Vehicle fire protection control method based on inductor

Abstract

The invention relates to the technical field of new energy automobiles, and discloses an inductor-based vehicle fire protection control method, which comprises the following steps of: acquiring the matrix temperature of a vehicle battery compartment, the characteristic data of infrared thermal imaging in a passenger compartment and the content of ppm-level combustible gas in a warehouse based on sensors distributed in an array in a vehicle; carrying out data preprocessing on the collected characteristic data of infrared thermal imaging in the passenger cabin, and generating a multi-dimensional open fire comprehensive detection coefficient according to the data preprocessing; reversely combining and generating a fire prediction model and a targeted fire extinguishing model based on the multi-dimensional open fire comprehensive detection coefficient; fire extinguishing execution modules are arranged in a passenger compartment, a warehouse and a battery compartment of a vehicle. According to the method, a data-driven fire prediction model is constructed based on the empirical formula of the temperature difference and the open fire detection coefficient fitted by the sample data, early fire early warning and graded response are supported, fire diffusion is avoided, and vehicle loss is reduced to the maximum extent.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy vehicles, and particularly relates to a vehicle fire protection control method based on sensors. BACKGROUND

[0002] With the rapid development of new energy vehicles, the fire risk caused by potential fire sources such as battery systems, electrical components and cargo warehouse combustibles is increasingly prominent. The existing vehicle fire protection system mainly relies on a single sensor (such as a temperature or smoke sensor), which is difficult to comprehensively capture multi-dimensional fire characteristics such as local overheating of the battery compartment, open fire in the passenger compartment or combustible gas leakage in the cargo compartment, and is prone to false positives or false negatives due to environmental interference. In addition, the traditional fire extinguishing system often uses a single trigger mode, which has insufficient response speed and lacks precision in the coverage range of the fire extinguishing agent, which may delay the initial fire control or cause resource waste. At the same time, most systems lack real-time communication modules, and fire information cannot be transmitted to the rescue platform in a timely manner, affecting the efficiency of accident response and tracing.

[0003] An existing patent discloses a fire alarm and protection device for a passenger car lithium battery box (publication number CN107433000A). The fire alarm and protection device for the passenger car lithium battery box includes a vehicle control system, a fire extinguishing device arranged on the passenger car chassis and a plurality of battery boxes, a display screen and a control panel arranged in the cab; the battery boxes are connected with the fire extinguishing device by a fire extinguishing agent delivery pipeline; each battery box is provided with a detection module, and the detection module is connected with the display screen by a power supply and control system wire harness and connected with the fire extinguishing device by a fire detection wire harness. The technology disclosed in this patent is based on fixed weight or simple average in temperature monitoring, cannot dynamically integrate multi-sensor data, and is difficult to accurately reflect the overall thermal state of the battery compartment; and the fire determination threshold is a fixed value, which cannot adapt to the day-night temperature difference or regional climate fluctuations, further reducing the reliability of the system. SUMMARY

[0004] The present application provides a vehicle fire protection control method based on sensors to solve the problem that the prior art cannot dynamically integrate multi-sensor data and accurately reflect the overall thermal state of the battery compartment.

[0005] To solve the above technical problems, according to one aspect of the present application, more specifically, a vehicle fire protection control method based on sensors, a fire extinguishing execution module is arranged in the vehicle passenger compartment, cargo compartment and battery compartment, a thermocouple is arranged in the battery compartment, an infrared thermal imaging device is arranged in the passenger compartment, and a VOC sensor is arranged in the cargo compartment. The method comprises the following steps:

[0006] Collecting the matrix temperature of the vehicle battery compartment, the characteristic data of the infrared thermal imaging in the passenger compartment and the ppm-level combustible gas content in the cargo compartment;

[0007] The collected infrared thermal imaging feature data in the passenger compartment is preprocessed, and a multi-dimensional open fire comprehensive detection coefficient is generated according to the preprocessed infrared thermal imaging feature data in the passenger compartment;

[0008] Based on the multi-dimensional open fire comprehensive detection coefficient, a fire prediction model and a targeted fire extinguishing model are reversely combined and generated;

[0009] The targeted fire extinguishing model starts the fire extinguishing execution module of the corresponding compartment according to the feedback feature data;

[0010] The targeted fire extinguishing model allows the fire extinguishing execution module to spray aerosol in one of the battery compartment, the passenger compartment or the cargo compartment alone for 30ms according to the feedback feature data, while the fire prediction model allows the fire extinguishing execution module to spray aerosol in all of the battery compartment, the passenger compartment and the cargo compartment for 30ms according to the feedback feature data.

