Battery state estimation method and device, electronic equipment and storage medium

Abstract

The invention provides a battery state estimation method, which comprises the steps of acquiring battery charging data and battery charging temperature data of a target charging stage stored in a cloud server, inputting the battery charging data and the battery charging temperature data into a pre-trained analysis model, and obtaining a battery state estimation value of a battery, wherein after a pre-trained analysis model analyzes the battery charging data to obtain a target peak value, the initial peak value, the cut-off peak value and the target peak value of the battery are calculated to obtain a battery state estimated value, and the usable state of the battery is determined according to the battery state estimated value. According to the scheme, the analysis model is trained in advance, the battery charging data and the battery charging temperature data serve as input of the pre-trained analysis model, the battery state estimated value of the battery is obtained, and the method can achieve battery health state evaluation of the vehicle battery in the full working condition period and the full temperature range; and the calculation amount can be reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method, device, electronic device, and storage medium for estimating a battery state. Background Art

[0002] Lithium-ion batteries have been widely used in the field of electric vehicles. The battery management system (BMS) of electric vehicles records battery current, temperature, voltage and other data during vehicle driving, monitors battery status and safety, controls battery operating boundaries based on monitoring results, and extends battery life.

[0003] Currently, by regularly uploading BMS data to the cloud, it is possible to accumulate BMS data over a long period of time. By analyzing this cloud-based BMS data, the battery health status can be determined. However, due to complex operating conditions, low data accuracy, and battery consistency variations in real-world battery data, conventional analysis methods struggle to directly obtain effective information reflecting the battery health status, making it difficult to accurately identify the battery health status. Summary of the Invention

[0004] The present disclosure provides a battery status estimation method and device, electronic device, storage medium and chip to solve the problems in related technologies, learn vehicle battery charging data, and realize battery health status evaluation of the vehicle battery throughout the entire operating cycle and temperature range.

[0005] A first embodiment of the present disclosure provides a method for estimating a battery state, the method comprising:

[0006] Obtain battery charging data and battery charging temperature data of the target charging stage stored in the cloud server;

[0007] Inputting the battery charging data and the battery charging temperature data into a pre-trained analysis model to obtain a battery state estimation value of the battery, wherein the pre-trained analysis model analyzes the battery charging data to obtain a target peak value, and then calculates the battery state estimation value by calculating an initial peak value, a cutoff peak value, and the target peak value of the battery;

[0008] The usable state of the battery is determined according to the estimated battery state value.

[0009] In some embodiments, obtaining the estimated battery state by calculating the initial peak value, the cutoff peak value, and the target peak value of the battery includes:

[0010] Calculating a difference between the target peak value and the cutoff peak value to obtain a first peak difference;

[0011] Calculating the difference between the initial peak value and the cutoff peak value to obtain a second peak value difference;

[0012] The battery state estimation value is obtained according to the ratio of the first peak value difference to the second peak value difference.

[0013] In some embodiments, analyzing the battery charging data using the pre-trained analysis model to obtain a target peak value includes:

[0014] Determining at least one trip point corresponding to each single battery in sequence based on the charging voltage data in the battery charging data, where a battery pack includes multiple single batteries;

[0015] A target peak value of the target charging stage is obtained according to at least one charging capacity value corresponding to each voltage jump point.

[0016] In some embodiments, determining at least one trip point corresponding to each single battery based on the voltage data in the battery charging data includes:

[0017] performing cluster analysis on the battery charging data according to the battery charging temperature data, classifying battery charging data belonging to the same temperature range as one category, and obtaining classified battery charging data;

[0018] At least one trip point corresponding to each single battery is determined in sequence according to the charging voltage data in the classified battery charging data.

[0019] In some embodiments, obtaining the target peak value of the target charging stage according to at least one charging capacity value corresponding to each voltage trip point includes:

[0020] Extracting the charging capacity value corresponding to each voltage jump point in the target charging stage from the classified battery charging data to form a charging capacity data set;

[0021] Calculating the standard deviation of all charging capacity values ​​in the charging capacity data set corresponding to each voltage jump point;

[0022] Draw a curve according to each voltage jump point and the corresponding standard deviation in the target charging stage;

[0023] The peak value of the curve is determined as the target peak value of the target charging stage.

[0024] In some embodiments, the training of the analysis model includes:

[0025] Acquire the training vehicle data from the initial training stage to the final training stage of the battery from the cloud server, and extract the training battery charging data for each charging from the training vehicle data;

[0026] Preprocessing the training battery charging data to obtain at least one training target peak value of the battery from the initial training stage to the end training stage;

[0027] The analysis model is trained based on the at least one training target peak and the preset temperature range to obtain a trained analysis model.

[0028] In some embodiments, preprocessing the training battery charging data to obtain at least one training target peak value present in the full life cycle of the battery includes:

[0029] Classifying the training battery charging data according to different preset temperature ranges to obtain classified training battery charging data;

[0030] Determine the training trip point corresponding to each battery cell in each charge according to the chronological order of the classified training battery charging data within the same preset temperature range;

[0031] Obtaining at least one training charge capacity value corresponding to each training jump point to form a training charge capacity data set;

[0032] Calculating the standard deviation of all training charge capacity values ​​in the training charge capacity data set corresponding to each training jump point;

[0033] Generating a training curve according to each of the training jump points and their corresponding standard deviations;

[0034] Extracting at least one training target peak value in a training curve from an initial training stage to an end training stage of the battery;

[0035] The at least one training target peak value and the number of battery cycles from the initial training stage to the final training stage are trained to obtain a relationship between the training target peak value and the number of battery cycles.

