicle terminal and road infrastructure. For example, an RSU may be a roadside base station. For example, RSUs can be used for a variety of applications including traffic monitoring, vehicle-to-vehicle and vehicle-to-infrastructure communications, toll collection, parking management, and emergency response. In addition, the RSU can provide real-time information on road and traffic conditions to vehicle terminals to support the development and deployment of connected and automated vehicles. For example, the RSU can communicate with vehicle terminals and other infrastructure components through various wireless communication protocols such as 3GPP-based C-V2X, Dedicated Short Range Communications (DSRC), cellular networks, Wi-Fi or Bluetooth.

For example, a vehicle terminal, a base station, an external vehicle terminal, and an RSU may perform device-to-device (D2D) communication with each other and may perform UU communication with a base station (eg, gNB and/or eNB). . In a time division multiple access (TDMA) and frequency division multiples access (FDMA) system for performing the D2D communication or the UU communication, accurate time and frequency synchronization may be required. If time and frequency synchronization are not accurate, system performance may deteriorate due to Inter Symbol Interference (ISI) and Inter Carrier Interference (ICI). In D2D communication according to an example, for time/frequency synchronization, a synchronization signal (SS) may be used in a physical layer, and a master information block (MIB) may be used in a radio link control (RLC) layer.

In the D2D communication process, vehicle terminals, base stations, external vehicle terminals, and RSUs are directly synchronized with GNSS (global navigation satellite systems), or indirectly through terminals directly synchronized with GNSS (within network coverage or outside network coverage). can be synchronized to GNSS. When GNSS is set as a synchronization source, the vehicle terminal, base station, external vehicle terminal and RSU can calculate the DFN and subframe number using Coordinated Universal Time (UTC) and (pre)set Direct Frame Number (DFN) offset.

Alternatively, the vehicle terminal, the base station, the external vehicle terminal, and the RSU may be directly synchronized to another base station or synchronized to another terminal that is time/frequency synchronized to the another base station. For example, the another base station may be an eNB or a gNB. For example, when a vehicle terminal, a base station, an external vehicle terminal, and an RSU are within network coverage, the vehicle terminal, base station, external vehicle terminal, and RSU receive synchronization information provided by the base station and may be directly synchronized with the base station. . After that, the vehicle terminal, the base station, the external vehicle terminal, and the RSU may provide synchronization information to other adjacent terminals. When the base station timing is set as a synchronization criterion, a vehicle terminal, a base station, an external vehicle terminal, and an RSU are a cell associated with a corresponding frequency (when within cell coverage at the frequency), a primary cell, or a serving cell ( out of cell coverage at the frequency).

A base station (eg, a serving cell) may provide synchronization configuration for a carrier used for device-to-device (D2D) or sidelink (SL) communication. In this case, the vehicle terminal, the external vehicle terminal, and the RSU may follow the synchronization setting received from the base station. If the vehicle terminal, the base station, the external vehicle terminal, and the RSU do not detect any cell in the carrier used for the D2D or SL communication and do not receive synchronization settings from the serving cell, the vehicle terminal, the base station, the external vehicle terminal, and the RSU The RSU may follow preset synchronization settings.

Alternatively, the vehicle terminal, the base station, the external vehicle terminal, and the RSU may be synchronized with other terminals that do not directly or indirectly acquire synchronization information from the base station or GNSS. Synchronization source and preference may be set in advance for the terminal. Alternatively, the synchronization source and preference may be set through a control message provided by the base station.

4 is a diagram showing the configuration of an electric vehicle battery protection cover according to an embodiment. 5 is a diagram showing a configuration of an electric vehicle battery protection cover including an extinguishing powder layer according to an embodiment. The embodiments of FIGS. 4 to 5 may be combined with various embodiments of the present disclosure.

Referring to FIG. 4 , the electric vehicle battery protection cover may be composed of a plurality of layers, and the plurality of layers include a first cover layer 410 coated with a first heat-resistant coating agent 411 and a second heat-resistant coating agent 431. A buffer layer 420 positioned between the applied second cover layer 430 , the first cover layer 410 and the second cover layer 430 may be included.

