Charging curve generation method, device and equipment

Abstract

The charging curve generation method comprises the steps that a current standing voltage and a charging plan corresponding to a target battery are obtained, and the current standing voltage is the voltage of the target battery at the last moment before the current charging process; the charging plan is used for reflecting current and temperature of the target battery at different moments in the charging process; according to the current standing voltage, the charging plan, a first preset mapping relation and a second preset mapping relation, predicting voltages of the target battery at different moments in a plurality of charging processes; the plurality of charging processes comprise the current charging process and a charging process after the current charging process; and generating a full-life charging curve of the target battery according to the voltages of the target battery at different moments in the plurality of charging processes.

Description

Technical Field

[0001] The present application relates to the field of battery management technology, and in particular to a charging curve generation method, device and equipment. Background Art

[0002] With the severe energy shortage and environmental protection problems, higher requirements are placed on batteries. The new generation of lithium-ion batteries are widely used in various fields, such as new energy vehicles and electronic products, due to their characteristics of less pollution and energy diversification.

[0003] Lithium-ion batteries will age with use. When the aging of lithium-ion batteries is serious, it may cause safety hazards. Effective lithium-ion battery evaluation technology helps the battery management system to perceive the battery status in real time, thereby determining the aging degree of lithium-ion batteries, and promptly reminding and eliminating safety hazards. Early detection of problems helps to intervene and manage lithium-ion batteries early. In the early use stage of lithium-ion batteries, predicting the long-term battery status of lithium-ion batteries in the future has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present application provides a charging curve generation method, device and equipment, aiming to predict the future long-term battery state of a lithium-ion battery.

[0005] In a first aspect, a charging curve generating method is provided, comprising:

[0006] Obtaining a current resting voltage and a charging plan corresponding to a target battery, wherein the current resting voltage is the voltage of the target battery at the last moment before the current charging process, and the charging plan is used to reflect the current and temperature of the target battery at different moments during the charging process;

[0007] The voltage of the target battery at different moments in multiple charging processes is predicted according to the current static voltage, the charging plan, the first preset mapping relationship and the second preset mapping relationship; the first preset mapping relationship represents the mapping relationship between the first current, the first temperature and the first voltage and the second voltage, the first current is the current at a first moment, the first moment is any moment in the charging process, the first temperature is the temperature at the first moment, the first voltage is the voltage at the previous moment of the first moment, and the second voltage is the voltage at the first moment; the second preset mapping relationship represents the mapping relationship between the first static voltage, the second current and the second temperature and the second static voltage, the first static voltage is the voltage at the last moment before the first charging process, the first charging process is any charging process, the second current is the current at the first moment in the first charging process, the second temperature is the temperature at the first moment in the first charging process, the second static voltage is the voltage at the last moment before the second charging process, and the second charging process is the next charging process of the first charging process; the multiple charging processes include the current charging process and the charging process after the current charging process;

[0008] A full-life charging curve of the target battery is generated according to the voltage of the target battery at different moments in the multiple charging processes.

[0009] In this technical solution, after obtaining the current static voltage corresponding to the target battery and the charging plan reflecting the current and temperature of the battery at different times during the charging process, the voltage of the target battery at different times during multiple charging processes is predicted according to the current static voltage, the charging plan, the first preset mapping relationship and the second preset mapping relationship. Then, according to the voltage of the target battery at different times during the multiple charging processes, a full-life charging curve of the target battery is generated. Since the multiple charging processes include the current charging process and the charging process after the current charging process, the charging process after the current charging process is a future charging process, which realizes the generation of the long-term charging curve of the battery in the future. Since the charging curve reflects the battery status, the prediction of the long-term battery status in the future is realized, which is helpful to detect the abnormal status of the battery early. Since the first preset mapping relationship represents the mapping relationship between the first current, the first temperature and the first voltage and the second voltage, the first current is the current at any time during the charging process, the first temperature is the temperature at any time, and the first voltage is the temperature at any time. The first static voltage is the voltage at the last moment, the second voltage is the voltage at any moment, the second preset mapping relationship represents the mapping relationship between the first static voltage, the second current and the second temperature, and the second static voltage, the first static voltage is the voltage at the last moment before the first charging process, and the second current is the current at the first moment in the first charging process, which is equivalent to predicting the voltage at the next moment in the two adjacent moments according to the voltage at the last moment in the two adjacent moments, and the current and temperature at the next moment in the two adjacent moments, and predicting the static voltage of the next charging process in the two adjacent charging processes according to the static voltage corresponding to the last charging process in the two adjacent charging processes and the current and temperature at the first moment of the next charging process in the two adjacent charging processes. Therefore, it is only necessary to predict the voltage at each moment in multiple charging processes based on the static voltage at the last moment before the charging process and the current and temperature at each moment included in the charging plan, and use less data to predict the battery state of the battery in the long term in the future, which is simple and convenient.

[0010] In combination with the first aspect, in a possible implementation, predicting the voltage of the target battery at different times in multiple charging processes according to the current static voltage, the charging plan, the first preset mapping relationship, and the second preset mapping relationship includes: taking the current static voltage as the target static voltage, and taking the current charging process as the target charging process; predicting the voltage of the target battery at different times in the target charging process according to the first preset mapping relationship, the target static voltage, and the charging plan, and obtaining the current and temperature of the target battery at the first moment in the charging process from the charging plan to obtain a first target current and a first target temperature; determining, according to the second preset mapping relationship, the voltage corresponding to the target battery at different times in the target charging process; and obtaining, according to the second preset mapping relationship, the voltage corresponding to the target battery at different times in the target charging process. The target static voltage, the first target current and the voltage corresponding to the first target temperature are obtained to obtain a next static voltage corresponding to the target static voltage, wherein the next static voltage is the voltage at the last moment before the next charging process of the target charging process; taking the next static voltage as the target static voltage, and taking the next charging process of the target charging process as the target charging process, executing the steps of predicting the voltage of the target battery at different moments in the target charging process according to the first preset mapping relationship, the target static voltage and the charging plan, and obtaining the current and temperature of the target battery at the first moment in the charging process from the charging plan to obtain the first target current and the first target temperature.

[0011] According to the first preset mapping relationship, the voltage at the next moment between two adjacent moments is predicted, and according to the second preset mapping relationship, the static voltage before the next charging process between two adjacent charging processes is predicted, and the charging process is continuously iterated to realize the prediction of the voltage at each moment in multiple charging processes.

[0012] In combination with the first aspect, in a possible implementation, predicting the voltage of the target battery at different moments in the target charging process according to the first preset mapping relationship, the target resting voltage and the charging plan includes: taking the target resting voltage as the target known voltage, and taking the first moment in the current charging process as the target moment; obtaining the current and temperature of the target battery at the target moment from the charging plan, and obtaining a second target current and a second target temperature; determining the voltage corresponding to the target known voltage, the second target current and the second target temperature according to the first preset mapping relationship, and obtaining the voltage at the target moment; taking the voltage at the target moment as the target known voltage, and taking the moment next to the target moment as the target moment, and executing the step of obtaining the current and temperature of the target battery at the target moment from the charging plan, and obtaining the second target current and the second target temperature.

