Battery state of charge estimation method and battery state of charge estimation device

Abstract

The invention discloses a battery state-of-charge estimation method and a battery state-of-charge estimation device, and belongs to the technical field of batteries. The method comprises the steps of obtaining a first operation parameter of a target battery in a current detection stage through a battery management unit; obtaining a first charge estimation value based on the first operation parameter through a target time sequence observation model; the target time sequence observation model is used for executing a PITS algorithm; based on a target filtering algorithm, correcting the first charge estimation value, and obtaining a target charge state of the target battery at the current moment; the current moment is the end point moment of the current detection stage. The battery charge state estimation method disclosed by the invention is used for solving the problem of low estimation accuracy of the battery charge state.

Description

Technical Field

[0001] This application belongs to the field of battery technology, and in particular relates to a battery state of charge estimation method and a battery state of charge estimation device. Background Technology

[0002] The state of charge (SOC) of a battery reflects its remaining usable capacity and is a key indicator for balancing control and determining whether a battery is overcharged or over-discharged. Typically, the battery's SOC can be estimated using OCV-SOC curves or by constructing a battery model.

[0003] However, due to factors such as battery aging, ambient temperature, complex operating conditions, and noise, it is difficult to accurately estimate the battery's state of charge. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a battery state of charge estimation method and a battery state of charge estimation device to solve the problem of low accuracy in battery state of charge estimation.

[0005] In a first aspect, this application provides a method for estimating the state of charge of a battery, including: The battery management unit obtains the first operating parameters of the target battery at the current testing stage. The first charge estimate is obtained based on the first operating parameters using the target time series observation model; the target time series observation model is used to execute the PITS algorithm. Based on the target filtering algorithm, the first charge estimate is corrected to obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage.

[0006] According to the battery state of charge estimation method of this application, the first operating parameters of the target battery in the current detection stage are obtained through the battery management unit; the first charge estimate is obtained based on the first operating parameters through the target time series observation model; the target time series observation model is used to execute the PITS algorithm; the first charge estimate is corrected based on the target filtering algorithm to obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage, and the first charge estimate obtained by the target time series observation model based on the first operating parameters of the target battery is more in line with the operating conditions of the target battery in the current detection stage, and the noise influence is eliminated by the target filtering algorithm to improve the accuracy of the target battery state of charge estimation.

[0007] According to one embodiment of this application, based on a target filtering algorithm, the first charge estimate is corrected to obtain the target state of charge of the target battery at the current moment, including: The battery management unit obtains a second charge estimate based on the first operating parameters. The estimated value of the third charge is obtained by using the ampere-hour integration algorithm; Based on the target filtering algorithm, the first charge estimate is corrected by the second and third charge estimates to obtain the target state of charge of the target battery at the current moment.

[0008] According to one embodiment of this application, obtaining a third charge estimate using an ampere-hour integration algorithm includes: The third charge estimate is obtained by using the ampere-hour integration algorithm based on the historical state of charge and historical current value at historical moments. The historical moment is the end moment of the target historical detection stage, and the target historical detection stage is the previous detection stage of the current detection stage.

[0009] According to one embodiment of this application, before obtaining a first charge estimate based on first operating parameters using a target time-series observation model, the method includes: The second operating parameter of the historical detection phase and the historical measured charge values ​​are used as the training dataset; the number of historical detection phases is at least 1. Preprocess the training dataset; The target time series observation model is trained based on the training dataset after preprocessing.

[0010] According to one embodiment of this application, preprocessing operations are performed on the training dataset, including: For each historical measured charge value, if the historical measured charge value is full charge and is not the first full charge, a correction operation is performed on the historical measured charge value based on the second operating parameter.

[0011] According to one embodiment of this application, training a target time-series observation model based on a preprocessed training dataset includes: The second operating parameter of each historical detection stage is input into the target time series observation model to obtain the estimated state of charge of the historical detection stage; Based on the estimated state of charge and the historical measured charge values ​​from the historical detection phase, a target loss function is constructed to fine-tune the target time-series observation model.

[0012] Secondly, this application provides a battery state of charge estimation device, comprising: The first acquisition module is used to acquire the first operating parameters of the target battery in the current detection stage through the battery management unit; The second acquisition module is used to acquire the first charge estimate based on the first operating parameters through the target time series observation model; the target time series observation model is used to execute the PITS algorithm. The filtering module is used to correct the first charge estimate based on the target filtering algorithm and obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage.

