Battery pack available energy determination method, system, power consuming device, and storage medium

Abstract

The present disclosure relates to a battery assembly available energy determination method, system, power consumption device and storage medium, wherein the method comprises: acquiring a current terminal voltage and a current battery temperature of a battery assembly, and set operation data of the battery assembly within a set time period; determining a predicted terminal voltage sequence of the battery assembly within the set time period according to the current terminal voltage, the current battery temperature and the set operation data; determining a predicted operation time period of the battery assembly according to the predicted terminal voltage sequence and the set cut-off voltage; determining a remaining available energy of the battery assembly according to a target predicted terminal voltage sequence and a target set current sequence within the predicted operation time period; and outputting the remaining available energy of the battery assembly.

Description

Technical Field

[0001] This disclosure relates to the field of battery module management technology, and more specifically, to a method, system, electrical device, and storage medium for determining the available energy of a battery module. Background Technology

[0002] The state of energy (SOE) of a battery module is an important indicator characterizing the ratio between the current remaining usable energy of the module and its total usable energy. It reflects the level of energy that the module can continue to release or absorb under actual operating conditions (e.g., discharge conditions, charging conditions). In energy storage systems, SOE can help the energy management system (EMS) accurately determine the chargeable and dischargeable energy of each battery module group, optimize energy distribution among multiple battery module groups, and dynamically support various operating modes such as peak shaving and valley filling, emergency backup power, and photovoltaic self-consumption.

[0003] Currently, the common method for estimating the remaining energy of lithium battery modules is the power integration method. The power integration method (also known as the ampere-hour integration method) accumulates the charge and discharge energy by integrating current and voltage in real time, thereby calculating the SOE (State of Energy). However, this method has some technical drawbacks: First, it relies on the initial SOE value and accumulates errors over long-term operation; second, it fails to fully consider the impact of battery module aging, temperature changes, and dynamic operating conditions (such as variable rate charging and discharging) on ​​the actual usable energy of the battery module, resulting in insufficient estimation accuracy in complex real-world application scenarios. Summary of the Invention

[0004] One objective of this disclosure is to provide a new scheme for determining the available energy of a battery module, thereby addressing the problem of low estimation accuracy in related energy estimation methods and improving the estimation accuracy of the available energy of the battery module.

[0005] According to a first aspect of this disclosure, a method for determining the available energy of a battery assembly is provided, the method comprising: The current terminal voltage and current battery temperature of the battery module are obtained, as well as the set operating data of the battery module within a set time period; the set time period is a time period with the current time as the starting time and the set operating data includes a set current sequence, a set temperature sequence, and a set cutoff voltage. Based on the current terminal voltage, the current battery temperature, and the set operating data, determine the predicted terminal voltage sequence of the battery module within the set time period; The predicted operating time period of the battery module is determined based on the predicted terminal voltage sequence and the set cutoff voltage. The remaining usable energy of the battery module is determined based on the target predicted terminal voltage sequence and the target set current sequence during the predicted operating period. Output the remaining usable energy of the battery assembly.

[0006] Optionally, determining the predicted terminal voltage sequence of the battery module within the set time period based on the current terminal voltage, the current battery temperature, and the set operating data includes: The current terminal voltage, current battery temperature, and the set operating data are input into the terminal voltage prediction model to obtain the predicted terminal voltage sequence of the battery module within the set time period. The terminal voltage prediction model includes an open-circuit voltage estimation module, a model parameter prediction module, and an equivalent circuit model. The open-circuit voltage estimation module is used to determine the estimated open-circuit voltage value based on the current terminal voltage and the current battery temperature, and to reversely determine the current state of charge of the battery module by comparing the estimated open-circuit voltage value with the current terminal voltage. The model parameter prediction module is used to determine the current model parameters of the equivalent circuit model of the battery assembly based on the current state of charge and the current battery temperature. The equivalent circuit model is used to determine the charge state at the next moment based on the charge state at the previous moment and the set current at the previous moment, taking the current charge state as the starting point for rapid propagation, so as to obtain the charge state corresponding to each step. The equivalent circuit model is also used to determine the polarization voltage at the next moment based on the model parameters and the set current at the previous moment, taking the current polarization voltage as the starting point for rapid propagation, and thus obtaining the polarization voltage corresponding to each step. The open-circuit voltage estimation module is also used to determine the open-circuit voltage corresponding to each step based on the state of charge and battery temperature corresponding to each step. The model parameter prediction module is also used to determine the model parameters corresponding to each step based on the state of charge and battery temperature corresponding to each step. The equivalent circuit model is also used to determine the predicted terminal voltage for each step based on the model parameters, polarization voltage, open-circuit voltage, and set current, thereby obtaining the predicted terminal voltage sequence.

