Apparatus and method for battery SOC estimation

Abstract

An apparatus for estimating a battery state of charge (SOC) includes a pre-processing unit (200) configured to detect operating parameters of the battery and filter at least a portion of the parameters to generate filtered parameters; a SOC estimation unit (300) configured to calculate a nominal SOC using a first neural network based on the operating parameters and the filtered parameters; a validity estimation unit (400) configured to estimate a validity value indicative of the validity of the nominal SOC output by the SOC estimation unit (300) based on the operating parameters and the filtered parameters; and a SOC Kalman filter (500) configured to perform a Kalman filtering algorithm based on the operating parameters, the transmitted nominal SOC and the validity value, thereby outputting an estimated SOC of the battery.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This disclosure claims priority to patent application Ser. No. 17 / 750,654, filed with the U.S. Patent and Trademark Office on May 23, 2022, and entitled "Apparatus and Method for Battery SOC Estimation." [Technical field]

[0002] FIELD OF THE DISCLOSURE Embodiments of the present disclosure relate generally to the field of battery technology, and more particularly to an apparatus and method for estimating battery state of charge (SOC). [Background technology]

[0003] This section introduces material that may be helpful in improving the understanding of the present disclosure, and therefore, the statements in this section should be read in this light, and should not be construed as admissions that material is or is not in the prior art.

[0004] Secondary (rechargeable) batteries are used in energy storage applications in personal portable electronic devices, electric vehicles, and power systems. Battery SOC is defined as the percentage of remaining capacity of the battery relative to its maximum capacity and is a key value calculated by a Battery Management System (BMS). The BMS uses SOC to indicate when the battery needs to be recharged, to extend battery life by preventing overcharging or over-discharging, and in electric vehicle applications to indicate the driving range. Battery SOC cannot be measured directly and must be estimated using available measurements.

[0005] One common method for estimating battery SOC is the coulomb counting method with open circuit voltage (OCV) and end-of-charge correction. In this method, the BMS calculates the SOC based on the net charge extracted from the battery during operation by integrating the current drawn from the battery (i.e., counting the coulombs extracted). If the battery voltage reaches an equilibrium state after a sufficiently long rest period, the equilibrium voltage (OCV) can be used to correct the SOC based on the OCV vs. SOC relationship. The SOC can also be corrected by setting it to 100% when the battery voltage reaches its rated value at the end of a given charging sequence. The advantage of this method is its relative simplicity.

[0006] There has been much research into developing battery SOC estimation methods based on the Kalman filter algorithm used in conjunction with the equivalent circuit model (ECM) of the battery. Researchers have reported methods based on the extended Kalman filter (EKF), the unscented Kalman filter (UKF), and the sigma point Kalman filter (SPKF), collectively referred to as "xKF". In general, these methods are capable of accurate estimation as long as the covariance parameters of the ECM and the corresponding xKF are accurate.

[0007] The researchers also report a battery SOC estimation method using the xKF approach combined with a neural network SOC model, which can be developed efficiently and reliably using a commercially available neural network optimization package. Summary of the Invention [Problem to be solved by the invention]

[0008] The inventors of the present disclosure have discovered that each of the existing battery SOC estimation methods has several limitations.

[0009] Coulomb counting methods are known to be inaccurate under certain conditions. If the initial SOC estimate is incorrect, the SOC estimation error will persist until the conditions for proper OCV or end-of-charge SOC correction are met. Furthermore, integrating current for a long period of time without SOC correction can result in an inaccurate SOC due to the accumulation of current measurement errors.

[0010] For methods based on xKF used in conjunction with ECM, significant engineering resources may be required to achieve accuracy targets. First, the required ECM prediction accuracy can be achieved by scheduling ECM parameters based on operating zones. Operating zones may be defined using sensed physical quantities such as temperature and current and calculated values ​​such as SOC. Second, if ECM prediction accuracy is known to vary with operating zones, the xKF covariance parameters may be scheduled according to operating zones. The process of constructing such parameter schedules often requires significant engineering development resources.

[0011] Regarding how the xKF approach can be used in conjunction with a neural network SOC model, because the model's prediction accuracy can vary by operating zone (e.g., it can be inaccurate in "flat" voltage zones where SOC does not correlate well with available measurements), the covariance parameters of the xKF may be scheduled according to operating zone to achieve accuracy targets. Development of such parameter schedules may require significant engineering resources. [Means for solving the problem]

[0012] Generally, embodiments of the present disclosure provide an apparatus for estimating a battery SOC, a method for estimating a battery SOC, and a method for calculating parameters used in estimating a battery SOC. The present disclosure aims to accurately estimate the battery SOC using a systematic and efficient development approach.