[0013] According to the battery state of charge estimation device of this application, the first operating parameters of the target battery in the current detection stage are obtained through the battery management unit; a first charge estimate is obtained based on the first operating parameters through the target time series observation model; the target time series observation model is used to execute the PITS algorithm; the first charge estimate is corrected based on the target filtering algorithm to obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage, and the first charge estimate obtained by the target time series observation model based on the first operating parameters of the target battery is more in line with the operating conditions of the target battery in the current detection stage, and the noise influence is eliminated by the target filtering algorithm to improve the accuracy of the target battery state of charge estimation.

[0014] According to one embodiment of this application, the filtering module includes: The first acquisition unit is used to acquire a second charge estimate based on the first operating parameters through the battery management unit; The second acquisition unit is used to acquire the third charge estimate through the ampere-hour integration algorithm; The filtering unit is used to correct the first charge estimate based on the second charge estimate and the third charge estimate using the target filtering algorithm, so as to obtain the target state of charge of the target battery at the current moment.

[0015] According to one embodiment of this application, the second acquisition unit is used for: The third charge estimate is obtained by using the ampere-hour integration algorithm based on the historical state of charge and historical current value at historical moments. The historical moment is the end moment of the target historical detection stage, and the target historical detection stage is the previous detection stage of the current detection stage.

[0016] According to one embodiment of this application, the battery state of charge estimation device further includes: A determination module is used to determine the second operating parameters of the historical detection phase and the historical measured charge values ​​as the training dataset; the number of historical detection phases is at least 1. The processing module is used for preprocessing the training dataset; The training module is used to train the target time series observation model based on the training dataset after preprocessing.

[0017] Thirdly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the battery state-of-charge estimation method described in the first aspect.

[0018] Fourthly, this application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the battery state-of-charge estimation method described in the first aspect.

[0019] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the battery state-of-charge estimation method described in the first aspect.

[0020] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0021] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is one of the flowcharts illustrating the battery state-of-charge estimation method provided in the embodiments of this application; Figure 2 This is the second flowchart illustrating the battery state of charge estimation method provided in the embodiments of this application; Figure 3 This is the third flowchart illustrating the battery state-of-charge estimation method provided in the embodiments of this application; Figure 4 This is a schematic diagram of the battery state of charge estimation device provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0023] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0024] The battery state of charge estimation method and battery state of charge estimation device provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0025] Among them, the battery state of charge estimation method can be applied to the terminal, and can be executed by the hardware or software in the terminal.

[0026] The terminal includes, but is not limited to, portable communication devices such as mobile phones or tablets with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads). It should also be understood that, in some embodiments, the terminal may not be a portable communication device, but rather a desktop computer with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads).

[0027] The following embodiments describe a terminal including a display and a touch-sensitive surface. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and joystick.

[0028] The battery state of charge estimation method provided in this application embodiment can be executed by an electronic device or a functional module or entity in an electronic device that can implement the battery state of charge estimation method. The electronic devices mentioned in this application embodiment include, but are not limited to, mobile phones, tablets, computers, cameras and wearable devices. The battery state of charge estimation method provided in this application embodiment is described below using an electronic device as the execution subject.

[0029] like Figure 1 As shown, the battery state of charge estimation method includes steps 110, 120 and 130.

[0030] Step 110: Obtain the first operating parameters of the target battery in the current detection stage through the battery management unit.

[0031] In practical implementation, the target battery can be a lithium-ion battery (such as a lithium iron phosphate battery, a ternary lithium battery, etc.) or any other theoretically feasible battery. The target battery can be a single cell or a battery pack; this application does not impose specific restrictions in this regard.

[0032] In some embodiments, the operating parameters of the target battery can be obtained through a Battery Management System (BMS) based on a preset detection cycle. The preset detection cycle can be the detection time of a detection phase. The operating parameters may include the total battery pack voltage, highest single-cell voltage, lowest single-cell voltage, current, highest temperature, and lowest temperature of the target battery during that detection phase.

[0033] In actual execution, the first operating data may include data such as the total battery pack voltage, highest single cell voltage, lowest single cell voltage, current, highest temperature, and lowest temperature of the target battery at the current testing stage.

[0034] In some embodiments, after obtaining the first operating parameters, preprocessing operations can be performed on the first operating parameters. Preprocessing operations may include normalization, outlier removal, etc.

[0035] Step 120: Obtain the first charge estimate based on the first operating parameters using the target time series observation model; the target time series observation model is used to execute the PITS algorithm.

[0036] In actual implementation, the target time series observation model can be a pre-trained model, or it can be a model that executes the Part Independence of Time Series (PITS) algorithm.

[0037] In some embodiments, before obtaining the first charge estimate based on the first operating parameters through the target time-series observation model, the target time-series observation model can be pre-trained based on the operating parameters of the target battery's historical detection phase.

