SOC calculation method, detection component, system and device for rechargeable battery
By obtaining the status information and pressure information of the rechargeable battery, combining voltage and current information, using the pressure-SOC table and model for SOC calculation, the problem of increasing SOC estimation error in the prior art is solved, and higher calculation accuracy is achieved and operational efficiency.
Patent Information
- Application Number
- CN202410881707.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-03
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-03
AI Technical Summary
In the prior art, the estimation error of the rechargeable battery SOC increases with the use time, and it is difficult to obtain an accurate SOC value.
By obtaining the status information of the rechargeable battery to be tested, selecting the corresponding SOC calculation strategy, combining voltage information, current information and pressure information for calculation, and using the pressure-SOC table and model for SOC calculation, including the static state and charge and discharge state. Strategy, using CNN-LSTM or GRU-Attention model for training to develop a stress-SOC model.
It improves the accuracy of SOC calculations, reduces estimation errors, can more accurately identify battery status, optimizes SOC display effect, prevents SOC jumps, and improves operational efficiency and customer experience.
Smart Images

Figure CN118409225B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of rechargeable battery detection, and in particular to a SOC calculation method, detection component, system, and device for a rechargeable battery. Background Art
[0002] With the rapid development of the domestic new energy industry, the installed capacity of electrochemical energy storage is increasing. As an important part of the development of new energy, new energy batteries have been widely used in people's daily lives, such as new energy vehicles that use rechargeable battery packs as power sources, and energy storage stations that use rechargeable batteries as energy storage.
[0003] During use, the state of the rechargeable battery is usually tested to determine its performance and reliability. The remaining capacity (state of charge, SOC) of the rechargeable battery is one of the important indicators to characterize the battery state. At present, the common SOC estimation method is the ampere-hour integration method. However, when the ampere-hour integration method is used to estimate the SOC of the rechargeable battery, the estimation error will gradually increase with the use time of the rechargeable battery. Based on this, how to correct the SOC value of the rechargeable battery to obtain a more accurate SOC value has become a problem that needs to be solved urgently. Summary of the invention
[0004] The embodiments of the present application provide a method, a detection component, a system, and a device for calculating the SOC of a rechargeable battery, which are used to solve the technical problem that the estimation result is not accurate enough when estimating the SOC of a rechargeable battery.
[0005] To this end, according to one aspect of an embodiment of the present application, a method for calculating the SOC of a rechargeable battery is provided, and the method for calculating the SOC of a rechargeable battery includes: obtaining state information of a rechargeable battery to be tested; selecting a corresponding SOC calculation strategy according to the state information of the rechargeable battery to be tested; obtaining voltage information, current information and pressure information of the rechargeable battery to be tested; calculating the SOC of the rechargeable battery to be tested according to the SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested, in combination with the voltage information, current information and pressure information of the rechargeable battery to be tested; wherein the state information of the rechargeable battery to be tested includes a static state and a charge and discharge state, and the SOC calculation strategy includes a static state calculation strategy corresponding to the static state and a charge and discharge state calculation strategy corresponding to the charge and discharge state.
[0006] Optionally, when the state of the rechargeable battery to be tested is a static state, the specific method for calculating the SOC of the rechargeable battery to be tested according to the static state calculation strategy corresponding to the static state is: according to the pressure-SOC table in the static state, combined with the pressure information of the rechargeable battery to be tested, obtain the SOC value corresponding to the pressure information of the rechargeable battery to be tested; wherein, the pressure information is the pressure magnitude, and the pressure-SOC table is a correspondence table between the pressure magnitude and the SOC value.
[0007] Optionally, the pressure-SOC table in the static state is obtained by the following method: charging or discharging a battery of the same model as the rechargeable battery to be tested, stopping charging or discharging when the battery reaches a preset SOC value, and obtaining the pressure of the battery after being static.
[0008] Optionally, when the state of the rechargeable battery to be tested is a charging state or a discharging state, the method for calculating the SOC of the rechargeable battery to be tested according to the charging and discharging state calculation strategy corresponding to the charging and discharging state is: judging whether the rechargeable battery to be tested is in a charging state or a discharging state; calculating the SOC value according to the pressure-SOC model under the charging and discharging state combined with the voltage information, current information and pressure information of the rechargeable battery to be tested.
[0009] Optionally, the pressure-SOC model under the charge and discharge state is obtained by the following method: charging and discharging a battery of the same model as the rechargeable battery to be tested for multiple times, obtaining the SOC value, pressure information, voltage information and current information of the battery under multiple charges and discharges as a data set, selecting part of the data in the data set as training set data, and normalizing the training set data; training the training set data through a network training model; outputting the training results, and formulating the pressure-SOC model.