[0011] Further, the matrix temperature of the vehicle battery compartment is collected by the 8-channel thermocouple array distributedly arranged in the battery compartment;

[0012] The infrared thermal imaging feature data in the passenger compartment is collected by the infrared thermal imaging device arranged in the passenger compartment;

[0013] The ppm-level flammable gas content in the cargo compartment is monitored by the VOC sensor arranged in the cargo compartment.

[0014] Further, the matrix temperature is calculated by using the dynamic weight-gradient composite temperature model based on the data collected by the 8-channel thermocouple array distributedly arranged in the battery compartment.

[0015] Further, the open fire comprehensive detection coefficient refers to the deviation value between the value obtained after eliminating the temperature error collected by infrared thermal imaging by using two-point correction method and the threshold value set based on the environmental temperature.

[0016] Further, the targeted fire extinguishing model performs first-level local suppression on the battery compartment, the passenger compartment or the cargo compartment according to whether the matrix temperature of the battery compartment, the open fire comprehensive detection coefficient of the passenger compartment or the ppm-level flammable gas content in the cargo compartment exceeds the set value.

[0017] Further, the fire prediction model judges whether to perform second-level all-compartment coverage on the vehicle according to the matrix temperature of the battery compartment and the open fire comprehensive detection coefficient of the passenger compartment, and the calculation formula is:

[0018] ;

[0019] In the formula, represents the condition coefficient for determining whether to perform the second-level full-bin coverage; represents the matrix temperature of the vehicle battery bin, unit ℃; represents the threshold value set based on the adaptive environmental temperature; represents the comprehensive detection coefficient of the collected open fire in the passenger compartment.

[0020] Further, the fire extinguishing execution module sprays aerosol in one of the battery compartment, the passenger compartment or the cargo compartment alone for 30ms, which is a first-level local suppression operation performed by the aerosol sprayer arranged in the battery compartment, the passenger compartment and the cargo compartment;

[0021] The fire extinguishing execution module sprays aerosol in the battery compartment, the passenger compartment and the cargo compartment simultaneously for 30ms, which is a first-level full-bin coverage operation performed by the aerosol sprayer and the high-pressure perfluorohexone pipe network system arranged in the battery compartment, the passenger compartment and the cargo compartment.

[0022] Further, the fire extinguishing execution module starts the emergency communication module after performing the first-level local suppression or the second-level full-bin coverage.

[0023] Further, the emergency communication module integrates 4G / 5G+V2X dual-mode communication and automatically sends the fire grade, location information and vehicle state predicted by the fire prediction model.

[0024] The vehicle fire protection control method based on the inductor provided by the application has the following effects compared with the prior art:

[0025] 1、The application collects data in multiple dimensions through the 8-channel thermocouple array of the battery compartment, the infrared thermal imaging device of the passenger compartment and the VOC sensor of the cargo compartment, combines the dynamic weight-gradient composite temperature model and the two-point correction method, significantly improves the accuracy of temperature monitoring and open fire detection, reduces the false alarm and missed alarm risk caused by environmental interference, and provides a high-reliability data basis for fire prediction.

[0026] 2、The application adopts a two-level fire extinguishing strategy, the first level performs local suppression on the fire source through a 30ms fast aerosol sprayer, and the second level realizes full-bin coverage through a high-pressure perfluorohexone pipe network system. This mechanism can quickly control the initial fire, completely extinguish the spreading fire, reduce the waste of fire extinguishing agent, and avoid misoperation on the unburned area.

[0027] 3、The application effectively integrates the multi-channel thermocouple data in the battery compartment through dynamic weight distribution (based on an exponential weighted temperature fusion term) and a maximum temperature change rate term, solves the limitations of single-point temperature monitoring, accurately reflects the overall thermal state of the battery compartment, and provides more comprehensive temperature feature parameters for fire prediction.

[0028] 4、The application dynamically adjusts the open fire detection threshold based on the ambient temperature, and introduces standard deviation calculation to obtain safety margin, effectively reducing false triggering caused by environmental fluctuations; after fire extinguishing execution, the 4G / 5G+V2X emergency communication module is automatically started, and the fire level, position and vehicle state information are sent in real time, providing support for remote monitoring and rapid rescue.

