Battery pack bottom scraping identification method, device and equipment and storage medium

Abstract

The invention provides a battery pack bottom scraping identification method, device and equipment and a storage medium, and relates to the technical field of electric vehicles. The method comprises the following steps: acquiring driving data and environment data when a target vehicle runs; and according to the driving data and the environment data, identifying whether the battery pack of the target vehicle is scraped. According to the method, the driving data and the environment data are easy to obtain, more comprehensive, accurate and objective description data related to vehicle running and driving conditions can be obtained by combining the driving data and the environment data, the data not only contain the running state of the vehicle, but also integrate the influence of external environment factors on vehicle running, and the driving safety of the vehicle is improved. Therefore, a more comprehensive and multi-dimensional analysis view angle is provided, and the accuracy of battery pack bottom scraping identification is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of electric vehicles, and in particular to a method, device, equipment and storage medium for identifying battery pack bottom scraping. Background Art

[0002] With the continuous advancement of automobile technology, electric vehicles are becoming increasingly important as an environmentally friendly and energy-saving mode of travel. During the driving of electric vehicles, the battery pack structure at the bottom is at risk of being scratched, which may cause damage to the battery pack shell or even the internal structure, affecting the driving safety and service life of the vehicle.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] The purpose of the present disclosure is to provide a method, device, equipment and storage medium for identifying battery pack bottom scratches.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for identifying a battery pack bottom scratch is provided, comprising: acquiring driving data and environmental data of a target vehicle while it is traveling; and identifying whether a battery pack of the target vehicle has a bottom scratch based on the driving data and the environmental data.

[0006] In some embodiments, the battery pack scraping identification method further includes: in response to identifying that the battery pack of the target vehicle has been scraped, acquiring battery parameter data of the target vehicle; and determining the battery pack scraping risk level of the target vehicle based on the battery parameter data.

[0007] In some embodiments, the driving data includes vehicle status information and driving behavior information; and the environmental data includes road information and weather information.

[0008] In some embodiments, the driving data and environmental data of the target vehicle are obtained while it is driving, including: during the driving process of the target vehicle, the driving data and environmental data at multiple moments in a sliding time window are obtained; wherein the sliding time window covers a set time length before the current moment, and is updated at a preset frequency.

[0009] In some embodiments, identifying whether the battery pack of the target vehicle has been scratched based on the driving data and the environmental data includes: arranging the driving data and the environmental data in time series to construct a multi-dimensional time series feature vector of the target vehicle when it is traveling; processing the multi-dimensional time series feature vector through a trained scratch identification model to obtain a battery scratch identification result of the target vehicle; wherein the battery scratch identification result indicates whether the battery pack of the target vehicle has been scratched.

[0010] In some embodiments, the battery pack bottom scratch identification method also includes: obtaining historical driving data and historical environmental data of multiple sample vehicles during historical driving; wherein the multiple sample vehicles include vehicles that have experienced bottom scratches during historical driving and vehicles that have not experienced bottom scratches during historical driving; constructing a sample time series feature vector for each sample vehicle based on the corresponding historical driving data and historical environmental data; determining a training label for each sample vehicle based on the bottom scratch occurrence of each sample vehicle; processing the sample time series feature vector through an initial bottom scratch identification model to obtain a predicted label for each sample vehicle; constructing a loss function based on the predicted label and the corresponding training label, and training the initial bottom scratch identification model through the loss function to obtain a trained bottom scratch identification model.

[0011] In some embodiments, obtaining the battery parameter data of the target vehicle includes: obtaining the battery parameter data corresponding to the driving data in time; wherein the battery parameter data includes at least one of the following: battery temperature, battery voltage, insulation information, and fault code.

[0012] In some embodiments, the battery pack scratch risk level of the target vehicle is determined based on the battery parameter data, including: determining the risk information corresponding to each battery parameter based on the battery parameter data; determining the battery pack risk value of the target vehicle based on preset weights of each battery parameter and the corresponding risk information; and determining the battery pack scratch risk level of the target vehicle based on a risk threshold and the battery pack risk value.

[0013] In some embodiments, determining the battery pack scratch risk level of the target vehicle based on the battery parameter data includes: determining battery characteristics based on the battery parameter data; processing the battery characteristics through a trained battery pack risk rating model to obtain the battery pack scratch risk level of the target vehicle.

[0014] In some embodiments, the battery pack bottom scratch identification method further includes: in response to identifying that the battery pack of the target vehicle is scratched, sending a prompt message to a related terminal of the target vehicle.

[0015] According to a second aspect of an embodiment of the present disclosure, a battery pack bottom-scratching identification device is provided, comprising: an acquisition unit for acquiring driving data and environmental data of a target vehicle while it is traveling; and a bottom-scratching identification unit for identifying whether a battery pack of the target vehicle has been scratched based on the driving data and the environmental data.

[0016] In some embodiments, the battery pack scraping identification device also includes a scraping risk rating unit, wherein the acquisition unit is further used to acquire battery parameter data of the target vehicle in response to identifying that the battery pack of the target vehicle has been scraped; the scraping risk rating unit is used to determine the battery pack scraping risk level of the target vehicle based on the battery parameter data.

[0017] In some embodiments, the driving data includes vehicle status information and driving behavior information; and the environmental data includes road information and weather information.

[0018] In some embodiments, the acquisition unit acquires driving data and environmental data of the target vehicle while it is driving, including: during the driving process of the target vehicle, acquiring driving data and environmental data at multiple moments in a sliding time window; wherein the sliding time window covers a set duration before the current moment, and performs sliding updates at a preset frequency.

[0019] In some embodiments, a bottom-scraping identification unit identifies whether the battery pack of the target vehicle has been scratched based on the driving data and the environmental data, including: arranging the driving data and the environmental data in time series to construct a multi-dimensional time series feature vector of the target vehicle when it is traveling; processing the multi-dimensional time series feature vector through a trained bottom-scraping identification model to obtain a battery bottom-scraping identification result of the target vehicle; wherein the battery bottom-scraping identification result indicates whether the battery pack of the target vehicle has been scratched.

