Estimation device

Abstract

To improve the accuracy of SOC estimation while reducing the computational load on the estimation device. [Solution] The effective resistance estimation unit 11 of the estimation device 1 estimates the effective resistance R(k), which is the overvoltage response of the battery 5 to a predetermined current input pattern, based on the measured values ​​of the current i(k) and terminal voltage v(k) flowing through the battery 5. The SOC estimation unit 14 inputs the current i(k) and the time-series data of the effective resistance parameter bhat(k) estimated by the effective resistance estimation unit 11 to the estimation model EM and calculates the SOCx of the battery 5. c We estimate (k). The estimation model EM can be created by learning the correspondence between the time-series data of the current i(k) flowing through battery 5 and the effective resistance R(k), and the state of charge (SOC) of battery 5.

Description

[Technical Field]

[0001] The present invention relates to an estimation device and an estimation system. [Background technology]

[0002] Batteries are used, for example, to supply power to drive sources such as vehicle motors. When controlling battery charging or vehicle operation, it is necessary to estimate the battery's State of Charge (SOC). One method for estimating the State of Charge (SOC) is to use the SOC-OCV characteristics of the battery. In this method, the open-circuit voltage (OCV) is estimated from the measured values ​​of the current flowing through the battery and the terminal voltage, and the SOC is estimated by referring to the SOC-OCV characteristics.

[0003] In recent years, LFP (lithium iron phosphate) batteries have attracted attention as vehicle batteries due to their low cost and long lifespan. LFP batteries have a relatively flat SOC-OCV characteristic. Therefore, in the case of LFP batteries, estimation methods using the SOC-OCV characteristic may result in large estimation errors. Patent Document 1 proposes a method for estimating the SOC of an LFP battery based on the battery's internal resistance. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Patent No. 6733485 [Overview of the Initiative] [Problems that the invention aims to solve]

[0005] However, the internal resistance of a battery depends not only on the State of Charge (SOC) but also on factors such as the magnitude and direction of the current. Therefore, when estimating SOC based on internal resistance, it is necessary to conduct numerous experiments and simulations to create maps and conversion logic. Further, when estimating SOC, it is expected that estimation accuracy can be improved by using data of a large number of points. However, if the estimation device performs arithmetic processing using a map or conversion logic on each piece of data of a large number of points, the arithmetic load increases. It is desirable to improve the SOC estimation accuracy while reducing the arithmetic load of the estimation device. [Means for Solving the Problem]

[0006] One aspect of the present invention is An estimation device for estimating a state of charge of a battery, comprising: a first estimation unit that estimates an overvoltage response of the battery to a predetermined input pattern of the current based on measured values of a current flowing through the battery and a terminal voltage; a second estimation unit that inputs the current flowing through the battery and time-series data of the overvoltage response estimated by the first estimation unit into an estimation model created by machine learning, and estimates the state of charge of the battery; the estimation model is created by learning a correspondence relationship among the current flowing through the battery, the time-series data of the overvoltage response of the battery, and the state of charge of the battery. [Effect of the Invention]

[0007] According to the present invention, it is possible to improve the SOC estimation accuracy while reducing the arithmetic load of the estimation device. [Brief Description of the Drawings]

[0008] [Figure 1] It is a block diagram showing the configuration of the estimation device according to the embodiment. [Figure 2] It is a diagram showing an equivalent circuit representing a battery system. [Figure 3] It is a graph showing an example of an overvoltage response to an impulse input of current. [Figure 4] It is a diagram showing an example of machine learning for the estimation model EM. [Figure 5](a) is a graph showing time-series data of current used for SOC estimation, and (b) is a graph showing time-series data of terminal voltage. [Figure 6] It is a graph showing SOC estimation results. [Figure 7] It is a graph showing the true value of SOC. [Figure 8] It is a flowchart showing processing of the estimation device in the present embodiment. [Figure 9] It is a diagram showing the configuration of an estimation system including the estimation device. [Figure 10] It is a block diagram showing the configuration of an estimation device according to Modification 1. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an estimation device according to an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a configuration of an estimation device 1 according to the embodiment. As shown in FIG. 1, the estimation device 1 estimates a state of charge (SOC) of a battery 5 installed in a vehicle such as an electric vehicle or a hybrid electric vehicle. The battery 5 is a rechargeable secondary battery. Although the type of the battery 5 is not limited, an LFP (lithium iron phosphate) battery can be used as an example. The LFP battery uses lithium (Li), iron (Fe), and phosphorus (P) as a positive electrode material. LFP batteries are attracting attention because they are less expensive than secondary batteries using rare metals such as nickel and cobalt, have high thermal stability, and have a long service life. When discharged, the battery 5 supplies electric power to an electric motor that is a driving source of the vehicle. Further, during braking of the vehicle, the battery 5 is charged with regenerative energy from the electric motor. The battery 5 is also charged by an external charging facility such as a quick charger or a household power outlet.