[0013] As a first aspect, a pre-processing unit (200) configured to detect operating parameters of the battery and filter at least a portion of the parameters to generate filtered parameters; a SOC estimation unit (300) configured to calculate a nominal SOC using a first neural network based on the operating parameters and the filtered parameters sent from the pre-processing unit; a validity estimation unit (400) configured to estimate a validity value indicative of the validity of the nominal SOC output by the SOC estimation unit (300) based on the operational parameters and the filtered parameters transmitted from the pre-processing unit; and a SOC Kalman filter (500) configured to perform a Kalman filtering algorithm based on the operating parameters transmitted from the pre-processing unit, the nominal SOC transmitted from the SOC estimation unit, and the validity value transmitted from the validity estimation unit, thereby outputting an estimated SOC of the battery.

[0014] As a second aspect, detecting operating parameters of the battery and filtering at least a portion of the parameters to generate filtered parameters; calculating a nominal SOC using a first neural network based on the operating parameters and the filtered parameters; calculating a validity value indicative of the validity of the nominal SOC based on the operating parameters and the filtered parameters; A method for estimating a battery state of charge (SOC) is provided, the method comprising: executing a Kalman filtering algorithm with a SOC Kalman filter based on operating parameters, a nominal SOC and a validity value, thereby outputting an estimated SOC of the battery.

[0015] As a third aspect, calculating a nominal SOC based on experimental data; calculating a squared nominal SOC error based on experimental data; Identifying a subset of data from the data set having a squared nominal SOC error less than a first predetermined value; A method is provided for calculating parameters used in battery state of charge (SOC) estimation, comprising: calculating a variance of the difference between true SOC and the nominal SOC for the identified subset of data, the calculated result being a parameter R used in a Kalman filtering algorithm.

[0016] According to various embodiments of the present disclosure, a first neural network is used to estimate a nominal SOC and calculate a validity value of the nominal SOC, and a SOC Kalman filter calculates an estimated SOC based on the nominal SOC and the validity value. Thus, a systematic and efficient development methodology can be used to accurately estimate a battery SOC. [Brief description of the drawings]

[0017] The above and other aspects, features, and advantages of various embodiments of the present disclosure will become more fully apparent from the following detailed description, taken by way of example in conjunction with the accompanying drawings, in which like reference numbers or letters are used to designate similar or equivalent elements, and in which the drawings are presented for a better understanding of the embodiments of the present disclosure and are not necessarily drawn to scale. [Figure 1] FIG. 1 is a block diagram that illustrates generally an apparatus for estimating the SOC of a battery according to a preferred embodiment of the present disclosure. [Diagram 2] FIG. 2 shows a schematic diagram of a pre-treatment unit according to a preferred embodiment of the present disclosure. [Diagram 3] FIG. 2 illustrates a schematic diagram of a SOC estimation unit according to a preferred embodiment of the present disclosure. [Figure 4] FIG. 2 illustrates a schematic diagram of a validity estimation unit according to a preferred embodiment of the present disclosure; [Diagram 5]FIG. 2 is a schematic diagram of a SOC Kalman filter according to a preferred embodiment of the present disclosure. [Figure 6] FIG. 2 is a block diagram that generally illustrates an apparatus for estimating the SOC of a battery according to another embodiment of the present disclosure. [Figure 7] 4 is a flowchart sequentially illustrating a procedure for calculating parameters used in SOC estimation according to a preferred embodiment of the present disclosure. [Figure 8] 1 is a flowchart of a method for estimating a battery state of charge according to an embodiment. [Figure 9] 1 is a schematic diagram of a structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] The present disclosure will be described with reference to several examples. It should be understood that these embodiments are discussed for the purpose of helping artisans to better understand and thus practice the present disclosure, and are not intended to imply any limitation on the scope of the present disclosure.

[0019] The terms "first" and "second" as used herein refer to different elements. The singular forms "a" and "an" are to be construed to include the plural unless the context clearly dictates otherwise. The terms "comprise", "includes", "have", "have", "includes" and "including" as used herein specify the presence of stated features, elements, and / or components, etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof. The term "based on" shall be construed as "based at least in part on". The terms "one embodiment" and "an embodiment" shall be construed as "at least one embodiment". The term "another embodiment" shall be construed as "at least one other embodiment". Other definitions may be expressly or impliedly included below.