[0007] Optionally, the terminal voltage prediction model is trained through the following steps: Obtain a training sample set; wherein, each training sample in the training sample set includes the initial terminal voltage of the sample, the initial battery temperature of the sample, the sample running data, and the sample terminal voltage sequence, and the sample running data includes the sample current sequence and the sample battery temperature sequence; The training sample set is used to train the terminal voltage prediction model, resulting in the trained terminal voltage prediction model.

[0008] Optionally, obtaining the training sample set includes: Historical operating data of the sample battery module under different operating conditions are obtained to obtain an operating dataset; the historical operating data includes the sample current, sample terminal voltage and sample battery temperature of the sample battery module at each moment within a set operating cycle. For any given historical running data, the historical running data is divided into multiple sub-running data segments at a set time interval; For any sub-running data segment, the sample initial terminal voltage, sample initial battery temperature, sample battery temperature sequence, sample current sequence, and sample terminal voltage sequence corresponding to the sub-running data segment are used as a training sample to obtain the training sample set corresponding to the running dataset.

[0009] Optionally, the loss function during model training includes voltage prediction error terms and physical equation residual terms; The voltage prediction error term is calculated by the difference between the terminal voltage sequence predicted by the calculation model and the sample terminal voltage sequence. The residual terms of the physical equations are calculated by the difference between the rate of change of the polarization voltage within the model and the rate of change of the reference voltage.

[0010] Optionally, after determining the remaining available energy of the battery assembly, the method further includes: During the operation of the battery assembly, the actual operating data of the battery assembly is stored; the actual operating data includes the measured current, measured terminal voltage, and measured battery assembly temperature at each moment within a set operating cycle. When a set event is triggered, the training sample set is updated based on the actual operating data of the battery component to obtain the updated training sample set. The updated terminal voltage prediction model is obtained by retraining the terminal voltage prediction model using the updated training sample set.

[0011] Optionally, the setting event includes at least one of the following: The prediction error of the terminal voltage prediction model is greater than or equal to the error threshold. The time interval between the current time and the last model training time is greater than or equal to the time interval threshold.

[0012] According to a second aspect of this disclosure, a battery management system is provided, the system comprising: a memory and a processor, the memory storing executable instructions for controlling the processor to operate to perform the method according to a first aspect of this disclosure.

[0013] According to a third aspect of this disclosure, an electrical device is provided, comprising: a battery assembly and the battery management system described in the second aspect.

[0014] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the method as described in the first aspect.

[0015] One beneficial effect of this disclosure is that a predicted terminal voltage sequence is obtained by using the current battery temperature, current terminal voltage, and set operating data of the battery module. Then, based on this predicted terminal voltage sequence, the remaining usable energy of the battery module is obtained. Since this remaining usable energy is calculated based on the current state of the battery module (i.e., current battery temperature and current terminal voltage) and set operating data under planned future operating conditions, the result is more accurate and practical than SOE estimation based on a fixed rated energy. This solves the problem of low estimation accuracy in related art's usable energy estimation methods and improves the accuracy of estimating the usable energy of battery modules.

[0016] Other features and advantages of the invention will become clear from the following detailed description of exemplary embodiments of the invention with reference to the accompanying drawings. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of the invention and, together with their description, serve to explain the principles of the invention.