[0038] In some embodiments, the first operating parameters can be used as input to the target time-series observation model. The target time-series observation model can obtain the state of charge observation value of the target battery in the current detection stage based on the data such as the total battery pack voltage, highest single cell voltage, lowest single cell voltage, current, highest temperature, and lowest temperature of the target battery in the current detection stage, and obtain the first charge estimate value based on the state of charge observation value.

[0039] In some embodiments, the first charge estimate can be obtained based on the following formula: ; in, This represents the first charge estimate in the current detection phase. This represents the observed state of charge during the current detection phase. This indicates the voltage measurement value at the current detection stage. This indicates the current measurement value at the current detection stage. This indicates the battery temperature measurement value at the current testing stage. Indicates observation noise. Measuring noise It follows a normal distribution.

[0040] Step 130: Based on the target filtering algorithm, correct the first charge estimate and obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage.

[0041] In actual implementation, the target filtering algorithm can be a Kalman filtering algorithm, such as the Unscented Kalman Filter (UKF) algorithm, or any other theoretically feasible filtering algorithm. This application does not impose any specific restrictions on this.

[0042] In some embodiments, the third charge estimate of the target battery at the current detection stage can be obtained by the ampere-hour integration algorithm, and the first charge estimate can be corrected based on the third charge estimate by the target filtering algorithm to obtain the target state of charge of the target battery at the current moment.

[0043] In some embodiments, after obtaining the target state of charge at the current moment, the target state of charge at the current moment can be used as the input to the ampere-hour integration algorithm.

[0044] According to the battery state of charge estimation method of this application embodiment, the battery management unit obtains the first operating parameters of the target battery in the current detection stage; the target time series observation model obtains the first charge estimate based on the first operating parameters; the target time series observation model is used to execute the PITS algorithm; the first charge estimate is corrected based on the target filtering algorithm to obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage, and the first charge estimate obtained by the target time series observation model based on the first operating parameters of the target battery is more in line with the operating conditions of the target battery in the current detection stage, and the target filtering algorithm eliminates the influence of noise to improve the accuracy of the target battery state of charge estimation.

[0045] In some embodiments, the battery management unit obtains a second charge estimate based on the first operating parameters; obtains a third charge estimate using an ampere-hour integration algorithm; and corrects the first charge estimate using the second and third charge estimates using a target filtering algorithm to obtain the target state of charge of the target battery at the current moment.

[0046] Generally, the battery management unit (BMU) uses the highest single-cell voltage for charge estimation when the target battery is charging, and the lowest single-cell voltage for charge estimation when the target battery is discharging. However, since the battery alternates between charging and discharging during operation, the charge estimation by the BMU is affected by the inconsistency of single-cell voltages. In some embodiments, this application can obtain the voltage difference of the target battery at the current detection stage based on the lowest and highest single-cell voltages, and then obtain a second charge estimate by the BMU based on the voltage difference.

[0047] In some embodiments, the pressure difference of the target battery at the current detection stage can be obtained based on the following formula: ; in, For pressure difference, This is the highest single-unit voltage. This is the lowest unit voltage.

[0048] In some embodiments, an ampere-hour integration algorithm can be used to obtain a third charge estimate based on the state of charge and operating parameters of the target battery during historical detection phases.

[0049] In actual implementation, the third charge estimate includes the charge estimate at each moment in the current detection phase.

[0050] In some embodiments, the target filtering algorithm may be an unscented Kalman filter algorithm.

[0051] In some embodiments, a target filtering algorithm can be used to iteratively correct the first charge estimate based on the second charge estimate and the charge estimate (i.e., the third charge estimate) obtained at each moment of the current detection stage through the ampere-hour integration algorithm, so as to obtain the target state of charge of the target battery at the current moment.

[0052] According to the battery state of charge estimation method of this application embodiment, the battery management unit obtains the first operating parameters of the target battery in the current detection stage; the target time series observation model obtains the first charge estimate based on the first operating parameters; the target time series observation model is used to execute the PITS algorithm; the battery management unit obtains the second charge estimate based on the first operating parameters; the ampere-hour integration algorithm obtains the third charge estimate; the target filtering algorithm corrects the first charge estimate based on the second and third charge estimates to obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage, and the first charge estimate obtained by the target time series observation model based on the first operating parameters of the target battery is more consistent with the operating conditions of the target battery in the current detection stage, and the target filtering algorithm eliminates the influence of noise to improve the accuracy of the target battery state of charge estimation.