[0020] (First aspect of embodiment) In a first aspect of an embodiment, an apparatus for estimating a battery state of charge (SOC) is provided.

[0021] 1 is a block diagram that illustrates a schematic diagram of an apparatus 10 for estimating a battery SOC according to an embodiment of the present disclosure. As shown in FIG. 1, the apparatus 10 includes a pre-processing unit 200, a SOC estimation unit 300, a validity estimation unit 400, and a SOC Kalman filter 500.

[0022] In at least one embodiment, pre-processing unit 200 is configured to detect operating parameters (shown in FIG. 1 ) of battery 100 and filter at least a portion of the operating parameters to generate filtered parameters. For example, the operating parameters detected by pre-processing unit 200 include current, voltage, and temperature, and the filtered parameters include a filtered current and a filtered voltage. However, embodiments are not so limited and the operating parameters and filtered parameters may be of other types.

[0023] The SOC estimation unit 300 is configured to calculate a nominal SOC using a first neural network based on the operating parameters and the filtered parameters sent from the pre-processing unit 200 .

[0024] The validity estimation unit 400 is configured to estimate a validity value based on the operating parameters and the filtered parameters sent from the pre-processing unit 200. The validity value indicates the validity of the nominal SOC output by the SOC estimation unit 300.

[0025] The SOC Kalman filter 500 is configured to perform a Kalman filtering algorithm based on the operating parameters (e.g., current) sent from the pre-processing unit 200, the nominal SOC sent from the SOC estimation unit 300, and the validity value sent from the validity estimation unit 400, and output an estimated SOC of the battery 100.

[0026] According to the first aspect of the present disclosure, a first neural network is used to estimate a nominal SOC, a validity value of the nominal SOC is calculated, and a SOC Kalman filter calculates an estimated SOC based on the nominal SOC and the validity value. Thus, a systematic and efficient development method can be used to accurately estimate a battery SOC.

[0027] 2 is a schematic diagram of a pre-processing unit 200 according to an embodiment of the present disclosure. As shown in FIG. 2, the pre-processing unit 200 includes a current detection unit 210, a voltage detection unit 220, a temperature detection unit 230, a current low-pass filter 240, and a voltage low-pass filter 250.

[0028] In at least one embodiment, the method for detecting the current, voltage and temperature of the battery 100 may refer to the related art.

[0029] The current low pass filter 240 may filter the current using a time constant of T seconds and output a filtered current. The voltage low pass filter 250 may filter the voltage using a time constant of T seconds and output a filtered voltage.

[0030] In a preferred embodiment, the current low pass filter 240 and the voltage low pass filter 250 may be implemented according to the following discretized filter calculations:

number

[0031] Here, the calculation cycle time of the current low-pass filter 240 and / or the voltage low-pass filter 250 is T s where k is the calculation cycle and u is the input signal. k , the filtered signal is x k . And the filtered signal for the next calculation cycle is x k+1 For the current low-pass filter 240, the input signal u k is the current, the filtered signal x k is the filtered current. For the voltage low pass filter 250, the input signal u k is the voltage and the filtered signal x k is the filtered voltage.

[0032] FIG. 3 is a schematic diagram of an SOC estimation unit 300 according to an embodiment of the present disclosure. A first neural network (i.e., SOC neural network) is used in the SOC estimation unit 300. As shown in FIG. 3, 310 is an input layer of the SOC neural network, for example, current, voltage, temperature, filtered current and filtered voltage are input to the input layer 310. 320 is a hidden layer of the SOC neural network. 330 is an output layer of the SOC neural network. The operation principle of the SOC neural network can be referred to the related art.

[0033] 4 is a schematic diagram of a validity estimation unit 400 according to an embodiment of the present disclosure. As shown in FIG. 4, the validity estimation unit 400 includes a squared SOC error estimation unit 410 and a validity classification circuit 450.

[0034] The squared SOC error estimation unit 410 can estimate the squared nominal SOC error using a second neural network (i.e., a squared SOC error neural network) based on the operating parameters and the filtered parameters. The squared nominal SOC error indicates the square of the difference between the true SOC and the nominal SOC.

[0035] As shown in Fig. 4, 420 is an input layer of a second neural network (i.e., a squared SOC error neural network), for example, current, voltage, temperature, filtered current and filtered voltage are input to the input layer 420. 430 is a hidden layer of the squared SOC error neural network. 440 is an output layer of the squared SOC error neural network, for example, the squared nominal SOC error is output from the output layer 440. The operation principle of the squared SOC error neural network can be referred to the related art.

