A method and system for battery safety protection in a vehicle collision

Abstract

The application relates to the technical field of automobile power battery protection, in particular to a battery safety protection method and system in automobile collision, which comprises the following steps: acquiring first information and second information, the first information is current, voltage and temperature data of a vehicle power battery monitored in real time, and the second information is historical abnormal data of the power battery after the vehicle suffers a collision; a convolutional neural network model is used to extract features of the first information and the second information, and a prediction result is obtained; a protection mode corresponding to the power battery after the vehicle suffers a collision is determined according to the prediction result; and the power battery of the vehicle is protected according to the protection mode. According to the application, corresponding control commands are sent according to the predicted abnormal conditions to protect the power battery of the vehicle, the safety of the power battery of the vehicle can be effectively improved, the possibility of explosion or electric leakage of the power battery of the vehicle is reduced, and the safety of drivers and passengers is ensured.

Description

Technical Field

[0001] This invention relates to the field of automotive power battery protection technology, and more specifically, to a method and system for battery safety protection in automotive collisions. Background Technology

[0002] With the increasing scarcity of fuel resources, intensified environmental pollution, and growing awareness of environmental protection, my country has begun to vigorously develop new energy vehicles. In these vehicles, the power battery pack, as the energy source, occupies a crucial position. During collisions, the power battery is prone to explosion or leakage, leading to safety accidents. Current technologies typically employ high-performance enclosure structures for battery safety protection; however, this still cannot prevent cracks or short circuits in the battery after a collision. Therefore, there is an urgent need for a battery safety protection method in automotive collisions to address cracks or short circuits in the power battery after a collision. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for battery safety protection in automobile collisions, so as to improve the above-mentioned problems.

[0004] To achieve the above objectives, the embodiments of this application provide the following technical solutions:

[0005] On one hand, embodiments of this application provide a method for battery safety protection in a car collision, the method comprising:

[0006] The system acquires first information and second information. The first information is real-time monitored data on the current, voltage, and temperature of the vehicle's power battery. The second information is historical abnormal data of the power battery after a collision. The historical abnormal data includes abnormal current, abnormal voltage, and abnormal temperature of the vehicle's power battery.

[0007] The first and second information are extracted using a convolutional neural network model to obtain a prediction result, which includes a short circuit or leakage of the vehicle's power battery.

[0008] Based on the prediction results, determine the corresponding protection method for the power battery after the vehicle is involved in a collision.

[0009] The vehicle's power battery is protected according to the aforementioned protection method.

[0010] Secondly, embodiments of this application provide a battery safety protection system during a car collision, the system comprising:

[0011] The acquisition module is used to acquire first information and second information. The first information is the real-time monitored current, voltage and temperature data of the vehicle's power battery. The second information is the historical abnormal data of the power battery after the vehicle has been involved in a collision. The historical abnormal data includes abnormal current, abnormal voltage and abnormal temperature of the vehicle's power battery.

[0012] An extraction module is used to extract features from the first information and the second information using a convolutional neural network model to obtain a prediction result, the prediction result including a short circuit in the vehicle power battery or leakage in the vehicle power battery.

[0013] The first processing module is used to determine the protection method corresponding to the power battery after the car is hit by a collision based on the prediction results.

[0014] The second processing module is used to provide safety protection for the vehicle's power battery according to the protection method.

[0015] Thirdly, embodiments of this application provide a battery safety protection device in a vehicle collision, the device including a memory and a processor. The memory stores a computer program; the processor executes the computer program to implement the steps of the aforementioned battery safety protection method in a vehicle collision.

[0016] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described battery safety protection method in a car collision.

[0017] The beneficial effects of this invention are as follows:

[0018] This invention predicts abnormal situations that may occur in a vehicle's power battery after a collision by monitoring the current, voltage, and temperature data of the vehicle's power battery in real time, as well as abnormal current, voltage, and temperature when the vehicle is involved in an accident. Based on the predicted abnormal situations, corresponding control commands are sent to protect the vehicle's power battery. Different protective measures are taken according to different abnormal situations, which can effectively improve the safety of the vehicle's power battery and reduce the possibility of explosion or leakage, thereby ensuring the safety of the driver and passengers.