The first cover layer 410 may be a film having heat resistance and flexibility to which a first heat resistant coating 411 is applied to block high heat generated by thermal runaway due to a fire of the battery module. For example, the first cover layer 410 may be a film made of polyimide. Polyimide is a polymer of imide monomers. Generally, a polymer solution obtained by solution polymerization of aromatic dianhydride and aromatic diamine is mixed with a catalyst, applied in the form of a film, and dried at a high temperature. It can be prepared by dehydration ring closure.

The first heat-resistant coating agent 411 is a coating agent applied to the first cover layer 410 to block high heat generated by a fire of the battery module. For example, the first heat-resistant coating agent 411 is a coating agent in which silicon carbide is added to a binder prepared by mixing a dispersion solution of silica sol containing 30 to 45 mass percent of solid components dispersed in water and an aluminum hydroxide solution. can The silica sol may be a solution in which the surface is preserved in a sol state having siloxane groups of the form =Si-O-Si= or silanol groups of the form ≡Si-OH. Silica (SiO ₂ ) in the silica sol may be in a particulate state having an average particle diameter of 1 to 1000 nm. A dispersion solution can be created by adding water to a silica sol. For example, the weight ratio of silica sol dispersed in water may be silica sol: water = 100: 110 to 30.

Aluminum hydroxide solution means a mixture of Al(OH) ₃ and water. The amount of aluminum hydroxide added to water may be determined according to the saturation condition of aluminum hydroxide at room temperature, and for example, Al(OH) ₃ may be added in an amount of 0.1 to 1.0 parts by weight based on 100 parts by weight of water. Alternatively, Al(OH) ₃ may be added in an amount that saturates water at room temperature. The dispersion solution and the aluminum hydroxide solution may have a weight ratio of the dispersion solution: the aluminum hydroxide solution = 100: 15 to 40. Silicon carbide may be added to the binder in the form of a powder having an average diameter of 5 nm to 100 μm. The weight ratio of silicon carbide to the binder may be binder: filler = 100: 10 to 100. Through this, a ceramic coating agent having heat resistance can be prepared.

The buffer layer 420 may be a film that serves as a buffer to increase durability against an impact applied from the outside of the battery module and a pressure caused by an explosion when the battery module catches fire. For example, the buffer layer 420 may be a polyurethane film. Polyurethane refers to a polymeric compound in which urethane bonds are repeatedly included in the main chain of the polymer, and a hydroxyl catalyst (R ' - (OH) N ≥ 2) or can be produced under conditions of UV activation. For example, the buffer layer 420 may be made of the same material as the first fire hose and the second fire hose.

The second cover layer 430 may be a film having elasticity to protect the battery module from impact applied from the outside. For example, the second cover layer 430 may be a film made of flame retardant silicone rubber. Flame retardant silicone rubber refers to a composite in which a specific compound is mixed with silicone rubber, and can improve high-temperature and flame safety of the composite, such as fire resistance, thermal decomposition, and flame-blocking properties, and have flame retardancy. For example, a film made of flame retardant silicone rubber is made by adding inorganic flame retardants aluminum trihydroxide (ATH, Al(OH) ₃ ) and magnesium dihydroxide (MDH, Mg(OH) ₂ ) to silicone rubber. It may be an added complex. Alternatively, the film of flame retardant silicone rubber material may be a composite obtained by mixing perlite, which is a white porous material, prepared by pulverizing perlite and subjecting to high temperature overheating/foaming to silicone rubber. For example, a film of flame retardant silicone rubber material mixed with pearlite forms amorphous silica (Sio ₂ ) on the surface during thermal decomposition to block heat supplied from a heat source and prevent the inflow of oxygen. Methylhydrosilane ( Methylhydrosilane) and hydrosilane (Hydrosilane), polydimethylsiloxane (PDMS, Polydimethyl siloxane) consisting of a 1: 1 weight ratio and pearlite, a white porous body mainly composed of perlite, can be prepared by mixing.

The second heat-resistant coating agent 421 is a coating agent applied to the second cover layer 420 to block high heat generated by a fire of the battery module. For example, the second heat-resistant coating agent 421 may be a coating agent composed of a solution containing polyurethane-urea. Here, polyurethane-urea may refer to a form in which a urethane group and a urea group are sequentially bonded. For example, polyurethane-urea can be prepared from organic polyisocyanates and compounds having active hydrogen atoms capable of reacting with isocyanate groups. The compound having an active hydrogen atom is an organic compound having a molecular weight of 400 to 1200, and may generally be a polyether polyol or a polyester polyol type. For example, line-XS-252 from Line X may be used as the second heat-resistant coating agent.