[0020] In some embodiments, the battery pack bottom scraping identification device also includes a bottom scraping identification model training unit, which is used to: obtain historical driving data and historical environmental data of multiple sample vehicles during historical driving; wherein the multiple sample vehicles include vehicles that have bottom scraped during historical driving and vehicles that have not bottom scraped during historical driving; construct a sample time series feature vector for each sample vehicle based on the corresponding historical driving data and historical environmental data; determine a training label for each sample vehicle based on the bottom scraping occurrence of each sample vehicle; process the sample time series feature vector through an initial bottom scraping identification model to obtain a predicted label for each sample vehicle; construct a loss function based on the predicted label and the corresponding training label, and train the initial bottom scraping identification model through the loss function to obtain a trained bottom scraping identification model.

[0021] In some embodiments, the acquisition unit acquires the battery parameter data of the target vehicle, including: acquiring the battery parameter data corresponding to the driving data in time; wherein the battery parameter data includes at least one of the following: battery temperature, battery voltage, insulation information, and fault code.

[0022] In some embodiments, a battery pack scraping risk rating unit determines a battery pack scraping risk level of the target vehicle based on the battery parameter data, including: determining risk information corresponding to each battery parameter based on the battery parameter data; determining a battery pack risk value of the target vehicle based on preset weights of each battery parameter and corresponding risk information; and determining a battery pack scraping risk level of the target vehicle based on a risk threshold and the battery pack risk value.

[0023] In some embodiments, a battery pack scraping risk rating unit determines a battery pack scraping risk level of the target vehicle based on the battery parameter data, including: determining battery characteristics based on the battery parameter data; processing the battery characteristics through a trained battery pack risk rating model to obtain the battery pack scraping risk level of the target vehicle.

[0024] In some embodiments, the battery pack bottom scraping identification device further includes a prompt unit for sending a prompt message to a related terminal of the target vehicle in response to identifying that the battery pack of the target vehicle has been scraped.

[0025] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, characterized in that it includes: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above-mentioned battery pack bottom scraping identification method.

[0026] According to a fourth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided. When instructions in the storage medium are executed by a processor of a mobile terminal, the mobile terminal is enabled to execute a method for identifying battery pack bottom scratches. The method comprises: acquiring driving data and environmental data of a target vehicle while it is traveling; and identifying whether a battery pack of the target vehicle has been scratched based on the driving data and the environmental data.

[0027] According to a fifth aspect of an embodiment of the present disclosure, there is provided a computer program product, comprising a computer program, which implements the above-mentioned method for identifying battery pack bottom scratches when executed by a processor.

[0028] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0029] The present disclosure can predict and identify the battery pack scraping event of the target vehicle based on the driving data and environmental data of the target vehicle at the same time. Among them, the driving data and environmental data can be obtained without adding additional functional modules to the vehicle, and have the characteristics of easy acquisition; and by combining the driving data and environmental data, more comprehensive, accurate and objective description data about the vehicle operation and driving conditions can be obtained. These data not only include the vehicle's own operating status, but also incorporate the impact of external environmental factors on vehicle driving, thereby providing a more comprehensive and multi-dimensional analysis perspective, and improving the accuracy of battery pack scraping identification.

[0030] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0032] Figure 1 It is a flowchart of a method for identifying a battery pack bottom scratch according to some embodiments of the present disclosure.

[0033] Figure 2 It is a flowchart of a method for identifying a battery pack bottom scratch according to some embodiments of the present disclosure.

[0034] Figure 3 It is a flowchart of a method for identifying a battery pack bottom scratch according to some embodiments of the present disclosure.

[0035] Figure 4 It is a flowchart of training a bottom-scratching recognition model in a method for identifying bottom-scratching of a battery pack according to some embodiments of the present disclosure.

[0036] Figure 5 It is a schematic diagram of a scenario in which a vehicle bottom is scraped in a method for identifying battery pack bottom scrapes according to some embodiments of the present disclosure.

[0037] Figure 6 It is a flowchart of a method for identifying a battery pack bottom scratch according to some embodiments of the present disclosure.

[0038] Figure 7 It is a flowchart of a method for identifying a battery pack bottom scratch according to some embodiments of the present disclosure.

[0039] Figure 8 It is a block diagram of a battery pack bottom scratch identification device according to some embodiments of the present disclosure.

[0040] Fig. 9It is a block diagram of a device for identifying battery pack bottom scratches according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0041] Here, some exemplary embodiments of the present disclosure will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. Various changes, modifications and equivalents of the methods, devices and / or systems described herein will become apparent after understanding the present disclosure. For example, the order of operations described herein is merely an example and is not limited to those orders set forth herein, but can be changed as becomes apparent after understanding the present disclosure, except for operations that must be performed in a specific order. In addition, for the purpose of improving clarity and brevity, descriptions of features known in the art may be omitted.

[0042] The following exemplary embodiments are not intended to represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0043] In related technologies, pressure sensors or brittle conductive material layers and electrical sensors can be placed on the bottom surface of the battery pack to collect signal changes to determine whether the battery pack is scratched. However, such methods require changes to the battery design, which is not suitable for vehicles that have already been put on the market, and increases the cost of the entire vehicle.

[0044] In related technologies, visual recognition technology can also be used to obtain information about obstacles in front of the vehicle to be tested, and to determine the type of obstacles, so as to avoid scraping caused by obstacles or to promptly detect the existence of obstacles that cause scraping. However, in this type of method, visual recognition technology has difficulty in identifying certain scenes, such as difficulty in distinguishing between accumulated water and large potholes, difficulty in identifying uneven non-urban roads, etc., and the recognition accuracy is low.

[0045] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0046] Figure 1 is a flowchart of a battery pack bottom scraping identification method according to some embodiments of the present disclosure. Figure 1 As shown, the battery pack bottom scraping identification method may include the following steps.

[0047] In step S110, driving data and environmental data of the target vehicle are obtained.

[0048] In the disclosed embodiment, the target vehicle may be an electric vehicle, an electric two-wheeled vehicle, etc., and the bottom of the target vehicle may have a battery pack structure. During the driving process of the target vehicle, the driving data of the target vehicle and the environmental data around the target vehicle during the process may be extracted in real time.

[0049] Driving data can be used to detect abnormal driving conditions, such as sudden deceleration, acceleration, or bumps, which may be signs of battery pack bottoming and can meet the scenario of battery pack bottoming. Environmental data can be used to detect whether the natural environment or road environment has formed conditions that lead to battery pack bottoming.