[0019] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the battery safety protection method in a car collision as described in an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram of the battery safety protection system in a car collision as described in an embodiment of the present invention.

[0023] Figure 3 This is a schematic diagram of the battery safety protection device in a car collision as described in an embodiment of the present invention.

[0024] The diagram is labeled as follows: 901, Acquisition module; 902, Extraction module; 903, First processing module; 904, Second processing module; 800, Battery safety protection device in car collision; 801, Processor; 802, Memory; 803, Multimedia component; 804, I / O interface; 805, Communication component. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0026] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0027] Example 1:

[0028] This embodiment provides a battery safety protection method in a car collision. It can be understood that this embodiment can set up a scenario, such as: when driving an electric vehicle, the electric vehicle is hit by a collision and the power battery of the electric vehicle needs to be monitored and protected.

[0029] See Figure 1 The figure shows that the method includes steps S1, S2, S3, and S4, which are specifically as follows:

[0030] Step S1: Obtain first information and second information. The first information is the real-time monitored current, voltage and temperature data of the vehicle's power battery. The second information is the historical abnormal data of the power battery after the vehicle has been involved in a collision. The historical abnormal data includes abnormal current, abnormal voltage and abnormal temperature of the vehicle's power battery.

[0031] It is understandable that the voltage and temperature data of the vehicle's power battery in the first information are obtained from real-time monitoring by the power battery management system. The voltage data is obtained through voltage acquisition circuit and A / D conversion circuit, and the temperature data includes the temperature data of the vehicle's power battery, the ambient temperature, and the temperature data of the power battery pack. The current of the vehicle's power battery can be detected using the Hall effect. Detecting the current of the vehicle's power battery using the Hall effect is a technique well-known to those skilled in the art, so it will not be elaborated here. It should be noted that the working principle of the Hall effect is electromagnetic induction. It obtains the voltage value by controlling the changes in the magnetic field and current. Therefore, it is necessary to amplify the voltage signal to improve the accuracy of current measurement.

[0032] With the development of my country's new energy vehicle industry, the quality and safety of electric vehicles have gradually gained attention, and the collision safety of electric vehicles has become even more prominent. After a collision, the high-voltage electrical system and power battery of electric vehicles are prone to short circuits, leakage, and temperature rise, which can lead to fires or even explosions. Therefore, it is necessary to collect abnormal current, abnormal voltage, and abnormal temperature of the vehicle's power battery when it leaks or short-circuits, based on the historical abnormal data of the power battery after a collision, to facilitate subsequent processing.

[0033] Step S2: Use a convolutional neural network model to extract features from the first information and the second information to obtain prediction results. The prediction results include short circuit or leakage of the vehicle power battery.

[0034] Understandably, the current state of the vehicle's power battery can be predicted by analyzing real-time monitoring data of its current, voltage, and temperature, as well as abnormal current, voltage, and temperature during abnormal situations. This prediction can be achieved using a convolutional neural network model. By extracting features from the first and second pieces of information using the convolutional neural network model and comparing the extracted features, the current state of the vehicle's power battery can be determined.

[0035] It is understood that step S2 further includes steps S21, S22, and S23, which are specifically as follows:

[0036] Step S21: Use a convolutional neural network model to extract features from the first information to obtain a first feature vector; use a convolutional neural network model to extract features from the second information to obtain a second feature vector.

[0037] Step S22: Calculate the Euclidean distance between the first feature vector and the second feature vector;

[0038] Step S23: Determine whether the Euclidean distance is greater than a preset distance threshold. If the Euclidean distance is greater than the preset distance threshold, it is determined that there is no abnormality in the current vehicle. If the Euclidean distance is less than the preset distance threshold, the prediction result is obtained.

[0039] It is understood that the first feature vector is the feature information of the real-time monitored vehicle power battery data, and the second feature vector is the feature information when the vehicle power battery leaks or short-circuits after a collision. The smaller the Euclidean distance, the higher the prediction accuracy. When the Euclidean distance between the first feature vector and the second feature vector is less than the preset distance threshold, it can be predicted that the real-time state of the currently monitored power battery is normal, leaking, or short-circuited. It should be noted that calculating the Euclidean distance between the two vectors is a technique well known to those skilled in the art, so it will not be elaborated here.

[0040] Step S3: Determine the protection method corresponding to the power battery after the car is hit by a collision based on the prediction results.