[0010] A voltage sensor 6, a current sensor 7, and a temperature sensor 8 are connected to the battery 5. The voltage sensor 6 measures the terminal voltage v(k) of the battery 5. The current sensor 7 measures the current i(k) flowing through the battery 5. The temperature sensor 8 measures the surface temperature T(k) of the battery 5. The voltage sensor 6, current sensor 7, and temperature sensor 8 perform measurements at a predetermined sampling period, for example, from the time the vehicle's ignition is turned ON to OFF. The estimation device 1 is connected to the voltage sensor 6, current sensor 7, and temperature sensor 8 by wire or wireless connection, and is capable of acquiring the respective measurement values.

[0011] The estimation device 1 can be composed of, for example, an ECU (Electronic Control Unit) installed in a vehicle. Although not shown in the diagram, the ECU consists of a processor such as a CPU (Central Processing Unit) and memory such as ROM (Read-only Memory) and RAM (Random Access Memory). The memory stores various programs to be executed by the estimation device 1, and the processor executes these programs to realize the functional configuration of the estimation device 1. The memory also stores various data necessary for the processing of the estimation device 1, and temporarily stores the processing results. Although a detailed explanation is omitted, the ECU may, in addition to estimating the State of Charge (SOC), perform charge / discharge control of the battery 5 and vehicle operation control based on the SOC. Alternatively, the ECU may output the estimated SOC to an external control device.

[0012] As shown in Figure 1, the estimation device 1 comprises an effective resistance estimation unit 11 (first estimation unit), a low-pass filter 12, and a SOC estimation unit 14 (second estimation unit). The effective resistance estimation unit 11 estimates the effective resistance R(k) based on the terminal voltage v(k) and current i(k) of the battery 5 obtained from the voltage sensor 6 and the current sensor 7. The effective resistance R(k) represents the overvoltage response of battery 5 to a given current input pattern and is one of the parameters that indicate the characteristics of the battery 5's internal impedance. "The overvoltage response of battery 5 to a given current input pattern" means, for example, the impulse response to an impulse current input, or the step response to a step input.

[0013] The low-pass filter 12 performs low-pass filtering on the measured value of the battery current i(k) obtained from the current sensor 7. The low-pass filter 12 can be, for example, a moving average filter or a time-lag filter. In this embodiment, an example is described in which the low-pass filter 12 is a moving average filter and outputs a moving average value ibar(k) from the measured value of the current i(k). Here, "bar" means the average value.

[0014] The SOC estimation unit 14 inputs the current flowing through the battery 5, the time-series data of the effective resistance (overvoltage response), and the temperature of the battery 5 into the estimation model EM to calculate the SOCx of the battery 5. c Estimate (k). Specifically, the SOC estimation unit 14 inputs the moving average value ibar(k) of the current obtained by low-pass filtering the measured current i(k), the parameter bhat(k) of the effective resistance R(k) estimated by the effective resistance estimation unit 11, and the measured temperature T(k) of the battery 5 obtained from the temperature sensor 8 into the estimation model EM. Here, "hat" means the estimated value.

[0015] Furthermore, instead of using the temperature sensor 8's measurement for battery 5, the temperature of battery 5 may be estimated using a thermal equivalent circuit model that takes into account the heat generated by the battery's internal resistance. In this case, since the internal temperature of the battery can be estimated, it is expected that the accuracy of the SOC calculation will be further improved.

[0016] Figure 2 shows an equivalent circuit representing the battery system. In Figure 2, i(k) is the current flowing through battery 5, with the discharge direction being considered positive. Also, v(k) is the terminal voltage, and voc (k) is the open circuit voltage. Here, k represents a discrete time instant, for example, i(k) is at time kT s means the value of current i at this instant, where Ts is the sampling period. As shown in Figure 2, the battery system can be represented as an equivalent circuit consisting of an electromotive force and an internal impedance. The voltage of the electromotive force is the open circuit voltage v oc (k), and the voltage across the internal impedance is the overpotential η(k).

[0017] Generally, when the battery 5 is discharged, the terminal voltage v(k) is lower than the open circuit voltage; when the battery is charged, the terminal voltage v(k) is higher than the open circuit voltage. This is caused by the existence of the internal impedance of the battery, and the difference between the terminal voltage v(k) and the open circuit voltage is called overpotential. That is, the overpotential η(k) is expressed by the following formula (1).

Mathematical expression

Mathematical expression

[0018] The estimation device 1 estimates the SOC x c (k) defined by this formula (2) using the current i(k) and terminal voltage v(k) measurable from the battery 5. For example, the current integration method is known as a method for calculating SOC based on equation (2). However, the current integration method has the drawback of not being able to account for errors in the initial value of the integration or errors in current measurement. Another known method involves using the correspondence between open-circuit voltage and SOC (SOC-OCV characteristic) for estimation. However, the aforementioned LFP battery has a relatively flat SOC-OCV characteristic, and the region in which the open-circuit voltage changes depending on the SOC is small, and the range of change is not sufficient. Therefore, when an LFP battery is used as battery 5, the estimation method using the SOC-OCV characteristic may not be able to ensure the accuracy of the SOC estimation.

[0019] Therefore, the estimation device 1 of this embodiment estimates the SOC by using the correspondence between the internal impedance of the battery 5 and the SOC, instead of the SOC-OCV characteristics. Specifically, the effective resistance estimation unit 11 of the estimation device 1 models the internal impedance of the battery 5 and calculates the effective resistance that represents the characteristics of the internal impedance. The effective resistance estimation unit 11 uses the μMarkov model M as the model for the internal impedance of the battery 5.

