Electric vehicle power battery monitoring method, device, server and medium

Abstract

The present application relates to the field of electric vehicle battery technology, and in particular to a power battery monitoring method, device, server, and medium for electric vehicles, which include: receiving charging data and discharging data collected by a target vehicle in a preset state of charge (SOC) interval; matching a pre-trained battery attenuation model based on the identity of the target vehicle, inputting the charging data and discharging data into the battery attenuation model, and outputting the actual attenuation of the power battery in the target vehicle; if the actual attenuation is less than a preset abnormal threshold, the power battery is determined to be in a preset abnormal state, and an early warning prompt is generated for the power battery of the target vehicle; otherwise, the power battery of the target vehicle is determined to be in a preset normal state. This solves the problems in the related art of users being unable to timely and accurately grasp the battery attenuation status, resulting in extremely low efficiency and a waste of time and cost, reduced user vehicle safety, and reduced user experience.

Description

Technical Field

[0001] The present application relates to the technical field of electric vehicle batteries, and in particular to a method, device, server, and medium for monitoring a power battery of an electric vehicle. Background Art

[0002] With the rapid development of new energy electric vehicles, electric vehicle batteries are not only the core components of electric vehicles, but also the key technical bottleneck restricting the development of electric vehicles. During the use of electric vehicles, the power battery will experience battery degradation as the number of charge and discharge cycles increases, and the battery rated capacity will decrease. At the same time, power battery degradation will lead to incorrect judgment of cruising range. In severe cases, the current and voltage of the entire vehicle may even become unstable, affecting the normal use of the vehicle.

[0003] In related technologies, electric vehicle users cannot understand the battery degradation in real time and can only use the manufacturer's professional equipment for testing, and then decide to replace the battery based on the specific degradation of the battery. This is extremely inefficient and wastes time and cost. It cannot fundamentally avoid traffic accidents caused by battery failure, reduces user safety, and reduces user experience. Summary of the Invention

[0004] The present application provides a method, device, server and medium for monitoring the power battery of an electric vehicle to solve the problems in related technologies such as users being unable to timely and accurately grasp the battery degradation status, extremely low efficiency and wasting time and cost, reducing user vehicle safety and user experience.

[0005] A first aspect of the present application provides a method for monitoring a power battery of an electric vehicle, which is applied to a server and includes the following steps: receiving charging data and discharging data collected from a target vehicle in a preset state of charge (SOC) interval; matching a pre-trained battery attenuation model according to the identity of the target vehicle, inputting the charging data and the discharging data into the battery attenuation model, and outputting the actual attenuation of the power battery in the target vehicle; if the actual attenuation is less than a preset abnormal threshold, determining that the power battery is in a preset abnormal state, and generating an early warning prompt for the power battery of the target vehicle; otherwise, determining that the power battery of the target vehicle is in a preset normal state.

[0006] According to the above technical means, the embodiment of the present application collects relevant data of the target vehicle in the charging and discharging state, matches the attenuation model trained in advance according to the identity identification of the target vehicle, and inputs the data into the battery attenuation model. The actual attenuation of the power battery is calculated in real time through the battery attenuation model. When the actual attenuation value is within the normal threshold, the vehicle power battery is judged to be in a normal state; when the actual attenuation value is less than the abnormal threshold, the battery is judged to be abnormal and an early warning prompt is issued, realizing real-time calculation and monitoring of the attenuation of the electric vehicle power battery in the cloud, so that users can grasp the battery attenuation status in a timely and accurate manner, eliminate safety hazards caused by battery attenuation, reduce detection time and maintenance costs, and improve the safety of customers' electric vehicles.

[0007] Optionally, the charging data includes charging voltage, charging current and charging time, and the discharging data includes discharging voltage, discharging current and discharging time. The charging data and the discharging data are input into the battery attenuation model to output the actual attenuation degree of the power battery in any vehicle, including: calculating the actual charging power based on the charging voltage, the charging current and the charging time; calculating the actual discharging power based on the discharging voltage, the discharging current and the discharging time; calculating the ratio of the actual charging power to the actual discharging power, and calculating the actual attenuation degree of the power battery based on the ratio.

[0008] According to the above technical means, the embodiment of the present application calculates the actual charging power based on the relevant data of charging, and calculates the actual discharge power based on the relevant data of discharging, and then calculates the battery attenuation by the ratio of the time charging power to the actual discharge power. It fully takes into account that the attenuation is calculated by the ratio of the discharge electric work to the charging electric work, which is more in line with the actual situation, making the obtained data more practical and more accurate.

[0009] Optionally, the charging data also includes a battery charging temperature, a first ambient temperature, and a number of charging times; the discharging data also includes a battery discharging temperature, a second ambient temperature, and a number of discharge times; and calculating the actual attenuation of the power battery based on the ratio includes: matching an attenuation correction coefficient based on the battery charging temperature, the first ambient temperature, the number of charging times, the battery discharging temperature, the second ambient temperature, and / or the number of discharge times; and calculating the actual attenuation of the power battery based on the ratio and the attenuation correction coefficient.

[0010] According to the above technical means, the embodiment of the present application calculates the matching attenuation correction coefficient through external factors such as the battery charging temperature, number of charges, ambient temperature, and battery discharge temperature, and calculates the actual attenuation of the power battery based on the ratio of the time charging power to the actual discharge power and the attenuation correction coefficient. It fully considers the impact of external factors on the actual attenuation of the power battery, and makes relevant corrections in the calculation to ensure the accuracy of the calculation.