[0041] It is understood that step S3 further includes step S31, which specifically includes:

[0042] Step S31: Determine the corresponding protection method based on the prediction result. If the prediction result indicates that the vehicle's power battery is leaking current, determine the target area based on the image of the vehicle's power battery and send a first control command. The first control command is a command to cut off the power of the vehicle's power battery. If the vehicle's power battery is short-circuited, determine the temperature information of at least one area in the power battery based on the image of the vehicle's power battery and send a second control command based on the temperature information of each area. The second control command is used to control the cooling device to cool the area of ​​the vehicle's power battery to be cooled.

[0043] Understandably, when a vehicle collision causes leakage or short circuit in the vehicle's power battery, appropriate protective measures must be taken to ensure the safety of the vehicle's power battery and thus the personal safety of the driver. When the vehicle's power battery leaks, the power-off protection can effectively ensure the personal safety of the driver. When the vehicle's power battery short-circuits, it is necessary to cool down the vehicle's power battery in a timely manner to prevent the vehicle's power battery from exploding and endangering the personal safety of the driver.

[0044] In this step, when the judgment result indicates that the vehicle's power battery is leaking current, an image acquisition device installed at the vehicle's power battery location acquires an image of the power battery. A target detection algorithm is then used to detect the defect location of the power battery, which is the location where the power battery defect occurred during a collision. A first control command is then sent to implement power-off protection for the vehicle's power battery. It should be noted that the target detection algorithm can be YOLO5, but is not limited to YOLO5. The target detection algorithm can locate the leakage point, facilitating subsequent repairs of the vehicle's power battery. Furthermore, in the electric vehicle's collision power-off protection system, the battery management unit and other vehicle control units only receive the CAN signal emitted by the airbag. Due to vehicle collisions, damage or excessive length of the vehicle's CAN bus during the collision can prevent the battery management system and other vehicle control units from receiving signals from the airbag or cause signal delays. Consequently, the battery management unit and other vehicle control units cannot properly execute the power-off protection strategy, leading to an accident. Therefore, in this application, the first control command signal is transmitted in three forms: CAN signal, wire current signal, and wireless signal. When the battery management unit receives any form of the first control command signal, the vehicle's power-off protection can be realized. The wireless signal effectively solves the problem of the vehicle's CAN bus being damaged during a collision, causing the battery management system to be unable to receive or delay signal reception, thus improving the reliability and stability of the power-off protection during vehicle collisions.

[0045] It is understood that step S31 further includes steps S311, S312, and S313, which are specifically as follows:

[0046] Step S311: Divide the vehicle's power battery image into at least one region to obtain at least one region image;

[0047] Understandably, in this step, the vehicle's power battery can be divided into three equal areas from left to right. Since the vehicle's power battery may deform during a collision, leading to a short circuit, dividing the vehicle's power battery into three equal areas from left to right can achieve the initial location of the short circuit area, so as to achieve precise cooling treatment later. It should be noted that the vehicle's power battery is not limited to being divided into three areas.

[0048] Step S312: Perform grayscale processing on each of the region images to obtain at least one grayscale processed region image;

[0049] It is understandable that grayscale processing of each region of the image is a technique well-known to those skilled in the art, and therefore will not be elaborated upon here.

[0050] Step S313: Obtain the temperature information of each region image based on the gray level corresponding to the red channel of at least one of the grayscale processed region images.

[0051] Understandably, due to the large size of vehicle power batteries, detecting the temperature of the entire vehicle power battery would result in significant errors. Therefore, by dividing the vehicle power battery into multiple regions and detecting the grayscale value corresponding to the red channel of the image for each region, accurate temperature detection of different regions on the vehicle power battery can be achieved, thus obtaining the temperature information of each region's image. It should be noted that the higher the grayscale value corresponding to the red channel, the higher the temperature.

[0052] It is understood that step S31 further includes steps S314, S315, and S316, which are specifically as follows:

[0053] Step S314: Calculate the temperature change of each region based on the temperature information of each region;

[0054] It is understandable that the temperature information for each region includes the temperature information for each moment within that region. The temperature change for each region can be calculated by combining the current temperature data with the temperature data for the next moment after that current moment. Specifically:

[0055]

[0056] In the above formula, T i Let t2 represent the temperature change of the i-th region, t2 and t1 represent the temperature data of the next time after the current time and the temperature data of the current time, respectively, and K represent the unit time, K = K2 - K1, where K2 and K1 represent the next time after the current time and the current time, respectively. It should be noted that the length of the unit time is determined by the frequency of collecting temperature information of each region.