[0020] Figure 3 is a graph showing an example of the overvoltage response to an impulse current input. Figure 3(a) shows the time-series data of current i(k) measured at a predetermined sampling period (e.g., 0.1 seconds). Figure 3(b) shows the time-series data of overvoltage η(k) corresponding to Figure 3(a), and Figure 3(c) shows the time-series data of effective resistance R(k) shown in Figure 3(b). As shown in Figures 3(a) and 3(b), when an impulse current is applied, the overvoltage of battery 5 increases rapidly and then decreases gradually. As shown in Figure 3(c), the effective resistance R(k) can be expressed as the integral value of the overvoltage η(k) from the start of current input to a predetermined time (x seconds) (effective resistance for x seconds). The effective resistance R(k) reflects the change in overvoltage η(k) shown in Figure 3(b), and fluctuates greatly in the range SR from the start of current input to a predetermined time (x seconds), but thereafter the fluctuation converges and maintains an almost constant value.

[0021] As mentioned above, the overvoltage η(k) is the voltage across the internal impedance of battery 5. Therefore, the effective resistance R(k), which indicates the overvoltage response of battery 5, can be used as a parameter indicating the change in the internal impedance of battery 5. Here, using the μMarkov model M, for example, it is possible to estimate the effective resistance R(k) every 0.1 seconds over a period of 0.1 seconds to 5 seconds, and obtain time-series data consisting of 50 estimated values. In the time-series data, SOCx c If the effective resistance R(k) varies significantly depending on (k) (see range SR in (c) of Figure 3), the machine learning device 200 (see Figure 4) described later will capture the characteristics of that variation, and SOCx c (k) can be estimated with high accuracy.

[0022] This section describes a method for estimating the effective resistance R(k) using the μ-Markov model M. The value of time K in the step response of the internal impedance G(q) in the battery system shown in Figure 2 is given by the K-step effective resistance R K It can be defined as follows: Effective resistance R K This can be calculated using the impulse response g(k) of system G(q) by the following equation (3).

number

number

[0023] Here, if we choose the order p to be equal to the order of the true system, there exists a set of parameters for which equation (4) is equivalent to that of the true system. On the other hand, if the order p is different from the true order, no such set of parameters exists. However, the estimated value b of the impulse response l Regarding this, it has been shown that it provides effective estimates without depending on the order p of the system, which is an excellent property of the μ-Markov model M.

[0024] The effective resistance estimation unit 11 uses the successive least squares method to estimate the effective resistance using the μMarkov model M. The successive least squares method is a successive application of the least squares method for linear regression models, as shown in equations (5) to (10) below.

number

[0025] In actual batteries 5, the dynamic characteristics change moment by moment depending on the SOC and temperature. Therefore, a forgetting coefficient λ is used in equation (7). The forgetting coefficient is a parameter set by the user in the range of 0 < λ ≤ 1, and reducing the value of the forgetting coefficient λ improves the ability to track parameter changes. On the other hand, since less data is used effectively, sensitivity to noise increases and estimation errors become larger. It is desirable to determine the value of the forgetting coefficient λ by considering the trade-off between the ability to track parameter changes and sensitivity to noise.

[0026] The effective resistance estimation unit 11 takes the current i(k) measured by the current sensor 7 as input u(k) and the terminal voltage v(k) measured by the voltage sensor 6 as output y(k) to calculate the regression vector φ (see equation (9)) that constitutes the μMarkov model M. From the calculated regression vector φ, the effective resistance estimation unit 11 calculates the parameter θhat (see equation (6)). For SOC estimation, among the calculated parameters θhat, the parameter bhat(b0···b K Use ).

[0027] Here, SOC estimation includes all calculated parameters b0...b K It is also possible to use only the parameters within the range where the change in effective resistance R(k) is large (for example, the range SR shown in Figure 3(c)). As shown in Figure 3(c), the effective resistance R(k) of the battery fluctuates significantly immediately after the start of current input, and then gradually converges to a nearly constant value. In machine learning, the characteristics of large fluctuations in the effective resistance R(k) are captured and SOCx c To estimate (k), it is assumed that parameters in the range of low variability contribute little to the estimation accuracy of SOC.

[0028] As mentioned above, the μMarkov model M itself is a system that reduces the number of unnecessary data points, but by further excluding parameters that have a low contribution to estimation accuracy, the computational load on the estimation device 1 can be reduced.

[0029] The effective resistance estimation unit 11 uses, for example, parameters b0...b K From this, parameters whose fluctuations exceed a predetermined amount may be extracted and input to the SOC estimation unit 14 as time-series data of the effective resistance R(k). The effective resistance estimation unit 11 may, for example, calculate the amount of fluctuation of the parameter at each time point from the previous time point, and determine the range in which the fluctuation amount exceeds a predetermined amount as the range from which to extract parameters. This predetermined amount can be set to, for example, a value of at least four times the voltage detection resolution to suppress the effect of quantization errors. Alternatively, if the fluctuation pattern of the effective resistance is predictable, the effective resistance estimation unit 11 may, for example, extract parameters included in a predetermined period from the start of current input.