[0011] Optionally, the battery attenuation model is trained based on the historical charging data and historical discharging data of the target vehicle, including: obtaining the historical charging data and historical discharging data of the target vehicle in a preset SOC range, wherein the historical charging data includes the historical charging voltage, the historical charging current and the historical charging time, and the historical discharging data includes the historical discharge voltage, the historical discharge current and the historical discharge time; calculating one or more historical charging powers based on the historical discharge voltage, the historical discharge current and the historical discharge time; calculating one or more historical discharge powers based on the historical discharge voltage, the historical discharge current and the historical discharge time; calculating the ratio of the historical charging power to the historical discharge power, using the ratio to calculate one or more attenuation degrees of the power battery, and using the one or more attenuation degrees to train a neural network to obtain the battery attenuation model.

[0012] According to the above technical means, the embodiment of the present application obtains the historical charging data and historical discharging data of the target vehicle in the SOC range, and calculates the historical charging and discharging power based on the historical charging and discharging voltage, historical charging and discharging current and historical charging and discharging time in the historical data, calculates the ratio of the historical charging power to the historical discharging power to obtain multiple historical attenuation degrees, and trains the neural network through the attenuation degree to obtain a battery attenuation model, continuously optimizes the battery attenuation model, and finally obtains a battery attenuation degree with higher accuracy.

[0013] Optionally, the historical charging data also includes historical battery charging temperature, historical first ambient temperature and historical charging times, and the historical discharging data also includes historical battery discharging temperature, historical second ambient temperature and historical discharge times. The use of the ratio to calculate one or more attenuation degrees of the power battery includes: calculating an attenuation correction coefficient based on the historical battery charging temperature, the historical first ambient temperature, the historical charging times, the historical battery discharging temperature, the historical second ambient temperature and / or the historical discharge times; and calculating one or more attenuation degrees of the power battery using the attenuation correction coefficient and the ratio.

[0014] According to the above technical means, the embodiment of the present application obtains a historical attenuation correction coefficient based on historical relevant battery charging temperature, ambient temperature, discharge temperature, etc., and obtains multiple attenuation degrees of the power battery based on the historical attenuation correction coefficient and the ratio of historical charging power to historical discharge power. Taking into account the influence of external factors on the actual attenuation degree of the power battery, a more accurate battery attenuation degree is obtained by continuously optimizing the battery attenuation model.

[0015] Optionally, after outputting the actual attenuation degree of the power battery in the target vehicle, the method further includes: optimizing the battery attenuation model using the actual attenuation degree.

[0016] It can be understood that the embodiment of the present application uses the actual attenuation degree to optimize the battery attenuation model, so that the calculation results are more accurate, which helps users to accurately understand the battery attenuation status.

[0017] A second aspect of the present application provides a power battery monitoring device for an electric vehicle, which is applied to a server and includes: a receiving module for receiving charging data and discharging data collected from a target vehicle in a preset state of charge (SOC) interval; a processing module for matching a pre-trained battery attenuation model according to an identity identifier of the target vehicle, inputting the charging data and the discharging data into the battery attenuation model, and outputting the actual attenuation degree of the power battery in the target vehicle; a determination module for determining that the power battery is in a preset abnormal state if the actual attenuation degree is less than a preset abnormal threshold, and generating an early warning prompt for the power battery of the target vehicle; otherwise, determining that the power battery of the target vehicle is in a preset normal state.

[0018] Optionally, the processing module is used to: calculate the actual charging power based on the charging voltage, the charging current and the charging time; calculate the actual discharge power based on the discharge voltage, the discharge current and the discharge time; calculate the ratio of the actual charging power to the actual discharge power, and calculate the actual attenuation degree of the power battery based on the ratio.

[0019] Optionally, the processing module is further used to: match the attenuation correction coefficient according to the battery charging temperature, the first ambient temperature, the number of charging times, the battery discharging temperature, the second ambient temperature and / or the number of discharge times; and calculate the actual attenuation of the power battery according to the ratio and the attenuation correction coefficient.

[0020] Optionally, the processing module is further used to: obtain historical charging data and historical discharging data of the target vehicle in a preset SOC range, wherein the historical charging data includes historical charging voltage, historical charging current and historical charging time, and the historical discharging data includes historical discharge voltage, historical discharge current and historical discharge time; calculate one or more historical charging powers based on the historical charging voltage, the historical charging current and the historical charging time; calculate one or more historical discharge powers based on the historical discharge voltage, the historical discharge current and the historical discharge time; calculate the ratio of the historical charging power to the historical discharge power, use the ratio to calculate one or more attenuation degrees of the power battery, and use the one or more attenuation degrees to train a neural network to obtain the battery attenuation model.

[0021] Optionally, the processing module is further used to: calculate an attenuation correction coefficient based on the historical battery charging temperature, the historical first ambient temperature, the historical charging times, the historical battery discharging temperature, the historical second ambient temperature and / or the historical discharge times; and use the attenuation correction coefficient and the ratio to calculate one or more attenuation degrees of the power battery.

[0022] Optionally, the processing module is further used to: optimize the battery attenuation model using the actual attenuation degree.

[0023] The third aspect of the present application provides a server, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the power battery monitoring method for an electric vehicle as described in the above embodiment.