[0010] Optionally, the network training model includes any one of a CNN-LSTM model, a GRU-Attention model or a CNN-BILSTM model. CNN stands for Convolutional Neural Networks, LSTM stands for Long Short-Term Memory, GRU stands for Gate Recurrent Unit, Attention stands for Attention Mechanism, and BILSTM stands for Bi-directional Long Short-Term Memory.
[0011] Optionally, the network training model uses a CNN-LSTM network with an Attention mechanism to train the training set data.
[0012] Optionally, training the training set data through a CNN-LSTM network with an Attention mechanism includes: processing the training set data through CNN to extract features with local spatial invariance to form a local feature set; dynamically focusing on different parts of the local feature set through Attention, calculating the importance weight of each feature, weighting the features, and highlighting important features; capturing and modeling the dependencies in the time series through LSTM to handle long-term memory and short-term memory problems in the sequence data.
[0013] Optionally, there is a corresponding relationship between the rechargeable battery to be tested and the SOC calculation strategy, and before calculating the SOC of the rechargeable battery to be tested, the method further includes the following steps: acquiring the SOC calculation strategy corresponding to the rechargeable battery to be tested.
[0014] According to another aspect of an embodiment of the present application, a detection component is provided, which calculates the SOC of a rechargeable battery to be tested by the above-mentioned SOC calculation method of a rechargeable battery; the detection component includes a data acquisition unit and a detection unit, and the data acquisition unit is communicatively connected with the detection unit; the data acquisition unit includes at least a thin film pressure sensor, a voltage collector and a current collector, the thin film pressure sensor is used to collect pressure information of the rechargeable battery to be tested, the voltage collector is used to collect voltage information of the rechargeable battery to be tested, and the current collector is used to collect current information of the rechargeable battery to be tested; the detection unit includes at least an SOC calculation unit, and the SOC calculation unit calculates the SOC of the rechargeable battery to be tested according to an SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested, in combination with the voltage information, current information and pressure information of the rechargeable battery to be tested.
[0015] According to another aspect of an embodiment of the present application, a system for calculating the SOC of a rechargeable battery is provided. The system calculates the SOC of a rechargeable battery to be tested by using the above-mentioned method for calculating the SOC of a rechargeable battery.
[0016] According to another aspect of an embodiment of the present application, a SOC calculation device for a rechargeable battery is provided, the device comprising a rechargeable battery to be tested and the above-mentioned detection component, wherein the detection component is used to calculate the SOC of the rechargeable battery to be tested.
[0017] The SOC calculation method of the rechargeable battery provided in the embodiment of the present application has the beneficial effect that: in the embodiment of the present application, the SOC value of the rechargeable battery to be tested is calculated by obtaining the pressure information of the rechargeable battery to be tested, and the pressure information will not have a voltage platform area, and will not be disturbed by the current acquisition error, the estimation error is smaller, and the accuracy is higher. It can be understood that by improving the accuracy of the SOC value calculation, on the one hand, a larger charge and discharge window can be used to achieve full charge or full discharge of the rechargeable battery, improving operational efficiency and revenue; on the other hand, the SOC display effect can be optimized to prevent the battery's SOC from jumping, further improving the customer's experience. At the same time, when the SOC of the rechargeable battery to be tested is calculated based on the pressure information of the rechargeable battery to be tested, the state of the rechargeable battery is divided into a static state and a charge and discharge state, so that the corresponding SOC calculation strategy can be selected by identifying the state of the rechargeable battery, which can further improve the accuracy of the SOC value calculation of the rechargeable battery.
[0018] Similarly, a detection component using the SOC calculation method of a rechargeable battery, a system using the SOC calculation method of a rechargeable battery, and a device using the detection component also have the above advantages. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0020] in:
[0021] Figure 1 It is a schematic flow chart of a method for calculating the SOC of a rechargeable battery shown in an embodiment of the present application;
[0022] Figure 2 It is a schematic diagram of pressure changes detected by a thin-film pressure sensor during multiple charge and discharge cycles of a rechargeable battery shown in an embodiment of the present application;
[0023] Figure 3 is a schematic diagram of changes in pressure, voltage and capacity of a rechargeable battery during a single charge and discharge cycle shown in an embodiment of the present application;
[0024] Figure 4 is a schematic diagram of pressure change of a rechargeable battery from a charging and discharging state to a static state shown in an embodiment of the present application;
[0025] Figure 5It is a schematic diagram of a flow chart showing a method of calculating the SOC of a rechargeable battery to be tested by a static state calculation strategy according to an embodiment of the present application;
[0026] Figure 6 is a schematic diagram of a pressure-SOC table of a rechargeable battery shown in an embodiment of the present application;
[0027] Figure 7 It is a schematic diagram of a flow chart showing a method of calculating the SOC of a rechargeable battery to be tested by a charge and discharge state calculation strategy according to an embodiment of the present application;
[0028] Figure 8 It is a flow chart of a pressure-SOC model for obtaining a charge-discharge state shown in an embodiment of the present application;
[0029] Fig. 9 It is a schematic diagram of the pressure change of a rechargeable battery detected by a thin film pressure sensor during multiple charge and discharge cycles shown in an embodiment of the present application;
[0030] Fig.10 is a flow chart of another method for calculating the SOC of a rechargeable battery shown in an embodiment of the present application;
[0031] Fig.11 It is a module schematic diagram of the detection component shown in the embodiment of the present application. DETAILED DESCRIPTION
[0032] In order to facilitate the understanding of the present application, the present application will be described more comprehensively with reference to the relevant drawings below. The preferred embodiments of the present application are provided in the drawings. However, the present application can be implemented in many other different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive.