For example, the first heat resistant coating agent 411 or the second heat resistant coating agent 431 may be applied to the inside and outside of the exhaust pipe. For example, the first heat resistant coating 411 or the second heat resistant coating 431 may be applied to the inside and outside of the first fire hose and the second fire hose.

Referring to FIG. 5 , an extinguishing powder layer 510 may be further included in the plurality of layers constituting the electric vehicle battery protection cover.

For example, the extinguishing powder layer 510 may directly contact a battery module provided in an electric vehicle. The extinguishing powder layer 510 may be formed in a form in which a material melted at a temperature of 90 degrees to 120 degrees surrounds the first extinguishing powder 511 and the second extinguishing powder 512 .

For example, as the extinguishing powder layer 510 melts in the event of a fire in a battery module provided in an electric vehicle, the first extinguishing powder 511 and the second extinguishing powder 512 included in the extinguishing powder layer 510 cause the battery module to can be supplied to Through this, it is possible to secure time for rescuing occupants by delaying the spread of fire in the event of a fire in the battery module provided in the electric vehicle for a certain period of time through two types of extinguishing powder.

Typically, thermal runaway of a battery module is observed before a fire occurs in the battery module. As a precursor to thermal runaway, an exothermic reaction occurs in the cathode material of the battery module at 130 to 150 degrees. At this time, if the cathode material is not properly cooled, the temperature continues to rise, resulting in thermal runaway. Therefore, by using the material of the extinguishing powder layer 510 as a material that melts at a temperature of 160 to 180 degrees, when the cooling of the cathode material of the battery module fails and the temperature continues to rise, the fire extinguishing occurs at the beginning of the thermal runaway phenomenon. Powder layer 510 may be melted. When the extinguishing powder layer 510 is melted, the first extinguishing powder 511 and the second extinguishing powder 512 included in the extinguishing powder layer 510 may be supplied to the battery module.

For example, a polypropylene (PP) material may be used as a material that melts at a temperature of 160 to 180 degrees in the extinguishing powder layer 510 . Polypropylene is a thermoplastic resin obtained by polymerizing propylene, and is used for manufacturing various plastic products because it is light and easy to mold and process, and is used as a surface protection film because of its good strength.

For example, the first extinguishing powder 511 may be a powder that causes a suffocation effect by covering a battery module in which a fire has occurred. For example, the first digested powder 511 may be expanded vermiculite powder having a particle size of 160 μm to 200 μm. Vermiculite is produced by weathering or deterioration of mica and has the property of expanding and expanding when the moisture it contains is dehydrated. At this time, the expanded vermiculite powder is a mixture of chemically expanded vermiculite and thermally expanded vermiculite, and the chemically expanded vermiculite is 95%, and the remaining 5% may be composed of thermally expanded vermiculite. For example, the second extinguishing powder 512 may be a powder having an effect of cooling the temperature of a battery module in which a fire has occurred. For example, the second extinguishing powder 512 may include 75 parts by weight of ammonium monophosphate, 10 parts by weight of graphite, and 15 parts by weight of silica. Here, monobasic ammonium phosphate (NH ₄ H ₂ PO ₄ ) is a crystal powder prepared by neutralizing phosphoric acid with ammonia. At this time, for example, the mixing ratio of the first extinguishing powder 511 and the second extinguishing powder 512 may be 7:3 by weight.

6 is a flowchart of a method for a device for protecting a battery module included in an electric vehicle to determine a fire risk level and transmit a message according to the fire risk level according to an embodiment. The embodiments of FIG. 6 can be combined with various embodiments of the present disclosure.

Referring to FIG. 6 , an operating method of a fire detection module in a device for protecting a battery module included in an electric vehicle will be described.

In step S610, the fire detection module may measure the temperature of the battery module and the amount of impact applied to the battery module in real time through the sensor unit.

For example, the fire detection module may measure the temperature of the battery module in real time through a temperature sensor. For example, the fire detection module may measure the amount of impact applied to the battery module in real time through an impact sensor. Here, the impact sensor can detect the degree of impact by detecting an amplitude signal that is changed by the impact when an impact is applied to the target object.