[0029] 5、The application is based on the temperature difference and open fire detection coefficient empirical formula (conditional coefficient g) fitted by sample data, and a data-driven fire prediction model is constructed to support early fire warning and hierarchical response, avoid fire spread, and minimize vehicle loss. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 is a structural schematic diagram of the application;

[0031] Figure 2 is a conditional coefficient g and temperature difference relationship diagram in the application;

[0032] Figure 3 is a conditional coefficient g and detection coefficient relationship diagram in the application;

[0033] Figure 4 is a conditional coefficient g and temperature difference , detection coefficient model diagram in the application. DETAILED DESCRIPTION

[0034] In order to make the technical scheme of the application clearer, the application will be further described in detail below in combination with the drawings and specific embodiments.

[0035] Embodiment 1

[0036] As shown in Figure 1 , according to one aspect of the application, a vehicle fire protection control method based on inductor is provided, which comprises the following:

[0037] Based on the array distribution of sensors in the vehicle, the matrix temperature of the vehicle battery compartment, the feature data of infrared thermal imaging in the passenger compartment, and the ppm-level flammable gas content in the cargo compartment are collected; the battery compartment is distributed with an 8-channel thermocouple array (wherein the distance between each two thermocouples is equal); the passenger compartment is equipped with an infrared thermal imaging device; the cargo compartment is equipped with a VOC sensor for monitoring ppm-level flammable gas content.

[0038] Among them, the 8-channel thermocouple array refers to a temperature detection system composed of 8 distributed thermocouples in the battery compartment, which is used for multi-point synchronous monitoring of temperature changes.

[0039] Infrared thermal imaging equipment is a device that detects the temperature distribution of the surface of an object using infrared radiation principles, and can generate thermal images for fire detection.

[0040] VOC sensor refers to a volatile organic compound sensor used to detect the content of flammable gas in ppm (parts per million) in the warehouse.

[0041] Temperature data is collected by an 8-channel thermocouple array distributed in the battery compartment, and the matrix temperature is calculated by combining a dynamic weight-gradient composite temperature model (including exponential weighted temperature fusion, maximum temperature change rate, and spatial gradient term). Multi-sensor fusion and dynamic weight distribution significantly improve the accuracy of temperature monitoring, avoid single-point errors, and provide a high-precision data foundation for fire prediction.

[0042] The matrix temperature is calculated based on the data collected by the 8-channel thermocouple array distributed in the battery compartment and using a dynamic weight-gradient composite temperature model; the dynamic weight-gradient composite temperature model includes an exponential weighted temperature fusion term and a maximum temperature change rate term. The specific calculation formula of the dynamic weight-gradient composite temperature model is:

[0043] ;

[0044] wherein, Tm represents the matrix temperature of the vehicle battery compartment, in ℃, wi represents the influence weight of the i-channel thermocouple on the matrix temperature, and has:

[0045] ;

[0046] In the formula, Ti represents the real-time detection temperature of the i-channel thermocouple, in ℃; wi represents the weight sensitivity coefficient, and is taken as ℃; Tb represents the reference temperature of the battery compartment (usually taken as the ambient temperature + 20℃); ΔTi represents the temperature change amount of the thermocouple in time; Δt represents the sampling time interval, in s; α represents the change rate weight coefficient (generally taken as 0.2~0.5).

[0047] The dynamic weight-gradient composite temperature model is an algorithm for calculating the matrix temperature of the battery compartment, which combines exponential weighted temperature fusion ( ) and maximum temperature change rate ( ).

[0048] The matrix temperature is a comprehensive temperature value calculated by the 8-channel thermocouple array data, which reflects the overall thermal state of the battery compartment.

[0049] Embodiment 2

[0050] As shown in the following formula, the feature data of the collected infrared thermal imaging in the passenger compartment is pre-processed, and a multi-dimensional open fire comprehensive detection coefficient is generated according to the pre-processed feature data of the infrared thermal imaging in the passenger compartment. Figure 1

[0051] The open fire comprehensive detection coefficient (c) is a quantitative index calculated based on the infrared thermal imaging data, reflecting the possibility of the existence of open fire in the passenger compartment. The deviation value between the value obtained after eliminating the temperature error collected by the infrared thermal imaging by using the two-point correction method (the two-point correction method is a calibration method for infrared thermal imaging data, which eliminates the temperature measurement error by using two reference points of black body and ambient temperature) and the threshold value set adaptively based on the ambient temperature. The specific calculation formula of the open fire comprehensive detection coefficient is as follows:

[0052]

[0053] In the formula, c represents the open fire comprehensive detection coefficient of the collected passenger compartment, and when c < 0, it means that the first level of local suppression needs to be performed on the passenger compartment (whether to perform the second level of full compartment coverage needs to be judged again later). In the formula, c represents the value obtained after eliminating the temperature error collected by the infrared thermal imaging by using the two-point correction method; and c0 represents the threshold value set adaptively based on the ambient temperature; and then there is:

[0054]

[0055] In the formula, c represents the value obtained after eliminating the temperature error collected by the infrared thermal imaging by using the two-point correction method; and c0 represents the threshold value set adaptively based on the ambient temperature; and then there is: In the formula, c represents the value obtained after eliminating the temperature error collected by the infrared thermal imaging by using the two-point correction method; and c0 represents the threshold value set adaptively based on the ambient temperature; and then there is:

[0056]

[0057] In the formula, c represents the value obtained after eliminating the temperature error collected by the infrared thermal imaging by using the two-point correction method; and c0 represents the threshold value set adaptively based on the ambient temperature; and then there is: In the formula, T represents the ambient temperature outside the vehicle, unit: ℃; and T0 represents the preset safety margin (typical value: 10℃), and T0 < T < T0 + 10; and T0 represents the standard deviation of the ambient temperature in the past 5 minutes.

[0058] ​​​​​​​​​​​Two-point correction method is used to eliminate errors of infrared thermal imaging data of the passenger compartment, and a comprehensive fire detection coefficient (deviation value) is generated by combining the adaptive threshold of the ambient temperature. The fluctuation of the ambient temperature reduces the interference on the detection, reduces the false alarm rate, ensures that the fire extinguishing is triggered only when there is a clear fire, and improves the reliability of the system.

[0059] Embodiment 3

[0060] As shown in Figure 1 , based on the fire extinguishing execution module built in the vehicle passenger compartment, cargo compartment and battery compartment, the target fire extinguishing model starts the fire extinguishing execution module of the corresponding compartment according to the feedback characteristic data; the target fire extinguishing model respectively performs first-level local suppression on the battery compartment, passenger compartment or cargo compartment according to whether the matrix temperature of the battery compartment, the comprehensive fire detection coefficient of the passenger compartment or the content of ppm-level flammable gas in the cargo compartment exceeds the set value.

[0061] The target fire extinguishing model starts the decision model of the fire extinguishing device of a specific compartment (battery compartment, passenger compartment or cargo compartment) according to the fire characteristic data of the compartment. Among them, the target fire extinguishing model starts the local suppression of the corresponding compartment according to whether the battery compartment temperature, passenger compartment fire coefficient or cargo compartment flammable gas content exceeds the threshold value. Precise positioning of the fire source position and directional fire extinguishing can reduce the waste of fire extinguishing agent, avoid misoperation on the unburned area, and improve the fire extinguishing efficiency.

[0062] Embodiment 4

[0063] As shown in Figure 1 , the fire prediction model will make the fire extinguishing execution module perform second-level full-compartment coverage according to the feedback characteristic data.

[0064] The first-level local suppression is to use a 30ms fast-response aerosol sprayer to perform fast suppression on one of the battery compartment, passenger compartment and cargo compartment; the second-level full-compartment coverage is to use a high-pressure perfluorohexone pipe network system (a high-pressure pipe network fire extinguishing system using perfluorohexone, a clean fire extinguishing agent, as the fire extinguishing medium) to simultaneously perform fire extinguishing agent coverage on the battery compartment, passenger compartment and cargo compartment.

[0065] The first-level local suppression uses a 30ms fast-response aerosol sprayer to control the initial fire; the second-level full-compartment coverage uses a high-pressure perfluorohexone pipe network system to comprehensively cover all compartments. The hierarchical response mechanism takes into account fast control and comprehensive extinguishing, optimizes resource allocation, shortens response time, and maximizes fire loss reduction.

[0066] The fire prediction model judges whether to perform second-level full-compartment coverage on the vehicle according to the matrix temperature of the battery compartment and the comprehensive fire detection coefficient of the passenger compartment, and the calculation formula is:

[0067] ;

[0068] In the formula, represents the condition coefficient for determining whether to perform the second-level full-warehouse coverage; represents the matrix temperature of the vehicle battery warehouse, in ℃; represents the threshold value set based on the adaptive ambient temperature; represents the comprehensive detection coefficient of open fire in the passenger warehouse, when represents that the first-level local suppression needs to be performed on the passenger warehouse.