[0050] In an exemplary embodiment, the battery pack bottom scratch identification method provided by the present disclosure can be executed by a cloud server; the target vehicle can record driving data in real time and report it to a designated server, and then the cloud server obtains the required driving data from the designated server, or directly reports the driving data to the cloud server; and, the cloud server can obtain environmental data from a related service platform.

[0051] In an exemplary embodiment, the battery pack bottom scratch identification method provided by the present disclosure can also be executed by a functional module arranged on the target vehicle; the target vehicle can synchronize driving data to the functional module in real time; and the functional module can communicate with the relevant service platform to obtain environmental data from the relevant service platform.

[0052] In the following embodiments, a cloud server is taken as an example to illustrate the execution subject of this solution.

[0053] In some embodiments of the present disclosure, the driving data includes vehicle status information and driving behavior information; the environmental data includes road information and weather information.

[0054] In the disclosed embodiments, the vehicle status information can be used to describe the operating status of the target vehicle itself, and may include, for example, vehicle speed, lateral acceleration, longitudinal acceleration, vertical acceleration, steering angle, vehicle power and other signals. For example, a sharp change in vehicle speed and acceleration may indicate that the vehicle is experiencing an uneven road surface or an emergency avoidance situation, which may increase the possibility of the battery pack being scraped, and is consistent with the scenario where the battery pack has been scraped. For another example, when the vehicle is bumped or scratched from the bottom, it will generate a certain amount of resistance and targeting in the longitudinal or vertical direction. Therefore, under the same road, driving behavior and vehicle power output, the objective fact of scraping the bottom can be reflected in the changes in the longitudinal and vertical acceleration of the vehicle.

[0055] Driving behavior information can reflect the driver's driving habits and behaviors, for example, it may include signals such as the accelerator pedal opening, brake pedal opening, steering wheel rotation angle, etc. The driver's driving behavior can indirectly affect the risk of battery pack scraping. For example, sudden acceleration may cause the bottom of the vehicle to come into stronger contact with the ground, and frequent lane changes may increase the chances of the vehicle driving under different road conditions, which may increase the possibility of battery pack scraping and meet the scenario where the battery pack has scraped.

[0056] Road information can be used to describe the road conditions that the vehicle travels through, and may include, for example: road material, road slope, curve radius, whether there are speed bumps, etc.; among them, the road slope can affect the vehicle resistance, and the road material can affect the flatness of the road surface; uneven roads or steep slopes may increase the risk of the battery pack contacting the ground, causing the battery pack to scrape the bottom.

[0057] Weather information may include, for example: rainfall, snowfall, visibility, wind speed, temperature and humidity, etc.; among which, rainfall may affect vehicle resistance, and rainfall may also cause the road surface to be slippery, increasing the risk of vehicle loss of control and bottoming out.

[0058] In an exemplary embodiment, road information may be obtained from a map service platform in combination with GPS or other positioning technologies; weather information may be obtained from a vehicle-mounted meteorological sensor, or may be obtained from a meteorological service platform in combination with GPS or other positioning technologies.

[0059] In the disclosed embodiments, driving data and environmental data are easy to obtain and can be acquired without adding additional functional modules to the vehicle. Therefore, there is no need to change the existing design of the battery and the vehicle. Moreover, by combining driving data and environmental data, more comprehensive, accurate and objective descriptive data about the operation and driving conditions of the vehicle can be obtained. These data not only include the operating status of the vehicle itself, but also incorporate the impact of external environmental factors on vehicle driving, thereby providing a more comprehensive and multi-dimensional analysis perspective, thereby improving the accuracy of identifying battery pack bottom scratches.

[0060] In step S120, it is identified whether the battery pack of the target vehicle is scratched based on the driving data and the environmental data.

[0061] In the disclosed embodiment, the battery pack scraping event can be predicted and identified by combining driving data and environmental data, and by analyzing the vehicle's speed, position, acceleration and other parameters as well as factors such as the road slope and weather conditions, it can be determined whether the vehicle is at a high risk of scraping. It can be identified whether the target vehicle has a battery pack scraping event within the above sliding time window.

[0062] In an exemplary embodiment, algorithms such as machine learning or deep learning may be used to predict and identify battery pack bottom scraping events.

[0063] It can be seen from the above steps that the battery pack bottom scraping identification method provided by the present disclosure can simultaneously predict and identify the battery pack bottom scraping event of the target vehicle based on the driving data and environmental data of the target vehicle. Among them, the driving data and environmental data are easy to obtain and can be obtained without adding additional functional modules to the vehicle, so there is no need to change the existing design of the battery and the vehicle; and by combining the driving data and environmental data, more comprehensive, accurate and objective description data about the vehicle operation and driving conditions can be obtained. These data not only include the vehicle's own operating status, but also incorporate the impact of external environmental factors on vehicle driving, thereby providing a more comprehensive and multi-dimensional analysis perspective, and improving the accuracy of battery pack bottom scraping identification.

[0064] Figure 2 It is a flowchart of a method for identifying a battery pack bottom scratch according to some embodiments of the present disclosure.

[0065] In the disclosed embodiment, Figure 2 Steps S210 and S220 in the battery pack bottom scraping identification method are respectively Figure 1 Steps S110 and S120 in the battery pack bottom scraping identification method shown correspond to each other and will not be repeated here.

[0066] In the embodiment of the present disclosure, Figure 1 Based on the battery pack bottom scraping identification method shown, Figure 2 The battery pack bottom scraping identification method shown may also include the following steps.

[0067] Step S230, in response to identifying that the battery pack of the target vehicle is scratched, obtaining battery parameter data of the target vehicle.

[0068] In the disclosed embodiment, when it is identified that the battery pack of the target vehicle has been scraped, a response mechanism can be triggered to obtain the battery parameter data of the target vehicle. The battery parameter data can be used to further analyze the severity of the battery pack scraping event. The battery parameter data may include recorded data of one or more battery parameters; the battery parameter data may be a series of data recorded at multiple times.

[0069] In some embodiments of the present disclosure, obtaining the battery parameter data of the target vehicle may include: obtaining the battery parameter data corresponding to the driving data in time.

[0070] The battery parameter data includes at least one of the following: battery temperature, battery voltage, insulation information, and fault code.

[0071] In the disclosed embodiment, the acquired battery parameter data may correspond in time to the driving data in which the bottom scraping event is identified in the aforementioned steps, that is, the battery parameter data within the aforementioned sliding time window may be acquired for accurate analysis of the battery status and performance in the time period when the bottom scraping event occurs.