[0036] In some embodiments, the training the analysis model based on the at least one training target peak value and the preset temperature range to obtain a trained analysis model includes:

[0037] Model parameters in the analysis model are trained based on the at least one training target peak value and the preset temperature range to obtain a relationship between the model parameters and temperature, so as to obtain a trained analysis model.

[0038] A second embodiment of the present disclosure provides a device for estimating a battery state, the device comprising:

[0039] an acquisition unit, configured to acquire battery charging data and battery charging temperature data of a target charging stage stored in a cloud server;

[0040] an analysis unit, configured to input the battery charging data and the battery charging temperature data into a pre-trained analysis model to obtain an estimated battery state value of the battery, wherein, after the pre-trained analysis model analyzes the battery charging data to obtain a target peak value, the estimated battery state value is obtained by calculating an initial peak value, a cutoff peak value, and the target peak value of the battery;

[0041] The determining unit determines a usable state of the battery according to the estimated battery state value.

[0042] In some embodiments, the analysis unit is further configured to:

[0043] Calculating a difference between the target peak value and the cutoff peak value to obtain a first peak difference;

[0044] Calculating the difference between the initial peak value and the cutoff peak value to obtain a second peak value difference;

[0045] The battery state estimation value is obtained according to the ratio of the first peak value difference to the second peak value difference.

[0046] In some embodiments, the analysis unit is further configured to:

[0047] Determining at least one trip point corresponding to each single battery in sequence based on the charging voltage data in the battery charging data, where a battery pack includes multiple single batteries;

[0048] A target peak value of the target charging stage is obtained according to at least one charging capacity value corresponding to each voltage jump point.

[0049] In some embodiments, the analysis unit is further configured to:

[0050] performing cluster analysis on the battery charging data according to the battery charging temperature data, classifying battery charging data belonging to the same temperature range as one category, and obtaining classified battery charging data;

[0051] At least one trip point corresponding to each single battery is determined in sequence according to the charging voltage data in the classified battery charging data.

[0052] In some embodiments, obtaining the target peak value of the target charging stage according to at least one charging capacity value corresponding to each voltage trip point includes:

[0053] Extracting the at least one charging capacity value corresponding to each voltage trip point in the target charging stage from the classified battery charging data to form a charging capacity data set;

[0054] Calculating the standard deviation of all charging capacity values ​​in the charging capacity data set corresponding to each voltage jump point;

[0055] Draw a curve according to each voltage jump point and the corresponding standard deviation in the target charging stage;

[0056] The peak value of the curve is determined as the target peak value of the target charging stage.

[0057] In some embodiments, the apparatus includes a training unit;

[0058] The training unit comprises:

[0059] an acquisition module, configured to acquire, from the cloud server, training vehicle data from the initial training stage to the final training stage of the battery, and extract training battery charging data for each charging period from the training vehicle data;

[0060] a processing module, configured to pre-process the training battery charging data to obtain at least one training target peak value of the battery from the initial training stage to the end training stage;

[0061] A training module is used to train the analysis model based on the at least one training target peak and the preset temperature range to obtain a trained analysis model.

[0062] In some embodiments, the processing module is further configured to:

[0063] Classifying the training battery charging data according to different preset temperature ranges to obtain classified training battery charging data;

[0064] Determine the training trip point corresponding to each battery cell in each charge according to the chronological order of the classified training battery charging data within the same preset temperature range;

[0065] Obtaining at least one training charge capacity value corresponding to each training jump point to form a training charge capacity data set;

[0066] Calculating the standard deviation of all training charge capacity values ​​in the training charge capacity data set corresponding to each training jump point;

[0067] Generating a training curve according to each of the training jump points and their corresponding standard deviations;

[0068] Extracting at least one training target peak value in a training curve from an initial training stage to an end training stage of the battery;

[0069] The at least one training target peak value and the number of battery cycles from the initial training stage to the final training stage are trained to obtain a relationship between the training target peak value and the number of battery cycles.

[0070] In some embodiments, the training module is further configured to:

[0071] Model parameters in the analysis model are trained based on the at least one training target peak value and the preset temperature range to obtain a relationship between the model parameters and temperature, so as to obtain a trained analysis model.

[0072] A third aspect of the present disclosure provides a vehicle, comprising:

[0073] processor;

[0074] a memory for storing processor-executable instructions;

[0075] The processor is configured to implement the method described in the embodiment of the first aspect of the present disclosure.

[0076] The fourth aspect embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the method described in the first aspect embodiment of the present disclosure.