[0057] Step S315: Determine the risk level of the area to be cooled based on the temperature change of each area, and send a second control command based on the risk level of the area to be cooled, wherein the area to be cooled is the area where the temperature change is greater than a preset first threshold.

[0058] It is understood that step S315 further includes steps S3151, S3152, and S3153, which are specifically as follows:

[0059] Step S3151: Determine the temperature change of each area against the preset threshold information to obtain the risk level of each area on the vehicle's power battery.

[0060] It is understood that step S3151 further includes steps S31511 and S31512, which are specifically as follows:

[0061] Step S31511: Obtain the preset first threshold, second threshold, and third threshold;

[0062] Step S31512: Compare the temperature change in each region with the preset first threshold, the second threshold, and the third threshold. If the temperature change in the current detection region is greater than the preset first threshold but less than the preset second threshold, the risk level of the current detection region is determined to be low risk. If the temperature change in the current detection region is greater than the preset second threshold but less than the preset third threshold, the risk level of the current detection region is determined to be medium risk. If the temperature change in the current detection region is greater than the preset third threshold, the risk level of the current detection region is determined to be high risk.

[0063] Understandably, when the temperature change (T1) of the first region of the vehicle's power battery is less than a preset first threshold, the risk level of the first region of the vehicle's power battery is judged to be normal; when the temperature change (T1) of the first region of the vehicle's power battery is greater than the preset first threshold but less than a preset second threshold, the risk level of the first region of the vehicle's power battery is judged to be low risk; when the temperature change (T1) of the first region of the vehicle's power battery is greater than the preset second threshold but less than a preset third threshold, the risk level of the first region of the vehicle's power battery is judged to be medium risk; and when the temperature change (T1) of the first region of the vehicle's power battery is greater than the preset third threshold, the risk level of the first region of the vehicle's power battery is judged to be high risk. It should be noted that the settings of the first, second, and third thresholds are related to the vehicle's driving mode. When the vehicle is set to Sport mode, the settings of the first, second, and third thresholds must be greater than the settings of the first, second, and third thresholds when the vehicle is in Eco mode.

[0064] Step S3152: Determine the opening angle of the valve of each cooling device according to the risk level of each area on the vehicle power battery to obtain control information;

[0065] Understandably, the opening angle of the valve for each cooling device can be determined based on the risk level of each area on the vehicle's power battery. The higher the risk level, the larger the opening angle of the valve for each cooling device, ensuring that more cooling material can cool the vehicle's power battery per unit time. It should be noted that when the vehicle's power battery is at a normal risk level, there is no need to open the valve of the cooling device. When the vehicle's power battery is at a low risk level, the opening angle of the valve is 30°. When the vehicle's power battery is at a medium risk level, the opening angle of the valve is 60°. When the vehicle's power battery is at a high risk level, the valve is fully open at 90°. It should also be noted that the cooling material can be dry ice or liquid nitrogen.

[0066] Step S3153: Send the second control command according to the control information.

[0067] Understandably, the opening angle of the cooling device's valve can be determined based on the control information, thereby sending a second control command to control the cooling device's valve. It should be noted that the second control command signal is also sent in three forms: CAN signal, wire current signal, and wireless signal. When the vehicle control unit receives any form of the second control command signal, it can control the cooling device's valve. Sending the second control command in the form of a wireless signal can effectively improve the stability and reliability of the cooling device's valve control, thereby better ensuring the personal safety of the driver.

[0068] Step S316: In response to the second control command, the opening valve of the cooling device for the corresponding area to be cooled is activated.