[0030] Here, effective resistance is a parameter that indicates the characteristics of the internal impedance and depends on the State of Cycles (SOC). However, effective resistance also depends on the magnitude and direction of the current flowing through the battery 5, as well as the temperature of the battery 5. Therefore, in order to accurately estimate the SOC from the effective resistance, it is necessary to consider the current and temperature of the battery 5 during the estimation process. For this reason, the SOC estimation unit 14 performs the estimation using three data points: the effective resistance R(k), current i(k), and temperature T(k) of the battery 5.

[0031] In the conventional approach to estimating SOC by considering three points—effective resistance R(k), current i(k), and temperature T(k)—it is necessary to perform numerous experiments and simulations to create maps and conversion logic. Furthermore, the SOC estimation unit 14 needs to create a complex program to refer to the maps and execute the conversion logic. Furthermore, the estimation method using the μMarkov model M described above allows for the estimation of the effective resistance R(k) every 0.1 seconds, for example, and the time-series data of the effective resistance R(k) consists of multiple estimated values. Performing complex calculations on multiple estimated values ​​in the SOC estimation unit 14 leads to an increase in the computational load of the estimation device 1.

[0032] Therefore, in this embodiment, the SOC estimation unit 14 receives an input signal (for example, the effective resistance R(k), current i(k), and temperature T(k) of the battery 5) and an output signal, SOCx c We estimate SOC using the estimation model EM, which has learned the correspondence with (k). Figure 4 shows an example of machine learning for the estimation model EM. As shown in Figure 4, the estimation model EM can be pre-created, for example, using the machine learning device 200, and then implemented in the estimation device 1. The machine learning device 200 may be an external device to the vehicle. In this case, the estimation model EM created by the machine learning device 200 may be implemented in the estimation device 1 before it is installed in the vehicle. Alternatively, the estimation model EM may be delivered to the estimation device 1 after it has been installed in the vehicle via the cloud or the like. Alternatively, the machine learning device 200 may be installed in the vehicle. In this case, the machine learning device 200 may use data obtained by operating the battery 5 while the vehicle is running to create or update the estimation model EM.

[0033] The SOC estimation model EM can be expressed, for example, by the following equation (11).

number

number

number

[0034] In this embodiment, the nonlinear function f in equation (11) is constructed using a machine learning model. The machine learning model is not limited to a specific model, but for example, a neural network (NN), a random forest, etc., can be used. As shown in Figure 4, machine learning requires a dataset DS consisting of input data (parameter bhat(k), moving average value of current ibar(k), temperature T(k)) and output data (true value of SOC) for a nonlinear function f. A machine learning model can create an estimation model EM that estimates the State of Computer Occasion (SOC) based on the input data by learning the correspondence between input and output data. For example, a machine learning model can efficiently learn a nonlinear function f by using methods such as backpropagation on the dataset DS.

[0035] In equation (11), only a finite-length moving average is used for the current i(k). Also, the measured value of the terminal voltage v(k) of battery 5 is not used directly. Therefore, the estimation method of SOC corresponding to the current integration method in equation (2), and the open-circuit voltage v from the terminal voltage v(k) are not used. oc It is considered impossible to create a model that corresponds to the conventional estimation method of calculating (k) and estimating SOC. These findings indicate that SOC estimation using machine learning models is a different approach from conventional estimation methods.

[0036] The training dataset DS can be created, for example, using the following method: • Create a charge / discharge measurement device equipped with a battery of the same type as the battery 5 used in the vehicle (e.g., an LFP battery) that simulates the discharge and charge that occur when the vehicle is running. Regarding discharge, the load size is controlled by connecting multiple resistors of different sizes in parallel to battery 5 and switching these connections using a MOSFET (Metal-oxide-semiconductor Field-effect Transistor), etc. Regarding charging, the system controls the switching between CC (Constant Current) charging and CV (Constant Voltage) charging. • Operate the charge / discharge measurement device with a program that performs random charge and discharge operations. The voltage sensor 6, current sensor 7, and temperature sensor 8 measure the current i(k), terminal voltage v(k), and temperature T(k) of the battery 5. The measured values ​​of terminal voltage v(k) and current i(k) are input into the μMarkov model M to calculate the parameter θhat(k) of the effective resistance R(k). The current i(k) is subjected to a low-pass filter to calculate the moving average value ibar(k). Using the measured values ​​of terminal voltage v(k) and current i(k), the true SOC value is calculated using the current integration method of equation (2). Create a dataset DS that takes the parameter bhat(k) of the effective resistance R(k), the moving average value of the current ibar(k), and the temperature T(k) as input data, and outputs the true value of SOC as the output data.

[0037] [Example of experiment] The usefulness of SOC estimation using the machine learning-based estimation model EM is explained based on experimental examples. Figure 5(a) is a graph showing the data for the current i(k) used in SOC estimation, and Figure 5(b) is a graph showing the data for the terminal voltage v(k). Although not shown in the diagram, data for the temperature T(k) of battery 5 is also prepared in the experiment. The estimation model EM used in the experiment was created by inputting the aforementioned training dataset DS (see Figure 4) into an NN model. For training, the regression learner app included in MATLAB® Statistics and Machine Learning Toolbox was used, with the number of fully connected layers set to 1, the layer size to 100, and the iteration limit to 500.