[0036] 4, the validity classification circuit 450 can output a validity value based on the magnitude of the squared nominal SOC error being below a first predetermined value and the elapsed running time since the current low pass filter initialization or the voltage low pass filter initialization being greater than a second predetermined value. For example, the first predetermined value can be E 2 In a preferred embodiment, the parameter E is 1%. The second predetermined value may be 3T, where T is the time constant of the current low pass filter 240 and the voltage low pass filter 250.

[0037] For example, the validity of the nominal SOC is determined by the squared nominal SOC error E 2 If it is less than 1, and if the elapsed run time since current low pass filter initialization and / or voltage low pass filter initialization is greater than 3T, then it is set to 1 (valid). Otherwise, nominal SOC validity is set to 0 (invalid).

[0038] As shown in FIG. 4, in a preferred embodiment, the validity classification circuit 450 includes a first judgment unit 451, a second judgment unit 452, and a logic unit 453. The first judgment unit 451 can judge whether the squared nominal SOC error is below a first predetermined value. For example, if the squared nominal SOC error is below the first predetermined value, the first judgment unit 451 can output 1. The second judgment unit 452 can judge whether the elapsed execution time from the initialization of the current low pass filter and / or the initialization of the voltage low pass filter exceeds a second predetermined value. For example, if the elapsed execution time from the initialization of the current low pass filter and / or the initialization of the voltage low pass filter exceeds a second predetermined value, the second judgment unit 452 can output 1. The logic unit 453 can output a validity value according to the judgment result of the first judgment unit 451 and the judgment result of the second judgment unit 452. For example, the logic unit 453 may be an AND gate, and may output 1 if both the first judgment unit 451 and the second judgment unit 452 output 1. However, the embodiment is not limited thereto, and the validity classification circuit 450 may have other structures.

[0039] 5 is a schematic diagram of a SOC Kalman filter 500 in accordance with one embodiment of the present disclosure. The SOC Kalman filter 500 includes a gain calculator 510 and an estimated SOC calculator 520.

[0040] The gain calculator 510 may apply a gain selection unit 560 to calculate a gain value based on the validity value, a parameter Q (530) and a parameter R (540).

[0041] In a preferred embodiment of the gain selection unit 560, if the validity value indicates that the nominal SOC is valid (eg, the validity value is 1), the gain value is calculated according to a Kalman filter formulation.

number

[0042] In a preferred embodiment of the gain selection unit 560, if the validity value indicates that the nominal SOC is invalid (e.g., if the validity value is 0), the gain is set to 0. Mathematically, if the nominal SOC is invalid, this is equivalent to setting the covariance associated with the error between the nominal SOC and the true SOC to infinity.

[0043] Parameter Q (530) is a covariance related to the rate of increase of the SOC covariance if the SOC is not otherwise corrected. Parameter Q can be estimated based on a combination of factors such as current sensor accuracy, coulombic efficiency uncertainty, SOC Kalman filter calculation cycle time uncertainty, and cell capacity uncertainty.

[0044] Parameter R (540) is the covariance associated with the error between the nominal SOC and the true SOC when the validity value indicates that the nominal SOC is valid (eg, a validity value of 1).

[0045] The estimated SOC calculator 520 can calculate the estimated SOC based on the nominal SOC, the current, parameter B (550) and the gain value.

[0046] Parameter B is the predicted change in SOC for one amp of current over the time period from the previous calculation cycle of the SOC Kalman filter to the current calculation cycle. Parameter B may be determined based on the SOC Kalman filter calculation cycle time (Ts) and the rated capacity (Q) of the battery 100. In a preferred embodiment, parameter B (550) is calculated according to the following formula:

number

[0047] 1, the parameters used by the device 10 may be preset, and the device 10 may directly use the parameters. The parameters may include weights of the first neural network, weights of the second neural network, and a parameter R, etc. These parameters may be calculated by a computer independent of the device 10.

[0048] 6, in at least another embodiment, the apparatus 10a may include a pre-processing unit 200, a SOC estimation unit 300, a validity estimation unit 400, and a SOC Kalman filter 500. The apparatus 10a may further include a parameter calculator 600 for calculating parameters used in the apparatus 10a. The parameters may include weights of the first neural network, weights of the second neural network, and a parameter R, etc. Although the same parts of the apparatus 10a and the apparatus 10 will not be described, the parameter calculator 600 will be described below.