In step S620, the fire detection module may determine the fire risk of the battery module through a fire risk prediction model using a neural network based on basic information related to the electric vehicle, the temperature of the battery module, and the amount of impact applied to the battery module.

Information related to the electric vehicle may include information about the year of the electric vehicle and information about the model of the electric vehicle. Information on the model year of the electric vehicle may be information on the year the electric vehicle was manufactured, and information on the model of the electric vehicle may be information on the model name of the electric vehicle. For example, the information related to the electric vehicle may be information previously received by the fire detection module from the vehicle terminal inside the electric vehicle.

For example, a basic vector for a battery module may be determined through data preprocessing of basic information related to an electric vehicle. The basic vector for the battery module may include a value related to the age of the electric vehicle, a value related to the shape of the battery, a value related to the capacity of the battery, and a value related to the configuration of the battery.

For example, a value related to the year of the electric vehicle may be a value representing a period from the date the electric vehicle was manufactured to the current date.

For example, it may have a different value depending on a combination of a value related to the type of battery, a value related to the capacity of the battery, and a value related to the configuration of the battery, and the year the electric vehicle was manufactured and the model name of the electric vehicle. For example, the matching relationship between each of the values related to the type of battery, the value for the capacity of the battery, and the value related to the configuration of the battery, and the combination of the year the electric car was manufactured and the model name of the electric car are pre-stored in the memory of the fire detection module. It can be. For example, when the fire detection module receives information related to an electric vehicle from a vehicle terminal inside the electric vehicle, the fire detection module determines a value related to the type of battery matched to the electric vehicle and a value related to the capacity of the battery based on the information related to the electric vehicle. values and values related to the configuration of the battery can be determined.

The value related to the type of battery is a value indicating one type among a plurality of types, and may be, for example, a value indicating one type among three types. For example, the three types may include a cylindrical battery, a pouch-type battery, and a prismatic battery. A cylindrical battery is a battery in the form of a cylinder in which a positive electrode and a negative electrode are manufactured by a winding method. A pouch-type battery is a battery in which a cathode material, an anode material, a separator, an electrolyte, and the like are packaged in a pouch film. A prismatic battery is a battery in which aluminum is packaged in a rectangular shape. And, a value representing each type may be preset for the memory. For example, a value related to the type of battery may be determined as a value matched to a year in which the electric vehicle was manufactured and a model name of the electric vehicle.

The value for the capacity of the battery is a value representing the total amount of power stored in the battery module. For example, the value for the capacity of the battery may be determined as a value matched to the year the electric vehicle was manufactured and the model name of the electric vehicle.

The value related to the configuration of the battery is a value representing each type of elements constituting the battery module, and for example, the elements constituting the battery module may include a positive electrode material, a negative electrode material, a separator, and an electrolyte. For example, the value related to the configuration of the battery is a value representing the type of the positive electrode material of the battery module, a value representing the type of the negative electrode material of the battery module, a value representing the type of separator of the battery module, and a value representing the type of electrolyte of the battery module. may consist of Values representing each type may be pre-stored in the memory of the fire detection module. A value representing the type of cathode material may be a value representing any one of LCO (LiCoO₂), NCM (LiNiCoMn), NCA (LiNiCoAlO₂), LMO (LiMn₂O4), or LFP (LiFePO₄). A value representing the type of negative electrode material may be a value representing any one of natural graphite, artificial graphite, low-crystalline carbon, or silicon. The value representing the type of electrolyte may be a value representing either a liquid electrolyte or a solid electrolyte. A value representing the type of separator may be a value representing any one of a dry separator, a wet separator, and a ceramic coating separator. For example, a value related to the configuration of the battery may be determined as a value matched to the year in which the electric vehicle was manufactured and the model name of the electric vehicle.

Through this, since stability is different depending on the shape, configuration, and capacity of the battery module, a weight according to the specification of the battery module may be reflected when determining the fire risk.

For example, the state vector of the battery module may be determined through data preprocessing on the temperature of the battery module and the amount of impact applied to the battery module. The state vector may include a value for temperature per unit time and a value for impulse per unit time.

The value for temperature per unit time may be a value for temperature measured at unit time intervals. For example, the unit time may be in seconds. The value for the impulse per unit time may be a value for the impulse measured at unit time intervals. For example, the unit time may be in seconds.