[0053] In some embodiments, the third charge estimate is obtained by using the ampere-hour integration algorithm based on the historical state of charge and historical current value at a historical moment; the historical moment is the end moment of the target historical detection stage, and the target historical detection stage is the previous detection stage of the current detection stage.

[0054] In actual execution, the state of charge output by the target filtering algorithm in each detection stage can be stored, and this state of charge can be used as the input of the ampere-hour integration algorithm.

[0055] In some embodiments, the third charge estimate can be obtained based on the following formula: ; in, For the current of a historical moment, For the testing cycle, For battery capacity, For Coulomb efficiency, Historical charge state For Gaussian process noise, and This represents the estimated value of the third charge.

[0056] According to the battery state of charge estimation method of this application embodiment, the battery management unit obtains the first operating parameters of the target battery in the current detection stage; the target time series observation model obtains a first charge estimate based on the first operating parameters; the target time series observation model is used to execute the PITS algorithm; the battery management unit obtains a second charge estimate based on the first operating parameters; the ampere-hour integration algorithm obtains a third charge estimate based on the historical state of charge and historical current values ​​at historical times; the target filtering algorithm corrects the first charge estimate based on the second and third charge estimates to obtain the target state of charge of the target battery at the current time; the current time is the end time of the current detection stage, and the first charge estimate obtained by the target time series observation model based on the first operating parameters of the target battery is more consistent with the operating conditions of the target battery in the current detection stage, and the target filtering algorithm eliminates the influence of noise to improve the accuracy of the target battery state of charge estimation.

[0057] In some embodiments, before obtaining the first charge estimate based on the first operating parameters through the target time-series observation model, the second operating parameters of the historical detection stage and the historical measured charge values ​​can be determined as the training dataset; the number of historical detection stages is at least 1; the training dataset is preprocessed; and the target time-series observation model is trained based on the preprocessed training dataset.

[0058] In practice, preprocessing operations may include normalization. In some embodiments, after the training dataset is determined, each class of second running parameters in the training dataset may be normalized. For example, the current in the training dataset may be normalized.

[0059] In some embodiments, each type of second operating parameter can be normalized based on the following formula: ; in, This refers to the i-th normalized second operating parameter in this category. For the i-th second running parameter in this type of second running parameter, This represents the minimum value among the second running parameters of this class. This indicates the maximum value among the second running parameters of this class.

[0060] In practice, the task of the target time-series observation model is to learn the segment embedding function for each time series in the training dataset. The target time-series observation model executing the PITS algorithm employs channel independence and segment independence (PI), meaning that all channels (parameters from different sensors that are input variables into the model) and segments share the same model weights and are embedded independently. The model utilizes an MLP as the PI architecture; the Linear model consists of a single fully connected (FC) layer, and the MLP consists of a two-layer MLP with ReLU. The FC layers process the segment representation for segment reconstruction.

[0061] In some embodiments, the sum of reconstruction loss and hierarchical contrast loss can be determined as the target loss, and the target time series observation model can be adjusted based on the target loss.

[0062] According to the battery state of charge estimation method of this application embodiment, before obtaining the first charge estimate value based on the first operating parameters through the target time series observation model, the second operating parameters of the historical detection stage and the historical measured charge values ​​can be determined as the training dataset; the number of historical detection stages is at least 1; the training dataset is preprocessed; based on the preprocessed training dataset, the target time series observation model is trained to make the target time series observation model more adaptable to operating conditions, so as to achieve the purpose of estimating the state of charge of the target battery under different temperature changes and complex operating conditions, thereby improving the accuracy of the state of charge estimation of the target battery.

[0063] In some embodiments, for each historical measured charge value, if the historical measured charge value is full charge and is not the first full charge, a correction operation is performed on the historical measured charge value based on the second operating parameter.

[0064] In some embodiments, after obtaining the training dataset, the historical measured charge values ​​for each historical detection stage in the training dataset are corrected.

[0065] In some embodiments, for each historical measured charge value, if the historical measured charge value is full charge (i.e., historical measured charge value = 100%) and the historical measured charge value is the first full charge in the training dataset, the historical measured charge value is not corrected.

[0066] In some embodiments, for each historical measured charge value, if the historical measured charge value is a full charge (i.e., historical measured charge value = 100%) and the historical measured charge value is not the first full charge in the training dataset (e.g., the historical measured charge value is the third full charge in the training dataset), the historical measured charge value is corrected based on the historical current.

[0067] In some embodiments, the f-th historical measured charge value of a full charge appears in the training dataset. In this case, obtain the current charging cycle capacity. The measured change in charge is obtained based on the following formula: ; in, This represents the measured change in charge. Indicates the time when the first full charge appears. This represents the historical measured charge value of the f-th full charge. The time of its appearance, Represents the historical current variation function. This indicates the current charging cycle capacity.