[0013] According to the first preset mapping relationship, the voltage at the next moment between two adjacent moments is predicted, and the time is continuously iterated to achieve the prediction of the voltage at each moment in the charging process.

[0014] In combination with the first aspect, in a possible implementation method, determining the voltage corresponding to the target known voltage, the second target current and the second target temperature according to the first preset mapping relationship to obtain the voltage at the target moment includes: inputting the target known voltage, the second target current and the second target temperature into a first preset model to obtain the voltage at the target moment, the first preset model being obtained through pre-training, and the first preset model being used to reflect the first preset mapping relationship.

[0015] The pre-trained model is used to predict the voltage at the next moment between two adjacent moments in the charging process to ensure the accuracy of voltage prediction.

[0016] In combination with the first aspect, in a possible implementation method, determining the voltage corresponding to the target quiescent voltage, the first target current and the first target temperature according to the second preset mapping relationship, and obtaining the next quiescent voltage corresponding to the target quiescent voltage, includes: inputting the target quiescent voltage, the first target current and the first target temperature into a second preset model to obtain the next quiescent voltage corresponding to the target quiescent voltage, the second preset model being obtained through pre-training, and the second preset model being used to reflect the second preset mapping relationship.

[0017] The pre-trained model is used to predict the static voltage before the next charging process in two adjacent charging processes to ensure the accuracy of the static voltage prediction.

[0018] In combination with the first aspect, before taking the next quiescent voltage as the target quiescent voltage, the method further includes: correcting the next quiescent voltage according to a third preset mapping relationship, wherein the third preset mapping relationship represents a mapping relationship between a quiescent voltage predicted based on the second preset mapping relationship and an actual quiescent voltage.

[0019] The static voltage corresponding to the charging process is corrected according to the third preset mapping relationship to improve the accuracy of static voltage prediction.

[0020] In combination with the first aspect, in a possible implementation method, before generating the full-life charging curve of the target battery according to the voltage of the target battery at different times in the multiple charging processes, it also includes: correcting the voltage of the target battery at different times in the multiple charging processes according to a fourth preset mapping relationship, and the fourth preset mapping relationship represents the mapping relationship between the charging curve predicted based on the first preset mapping relationship and the actual charging curve.

[0021] After the voltages of the target battery at different times during the multiple charging processes are predicted, the voltages of the target battery at different times during the multiple charging processes are corrected according to a fourth preset mapping relationship to improve the accuracy of the charging curve.

[0022] In a second aspect, a charging curve generating device is provided, comprising:

[0023] an acquisition unit, configured to acquire a current resting voltage and a charging plan corresponding to a target battery, wherein the current resting voltage is the voltage of the target battery at the last moment before the current charging process, and the charging plan is configured to reflect the current and temperature of the target battery at different moments during the charging process;

[0024] a voltage prediction unit, configured to predict the voltage of the target battery at different times during a plurality of charging processes according to the current static voltage, the charging plan, the first preset mapping relationship, and the second preset mapping relationship;

[0025] The first preset mapping relationship represents a mapping relationship between a first current, a first temperature, and a first voltage, and a second voltage, wherein the first current is a current at a first moment, the first moment is any moment in the charging process, the first temperature is a temperature at the first moment, the first voltage is a voltage at a moment before the first moment, and the second voltage is a voltage at the first moment;

[0026] The second preset mapping relationship represents a mapping relationship between a first static voltage, a second current and a second temperature, and a second static voltage, wherein the first static voltage is a voltage at the last moment before a first charging process, the first charging process is any charging process, the second current is a current at the first moment in the first charging process, the second temperature is a temperature at the first moment in the first charging process, the second static voltage is a voltage at the last moment before a second charging process, and the second charging process is a charging process next to the first charging process;

[0027] The multiple charging processes include the current charging process and a charging process after the current charging process;

[0028] A curve generating unit is used to generate a full-life charging curve of the target battery according to the voltage of the target battery at different moments in the multiple charging processes.

[0029] In a third aspect, a computer device is provided, comprising a memory and a processor, wherein the memory is connected to the processor, and the processor is used to execute one or more computer programs stored in the memory, and when the processor executes the one or more computer programs, the computer device implements the charging curve generation method of the first aspect.

[0030] In a fourth aspect, a battery device is provided, comprising the aforementioned charging curve generating apparatus, or comprising the aforementioned computer device.

[0031] The present application achieves the following technical effects: since multiple charging processes include the current charging process and the charging process after the current charging process, the charging process after the current charging process is the future charging process, which realizes the generation of the long-term charging curve of the battery in the future. Since the charging curve reflects the battery state, the prediction of the long-term battery state in the future is realized, which helps to detect the abnormal state of the battery early; since the first preset mapping relationship represents the mapping relationship between the first current, the first temperature and the first voltage and the second voltage, the first current is the current at any moment in the charging process, the first temperature is the temperature at any moment, the first voltage is the voltage at the moment before any moment, and the second voltage is the voltage at any moment, the second preset mapping relationship represents the mapping relationship between the first static voltage, the second current and the second temperature, and the second static voltage, the first static voltage is the current at any moment in the charging process, the first temperature is the temperature at any moment, the first voltage is the voltage at the moment before any moment, and the second voltage is the voltage at any moment. The voltage is the voltage at the last moment before the first charging process, and the second current is the current at the first moment in the first charging process, which is equivalent to predicting the voltage at the next moment between two adjacent moments based on the voltage at the previous moment between the two adjacent moments and the current and temperature at the next moment between the two adjacent moments, and predicting the static voltage of the next charging process between the two adjacent charging processes based on the static voltage corresponding to the previous charging process between the two adjacent charging processes and the current and temperature at the first moment of the next charging process between the two adjacent charging processes. Therefore, it is only necessary to predict the voltage at each moment in multiple charging processes based on the static voltage at the last moment before the charging process and the current and temperature at each moment included in the charging plan, and use less data to predict the battery status of the battery in the long term in the future, which is simple and convenient. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0033] Figure 1 A schematic diagram of a flow chart of a charging curve generation method provided in an embodiment of the present application;

[0034] Figure 2 A schematic diagram of a full-life charging curve provided in an embodiment of the present application;

[0035] Figure 3 A schematic diagram of a process for predicting the voltage of a target battery at different times during multiple charging processes provided in an embodiment of the present application;

[0036] Figure 4 A schematic diagram of a process for predicting the voltage of a target battery at different times during a charging process provided in an embodiment of the present application;

[0037] Figure 5A A schematic diagram of a first preset model provided in an embodiment of the present application;

[0038] Figure 5B A schematic diagram of a second preset model provided in an embodiment of the present application;

[0039] Figure 5C A schematic diagram of a third preset model provided in an embodiment of the present application;

[0040] Figure 6 A schematic diagram of a flow chart of another charging curve generating method provided in an embodiment of the present application;

[0041] Figure 7 A schematic diagram of a fourth preset model provided in an embodiment of the present application;

[0042] Figure 8 A schematic diagram of a process for establishing a preset mapping relationship in an embodiment of the present application;

[0043] Fig. 9 It is a structural schematic diagram of a charging curve generating device provided in an embodiment of the present application;

[0044] Fig.10 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] It is understandable that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other, all within the scope of protection of the present application. In addition, although the functional module division is performed in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a sequence different from the module division in the device or the flow chart. Furthermore, the words "first", "second", "third", etc. used in this application do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.