[0077] In summary, according to the battery status estimation method proposed in the present disclosure, the method includes obtaining battery charging data and battery charging temperature data of the target charging stage stored in a cloud server, inputting the battery charging data and battery charging temperature data into a pre-trained analysis model to obtain a battery status estimation value of the battery, wherein, after the pre-trained analysis model analyzes the battery charging data to obtain a target peak value, the battery status estimation value is obtained by calculating the initial peak value, the cutoff peak value, and the target peak of the battery, and the usable state of the battery is determined based on the battery status estimation value. The solution of the present disclosure pre-trains the analysis model, and uses the battery charging data and battery charging temperature data as inputs of the pre-trained analysis model to obtain a battery status estimation value of the battery. This method can not only realize the battery health status evaluation of the vehicle battery throughout the entire operating cycle and temperature range, but also reduce the amount of calculation.

[0078] 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 disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0080] Figure 1 A flowchart of a battery status estimation method provided in an embodiment of the present disclosure;

[0081] Figure 2 A schematic diagram of a trip point and a voltage curve provided in an embodiment of the present disclosure;

[0082] Figure 3 A schematic diagram of an average battery voltage provided by an embodiment of the present disclosure;

[0083] Figure 4 A flowchart of a battery status estimation method provided in an embodiment of the present disclosure;

[0084] Figure 5 A schematic diagram of the relationship between voltage and battery capacity provided in an embodiment of the present disclosure;

[0085] Figure 6 A flowchart of a battery status estimation method provided in an embodiment of the present disclosure;

[0086] Figure 7 A flowchart of a battery status estimation method provided in an embodiment of the present disclosure;

[0087] Figure 8 A flowchart of a battery status estimation method provided in an embodiment of the present disclosure;

[0088] Figure 9 A schematic diagram of performing statistical cluster analysis on the temperature at a target peak value P for training provided by an embodiment of the present disclosure;

[0089] Figure 10 A schematic diagram of a battery status estimation effect provided by an embodiment of the present disclosure;

[0090] Figure 11 A schematic structural diagram of a battery status estimation device provided by an embodiment of the present disclosure;

[0091] Figure 12 A schematic structural diagram of a vehicle provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0092] The following describes in detail embodiments of the present disclosure, 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 disclosure, and should not be construed as limiting the present disclosure.

[0093] Lithium-ion batteries have been widely used in the field of electric vehicles. The battery management system (BMS) of electric vehicles records battery current, temperature, voltage and other data during vehicle driving, monitors battery status and safety, controls battery operating boundaries based on monitoring results, and extends battery life.

[0094] Currently, by regularly uploading BMS data to the cloud, it is possible to accumulate BMS data over a long period of time. By analyzing this cloud-based BMS data, the battery health status can be determined. However, due to complex operating conditions, low data accuracy, and battery consistency variations in real-world battery data, conventional analysis methods struggle to directly obtain effective information reflecting the battery health status, making it difficult to accurately identify the battery health status.

[0095] Therefore, in order to solve the problems existing in the related art, the present disclosure proposes a battery status prediction method, which pre-trains the analysis model and uses the battery charging data and battery charging temperature data as the input of the pre-trained analysis model to obtain the battery status estimation value of the battery, and determines the battery's usable status based on the battery status estimation value. This method can not only realize the battery health status evaluation of the vehicle battery throughout the entire operating cycle and temperature range, but also reduce the amount of calculation.

[0096] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0097] In each embodiment of the present disclosure, unless otherwise specified or provided for by logic, the terms and / or descriptions between the embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form a new embodiment based on their inherent logical relationships.

[0098] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0099] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "said", "the", "the", etc., may mean "one and only one", or "one or more", "at least one", etc. For example, when using articles such as "a", "an", "the" in English in translation, the noun following the article may be understood as a singular expression or a plural expression.

[0100] In some embodiments, terms such as "in response to...", "in response to determining...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. can be used interchangeably.

[0101] In some embodiments, terms such as "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not less than", and "above" can be replaced with each other, and terms such as "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", and "below" can be replaced with each other.

[0102] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0103] In the embodiments of the present disclosure, terms such as “import”, “input”, and “read in” can be used interchangeably.

[0104] Figure 1 This is a flow chart of a battery status estimation method provided by an embodiment of the present disclosure. This method can be applied to a vehicle that has the ability to obtain data from a cloud server, or applied to a cloud server, or by a client that has communication with the vehicle, etc., and this disclosure is not limited to such application scenarios. Figure 1 As shown, the battery status estimation method includes steps 101-103.

[0105] Step 101: Obtain battery charging data and battery charging temperature data of a target charging stage stored in a cloud server.

[0106] Vehicle driving data, battery data, temperature data, and other data generated during vehicle operation and battery use are all stored in the cloud server. The battery status estimation method employed in the disclosed embodiments primarily utilizes the battery data and temperature data stored in the cloud server. Battery data includes, but is not limited to, battery charging data, battery discharging data, and battery charging temperature data. Battery charging data includes, but is not limited to, charging voltage data, charging current data, and charging capacitance data. Specifically, the disclosed embodiments do not limit the types of data stored in the cloud server.

[0107] Step 102: Input the battery charging data and the battery charging temperature data into a pre-trained analysis model to obtain an estimated battery state value of the battery. After the pre-trained analysis model analyzes the battery charging data to obtain a target peak value, the estimated battery state value is obtained by calculating the initial peak value, the cutoff peak value, and the target peak of the battery.