[0049] FIG. 7 is a flow chart illustrating sequential blocks for calculating parameters used in SOC estimation by parameter calculator 600, according to one embodiment of the present disclosure.

[0050] In block S010, current, voltage, and temperature data are extracted from experimental results (ie, experimental data) from battery tests designed to be representative of operating conditions of a battery application.

[0051] In block S020, the current is filtered using a low pass filter in a manner consistent with the operation of current low pass filter 240, the voltage is filtered in a manner consistent with the operation of voltage low pass filter 250, and the true SOC is calculated using a coulomb counting method. For example, parameter calculator 600 can control pre-processing unit 200 to filter the current and voltage, or parameter calculator 600 can filter the current and voltage itself.

[0052] In block S030, the first neural network is trained. For example, the weights of the SOC neural network (first neural network) are optimized using a training algorithm, such as the Levenberg-Marquardt algorithm, with the goal of minimizing the RMS error between the true SOC value calculated in block S020 and the nominal SOC value calculated by the SOC neural network (first neural network) being trained. These are evaluated with the corresponding current, voltage, temperature, filtered current and filtered voltage values ​​collected in blocks S010 and S020.

[0053] In block S040, a nominal SOC value is calculated by evaluating a trained SOC neural network using the current, voltage, temperature, filtered current, and filtered voltage values ​​collected in blocks S010 and S020. For example, parameter calculator 600 controls SOC estimation unit 300 to calculate the nominal SOC using the trained SOC neural network (first neural network).

[0054] In block S050, the squared SOC prediction error is calculated as the square of the difference between the true SOC value and the corresponding nominal SOC value.

[0055] In block S060, a second neural network is trained. For example, the weights of the squared SOC error neural network (second neural network) are optimized using a training algorithm, such as the Levenberg-Marquardt algorithm, with the goal of minimizing the RMS error between the squared SOC prediction error calculated in block S050 and the squared nominal SOC error value calculated by the squared SOC error neural network (second neural network) during training, which are evaluated with the corresponding current, voltage, temperature, filtered current and filtered voltage values ​​collected in blocks S010 and S020.

[0056] In block S070, a squared nominal SOC error value is calculated by evaluating a trained squared SOC error neural network using the current, voltage, temperature, filtered current and filtered voltage values ​​collected in blocks S010 and S020. For example, parameter calculator 600 controls validity estimation unit 400 to calculate the squared nominal SOC error using the trained squared SOC error neural network (second neural network).

[0057] In block S080, the squared nominal SOC error value E 2 A subset of the original data set is identified that is less than 1. In one example embodiment, the parameter E is set to 1%.

[0058] In block S090, a parameter R is calculated for the data subset identified in block S080 as the variance of the difference between the true SOC value and the corresponding nominal SOC value. The parameter R is used in the Kalman filtering algorithm.

[0059] In FIG. 7, blocks S010, S020, and S030 refer to the process of calculating the weights of the first neural network, blocks S040, S050, and S060 refer to the process of calculating the weights of the second neural network, and blocks S070, S080, and S090 refer to the process of calculating the parameter R.

[0060] In at least one embodiment, the method illustrated in FIG. 7 is implemented to calculate parameters that are used in the method of estimating battery SOC performed by device 10 or 10a.

[0061] In at least another embodiment, the method illustrated in Figure 7 and the method of estimating the battery SOC performed by device 10 or 10a may be performed independently. For example, the method illustrated in Figure 7 may be provided to calculate parameters that are used to estimate the battery SOC in a manner different from that performed by device 10 or 10a. As another example, the parameters used by device 10 or 10a may be calculated in a manner different from that illustrated in Figure 7.

[0062] As can be seen from the above embodiment, the first neural network is used to estimate the nominal SOC, the effectiveness value of the nominal SOC is calculated, and the SOC Kalman filter calculates the estimated SOC based on the nominal SOC and the effectiveness value. Therefore, by using a systematic and efficient development method, the battery SOC can be accurately estimated.

[0063] In this disclosure, a second neural network is used to estimate the validity of the nominal SOC based on the operating zone, and the KF gain is set to zero in the operating zone where the nominal SOC is predicted to be invalid, and is calculated according to the KF gain formula otherwise.

[0064] The present disclosure provides a method for calculating parameters used in battery SOC estimation that uses a commercially available neural network optimization package and allows for high accuracy in neural networks with relatively few engineering resources.

[0065] The present disclosure has proven extremely useful in providing accurate SOC estimation, particularly in applications such as LFP cell chemistry.