[0033] It should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.
[0034] It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.
[0035] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.
[0037] It should also be noted that, in the embodiments of the present application, the same figure mark is used to represent the same component or the same part. For the same parts in the embodiments of the present application, the figure may only mark one of the parts or components as an example. It should be understood that the figure mark also applies to other identical parts or components.
[0038] The remaining capacity (SOC) of a rechargeable battery is one of the important indicators that characterize the battery status. The common SOC estimation method in related technologies is the ampere-hour integration method. However, when the ampere-hour integration method is used to estimate the SOC of a rechargeable battery, the estimation error will gradually increase with the use time of the rechargeable battery.
[0039] See also Figure 1 In order to further improve the accuracy of the SOC estimation of the rechargeable battery, the embodiment of the present application provides a method for calculating the SOC of the rechargeable battery to calculate the SOC of the rechargeable battery to be tested. The method mainly includes the following steps:
[0040] Obtaining status information of the rechargeable battery to be tested;
[0041] Selecting a corresponding SOC calculation strategy according to the state information of the rechargeable battery to be tested;
[0042] Obtaining voltage information, current information and pressure information of the rechargeable battery to be tested;
[0043] The SOC of the rechargeable battery to be tested can be calculated according to an SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested and in combination with the voltage information, current information and pressure information of the rechargeable battery to be tested.
[0044] The state information of the rechargeable battery to be tested includes a static state and a charge-discharge state, and the SOC calculation strategy includes a static state calculation strategy corresponding to the static state and a charge-discharge state calculation strategy corresponding to the charge-discharge state.
[0045] In the embodiment of the present application, the static state refers to a state in which the external device does not charge the rechargeable battery or the rechargeable battery does not provide power to the external device.
[0046] In one embodiment of the present application, the voltage information of the rechargeable battery to be tested refers to the charging voltage of the rechargeable battery, or the current voltage; the current information of the rechargeable battery to be tested refers to the charging current, or the discharge current of the rechargeable battery; the pressure information of the rechargeable battery to be tested refers to the pressure size information, and / or the information on the change of pressure over time, and / or the information on the change of pressure with current.
[0047] In the embodiment of the present application, the SOC of the rechargeable battery to be tested can be calculated by a battery management system (BMS), a processor, or other systems. For ease of description, the following example is taken as an example of the battery management system calculating the SOC of the rechargeable battery to be tested, but it is not intended to be limiting.
[0048] In the embodiment of the present application, the state of the rechargeable battery to be tested can be judged by the battery management system, that is, the battery management system can judge whether the rechargeable battery to be tested is in a static state or a charging and discharging state. The relevant technology of judging the state of the rechargeable battery to be tested by the battery management system is a relatively mature technology in the field, and will not be described in detail here.
[0049] It is understandable that the voltage information, current information and pressure information of the rechargeable battery to be tested can be obtained through the battery management system. Among them, the relevant technology of obtaining the voltage information and current information of the rechargeable battery through the battery management system is a relatively mature technology in the field and will not be described in detail here.
[0050] In the present application, as an implementation mode, the pressure information of the rechargeable battery to be tested is obtained by a thin film pressure sensor, and the thin film pressure sensor is connected to the battery management system in communication to transmit the obtained pressure information to the battery management system. The thin film pressure sensor can be arranged between the rechargeable battery to be tested and other rechargeable batteries; the thin film pressure sensor can also be arranged between the rechargeable battery to be tested and its adjacent shell. Taking lithium-ion batteries as an example, when lithium-ion batteries are charged, as lithium ions are continuously embedded, the active particles on the negative electrode undergo corresponding volume expansion, and these volume expansions will cause the battery to squeeze the thin film pressure sensor, and then the size of the squeezing force can be obtained through the thin film pressure sensor. Among them, the thin film pressure sensor can be set as a pressure sensor covering a partial area of the rechargeable battery to be tested to obtain the pressure size of the area of the rechargeable battery to be tested; the thin film pressure sensor can also be set as a single-point pressure sensor to obtain the pressure size of a certain point of the rechargeable battery to be tested.