[0038] The current i(k) and terminal voltage v(k) data shown in Figure 5 were input into a μMarkov model M to calculate the parameter θhat(k) of the effective resistance R(k). Furthermore, a low-pass filter was applied to the current i(k) data to calculate the moving average value ibar(k). The data to be input to the estimation model EM included the parameter bhat(k) for the effective resistance R(k) over 5 seconds, the effective resistance value over 5 seconds, the moving average value of the current ibar(k), and the temperature T(k).

[0039] Using the estimation model EM, we estimated the State of Computing (SOC) under the following conditions 1 to 4. • Example 1: The state of error (SOC) was estimated by inputting three parameters—the parameter bhat(k) of the effective resistance R(k) over a 5-second period, the moving average value of the current ibar(k), and the temperature T(k)—into the estimation model EM. • Second example: The state of charge (SOC) was estimated by inputting three points—effective resistance, moving average value of current ibar(k), and temperature T(k)—into the estimation model EM. • Third example: The state of error (SOC) was estimated by inputting two parameters, bhat(k), which is the parameter of the effective resistance R(k) over a 5-second period, and ibar(k), which is the moving average value of the current, into the estimation model EM. • Example 4: The State of Control (SOC) was estimated by inputting only the parameter bhat(k) of the effective resistance R(k) over a 5-second period into the estimation model EM.

[0040] Figure 6(a) is a graph showing the true value of SOC. Figure 6(b) is a graph showing the SOC estimation results for the first example. Figure 6(c) is a graph showing the SOC estimation results for the second example. Figure 7(a) is a graph showing the SOC estimation results for the third example. Figure 7(b) is a graph showing the SOC estimation results for the fourth example.

[0041] The first example is an experimental example in accordance with the embodiment, in which the SOC is estimated using bhat(k), a parameter of multiple points in the effective resistance R(k) obtained from the μMarkov model. On the other hand, the second example estimates the SOC using a single 5-second effective resistance value. Both the first example (see Figure 6(b)) and the second example (see Figure 6(c)) track the true SOC value (see Figure 6(a)), but the first example has fewer outliers than the second example, indicating that it tracks the true SOC more closely. This confirms the usefulness of SOC estimation using a large number of data points.

[0042] In the third and fourth examples, similar to the first example, the multi-point parameter bhat(k) of the effective resistance R(k) obtained from the μMarkov model is used, but in the third example, the temperature T(k) is not input into the estimation model EM. In the fourth example, the moving average value ibar(k) of the current and the temperature T(k) are not input into the estimation model EM. Both the third example (see Figure 7(a)) and the fourth example (see Figure 7(b)) track the true SOC value (see Figure 6(a)), but the third example has fewer outliers than the fourth example. Furthermore, comparing the third and fourth examples with the first example (see Figure 6(b)), it can be seen that the first example has fewer outliers and tracks the true SOC more closely. The RMSE (Root Mean Square Error) for the first and third examples were 2.88 and 3.00, respectively.

[0043] As mentioned above, the estimation model EM is created by learning the correspondence between the input signal and SOCxc(k). From the experimental results of the first, third, and fourth examples, it can be seen that by increasing the number of input signal points to the estimation model EM, the estimation model EM can capture a wider range of fluctuation characteristics, thereby improving the accuracy of SOC estimation.

[0044] [Estimation process for effective resistance] Figure 8 is a flowchart showing the processing of the estimation device 1 in this embodiment. As shown in Figure 8, the estimation device 1 acquires measured values ​​of terminal voltage v(k), current i(k), and temperature T(k) from the voltage sensor 6, current sensor 7, and temperature sensor 8 at a predetermined sampling period (step S01). The effective resistance estimation unit 11 estimates the effective resistance R(k) using the μMarkov model M based on the measured values ​​of terminal voltage v(k) and current i(k) (step S02). The low-pass filter 12 calculates a moving average value ibar(k) by applying a low-pass filter to the measured value of current i(k) (step S03). The SOC estimation unit 14 inputs the effective resistance parameter bhat(k), the moving average value of the current ibar(k), and the temperature T(k) into the estimation model EM to calculate SOCx c (k) is estimated (step S04).

[0045] [Estimation System] Figure 9 shows the configuration of the estimation system 100, including the estimation device 1. As shown in Figure 9, the estimation system 100 comprises one or more vehicles VH equipped with estimation device 1, and a machine learning device 2 that performs machine learning of the estimation model EM based on data collected from estimation device 1. The machine learning device 2 can perform machine learning of the estimation model EM in the same manner as the machine learning device 200 shown in Figure 4. Each vehicle's (VH) estimation device 1 has the configuration shown in Figure 1 and is equipped with an estimation model EM that was created in advance using machine learning. Each estimation device 1 performs SOC estimation using the estimation model EM while the vehicle (VH) is in motion.

[0046] Machine learning device 2 can consist of an information processing device equipped with a processor such as a CPU and memory such as ROM and RAM. The memory stores various programs to be executed by machine learning device 2. The processor executes these programs, thereby realizing the functional configuration of machine learning device 2. Furthermore, the memory also stores an estimation model EM similar to the estimation model EM provided in each estimation device 1.