[0024] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the power battery monitoring method for an electric vehicle as described in the above embodiment.

[0025] Therefore, this application has at least the following beneficial effects:

[0026] (1) The embodiment of the present application collects relevant data of the target vehicle in the charging and discharging state, matches the attenuation model obtained by pre-training according to the identity identification of the target vehicle, and inputs the data into the battery attenuation model. The actual attenuation of the power battery is calculated in real time through the battery attenuation model. When the actual attenuation value is within the normal threshold, the vehicle power battery is determined to be in a normal state; when the actual attenuation is less than the abnormal threshold, the battery is determined to be abnormal and an early warning prompt is issued, thereby realizing real-time calculation and monitoring of the attenuation of the electric vehicle power battery in the cloud, so that users can timely and accurately grasp the battery attenuation status, eliminate safety hazards caused by battery attenuation, reduce detection time and maintenance costs, and improve the safety of customers' electric vehicles.

[0027] (2) The embodiment of the present application calculates the actual charging power based on the relevant data of charging, and calculates the actual discharging power based on the relevant data of discharging, and then calculates the battery attenuation by the ratio of the time charging power to the actual discharging power. It fully considers that the attenuation is calculated by the ratio of the discharge electric work to the charging electric work, which is more in line with the actual situation, making the obtained data more practical and accurate.

[0028] (3) The embodiment of the present application calculates the matching attenuation correction coefficient through external factors such as the battery charging temperature, number of charges, ambient temperature, and battery discharge temperature, and calculates the actual attenuation of the power battery based on the ratio of the time charging power to the actual discharge power and the attenuation correction coefficient. It fully considers the impact of external factors on the actual attenuation of the power battery, and makes relevant corrections in the calculation to ensure the accuracy of the calculation.

[0029] (4) The embodiment of the present application obtains the historical charging data and historical discharging data of the target vehicle in the SOC range, and calculates the historical charging and discharging power based on the historical charging and discharging voltage, historical charging and discharging current and historical charging and discharging time in the historical data, calculates the ratio of the historical charging power to the historical discharging power to obtain multiple historical attenuation degrees, and trains the neural network through the attenuation degree to obtain a battery attenuation model, continuously optimizes the battery attenuation model, and finally obtains a battery attenuation degree with higher accuracy.

[0030] (5) The embodiment of the present application obtains a historical attenuation correction coefficient based on historical relevant battery charging temperature, ambient temperature, discharge temperature, etc., and obtains multiple attenuations of the power battery based on the historical attenuation correction coefficient and the ratio of historical charging power to historical discharge power. Taking into account the influence of external factors on the actual attenuation of the power battery, a more accurate battery attenuation is obtained by continuously optimizing the battery attenuation model.

[0031] (6) The embodiment of the present application utilizes the actual attenuation degree to optimize the battery attenuation model, making the calculation results more accurate and facilitating the user to accurately grasp the battery attenuation status.

[0032] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0034] Figure 1 This is a flow chart of a method for monitoring a power battery of an electric vehicle according to an embodiment of the present application;

[0035] Figure 2 This is an overall flow chart of real-time calculation and monitoring of vehicle battery degradation according to an embodiment of the present application;

[0036] Figure 3 A flowchart of automobile battery degradation modeling according to an embodiment of the present application;

[0037] Figure 4 A flowchart for real-time calculation of vehicle battery attenuation according to an embodiment of the present application;

[0038] Figure 5 An overall technical diagram for modeling and calculating the attenuation of a vehicle battery according to an embodiment of the present application;

[0039] Figure 6 Schematic diagram of a power battery monitoring device for an electric vehicle according to an embodiment of the present application;

[0040] Figure 7 Schematic diagram of the structure of a server according to an embodiment of the present application. DETAILED DESCRIPTION

[0041] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0042] With the rapid development of new energy electric vehicles, electric vehicle batteries are not only the core components of electric vehicles, but also the key technical bottleneck restricting the development of electric vehicles. The power battery will experience battery degradation as the number of charge and discharge cycles increases, and the battery rated capacity will decrease. At the same time, the power battery degradation will lead to incorrect judgment of the cruising range. In severe cases, the current and voltage of the entire vehicle may even be unstable, affecting the normal use of the vehicle and endangering driving safety. The embodiment of the present application establishes real-time calculation and monitoring of electric vehicle power battery degradation, which can help automobile manufacturers and users to timely and accurately grasp the battery degradation status, and provide a basis for manufacturers to provide users with smarter and more efficient battery care and maintenance, eliminate safety hazards caused by battery degradation, and improve customer vehicle safety.

[0043] In the related technology (1), only the ratio of the target battery's charging capacity to the rated battery capacity is considered to calculate the battery attenuation, without considering that the discharge capacity is the actual battery storage capacity. The calculation result has a large deviation, and ignores the influence of ambient temperature, battery temperature, and battery cycle charge and discharge times on battery charging and discharging and battery attenuation. The collected data cannot be used for real-time calculation and monitoring of the corresponding vehicle, which in turn affects the judgment of the battery attenuation of the entire vehicle.

[0044] In the related technology (2), only the charging data collected through the charging condition is considered, and the battery input power is calculated by the formula Q=IT. Since the current of the battery changes during the charging process, the author uses the SVM model to extract the characteristic value to predict the power. The battery health status is determined by predicting the ratio of the input power under the charging condition to the initial capacity of the battery. Similarly, only the power charged under the charging condition is considered, and the discharge power is not considered.