[0018] Figure 1 This is a flowchart of a method for determining the available energy of a battery module according to the present application; Figure 2 This is a schematic diagram of the structure of a terminal voltage prediction model provided in this application; Figure 3 This is a schematic diagram of the equivalent circuit model of a battery assembly according to an example provided in this application; Figure 4 This is a schematic diagram of a battery management system provided in this application; Figure 5 This is a structural schematic diagram of an electrical device provided in this application. Detailed Implementation

[0019] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0020] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0021] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0022] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0024] <Method Implementation> Figure 1 This is a flowchart of a method for determining the available energy of a battery module according to the present application.

[0025] like Figure 1 As shown, the method for determining the available energy of the battery module in this embodiment can be specifically executed by the battery management system.

[0026] Specifically, the method for determining the available energy of the battery assembly in this embodiment may include the following steps S1100 to S1500: Step S1100: Obtain the current terminal voltage and current battery temperature of the battery module, as well as the set operating data of the battery module within a set time period; The set time period is a time period with the current time as the starting time and the set operating data includes the set current sequence, the set temperature sequence, and the set cutoff voltage.

[0027] The inventors discovered that the remaining usable energy of a battery module is not a fixed amount, but a dynamic variable. Furthermore, the total energy released by the battery module varies under different currents and temperatures in the future. For example, the same battery discharging to its cutoff voltage with a high current will actually release less energy than discharging with a low current, because the internal resistance loss is greater and the voltage drops faster under high current. In other words, the remaining usable energy of a battery module is related to its current state (such as current terminal voltage and current battery temperature) and its planned operating conditions (such as charging and discharging conditions). Therefore, this application dynamically predicts the remaining usable energy of the battery module based on its current state and planned operating conditions.

[0028] In this embodiment, the battery assembly can be a battery module or a battery pack, etc., and there is no limitation here.

[0029] The front-end voltage can be the measured voltage of the positive and negative terminals of the battery module at the current moment.

[0030] If the battery assembly is equivalent to... Figure 3 The equivalent circuit model shown indicates that the terminal voltage is... Figure 3 The U in [the text].

[0031] The current battery temperature can be the temperature of the battery module at the current moment, which directly affects the electrochemical reaction rate, internal resistance and capacity inside the battery module. Different battery temperatures result in drastically different battery performance and energy release.

[0032] The set operating data can be based on the target planned operating conditions of the battery module within a set time period. It reflects the operating data of the battery module running under the target planned operating conditions within the set time period. In other words, the set operating data describes the working blueprint of the battery module under the future planned operating conditions. The target planned operating conditions can be one of the following: charging condition, discharging condition, or mixed charging and discharging condition.

[0033] When setting operating data, you can refer to spot market electricity prices, frequency regulation instructions, etc.

[0034] The set time period can refer to a period of time that starts from the current moment and extends into the future for a set duration.

[0035] The duration can be set to, for example, 2 hours, 3 hours, etc., and there is no limit here.

[0036] The set operating data includes a set current sequence and a set temperature sequence. The set current sequence characterizes the magnitude and direction of the charging or discharging current that the battery module is planned to withstand within a set time period, and directly determines the rate of energy consumption or replenishment.

[0037] Setting a temperature sequence can characterize the temperature change of the battery module within a set time period.

[0038] The set cutoff voltage can be the critical value at which safety requirements are met under the target planned operating conditions. The set cutoff voltage is used to characterize the termination condition of the battery module's operation under the target planned operating conditions.

[0039] When the target planned operating condition is discharge, the set cutoff voltage is the discharge cutoff voltage. When the target planned operating condition is charging, the set cutoff voltage is the charging cutoff voltage.

[0040] Step S1200: Determine the predicted terminal voltage sequence of the battery module within the set time period based on the current terminal voltage, the current battery temperature, and the set operating data.

[0041] In one embodiment of this application, step S1200, which determines the predicted terminal voltage sequence of the battery module within the set time period based on the current terminal voltage, the current battery temperature, and the set operating data, includes step S2000.

[0042] Step S2000: Input the current terminal voltage, current battery temperature and the set operating data into the terminal voltage prediction model to obtain the predicted terminal voltage sequence of the battery module within the set time period.

[0043] In this embodiment, the battery assembly can be represented by an equivalent circuit model, which can be as follows: Figure 3 As shown. The equivalent circuit model can be imagined as an electrical representation of a "black box" battery, which includes an ideal voltage source (i.e., the open-circuit voltage). It can also be written as OCV), Ohmic internal resistance ( ), RC parallel network.