[0047] The machine learning device 2 is connected to each estimation device 1 via a network. The machine learning device 2 comprises a data acquisition unit 21, a storage unit 22, and a machine learning unit 23. The storage unit 22 consists of memory. For example, the storage unit 22 stores data necessary for processing each functional configuration of the machine learning device 2. The storage unit 22 also temporarily stores the processing results of each functional configuration.

[0048] The data acquisition unit 21 receives input data from the estimation device 1 installed in the vehicle VH to the estimation model EM (effective resistance parameter bhat(k), moving average value of current ibar(k), temperature T(k)) and output data, the estimated SOC value x c (k) is collected. The data collection unit 21 stores the collected data in the storage unit 22 as a training dataset DS. The data collection unit 21 can, for example, randomly select vehicles (VH) based on predetermined conditions and collect data. The predetermined conditions can be set based on, for example, the type of vehicle (VH), geographical information of the area in which the vehicle (VH) travels, and environmental information such as temperature or weather. The data collection unit 21 can attach tags to the data set DS stored in the storage unit 22 for classification purposes, such as the type of vehicle VH, geographical information, and environmental information.

[0049] The machine learning unit 23 performs machine learning on the estimation model EM using the dataset DS stored in the memory unit 22. The dataset DS stored in the memory unit 22 is collected from actual running vehicles VH and reflects the type of vehicle VH, geographical information, environmental information, etc. By performing machine learning on the estimation model EM using this dataset DS, the estimation model EM can be updated to reflect the actual running conditions of the vehicle VH.

[0050] The machine learning unit 23 transmits the update data UD of the estimation model EM to the estimation device 1 of the vehicle VH. Estimation device 1 can update the estimation model EM by installing the received update data UD into the estimation model EM. The machine learning unit 23 may send the same update data UD to all estimation devices 1, or it may create multiple different update data UDs and select the update data UD to send according to the vehicle VH. The machine learning unit 23 can, for example, search for tags to extract machine learning datasets (MDS) that meet specific conditions. The machine learning unit 23 can update the estimation model EM using only the extracted machine learning datasets (MDS). This makes it possible to optimize the estimation model EM according to the type of vehicle VH, geographical conditions, environmental conditions, etc. The updated estimation model EM data (UD) is then sent to the estimation device 1 of the vehicle VH that matches the type of vehicle VH, geographical conditions, environmental conditions, etc. This allows the estimation device 1 to use the optimized estimation model EM, and an improvement in the estimation accuracy of SOC is expected.

[0051] As described above, the estimation device 1 of this embodiment has the following configuration. (1) Estimation device 1 is the SOCx of battery 5 c (k) Estimate the charge level. The estimation device 1 comprises an effective resistance estimation unit 11 (first estimation unit) and a SOC estimation unit 14 (second estimation unit). The effective resistance estimation unit 11 estimates the effective resistance R(k), which is the overvoltage response of the battery 5 to a predetermined current input pattern, based on the measured values ​​of the current i(k) and terminal voltage v(k) flowing through the battery 5. The SOC estimation unit 14 inputs the current i(k) flowing through the battery 5 and the parameter bhat(k), which is time-series data of the effective resistance estimated by the effective resistance estimation unit 11, into an estimation model EM created by machine learning, and calculates the SOCx of the battery 5. c Estimate (k). "Current i(k) flowing through battery 5" may be, for example, a measured value of current i(k), or it may be a moving average value ibar(k) obtained by processing the measured value of current i(k) with a low-pass filter. The estimation model EM can be created by learning the correspondence between the current i(k) flowing through battery 5, the time-series data of the effective resistance, and the state of charge (SOC) of battery 5.

[0052] The estimation device 1 of this embodiment can improve the estimation accuracy of SOC while reducing the computational load. LFP batteries are attracting attention as batteries 5 that supply power to the drive source of the vehicle VH. However, LFP batteries have a relatively flat SOC-OCV characteristic, and estimation errors are likely to occur in SOC estimation methods based on SOC-OCV characteristics. The estimation device 1 of this embodiment focuses on the correspondence between the SOC and the internal impedance of the battery 5, and estimates the SOC based on the effective resistance, which is one of the parameters that indicate the characteristics of the internal impedance.

[0053] Here, the effective resistance also varies due to various factors other than the State of Control (SOC). In a typical approach, if these factors are also considered, it is necessary to perform numerous experiments and simulations to generate maps and conversion logic. Furthermore, by using a large number of data points for estimation, the estimation accuracy is expected to improve. However, if the estimation device 1 performs calculations using the aforementioned map and logic for each of the numerous data points, the computational load will increase.

[0054] In the estimation device 1 of this embodiment, the SOC estimation unit 14 estimates the SOC using the estimation model EM created using the training dataset DS. By utilizing machine learning, the effort required for experiments and simulations to generate maps and transformation logic can be reduced. Furthermore, the SOC estimation unit 14 does not need to perform complex calculations using maps or transformation logic when estimating the SOC. Therefore, the estimation device 1 can improve the accuracy of SOC estimation by using a large amount of data while reducing the computational load.