[0108] Before executing this step, the disclosed embodiment pre-trains the analysis model. The training data for the analysis model is obtained by learning the battery charging data for each single battery within a preset temperature range from the initial training phase to the end point. The initial training phase includes, but is not limited to, the first charge of the battery after packaging, and the end training phase is the last charge at the time of training the analysis model.

[0109] In the embodiment of the present disclosure, the training battery charging data used by the analysis model includes but is not limited to battery current, charging temperature, battery capacity, etc. in the battery charging data. This type of battery charging data is training data for the entire operating cycle and full temperature range under the actual vehicle operating conditions, and can reflect effective information on the battery health status.

[0110] The initial peak value and the cut-off peak value are preset values, and the battery state estimation value of the battery is calculated and output based on the initial peak value, the cut-off peak value, the battery charging data, and the battery charging temperature data.

[0111] As an implementable manner of the embodiment of the present disclosure, the estimated battery status of the battery may be in the form of a percentage or a numerical value, which is not limited in the specific embodiment of the present disclosure.

[0112] Step 103: Determine the usable state of the battery according to the estimated battery state value.

[0113] When determining the battery's usable state, the system uses a pre-set usable warning threshold to determine the battery's usable state. For example, if the estimated battery state exceeds the warning threshold, the battery is determined to be unusable and a warning message is issued. If the estimated battery state does not exceed the warning threshold, the battery is determined to be usable and the vehicle battery life is predicted.

[0114] As an implementable manner, when the battery status estimate is in percentage form, the alarm threshold is determined to be 80%, or 85%, etc. Specifically, the embodiment of the present disclosure does not limit the specific value of the alarm threshold.

[0115] In summary, according to the battery status estimation method proposed in the present disclosure, the method includes obtaining battery charging data and battery charging temperature data of the target charging stage stored in a cloud server, inputting the battery charging data and battery charging temperature data into a pre-trained analysis model to obtain a battery status estimation value of the battery, wherein, after the pre-trained analysis model analyzes the battery charging data to obtain a target peak value, the battery status estimation value is obtained by calculating the initial peak value, the cutoff peak value, and the target peak of the battery, and the usable state of the battery is determined based on the battery status estimation value. The solution of the present disclosure pre-trains the analysis model, and uses the battery charging data and battery charging temperature data as inputs of the pre-trained analysis model to obtain a battery status estimation value of the battery. This method can not only realize the battery health status evaluation of the vehicle battery throughout the entire operating cycle and temperature range, but also reduce the amount of calculation.

[0116] In order to reduce the computational complexity of the analysis model, after obtaining the peak value and battery cycle number through a machine learning algorithm, as well as obtaining the analysis model of each temperature interval (temperature range) and the model parameters regarding temperature, the battery charging data and battery charging temperature data are used as input through the analysis model, and the corresponding initial peak value and cutoff peak value are output.

[0117] Based on the output initial peak value and cutoff peak value, the battery state estimation value is obtained by calculating the initial peak value, cutoff peak value, and target peak value of the battery in the analysis model. The calculation formula used is as follows:

[0118]

[0119] First, calculate the target peak value P i With the cut-off peak P end (T), obtain the first peak difference, and calculate the initial peak value P int (T) and the cut-off peak P end (T) to obtain a second peak difference, and obtain the battery state estimated value SOH according to the ratio of the first peak difference to the second peak difference.

[0120] The charging voltage data and battery charging temperature data of each single battery (including battery cells) in a vehicle are extracted through the vehicle cloud server. The cloud server obtains the data from the actual vehicle after compression processing. Compared with the actual vehicle data, there will be a large degree of distortion, which cannot directly reflect the actual situation of the battery. It is difficult to directly obtain effective information from the battery charging data and battery charging temperature data.

[0121] In some embodiments of the present disclosure, the target peak value is obtained by analyzing the battery charging data and the battery charging temperature data by the pre-trained analysis model, which can be implemented in but not limited to the following ways, including: determining at least one jump point corresponding to each single cell based on the charging voltage data in the battery charging data, a battery pack contains multiple single cells, and obtaining the target peak value of the target charging stage according to at least one charging capacity value corresponding to each voltage jump point.

[0122] In order to understand the target peak more intuitively, Figure 2 As shown, Figure 2 A schematic diagram of a trip point and a voltage curve provided in an embodiment of the present disclosure. Figure 3 A schematic diagram of an average battery voltage provided by an embodiment of the present disclosure, comprising Figure 2 It can be seen that the battery will reach a maximum value at 4.378V during each charge, and Figure 3 The temperature at the maximum value of STD_V is relatively stable, so the STD_V at 4.378V can be used as the peak P value acquisition target.

[0123] It should be noted that Figure 2 and Figure 3 The exemplary description is only provided for ease of understanding and is not intended to limit the specific values ​​appearing in the figures. The embodiments of the present disclosure do not limit the specific values ​​of the peak values ​​and voltages.