[0044] The ideal voltage source (OCV) is the voltage generated by the chemical energy stored inside the battery module. This ideal voltage source is not a fixed value; it varies with the battery's state of charge (SOC) and temperature. Ohmic internal resistance ( The internal impedance of the battery module is ohmic. This internal resistance also changes with the battery's state of charge (SOC) and temperature.

[0045] RC parallel network, i.e. Figure 3 The middle is composed of polarization resistors and polarization capacitor A parallel network. RC parallel networks are used to simulate the polarization effect of battery modules. The polarization effect refers to the phenomenon where, when the current changes suddenly, the electrochemical reactions inside the battery module cannot keep up instantaneously, resulting in a slow voltage change; this process is essentially similar to the charging or discharging process of a capacitor. This represents the resistance to the polarization effect. This represents the ability of the polarization effect to store charge.

[0046] ocv、 , , These parameters are all dynamically changing, and, according to Figure 3 The circuit shown yields the formula for calculating the terminal voltage of the battery module at time t, as shown in formula (1): (1) in, Let be the terminal voltage of the battery module at time t, i.e., Figure 3 In , which is the open-circuit voltage of the battery module at time t, that is, the value of the ideal voltage source mentioned above. I(t) is the operating current flowing through the battery module at time t. It is the Ohmic internal resistance at time t. It is the polarization voltage generated on the RC parallel network (polarization element) at time t, which is related to... , related.

[0047] Based on this, a terminal voltage prediction model is constructed, such as... Figure 2 As shown, the terminal voltage prediction model 200 includes an open-circuit voltage estimation module 210, a model parameter prediction module 220, and an equivalent circuit model 230.

[0048] The open-circuit voltage estimation module 210 can be a common neural network structure, such as a multilayer perceptron (MLP), which is not limited here. The open-circuit voltage estimation module 210 can be pre-trained to achieve the following corresponding functions.

[0049] The model parameter prediction module 220 can be a common neural network structure, which can be pre-trained to achieve the following corresponding functions. The model parameter prediction module 220 can have the same structure as the open-circuit voltage estimation module 210, but without sharing parameters. Alternatively, the model parameter prediction module 220 can have a different structure from the open-circuit voltage estimation module 210 and not share parameters; this is not limited here.

[0050] The open-circuit voltage estimation module is used to determine the estimated open-circuit voltage value based on the current terminal voltage and the current battery temperature, and to reversely determine the current state of charge of the battery module by comparing the estimated open-circuit voltage value with the current terminal voltage.

[0051] Specifically, using the current battery temperature as a known condition, the open-circuit voltage estimation module sequentially calculates different candidate values ​​for the state of charge (SOC), obtaining the corresponding candidate open-circuit voltage values. Then, from these different candidate open-circuit voltage values, a target candidate open-circuit voltage is selected. The target candidate open-circuit voltage is the one with the smallest absolute difference between itself and the current terminal voltage. The SOC corresponding to the target candidate open-circuit voltage is then taken as the current SOC.

[0052] The model parameter prediction module is used to determine the current model parameters of the equivalent circuit model of the battery module based on the current state of charge and the current battery temperature.

[0053] The model parameters include ohmic internal resistance, polarization resistance, and polarization capacitance.

[0054] The equivalent circuit model is used to quickly determine the next state of charge based on the current state of charge as the starting point, the previous state of charge and the set current at the previous moment, and obtain the state of charge corresponding to each step.

[0055] Specifically, the state of charge at time k+1 can be calculated using formula (2). : (2) in, Coulomb efficiency is a dimensionless coefficient (usually less than or equal to 1). It reflects the charge loss caused by side reactions (such as gas evolution and self-discharge) during the charging and discharging process of the battery module. Δt is the time step, measured in seconds (s), which represents the actual time interval between two SOC updates. This is the set current from the previous moment. Specifically, it could be the average value of a set current sequence over a time interval [k, k+1], or... This is the set current for the set current sequence at time k. This refers to the nominal capacity of the battery module. Let k be the state of charge at time k.