[0047] The technical solution of the present application is applicable to the application scenarios of lithium-ion batteries. The technical solution of the present application is used to predict the full-life charging curve of lithium-ion batteries in the application scenarios of lithium-ion batteries. The full-life charging curve of lithium-ion batteries refers to the charging curve of lithium-ion batteries from the time when the lithium-ion batteries are put into use to the time when the lithium-ion batteries are aged and cannot continue to be used. Among them, the technical solution of the present application is applied to equipment containing lithium-ion batteries, and equipment containing lithium-ion batteries is, for example, electric vehicles, electronic equipment, energy storage equipment, drones, power tools, etc., and the present application does not limit it.

[0048] In order to predict the full-life charging curve of a lithium-ion battery, the present application obtains charging data of a lithium-ion battery during multiple cycles of charging and discharging under conditions such as different temperatures, different charge and discharge rates, and different ambient temperatures in advance, wherein the charging data includes the voltage, current, and temperature of the lithium-ion battery, and pre-establishes multiple mapping relationships based on the charging data, wherein the mapping relationships are used to reflect the changes in charging data of the lithium-ion battery at adjacent moments in the same charging process, and the changes in charging data of the lithium-ion battery in adjacent charging processes; based on the multiple mapping relationships established in advance and in combination with the charging plan of the lithium-ion battery, a full-life charging curve of the lithium-ion battery is generated, wherein the full-life curve of the lithium-ion battery includes the voltage of the lithium-ion battery at different moments in multiple charging processes, reflects the battery status of the lithium-ion battery in the long term in the future, helps to predict the possible aging of the battery in the future, and facilitates timely management of the lithium-ion battery, thereby slowing down the battery aging rate and extending the battery life.

[0049] The following specifically takes lithium-ion batteries as an example to introduce the technical solution of the present application. It is understandable that the technical solution of the present application is also applicable to other types of batteries, such as sodium-ion batteries, perovskite batteries, semi-solid-state batteries, all-solid-state batteries, etc.

[0050] See also Figure 1 , Figure 1 A schematic diagram of a charging curve generation method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method comprises the following steps:

[0051] S101, obtaining a current static voltage and a charging plan corresponding to a target battery.

[0052] Here, the target battery is a lithium-ion battery whose charging curve needs to be predicted.

[0053] The current static voltage corresponding to the target battery is the voltage of the target battery at the last moment before the current charging process. The current charging process refers to the first charging process that needs to be predicted for the charging curve. The current charging process is, for example, the charging process that is currently being performed or is about to be performed. The time sequence is represented as t1, t2, t3, ..., t n For example, assuming t i The time is the time when the target battery starts to charge, and the current static voltage of the target battery is the target battery at t i-1 The voltage of the target battery at the last moment when charging starts is obtained to obtain the current static voltage corresponding to the target battery.

[0054] The charging plan corresponding to the target battery is used to reflect the current and temperature of the target battery at different times during the charging process. The charging plan corresponding to the target battery is pre-set and saved in the battery management system corresponding to the target battery, and the charging plan corresponding to the target battery is obtained from the battery management system corresponding to the target battery. For example, the charging plan is an SOP charging function pre-set in the battery management system. It is understandable that the SOP charging function is presented in a table, curve or function form.

[0055] S102, predicting the voltage of the target battery at different times during multiple charging processes according to the current static voltage, the charging plan, the first preset mapping relationship, and the second preset mapping relationship.

[0056] Here, the multiple charging processes include a current charging process and a plurality of charging processes after the current charging process, and the plurality of charging processes refer to a plurality of charging processes from the end of the current charging process to the time when the target battery ages and cannot be used.

[0057] The first preset mapping relationship represents the mapping relationship between the first current, the first temperature and the first voltage, and the second voltage, the first current is the current at a first moment, the first moment is any moment in the charging process, the first temperature is the temperature at the first moment, the first voltage is the voltage at the previous moment of the first moment, and the second voltage is the voltage at the first moment; that is, the first preset mapping relationship represents the mapping relationship between the voltage at the previous moment of two adjacent moments in the charging process, the current and temperature at the next moment of two adjacent moments, and the voltage at the next moment of two adjacent moments in the charging process.

[0058] The second preset mapping relationship represents the mapping relationship between the first static voltage, the second current and the second temperature, and the second static voltage, the first static voltage is the voltage at the last moment before the first charging process, the second current is the current at the first moment in the first charging process, the first charging process is the first charging process in the current charging process, the second temperature is the temperature at the first moment in the first charging process, the second static voltage is the temperature at the last moment before the second charging process, and the second charging process is the next charging process of the first charging process; that is, the second preset mapping relationship represents the mapping relationship between the static voltage corresponding to the previous charging process of two adjacent charging processes and the current and temperature at the first moment of the next charging process of two adjacent charging processes, and the static voltage corresponding to the next charging process of two adjacent charging processes.

[0059] The first preset mapping relationship and the second preset mapping relationship are obtained by pre-establishment. The specific process of establishing the first preset mapping relationship and the second preset mapping relationship will be introduced in detail later. Please refer to the description later.

[0060] The specific process of predicting the voltage of the target battery at different times during multiple charging processes will be described in detail later. Please refer to the description later.

[0061] S103, generating a full-life charging curve of the target battery according to the voltage of the target battery at different times during multiple charging processes.

[0062] Here, the full life charging curve of the target battery includes the voltage at different times during multiple charging processes. The full life charging curve of the target battery takes time as the horizontal axis and takes the voltage at different times during multiple charging processes as the vertical axis. For example, the full life charging curve of the target battery is as follows: Figure 2 shown.