[0124] As a refinement of the above embodiment, when determining at least one trip point corresponding to each single battery in sequence based on the voltage data in the battery charging data, the following method may be used: Figure 4 The method shown is implemented, the method comprising:

[0125] Step 401 : performing cluster analysis on the battery charging data according to the battery charging temperature data, and classifying the battery charging data belonging to the same temperature range as one class to obtain classified battery charging data.

[0126] During specific implementation, the temperature range may be set according to the characteristics of different types of batteries. The embodiment of the present disclosure does not limit the size of the temperature range.

[0127] Step 402 : determining at least one trip point corresponding to each single battery in sequence according to the charging voltage data in the classified battery charging data.

[0128] The battery charging data includes the battery charging voltage data. Since the charging voltage data in the cloud server is compressed, there may be voltage jump points. The voltage jump point can be understood as the change between the current charging voltage data and the next charging voltage data exceeds the preset change range, so a voltage jump occurs.

[0129] In one charging cycle, there are multiple voltage trip points for each single battery.

[0130] In order to understand the voltage jump point more intuitively, such as Figure 5 As shown, Figure 5 A schematic diagram of the relationship between voltage and battery capacity provided in an embodiment of the present disclosure, Figure 5 The charging voltage curve is obtained by plotting the charging voltage data of each battery. The jump point V of the voltage curve is obtained based on the voltage data accuracy, which can be understood as Figure 5 Each line in the graph contains multiple "sawtooth points". It should be noted that Figure 5 This is merely an exemplary description for facilitating understanding of the voltage trip point, and is not a specific limitation on the relevant data.

[0131] The above voltage data accuracy is due to the compression of charging voltage data by the cloud server.

[0132] As a refinement of the above embodiment, when obtaining the target peak value of the target charging stage according to at least one charging capacity value corresponding to each voltage jump point, the following method can be used: Figure 6 The method shown is implemented, the method comprising:

[0133] Step 601 : extracting the at least one charging capacity value corresponding to each voltage jump point in the target charging stage from the classified battery charging data to form a charging capacity data set.

[0134] In the embodiment of the present disclosure, the battery charging data includes the charging capacity value corresponding to each voltage jump point, and the jump point V in the jth charge is extracted. j (i) Each battery’s corresponding charging capacity value C j (i) Forming a charge capacity dataset C j，i .

[0135] Step 602, calculating the standard deviation of all charging capacity values ​​in the charging capacity data set corresponding to each voltage jump point;

[0136] Calculate the charging capacity data set C according to any standard deviation calculation method in the relevant technology j，i Standard deviation STD_C j,i The calculation method of the standard deviation will not be further described in detail in this embodiment of the present disclosure.

[0137] Step 603: Draw a curve according to each voltage jump point in the target charging stage and the corresponding standard deviation.

[0138] For a battery charging cycle, obtain all voltage jump points V of the single battery in the jth charging j Corresponding STD_C j,i , plot the standard deviation curve STD_C j -V j curve.

[0139] Step 604: Determine the peak value of the curve as the target peak value of the target charging stage.

[0140] Calculate STD_C by curve calculation method j -V j The target peak value of the curve is used to estimate the health status of the battery based on the target peak value, thereby achieving vehicle safety inspection. For more information about the target peak value, please refer to Figure 2 .

[0141] The analysis model is used to calculate the estimated battery state of the battery. Before executing the method described in the embodiment of the present disclosure, the analysis model needs to be trained in advance, such as Figure 7 As shown, the method includes:

[0142] Step 701: Acquire training vehicle data from the cloud server from the initial training stage to the final training stage of the battery, and extract training battery charging data for each charging from the training vehicle data;

[0143] Step 702: pre-process the training battery charging data to obtain at least one training target peak value of the battery from the initial training stage to the end training stage;

[0144] The specific implementation method can be adopted but not limited to the following methods, such as Figure 8 Shown, including:

[0145] Step 7021: Classify the training battery charging data according to different preset temperature ranges to obtain classified training battery charging data.

[0146] Step 7022: Determine at least one training trip point corresponding to each single battery in each charging step according to the chronological order of the classified training battery charging data within the same preset temperature range.

[0147] The training battery charging data includes the battery's training charging voltage data. Since the training charging voltage data in the cloud server is compressed, there may be voltage jump points. The voltage jump points can be understood as the change between the current training charging voltage data and the next training charging voltage data, which exceeds the preset change range, so a training voltage jump occurs.

[0148] In one charging cycle, multiple training voltage trip points are included for each single battery.

[0149] Step 7023: Obtain at least one training charging capacity value corresponding to each training jump point to form a training charging capacity data set;

[0150] Step 7024: Calculate the standard deviation of all training charge capacity values ​​in the training charge capacity data set corresponding to each training jump point.

[0151] Step 7025: Generate a training curve based on the training jump points and their corresponding standard deviations.

[0152] Step 7026: Extract at least one training target peak value from the training curve from the initial training stage to the final training stage of the battery.

[0153] It should be noted that in order to distinguish the different names of the training phase and the usage phase, in the training phase, the training battery charging data is used to distinguish from the battery charging data in the usage phase, but their essence is battery charging data. In addition to the training battery charging data, there are also training jump points, training charging capacity values, training charging capacity data sets, training curves, training target peaks, etc.