[0056] The equivalent circuit model is also used to determine the polarization voltage at the next moment by taking the current polarization voltage as the starting point for rapid propagation, based on the model parameters and the set current at the previous moment, thus obtaining the polarization voltage corresponding to each step.

[0057] Based on the equivalent circuit model, the circuit differential equation can be obtained. Specifically, it can be the equation shown in formula (3): (3) Discretizing the equation yields the polarization voltage at time k+1. The quick formula (4): (4) in, , This is the set current from the previous moment. The initial value of the polarization voltage is 0, meaning the current polarization voltage is 0. Let be the polarization voltage at time k.

[0058] The open-circuit voltage estimation module is also used to determine the open-circuit voltage for each step based on the state of charge and battery temperature for each step.

[0059] Specifically, it can be expressed by formula (5): (5) in, Let be the state of charge at time t. Let be the battery temperature at time t. This is an open-circuit voltage estimation module.

[0060] The model parameter prediction module is also used to determine the model parameters for each step based on the state of charge and battery temperature corresponding to each step.

[0061] Specifically, it can be expressed by formula (6): (6) in, This is the model parameter prediction module.

[0062] The equivalent circuit model is also used to determine the predicted terminal voltage for each step based on the model parameters, polarization voltage, open-circuit voltage, and set current, thus obtaining the predicted terminal voltage sequence.

[0063] In this embodiment, by using the model parameters corresponding to any step (e.g., ), polarization voltage Substitute the open-circuit voltage ocv(t) and the set current I(t) into formula (1) to determine the predicted terminal voltage corresponding to this step, and then obtain the predicted terminal voltage sequence corresponding to multiple steps.

[0064] In one embodiment of this application, the terminal voltage prediction model is trained through the following steps S3100 to S3200: Step S3100: Obtain the training sample set; Each training sample in the training sample set includes the initial terminal voltage, the initial battery temperature, the sample operation data, and the sample terminal voltage sequence. The sample operation data includes the sample current sequence and the sample battery temperature sequence.

[0065] In one embodiment of this application, obtaining the training sample set in step S3100 includes: steps S3100.1 to S3100.3.

[0066] Step S3100.1: Obtain historical operating data of the sample battery module under different operating conditions to obtain an operating dataset; the historical operating data includes the sample current, sample terminal voltage, and sample battery temperature of the sample battery module at each moment within a set operating cycle.

[0067] In this embodiment, different operating conditions may include charging conditions, discharging conditions, and mixed charging and discharging conditions.

[0068] The running cycle can be set to one month, 30 days, etc., and there is no limitation here.

[0069] In one example, the operating cycle could be set to one month. This is because the degradation of lithium batteries is a relatively long process. Within one month, the battery's aging state can be considered relatively consistent and without significant changes. Therefore, the operating data during this period can be considered the battery's performance under its current aging state.

[0070] The sample current, sample terminal voltage, and sample battery temperature at each moment are all measured values.

[0071] Step S3100.2: For any historical running data, divide the historical running data into multiple sub-running data segments at a set time interval.

[0072] In this embodiment, the time interval can be a set duration, such as 2 hours, etc., and is not limited here.

[0073] Step S3100.3: For any sub-running data segment, take the sample initial terminal voltage, sample initial battery temperature, sample battery temperature sequence, sample current sequence, and sample terminal voltage sequence corresponding to the sub-running data segment as a training sample to obtain the training sample set corresponding to the running dataset.

[0074] In this embodiment, the sample terminal voltage at the initial moment in the sub-running data segment is taken as the sample initial terminal voltage of the sub-running data segment, and the battery temperature at the initial moment in the sub-running data segment is taken as the sample initial battery temperature of the sub-running data segment. Then, the other sample terminal voltages in the sub-running data segment, excluding the initial moment, are taken as the sample terminal voltage sequence of the sub-running data segment. The other sample battery temperatures in the sub-running data segment, excluding the initial moment, are taken as the sample battery temperature sequence of the sub-running data segment. The other sample currents in the sub-running data segment, excluding the initial moment, are taken as the sample current sequence of the sub-running data segment.