[0045] To this end, the embodiments of the present application propose a power battery monitoring method, device, server and medium for electric vehicles. Among them, the embodiments of the present application calculate the battery attenuation by the ratio of the actual discharge power to the actual charge power, thereby improving the accuracy of monitoring. The following will be described with reference to the accompanying drawings.

[0046] Specifically, Figure 1 A flow chart of a method for monitoring a power battery of an electric vehicle provided in an embodiment of the present application.

[0047] like Figure 1 As shown, the electric vehicle power battery monitoring method includes the following steps:

[0048] In step S101 , charging data and discharging data collected from a target vehicle in a preset state of charge (SOC) interval are received.

[0049] Among them, the preset state of charge can be the ratio of the remaining capacity of a lithium battery after it has been used for a period of time or has been left unused for a long time to its capacity in a fully charged state. It is usually expressed as a percentage, generally expressed in one byte, or two hexadecimal digits, meaning that the remaining power is 0% to 100%. When SOC = 0, it means that the battery is fully discharged, and when SOC = 1, it means that the battery is fully charged. No specific limitation is made here.

[0050] It can be understood that the embodiment of the present application receives charging data and discharging data collected by the target vehicle in the state of charge (SOC) interval to prepare for subsequent matching of the battery attenuation model.

[0051] In step S102, a pre-trained battery attenuation model is matched according to the identity of the target vehicle, the charging data and the discharging data are input into the battery attenuation model, and the actual attenuation degree of the power battery in the target vehicle is output.

[0052] Among them, the battery attenuation model obtained by pre-training can be a battery attenuation model obtained by analysis and modeling through a neural network learning method, and is not specifically limited here.

[0053] It can be understood that the embodiment of the present application collects relevant data of the target vehicle in the charging and discharging state, matches the attenuation model trained in advance according to the identity identification of the target vehicle, and inputs the data into the battery attenuation model. The actual attenuation of the power battery is calculated in real time through the battery attenuation model, so that the user can grasp the battery attenuation status in a timely and accurate manner.

[0054] It should be noted that the charging data includes not only the charging voltage, charging current and charging time, but also the battery charging temperature, the first ambient temperature and the number of charges; the discharging data includes not only the discharge voltage, discharge current and discharge time, but also the battery discharge temperature, the second ambient temperature and the number of discharges; and the actual attenuation of the power battery is calculated using the charging and discharging data, which is not specifically limited here.

[0055] In one embodiment of the present application, the charging data includes the charging voltage, charging current and charging time, and the discharging data includes the discharge voltage, discharge current and discharge time. The charging data and the discharge data are input into the battery attenuation model to output the actual attenuation of the power battery in any vehicle, including: calculating the actual charging power based on the charging voltage, charging current and charging time; calculating the actual discharge power based on the discharge voltage, discharge current and discharge time; calculating the ratio of the actual charging power to the actual discharge power, and calculating the actual attenuation of the power battery based on the ratio.

[0056] It can be understood that the embodiment of the present application calculates the actual charging power based on the relevant data of charging, and calculates the actual discharge power based on the relevant data of discharging, and then calculates the battery attenuation by the ratio of the time charging power to the actual discharge power. It fully takes into account that the attenuation is calculated by the ratio of the discharge electric work to the charging electric work, which is more in line with the actual situation, making the obtained data more practical and more accurate.

[0057] Specifically, the cloud analyzes and models the collected electric vehicle battery charging and discharging data through a neural network learning method, and the attenuation value is α, the attenuation value is The charging formula calculates the charging electric work

[0058]

[0059] In another embodiment of the present application, the charging data also includes the battery charging temperature, the first ambient temperature and the number of charges, and the discharging data also includes the battery discharging temperature, the second ambient temperature and the number of discharges. The actual attenuation of the power battery is calculated according to the ratio, including: matching the attenuation correction coefficient according to the battery charging temperature, the first ambient temperature, the number of charges, the battery discharge temperature, the second ambient temperature and / or the number of discharges; and calculating the actual attenuation of the power battery according to the ratio and the attenuation correction coefficient.

[0060] The first ambient temperature may be the ambient temperature of the vehicle in a charging state, which is not specifically limited here.

[0061] The second ambient temperature may be the ambient temperature when the vehicle is in a driving process or has not been used for a long time, or when the vehicle is in a discharging state, and is not specifically limited here.

[0062] It can be understood that the embodiment of the present application calculates the matching attenuation correction coefficient through external factors such as the battery charging temperature, number of charges, ambient temperature, and battery discharge temperature, and calculates the actual attenuation of the power battery based on the ratio of the time charging power to the actual discharge power and the attenuation correction coefficient. It fully considers the impact of external factors on the actual attenuation of the power battery, and makes relevant corrections in the calculation to ensure the accuracy of the calculation.

[0063] Specifically, considering the possible influencing factors of the battery including ambient temperature, battery temperature, and vehicle charge and discharge times, the output battery attenuation is obtained. Get the vehicle battery attenuation model.