[0066] The correlation between SOC and available measurements varies significantly across operating zones.

[0067] (Second aspect of embodiment) In a second aspect of the embodiment, a method for estimating a battery state of charge (SOC) is provided. The method corresponds to the device for estimating a battery state of charge (SOC) provided in the first aspect of the embodiment. The same content as in the first aspect of the embodiment is omitted.

[0068] FIG. 8 is a flowchart of a method for estimating a battery state of charge according to an embodiment.

[0069] As shown in FIG. 8 , the method includes:

[0070] S801, operating parameters of a battery are detected, and at least a portion of the parameters are filtered to generate filtered parameters.

[0071] S802, a nominal SOC is calculated using a first neural network based on the operating parameters and the filtered parameters.

[0072] S803, a validity value is calculated based on the operating parameters and the filtered parameters, and the validity value indicates the validity of the nominal SOC; and

[0073] S804, a Kalman filtering algorithm is performed based on the operating parameters, the nominal SOC and the validity value, which outputs an estimated SOC of the battery.

[0074] For details of each block, refer to the corresponding description in the first aspect of the embodiment.

[0075] As shown in FIG. 8 , the method may further include:

[0076] S805, parameters used for battery SOC estimation are calculated.

[0077] For details of block S805, refer to the flowchart of FIG. 7 in the first aspect of the embodiment.

[0078] As can be seen from the above embodiment, the first neural network is used to estimate the nominal SOC, the second neural network is used to estimate the effectiveness value of the nominal SOC, and the SOC Kalman filter calculates the estimated SOC based on the nominal SOC and the effectiveness value. Furthermore, the parameters are calculated using a well-defined optimization-based workflow. Therefore, the battery SOC can be accurately estimated by using a systematic and efficient development methodology.

[0079] (Third aspect of embodiment) A third aspect of an embodiment of the present disclosure provides an electronic device including the device 10, 10a or the parameter calculator 600 described in the first aspect of the embodiment.

[0080] 9 is a schematic diagram of the structure of an electronic device in an embodiment of the present disclosure. As shown in FIG. 9, the electronic device 900 may include a processor 910 and a memory 920, and the memory 920 is connected to the processor 910. The memory 920 may store various data, and may further store a program 930 for data processing and execute the program 930 under the control of the processor 910.

[0081] In one implementation, the functionality of the device 10, 10a or the parameter calculator 600 may be integrated into the processor 910. The processor 910 may be configured to perform the method of the second aspect of the embodiment.

[0082] In another implementation, the device 10, 10a or parameter calculator 600 and the processor 910 may be configured separately. For example, the device 10, 10a or parameter calculator 600 may be configured as a chip connected to the processor 910, and the functions of the device 10 or parameter calculator 600 may be performed under the control of the processor 910.

[0083] An embodiment of the present disclosure may further provide a computer readable program that, when executed on an apparatus or electronic device, causes the apparatus or electronic device to perform the method described in the second aspect of the embodiment of the present disclosure.

[0084] An embodiment of the present disclosure further provides a computer storage medium including a computer readable program, said program causing an apparatus or electronic device to perform the method described in the second aspect of the embodiment of the present disclosure.

[0085] The above apparatus and methods of the present disclosure may be implemented by hardware or hardware in combination with software. The present disclosure relates to a computer readable program that, when executed by a logic device, enables the logic device to execute the above apparatus or components or execute the above method or steps. The present disclosure also relates to a storage medium, such as a hard disk, a floppy disk, a CD, a DVD, a flash memory, etc., for storing the above program.

[0086] The methods / apparatuses described in relation to the embodiments of the present disclosure may be directly implemented in hardware, or may be implemented as software modules executed by a processor, or a combination thereof. For example, one or more functional block diagrams and / or one or more combinations of functional block diagrams illustrated in the drawings may correspond to software modules of a computer program procedure or to hardware modules. Such software modules may correspond to steps illustrated in the drawings, respectively. And the hardware modules may be implemented by fixing the soft modules using, for example, a field programmable gate array (FPGA).

[0087] The soft module may be located in a RAM, a flash memory, a ROM, an EPROM, an EEPROM, a register, a hard disk, a floppy disk, a CD-ROM, or other forms of memory media known in the art. The memory medium may be connected to the processor, allowing the processor to read information from the memory medium and write information to the memory medium. Alternatively, the memory medium may be a component of the processor. The processor and the memory medium may be located in an ASIC. The soft module may be stored in the memory of the mobile terminal, or may be stored in a pluggable memory card of the mobile terminal. For example, if the equipment (such as a mobile terminal) uses a relatively large capacity MEGA-SIM card or a large capacity flash memory device, the soft module may be stored in the MEGA-SIM card or the large capacity flash memory device.