[0051] In the present application, as an implementation method, the SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested can be stored in the battery management system in advance, and the SOC of the rechargeable battery to be tested is calculated by the battery management system. Of course, in other implementation methods, the SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested can also be stored in the cloud, and when the battery management system calculates the SOC of the rechargeable battery to be tested, the battery management system obtains the SOC calculation strategy corresponding to the rechargeable battery to be tested from the cloud.
[0052] Please combine Figure 2 and Figure 3 , experiments have shown that, affected by the coupling relationship between the particle phase change and volume expansion generated during the insertion and extraction of lithium ions in the positive electrode lithium iron phosphate material and the negative electrode graphite material, the pressure curve of the rechargeable battery presents regular and repeatable changes during the multiple charge and discharge processes of the rechargeable battery. Therefore, in the embodiment of the present application, the SOC value of the rechargeable battery to be tested is calculated by obtaining the pressure information of the rechargeable battery to be tested. The pressure information will not have a voltage platform area, and will not be affected by the current acquisition error. The estimation error is smaller and the accuracy is higher. It can be understood that by improving the accuracy of the SOC value calculation, on the one hand, a larger charge and discharge window can be used to achieve full charge or full discharge of the rechargeable battery, thereby improving operational efficiency and revenue; on the other hand, the SOC display effect can be optimized to prevent the battery's SOC from jumping, further improving the customer experience.
[0053] Taking lithium-ion batteries as an example, when lithium-ion batteries are turned from the charge and discharge stage to static state, the negative electrode lithium insertion and removal phenomena will occur with the relaxation process, and the negative electrode lithium will dissolve and retreat, commonly known as the lithium withdrawal process. This process will cause the negative electrode lithium insertion compound (LiCx) intermediate phase to also undergo a relaxation discontinuous phase transition retreat, causing the negative electrode expansion thickness to retreat during the relaxation stage. Among them, LiCx is formed when the lithium ions of the positive electrode active material are released under the action of external voltage during charging, and the lithium ions migrate and diffuse to the negative electrode through the electrolyte and are embedded in the negative electrode surface or bulk phase. Please refer to Figure 4 , Figure 4 The horizontal axis represents time (time, T), and the vertical axis represents pressure (F), and the unit of pressure is kilogram-force (kgf). Experiments have shown that the above changes will cause the expansion force applied to the thin film pressure sensor to change. Simply put, when the rechargeable battery changes from a charge and discharge state to a static state, the rechargeable battery will reduce the pressure applied to the thin film pressure sensor. Therefore, the pressure change law of the rechargeable battery in the charge and discharge state is different from the pressure change law in the static state. However, the calculation of SOC is full-time, that is, as long as the rechargeable battery is powered on, regardless of whether it is in a charge and discharge state or a static state, the SOC value of the rechargeable battery must be calculated. Therefore, in an embodiment of the present application, when the SOC of the rechargeable battery is calculated based on the pressure information of the rechargeable battery, the state of the rechargeable battery is divided into a static state and a charge and discharge state, so that the corresponding SOC calculation strategy can be selected by identifying the state of the rechargeable battery, which can further improve the accuracy of the calculation of the SOC value of the rechargeable battery.
[0054] See also Figure 5 As a feasible implementation method, when the state of the rechargeable battery to be tested is a static state, the specific method for calculating the SOC of the rechargeable battery to be tested according to the static state calculation strategy corresponding to the static state is:
[0055] According to the pressure-SOC table in the static state, combined with the pressure information of the rechargeable battery to be tested, an SOC value corresponding to the pressure information of the rechargeable battery to be tested is obtained.
[0056] The pressure information is the pressure magnitude, and the pressure-SOC table is a corresponding relationship table between the pressure magnitude and the SOC value.
[0057] It is understandable that when the rechargeable battery is in a static state, the external device does not charge the rechargeable battery, and the rechargeable battery does not provide power to the external device. At this time, there is a one-to-one correspondence between the pressure applied by the rechargeable battery on the thin-film pressure sensor and its SOC value, and the corresponding relationship between the SOC value and the pressure in this state can be obtained in advance through experiments. Therefore, in this state, the corresponding SOC value can be found only by obtaining the pressure and combining it with the pressure-SOC table. It is understandable that using this method to calculate the SOC value of the rechargeable battery in a static state can further improve the calculation efficiency while taking into account the calculation accuracy.
[0058] As a feasible implementation method, the pressure-SOC table in the static state can be obtained by the following method: charge or discharge a battery of the same model as the rechargeable battery to be tested, stop charging or discharging when the battery reaches a preset SOC value, and obtain the pressure size of the battery after it is static.