[0064] In an embodiment of the present application, a battery attenuation model is trained based on historical charging data and historical discharging data of a target vehicle, including: obtaining historical charging data and historical discharging data of the target vehicle in a preset SOC range, wherein the historical charging data includes historical charging voltage, historical charging current and historical charging time, and the historical discharging data includes historical discharge voltage, historical discharge current and historical discharge time; calculating one or more historical charging powers based on the historical charging voltage, historical charging current and historical charging time; calculating one or more historical discharge powers based on the historical discharge voltage, historical discharge current and historical discharge time; calculating the ratio of the historical charging power to the historical discharge power, using the ratio to calculate one or more attenuation degrees of the power battery, and using the one or more attenuation degrees to train a neural network to obtain a battery attenuation model.

[0065] It can be understood that the embodiment of the present application obtains the historical charging data and historical discharging data of the target vehicle in the SOC range, and calculates the historical charging and discharging power based on the historical charging and discharging voltage, historical charging and discharging current and historical charging and discharging time in the historical data, calculates the ratio of the historical charging power to the historical discharging power to obtain multiple historical attenuation degrees, and trains the neural network through the attenuation degree to obtain a battery attenuation model, continuously optimizes the battery attenuation model, and finally obtains a battery attenuation degree with higher accuracy.

[0066] Specifically, through real-time data collection of electric vehicles, the collected data is analyzed in real time on the cloud, and the vehicle discharge electric work is calculated in real time on the cloud. By extracting the last charging electric work stored in the cloud, the vehicle discharge electric work and charging electric work in the same power range are input into the established battery attenuation model to obtain the real-time battery attenuation of the vehicle. The calculated real-time battery attenuation is used for real-time calculation and monitoring of the battery attenuation in the cloud.

[0067] In an embodiment of the present application, the historical charging data also includes the historical battery charging temperature, the historical first ambient temperature and the historical charging times, and the historical discharging data also includes the historical battery discharging temperature, the historical second ambient temperature and the historical discharge times. The ratio is used to calculate one or more attenuation degrees of the power battery, including: calculating the attenuation correction coefficient based on the historical battery charging temperature, the historical first ambient temperature, the historical charging times, the historical battery discharge temperature, the historical second ambient temperature and / or the historical discharge times; and calculating one or more attenuation degrees of the power battery using the attenuation correction coefficient and the ratio.

[0068] It can be understood that the embodiment of the present application obtains a historical attenuation correction coefficient based on historical relevant battery charging temperature, ambient temperature, discharge temperature, etc., and obtains multiple attenuation degrees of the power battery based on the historical attenuation correction coefficient and the ratio of historical charging power to historical discharge power. Taking into account the impact of external factors on the actual attenuation degree of the power battery, a more accurate battery attenuation degree is obtained by continuously optimizing the battery attenuation model.

[0069] In an embodiment of the present application, after outputting the actual attenuation degree of the power battery in the target vehicle, the method further includes: optimizing the battery attenuation model using the actual attenuation degree.

[0070] It can be understood that the embodiment of the present application uses the actual attenuation degree to optimize the battery attenuation model, so that the calculation results are more accurate, which helps users to accurately understand the battery attenuation status.

[0071] In step S103, if the actual attenuation degree is less than the preset abnormal threshold, the power battery is determined to be in a preset abnormal state, and a power battery warning prompt is generated for the target vehicle; otherwise, the power battery of the target vehicle is determined to be in a preset normal state.

[0072] The preset abnormality threshold may be an abnormality threshold set in advance by the user. For example, when the battery attenuation α is less than 80%, the battery will be considered to be in an abnormal state. No specific limitation is given here.

[0073] It can be understood that in the embodiment of the present application, when the actual attenuation degree is less than the abnormal threshold, the battery is judged to be abnormal and an early warning prompt is issued, thereby realizing real-time calculation and monitoring of the attenuation of the electric vehicle power battery in the cloud, allowing users to grasp the battery attenuation status in a timely and accurate manner, eliminating safety hazards caused by battery attenuation, reducing detection time and maintenance costs, and improving the safety of customers' electric vehicles.

[0074] According to the power battery monitoring method of electric vehicles proposed in the embodiment of the present application, by collecting relevant data of the target vehicle in the charging and discharging state, matching the attenuation model obtained by pre-training according to the identity identification of the target vehicle, and inputting the data into the battery attenuation model, the actual attenuation of the power battery is calculated in real time by the battery attenuation model. When the actual attenuation value is within the normal threshold, the vehicle power battery is determined to be in a normal state; when the actual attenuation is less than the abnormal threshold, the battery is determined to be abnormal and an early warning prompt is issued, realizing real-time calculation and monitoring of the attenuation of the electric vehicle power battery in the cloud, so that users can grasp the battery attenuation status in a timely and accurate manner, eliminate safety hazards caused by battery attenuation, reduce detection time and maintenance costs, and improve the safety of customers' electric vehicles. Therefore, it solves the problems in the related technology that users cannot grasp the battery attenuation status in a timely and accurate manner, which is extremely inefficient and wastes time and cost, reduces the safety of users' vehicles, and reduces the user experience.