[0063] In the above Figure 1In the corresponding technical solution, after obtaining the current static voltage corresponding to the target battery and the charging plan reflecting the current and temperature of the battery at different times during the charging process, the voltage of the target battery at different times during multiple charging processes is predicted according to the current static voltage, the charging plan, the first preset mapping relationship and the second preset mapping relationship, and then the full-life charging curve of the target battery is generated according to the voltage of the target battery at different times during the multiple charging processes. Since the multiple charging processes include the current charging process and the charging process after the current charging process, the charging process after the current charging process is a future charging process, which realizes the generation of the long-term charging curve of the battery in the future. Since the charging curve reflects the battery status, the prediction of the long-term battery status in the future is realized, which is helpful to detect the abnormal status of the battery early. Since the first preset mapping relationship represents the mapping relationship between the first current, the first temperature and the first voltage and the second voltage, the first current is the current at any time during the charging process, the first temperature is the temperature at any time, and the first voltage is the temperature at any time. The first static voltage is the voltage at the last moment, the second voltage is the voltage at any moment, the second preset mapping relationship represents the mapping relationship between the first static voltage, the second current and the second temperature, and the second static voltage, the first static voltage is the voltage at the last moment before the first charging process, and the second current is the current at the first moment in the first charging process, which is equivalent to predicting the voltage at the next moment in the two adjacent moments according to the voltage at the last moment in the two adjacent moments, and the current and temperature at the next moment in the two adjacent moments, and predicting the static voltage of the next charging process in the two adjacent charging processes according to the static voltage corresponding to the last charging process in the two adjacent charging processes and the current and temperature at the first moment of the next charging process in the two adjacent charging processes. Therefore, it is only necessary to predict the voltage at each moment in multiple charging processes based on the static voltage at the last moment before the charging process and the current and temperature at each moment included in the charging plan, and use less data to predict the battery state of the battery in the long term in the future, which is simple and convenient.

[0064] Next, we will introduce the specific process of predicting the voltage of the target battery at different times during multiple charging processes. Figure 3 , Figure 3 A schematic diagram of a process for predicting the voltage of a target battery at different times during multiple charging processes provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the following steps A1-A6 are included:

[0065] A1. The current static voltage is used as the target static voltage, and the current charging process is used as the target charging process.

[0066] A2. Predicting the voltage of the target battery at different times during the target charging process according to the first preset mapping relationship, the target static voltage, and the charging plan.

[0067] Among them, through the following Figure 4 The process steps shown in the figure predict the voltage of the target battery at different times during the target charging process, including the following steps A21-A28:

[0068] A21. Take the target static voltage as the target known voltage.

[0069] A22. The first moment in the target charging process is taken as the target moment.

[0070] A23. Obtain the current and temperature of the target battery at the target time from the charging plan to obtain a second target current and a second target temperature.

[0071] A24. Determine the voltage corresponding to the target known voltage, the second target current, and the second target temperature according to the first preset mapping relationship, and obtain the voltage at the target time.

[0072] In some possible embodiments, the first preset mapping relationship is expressed by a first preset model obtained by pre-training, and the first preset model is used to reflect the first preset mapping relationship. The first preset model is shown as M1 in 5A. The first preset model is based on the voltage U at the previous moment of two adjacent moments. i-1 , the current I at the next moment between two adjacent moments i and the temperature T of the next moment between two adjacent moments i As the input parameter, the voltage U at the next moment between two adjacent moments is i as an output parameter.

[0073] The first preset model is a model of any network structure, and the first preset model includes but is not limited to a convolutional neural network, a densely connected network, a recurrent neural network, a long short-term memory network, an attention mechanism model, a Transformer, etc.

[0074] Taking the network structure of the first preset model as a multi-layer perception (MLP) as an example, the first preset model is Figure 5A As shown in m1 in the figure, the first preset model includes an input layer, a hidden layer and an output layer. The input layer of the first preset model is used to input U i-1 ,I i and T i , the hidden layer of the first preset model is used to input U i-1 ,I i and T iThe data is processed to obtain hidden features. The connection matrix between the hidden layer of the first preset model and the input layer of the first preset model is 3*Q1, where Q1 is the number of neurons in the hidden layer of the first preset model, that is, the data dimension of the hidden features output by the hidden layer of the first preset model; the output layer of the first preset model is used to output U according to the hidden features output by the hidden layer of the first preset model. i , the connection matrix between the output layer of the first preset model and the hidden layer of the first preset model is Q1*1. It can be understood that, Figure 5A The m1 in this document is merely an example used to explain the first preset model in this document and does not limit this document.

[0075] When the first preset mapping relationship is expressed by the first preset model, the target known voltage, the second target current and the second target temperature are input into the first preset model to obtain the voltage at the target moment.

[0076] Take the first preset model as Figure 5A Taking m1 in as an example, the target known voltage, the second target current and the second target temperature are input into the first preset model. The target known voltage, the second target current and the second target temperature form a 1*3 matrix. The hidden layer in the first preset model multiplies the 1*3 input matrix with the 3*Q1 connection matrix to obtain a 1*Q1 hidden matrix. The output layer in the first preset model multiplies the 1*Q1 hidden matrix with the Q1*1 connection matrix to output the voltage at the first target moment.

[0077] The pre-trained model is used to predict the voltage at the next moment between two adjacent moments in the charging process to ensure the accuracy of voltage prediction.

[0078] A25. Determine whether the target time is the last time in the target charging process.

[0079] If the target time is the last time in the target charging process, it means that the target charging process is finished, and step A28 is executed; if the target time is not the last time in the target charging process, it means that the target charging process is not finished, and step A26 is executed.

[0080] A26. The voltage at the target time is taken as the target known voltage.

[0081] A27. Set the next moment of the target moment as the target moment and execute step A23.

[0082] A28. Voltage prediction for ending the target charging process.

[0083] Through the above steps A21 to A28, the voltage at the next moment between two adjacent moments is predicted according to the first preset mapping relationship, and the time is continuously iterated to achieve the prediction of the voltage at each moment in the charging process.

[0084] A3. From the charging plan, obtain the current and temperature of the target battery at the first moment of the charging process to obtain a first target current and a first target temperature.

[0085] A4. Determine a voltage corresponding to the target quiescent voltage, the first target current, and the first target temperature according to a second preset mapping relationship, and obtain a next quiescent voltage corresponding to the target quiescent voltage.

[0086] Here, the next static voltage corresponding to the target static voltage is the voltage at the last moment before the next charging process of the target charging process obtained by prediction.

[0087] In some possible embodiments, the second preset mapping relationship is expressed by a second preset model obtained by pre-training, and the second preset model is used to reflect the second preset mapping relationship. The second preset model is shown as M2 in 5B. The second preset model is based on the static voltage u corresponding to the previous charging process in two adjacent charging processes. j-1 , the current I at the first moment of the next charging process between two adjacent charging processes j1 And the temperature T at the first moment of the next charging process between two adjacent charging processes j1 As the input parameter, the static voltage u corresponding to the next charging process of the two adjacent charging processes is j As an output parameter, it is understandable that the adjacency of two charging processes in the present application refers to the adjacency of the charging processes in sequence, rather than the adjacency in charging time, and the charging start time of the next charging process of two adjacent charging processes is not necessarily the charging end time of the previous charging process of the two adjacent charging processes.