For example, the fire risk of the battery module may be determined based on a basic vector of the battery module and a state vector of the battery module being input to a neural network. A neural network may include an input layer, one or more hidden layers, and an output layer. Each learning data composed of a plurality of base vectors, a plurality of state vectors, and a plurality of answer fire risks is input to the input layer of the neural network, passes through the one or more hidden layers and the output layer, and is output as an output vector. An output vector is input to a loss function layer connected to the output layer, and the loss function layer outputs a loss value using a loss function that compares the output vector with the correct answer vector for each learning data, and outputs a loss value of the neural network. Parameters may be learned in a direction in which the loss value becomes smaller.

A base vector and a state vector may be composed of one set, and a plurality of sets may be pre-stored in the memory of the fire detection module. The correct answer is the fire risk. It may be a value indicating the degree of risk of fire occurring in the battery module, determined based on the basic vector and the state vector. For example, each of a plurality of correct answer fire risks is a fire risk corresponding to one set consisting of a basic vector and a state vector, and may be pre-stored in the memory of the fire detection module.

Additionally, for example, the correct fire risk may be determined by Equation 1 below.

In Equation 1, H _f is the correct answer fire risk, P _use is the period from the date the electric vehicle was manufactured to the present date, n _avg is the average number of times the electric vehicle is charged during a specific period, and n ₀ is the basic value for the average number of times, the e _cap is the value for the capacity of the battery module, the e ₀ is the basic value for the capacity of the battery module, and the C(t) is the temperature value over time is a function, wherein t ₁ is the closest point in time at which the temperature is measured at or above the value a from the current point in time, where a is a constant, F(t) is a function representing the impulse over time, and t ₀ is the current point in time is the closest point in time at which the impulse is measured to be greater than or equal to a preset value from , w ₁ is a first weight according to a value related to the configuration of the battery module, and w ₂ is a second weight according to a value related to the shape of the battery module. can

For example, the period from the date the electric vehicle was manufactured to the current date may be a value related to the year of the electric vehicle, and may be determined based on information about the year the electric vehicle was manufactured.

For example, the average number of times an electric vehicle is charged during a specific period may be different according to the model name of the electric vehicle, and may be pre-stored in the memory of the fire detection module for each model name of the electric vehicle. For example, the average number of times an electric vehicle is charged during a specific period may be determined as a value corresponding to a model name of the corresponding electric vehicle. Here, the specific period may be 6 months or 1 year. For example, the basic value for the average number of times is a standard value for comparison with the average number of charging times of an electric vehicle during a specific period, and may be an average value of the average number of times for each model name of a plurality of electric vehicles.

For example, the basic value for the capacity of the battery module may be an average of values for the capacity of the battery module for each combination of the year the EV was manufactured and the model name of the EV. For example, a basic value for the capacity of the battery module may be pre-stored in the memory of the fire detection module.

For example, C(t) may be determined based on a value for temperature per unit time, and a may be set to a temperature of 60 degrees. The F(t) may be determined based on a value for an impulse per unit time.

For example, w ₁ may have different values depending on values related to the configuration of the battery module, and may be greater than 0 and less than 1. That is, the first weight may be determined differently according to each type of the positive electrode material, the negative electrode material, the separator, and the electrolyte. For example, the first weight may be determined as a large value according to each type of a positive electrode material, a negative electrode material, a separator, and an electrolyte having relatively low safety.

For example, in the case of a cathode material, the first weight may be set to be large in the order of NCA, NCM, LMO, LCO, and LFP according to the lattice structure of the crystal and the characteristics of the material. That is, the first weight may be set higher for a cathode material having relatively lower safety. For example, in the case of an anode material, the first weight may be set to be high in the order of silicon, natural graphite, artificial graphite, and low-crystalline carbon according to the characteristics of the material. For example, in the case of an electrolyte, the liquid electrolyte may have a higher first weight than the solid electrolyte. For example, since a separator is required when the electrolyte is a liquid electrolyte, the first weight may be set to be large in the order of a dry separator, a wet separator, and a ceramic coating separator in the case of a liquid electrolyte. At this time, the importance according to the risk of fire may be in the order of the cathode material, followed by the electrolyte, the separator, and the anode material. For example, the specific gravity of the first weight according to the type of cathode material is 0.6, the specific gravity of the first weight according to the type of electrolyte is 0.25, the specific gravity of the first weight according to the type of separator is 0.1, and the specific gravity of the first weight according to the type of negative electrode material is 0.6. The proportion of the weight may be set to 0.05.