[0069] In the above formula, when represents that the condition for performing the first-level local suppression in the passenger warehouse is not met; and at this time , then it also represents that the condition for performing the second-level full-warehouse coverage is not met.

[0070] When and are not practically meaningful, therefore, the necessary condition for performing the second-level full-warehouse coverage in the present application is , .

[0071] Among them, when the matrix temperature of the vehicle battery warehouse is ℃, and the threshold value set based on the adaptive ambient temperature is ℃, the comprehensive detection coefficient of open fire in the passenger warehouse is . Then there is:

[0072] ;

[0073] From the calculation in the above formula, it can be known that the condition coefficient for determining whether to perform the second-level full-warehouse coverage is ; and by comparing multiple sets of data, there is:

[0074] Table 1 Partial implementation data and vehicle actual state

[0075]

[0076] According to the data in Table 1 above, it can be known that when the sample data tends to infinity, there will be a dividing line to divide the state of the vehicle with the value of the condition coefficient g, when after that, there will be obvious abnormalities. Based on this, the state of the vehicle can be determined by .

[0077] Example 5

[0078] As Figures 1-4As shown, a fire prediction model and a targeted fire extinguishing model are generated by reversely combining multi-dimensional open flame comprehensive detection coefficients. Based on sample data, empirical formulas (such as the conditional coefficient g) are fitted to temperature differences and open flame detection coefficients to construct a fire prediction model to determine the fire severity. This data-driven model enhances prediction accuracy, supports early warning and proactive intervention, and prevents the spread of fire.

[0079] The fire prediction model formula is an empirical analysis conducted to solve practical business problems. The resulting data and the characteristic relationships between the data are the external manifestations of the empirical formula (an empirical formula is a mathematical relationship established based on experimental data or observations, rather than derived from theory). The reasoning process is as follows:

[0080] 1) Fit the formula of the conditional coefficient g used to determine whether to execute the second-level full warehouse coverage.

[0081] Among them, the conditional coefficient g used to determine whether to execute the second-level full-bin coverage can be expressed by the number of obviously abnormal vehicles in the sample.

[0082] For example, if data from 100 vehicle samples is collected and the degree of abnormality of a certain vehicle exceeds the data from the other 50 samples after manual evaluation, then it means that the conditional coefficient g=50% for the vehicle after manual evaluation to implement the second-level full warehouse coverage.

[0083] Other data are calculated and fitted using data collected by the device itself.

[0084] 2) Condition coefficient g and temperature difference Establish a mathematical model of the relationship between Figure 2 As shown in the figure, the red dots are the distribution of the 100 samples collected), then:

[0085] (Formula 1)

[0086] In the above formula 1, k represents an empirical constant for adjusting the sensitivity of the above model.

[0087] 3) Condition coefficient g and detection coefficient Establish a mathematical model of the relationship between Figure 3 As shown in the figure, the blue dots are the distribution of the 100 samples collected), then:

[0088] (Formula 2)

[0089] In the above formula 2, k represents an empirical constant for adjusting the sensitivity of the above model.

[0090] 4) Condition coefficient g and temperature difference , the detection coefficient between the relationship to establish a mathematical model (as Figure 4 shown, the temperature difference , the detection coefficient positive correlation between the relationship), and combined by the above formula 1 and formula 2 characteristic relationship, then:

[0091] g= (formula 1) x (formula 2);

[0092] Then according to the above derivation can know that the fire prediction model formula is:

[0093] .

[0094] Example 6

[0095] As Figure 1 shown, the fire extinguishing execution module starts the emergency communication module after executing the first level local suppression or the second level full warehouse covering. The emergency communication module integrates 4G / 5G+V2X (V2X represents Vehicle-to-Everything (car networking) technology, realizes the communication between vehicle and surrounding environment (other vehicles, infrastructure, etc.)) dual-mode communication, automatically sends the fire level, position information and vehicle state predicted by the fire prediction model. After the fire extinguishing execution, the 4G / 5G+V2X dual-mode emergency communication module is automatically started, and the fire level, position and vehicle state information are sent in real time. Remote monitoring and rapid rescue response are realized, the safety of passengers is improved, and key data support is provided for accident tracing.