[0088] The second preset model is a model of any network structure, and the second preset model includes but is not limited to a convolutional neural network, a densely connected network, a recurrent neural network, a long short-term memory network, an attention mechanism model, a Transformer, etc.

[0089] Taking the network structure of the second preset model as MLP as an example, the second preset model is Figure 5B As shown in m2 in the figure, the second preset model includes an input layer, a hidden layer and an output layer. The input layer of the second preset model is used to input u j-1 ,I j1 and T j1 , the hidden layer of the second preset model is used to input u j-1 ,I j1 and Tj1 The data is processed to obtain hidden features. The connection matrix between the hidden layer of the second preset model and the input layer of the second preset model is 3*Q2, where Q2 is the number of neurons in the hidden layer of the second preset model, that is, the data dimension of the hidden features output by the hidden layer of the second preset model; the output layer of the second preset model is used to output u according to the hidden features output by the hidden layer of the second preset model. j , the connection matrix between the output layer of the second preset model and the hidden layer of the second preset model is Q2*1. It can be understood that, Figure 5B The m2 in this document is merely an example used to explain the second preset model in this document and does not limit this document.

[0090] When the second preset mapping relationship is expressed by the second preset model, the target quiescent voltage, the first target current and the first target temperature are input into the second preset model to obtain a next quiescent voltage corresponding to the target quiescent voltage.

[0091] Taking the second preset model as shown by m2 in 5B as an example, the target quiescent voltage, the first target current and the first target temperature are input into the second preset model. The target quiescent voltage, the first target current and the first target temperature constitute a 1*3 input matrix. The hidden layer in the second preset model multiplies the 1*3 input matrix with the 3*Q2 connection matrix to obtain a 1*Q2 hidden matrix. The output layer in the second preset model multiplies the 1*Q2 hidden matrix with the Q2*1 connection matrix to output the next quiescent voltage corresponding to the target quiescent voltage.

[0092] The pre-trained model is used to predict the static voltage before the next charging process in two adjacent charging processes to ensure the accuracy of the static voltage prediction.

[0093] A5. The next static voltage corresponding to the target static voltage is used as the target static voltage.

[0094] In some optional embodiments, before taking the next quiescent voltage corresponding to the target quiescent voltage as the target quiescent voltage, the next quiescent voltage corresponding to the target quiescent voltage is corrected according to a third preset mapping relationship.

[0095] The third preset mapping relationship represents the mapping relationship between the static voltage predicted based on the second preset mapping relationship and the actual static voltage.

[0096] The third preset mapping relationship is obtained by pre-establishment, and the specific process of establishing the third preset mapping relationship will be described in detail later.

[0097] In some possible embodiments, the third preset mapping relationship is expressed by a third preset model obtained by pre-training, and the third preset model is used to reflect the third preset mapping relationship. The third preset model is shown as M3 in 5C. The third preset model is based on the static voltage u predicted based on the second preset mapping relationship. j As input parameter, and output the corrected static voltage u jx .

[0098] The third preset model is a model of any network structure, and the third preset model includes but is not limited to a convolutional neural network, a densely connected network, a recurrent neural network, a long short-term memory network, an attention mechanism model, a Transformer, etc.

[0099] Taking the network structure of the third preset model as MLP as an example, the third preset model is Figure 5C As shown in m3 in FIG. 1 , the third preset model includes an input layer, a hidden layer and an output layer. The input layer of the third preset model is used to input u j , the hidden layer of the third preset model is used to input u j The data is processed to obtain hidden features. The connection matrix between the hidden layer of the third preset model and the input layer of the third preset model is 1*Q3, where Q3 is the number of neurons in the hidden layer of the third preset model, that is, the data dimension of the hidden features output by the hidden layer of the third preset model; the output layer of the third preset model is used to output u according to the hidden features output by the hidden layer of the third preset model. jx , the connection matrix between the output layer of the third preset model and the hidden layer of the third preset model is Q3*1. It can be understood that, Figure 5C The m3 in this document is merely an example used to explain the third preset model in this document and does not limit this document.

[0100] In the case where the third preset mapping relationship is expressed by the third preset model, the next quiescent voltage corresponding to the target quiescent voltage is input into the third preset model to obtain the corrected next quiescent voltage corresponding to the target quiescent voltage.

[0101] The third preset model is Figure 5C Taking m3 in the figure as an example, the next static voltage corresponding to the target static voltage is input into the third preset model, the hidden layer in the third preset model multiplies the next static voltage corresponding to the target static voltage with the connection matrix of 1*Q3 to obtain the hidden matrix of 1*Q3, and the output layer in the third preset model multiplies the hidden matrix of 1*Q3 with the connection matrix of Q3*1 to output the corrected next static voltage corresponding to the target static voltage.

[0102] After obtaining the corrected next static voltage corresponding to the target static voltage, the corrected next static voltage corresponding to the target static voltage is used as the target static voltage, and step A6 is executed.

[0103] The static voltage corresponding to the charging process is corrected according to the third preset mapping relationship to improve the accuracy of static voltage prediction.

[0104] A6. Take the next charging process of the target charging process as the target charging process and execute steps A2 and A3.

[0105] In the above steps A1-A6, the voltage at the next moment between two adjacent moments is predicted according to the first preset mapping relationship, and the static voltage before the next charging process between two adjacent charging processes is predicted according to the second preset mapping relationship, and the charging process is continuously iterated to realize the prediction of the voltage at each moment in multiple charging processes.

[0106] See also Figure 6 , Figure 6 A schematic diagram of a flow chart of another charging curve generation method provided in an embodiment of the present application, such as Figure 6 As shown, the method comprises the following steps:

[0107] S201, obtaining a current static voltage and a charging plan corresponding to a target battery.

[0108] S202, predicting the voltage of the target battery at different times during multiple charging processes according to the current static voltage, the charging plan, the first preset mapping relationship, and the second preset mapping relationship.

[0109] Here, regarding the specific implementation method of steps S201-S202, please refer to the description of the aforementioned steps S101-S102, which will not be repeated here.

[0110] S203: Correcting the voltage of the target battery at different times during the plurality of charging processes according to a fourth preset mapping relationship.

[0111] Here, the fourth preset mapping relationship represents the mapping relationship between the charging curve predicted based on the first preset mapping relationship and the actual charging curve.

[0112] The fourth preset mapping relationship is obtained by pre-establishment, and the specific process of establishing the fourth preset mapping relationship will be described in detail later.

[0113] In some possible embodiments, the fourth preset mapping relationship is expressed by a fourth preset model obtained by pre-training, and the fourth preset model is used to reflect the fourth preset mapping relationship. The fourth preset model is shown as M4 in 7. The fourth preset model is based on the voltages (U1, U2, ..., U m ) as input parameters, and output the corrected voltage at different times during the charging process (U 1x ,U 2x ,…,U mx ).