For example, w ₂ has different values depending on the shape of the battery module, and may be greater than 0 and less than 1. For example, when the value for the shape of the battery module indicates a pouch type, the second weight may have the largest value. For example, when the value for the shape of the battery module represents an angular shape, the second weight may have the smallest value.

Through this, the fire detection module determines the answer fire risk by weighting not only the temperature and impact amount of the battery module, but also the composition and shape of the battery module, the capacity, and the age of the electric vehicle, thereby predicting the fire risk using more accurate learning data. model can be trained.

A gated recurrent unit (GRU) model obtained by modifying a recurrent neural network (RNN) may be used as a fire risk prediction model.

In general, RNNs can effectively model time-series information because the hidden layer value for an existing input stored inside is considered in the output for the next input value. However, since RNN is a structure that depends on past observation values, problems such as vanishing gradient or exploding gradient may occur. A model to solve this problem is LSTM (long short term memory networks), and by replacing nodes inside the LSTM with memory cells, information can be accumulated or some of past information can be deleted, and the problem of the RNN can be supplemented. GRU is a model that improves speed by simply transforming the structure of LSTM.

For example, one or more hidden layers may include one or more GRU blocks, and one GRU block may include a reset gate and an update gate. Here, the reset gate and the update gate may include sigmoid layers. For example, a sigmoid layer is a sigmoid function ( ) may be a layer whose activation function is For example, the hidden state may be controlled through a reset gate and an update gate, and weights according to each gate and input may exist.

Specifically, for example, the reset gate resets past information, and the weight r(t) derived through the previous hidden layer may be determined by Equation 2.

For example, when a plurality of base vectors and a plurality of state vectors are input to an input layer, and the reset gate receives an input value (x _t ) of the current time generated based on the plurality of base vectors and the plurality of state vectors, Dot product with the weight W _r at the current time, and the hidden state (h _(t-1) ) at the previous time, generated based on the plurality of base vectors and the plurality of state vectors, with the weight U _r at the previous time, and finally The sum of the two values is input to the sigmoid function, and the result can be output as a value between 0 and 1. Through the value between 0 and 1, it may be determined how much to utilize the hidden state value of the previous time.

The update gate determines the update rate for past and present information, and z(t) is the amount of information at the current time, which can be determined by Equation 3.

For example, if the input value (x _t ) at the current time is input, the dot product is performed with the weight W _z at the current time, and the hidden state (h _(t-1) ) at the previous time is the dot product with the weight U _z at the previous time. Finally, by adding the two values and inputting them to the sigmoid function, the result can be output as a value between 0 and 1. Further, 1-z(t) may be multiplied by information (h _(t-1) ) of the hidden layer at the previous point in time.

Through this, z(t) can reflect how much current information will be used and how much 1-z(t) will be used for past information.

By multiplying the result of the reset gate, the information candidate group of the current time point t can be determined by Equation 4.

For example, if the input value (x _t ) at the current time is input, the dot product of the weight W _h at the current time and the hidden state (h _(t-1) ) at the previous time is the weight U _h at the previous time It can be input to the tanh function by adding the dot product and multiplying by r(t).

By combining the result of the update gate and the candidate group, the weight of the hidden layer at the current time can be determined by Equation 5.

For example, the value obtained by multiplying the output value z(t) of the update gate by the current hidden state (h(t)), the value 1-z(t) discarded from the update gate, and the hidden state (h( The weight of the hidden layer at the current time may be determined as the sum of values multiplied by t-1)).

Through this process, a fire risk prediction model may be trained based on a plurality of basic vectors, a plurality of state vectors, and a plurality of correct answer fire risks.

In step S630, the fire detection module may transmit a warning message to the pre-connected terminal through the communication unit based on the fact that the fire risk is greater than or equal to a preset first value. The fire risk may be a value greater than 0 and less than or equal to 100. Here, the caution message is a message informing that caution is necessary because there is a risk of fire. The pre-connected terminal may be at least one of a vehicle terminal inside the electric vehicle or a pre-connected occupant's smartphone. For example, the warning message may include information on the state of the electric vehicle and information on how to deal with a fire. For example, the information on the state of the electric vehicle may include information on the temperature and impact amount of a battery module currently installed in the electric vehicle. Information on how to cope with a fire may include an image and text explaining how to cope with the occupant in case of a fire in the battery module.