[0059] It can be understood that during the initial relaxation period of charging of a rechargeable battery, the thickness of the negative electrode decreases due to the initial phase change regression; in the middle of charging, the thickness of the negative electrode changes relatively slowly due to the phase change regression; at the end of charging, the thickness of the negative electrode decreases due to the phase change regression; the change in thickness of the negative electrode during the relaxation stage of the discharge process is opposite to the above stage. In addition, at the end of charging and discharging, the increase in non-uniformity caused by the concentration difference of lithium ions (Li+) in the solid phase leads to more intense phase change withdrawal behavior at the end of charging and discharging, causing the corresponding stage thickness withdrawal change to be more significant. In other words, the pressure changes caused by the withdrawal phenomenon of the rechargeable battery after standing at different SOC values are quite different. By detecting the corresponding pressure size of the rechargeable battery, the SOC value of the rechargeable battery can be accurately mapped. Therefore, in this embodiment, by changing the size of the SOC value, the pressure size data corresponding to different SOC values can be obtained, and these data can be summarized to obtain a pressure-SOC table. As Figure 6 As shown, it is a schematic diagram of a pressure-SOC table of a rechargeable battery. Figure 6 The F in it stands for pressure.
[0060] See also Figure 7 As a feasible implementation method, when the state of the rechargeable battery to be tested is a charging state or a discharging state, the specific method for calculating the SOC of the rechargeable battery to be tested according to the charge and discharge state calculation strategy corresponding to the charge and discharge state is:
[0061] Determine whether the rechargeable battery to be tested is in a charging state or a discharging state;
[0062] The SOC value is calculated according to the pressure-SOC model under the charge and discharge state combined with the voltage information, current information and pressure information of the rechargeable battery to be tested.
[0063] The pressure-SOC model may be a preset curve, the horizontal coordinate of the curve is the pressure magnitude, or the change of pressure over time, or the change of pressure over current, and the vertical coordinate of the curve is the SOC value. The pressure-SOC model may also be a preset calculation model, and the SOC value may be calculated by inputting pressure information. The calculation model may be a linear equation or a nonlinear equation related to the pressure information and the SOC.
[0064] Among them, the pressure-SOC model can be a model with pressure magnitude, current information and voltage information as input parameters; the pressure-SOC model can also be a model with pressure magnitude, the magnitude of pressure change with current, voltage information and current information as input parameters; the pressure-SOC model can also be a model with pressure magnitude, the magnitude of pressure change with time, the magnitude of pressure change with current, voltage information and current information as input parameters.
[0065] Please continue reading Figure 2 and Figure 3 , Figure 2 and Figure 3 The horizontal axis represents time (time, T), and the vertical axis represents pressure (F). The unit of pressure is kilogram-force (kgf). Figure 3 The unit of electricity (ampere-hour, Ah) is also shown. It can be understood that during the charging and discharging process of lithium-ion batteries, the insertion and extraction of lithium ions in the electrode active material will cause the battery to expand and contract. However, from the perspective of the SOC change of the battery, the expansion and contraction of the battery are not completely symmetrical, that is, when the rechargeable battery is charged from a 20% SOC state to a 30% SOC state, the pressure or pressure change detected by the thin film pressure sensor may be different from the pressure or pressure change detected by the thin film pressure sensor when the rechargeable battery is discharged from a 40% SOC state to a 30% SOC state. At the same time, there is also a certain pressure information that corresponds to a certain SOC in the charging state and another SOC in the discharging state, and the SOCs in these two states are not the same. Therefore, in the embodiment, by judging whether the rechargeable battery is in a charging state or a discharging state, a more accurate SOC calculation result can be further obtained. Of course, in other embodiments, the charging and discharging state of the rechargeable battery can be directly analyzed and judged without directly analyzing and judging the charging and discharging state of the rechargeable battery, and the charging and discharging state of the rechargeable battery can be directly obtained by bringing in current information. It can be understood that the current information can be used to intuitively determine whether the rechargeable battery is being charged or discharged.
[0066] See also Figure 8 As an implementation method, the pressure-SOC model under the charge and discharge state can be obtained by the following method:
[0067] Perform multiple charge and discharge on a battery of the same model as the rechargeable battery to be tested, obtain the SOC value, pressure information, voltage information and current information of the battery under multiple charge and discharge as a data set, select part of the data in the data set as training set data, and perform normalization on the training set data;
[0068] Train the training set data through the network training model;
[0069] Output the training results and formulate the stress-SOC model.
[0070] It is understandable that the training set data contains data information of multiple dimensions. In order to eliminate the scale effect between different data information and ensure the comparability between data indicators, the training data is normalized in the embodiment of the present application, so that the data can be scaled to the same range, eliminating the dimensional differences between features, thereby improving the performance and stability of subsequent models. As a feasible implementation method, the training set data is scaled to between -1 and 1.