[0072] Among them, battery temperature is an important indicator reflecting the working status and safety of the battery. After the battery pack is scraped, the battery temperature may be abnormal. Too high or too low temperature may have an adverse effect on the performance and life of the battery. For example, too high temperature may cause battery performance to deteriorate and cause safety problems. Battery voltage is a basic parameter to measure the battery's power state. After the battery pack is scraped, abnormal changes in voltage may mean damage to the battery's internal structure or abnormal electrochemical reactions. The insulation performance of the battery pack can be directly related to the safety and reliability of the battery. The acquisition of insulation information helps to assess whether the battery pack has a risk of leakage or short circuit after scraping. Fault codes are codes generated by the battery management system (BMS) when an abnormal situation is detected. These codes can provide important information about the type and location of battery faults, which helps to quickly locate and solve the problem.

[0073] Through the embodiments of the present disclosure, these battery parameter data corresponding to the driving data in time are obtained, which can be used to timely understand whether the battery is in an abnormal working state, timely and comprehensively discover the problems and severity of the battery pack after the battery pack is scraped, and timely determine the risk level of the battery pack after the scraping, providing strong support for subsequent processing measures.

[0074] Step S240: determining the battery pack scratch risk level of the target vehicle according to the battery parameter data.

[0075] In the disclosed embodiment, the risk level of battery pack bottom scraping can be further evaluated based on the battery parameter data to reflect the actual risk status of the battery pack. The battery parameter data can be processed using regression algorithms, Bayesian, divergence algorithms (maximum separation algorithms), neural networks, etc. to obtain the risk level of battery pack bottom scraping.

[0076] In an exemplary embodiment, a statistical method may be used to analyze the battery parameter data, identify abnormal battery parameters, and determine the degree of abnormality of each abnormal battery parameter, thereby deriving the battery pack scratch risk level of the target vehicle.

[0077] In an exemplary embodiment, the divergence algorithm can be used to analyze the battery parameter data, wherein the divergence algorithm can be used to measure the difference or distance between two probability distributions. The distribution of the battery parameter data can be compared with the distribution under normal conditions, and the divergence between them (such as KL divergence) can be calculated to evaluate whether the battery pack is in an abnormal state. If the divergence value is large, it means that the battery parameter data is significantly different from the normal state, so it can be judged that the battery pack has a high risk of bottom scraping.

[0078] In an exemplary embodiment, a neural network model can be used to analyze battery parameter data, and a neural network model can be trained to identify the relationship between battery parameter data and bottom-scraping risk. By inputting a variety of battery parameter data and corresponding labeled bottom-scraping risk levels as training samples, the neural network can learn the mapping relationship from battery parameter data to bottom-scraping risk levels.

[0079] In an exemplary embodiment, it is also possible to consider combining and optimizing multiple algorithms to further improve the accuracy and reliability of risk assessment.

[0080] Through the disclosed embodiments, the battery pack bottom scraping identification method can not only detect the occurrence of bottom scraping events, but also further obtain battery parameter data to determine the risk level and evaluate the potential impact of bottom scraping events on battery pack safety and vehicle performance, thereby gaining a more comprehensive understanding of the safety status of the battery pack after bottom scraping occurs, which helps to improve the safety and reliability of electric vehicles and provide more powerful protection for the safe driving of electric vehicles.

[0081] In some embodiments of the present disclosure, driving data and environmental data of a target vehicle are obtained while it is traveling, including: during the driving process of the target vehicle, driving data and environmental data at multiple moments in a sliding time window are obtained; wherein the sliding time window covers a set duration before the current moment, and is updated at a preset frequency.

[0082] In the disclosed embodiment, the sliding time window may be a preset fixed duration, such as 5 minutes, 7 minutes, 10 minutes, etc.; the preset frequency may be, for example, 1 minute, 2 minutes, etc. In addition, the preset frequency may be set according to the sensitivity requirement of the bottom scraping recognition. For example, if a higher sensitivity is required, the preset frequency may be set higher.

[0083] The target vehicle can continuously collect and record driving data at a preset first collection frequency, and then report it to the cloud server, so that driving data collected at multiple times can be obtained; in an exemplary embodiment, the first collection frequency can reach milliseconds (such as 500 milliseconds, 800 milliseconds), so as to accurately and comprehensively reflect the driving conditions of the vehicle itself. For the part of the environmental data that may change (such as rainfall), the relevant service platform can continuously collect these environmental data that may change at a preset second collection frequency, so that the cloud server can obtain environmental data at multiple times.

[0084] For example, if the fixed duration is set to 10 minutes, the preset frequency is 2 minutes, and the current time is 10 am, then the sliding time window can cover the period from 9:50 to 10:00, that is, the driving data of multiple times collected at the first collection frequency during the period from 9:50 to 10:00, and the environmental data of multiple times collected at the second collection frequency can be obtained, and then used for battery pack bottom scraping identification in subsequent steps. As the vehicle continues to drive, when the current time is updated to 10:02, the sliding time window can be updated to cover the period from 9:52 to 10:02, so as to obtain the driving data and environmental data of multiple times during the period from 9:52 to 10:02, and then used for a new round of battery pack bottom scraping identification.

[0085] In the disclosed embodiment, through a continuously sliding time window, the latest changes in the vehicle's driving status in the recent period and the immediate impact of environmental factors can be continuously captured in real time, thereby achieving continuous, dynamic and comprehensive monitoring of the vehicle and the environment during the vehicle's driving process, with high data accuracy and real-time performance, providing more comprehensive and reliable data support for subsequent battery bottom scratching identification.

[0086] Figure 3 It is a flowchart of a method for identifying a battery pack bottom scratch according to some embodiments of the present disclosure.

[0087] In the present disclosure, Figure 3 Step S310 and Figure 1 This corresponds to step S110 in the battery pack bottom scraping identification method shown, and will not be repeated here.

[0088] In the embodiment of the present disclosure, Figure 1 Based on the battery pack bottom scraping identification method shown, Figure 3 The battery pack bottom scraping identification method shown may also include the following steps.

[0089] Step S320, arranging the driving data and the environmental data in time series to construct a multi-dimensional time series feature vector of the target vehicle when it is driving.

[0090] In the disclosed embodiment, the driving data and the environmental data can be organized in the order of occurrence to construct a multi-dimensional time series feature vector to reflect the actual situation of the vehicle during driving. This multi-dimensional time series feature vector not only contains information in multiple dimensions, but also retains the time relationship between the data points in each dimension to reflect the time series of data changes.