[0069] Understandably, according to the second control command, the opening valves of the cooling devices in the corresponding areas to be cooled will activate. Specifically, when the first and second areas of the vehicle's power battery are normal, and the third area is high-risk, the opening valves of the cooling devices near the third area will be fully open. When the first, second, and third areas of the vehicle's power battery are all medium-risk, the opening valves of the two cooling devices near the second and third areas will each open by 60°. The control of the remaining opening valves follows the same principle and will not be elaborated further. By classifying different areas into different risk levels, precise cooling of the vehicle's power battery is achieved, effectively improving the cooling efficiency of the vehicle's power battery, ensuring the personal safety of the driver, and avoiding ineffective cooling of unheated areas, thus saving costs.

[0070] Step S4: Protect the vehicle's power battery according to the protection method described above.

[0071] Understandably, different protective measures are taken based on the different abnormal conditions that the vehicle's power battery produces after a collision. This effectively improves the safety of the vehicle's power battery, reduces the possibility of the power battery exploding or leaking, and thus ensures the safety of the driver and passengers.

[0072] Example 2:

[0073] like Figure 2 As shown, this embodiment provides a battery safety protection system in a car collision. The system includes an acquisition module 901, an extraction module 902, a first processing module 903, and a second processing module 904, specifically:

[0074] The acquisition module 901 is used to acquire first information and second information. The first information is the real-time monitored current, voltage and temperature data of the vehicle's power battery. The second information is the historical abnormal data of the power battery after the vehicle has been involved in a collision. The historical abnormal data includes abnormal current, abnormal voltage and abnormal temperature of the vehicle's power battery.

[0075] Extraction module 902 is used to extract features from first information and second information using a convolutional neural network model to obtain prediction results, the prediction results including short circuit of vehicle power battery or leakage of vehicle power battery;

[0076] The first processing module 903 is used to determine the protection method corresponding to the power battery after the car is hit by a collision based on the prediction result.

[0077] The second processing module 904 is used to provide safety protection for the vehicle's power battery according to the protection method.

[0078] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0079] Example 3:

[0080] Corresponding to the above method embodiments, this embodiment also provides a battery safety protection device in a car collision. The battery safety protection device in a car collision described below and the battery safety protection method in a car collision described above can be referred to each other.

[0081] Figure 3 This is a block diagram illustrating a battery safety protection device 800 in a car collision according to an exemplary embodiment. Figure 3 As shown, the battery safety protection device 800 in a car collision may include: a processor 801 and a memory 802. The battery safety protection device 800 in a car collision may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0082] The processor 801 controls the overall operation of the battery safety protection device 800 in a car collision to complete all or part of the steps in the aforementioned battery safety protection method in a car collision. The memory 802 stores various types of data to support the operation of the battery safety protection device 800 in a car collision. This data may include, for example, instructions for any application or method operating on the battery safety protection device 800 in a car collision, as well as application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as a keyboard, mouse, and buttons. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the battery safety protection device 800 in the vehicle collision and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0083] In an exemplary embodiment, the battery safety protection device 800 in a vehicle collision may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the aforementioned battery safety protection method in a vehicle collision.

[0084] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-described battery safety protection method in a car collision. For example, the computer-readable storage medium may be the memory 802 including program instructions, which may be executed by the processor 801 of the battery safety protection device 800 in a car collision to complete the above-described battery safety protection method in a car collision.

[0085] Example 4:

[0086] Corresponding to the above method embodiments, this embodiment also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the battery safety protection method in a car collision described above.

[0087] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the battery safety protection method in a car collision as described in the above method embodiments.

[0088] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0089] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0090] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for battery safety protection in a car collision, characterized in that, include: The system acquires first information and second information. The first information is real-time monitored data on the current, voltage, and temperature of the vehicle's power battery. The second information is historical abnormal data of the power battery after a collision. The historical abnormal data includes abnormal current, abnormal voltage, and abnormal temperature of the vehicle's power battery. The first and second information are extracted using a convolutional neural network model to obtain prediction results, which include short circuit or leakage of the vehicle power battery. Based on the prediction results, determine the corresponding protection method for the power battery after the vehicle is involved in a collision. The vehicle's power battery is protected according to the aforementioned protection method; The convolutional neural network model is used to extract features from the first and second information to obtain prediction results, including: The first feature vector is obtained by using a convolutional neural network model to extract features from the first information; the second feature vector is obtained by using a convolutional neural network model to extract features from the second information. Calculate the Euclidean distance between the first feature vector and the second feature vector; Determine whether the Euclidean distance is greater than a preset distance threshold. If the Euclidean distance is greater than the preset distance threshold, it is determined that the current vehicle has no abnormal situation; if the Euclidean distance is less than the preset distance threshold, a prediction result is obtained.