[0068] The corrected historical measured charge values ​​are obtained based on the following formula: ; in, This represents the corrected historical measured charge value. This represents the correction value for the initial historical measured charge value. This represents the initial historical measured charge value. This represents the measured change in charge.

[0069] According to the battery state of charge estimation method of this application embodiment, before obtaining the first charge estimate value based on the first operating parameters through the target time series observation model, the second operating parameters of the historical detection stage and the historical measured charge values ​​can be determined as the training dataset; the number of historical detection stages is at least 1; the training dataset is preprocessed; based on the preprocessed training dataset, the target time series observation model is trained to make the target time series observation model more adaptable to operating conditions, so as to achieve the purpose of estimating the state of charge of the target battery under different temperature changes and complex operating conditions, thereby improving the accuracy of the state of charge estimation of the target battery.

[0070] In some embodiments, the second operating parameters of each historical detection stage are input into the target time series observation model to obtain the estimated state of charge of the historical detection stage; based on the estimated state of charge and the historical measured charge values ​​of the historical detection stage, a target loss function is constructed to fine-tune the target time series observation model.

[0071] In some embodiments, the second operating parameters of each historical detection stage can be input into the target time series observation model. Based on the second operating parameters, the target time series observation model obtains the estimated state of charge at each historical moment of the historical detection stage, obtains the error between the estimated state of charge at each historical moment and the historical measured state of charge, and uses the sum of the errors of all historical moments of the historical detection stage as the target loss function to fine-tune the target time series observation model based on the target loss function.

[0072] In some embodiments, the target loss function can be obtained based on the following formula: ; in, This represents the number of historical moments during the historical monitoring phase. This represents the estimated state of charge at the i-th historical moment. This represents the historical measured charge value at the i-th historical moment.

[0073] According to the battery state of charge estimation method of this application embodiment, before obtaining the first charge estimate value based on the first operating parameters through the target time-series observation model, the second operating parameters of the historical detection stage and the historical measured charge values ​​can be determined as the training dataset; the number of historical detection stages is at least 1; the training dataset is preprocessed; the second operating parameters of each historical detection stage are input into the target time-series observation model, and the target time-series observation model obtains the estimated state of charge at each historical moment of the historical detection stage based on the second operating parameters, obtains the error between the estimated state of charge at each historical moment and the historical measured charge value, and uses the sum of the errors of all historical moments of the historical detection stage as the target loss function, so as to fine-tune the target time-series observation model based on the target loss function, so as to make the target time-series observation model more adaptable to the operating conditions, and achieve the purpose of estimating the state of charge of the target battery under different temperature changes and complex operating conditions, so as to improve the accuracy of the state of charge estimation of the target battery.

[0074] To better understand the battery state-of-charge estimation method provided in the embodiments of this application, further explanation is provided below. It should be understood that the following discussion is merely exemplary.

[0075] This application provides a method for estimating the state of charge of a battery, the specific steps of which are as follows: Figure 2 As shown: In some embodiments, the battery state-of-charge estimation method can be performed by an edge device.

[0076] Step 210: Determine the second operating parameters of the historical detection stage and the historical measured charge values ​​as the training dataset; the number of historical detection stages is at least 1; perform preprocessing operations on the training dataset; train the target time series observation model based on the preprocessed training dataset.

[0077] In practice, preprocessing operations may include normalization. In some embodiments, after the training dataset is determined, each class of second running parameters in the training dataset may be normalized. For example, the current in the training dataset may be normalized.

[0078] In some embodiments, each type of second operating parameter can be normalized based on the following formula: ; in, This refers to the i-th normalized second operating parameter in this category. For the i-th second running parameter in this type of second running parameter, This represents the minimum value among the second running parameters of this class. This indicates the maximum value among the second running parameters of this class.

[0079] In some embodiments, for each historical measured charge value, if the historical measured charge value is full charge and is not the first full charge, a correction operation is performed on the historical measured charge value based on the second operating parameter.

[0080] In some embodiments, after obtaining the training dataset, the historical measured charge values ​​for each historical detection stage in the training dataset are corrected.

[0081] In some embodiments, for each historical measured charge value, if the historical measured charge value is full charge (i.e., historical measured charge value = 100%) and the historical measured charge value is the first full charge in the training dataset, the historical measured charge value is not corrected.

[0082] In some embodiments, for each historical measured charge value, if the historical measured charge value is a full charge (i.e., historical measured charge value = 100%) and the historical measured charge value is not the first full charge in the training dataset (e.g., the historical measured charge value is the third full charge in the training dataset), the historical measured charge value is corrected based on the historical current.