[0091] In an exemplary embodiment, the multi-dimensional time series feature vector may be in the form of a feature parameter matrix.

[0092] Step S330, processing the multi-dimensional time series feature vector through the trained bottom-scratching recognition model to obtain a battery bottom-scratching recognition result of the target vehicle; wherein the battery bottom-scratching recognition result indicates whether the battery pack of the target vehicle is bottom-scratched.

[0093] In the disclosed embodiment, the trained bottom-scraping recognition model can be constructed based on machine learning or deep learning algorithms, and has been trained and optimized using a large amount of historical data. The task of the bottom-scraping recognition model is to analyze the input feature vector and try to identify patterns or features related to battery pack bottom-scraping, thereby determining whether the battery pack of the target vehicle has been scratched. The bottom-scraping recognition model can be a classification model.

[0094] In an exemplary embodiment, an artificial intelligence algorithm such as LSTM (Long Short Term Memory) based on time series multi-features can be used to build a model. As a special recurrent neural network (RNN), the LSTM network has the ability to capture long-term dependencies in sequence data. In this embodiment, LSTM is used to process multi-dimensional feature vectors arranged in time series, so that the changes and effects of features in the time dimension can be considered to reduce underreporting.

[0095] In an exemplary embodiment, the bottom-scraping recognition model can output a battery bottom-scraping recognition result. This result is an indication of whether the battery pack of the target vehicle has been scratched. The battery bottom-scraping recognition result can also indicate in which scenario the battery pack of the target vehicle has or has not been scratched. For example, in some practical applications, when a raised obstacle appears on the road surface, bottom-scraping may or may not occur. Using the driving data and environmental data obtained in such a specific scenario for model training, the bottom-scraping recognition model can learn to recognize whether the bottom is scratched and the scenario experienced by the vehicle, so as to obtain a more accurate battery bottom-scraping recognition result.

[0096] Through the disclosed embodiments, machine learning or deep learning technology can be used to analyze driving data and environmental data to identify whether the battery pack of the target vehicle has been scraped. This method is efficient, accurate and real-time, and helps to improve the safety and reliability of the vehicle.

[0097] Figure 4 FIG. 1 is a flowchart of training a bottom scraping recognition model in a method for identifying the bottom scraping of a battery pack according to some embodiments of the present disclosure. Figure 4 As shown, in some embodiments of the present disclosure, the battery pack bottom scratch identification method also includes training a bottom scratch identification model according to the following steps.

[0098] Step S410, obtaining historical driving data and historical environmental data of multiple sample vehicles during historical driving; wherein the multiple sample vehicles include vehicles that have scraped the bottom during historical driving and vehicles that have not scraped the bottom during historical driving.

[0099] In the disclosed embodiment, the sample vehicles include both vehicles that have experienced bottom-scratching during historical driving and vehicles that have not experienced bottom-scratching. Such data distribution helps the model learn the difference between bottom-scratching and non-bottom-scratching.

[0100] Among them, historical driving data may include historical vehicle status information and historical driving behavior information; historical environmental data may include historical road information and historical weather information.

[0101] In an exemplary embodiment, the historical driving data and historical environmental data may be data within the above-mentioned set time period. For example, assuming the set time period is 10 minutes, for a vehicle that scrapes the bottom during historical driving, data of 5 minutes before and 5 minutes after the scraping time, a total of 10 minutes, may be obtained.

[0102] Step S420, constructing a sample time series feature vector of each sample vehicle according to the corresponding historical driving data and historical environment data.

[0103] In the disclosed embodiment, the sample time series feature vector may include a variety of information such as vehicle speed, acceleration, steering angle, road slope, weather conditions, etc. This information is arranged in chronological order to form a feature vector that can reflect the vehicle's driving status and surrounding environment.

[0104] Step S430, determining the training label of each sample vehicle according to the occurrence of underbody scraping of each sample vehicle.

[0105] In the disclosed embodiment, if the vehicle has a scratch during historical driving, its training label may be "scratched"; if no scratch occurred, the training label may be "not scratched". In an exemplary embodiment, the training labels may be identified using digital codes, for example, the "scratched" label may be "1" and the "not scratched" label may be "0".

[0106] In an exemplary embodiment, the specific scene in which the sample vehicle is located can be further subdivided. For example, the scene in which the vehicle does not scrape the bottom can include: driving on a normal road, passing through potholes, running up / down the curb, a single wheel going down the curb, going up and downhill in a shopping mall parking lot, a partial arch in the middle of the road surface, passing over a speed bump, etc.; the scene in which the vehicle scrapes the bottom can include: passing through road obstacles, potholes, running up / down the curb, a single wheel going down the curb, going up and downhill in a shopping mall parking lot, a partial arch in the middle of the road surface, passing over a speed bump, and sharp foreign objects splashing onto the chassis during normal road driving, causing damage to the battery pack, etc. By using more tags to identify various detailed scenes, the model can learn multi-scene classification and avoid the problem of scene interference.

[0107] Figure 5 It is a schematic diagram of a scenario in which a vehicle bottom is scraped in a method for identifying battery pack bottom scrapes according to some embodiments of the present disclosure.

[0108] like Figure 5 As shown, there are 6 scenarios 501 to 506 that may cause the vehicle to scrape the bottom (here, it is assumed that these 6 scenarios are used as examples for illustration, but the present disclosure is not limited to this). Among them, 501 is a scenario where there are road obstacles; 502 is a scenario where the road is potholed; 503 is a scenario where a single wheel of the vehicle goes off the curb; 504 is a scenario where there are uphill and downhill roads in a parking lot; 505 is a scenario where the middle of the road surface is partially arched; 506 is a scenario where the vehicle passes a speed bump.

[0109] Step S440, processing the sample time series feature vector through the initial bottom-scraping recognition model to obtain a predicted label for each sample vehicle.

[0110] In the disclosed embodiment, the prediction label is the result of the initial underbody scraping recognition model predicting whether the vehicle will have an underbody scraping according to the input sample time series feature vector.

[0111] Step S450, constructing a loss function according to the predicted label and the corresponding training label, training the initial bottom-scraping recognition model through the loss function, and obtaining a trained bottom-scraping recognition model.