[0114] The fourth preset model is a model of any network structure, and the fourth preset model includes but is not limited to a convolutional neural network, a densely connected network, a recurrent neural network, a long short-term memory network, an attention mechanism model, a Transformer, etc.

[0115] Taking the network structure of the fourth preset model as a bidirectional long short-term memory network (BiLSTM) as an example, the fourth preset model is as follows Figure 7 As shown in m4 in FIG. 1 , the fourth preset model includes an input layer, a forward LSTM, a backward LSTM, and an output layer. The input layer of the fourth preset model is used to input U1, U2, …, U m , the forward LSTM and backward LSTM of the fourth preset model are used to train U1, U2, ..., U m Forward time series feature extraction and backward time series feature extraction are performed in sequence; the output layer is used to output U 1x ,U 2x ,…,U mx Understandably, Figure 7 The m4 in this document is merely an example used to explain the fourth preset model in this application and does not limit this application.

[0116] When the fourth preset mapping relationship is expressed by the fourth preset model, the voltage at different moments in each of the multiple charging processes is respectively input into the fourth preset model to obtain the corrected voltage at different moments in each of the charging processes.

[0117] Take the fourth preset model as Figure 7 Taking m4 as an example, the voltages at different moments in the current charging process are added to the fourth preset model to obtain the corrected voltages at different moments in the current charging process; the voltages at different moments in the next charging process of the current charging process are added to the fourth preset model to obtain the corrected voltages at different moments in the next charging process of the current charging process; and so on, to obtain the corrected voltages at different moments in each charging process.

[0118] S204, generating a full-life charging curve of the target battery according to the voltage of the target battery at different times during multiple charging processes.

[0119] Here, regarding the specific implementation method of step S204, please refer to the description of the aforementioned step S103, which will not be repeated here.

[0120] In the above Figure 6 In the corresponding technical solution, after predicting the voltage of the target battery at different times during multiple charging processes, the voltage of the target battery at different times during multiple charging processes is corrected according to the fourth preset mapping relationship to improve the accuracy of the charging curve.

[0121] Next, the specific process of establishing the first preset mapping relationship, the second preset mapping relationship, the third preset mapping relationship, and the fourth preset mapping relationship is introduced. Figure 8 , Figure 8 The process steps for establishing a preset mapping relationship provided in the embodiment of the present application include the following steps S301-S315:

[0122] S301, obtaining charging data.

[0123] Among them, multiple groups of battery samples are obtained, each group of battery samples includes multiple lithium-ion batteries, the battery samples in the same group use the same charge and discharge parameters, and the battery samples in different groups use different charge and discharge parameters. The charge and discharge parameters include temperature, charge rate, and ambient humidity, that is, the corresponding temperature and / or charge rate and / or ambient humidity between two groups of battery samples are different.

[0124] The lithium-ion batteries in each group of battery samples are subjected to multiple charge and discharge cycle processes until the charging capacity of the lithium-ion batteries decays to a preset percentage (e.g., 80%) of the initial capacity, wherein one charge and discharge cycle process consists of a rest stage, a charging stage, and a discharge stage, the rest stage is located before the charging stage, the charging stage is located before the discharge stage, and the next stage of the discharge stage in the previous charge and discharge cycle process between two adjacent charge and discharge cycles is the rest stage in the next charge and discharge process between the two adjacent charge and discharge cycles.

[0125] During the multiple charge and discharge cycles of each lithium-ion battery, the voltage of each lithium-ion battery at the last moment of each rest stage is recorded as the resting voltage; and the voltage, current and temperature of each lithium-ion battery at two adjacent moments in each charging stage are recorded; the recorded voltage (including the resting voltage), current and temperature are used as charging data.

[0126] S302: Acquire a first sample data set from charging data.

[0127] The first sample data set includes a plurality of first sample data, and the first sample data is represented as (x1 k ,y1 k ), (x1 k ,y1 k ) represents the kth first sample data in the first sample data set; x1 k represents the input sample in the kth first sample data, x1 k = {U i-1 , I i , T i},U i-1 Indicates the voltage at the previous moment between two adjacent moments, I i represents the current at the next moment between two adjacent moments, T i Indicates the temperature of the next moment between two adjacent moments; y1 k Represents the output sample in the kth first sample data, y1 k =U i , U i Indicates the voltage at the next moment between two adjacent moments.

[0128] S303: Establish a first preset mapping relationship according to the first sample data set.

[0129] Among them, the input samples in the first sample data set are input into the first preset model, and the parameters of the first preset model are adjusted according to the output of the first preset model and the output samples corresponding to the input samples in the first sample data set until the first preset model converges, thereby establishing a first preset mapping relationship, that is, obtaining the first preset model reflecting the first preset mapping relationship.

[0130] S304: Acquire a second sample data set from the charging data.

[0131] The second sample data set includes a plurality of second sample data, and the second sample data is represented by (x2 k , y2 k ), (x2 k , y2 k ) represents the kth second sample data in the second sample data set; x2 k represents the input sample in the kth second sample data, x2 k = {u j-1 , I j1 , T j1},u j-1 It represents the static voltage at the last moment before the last charging process in two adjacent charging processes, I j1 Indicates the current at the first moment of the next charging process between two adjacent charging processes, T j1Indicates the temperature at the first moment of the next charging process between two adjacent charging processes; y2 k represents the output sample in the kth second sample data, y2 k =u j ,u j It refers to the static voltage at the last moment before the next charging process in two adjacent charging processes. The charging process refers to the process corresponding to the charging stage in the charge and discharge cycle.

[0132] S305: Establish a second preset mapping relationship according to the second sample data set.

[0133] Among them, the input samples in the second sample data set are input into the second preset model, and the parameters of the second preset model are adjusted according to the output of the second preset model and the output samples corresponding to the input samples in the second sample data set until the second preset model converges, thereby establishing a second preset mapping relationship, that is, obtaining a second preset model reflecting the second preset mapping relationship.

[0134] S306: Acquire the first input data set from the second sample data set.

[0135] The first input data set includes multiple first input data, the first input data is the input sample in the second sample data set, and the first input data is represented by x2 k , x2 k Represents the kth first input data in the first input data set.

[0136] S307: Determine a first predicted output data set corresponding to the first input data set according to a second preset mapping relationship.

[0137] The first prediction output data set includes a plurality of first prediction output data, and the first prediction output data is represented by y yk ,y yk represents x2 determined according to the second preset mapping relationship k The corresponding predicted value.

[0138] S308: Acquire a first output data set corresponding to the first input data set from the second sample data set.