[0096] The above-described embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it cannot be understood as limiting the scope of the patent of the present application. It should be noted that for ordinary skilled in the art, without departing from the concept of the present application, a number of variations and improvements can be made, which belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A vehicle fire protection control method based on a sensor, characterized in that: Fire extinguishing execution modules are configured in the vehicle's passenger compartment, cargo compartment, and battery compartment, and a thermocouple is configured in the battery compartment, an infrared thermal imaging device is configured in the passenger compartment, and a VOC sensor is configured in the cargo compartment. The method includes the following steps: Collect the matrix temperature of the vehicle battery compartment, the characteristic data of infrared thermal imaging in the passenger compartment, and the ppm-level combustible gas content in the cargo compartment; Preprocessing the collected infrared thermal imaging feature data of the passenger compartment, and generating a multi-dimensional open flame comprehensive detection coefficient based on the preprocessed infrared thermal imaging feature data of the passenger compartment; Reversely combine and generate a fire prediction model and a targeted fire extinguishing model based on the multi-dimensional open fire comprehensive detection coefficient; The targeted fire extinguishing model activates the fire extinguishing execution module of the corresponding compartment according to the feedback characteristic data; The targeted fire extinguishing model enables the fire extinguishing execution module to perform aerosol spraying on one of the battery compartment, passenger compartment or cargo compartment separately within 30ms based on the feedback characteristic data; while the fire prediction model enables the fire extinguishing execution module to perform aerosol spraying on all of the battery compartment, passenger compartment and cargo compartment within 30ms based on the feedback characteristic data.

2. The sensor-based vehicle fire protection control method according to claim 1, characterized in that: The matrix temperature of the vehicle battery compartment is collected through an 8-channel distributed array of thermocouples built into the battery compartment; The characteristic data of the infrared thermal imaging in the passenger compartment is collected by the infrared thermal imaging device built into the passenger compartment; The ppm level combustible gas content in the cargo warehouse is monitored by a VOC sensor built into the cargo warehouse.

3. The sensor-based vehicle fire protection control method according to claim 2, characterized in that: The matrix temperature is obtained based on the data collected by the distributed 8-channel thermocouple array in the battery compartment and calculated using the dynamic weight-gradient composite temperature model.

4. The sensor-based vehicle fire protection control method according to claim 2, characterized in that: The open flame comprehensive detection coefficient refers to the deviation between the value obtained after eliminating the temperature error collected by infrared thermal imaging using a two-point correction method and the threshold value set adaptively based on the ambient temperature.

5. The sensor-based vehicle fire protection control method according to claim 1, characterized in that: The targeted fire extinguishing model performs first-level local suppression on the battery compartment, passenger compartment or cargo compartment respectively according to whether the matrix temperature of the battery compartment, the comprehensive open flame detection coefficient of the passenger compartment or the ppm-level combustible gas content in the cargo compartment exceeds the set value.

6. The sensor-based vehicle fire protection control method according to claim 1, characterized in that: The fire prediction model determines whether to implement the second-level full compartment coverage for the vehicle based on the matrix temperature of the battery compartment and the comprehensive open flame detection coefficient of the passenger compartment. The calculation formula is: ； Where, Indicates the condition coefficient used to determine whether to execute the second-level full warehouse coverage; Indicates the matrix temperature of the vehicle battery compartment, unit: °C; Indicates setting an adaptive threshold based on the ambient temperature; Indicates the comprehensive detection coefficient of open flames collected in the passenger compartment.

7. The sensor-based vehicle fire protection control method according to claim 1, characterized in that: The fire extinguishing execution module performs aerosol spraying on one of the battery compartment, passenger compartment or cargo compartment within 30ms, and performs a first-level local suppression operation through aerosol sprayers configured in the battery compartment, passenger compartment and cargo compartment; The fire extinguishing execution module simultaneously performs aerosol spray coverage on the battery compartment, passenger compartment and cargo compartment within 30ms, and performs the first-level full-compartment coverage operation through aerosol sprayers and high-pressure perfluorohexanone pipe network systems configured in the battery compartment, passenger compartment and cargo compartment.

8. The sensor-based vehicle fire protection control method according to claim 1, characterized in that: The fire extinguishing execution module activates the emergency communication module after executing the first level local suppression or the second level full warehouse coverage.

9. The sensor-based vehicle fire protection control method according to claim 8, characterized in that: The emergency communication module integrates 4G / 5G+V2X dual-mode communication and automatically sends the fire level, location information and vehicle status predicted by the fire prediction model.

Images