[0071] As an implementation method, the network training model includes any one of a CNN-LSTM model, a GRU-Attention model or a CNN-BILSTM model.
[0072] It is understandable that convolutional neural networks (CNNs) are good at extracting features from local receptive fields. The network can efficiently process high-dimensional data (such as local fragments of images or time series) and extract features with local spatial invariance. Usually, a CNN network includes an input layer, a convolution layer, an activation layer, a pooling layer, a fully connected layer, and an output layer. By processing the training set data through a convolutional neural network (CNN), features with local spatial invariance can be extracted to form a local feature set, which provides favorable data support for the subsequent construction of a pressure-SOC model.
[0073] It can be understood that the attention mechanism (Attention) can dynamically focus on different parts of the input data, calculate the importance weight of each feature, and weight the features, thereby highlighting important features. It can also capture the relationship between distant elements in the sequence, which is conducive to improving the expressiveness and accuracy of the model. The attention mechanism can help the model pay more attention to important parts in a complex data feature space, and is very suitable for multimodal time series data for battery SOC estimation. In an embodiment of the present application, the network training model adds an attention mechanism based on GRU, and the GRU-Attention model can improve the model calculation accuracy of the pressure-SOC model.
[0074] It can be understood that the long short-term memory neural network (LSTM) can capture and model the dependencies existing in the time series, and is good at processing long-term memory and short-term memory problems in sequence data. The long short-term memory neural network effectively alleviates the gradient vanishing problem through its gating mechanism, so that the model can maintain stable learning ability in a longer sequence, mainly through the input gate, forget gate, and output gate. The operation of these gate structures enables the long short-term memory neural network to retain and transmit past information without easily forgetting it, thereby having excellent long-term and short-term memory capabilities. In an embodiment of the present application, by adding a long short-term memory neural network (LSTM) to the network training model, the dependencies existing in the time series are captured and modeled by the long short-term memory neural network (LSTM), which can more effectively process complex time series data, and further improve the SOC calculation ability and accuracy of the pressure-SOC model.
[0075] Take lithium batteries as an example. During the cyclic use, lithium batteries will continue to age, their capacity will gradually decay, and their appearance will gradually expand irreversibly. The changing pattern of these irreversible expansions is correlated to the changing trend of the pressure exerted by the lithium battery on the thin-film pressure sensor. Fig. 9 , Fig. 9 The horizontal axis represents the remaining power (SOC), and the vertical axis represents the pressure (F), and the unit of pressure is kilogram-force (kgf). Fig. 9 The pressure change of the rechargeable battery detected by the thin film pressure sensor under multiple charge and discharge cycles is Fig. 9 It can be seen that the change trend of the pressure data under any two complete charge and discharge of the rechargeable battery is basically the same. However, as the number of cycles increases, the irreversible expansion of the lithium battery increases, and the extrusion force between the lithium batteries or between the lithium batteries and the inner wall of the adjacent shell will gradually increase. Therefore, during the long-term use of the rechargeable battery, although the pressure change maintains the same trend in the same SOC change interval, the pressure detected at the same SOC value may not be the same. Therefore, in an embodiment of the present application, by adding a long short-term memory neural network (LSTM) to the network training model, the long short-term memory neural network (LSTM) is used to capture and model the dependencies in the time series, which can more effectively process complex time series data, and further improve the SOC calculation ability and accuracy of the pressure-SOC model.
[0076] As a specific implementation method, the network training model uses a CNN-LSTM network with an Attention mechanism to train the training set data.
[0077] Specifically, training the training set data through the CNN-LSTM network with the Attention mechanism includes:
[0078] The training set data is processed by convolutional neural network (CNN) to extract features with local spatial invariance and form a local feature set;
[0079] Through the attention mechanism, we dynamically focus on different parts of the local feature set, calculate the importance weight of each feature, weight the features, and highlight the important features;
[0080] The long short-term memory neural network (LSTM) is used to capture and model the dependencies in time series and deal with long-term memory and short-term memory problems in sequence data.
[0081] It can be understood that in this embodiment, the network training model uses a CNN-LSTM network with an Attention mechanism to train the training set data and formulate a pressure-SOC model. By combining the advantages of the CNN network, the LSTM network and the Attention mechanism, the CNN network is used to first perform efficient local feature extraction and dimensionality reduction on the data, and the LSTM network is used to capture and model long-term dependencies in the time series. The Attention mechanism is used to realize dynamic weighted features to improve the prediction accuracy and robustness of the pressure-SOC model. In this way, the pressure-SOC model can more effectively process complex time series data, further improving the SOC calculation capability and accuracy of the pressure-SOC model.