[0139] The first output data set includes a plurality of first output data, the first output data is an output sample in the second sample data set, and the first output data is represented by y2 k , y2 k represents the kth first output data in the first output data set.

[0140] S309: Determine a third sample data set according to the first predicted output data set and the first output data set.

[0141] The third sample data set includes a plurality of third sample data, and the third sample data is represented by (x3 k ,y3 k ), (x3 k ,y3 k ) represents the kth third sample data in the third sample data set; x3 k represents the input sample in the kth third sample data, x3 k =y yk ;y3 k represents the output sample in the kth third sample data, y3 k =y2 k .

[0142] S310: Establish a third preset mapping relationship according to a third sample data set.

[0143] Among them, the input samples in the third sample data set are input into the third preset model, and the parameters of the third preset model are adjusted according to the output of the third preset model and the output samples corresponding to the input samples in the third sample data set until the third preset model converges, thereby establishing a third preset mapping relationship, that is, obtaining the third preset model reflecting the third preset mapping relationship.

[0144] S311, obtaining a second input data set from the first sample data set.

[0145] The second input data set includes a plurality of second input data, and the second input data is represented by X1 v , X1 v represents the vth second input data in the second input data set, X1 v ={x1 vi , i=1,2,3,…,n}, n represents the time length of a charging stage, that is, the second input data includes all input samples contained in a charging stage in the first sample data set.

[0146] S312: Determine a second predicted output data set corresponding to the second input data set according to the first preset mapping relationship.

[0147] The second prediction output data set includes a plurality of second prediction output data, and the second prediction output data set is represented by Y1 v , Y1 v represents the vth second predicted output data in the second predicted output data set, Y1 v ={y yvi , i=1,2,3,…,n},y vi Indicates x1 determined according to the first preset mapping relationship vi The corresponding predicted value.

[0148] S313: Acquire a second output data set corresponding to the second input data set from the first sample data set.

[0149] The second output data set includes a plurality of second output data, and the second output data is represented by Y2 v , Y2 v represents the vth second output data in the second output data set, Y2 v ={y1 vi , i=1,2,3,…,n}, that is, the second output data includes all output samples contained in a charging stage in the first sample data set.

[0150] S314: Determine a fourth sample data set according to the second predicted output data set and the second output data set.

[0151] The fourth sample data set includes a plurality of fourth sample data, and the fourth sample data is represented by (X2 v , Y2 v ), (X2 v , Y2 v ) represents the vth fourth sample data in the fourth sample data set; X2 v represents the input sample in the vth fourth sample data, X2 v =Y1 v ;Y2 v Represents the output sample in the vth fourth sample data.

[0152] S315: Establish a fourth mapping relationship according to the fourth sample data set.

[0153] Among them, the input samples in the fourth sample data set are input into the fourth preset model, and the parameters of the fourth preset model are adjusted according to the output of the fourth preset model and the output samples corresponding to the input samples in the fourth sample data set until the fourth preset model converges, thereby establishing a fourth preset mapping relationship, that is, obtaining the fourth preset model reflecting the fourth preset mapping relationship.

[0154] In some possible embodiments, after more charging data of the target battery is acquired, the first mapping relationship, the second mapping relationship, the third mapping relationship, and the fourth mapping relationship are adjusted according to the acquired charging data.

[0155] The method of the present application is introduced above, and the device of the present application is introduced below.

[0156] See also Fig. 9 , Fig. 9 is a schematic diagram of the structure of a charging curve generating device provided in an embodiment of the present application, such as Fig. 9 As shown, the charging curve generating device 40 includes:

[0157] An acquisition unit 401 is used to acquire a current static voltage and a charging plan corresponding to a target battery, wherein the current static voltage is the voltage of the target battery at the last moment before the current charging process, and the charging plan is used to reflect the current and temperature of the target battery at different moments during the charging process;

[0158] A voltage prediction unit 402, configured to predict the voltage of the target battery at different times during multiple charging processes according to the current static voltage, the charging plan, the first preset mapping relationship, and the second preset mapping relationship;

[0159] The first preset mapping relationship represents a mapping relationship between the first current, the first temperature and the first voltage, and the second voltage, the first current is the current at the first moment, the first moment is any moment in the charging process, the first temperature is the temperature at the first moment, the first voltage is the voltage at the previous moment before the first moment, and the second voltage is the voltage at the first moment;

[0160] The second preset mapping relationship represents a mapping relationship between the first static voltage, the second current and the second temperature, and the second static voltage, wherein the first static voltage is the voltage at the last moment before the first charging process, the first charging process is any charging process, the second current is the current at the first moment in the first charging process, the second temperature is the temperature at the first moment in the first charging process, the second static voltage is the voltage at the last moment before the second charging process, and the second charging process is the next charging process of the first charging process;

[0161] The aforementioned multiple charging processes include the aforementioned current charging process and a charging process after the aforementioned current charging process;

[0162] The curve generating unit 403 is used to generate a full-life charging curve of the target battery according to the voltage of the target battery at different times during the multiple charging processes.

[0163] It should be noted that the charging curve generating device 40 is used to execute the charging curve generating method provided in the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in the embodiment of the charging curve generating device 40, please refer to the charging curve generating method provided in the embodiment of the present application.

[0164] See also Fig.10 , Fig.10is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, wherein the computer device 50 includes a processor 501 and a memory 502. The memory 502 is connected to the processor 501, for example, via a bus.

[0165] The processor 501 is configured to support the computer device 50 to perform the corresponding functions in the method in the above method embodiment. The processor 501 is a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof. The above hardware chip is an application specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above PLD is a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0166] The memory 502 is used to store program codes, etc. In some embodiments, the memory 502 includes a volatile memory (VM), such as a random access memory (RAM); in some embodiments, the memory 502 includes a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); in some embodiments, the memory 502 also includes a combination of the above-mentioned types of memory.

[0167] The memory 502 is used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the charging curve generation method in the embodiment of the present application. The processor executes various functional applications and data processing of the charging curve generation method by running the non-volatile software programs, instructions and modules stored in the memory, that is, realizes the functions of the charging curve generation method provided by the above method embodiment.

[0168] In some embodiments, the memory 502 includes a program storage area and a data storage area, wherein the program storage area stores an operating system and an application required for at least one function. The data storage area stores data created according to the use of the charging curve generating device, etc. In some embodiments, the memory includes a memory remotely arranged relative to the processor, and these remote memories are connected to the charging curve generating device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0169] The aforementioned one or more modules are stored in the aforementioned memory, and when executed by the aforementioned one or more processors, the charging curve generation method in any of the aforementioned method embodiments is executed, for example, the method steps described in the above method embodiments are executed to realize the functions of the modules described in the above device embodiments.

[0170] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method as described in the embodiment.