[0112] In the disclosed embodiment, a loss function can be constructed based on the prediction label and the corresponding training label. The loss function is used to measure the difference between the model prediction result and the actual result, that is, to measure the accuracy of the model prediction. Then, the initial bottom-scraping recognition model is trained by minimizing the loss function through an optimization algorithm (such as gradient descent) until the model performance reaches a preset standard (such as convergence to a preset state) or the number of training rounds reaches an upper limit, thereby obtaining a trained bottom-scraping recognition model. The trained bottom-scraping recognition model can learn the ability to identify bottom-scraping events from time series feature vectors and can be used in subsequent practical applications.

[0113] Through the disclosed embodiments, factors such as acceleration that affect the vehicle can be fully considered, and strong related signals such as vehicle status signals and driving behavior signals in different historical driving scenarios of the vehicle, as well as related signals such as road and weather information, can be obtained as training data for the model, so that the model can learn various characteristics and laws related to bottom scraping during vehicle driving, fully explore possible potential characteristics, identify various degrees of bottom scraping, and improve the accuracy of identifying battery pack bottom scraping. This recognition method based on machine learning has high flexibility and adaptability, and can continuously improve recognition accuracy as data increases and models are optimized.

[0114] Figure 6 It is a flowchart of a method for identifying a battery pack bottom scratch according to some embodiments of the present disclosure.

[0115] In the disclosed embodiment, Figure 6 Steps S610, S620 and S630 in the battery pack bottom scraping identification method are similar to Figure 2 Steps S210, S220 and S230 in the battery pack bottom scraping identification method shown correspond to each other and will not be repeated here.

[0116] In the embodiment of the present disclosure, Figure 2 Based on the battery pack bottom scraping identification method shown, Figure 6 The battery pack bottom scraping identification method shown may also include the following steps.

[0117] Step S640: determining risk information corresponding to each battery parameter according to the battery parameter data.

[0118] In the embodiment of the present disclosure, the battery parameter data may include at least one of the following: battery temperature, battery voltage, insulation information, fault code. The risk information corresponding to the battery parameter may be risky, no risk, risk trend, etc.

[0119] In the disclosed embodiments, different judgment criteria can be set for different battery parameters. For example, for the battery temperature parameter, a safe temperature range can be pre-set, and the relationship between the acquired battery temperature and the safe temperature range can be judged. If the acquired battery temperature exceeds the safe temperature range, it is determined to be risky; if the acquired battery temperature is stable within the safe temperature range, it is determined to be risk-free; if the acquired battery temperature has an upward trend, or it is predicted that it is about to exceed the safe temperature range, it is determined to have a risk trend. In an exemplary embodiment, risk information can be quantified into numerical values, for example, the numerical values ​​of "risky", "risk trend" and "no risk" can be in a decreasing relationship.

[0120] Step S650, determining the battery pack risk value of the target vehicle according to the preset weights of the various battery parameters and the corresponding risk information.

[0121] In the disclosed embodiment, different battery parameters may have different importance when assessing the risk of a battery pack and may be assigned different weights. The risk information of each battery parameter may be multiplied by its corresponding weight, and then these products may be added together to obtain a comprehensive battery pack risk value to intuitively reflect the actual risk status of the battery pack.

[0122] Step S660: determining the battery pack scratch risk level of the target vehicle according to the risk threshold and the battery pack risk value.

[0123] In the disclosed embodiment, one or more risk thresholds may be set, and these thresholds may be used to classify the battery pack risk value into different risk levels. For example, three levels of low risk, medium risk and high risk may be set, and each level corresponds to a different risk threshold range.

[0124] By comparing the calculated battery pack risk value with these thresholds, the target vehicle battery pack's scratch risk level can be determined, and different treatments can be performed accordingly. For example, if the risk value exceeds the high risk threshold, the system will issue a corresponding alarm or take other preventive measures to ensure the safety of the vehicle.

[0125] Through the embodiments of the present disclosure, a data-driven risk assessment method is provided, which can use battery parameter data and preset weights and thresholds to comprehensively assess the risk level of battery pack bottom scraping, which helps to timely discover and deal with potential safety hazards, provide an important basis for vehicle safety management, and improve the safety and reliability of electric vehicles.

[0126] Figure 7 It is a flowchart of a method for identifying a battery pack bottom scratch according to some embodiments of the present disclosure.

[0127] In the present disclosure, Figure 7Steps S710, S720 and S730 in the battery pack bottom scraping identification method are similar to Figure 2 Steps S210, S220 and S230 in the battery pack bottom scraping identification method shown correspond to each other and will not be repeated here.

[0128] In the embodiment of the present disclosure, Figure 2 Based on the battery pack bottom scraping identification method shown, Figure 7 The battery pack bottom scraping identification method shown may also include the following steps.

[0129] Step S740: determining battery characteristics according to the battery parameter data.

[0130] In the disclosed embodiments, the battery characteristics may be composed of direct measurement values ​​of battery parameters, or may be derived characteristics obtained through calculation or transformation. For example, statistical characteristics such as the maximum value, minimum value, average value, and fluctuation range of the battery temperature may be extracted; the change trend or stability index of the battery voltage and internal resistance may also be calculated.

[0131] In an exemplary embodiment, the battery parameter data acquired at multiple moments can be arranged in time series to construct a battery feature. The battery feature can be a time series feature, which can reflect the characterization and changes of various battery parameters over a period of time, such as the fluctuation range and change trend of the battery temperature, the fluctuation range and change trend of the voltage, the change rate of the insulation resistance, etc.

[0132] Step S750, processing the battery characteristics through the trained battery pack risk rating model to obtain the battery pack scratch risk level of the target vehicle.

[0133] In the disclosed embodiment, a battery pack risk rating model can be pre-trained using a large amount of historical data. This model can be an algorithm based on machine learning (such as decision trees, random forests, support vector machines, neural networks, etc.) or deep learning (such as convolutional neural networks, recurrent neural networks, etc.). During the training process, the battery pack risk rating model can learn the mapping relationship between battery characteristics and the risk level of battery pack bottoming.

[0134] The extracted battery features are used as input and passed to the trained battery pack risk rating model. After internal calculation and reasoning of the model, the risk level of the target vehicle battery pack can be output. The risk level can be a discrete classification label (such as low risk, medium risk, high risk) or a continuous value (indicating the degree of risk).