[0075] The following will be combined Figure 2 、 Figure 3 、 Figure 4 and Figure 5 The power battery monitoring method of electric vehicles is described in detail as follows:

[0076] Step 1: The purpose of this invention is to provide a method for real-time calculation and monitoring of electric vehicle power battery attenuation, which requires collecting data type 1: charging data of electric vehicles under static working conditions: V 充电电压 , I 充电电流 、P 充电温度 、T 充电时间 , SOC 1充电初始 , SOC 2充电结束 , charging times, charging battery temperature, charging environment temperature; the second data type to be collected: discharge data of electric vehicles in driving or discharging state: V 放电电压 , I 放电电流 、P 放电温度 、T 放电时间 , SOC 1放电初始 , SOC 2放电结束 , battery discharge temperature, discharge ambient temperature, charging status, discharge status, vehicle VIN (Vehicle Identification Number) code.

[0077] Step 2: Based on the data collected in the first step, the present invention configures the cloud to collect data in real time. The data collection requirements are: when the electric vehicle is in a static charging state, the judgment condition is that when the vehicle speed is 0 and the vehicle charging state is equal to the parking charging state, the charging data is collected in real time through the vehicle 4G: V 充电电压 , I 充电电流 、P 充电温度 、T 充电时间 , SOC 1充电初始 , SOC 2充电结束 , charging times, charging battery temperature, charging environment temperature, charging vehicle VIN code; in addition to collecting data on the vehicle in a stationary state, it is also necessary to collect data on the vehicle in a discharging state. The judgment condition is that when the DC external discharge state is equal to the discharge state, the discharge data of the electric vehicle in the driving or discharging state is recorded: V 放电电压 , I 放电电流 、P 放电温度 、T 放电时间 , SOC 1放电初始 , SOC 2放电结束 , battery discharge temperature, discharge environment temperature, discharge vehicle VIN code;

[0078] Step 3: Based on the charging and discharging data collected from the vehicle, perform real-time data analysis and synchronization in the cloud. Based on the charging data collected through 4G in the previous two steps: V 充电电压 , I 充电电流 、P 充电温度 、T 充电时间 , SOC 1充电初始 , SOC 2充电结束 , charging times, battery temperature, charging environment temperature, vehicle model VIN code; in addition to collecting data on the vehicle in a stationary state, it is also necessary to collect data on the vehicle in a discharging state. The judgment condition is that when the DC external discharge state is equal to the discharge state, the discharge data of the electric vehicle in the driving or discharging state is recorded: V 放电电压 , I 放电电流 、P 放电温度 、T 放电时间 , SOC 1放电初始 , SOC 2放电结束 After the battery discharge temperature, discharge environment temperature, and vehicle VIN code are parsed in the cloud, offline data synchronization is performed to synchronize the electric vehicle charging and discharging data to the offline server, perform neural network training, and establish the corresponding model.

[0079] Among them, Figure 3 As shown in the figure, the automobile battery degradation modeling flow chart: first, use HDFS (Hadoop Distributed File System) to extract and process relevant data from HIVE (data warehouse tool) for batch processing, then use MYSQL (relational database management system) and SPARK (big data analysis engine) to build a neural network, and input the data into online data analysis, stream computing, machine learning and graph computing scenarios to output the battery degradation model.

[0080] Step 4: Based on the massive amount of electric vehicle charging and discharging data collected, the battery attenuation model is obtained using a neural network, and the charging power is calculated according to the charging formula. At the same time, the massive electric vehicle discharge data collected is used to obtain the discharge power Influencing factors include charging and discharging environment temperature, charging and discharging battery temperature, and vehicle charging and discharging times.

[0081] The neural network learns from the input layer to the hidden layer and finally to the output layer to obtain the output battery attenuation By training the neural network with massive data samples, we can obtain battery electric power with higher accuracy under static charging conditions and battery electric power with higher accuracy under discharge conditions. By inputting ambient temperature, battery temperature and vehicle charging times, we can train the neural network and obtain an accurate and better battery attenuation model.

[0082] Step 5: Based on massive data training, the battery attenuation α data is obtained, and then the battery attenuation α model is continuously optimized and trained through the continuous accumulation of massive data from electric vehicles to obtain a battery attenuation α with better accuracy.

[0083] Step 6: If Figure 4 and Figure 5 As shown in the figure, by collecting real-time data of electric vehicles, the vehicle battery attenuation degree is calculated in real time. The static charging data of electric vehicles is uploaded to the cloud platform in real time through the vehicle-side data collection configuration module. The cloud platform adds the battery attenuation model obtained in step 5 to the real-time data of the vehicle: V 充电电压 , I 充电电流 、P 充电温度 、T 充电时间 , SOC 1充电初始 , SOC 2充电结束 , charging times, battery temperature, charging environment temperature, vehicle VIN code; and discharge data of electric vehicles in driving or discharging state: V 放电电压 , I 放电电流 、P 放电温度 、T 放电时间 , SOC 1放电初始 , SOC 2放电结束 , battery discharge temperature and vehicle VIN code are input together in the cloud to Flink for real-time calculation to obtain the real-time battery attenuation.

[0084] Step 7: The vehicle's electric battery attenuation is calculated in real time by Flink and monitored in the cloud. When the battery attenuation α is less than 80%, the battery is considered to be in an abnormal state. Based on this abnormal state, a monitoring warning is issued in the cloud. In normal states, the battery attenuation α value is displayed in real time for data display boards.

[0085] In summary, the embodiment of the present application utilizes real-time cloud data to collect discharge-related data of electric vehicle power batteries, calculates the power battery attenuation in real time through a neural network attenuation model, and uses the neural network model and the collected real-time data to calculate the battery attenuation, thereby realizing real-time battery attenuation calculation and monitoring of electric vehicles.