[0083] In some embodiments, the f-th historical measured charge value of a full charge appears in the training dataset. In this case, obtain the current charging cycle capacity. The measured change in charge is obtained based on the following formula: ; in, This represents the measured change in charge. Indicates the time when the first full charge appears. This represents the historical measured charge value of the f-th full charge. The time of its appearance, Represents the historical current variation function. This indicates the current charging cycle capacity.

[0084] The corrected historical measured charge values ​​are obtained based on the following formula: ; in, This represents the corrected historical measured charge value. This represents the correction value for the initial historical measured charge value. This represents the initial historical measured charge value. This represents the measured change in charge.

[0085] In some embodiments, the second operating parameters of each historical detection stage are input into the target time series observation model to obtain the estimated state of charge of the historical detection stage; based on the estimated state of charge and the historical measured charge values ​​of the historical detection stage, a target loss function is constructed to fine-tune the target time series observation model.

[0086] In some embodiments, the second operating parameters of each historical detection stage can be input into the target time series observation model. Based on the second operating parameters, the target time series observation model obtains the estimated state of charge at each historical moment of the historical detection stage, obtains the error between the estimated state of charge at each historical moment and the historical measured state of charge, and uses the sum of the errors of all historical moments of the historical detection stage as the target loss function to fine-tune the target time series observation model based on the target loss function.

[0087] In some embodiments, the target loss function can be obtained based on the following formula: ; in, This represents the number of historical moments during the historical monitoring phase. This represents the estimated state of charge at the i-th historical moment. This represents the historical measured charge value at the i-th historical moment.

[0088] Step 220: Obtain the first operating parameters of the target battery in the current detection stage through the battery management unit.

[0089] In practical implementation, the target battery can be a lithium-ion battery (such as a lithium iron phosphate battery, a ternary lithium battery, etc.) or any other theoretically feasible battery. The target battery can be a single cell or a battery pack; this application does not impose specific restrictions in this regard.

[0090] In some embodiments, the operating parameters of the target battery can be obtained through a Battery Management System (BMS) based on a preset detection cycle. The preset detection cycle can be the detection time of a detection phase. The operating parameters may include the total battery pack voltage, highest single-cell voltage, lowest single-cell voltage, current, highest temperature, and lowest temperature of the target battery during that detection phase.

[0091] In actual execution, the first operating data may include data such as the total battery pack voltage, highest single cell voltage, lowest single cell voltage, current, highest temperature, and lowest temperature of the target battery at the current testing stage.

[0092] In some embodiments, after obtaining the first operating parameters, preprocessing operations can be performed on the first operating parameters. Preprocessing operations may include normalization, outlier removal, etc.

[0093] Step 230: Obtain the first charge estimate based on the first operating parameters using the target time series observation model; the target time series observation model is used to execute the PITS algorithm.

[0094] In actual implementation, the target time series observation model can be a pre-trained model, or it can be a model that executes the Part Independence of Time Series (PITS) algorithm.

[0095] In some embodiments, before obtaining the first charge estimate based on the first operating parameters through the target time-series observation model, the target time-series observation model can be pre-trained based on the operating parameters of the target battery's historical detection phase.

[0096] In some embodiments, the first operating parameters can be used as input to the target time-series observation model. The target time-series observation model can obtain the state of charge observation value of the target battery in the current detection stage based on the data such as the total battery pack voltage, highest single cell voltage, lowest single cell voltage, current, highest temperature, and lowest temperature of the target battery in the current detection stage, and obtain the first charge estimate value based on the state of charge observation value.

[0097] In some embodiments, the first charge estimate can be obtained based on the following formula: ; in, This represents the first charge estimate in the current detection phase. This represents the observed state of charge during the current detection phase. This indicates the voltage measurement value at the current detection stage. This indicates the current measurement value at the current detection stage. This indicates the battery temperature measurement value at the current testing stage. Measuring noise It follows a normal distribution.

[0098] Step 240: Obtain a second charge estimate based on the first operating parameters through the battery management unit.

[0099] Generally, the battery management unit (BMU) uses the highest single-cell voltage for charge estimation when the target battery is charging, and the lowest single-cell voltage for charge estimation when the target battery is discharging. However, since the battery alternates between charging and discharging during operation, the charge estimation by the BMU is affected by the inconsistency of single-cell voltages. In some embodiments, this application can obtain the voltage difference of the target battery at the current detection stage based on the lowest and highest single-cell voltages, and then obtain a second charge estimate by the BMU based on the voltage difference.