[0154] Regarding the implementation of steps 7021 to 7026, please refer to the above-mentioned implementation process of inputting battery charging data and battery charging temperature data into the analysis model and obtaining the battery state estimation value. The implementation principle is similar and the details will not be repeated here.

[0155] Step 7027: Training the at least one training target peak value and the number of battery cycles from the initial training stage to the final training stage to obtain a relationship between the training target peak value and the number of battery cycles.

[0156] The temperature at the training target peak P value is statistically clustered and the results are as follows: Figure 9 As shown, Figure 9 Taking the example of dividing temperatures into four groups, a machine learning algorithm is used to learn the relationship between the training target peak value P for each charging group and the number of battery cycles (number of charge and discharge cycles), obtaining a numerical relationship. Since the relationship between P value and cycle number is approximately linear, it can be fitted into a model of the form y = Ax + B.

[0157] Step 703 : Training the analysis model based on the at least one training target peak value and the preset temperature range to obtain a trained analysis model.

[0158] Model parameters in the analysis model are trained based on the at least one training target peak value and the preset temperature range to obtain a relationship between the model parameters and temperature, so as to obtain a trained analysis model.

[0159] According to the example of step 7027, the values ​​of model parameters A and model parameters B obtained by learning under different temperature conditions are shown in Table 1, and the relationship between the values ​​of model parameters A and model parameter B and temperature is obtained through the machine learning algorithm.

[0160] Table 1 Relationship between temperature and model parameters

[0161]

[0162] As an implementation of the embodiment of the present disclosure, the battery state estimation value SOH is estimated by any of the above-mentioned battery state estimation methods, with the battery 1-500 cycle data as training data and the 500-1000 cycle data as test verification data, such as Figure 10 As shown in the figure, a comparison and verification of the fitted trend lines of the estimated SOH based on vehicle testing clearly shows that the results obtained by the two methods are basically consistent. Some errors caused by factors such as charging station stability, missing data, and environmental noise slightly interfere with the calculation results, but do not affect the credibility of the method. This proves that this method can predict the estimated battery state of health (SOH). Due to its low computational complexity and high prediction accuracy, it is suitable for real-time data monitoring and accurate prediction on vehicle cloud platforms.

[0163] Corresponding to the above-mentioned battery status estimation method, the present invention also provides a battery status estimation device. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, any details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment and will not be further described in the present invention. Figure 11 This is a schematic structural diagram of a battery status estimation device 110 provided in an embodiment of the present disclosure, the device comprising:

[0164] An acquiring unit 1101 is configured to acquire battery charging data and battery charging temperature data of a target charging stage stored in a cloud server;

[0165] an analysis unit 1102, configured to input the battery charging data and the battery charging temperature data into a pre-trained analysis model to obtain an estimated battery state value of the battery, wherein the pre-trained analysis model analyzes the battery charging data to obtain a target peak value, and then calculates the estimated battery state value by calculating an initial peak value, a cutoff peak value, and the target peak value of the battery;

[0166] The determining unit 1103 is configured to determine the usable state of the battery according to the estimated battery state.

[0167] In summary, according to the battery status estimation device proposed in the present disclosure, the device includes obtaining battery charging data and battery charging temperature data of the target charging stage stored in a cloud server, inputting the battery charging data and battery charging temperature data into a pre-trained analysis model to obtain a battery status estimation value of the battery, wherein, after the pre-trained analysis model analyzes the battery charging data to obtain a target peak value, the battery status estimation value is obtained by calculating the initial peak value, the cutoff peak value, and the target peak of the battery, and the usable state of the battery is determined according to the battery status estimation value. The solution of the present disclosure pre-trains the analysis model, and uses the battery charging data and battery charging temperature data as inputs of the pre-trained analysis model to obtain a battery status estimation value of the battery. This method can not only realize the battery health status evaluation of the vehicle battery throughout the entire operating cycle and temperature range, but also reduce the amount of calculation.

[0168] Furthermore, in a possible implementation of this embodiment, as Figure 11 As shown, the analysis unit 1102 is further configured to:

[0169] Calculating a difference between the target peak value and the cutoff peak value to obtain a first peak difference;

[0170] Calculating the difference between the initial peak value and the cutoff peak value to obtain a second peak value difference;

[0171] The battery state estimation value is obtained according to the ratio of the first peak value difference to the second peak value difference.

[0172] Furthermore, in a possible implementation of this embodiment, as Figure 11 As shown, the analysis unit 1102 is further configured to:

[0173] Determining at least one trip point corresponding to each single battery in sequence based on the charging voltage data in the battery charging data, where a battery pack includes multiple single batteries;

[0174] A target peak value of the target charging stage is obtained according to at least one charging capacity value corresponding to each voltage jump point.

[0175] Furthermore, in a possible implementation of this embodiment, as Figure 11 As shown, the analysis unit 1102 is further configured to:

[0176] performing cluster analysis on the battery charging data according to the battery charging temperature data, classifying battery charging data belonging to the same temperature range as one category, and obtaining classified battery charging data;

[0177] At least one trip point corresponding to each single battery is determined in sequence according to the charging voltage data in the classified battery charging data.