[0135] Through the disclosed embodiments, machine learning or deep learning techniques can be used to automatically identify and assess the risk level of battery pack bottom scraping. By training the model to learn the complex relationship between battery characteristics and risk level, more accurate and timely risk assessment results can be provided, thereby enhancing the safety and reliability of the vehicle.

[0136] In some embodiments of the present disclosure, the battery pack bottom scraping identification method further includes: in response to identifying that the battery pack of the target vehicle is scraped, sending a prompt message to a related terminal of the target vehicle.

[0137] In the disclosed embodiment, an alarm mechanism may be triggered after a scraping event is detected, and the cloud server may send a prompt message to one or more relevant terminals of the target vehicle. The relevant terminal may be an interface or terminal that is easily accessible and perceived by the driver during driving, such as an on-board display screen on the target vehicle, an audio device on the target vehicle, a driver's smartphone application, etc. The relevant terminal may also be the vehicle management platform of the target vehicle, and the vehicle management platform will then uniformly handle the battery pack scraping event, such as promptly notifying the driver that the battery pack has been scraped, entering the data into a database for vehicle R&D optimization, etc.

[0138] In the disclosed embodiment, the prompt information may include the alarm type, clearly informing the driver that this is an alarm about battery pack bottom scratching, so that the driver can quickly understand and respond, and take necessary measures in time to prevent battery damage or safety accidents. The prompt information may also include the battery pack bottom scratching risk level obtained by analyzing the battery parameter data, so that the driver can understand the urgency of the situation.

[0139] In an exemplary embodiment, the prompt information may also include suggested measures for the driver, such as slowing down and stopping, avoiding aggressive driving, contacting maintenance service, etc.

[0140] In an exemplary embodiment, if it is determined that the risk level of battery pack scraping is higher than the level threshold, the driver may be directly connected to a service hotline or contacted for rescue.

[0141] Through the embodiments of the present disclosure, timely and effective information prompts can be used to help drivers make correct response decisions, thereby ensuring driving safety to the greatest extent, reducing potential economic losses, and enhancing user experience.

[0142] It should be noted that the above figures are only schematic illustrations of the processes included in the methods according to some embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0143] The following are embodiments of the device disclosed herein, which can be used to execute the method embodiments disclosed herein. For details not disclosed in the device embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0144] Figure 8 is a block diagram of a battery pack bottom scraping identification device according to some embodiments of the present disclosure. Figure 8 The device includes: an acquisition unit 801, a bottom-scraping identification unit 802, a bottom-scraping risk rating unit 803, a bottom-scraping identification model training unit 804 and a prompt unit 805.

[0145] The acquisition unit 801 is used to acquire driving data and environmental data of the target vehicle when it is traveling; the bottom scraping identification unit 802 is used to identify whether the battery pack of the target vehicle is bottom scraped according to the driving data and the environmental data.

[0146] In some embodiments of the present disclosure, the acquisition unit 801 is further used to acquire battery parameter data of the target vehicle in response to identifying that the battery pack of the target vehicle has been scratched; the scratch risk rating unit 803 is used to determine the battery pack scratch risk level of the target vehicle based on the battery parameter data.

[0147] In some embodiments of the present disclosure, the driving data includes vehicle status information and driving behavior information; the environmental data includes road information and weather information.

[0148] In some embodiments of the present disclosure, the acquisition unit 801 acquires driving data and environmental data of the target vehicle while it is traveling, including: during the driving process of the target vehicle, acquiring driving data and environmental data at multiple moments in a sliding time window; wherein the sliding time window covers a set duration before the current moment, and performs sliding updates at a preset frequency.

[0149] In some embodiments of the present disclosure, the bottom-scraping identification unit 802 identifies whether the battery pack of the target vehicle has been scratched based on the driving data and the environmental data, including: arranging the driving data and the environmental data in time series to construct a multi-dimensional time series feature vector of the target vehicle when it is traveling; processing the multi-dimensional time series feature vector through a trained bottom-scraping identification model to obtain a battery bottom-scraping identification result of the target vehicle; wherein the battery bottom-scraping identification result indicates whether the battery pack of the target vehicle has been scratched.

[0150] In some embodiments of the present disclosure, the bottom-scraping recognition model training unit 804 is used to: obtain historical driving data and historical environmental data of multiple sample vehicles during historical driving; wherein the multiple sample vehicles include vehicles that have experienced bottom-scratching during historical driving and vehicles that have not experienced bottom-scratching during historical driving; construct a sample time series feature vector for each sample vehicle based on the corresponding historical driving data and historical environmental data; determine a training label for each sample vehicle based on the bottom-scratching occurrence of each sample vehicle; process the sample time series feature vector through an initial bottom-scratching recognition model to obtain a predicted label for each sample vehicle; construct a loss function based on the predicted label and the corresponding training label, and train the initial bottom-scratching recognition model through the loss function to obtain a trained bottom-scratching recognition model.

[0151] In some embodiments of the present disclosure, the acquisition unit 801 acquires the battery parameter data of the target vehicle, including: acquiring the battery parameter data corresponding to the driving data in time; wherein the battery parameter data includes at least one of the following: battery temperature, battery voltage, insulation information, and fault code.

[0152] In some embodiments of the present disclosure, the battery pack scraping risk rating unit 803 determines the battery pack scraping risk level of the target vehicle based on the battery parameter data, including: determining the risk information corresponding to each battery parameter based on the battery parameter data; determining the battery pack risk value of the target vehicle based on the preset weights of each battery parameter and the corresponding risk information; determining the battery pack scraping risk level of the target vehicle based on the risk threshold and the battery pack risk value.

[0153] In some embodiments of the present disclosure, the battery pack scraping risk rating unit 803 determines the battery pack scraping risk level of the target vehicle based on the battery parameter data, including: determining battery characteristics based on the battery parameter data; processing the battery characteristics through a trained battery pack risk rating model to obtain the battery pack scraping risk level of the target vehicle.

[0154] In some embodiments of the present disclosure, the prompt unit 805 is used to: in response to identifying that the battery pack of the target vehicle is scratched, send a prompt message to a related terminal of the target vehicle.

[0155] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0156] Fig. 91 is a block diagram of a device 900 for battery pack bottom scratch identification according to some embodiments of the present disclosure. For example, the device 900 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0157] Reference Fig. 9 , the device 900 may include one or more of the following components: a processing component 902 , a memory 904 , a power component 906 , a multimedia component 908 , an audio component 910 , an input / output (I / O) interface 912 , a sensor component 914 , and a communication component 916 .