[0088] One or more of the functional blocks and / or one or more combinations of functional blocks in the figures may be implemented as a universal processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any other suitable combination for performing the functions described herein. Also, one or more of the functional block diagrams and / or one or more combinations of the functional block diagrams in the figures may be implemented as a combination of a DSP and a microprocessor, a combination of multiple processors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0089] This disclosure has been described above with reference to specific embodiments. However, those skilled in the art should understand that such description is merely illustrative and is not intended to limit the protection scope of the present invention. According to the spirit and principle of the present invention, various variations and modifications may be made by those skilled in the art, and such variations and modifications are included in the scope of the present invention.

Claims

1. 1. An apparatus for estimating a battery state of charge (SOC), comprising: a pre-processing unit (200) configured to detect operating parameters of the battery and to filter at least a portion of the operating parameters to generate filtered parameters; an SOC estimation unit (300) configured to calculate a nominal SOC using a first neural network based on the operating parameters and the filtered parameters transmitted from the pre-processing unit (200); a validity estimation unit (400) configured to estimate a validity value indicative of the validity of the nominal SOC output by the SOC estimation unit (300) based on the operating parameters and the filtered parameters transmitted from the pre-processing unit (200); an SOC Kalman filter (500) configured to perform a Kalman filtering algorithm based on the operating parameters transmitted from the pre-processing unit (200), the nominal SOC transmitted from the SOC estimation unit (300), and the validity value transmitted from the validity estimation unit (400), thereby outputting an estimated SOC of the battery.

2. The operating parameters detected by the pre-processing unit (200) include current, voltage and temperature; the filtered parameters include a filtered current and a filtered voltage; The operating parameters transmitted to the SOC Kalman filter (500) include the current; The pre-treatment unit (200) a current low pass filter (240) configured to filter the current using a time constant T seconds and output the filtered current; and a voltage low pass filter (250) configured to filter the voltage using a time constant T seconds and output the filtered voltage.

3. The validity estimation unit (400) a squared SOC error estimation unit (410) configured to estimate a squared nominal SOC error indicative of a square of a difference between a true SOC and the nominal SOC using a second neural network based on the operating parameters and the filtered parameters; 3. The apparatus for estimating a battery state of charge of claim 2, comprising: a validity classification circuit (450) configured to output the validity value based on a magnitude of the squared nominal SOC error and an elapsed run time since a current low pass filter initialization and / or a voltage low pass filter initialization.

4. The magnitude of the squared nominal SOC error is a first predetermined value (E ２ 4. The apparatus for estimating a battery state of charge of claim 3, wherein the validity value indicates that the nominal SOC is valid if the validity value is below a first predetermined value (T) and the elapsed run time since initialization of the current low pass filter and / or initialization of the voltage low pass filter exceeds a second predetermined value (3T).

5. The validity classification circuit (450) a first determining unit (451) configured to determine whether the squared nominal SOC error is below the first predetermined value; a second determining unit (452) configured to determine whether the elapsed execution time from an initialization of the current low pass filter and / or an initialization of the voltage low pass filter exceeds the second predetermined value; 5. The apparatus for estimating a battery state of charge as claimed in claim 4, further comprising: a logic unit (453) configured to output the validity value based on the determination result of the first determination unit (451) and the determination result of the second determination unit (452).

6. The SOC Kalman filter (500) a gain calculator (510) configured to calculate a gain value based on the validity value, a parameter Q, and a parameter R, where the parameter Q is a covariance related to a rate of increase of an SOC covariance if the SOC is not otherwise modified, and the parameter R is a covariance related to an error between the nominal SOC and a true SOC if the validity value indicates that the nominal SOC is valid; and an estimated SOC calculator (520) configured to calculate the estimated SOC based on the nominal SOC, the current, a parameter B, and the gain value, the parameter B being determined according to an SOC Kalman filter calculation cycle time (Ts) and a rated capacity (C) of the battery.