2. The battery safety protection method in a car collision according to claim 1, characterized in that, Based on the prediction results, the corresponding protection method for the power battery after a collision is determined, including: Based on the prediction results, a corresponding protection method is determined. If the prediction result indicates that the vehicle's power battery is leaking current, a target area is determined based on the image of the vehicle's power battery, and a first control command is sent. The first control command is a command to cut off the power of the vehicle's power battery. If the vehicle's power battery is short-circuited, the temperature information of at least one area in the power battery is determined based on the image of the vehicle's power battery, and a second control command is sent based on the temperature information of each area. The second control command is used to control the cooling device to cool the area of ​​the vehicle's power battery that needs to be cooled.

3. The battery safety protection method in a car collision according to claim 2, characterized in that, Determining temperature information for at least one region within the vehicle's battery based on images of the battery, including: The vehicle's power battery image is divided into at least one region to obtain at least one region image; Each of the aforementioned region images is converted to grayscale to obtain at least one grayscale-processed region image; Temperature information for each region image is obtained based on the gray level corresponding to the red channel of at least one of the grayscale processed region images.

4. The battery safety protection method in a car collision according to claim 2, characterized in that, A second control command is sent based on the temperature information of each area, including: The temperature change of each region is calculated based on the temperature information of each region. The risk level of the area to be cooled is determined based on the temperature change of each area, and a second control command is sent based on the risk level of the area to be cooled, wherein the area to be cooled is the area where the temperature change is greater than a preset first threshold. In response to the second control command, the opening valve of the cooling device for the corresponding area to be cooled is activated.

5. The battery safety protection method in a car collision according to claim 4, characterized in that, The risk level of the area to be cooled is determined based on the temperature change in each of the areas, and a second control command is sent based on the risk level of the area to be cooled, including: The temperature change in each area is compared with the preset threshold information to determine the risk level of each area on the vehicle's power battery. The opening angle of the valve of each cooling device is determined based on the risk level of each area on the vehicle's power battery to obtain control information; The second control command is sent according to the control information.

6. The battery safety protection method in a car collision according to claim 5, characterized in that, The temperature change in each region is compared with preset threshold information to determine the risk level of each region on the vehicle's power battery, including: Obtain the preset first threshold, second threshold, and third threshold; The temperature change in each region is compared with the preset first threshold, the second threshold, and the third threshold. If the temperature change in the current detection region is greater than the preset first threshold but less than the preset second threshold, the risk level of the current detection region is determined to be low risk. If the temperature change in the current detection region is greater than the preset second threshold but less than the preset third threshold, the risk level of the current detection region is determined to be medium risk. If the temperature change in the current detection region is greater than the preset third threshold, the risk level of the current detection region is determined to be high risk.

7. A battery safety protection system for automobile collisions, characterized in that, include: The acquisition module is used to acquire first information and second information. The first information is the real-time monitored current, voltage and temperature data of the vehicle's power battery. The second information is the historical abnormal data of the power battery after the vehicle has been involved in a collision. The historical abnormal data includes abnormal current, abnormal voltage and abnormal temperature of the vehicle's power battery. The extraction module is used to extract features from the first and second information using a convolutional neural network model to obtain prediction results. The prediction results include whether the vehicle's power battery is short-circuited or leaking, including: The first feature vector is obtained by using a convolutional neural network model to extract features from the first information; the second feature vector is obtained by using a convolutional neural network model to extract features from the second information. Calculate the Euclidean distance between the first feature vector and the second feature vector; Determine whether the Euclidean distance is greater than a preset distance threshold. If the Euclidean distance is greater than the preset distance threshold, it is determined that the current vehicle has no abnormal situation; if the Euclidean distance is less than the preset distance threshold, a prediction result is obtained. The first processing module is used to determine the protection method corresponding to the power battery after the car is hit by a collision based on the prediction results. The second processing module is used to provide safety protection for the vehicle's power battery according to the protection method.

8. A battery safety protection system for automobile collisions, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the battery safety protection method in a car collision as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the battery safety protection method in a car collision as described in any one of claims 1 to 6.

Images