[0075] In one example, before performing step S3100.3, the method further includes: preprocessing any sub-running data segment to obtain a processed sub-running data segment as a new sub-running data segment.

[0076] In this example, preprocessing may include removing outliers, removing null values, and data normalization, which will not be elaborated here.

[0077] Correspondingly, step S3100.3 becomes: for any new sub-running data segment, the sample initial terminal voltage, sample initial battery temperature, sample battery temperature sequence, sample current sequence, and sample terminal voltage sequence corresponding to the new sub-running data segment are taken as a training sample to obtain the training sample set corresponding to the running dataset.

[0078] Step S3200: Train the terminal voltage prediction model using the training sample set to obtain the trained terminal voltage prediction model.

[0079] The model training method in this step can be a conventional model training method, which will not be elaborated here.

[0080] In one embodiment of this application, the loss function during model training includes a voltage prediction error term and a physical equation residual term; The voltage prediction error term is calculated by the difference between the terminal voltage sequence predicted by the calculation model and the sample terminal voltage sequence. The residual terms of the physical equations are calculated by the difference between the rate of change of the polarization voltage within the model and the rate of change of the reference voltage.

[0081] In this embodiment, the voltage prediction error term can be obtained by calculating the mean square of the differences between the predicted terminal voltage sequence (i.e., the predicted terminal voltage sequence) and the measured terminal voltage sequence. The voltage prediction error term is used to constrain the prediction accuracy of the model's output terminal voltage.

[0082] The residual terms of the physical equations can be obtained by calculating the mean square of the difference between the rate of change of the polarization voltage within the model and the rate of change of the reference voltage. The rate of change of the reference voltage can be the theoretical value of the rate of change of the polarization voltage derived from the equivalent circuit model.

[0083] The voltage prediction error term and the physical equation residual term are summed with fusion weights to obtain the loss function during model training. The fusion weights are adjustable hyperparameters used to balance the contribution ratio of the voltage prediction error term and the physical equation residual term to the total loss function.

[0084] Step S1300: Determine the predicted operating time period of the battery module based on the predicted terminal voltage sequence and the set cutoff voltage.

[0085] In this embodiment, the predicted operating time period can refer to the duration from the current moment until the battery terminal voltage reaches the set cutoff voltage.

[0086] In the predicted terminal voltage sequence, find the cutoff time when the terminal voltage first equals the set cutoff voltage. The difference between this cutoff time and the current time is the predicted running time period.

[0087] This step allows us to determine the actual duration (charging or discharging) that the battery can continuously operate under the target planned conditions.

[0088] Step S1400: Determine the remaining available energy of the battery module based on the target predicted terminal voltage sequence and the target set current sequence within the predicted operating time period.

[0089] In this embodiment, the target predicted voltage sequence can be the portion of voltage data corresponding to the predicted operating time period in the predicted voltage sequence. The target set current sequence can be the portion of current data corresponding to the predicted operating time period in the set current sequence.

[0090] For each moment within the predicted operating period, the instantaneous power is obtained by multiplying the predicted terminal voltage by the set current. Then, the remaining usable energy of the battery module is obtained by integrating (or discretely summing) the results over the predicted operating period. Specifically, the integration formula is shown in formula (7): (7) in, Remaining available energy represents the energy that a battery module can release or absorb from its current state to the cutoff voltage under the target planned operating conditions. This is for predicting the terminal voltage. To set the current.

[0091] Since this remaining available energy is calculated based on the current state of the battery module (i.e., current battery temperature and current terminal voltage) and set operating data under planned future operating conditions, the result is more accurate and practical than SOE estimation based on fixed rated energy. This solves the problem of low estimation accuracy in related technologies' available energy estimation methods and improves the accuracy of estimating the available energy of battery modules.

[0092] Step S1500: Output the remaining available energy of the battery assembly.

[0093] In this embodiment, the remaining available energy value is output to a higher-level system, such as an energy management system (EMS), battery management system (BMS), or monitoring platform. This provides crucial data for battery system operation scheduling, market decision-making (such as electricity spot trading), and safety management.

[0094] In one embodiment of this application, after outputting the remaining available energy of the battery assembly in step S1500, the method further includes steps S1600 to S1800.