In step S640, the fire detection module may transmit a report message to an external server, surrounding vehicle terminals, and pre-connected terminals through a communication unit based on the fact that the fire risk level is greater than or equal to a preset second value. Here, the report message is a message for performing a fire report upon determining that a fire has occurred. The external server may include a server capable of responding to an emergency, such as a server related to the National Fire Agency and a server related to the National Police Agency. For example, the preset second value may be greater than the preset first value.

For example, the report message includes information about the location of the electric vehicle, information about the location of the first fire extinguishing water inlet and the location of the second fire extinguishing water inlet, how to use the first nozzle fastening part, and how to use the second nozzle fastening part. information may be included. Information on the location of the electric vehicle is information for determining the location of the electric vehicle, and coordinate information obtained through the Global Positioning System (GPS) device installed in the electric vehicle and received from a photographing device (eg, black box) installed in the electric vehicle It can contain still images or moving images. For example, the fire detection module may periodically receive information on the location of the electric vehicle from a vehicle terminal inside the electric vehicle, and may periodically update and store the information on the location of the electric vehicle in a memory. The information on the location of the first fire extinguishing water inlet and the second fire extinguishing water inlet is information indicating the location of the first fire extinguishing water inlet and the second fire extinguishing water inlet of the electric vehicle, and the first fire extinguishing water inlet and the second fire extinguishing water inlet. It may include a drawing of an electric vehicle with a water inlet displayed. For example, information on the location of the first fire extinguishing water inlet and information on the location of the second fire extinguishing water inlet may be pre-stored in the memory of the fire detection module. The information on the method of using the first nozzle fastening unit and the method of using the second nozzle fastening unit is information indicating how to fasten the fire-fighting water supply nozzle to the first nozzle fastening unit and the second nozzle fastening unit, and the first nozzle fastening unit and An image of the second nozzle fastening unit and text on how to fasten the fire-fighting water supply nozzle to each nozzle fastening unit may be included.

In step S650, the fire detection module may operate a cooling fan connected to the fire detection module according to the fire risk.

For example, the fire detection module may be pre-connected with a cooling fan installed in the exhaust vent. For example, the fire detection module may determine the intensity of a cooling fan according to the degree of fire risk, and may transmit information about the intensity of the cooling fan to the cooling fan. The cooling fan may operate according to information about the strength of the cooling fan received from the fire detection module. For example, as the risk of fire increases, the strength of the cooling fan may be determined to increase.

Throughout this specification, a neural network, a neural network, and a network function may be used interchangeably. A neural network may consist of a set of interconnected computational units, which may be generally referred to as “nodes”. These “nodes” may also be referred to as “neurons”. A neural network includes at least two or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more “links”.

In a neural network, two or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, the input node to output node relationship can be created around the link. More than one output node can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, a node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may be determined based on the weight.

As described above, in a neural network, two or more nodes are interconnected through one or more links to form an input node and output node relationship in the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having the same number of nodes and links and different weight values between the links, the two neural networks may be recognized as different from each other.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (5)