[0086] Next, the power battery monitoring device for an electric vehicle proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0087] Figure 6 Schematic diagram of a power battery monitoring device for an electric vehicle according to an embodiment of the present application.

[0088] like Figure 6 As shown, the power battery monitoring device 10 of the electric vehicle includes: a receiving module 100 , a processing module 200 and a determination module 300 .

[0089] Among them, the receiving module 100 is used to receive the charging data and discharging data collected by the target vehicle in the preset state of charge (SOC) range; the processing module 200 is used to match the pre-trained battery attenuation model according to the identity of the target vehicle, input the charging data and discharging data into the battery attenuation model, and output the actual attenuation degree of the power battery in the target vehicle; the judgment module 300 is used to determine that the power battery is in a preset abnormal state if the actual attenuation degree is less than a preset abnormal threshold, and generate an early warning prompt for the power battery of the target vehicle; otherwise, it is determined that the power battery of the target vehicle is in a preset normal state.

[0090] In an embodiment of the present application, the processing module 200 is used to: calculate the actual charging power based on the charging voltage, charging current and charging time; calculate the actual discharge power based on the discharge voltage, discharge current and discharge time; calculate the ratio of the actual charging power to the actual discharge power, and calculate the actual attenuation of the power battery based on the ratio.

[0091] In an embodiment of the present application, the processing module 200 is further used to: match the attenuation correction coefficient according to the battery charging temperature, the first ambient temperature, the number of charging times, the battery discharging temperature, the second ambient temperature and / or the number of discharge times; and calculate the actual attenuation of the power battery according to the ratio and the attenuation correction coefficient.

[0092] In an embodiment of the present application, the processing module 200 is further used to: obtain historical charging data and historical discharging data of the target vehicle in a preset SOC range, wherein the historical charging data includes historical charging voltage, historical charging current and historical charging time, and the historical discharging data includes historical discharge voltage, historical discharge current and historical discharge time; calculate one or more historical charging powers based on the historical charging voltage, historical charging current and historical charging time; calculate one or more historical discharge powers based on the historical discharge voltage, historical discharge current and historical discharge time; calculate the ratio of the historical charging power to the historical discharge power, use the ratio to calculate one or more attenuation degrees of the power battery, and use the one or more attenuation degrees to train a neural network to obtain a battery attenuation model.

[0093] In an embodiment of the present application, the processing module 200 is further used to: calculate an attenuation correction coefficient based on the historical battery charging temperature, the historical first ambient temperature, the historical charging times, the historical battery discharging temperature, the historical second ambient temperature and / or the historical discharge times; and calculate one or more attenuation degrees of the power battery using the attenuation correction coefficient and the ratio.

[0094] In the embodiment of the present application, the processing module 200 is further configured to optimize the battery attenuation model using the actual attenuation degree.

[0095] It should be noted that the above explanation of the embodiment of the power battery monitoring method of an electric vehicle is also applicable to the power battery monitoring device of an electric vehicle in this embodiment, and will not be repeated here.

[0096] According to the power battery monitoring device of the electric vehicle proposed in the embodiment of the present application, by collecting relevant data of the target vehicle in the charging and discharging state, matching the attenuation model obtained by pre-training according to the identity identification of the target vehicle, and inputting the data into the battery attenuation model, the actual attenuation of the power battery is calculated in real time by the battery attenuation model. When the actual attenuation value is within the normal threshold, the vehicle power battery is judged to be in a normal state; when the actual attenuation is less than the abnormal threshold, the battery is judged to be abnormal and an early warning prompt is issued, realizing real-time calculation and monitoring of the attenuation of the electric vehicle power battery in the cloud, so that users can grasp the battery attenuation status in a timely and accurate manner, eliminate safety hazards caused by battery attenuation, reduce detection time and maintenance costs, and improve the safety of customers' electric vehicles. Therefore, it solves the problems in the related technology that users cannot grasp the battery attenuation status in a timely and accurate manner, which is extremely inefficient and wastes time and cost, reduces the safety of users' vehicles, and reduces the user experience.

[0097] Figure 7 This is a schematic diagram of the structure of the server provided in the embodiment of the present application. The server may include:

[0098] Memory 701 , processor 702 , and computer programs stored in the memory 701 and executable on the processor 702 .

[0099] When the processor 702 executes the program, the power battery monitoring method for the electric vehicle provided in the above embodiment is implemented.

[0100] Furthermore, the server further includes:

[0101] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0102] The memory 701 is used to store computer programs that can be run on the processor 702 .

[0103] The memory 701 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0104] If the memory 701, processor 702, and communication interface 703 are implemented independently, the communication interface 703, memory 701, and processor 702 can be connected to each other via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0105] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0106] The processor 702 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0107] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for monitoring the power battery of an electric vehicle.