[0100] In some embodiments, the pressure difference of the target battery at the current detection stage can be obtained based on the following formula: ; in, For pressure difference, This is the highest single-unit voltage. This is the lowest unit voltage.

[0101] Step 250: Using the ampere-hour integration algorithm, obtain the third charge estimate based on the historical state of charge and historical current value at historical moments; the historical moment is the end moment of the target historical detection stage, and the target historical detection stage is the previous detection stage of the current detection stage.

[0102] In actual execution, the state of charge output by the target filtering algorithm in each detection stage can be stored, and this state of charge can be used as the input of the ampere-hour integration algorithm.

[0103] In some embodiments, the third charge estimate can be obtained based on the following formula: ; in, For the current of a historical moment, For the testing cycle, For battery capacity, For Coulomb efficiency, Historical charge state For Gaussian process noise, process noise The normal distribution and This represents the estimated value of the third charge.

[0104] Step 260: Based on the target filtering algorithm, the first charge estimate is corrected using the second charge estimate and the third charge estimate to obtain the target state of charge of the target battery at the current moment.

[0105] In some embodiments, a target filtering algorithm can be used to iteratively correct the first charge estimate based on the second charge estimate and the charge estimate (i.e., the third charge estimate) obtained at each moment of the current detection stage through the ampere-hour integration algorithm, so as to obtain the target state of charge of the target battery at the current moment.

[0106] In some embodiments, such as Figure 3 As shown, after obtaining the target state of charge at the current moment, the target state of charge at the current moment can be used as the input of the ampere-hour integration algorithm.

[0107] This application also provides a battery state of charge estimation device.

[0108] like Figure 4 As shown, the battery state of charge estimation device 400 includes: a first acquisition module 410, a second acquisition module 420, and a filtering module 430.

[0109] The first acquisition module 410 is used to acquire the first operating parameters of the target battery in the current detection stage through the battery management unit; The second acquisition module 420 is used to acquire a first charge estimate based on the first operating parameters through the target time series observation model; the target time series observation model is used to execute the PITS algorithm. The filtering module 430 is used to correct the first charge estimate based on the target filtering algorithm and obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage.

[0110] According to the battery state of charge estimation device of this application, the first operating parameters of the target battery in the current detection stage are obtained through the battery management unit; a first charge estimate is obtained based on the first operating parameters through the target time series observation model; the target time series observation model is used to execute the PITS algorithm; the first charge estimate is corrected based on the target filtering algorithm to obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage, and the first charge estimate obtained by the target time series observation model based on the first operating parameters of the target battery is more in line with the operating conditions of the target battery in the current detection stage, and the noise influence is eliminated by the target filtering algorithm to improve the accuracy of the target battery state of charge estimation.

[0111] In some embodiments, the filtering module 430 includes: The first acquisition unit is used to acquire a second charge estimate based on the first operating parameters through the battery management unit; The second acquisition unit is used to acquire the third charge estimate through the ampere-hour integration algorithm; The filtering unit is used to correct the first charge estimate based on the second charge estimate and the third charge estimate using the target filtering algorithm, so as to obtain the target state of charge of the target battery at the current moment.

[0112] In some embodiments, the second acquisition unit is used for: The third charge estimate is obtained by using the ampere-hour integration algorithm based on the historical state of charge and historical current value at historical moments. The historical moment is the end moment of the target historical detection stage, and the target historical detection stage is the previous detection stage of the current detection stage.

[0113] In some embodiments, the battery state of charge estimation device 400 further includes: A determination module is used to determine the second operating parameters of the historical detection phase and the historical measured charge values ​​as the training dataset; the number of historical detection phases is at least 1. The processing module is used for preprocessing the training dataset; The training module is used to train the target time series observation model based on the training dataset after preprocessing.

[0114] In some embodiments, the processing module includes: The correction unit is used to perform a correction operation on each historical measured charge value based on the second operating parameter, provided that the historical measured charge value is full charge and is not the first full charge.

[0115] In some embodiments, the training module includes: The third acquisition unit is used to input the second operating parameters of each historical detection stage into the target time series observation model to obtain the estimated state of charge of the historical detection stage. The fine-tuning unit is used to construct a target loss function based on the estimated state of charge and the historical measured charge values ​​from the historical detection phase, so as to fine-tune the target time-series observation model.

[0116] The battery state-of-charge estimation device in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the device.

[0117] The battery state-of-charge estimation device in this application embodiment can be a device with an operating system. This operating system can be a Microsoft (Windows) operating system, an Android operating system, an iOS operating system, or other possible operating systems; this application embodiment does not specifically limit it.