[0095] Step S1600: During the operation of the battery module, the actual operating data of the battery module is processed to obtain and store the training samples corresponding to the actual operating data; the actual operating data includes the measured current, measured terminal voltage, and measured battery module temperature at each moment within a set operating cycle.

[0096] In this embodiment, the processing of actual operating data in this step can refer to steps S3100.1 to S3100.3 above, and will not be elaborated here.

[0097] Step S1700: When a set event is triggered, the training sample set is updated according to the training samples corresponding to the actual running data to obtain the updated training sample set.

[0098] In one embodiment of this application, the setting event includes at least one of the following: The prediction error of the terminal voltage prediction model is greater than or equal to the error threshold. The time interval between the current time and the last model training time is greater than or equal to the time interval threshold.

[0099] In this embodiment, the prediction error of the terminal voltage prediction model can be the root mean square error between the predicted terminal voltage sequence and the measured terminal voltage sequence.

[0100] The error threshold can be flexibly designed by the designer.

[0101] The time interval threshold can be, for example, 90 days.

[0102] Step S1800: Retrain the terminal voltage prediction model using the updated training sample set to obtain the updated terminal voltage prediction model.

[0103] In this embodiment, the terminal voltage prediction model is retrained using the updated training sample set and the training method described in step S3200 to obtain the updated terminal voltage prediction model.

[0104] The training process incorporates voltage prediction error terms and physical equation residuals. See above for a detailed explanation; it will not be repeated here.

[0105] Based on the above, the terminal voltage prediction model can adaptively track the decay and drift of battery characteristics, maintain high-precision prediction capability over a long period of time, and thus ensure the reliability of remaining available energy estimation throughout the entire battery life cycle without relying on costly periodic offline testing.

[0106] <System Implementation Example> In some embodiments, such as Figure 4 As shown, a battery management system 400 is also provided, including a memory 410 and a processor 420. The memory 410 stores executable instructions for controlling the processor 420 to operate and execute the battery component available energy determination method in any of the above embodiments.

[0107] <Example of Electrical Equipment> like Figure 5 As shown, this embodiment of the present disclosure provides an electrical device 500, including a battery assembly 510 and a battery management system 400.

[0108] The battery management system 400 can be as follows: Figure 4 The battery management system shown.

[0109] Electrical equipment 500 can include vehicles, ships, energy storage cabinets, drones, electric two-wheelers, electric multi-wheelers, etc.

[0110] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the above method embodiments.

[0111] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0112] This disclosure may be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement any of the methods in the foregoing embodiments of this disclosure.

[0113] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media may include, for example, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), compact disc-read-only memory (CD-ROM), digital versatile disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any combination thereof. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0114] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include one or more of copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to computer-readable storage media in the respective computing / processing device.

[0115] The computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object programs written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as Smalltalk, C++, etc.) and conventional procedural programming languages ​​(such as the "C" language or similar programming languages). The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network (e.g., a local area network or a wide area network), or it may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays, or programmable logic arrays, can execute computer-readable program instructions to implement various aspects of the embodiments of this disclosure by utilizing state information from the computer-readable program instructions.

[0116] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0117] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0118] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It should be noted that implementation in hardware, implementation in software, and implementation using a combination of software and hardware are all equivalent.

[0120] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, and are not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of this disclosure is defined by the appended claims.

Claims

1. A method for determining the available energy of a battery assembly, characterized in that, include: The current terminal voltage and current battery temperature of the battery module are obtained, as well as the set operating data of the battery module within a set time period; the set time period is a time period with the current time as the starting time and the set operating data includes a set current sequence, a set temperature sequence, and a set cutoff voltage. Based on the current terminal voltage, the current battery temperature, and the set operating data, determine the predicted terminal voltage sequence of the battery module within the set time period; The predicted operating time period of the battery module is determined based on the predicted terminal voltage sequence and the set cutoff voltage. The remaining usable energy of the battery module is determined based on the target predicted terminal voltage sequence and the target set current sequence during the predicted operating period. Output the remaining usable energy of the battery assembly.