[0158] The processing component 902 generally controls the overall operation of the device 900, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 902 may include one or more processors 920 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 902 may include one or more modules to facilitate the interaction between the processing component 902 and other components. For example, the processing component 902 may include a multimedia module to facilitate the interaction between the multimedia component 908 and the processing component 902.

[0159] The memory 904 is configured to store various types of data to support operations on the device 900. Examples of such data include instructions for any application or method operating on the device 900, contact data, phone book data, messages, pictures, videos, etc. The memory 904 can be implemented by 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 memory, flash memory, magnetic disk or optical disk.

[0160] The power component 906 provides power to the various components of the device 900. The power component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 900.

[0161] The multimedia component 908 includes a screen that provides an output interface between the device 900 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 908 includes a front camera and / or a rear camera. When the device 900 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0162] The audio component 910 is configured to output and / or input audio signals. For example, the audio component 910 includes a microphone (MIC), and when the device 900 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 904 or sent via the communication component 916. In some embodiments, the audio component 910 also includes a speaker for outputting audio signals.

[0163] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0164] The sensor assembly 914 includes one or more sensors for providing various aspects of status assessment for the device 900. For example, the sensor assembly 914 can detect the open / closed state of the device 900, the relative positioning of components, such as the display and keypad of the device 900, and the sensor assembly 914 can also detect the position change of the device 900 or a component of the device 900, the presence or absence of user contact with the device 900, the orientation or acceleration / deceleration of the device 900, and the temperature change of the device 900. The sensor assembly 914 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 914 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 914 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0165] The communication component 916 is configured to facilitate wired or wireless communication between the device 900 and other devices. The device 900 can access a wireless network based on a communication standard, such as WiFi, 3G, 4G, 5G, other communication standards, or a combination thereof. In some embodiments of the present disclosure, the communication component 916 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In some embodiments of the present disclosure, the communication component 916 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0166] In some embodiments of the present disclosure, the device 900 can 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 above methods.

[0167] In some embodiments of the present disclosure, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 904 including instructions, and the instructions can be executed by a processor 920 of the device 900 to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0168] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a mobile terminal, enables the mobile terminal to execute a battery pack bottom scratch identification method, the method comprising: obtaining driving data and environmental data of a target vehicle when it is traveling; and identifying whether the battery pack of the target vehicle is bottom scratched based on the driving data and the environmental data.

[0169] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0170] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A battery pack bottom scraping identification method, characterized in that: include: Acquire driving data and environmental data of the target vehicle while it is driving; It is determined whether the battery pack of the target vehicle is scratched based on the driving data and the environmental data.

2. The method according to claim 1, characterized in that The method further comprises: In response to identifying that a battery pack of the target vehicle is scratched, obtaining battery parameter data of the target vehicle; The battery pack scratch risk level of the target vehicle is determined based on the battery parameter data.

3. The method according to claim 1, characterized in that The driving data includes vehicle status information and driving behavior information; the environmental data includes road information and weather information.

4. The method according to claim 1, characterized in that: Obtain driving data and environmental data of the target vehicle, including: During the driving process of the target vehicle, the driving data and the environmental data at multiple moments in the sliding time window are acquired; The sliding time window covers a set time period before the current moment and is updated according to a preset frequency.

5. The method according to claim 1, 3 or 4, characterized in that: Identifying whether a battery pack of the target vehicle is scratched according to the driving data and the environmental data includes: Arranging the driving data and the environmental data in time series to construct a multi-dimensional time series feature vector when the target vehicle is driving; The multi-dimensional time series feature vector is processed by the trained bottom-scratching recognition model to obtain a battery bottom-scratching recognition result of the target vehicle; wherein the battery bottom-scratching recognition result indicates whether the battery pack of the target vehicle is bottom-scratched.

6. The method according to claim 5, characterized in that The method further comprises: Acquire historical driving data and historical environmental data of a plurality of sample vehicles during historical driving; wherein the plurality of sample vehicles include vehicles that scraped the bottom during historical driving and vehicles that did not scrape the bottom during historical driving; Constructing a sample time series feature vector for each sample vehicle according to the corresponding historical driving data and historical environmental data; Determine the training label of each sample vehicle according to the occurrence of underbody scraping of each sample vehicle; Processing the sample time series feature vectors through the initial scraping recognition model to obtain a predicted label for each sample vehicle; A loss function is constructed according to the predicted labels and the corresponding training labels, and the initial bottom-scraping recognition model is trained by the loss function to obtain a trained bottom-scraping recognition model.

7. The method according to claim 2, characterized in that Obtaining battery parameter data of the target vehicle, including: Acquire battery parameter data corresponding to the driving data in time; The battery parameter data includes at least one of the following: battery temperature, battery voltage, insulation information, and fault code.

8. The method according to claim 2 or 7, characterized in that: Determining the battery pack bottom scraping risk level of the target vehicle according to the battery parameter data includes: Determine risk information corresponding to each battery parameter according to the battery parameter data; Determining a battery pack risk value of the target vehicle according to preset weights of various battery parameters and corresponding risk information; The battery pack scraping risk level of the target vehicle is determined according to the risk threshold and the battery pack risk value.

9. The method according to claim 2 or 7, characterized in that: Determining the battery pack bottom scraping risk level of the target vehicle according to the battery parameter data includes: determining battery characteristics according to the battery parameter data; The battery characteristics are processed through the trained battery pack risk rating model to obtain the battery pack scratch risk level of the target vehicle.

10. The method according to claim 1 or 2, characterized in that: The method further comprises: In response to identifying that the battery pack of the target vehicle is scratched, a prompt message is sent to a related terminal of the target vehicle.

11. A battery pack bottom scraping identification device, characterized in that: include: An acquisition unit, used to acquire driving data and environmental data of a target vehicle when it is driving; A bottom scraping identification unit is used to identify whether the battery pack of the target vehicle has a bottom scraping according to the driving data and the environmental data.

12. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the steps of the method according to any one of claims 1 to 10.

13. A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a mobile terminal, enables the mobile terminal to perform a battery pack bottom scratch identification method, the method comprising: Acquire driving data and environmental data of the target vehicle while it is driving; It is determined whether the battery pack of the target vehicle is scratched based on the driving data and the environmental data.

Images