[0178] Furthermore, in a possible implementation of this embodiment, as Figure 11 As shown, the analysis unit 1102 is further configured to:

[0179] Extracting the charging capacity value corresponding to each voltage jump point in the target charging stage from the classified battery charging data to form a charging capacity data set;

[0180] Calculating the standard deviation of all charging capacity values ​​in the charging capacity data set corresponding to each voltage jump point;

[0181] Draw a curve according to each voltage jump point and the corresponding standard deviation in the target charging stage;

[0182] The peak value of the curve is determined as the target peak value of the target charging stage.

[0183] Furthermore, in a possible implementation of this embodiment, as Figure 11 As shown, the device includes a training unit;

[0184] The training unit 1104 includes:

[0185] An acquisition module 11041 is configured to acquire, from the cloud server, training vehicle data from the initial training phase to the final training phase of the battery, and extract training battery charging data for each charging phase from the training vehicle data;

[0186] The processing module 11042 is configured to pre-process the training battery charging data to obtain at least one training target peak value of the battery from the initial training stage to the end training stage;

[0187] The training module 11043 is configured to train the analysis model based on the at least one training target peak value and the preset temperature range to obtain a trained analysis model.

[0188] Furthermore, in a possible implementation of this embodiment, as Figure 11 As shown, the processing module 11042 is further configured to:

[0189] Classifying the training battery charging data according to different preset temperature ranges to obtain classified training battery charging data;

[0190] Determine the training trip point corresponding to each battery cell in each charge according to the chronological order of the classified training battery charging data within the same preset temperature range;

[0191] Obtaining at least one training charge capacity value corresponding to each training jump point to form a training charge capacity data set;

[0192] Calculating the standard deviation of all training charge capacity values ​​in the training charge capacity data set corresponding to each training jump point;

[0193] Generating a training curve according to each of the training jump points and their corresponding standard deviations;

[0194] Extracting at least one training target peak value in a training curve from an initial training stage to an end training stage of the battery;

[0195] The at least one training target peak value and the number of battery cycles from the initial training stage to the final training stage are trained to obtain a relationship between the training target peak value and the number of battery cycles.

[0196] Furthermore, in a possible implementation of this embodiment, as Figure 11 As shown, the training module 11043 is further used to:

[0197] Model parameters in the analysis model are trained based on the at least one training target peak value and the preset temperature range to obtain a relationship between the model parameters and temperature, so as to obtain a trained analysis model.

[0198] The embodiments provided above in this disclosure describe the methods and devices provided in these embodiments. To implement the various functions in the methods provided in these embodiments, electronic devices may include hardware structures and software modules, and implement these functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Certain of these functions may be implemented in the form of hardware structures, software modules, or a combination of hardware structures and software modules.

[0199] Figure 12 1 is a block diagram illustrating a vehicle 1200 according to an exemplary embodiment. For example, vehicle 1200 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or another type of vehicle. Vehicle 1200 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0200] Reference Figure 12 Vehicle 1200 may include various subsystems, such as an infotainment system 1210, a perception system 1220, a decision-making and control system 1230, a drive system 1240, and a computing platform 1250. Vehicle 1200 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of vehicle 1200 may be interconnected via wired or wireless means.

[0201] In some embodiments, the infotainment system 1210 may include a communication system, an entertainment system, a navigation system, and the like.

[0202] The perception system 1220 may include several sensors for sensing information about the environment surrounding the vehicle 1200. For example, the perception system 1220 may include a global positioning system (which may be a GPS system, a BeiDou system, or other positioning systems), an inertial measurement unit (IMU), a laser radar, a millimeter-wave radar, an ultrasonic radar, and a camera.

[0203] The decision control system 1230 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0204] Drive system 1240 may include components that provide power to vehicle 1200. In one embodiment, drive system 1240 may include an engine, a power source, a transmission system, and wheels. The engine may be an internal combustion engine, an electric motor, an air compression engine, or a combination thereof. The engine is capable of converting energy provided by the power source into mechanical energy.

[0205] Some or all functions of the vehicle 1200 are controlled by a computing platform 1250. The computing platform 1250 may include at least one processor 1251 and a memory 1252. The processor 1251 may execute instructions 1253 stored in the memory 1252.

[0206] The processor 1251 can be any conventional processor, such as a commercially available CPU. The processor can also include a graphics processor (GPU), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), or a combination thereof.

[0207] Memory 1252 can be implemented by any type of volatile or non-volatile memory 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.

[0208] In addition to instructions 1253 , memory 1252 may also store data, such as road maps, route information, and vehicle location, direction, speed, etc. The data stored in memory 1252 may be used by computing platform 1250 .

[0209] In the embodiment of the present disclosure, the processor 1251 may execute the instruction 1253 to complete all or part of the steps of the above-mentioned battery status estimation method.

[0210] Those skilled in the art will also appreciate that the various illustrative logical blocks and steps listed in the embodiments of the present disclosure may be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement functionality for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of the present disclosure.

[0211] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure as detailed in the appended claims.

[0212] Throughout this specification, references to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" indicate that a specific feature, structure, material, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative uses of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0213] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention 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 the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0214] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection having one or more wires (control method), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing it in a suitable manner if necessary, and then storing it in a computer memory.