2. The method according to claim 1, characterized in that, The step of determining the predicted terminal voltage sequence of the battery module within the set time period based on the current terminal voltage, the current battery temperature, and the set operating data includes: The current terminal voltage, current battery temperature, and the set operating data are input into the terminal voltage prediction model to obtain the predicted terminal voltage sequence of the battery module within the set time period. The terminal voltage prediction model includes an open-circuit voltage estimation module, a model parameter prediction module, and an equivalent circuit model. The open-circuit voltage estimation module is used to determine the estimated open-circuit voltage value based on the current terminal voltage and the current battery temperature, and to reversely determine the current state of charge of the battery module by comparing the estimated open-circuit voltage value with the current terminal voltage. The model parameter prediction module is used to determine the current model parameters of the equivalent circuit model of the battery assembly based on the current state of charge and the current battery temperature. The equivalent circuit model is used to determine the charge state at the next moment based on the charge state at the previous moment and the set current at the previous moment, taking the current charge state as the starting point for rapid propagation, so as to obtain the charge state corresponding to each step. The equivalent circuit model is also used to determine the polarization voltage at the next moment based on the model parameters and the set current at the previous moment, taking the current polarization voltage as the starting point for rapid propagation, and thus obtaining the polarization voltage corresponding to each step. The open-circuit voltage estimation module is also used to determine the open-circuit voltage corresponding to each step based on the state of charge and battery temperature corresponding to each step. The model parameter prediction module is also used to determine the model parameters corresponding to each step based on the state of charge and battery temperature corresponding to each step. The equivalent circuit model is also used to determine the predicted terminal voltage for each step based on the model parameters, polarization voltage, open-circuit voltage, and set current, thereby obtaining the predicted terminal voltage sequence.

3. The method according to claim 2, characterized in that, The terminal voltage prediction model is trained through the following steps: Obtain a training sample set; wherein, each training sample in the training sample set includes the initial terminal voltage of the sample, the initial battery temperature of the sample, the sample running data, and the sample terminal voltage sequence, and the sample running data includes the sample current sequence and the sample battery temperature sequence; The training sample set is used to train the terminal voltage prediction model, resulting in the trained terminal voltage prediction model.

4. The method according to claim 3, characterized in that, The acquisition of the training sample set includes: Historical operating data of the sample battery module under different operating conditions are obtained to obtain an operating dataset; the historical operating data includes the sample current, sample terminal voltage and sample battery temperature of the sample battery module at each moment within a set operating cycle. For any historical running data, the historical running data is divided into multiple sub-running data segments at a set time interval; For any sub-running data segment, the sample initial terminal voltage, sample initial battery temperature, sample battery temperature sequence, sample current sequence, and sample terminal voltage sequence corresponding to the sub-running data segment are used as a training sample to obtain the training sample set corresponding to the running dataset.

5. The method according to claim 3, characterized in that, The loss function during model training includes voltage prediction error terms and physical equation residual terms; The voltage prediction error term is calculated by the difference between the terminal voltage sequence predicted by the calculation model and the sample terminal voltage sequence. The residual terms of the physical equations are calculated by the difference between the rate of change of the polarization voltage within the model and the rate of change of the reference voltage.

6. The method according to any one of claims 1 to 5, characterized in that, After determining the remaining available energy of the battery assembly, the method further includes: During the operation of the battery assembly, the actual operating data of the battery assembly is stored; the actual operating data includes the measured current, measured terminal voltage, and measured battery assembly temperature at each moment within a set operating cycle. When a set event is triggered, the training sample set is updated based on the actual operating data of the battery component to obtain the updated training sample set. The updated terminal voltage prediction model is obtained by retraining the updated training sample set.

7. The method according to claim 6, characterized in that, The set event includes at least one of the following: The prediction error of the terminal voltage prediction model is greater than or equal to the error threshold. The time interval between the current time and the last model training time is greater than or equal to the time interval threshold.

8. A battery management system, characterized in that, It includes a memory and a processor, the memory storing executable instructions for controlling the processor to operate in order to perform the method according to any one of claims 1-7.

9. An electrical appliance, characterized in that, Includes the battery assembly and the battery management system as described in claim 8.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

Images