[0118] The battery state-of-charge estimation device 400 provided in this application embodiment can achieve... Figures 1 to 3 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0119] In some embodiments, such as Figure 5 As shown, this application embodiment also provides an electronic device 500, including a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501. When the program is executed by the processor 501, it implements the various processes of the above-described battery state of charge estimation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0120] It should be noted that the computer equipment in this application embodiment includes the mobile electronic equipment and non-mobile electronic equipment described above.

[0121] This application also provides a non-transitory computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described battery state of charge estimation method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0122] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0123] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described battery state of charge estimation method.

[0124] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0125] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described battery state of charge estimation method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0126] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0127] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0128] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0129] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0130] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions 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 one or more embodiments or examples.

[0131] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for estimating the state of charge of a battery, characterized in that, include: The battery management unit obtains the first operating parameters of the target battery at the current testing stage. Based on the first operating parameters, the first charge estimate is obtained using the target time series observation model; the target time series observation model is used to execute the PITS algorithm. Based on the target filtering algorithm, the first charge estimate is corrected to obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage.

2. The battery state-of-charge estimation method according to claim 1, characterized in that, The step of correcting the first charge estimate based on the target filtering algorithm to obtain the target state of charge of the target battery at the current moment includes: The battery management unit obtains a second charge estimate based on the first operating parameters. The estimated value of the third charge is obtained by using the ampere-hour integration algorithm; Based on the target filtering algorithm, the first charge estimate is corrected using the second charge estimate and the third charge estimate to obtain the target state of charge of the target battery at the current moment.

3. The battery state-of-charge estimation method according to claim 2, characterized in that, The step of obtaining the third charge estimate using the ampere-hour integration algorithm includes: The third charge estimate is obtained by using the ampere-hour integration algorithm based on the historical state of charge and historical current value at historical moments; the historical moment is the end moment of the target historical detection stage, and the target historical detection stage is the previous detection stage of the current detection stage.

4. The battery state-of-charge estimation method according to claim 1, characterized in that, Before obtaining the first charge estimate based on the first operating parameters using the target time-series observation model, the method includes: The second operating parameters of the historical detection phase and the historical measured charge values ​​are used as the training dataset; the number of the historical detection phases is at least 1. The training dataset is preprocessed. The target time series observation model is trained based on the training dataset after preprocessing.

5. The battery state-of-charge estimation method according to claim 4, characterized in that, The preprocessing operation on the training dataset includes: For each of the historical measured charge values, if the historical measured charge value is full charge but not the first full charge, a correction operation is performed on the historical measured charge value based on the second operating parameter.

6. The battery state-of-charge estimation method according to claim 4, characterized in that, The training of the target time-series observation model based on the preprocessed training dataset includes: The second operating parameters of each historical detection stage are input into the target time series observation model to obtain the estimated state of charge of the historical detection stage. Based on the estimated state of charge and the historical measured charge values ​​during the historical detection phase, a target loss function is constructed to fine-tune the target time-series observation model.

7. A battery state of charge estimation device, characterized in that, include: The first acquisition module is used to acquire the first operating parameters of the target battery in the current detection stage through the battery management unit; The second acquisition module is used to acquire a first charge estimate based on the first operating parameters using a target time series observation model; the target time series observation model is used to execute the PITS algorithm. The filtering module is used to correct the first charge estimate based on the target filtering algorithm to obtain the target state of charge of the target battery at the current moment; the current moment is the end moment of the current detection stage.

8. The battery state-of-charge estimation device according to claim 7, characterized in that, The filtering module includes: The first acquisition unit is used to acquire a second charge estimate based on the first operating parameters through the battery management unit; The second acquisition unit is used to acquire the third charge estimate through the ampere-hour integration algorithm; The filtering unit is used to correct the first charge estimate based on the second charge estimate and the third charge estimate using a target filtering algorithm, so as to obtain the target state of charge of the target battery at the current moment.

9. The battery state-of-charge estimation device according to claim 8, characterized in that, The second acquisition unit is used for: The third charge estimate is obtained by using the ampere-hour integration algorithm based on the historical state of charge and historical current value at historical moments. The historical moment is the end moment of the target historical detection stage, and the target historical detection stage is the previous detection stage of the current detection stage.

10. The battery state-of-charge estimation device according to claim 7, characterized in that, The device further includes: A determination module is used to determine the second operating parameters of the historical detection phase and the historical measured charge values ​​as a training dataset; the number of the historical detection phases is at least one. The processing module is used to perform preprocessing operations on the training dataset; The training module is used to train the target time series observation model based on the training dataset after preprocessing.

Images