In the device for protecting the battery module provided in the electric vehicle,
an electric vehicle battery protection cover composed of a plurality of layers and surrounding the battery module;
A first fire extinguishing water inlet formed on one side of the electric vehicle battery protection cover and including a first check valve;
A first fire hose having one side connected to the first check valve and the other side connected to a first nozzle coupling part provided at a lower end of a charging port of the electric vehicle;
A second fire extinguishing water inlet formed on the other side of the electric vehicle battery protection cover and including a second check valve;
a second fire hose having one side connected to the second check valve and the other side connected to a second nozzle coupling part provided at the lower end of the rear trunk of the electric vehicle;
an exhaust port formed on the other side of the electric vehicle battery protection cover and spaced apart from the second fire extinguishing water inlet in the width direction of the electric vehicle;
An exhaust pipe having one side connected to the exhaust port and the other side spaced apart from the second check valve in the width direction of the electric vehicle and connected to a third check valve provided at the bottom of the rear trunk of the electric vehicle,
A cover is installed on the first nozzle fastening part and the second nozzle fastening part, respectively, and after the cover is removed, the fire extinguishing water supply nozzle is fastened from the outside,
The plurality of layers may include a first cover layer made of polyimide to which a first heat-resistant coating agent is applied, a second cover layer made of flame retardant silicone rubber to which a second heat-resistant coating agent is applied to protect the battery module from external impact, and the It is located between the first cover layer and the second cover layer and includes a buffer layer of polyurethane material,
The first heat-resistant coating agent is applied to the exhaust pipe,
The second heat-resistant coating is applied to the first fire hose and the second fire hose,
An extinguishing powder layer in direct contact with the battery module is further included in the plurality of layers,
The extinguishing powder layer is composed of a material that melts at a temperature of 160 to 180 degrees and surrounds the first extinguishing powder and the second extinguishing powder,
When the battery module fires, the extinguishing powder layer is melted, so that the first extinguishing powder and the second extinguishing powder are supplied to the battery module,
A fire detection module is mounted on the battery module wrapped with the electric vehicle battery protection cover,
The fire detection module includes a control unit, a memory, a power supply unit, a sensor unit and a communication unit,
The control unit,
Measuring the temperature of the battery module and the amount of impact applied to the battery module in real time through the sensor unit;
Determine the fire risk of the battery module through a fire risk prediction model using a neural network based on basic information related to the electric vehicle, the temperature of the battery module, and the amount of impact applied to the battery module;
Based on the fact that the fire risk is greater than or equal to a preset value, a report message is transmitted to an external server, surrounding vehicle terminals, and pre-connected terminals through the communication unit;
The report message includes information on the location of the electric vehicle, information on the location of the first fire extinguishing water inlet and the location of the second fire extinguishing water inlet, how to use the first nozzle fastening part and how to use the second nozzle fastening part. contains information about
The basic information related to the electric vehicle includes information about the year of the electric vehicle and information about the model of the electric vehicle,
A basic vector for a battery module is determined through data preprocessing on basic information related to the electric vehicle;
The basic vector for the battery module is a value representing the period from the date the electric vehicle was manufactured to the present date, a value representing one of the types of a cylindrical battery, a pouch-type battery, and a prismatic battery, a value for the capacity of the battery, and a value for the battery module A value indicating the type of cathode material, a value indicating the type of anode material of the battery module, a value indicating the type of separator of the battery module, and a value indicating the type of electrolyte of the battery module,
A state vector for the battery module is determined through data preprocessing on the temperature of the battery module and the amount of impact applied to the battery module;
The state vector includes a value for temperature per unit time and a value for impulse per unit time,
The fire risk of the battery module is determined based on the basic vector and the state vector of the battery module being input to the neural network;
The neural network includes an input layer, one or more hidden layers and an output layer;
Each learning data composed of a plurality of base vectors, a plurality of state vectors, and a plurality of answer fire risks is input to the input layer of the neural network, passes through the one or more hidden layers and the output layer, and is output as an output vector. An output vector is input to a loss function layer connected to the output layer, and the loss function layer outputs a loss value using a loss function that compares the output vector with the correct answer vector for each learning data, and outputs a loss value of the neural network. The parameter is learned in a direction in which the loss value becomes smaller,
The fire detection module is pre-connected to a cooling fan installed in the exhaust port,
The strength of the cooling fan is determined according to the fire risk,
Information on the strength of the cooling fan is transmitted to the cooling fan;
The cooling fan operates according to the information on the strength of the cooling fan received from the fire detection module,
As the fire risk increases, the strength of the cooling fan is determined to increase.
Device.
delete According to claim 1,
The first heat-resistant coating agent is a coating agent in which silicon carbide is added to a binder prepared by mixing a dispersion solution of silica sol containing 30 to 45 mass percent of solid components dispersed in water and an aluminum hydroxide solution,
The second heat-resistant coating is a coating agent composed of a solution containing polyurethane-urea,
The first digested powder is an expanded vermiculite powder having a particle size of 160 ~ 200um,
The second extinguishing powder includes 75 parts by weight of ammonium monophosphate, 10 parts by weight of graphite, and 15 parts by weight of silica,
The mixing ratio of the first extinguishing powder and the second extinguishing powder is 7:3 by weight,
Device. delete delete

Images