[0171] Those skilled in the art understand that all or part of the processes in the above-mentioned embodiments are implemented by instructing the relevant hardware through a computer program, and the above-mentioned program is stored in a computer-readable storage medium, and when the program is executed, it includes the processes of the embodiments of the above-mentioned methods. Among them, the above-mentioned storage medium is a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0172] The embodiment of the present application further provides a battery device, which includes the aforementioned charging curve generating device 40 or the aforementioned computer device 50.

[0173] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A charging curve generation method, characterized in that: include: Obtaining a current resting voltage and a charging plan corresponding to a target battery, wherein the current resting voltage is the voltage of the target battery at the last moment before the current charging process, and the charging plan is used to reflect the current and temperature of the target battery at different moments during the charging process; Predicting the voltage of the target battery at different times during multiple charging processes according to the current static voltage, the charging plan, the first preset mapping relationship, and the second preset mapping relationship; The first preset mapping relationship represents a mapping relationship between a first current, a first temperature, and a first voltage, and a second voltage, wherein the first current is a current at a first moment, the first moment is any moment in the charging process, the first temperature is a temperature at the first moment, the first voltage is a voltage at a moment before the first moment, and the second voltage is a voltage at the first moment; The second preset mapping relationship represents a mapping relationship between a first static voltage, a second current and a second temperature, and a second static voltage, wherein the first static voltage is a voltage at the last moment before a first charging process, the first charging process is any charging process, the second current is a current at the first moment in the first charging process, the second temperature is a temperature at the first moment in the first charging process, the second static voltage is a voltage at the last moment before a second charging process, and the second charging process is a charging process next to the first charging process; The multiple charging processes include the current charging process and a charging process after the current charging process; A full-life charging curve of the target battery is generated according to the voltage of the target battery at different moments in the multiple charging processes.

2. The method according to claim 1, characterized in that The predicting, according to the current static voltage, the charging plan, the first preset mapping relationship and the second preset mapping relationship, the voltage of the target battery at different times during multiple charging processes includes: Taking the current static voltage as a target static voltage, and taking the current charging process as a target charging process; Predicting the voltage of the target battery at different times during the target charging process according to the first preset mapping relationship, the target static voltage, and the charging plan, and obtaining the current and temperature of the target battery at the first time during the charging process from the charging plan to obtain a first target current and a first target temperature; Determine, according to the second preset mapping relationship, a voltage corresponding to the target static voltage, the first target current, and the first target temperature, and obtain a next static voltage corresponding to the target static voltage, wherein the next static voltage is a voltage at a last moment before a next charging process of the target charging process; The next resting voltage is taken as the target resting voltage, and the next charging process of the target charging process is taken as the target charging process, and the steps of predicting the voltage of the target battery at different moments in the target charging process according to the first preset mapping relationship, the target resting voltage and the charging plan are performed, and the current and temperature of the target battery at the first moment in the charging process are obtained from the charging plan to obtain the first target current and the first target temperature.

3. The method according to claim 2, characterized in that The predicting, according to the first preset mapping relationship, the target static voltage and the charging plan, the voltage of the target battery at different times during the target charging process includes: Taking the target static voltage as the target known voltage, and taking the first moment in the current charging process as the target moment; From the charging plan, obtaining the current and temperature of the target battery at the target time, and obtaining a second target current and a second target temperature; Determine, according to the first preset mapping relationship, a voltage corresponding to the target known voltage, the second target current, and the second target temperature, to obtain the voltage at the target moment; The voltage at the target moment is taken as the target known voltage, and the moment after the target moment is taken as the target moment, and the step of obtaining the current and temperature of the target battery at the target moment from the charging plan to obtain a second target current and a second target temperature is performed.

4. The method according to claim 3, characterized in that The step of determining, according to the first preset mapping relationship, a voltage corresponding to the target known voltage, the second target current, and the second target temperature to obtain the voltage at the target moment includes: The target known voltage, the second target current and the second target temperature are input into a first preset model to obtain the voltage at the target moment, the first preset model is obtained through pre-training, and the first preset model is used to reflect the first preset mapping relationship.

5. The method according to claim 2, characterized in that: The step of determining, according to the second preset mapping relationship, a voltage corresponding to the target quiescent voltage, the first target current, and the first target temperature, and obtaining a next quiescent voltage corresponding to the target quiescent voltage includes: The target quiescent voltage, the first target current and the first target temperature are input into a second preset model to obtain a next quiescent voltage corresponding to the target quiescent voltage, the second preset model is obtained through pre-training, and the second preset model is used to reflect the second preset mapping relationship.

6. The method according to claim 2, characterized in that Before taking the next static voltage as the target static voltage, the method further includes: The next quiescent voltage is corrected according to a third preset mapping relationship, wherein the third preset mapping relationship represents a mapping relationship between a quiescent voltage predicted based on the second preset mapping relationship and a real quiescent voltage.

7. The method according to any one of claims 1 to 6, characterized in that: Before generating the full life charging curve of the target battery according to the voltage of the target battery at different moments in the multiple charging processes, the method further includes: The voltage of the target battery at different moments in a plurality of charging processes is corrected according to a fourth preset mapping relationship, wherein the fourth preset mapping relationship represents a mapping relationship between a charging curve predicted based on the first preset mapping relationship and an actual charging curve.

8. A charging curve generating device, characterized in that: include: an acquisition unit, configured to acquire a current resting voltage and a charging plan corresponding to a target battery, wherein the current resting voltage is the voltage of the target battery at the last moment before the current charging process, and the charging plan is configured to reflect the current and temperature of the target battery at different moments during the charging process; a voltage prediction unit, configured to predict the voltage of the target battery at different times during a plurality of charging processes according to the current static voltage, the charging plan, the first preset mapping relationship, and the second preset mapping relationship; The first preset mapping relationship represents a mapping relationship between a first current, a first temperature, and a first voltage, and a second voltage, wherein the first current is a current at a first moment, the first moment is any moment in the charging process, the first temperature is a temperature at the first moment, the first voltage is a voltage at a moment before the first moment, and the second voltage is a voltage at the first moment; The second preset mapping relationship represents a mapping relationship between a first static voltage, a second current and a second temperature, and a second static voltage, wherein the first static voltage is a voltage at the last moment before a first charging process, the first charging process is any charging process, the second current is a current at the first moment in the first charging process, the second temperature is a temperature at the first moment in the first charging process, the second static voltage is a voltage at the last moment before a second charging process, and the second charging process is a charging process next to the first charging process; The multiple charging processes include the current charging process and a charging process after the current charging process; A curve generating unit is used to generate a full-life charging curve of the target battery according to the voltage of the target battery at different moments in the multiple charging processes.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory is connected to the processor, and the processor is used to execute one or more computer programs stored in the memory. When the processor executes the one or more computer programs, the computer device implements the method according to any one of claims 1 to 7.

10. A battery device, comprising the charging curve generating apparatus as claimed in claim 8, or comprising the computer device as claimed in claim 9.

Images