7. The apparatus further includes a parameter calculator, the parameter calculator comprising: Controlling the SOC estimation unit (300) to calculate a nominal SOC based on experimental data; Controlling the validity estimation unit (400) to calculate a squared nominal SOC error based on the experimental data; identifying a subset of data from the data set having the squared nominal SOC error less than a first predetermined value; 3. The apparatus for estimating a battery state of charge as described in claim 2, configured to calculate a variance of a difference between a true SOC and the nominal SOC for an identified subset of data, the calculated result being a parameter R used in the Kalman filtering algorithm.

8. The parameter calculator further comprises: Calculate the true SOC using Coulomb counting based on the experimental data; training the first neural network with the objective of minimizing a root mean square error between the true SOC and the nominal SOC calculated by the first neural network during training; Calculating a squared SOC prediction error as the square of the difference between the true SOC and the nominal SOC calculated by the trained first neural network; 8. The apparatus for estimating a battery state of charge of claim 7, configured to train the second neural network with the objective of minimizing a root-mean-square error between the squared SOC prediction error and a squared nominal SOC error calculated by the second neural network during training.

9. 1. A method for estimating a battery state of charge (SOC), comprising: detecting operational parameters of the battery and filtering at least a portion of the parameters to generate filtered parameters; calculating a nominal SOC using a first neural network based on the operating parameters and the filtered parameters; calculating a validity value indicative of the validity of the nominal SOC based on the operating parameters and the filtered parameters; and performing a Kalman filtering algorithm by an SOC Kalman filter (500) based on the operating parameters, the nominal SOC and the validity value, thereby outputting an estimated SOC of the battery.

10. The sensed operating parameters include current, voltage and temperature; the filtered parameters include a filtered current and a filtered voltage; the operating parameters used to implement the Kalman filtering algorithm include the current; the filtered current is produced by a current low pass filter filtering the current using a time constant T seconds; 10. The method for estimating a battery state of charge of claim 9, wherein the filtered voltage is produced by a voltage low pass filter filtering the voltage with a time constant of T seconds.

11. The step of calculating the validity value comprises: estimating a squared nominal SOC error indicative of a square of a difference between a true SOC and the nominal SOC using a second neural network based on the operating parameters and the filtered parameters; 11. The method for estimating a battery state of charge of claim 10, comprising: outputting the validity value based on a magnitude of the squared nominal SOC error and an elapsed run time since initialization of the current low pass filter and / or initialization of the voltage low pass filter.

12. The magnitude of the squared nominal SOC error is a first predetermined value (E ２ 12. The method for estimating a battery state of charge of claim 11, wherein the validity value indicates that the nominal SOC is valid if the validity value is below a first predetermined value (0.01T) and the elapsed run time since initialization of the current low pass filter and / or initialization of the voltage filter exceeds a second predetermined value (3T).

13. The efficacy value is determining whether the squared nominal SOC error is below the first predetermined value; determining whether the elapsed run time since initialization of the current low pass filter and / or initialization of the voltage filter exceeds the second predetermined value; and outputting the validity value as a function of the determination of the squared nominal SOC error and the determination of the elapsed run time since initialization of the current low pass filter and / or initialization of the voltage filter.

14. The estimated SOC is calculating a gain value based on the validity value, a parameter Q, and a parameter R, where the parameter Q is a covariance related to a rate of increase of the SOC covariance if the SOC is not otherwise modified, and the parameter R is a covariance related to an error between the nominal SOC and a true SOC if the validity value indicates that the nominal SOC is valid; 11. The method for estimating a battery state of charge of claim 10, wherein the estimated SOC is calculated based on the nominal SOC, the current, the parameter B, and the gain value, the parameter B being determined according to an SOC Kalman filter calculation cycle time (Ts) and a rated capacity (C) of the battery.

15. The method further comprises: Calculating a nominal SOC based on experimental data; calculating a squared nominal SOC error based on the experimental data; identifying a subset of data from the data set having the squared nominal SOC error less than a first predetermined value; 11. The method for estimating a battery state of charge of claim 10, comprising the steps of: calculating a variance of a difference between a true SOC and the nominal SOC for the identified subset of data, the calculated result being a parameter R used in the Kalman filtering algorithm.

16. The method further comprises: calculating the true SOC using Coulomb counting based on experimental data; training the first neural network with the objective of minimizing a root mean square error between the true SOC and a nominal SOC calculated by the first neural network during training; calculating a squared SOC prediction error as the square of the difference between the true SOC and the nominal SOC calculated by the trained first neural network; 11. The method for estimating a battery state of charge of claim 10, configured to train the second neural network with the objective of minimizing a root-mean-square error between the squared SOC prediction error and a squared nominal SOC error calculated by the second neural network during training.

Images