[0082] See also Fig.10 In one embodiment, there is a corresponding relationship between the rechargeable battery to be tested and the SOC calculation strategy, and before calculating the SOC of the rechargeable battery to be tested, the following steps are also included:
[0083] Obtain the SOC calculation strategy corresponding to the rechargeable battery to be tested.
[0084] It is understandable that when conducting experiments on different types of rechargeable batteries, different types of rechargeable batteries may correspond to different pressure data at the same SOC value, so the training set data used for the network training model needs to be selected according to the corresponding rechargeable battery. In other words, for different types of rechargeable batteries, only the training set data used for training needs to be adjusted, and the method for the network training model to train the training set data is universal. In this way, the network training model can formulate a pressure-SOC model corresponding to the rechargeable battery by training with the training set data corresponding to the rechargeable battery. At the same time, by charging or discharging different types of rechargeable batteries, stopping charging or discharging when the battery reaches a preset SOC value, and obtaining the pressure size of the battery after standing for a certain period of time, the pressure-SOC table corresponding to different types of rechargeable batteries can be obtained.
[0085] It can be understood that by conducting experiments on different types of rechargeable batteries, SOC calculation strategies corresponding to different rechargeable batteries, namely pressure-SOC models and pressure-SOC tables, can be obtained. These SOC calculation strategies are marked so that there is a one-to-one correspondence between them and different types of rechargeable batteries. Therefore, when these SOC calculation strategies are stored in the same folder or in the cloud, the battery management system can obtain the SOC calculation strategy corresponding to the rechargeable battery to be tested by identifying the marking information. For example, when these SOC calculation strategies are stored in the cloud, the battery management system records the marking information corresponding to the rechargeable battery to be tested. The battery management system can find the corresponding SOC calculation strategy in the cloud through the marking information and call up and use the SOC calculation strategy.
[0086] Furthermore, since different rechargeable batteries have different identity information, the specific type of the rechargeable battery to be tested can be identified through the identity information, and the identity information of the rechargeable battery to be tested can be its model or number. As an implementation mode, in this embodiment, the SOC calculation strategy corresponding to the model of the rechargeable battery to be tested is obtained.
[0087] See also Fig.11 The second embodiment of the present application further provides a detection component, which calculates the SOC of the rechargeable battery to be tested by the SOC calculation method of the rechargeable battery in the first embodiment. The SOC calculation method and beneficial effects of the rechargeable battery to be tested in the first embodiment have been described above and will not be repeated here.
[0088] The detection component includes a data acquisition unit and a detection unit, and the data acquisition unit is communicatively connected with the detection unit. The data acquisition unit includes at least a thin film pressure sensor, a voltage collector and a current collector. The thin film pressure sensor is used to collect pressure information of the rechargeable battery to be tested, the voltage collector is used to collect voltage information of the rechargeable battery to be tested, and the current collector is used to collect current information of the rechargeable battery to be tested. The detection unit includes at least a SOC calculation unit, and the SOC calculation unit calculates the SOC of the rechargeable battery to be tested according to a SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested, combined with the voltage information, current information and pressure information of the rechargeable battery to be tested.
[0089] As an implementation mode, the SOC calculation strategy may be stored in the detection unit, and when calculating the SOC of the rechargeable battery to be detected, the SOC calculation unit directly calls the SOC calculation strategy.
[0090] As another implementation, the SOC calculation strategy can be stored in the cloud, and the detection unit is connected to the cloud in communication. When calculating the SOC of the rechargeable battery to be tested, the cloud responds to the detection unit, and the detection unit obtains the SOC calculation strategy corresponding to the identity information of the rechargeable battery to be tested. The SOC calculation unit calculates the SOC of the rechargeable battery to be tested according to the SOC calculation strategy combined with the voltage information, current information and pressure information of the rechargeable battery to be tested.
[0091] In the embodiment of the present application, the detection unit can be connected to a data acquisition unit for communication, and the detection unit can also be connected to multiple data acquisition units for communication. Taking the battery status detection device applied to a new energy vehicle as an example for explanation, as an implementation mode, the detection unit corresponds to a data acquisition unit, and the data acquisition unit and the detection unit are both arranged on a new energy vehicle. The detection unit can be a vehicle battery management system (BMS) of the new energy vehicle, and the SOC value of the rechargeable battery to be tested on the new energy vehicle is calculated by obtaining the voltage information, current information and pressure information of the rechargeable battery to be tested.
[0092] As another implementation, the detection unit corresponds to multiple data acquisition units, and the multiple data acquisition units are respectively arranged on multiple new energy vehicles. The detection unit is separately arranged and communicatively connected with the vehicle battery management systems of the multiple new energy vehicles. The detection unit obtains the voltage information, current information and pressure information on the new energy vehicle, calculates the SOC of the rechargeable battery to be tested through the SOC calculation strategy, and the detection unit feeds back the calculation results to the corresponding vehicle battery management system.