[0055] (2) In the estimation device 1 described in (1), the estimation model EM can be created by learning the correspondence between the current i(k) flowing through the battery 5, the temperature T(k) of the battery 5, the parameter bhat(k) which is time-series data of the effective resistance R(k) of the battery 5, and the state of charge (SOC) of the battery 5. The SOC estimation unit 14 can estimate the State of Charge (SOC) of the battery 5 by inputting the current i(k) flowing through the battery 5, the parameter bhat(k) of the effective resistance R(k) estimated by the effective resistance estimation unit 11, and the temperature T(k) of the battery 5 into the estimation model EM. The "temperature T(k) of the battery 5" may be a measurement obtained from a temperature sensor 8 that measures the surface temperature of the battery 5, or it may be the internal temperature of the battery 5 estimated by a thermal equivalent circuit model or the like.

[0056] One factor that affects the effective resistance R(k) is the temperature T(k) of the battery 5. In this embodiment, three points are used as input data for the estimation model EM: the effective resistance R(k), current i(k), and temperature T(k) of the battery 5. This allows for the calculation of SOCx c This can improve the estimation accuracy of (k). In this case, conventional estimation methods require considerable effort to generate maps and transformation logic by considering three points, and the computational processing is also complex. In this embodiment, machine learning can be used to create an estimation model EM that takes three points into consideration, while reducing the effort required. Furthermore, it is possible to improve the estimation accuracy of SOC while reducing the computational load on the estimation device 1.

[0057] (3) In the estimation device 1 of (1) or (2) above, The effective resistance estimation unit 11 estimates the effective resistance R(k) of the battery 5 by inputting the measured values ​​of the current i(k) flowing through the battery 5 and the terminal voltage v(k) of the battery 5 into the μMarkov model M.

[0058] The μMarkov model M combines the FIR model and the ARX model, reducing the number of parameters unnecessary for estimating the effective resistance R(k) in the FIR model. As a result, the estimation device 1 can improve the accuracy of the effective resistance R(k) estimation while reducing the computational load.

[0059] (4) In any of the estimation devices 1 described in (1) to (3) above, The SOC estimation unit 14 extracts the range SR in which the fluctuation exceeds a predetermined amount from the time-series data of the effective resistance R(k) estimated by the effective resistance estimation unit 11, and inputs it into the estimation model EM.

[0060] By extracting only the range from the time-series data of the effective resistance R(k) that is expected to contribute to the estimation accuracy of the State of Charge (SOC), the computational load on the estimation device 1 can be further reduced while maintaining the estimation accuracy of the SOC. As a specific example, the effective resistance estimation unit 11 can calculate the change in the parameter bhat(k) at each time point from the previous time point, extract the parameters bhat(k) within a range where the change is greater than or equal to a predetermined amount, and input them to the SOC estimation unit 14. Alternatively, the effective resistance estimation unit 11 can extract the parameters bhat(k) included in a predetermined period from the start of current input and input them to the SOC estimation unit 14.

[0061] (5) In any of the estimation devices 1 described in (1) to (4) above, The SOC estimation unit 14 inputs the measured value of the current i(k), which has been filtered by the low-pass filter 12, to the estimation model EM. The low-pass filter 12 can be, for example, a moving average filter. In this case, the SOC estimation unit 14 inputs the moving average value ibar(k) of the current to the estimation model EM.

[0062] The internal impedance of battery 5 changes depending on the magnitude of the current i(k) input to battery 5. It is assumed that there will be a delay between the timing of the change in the measured value of current i(k) and the timing of the change in the internal impedance of battery 5. Therefore, in this embodiment, a low-pass filter is applied to the measured value of current i(k) to reflect the delay in the change in internal impedance. As a result, the current i(k) input to the estimation model EM corresponds to the effective resistance R(k) which represents the change in overvoltage η(k), thereby improving the estimation accuracy of SOC.

[0063] The estimation system 100 according to this embodiment includes, for example, the following configuration. (7) The estimation system 100 comprises one or more vehicles VH and a machine learning device 2. Vehicle VH is equipped with an estimation device 1 as described in any of (1) to (5) above or (6) below. Power is supplied to the drive source of vehicle VH by battery 5. The machine learning device 2 is connected to the estimation device 1 for each vehicle VH via a network. Estimation device 1 receives input data to the estimation model EM (effective resistance parameter bhat(k), moving average value of current ibar(k), temperature T(k)) and output data to the estimation model EM (SOC estimate x c (k)) is sent to the machine learning device 2. Machine learning device 2 updates the estimated model EM using the input and output data received from estimation device 1. Machine learning device 2 then transmits the updated data UD (data related to the updated estimated model EM) to estimation device 1.

[0064] Thus, in the estimation system 100, the machine learning device 2 can collect data from the actual running vehicle VH and update the estimation model EM in real time. Furthermore, the machine learning device 2 can optimize the estimation model EM according to the type of vehicle VH, geographical conditions, environmental conditions, etc., for each estimation device 1, thereby further improving the estimation accuracy of SOC in each estimation device 1. Furthermore, by having the external machine learning device 2 update the estimation model EM, the computational load on the estimation device 1 for each vehicle VH can be reduced.