[0108] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0109] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0110] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0111] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0112] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0113] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for monitoring a power battery of an electric vehicle, characterized in that: The method is applied to a server, wherein the method comprises the following steps: Receive charging data and discharging data collected from the target vehicle in a preset state of charge (SOC) interval; matching a pre-trained battery attenuation model according to the identity of the target vehicle, inputting the charging data and the discharging data into the battery attenuation model, and outputting the actual attenuation degree of the power battery in the target vehicle; If the actual attenuation is less than a preset abnormal threshold, the power battery is determined to be in a preset abnormal state, and a power battery warning of the target vehicle is generated; otherwise, the power battery of the target vehicle is determined to be in a preset normal state; The charging data includes charging voltage, charging current and charging time, and the discharging data includes discharging voltage, discharging current and discharging time. Inputting the charging data and the discharging data into the battery attenuation model to output the actual attenuation of the power battery in any vehicle includes: Calculating actual charging power according to the charging voltage, the charging current, and the charging time; Calculating actual discharge power according to the discharge voltage, the discharge current, and the discharge time; calculating a ratio of the actual charging power to the actual discharging power, and calculating an actual attenuation degree of the power battery according to the ratio; The battery degradation model is trained based on the historical charging data and historical discharging data of the target vehicle, and includes: Acquire historical charging data and historical discharging data of the target vehicle in a preset SOC range, wherein the historical charging data includes historical charging voltage, historical charging current, and historical charging time, and the historical discharging data includes historical discharging voltage, historical discharging current, and historical discharging time; Calculate one or more historical charging powers according to the historical charging voltage, the historical charging current, and the historical charging time; Calculate one or more historical discharge powers according to the historical discharge voltage, the historical discharge current, and the historical discharge time; The ratio of the historical charging power to the historical discharging power is calculated, one or more attenuation degrees of the power battery are calculated using the ratio, and a neural network is trained using the one or more attenuation degrees to obtain the battery attenuation model.

2. The method according to claim 1, characterized in that The charging data further includes a battery charging temperature, a first ambient temperature, and a number of charging times; the discharging data further includes a battery discharging temperature, a second ambient temperature, and a number of discharging times; and calculating the actual attenuation degree of the power battery according to the ratio includes: matching an attenuation correction coefficient according to the battery charging temperature, the first ambient temperature, the number of charging times, the battery discharging temperature, the second ambient temperature and / or the number of discharging times; The actual attenuation degree of the power battery is calculated according to the ratio and the attenuation degree correction coefficient.

3. The method according to claim 1, characterized in that The historical charging data further includes historical battery charging temperature, historical first ambient temperature, and historical charging times; the historical discharging data further includes historical battery discharging temperature, historical second ambient temperature, and historical discharging times; and the calculation of one or more attenuation degrees of the power battery using the ratio includes: Calculating an attenuation correction coefficient according to the historical battery charging temperature, the historical first ambient temperature, the historical charging times, the historical battery discharging temperature, the historical second ambient temperature and / or the historical discharging times; One or more attenuation degrees of the power battery are calculated using the attenuation degree correction coefficient and the ratio.

4. The method according to any one of claims 1-2, characterized in that After outputting the actual attenuation degree of the power battery in the target vehicle, the method further includes: The battery degradation model is optimized using the actual degradation degree.

5. A power battery monitoring device for an electric vehicle, characterized in that: The device is applied to a server, wherein the device comprises the following steps: A receiving module is used to receive charging data and discharging data collected by the target vehicle in a preset state of charge (SOC) interval; a processing module, configured to match a pre-trained battery attenuation model according to the identity of the target vehicle, input the charging data and the discharging data into the battery attenuation model, and output an actual attenuation degree of the power battery in the target vehicle; a determination module, configured to determine that the power battery is in a preset abnormal state and generate a warning prompt for the power battery of the target vehicle if the actual attenuation degree is less than a preset abnormal threshold value; otherwise, determine that the power battery of the target vehicle is in a preset normal state; The processing module is used for: Calculate the actual charging power based on the charging voltage, charging current and charging time; Calculate the actual discharge power based on the discharge voltage, discharge current and discharge time; calculating a ratio of the actual charging power to the actual discharging power, and calculating an actual attenuation degree of the power battery according to the ratio; The processing module is further configured to: Acquire historical charging data and historical discharging data of the target vehicle in a preset SOC range, wherein the historical charging data includes historical charging voltage, historical charging current, and historical charging time, and the historical discharging data includes historical discharging voltage, historical discharging current, and historical discharging time; Calculate one or more historical charging powers according to the historical charging voltage, the historical charging current, and the historical charging time; Calculate one or more historical discharge powers according to the historical discharge voltage, the historical discharge current, and the historical discharge time; The ratio of the historical charging power to the historical discharging power is calculated, one or more attenuation degrees of the power battery are calculated using the ratio, and a neural network is trained using the one or more attenuation degrees to obtain the battery attenuation model.

6. The device according to claim 5, characterized in that The processing module is further configured to: matching the attenuation correction coefficient according to the battery charging temperature, the first ambient temperature, the number of charging times, the battery discharging temperature, the second ambient temperature and / or the number of discharging times; The actual attenuation degree of the power battery is calculated according to the ratio and the attenuation degree correction coefficient.

7. The device according to claim 5, characterized in that The processing module is further configured to: Calculate the attenuation correction coefficient based on the historical battery charging temperature, the historical first ambient temperature, the historical charging times, the historical battery discharging temperature, the historical second ambient temperature and / or the historical discharging times; One or more attenuation degrees of the power battery are calculated using the attenuation degree correction coefficient and the ratio.

8. The device according to claim 5, characterized in that The processing module is further configured to: The battery degradation model is optimized using the actual degradation degree.

9. A server, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the power battery monitoring method for an electric vehicle as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the power battery monitoring method of an electric vehicle as described in any one of claims 1 to 4.

Images