[0215] It should be understood that various parts of the embodiments of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple 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 to implement: 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 (PGA), a field programmable gate array (FPGA), etc.

[0216] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above-mentioned 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.

[0217] Furthermore, the functional units in the various embodiments of the present invention may be integrated into a single processing module, each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in either hardware or software functional modules. If the integrated modules are implemented as software functional modules and sold or used as standalone products, they may also be stored in a computer-readable storage medium. The aforementioned storage medium may be a read-only memory, a magnetic disk, or an optical disk, etc.

[0218] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for estimating a battery state, characterized in that: The method comprises: Obtain battery charging data and battery charging temperature data of the target charging stage stored in the cloud server; Inputting the battery charging data and the battery charging temperature data into a pre-trained analysis model to obtain a battery state estimation value of the battery, wherein the pre-trained analysis model analyzes the battery charging data to obtain a target peak value, and then calculates the battery state estimation value by calculating an initial peak value, a cutoff peak value, and the target peak value of the battery; The usable state of the battery is determined according to the estimated battery state value.

2. The method according to claim 1, characterized in that The step of obtaining the estimated battery state value by calculating the initial peak value, the cutoff peak value, and the target peak value of the battery includes: Calculating a difference between the target peak value and the cutoff peak value to obtain a first peak difference; Calculating the difference between the initial peak value and the cutoff peak value to obtain a second peak value difference; The battery state estimation value is obtained according to the ratio of the first peak value difference to the second peak value difference.

3. The method according to claim 1, characterized in that The analyzing the battery charging data using the pre-trained analysis model to obtain a target peak value includes: Determining at least one trip point corresponding to each single battery in sequence based on the charging voltage data in the battery charging data, where a battery pack includes multiple single batteries; A target peak value of the target charging stage is obtained according to at least one charging capacity value corresponding to each voltage jump point.

4. The method according to claim 3, characterized in that Determining at least one trip point corresponding to each single battery in sequence based on the voltage data in the battery charging data includes: performing cluster analysis on the battery charging data according to the battery charging temperature data, classifying battery charging data belonging to the same temperature range as one category, and obtaining classified battery charging data; At least one trip point corresponding to each single battery is determined in sequence according to the charging voltage data in the classified battery charging data.

5. The method according to claim 3, characterized in that Obtaining the target peak value of the target charging stage according to at least one charging capacity value corresponding to each voltage trip point includes: Extracting the at least one charging capacity value corresponding to each voltage trip point in the target charging stage from the classified battery charging data to form a charging capacity data set; Calculating the standard deviation of all charging capacity values ​​in the charging capacity data set corresponding to each voltage jump point; Draw a curve according to each voltage jump point and the corresponding standard deviation in the target charging stage; The peak value of the curve is determined as the target peak value of the target charging stage.

6. The method according to any one of claims 1 to 5, characterized in that The training of the analysis model includes: Acquire the training vehicle data from the initial training stage to the final training stage of the battery from the cloud server, and extract the training battery charging data for each charging from the training vehicle data; Preprocessing the training battery charging data to obtain at least one training target peak value of the battery from the initial training stage to the end training stage; The analysis model is trained based on the at least one training target peak and the preset temperature range to obtain a trained analysis model.

7. The method according to claim 6, characterized in that The preprocessing of the training battery charging data to obtain at least one training target peak value existing in the full life cycle of the battery includes: Classifying the training battery charging data according to different preset temperature ranges to obtain classified training battery charging data; Determine at least one training trip point corresponding to each single battery in each charge according to the chronological order of the classified training battery charging data within the same preset temperature range; Obtaining at least one training charge capacity value corresponding to each training jump point to form a training charge capacity data set; Calculating the standard deviation of all training charge capacity values ​​in the training charge capacity data set corresponding to each training jump point; Generating a training curve according to each of the training jump points and their corresponding standard deviations; Extracting at least one training target peak value in a training curve from an initial training stage to an end training stage of the battery; The at least one training target peak value and the number of battery cycles from the initial training stage to the final training stage are trained to obtain a relationship between the training target peak value and the number of battery cycles.

8. The method according to claim 6, characterized in that The training of the analysis model based on the at least one training target peak value and the preset temperature range to obtain a trained analysis model includes: Model parameters in the analysis model are trained based on the at least one training target peak value and the preset temperature range to obtain a relationship between the model parameters and temperature, so as to obtain a trained analysis model.

9. A battery status estimation device, characterized in that: The device comprises: an acquisition unit, configured to acquire battery charging data and battery charging temperature data of a target charging stage stored in a cloud server; an analysis unit, configured to input the battery charging data and the battery charging temperature data into a pre-trained analysis model to obtain an estimated battery state value of the battery, wherein, after the pre-trained analysis model analyzes the battery charging data to obtain a target peak value, the estimated battery state value is obtained by calculating an initial peak value, a cutoff peak value, and the target peak value of the battery; A determining unit is configured to determine a usable state of the battery according to the estimated battery state.

10. A vehicle, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the method according to any one of claims 1 to 7.

11. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

Images