[0065] [Example 1] Figure 10 is a block diagram showing the configuration of the estimation device 1A according to modified example 1. In Figure 10, although not shown, the estimation device 1A is connected to the voltage sensor 6, current sensor 7, and temperature sensor 8 (see Figure 1), similar to the embodiment, and receives measured values ​​of terminal voltage v(k), current i(k), and temperature T(k) from each of them. As shown in Figure 10, the estimation device 1A includes high-pass filters 15 and 16. High-pass filters 15 and 16 perform similar high-pass filtering. The high-pass filter 15 performs a high-pass filter process on the measured value of the terminal voltage v(k) obtained from the voltage sensor 6 and inputs it to the effective resistance estimation unit 11. The high-pass filter 16 performs a high-pass filter process on the measured value of current i(k) obtained from the current sensor 7 and inputs it to the effective resistance estimation unit 11.

[0066] As shown in the embodiment (see Figure 1), it is possible to estimate the effective resistance R(k) by directly inputting the measured value of the terminal voltage v(k) into the μMarkov model M. However, as shown in Figure 2, the terminal voltage v(k) has an overvoltage η(k) and an open-circuit voltage V oc The component (k) is included. Since the effective resistance R(k) represents the overvoltage response, the estimation accuracy can be further improved by inputting a component close to the overvoltage η(k) into the μMarkov model M.

[0067] In Modification 1, a high-pass filter is applied to the measured value of the terminal voltage v(k), thereby reducing the open-circuit voltage V oc Low-frequency components corresponding to (k) are removed, and components close to the overvoltage η(k) can be extracted. However, the high-pass filter also removes the low-frequency components of the overvoltage η(k) itself. Therefore, in order to maintain consistency of the elements input to the μMarkov model M, in Modification 1, the same high-pass filter is also applied to the measured value of the current i(k). This improves the accuracy of the estimation of the effective resistance R(k).

[0068] As described above, the estimation device 1A according to the modified example 1 has the following configuration. (6) In any of the above (1) to (5), The effective resistance estimation unit 11 estimates the effective resistance R(k) based on the measured values ​​of the current i(k) and terminal voltage v(k) that have been filtered by the high-pass filters 15 and 16.

[0069] By applying a high-pass filter to the measured terminal voltage v(k), the open-circuit voltage V oc By removing the low-frequency component corresponding to (k), a component close to the overvoltage η(k) can be extracted. By inputting a component close to the overvoltage η(k) into the μMarkov model M, the estimation accuracy of the effective resistance R(k), which is the overvoltage response, can be further improved. In addition, by applying a high-pass filter to the measured value of current i(k), the consistency of the elements input to the μMarkov model M can be maintained.

[0070] The estimation device 1A according to Modification 1 is also applicable to the estimation system 100 shown in Figure 9. That is, at least one vehicle VH constituting the estimation system 100 may be equipped with the estimation device 1A according to Modification 1. [Explanation of symbols]

[0071] 1, 1A: Estimation device 2,200: Machine Learning Device 5: Battery 6: Voltage sensor 7: Current sensor 8: Temperature sensor 11: Effective resistance estimation unit (first estimation unit) 12: Low-pass filter 14:SOC estimation section (second estimation section) 15, 16: High-pass filter 100: Estimation System M: μMarkov model EM: Estimated Model VH: Vehicle DS: Dataset

Claims

1. An estimation device for estimating the charge level of a battery, A first estimation unit estimates the overvoltage response of the battery to a predetermined input pattern of the current, based on the measured values ​​of the current flowing through the battery and the terminal voltage. The system includes a second estimation unit that inputs the current flowing through the battery and the time-series data of the overvoltage response estimated by the first estimation unit into an estimation model created by machine learning to estimate the charge level of the battery. The estimation device is created by learning the correspondence between the current flowing through the battery, the time-series data of the battery's overvoltage response, and the battery's charge level.

2. In claim 1, The estimation model is created by learning the correspondence between the current flowing through the battery, the battery temperature, the time-series data of the battery's overvoltage response, and the battery's charge level. The second estimation unit is an estimation device that inputs the current flowing through the battery, the time-series data of the overvoltage response estimated by the first estimation unit, and the temperature of the battery into the estimation model to estimate the charge level of the battery.

3. In claim 1, The first estimation unit is an estimation device that estimates the overvoltage response of the battery by inputting the current flowing through the battery and the measured values ​​of the terminal voltage of the battery into a μMarkov model.

4. In claim 1, The second estimation unit is an estimation device that extracts a range in which the fluctuation exceeds a predetermined amount from the time-series data of the overvoltage response estimated by the first estimation unit and inputs it into the estimation model.

5. In claim 1, The second estimation unit is an estimation device that inputs the measured value of the current, which has been processed with a low-pass filter, into the estimation model.

6. In claim 1, The first estimation unit is an estimation device that estimates the overvoltage response based on high-pass filtered measurements of the current and terminal voltage.

7. A vehicle comprising an estimation device as described in any one of claims 1 to 6, wherein power is supplied to a drive source by the battery, An estimation system comprising the estimation device and a machine learning device connected via a network, The estimation device transmits the input data to the estimation model and the output data of the estimation model to the machine learning device. An estimation system comprising a machine learning device that updates the estimation model using the input and output data received from the estimation device, and transmits data relating to the updated estimation model to the estimation device.

Images