[0093] The third embodiment of the present application further provides a SOC calculation system for a rechargeable battery, which calculates the SOC of the rechargeable battery to be tested by the SOC calculation method for the rechargeable battery in the first embodiment. The specific steps and beneficial effects of the SOC calculation method for the rechargeable battery in the first embodiment have been described above and will not be repeated here.
[0094] The SOC calculation system of the rechargeable battery may be an energy storage system, a battery management system, or a battery operation management system.
[0095] The fourth embodiment of the present application also provides a SOC calculation device for a rechargeable battery, the SOC calculation device for a rechargeable battery comprising a rechargeable battery to be tested and the above-mentioned detection device, the detection device calculates the SOC of the rechargeable battery to be tested by the SOC calculation method of the rechargeable battery in the first embodiment. The structure of the detection device and the SOC calculation method of the rechargeable battery have been described above and will not be repeated here.
[0096] The device may be a vehicle whose kinetic energy is provided by a rechargeable battery, a flying device whose kinetic energy is provided by a rechargeable battery, or an electronic product whose electrical energy is provided by a rechargeable battery.
[0097] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0098] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
[0099] In the several embodiments provided in the present application, it should be understood that the disclosed systems, systems and methods can be implemented in other ways. For example, the division of the unit is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling, direct coupling, or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the system or unit can be electrical, mechanical or other forms.
[0100] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media integrations. The available medium may be a read-only memory (ROM), or a random access memory (RAM), or a magnetic medium, such as a floppy disk, a hard disk, a tape, a magnetic disk, or an optical medium, such as a digital versatile disc (DVD), or a semiconductor medium, such as a solid state disk (SSD), etc.
Claims
1. A method for calculating the SOC of a rechargeable battery, characterized in that: The method comprises: Obtaining status information of the rechargeable battery to be tested; Selecting a corresponding SOC calculation strategy according to the state information of the rechargeable battery to be tested; Acquiring voltage information, current information and pressure information of the rechargeable battery to be tested; the pressure information is the pressure of a partial area or a preset point of the rechargeable battery to be tested; Calculating the SOC of the rechargeable battery to be tested according to an SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested, in combination with the voltage information, current information and pressure information of the rechargeable battery to be tested; Among them, the state information of the rechargeable battery to be tested includes a static state and a charge and discharge state, and the SOC calculation strategy includes a static state calculation strategy corresponding to the static state and a charge and discharge state calculation strategy corresponding to the charge and discharge state; the static state calculation strategy includes a pressure-SOC table under the static state, and the pressure-SOC table is a correspondence table between the pressure magnitude and the SOC value; the charge and discharge state calculation strategy includes a pressure-SOC model under the charge and discharge state, and the pressure-SOC model is obtained by learning the correlation between the SOC value, pressure information, voltage information and current information under multiple cycles of charge and discharge.
2. The SOC calculation method of a rechargeable battery according to claim 1, characterized in that: The state of the rechargeable battery to be tested is a static state; The step of calculating the SOC of the rechargeable battery to be tested according to the SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested and combining the voltage information, current information and pressure information of the rechargeable battery to be tested comprises: According to the pressure-SOC table in the static state, combined with the pressure information of the rechargeable battery to be tested, an SOC value corresponding to the pressure information of the rechargeable battery to be tested is obtained; The pressure information is the pressure magnitude.
3. The SOC calculation method of a rechargeable battery according to claim 2, characterized in that: The method further comprises: A battery of the same model as the rechargeable battery to be tested is charged or discharged, and the charging or discharging is stopped when the battery reaches a preset SOC value, and the pressure of the battery after being left at rest is obtained, thereby obtaining the pressure-SOC table in the rest state.
4. The SOC calculation method of a rechargeable battery according to claim 1, characterized in that: The state of the rechargeable battery to be tested is a charging state or a discharging state; The step of calculating the SOC of the rechargeable battery to be tested according to the SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested and combining the voltage information, current information and pressure information of the rechargeable battery to be tested comprises: Determining whether the rechargeable battery to be tested is in a charging state or a discharging state; The SOC value is calculated according to the pressure-SOC model under the charge and discharge state and in combination with the voltage information, current information and pressure information of the rechargeable battery to be tested.
5. The SOC calculation method of a rechargeable battery according to claim 4, characterized in that: The method further comprises: Performing multiple charging and discharging on a battery of the same model as the rechargeable battery to be tested, obtaining the SOC value, pressure information, voltage information and current information of the battery under multiple charging and discharging as a data set, selecting part of the data in the data set as training set data, and performing normalization processing on the training set data; Training the training set data through a network training model; The training results are output, and a pressure-SOC model under the charging and discharging state is formulated.
6. The SOC calculation method of a rechargeable battery according to claim 5, characterized in that: The network training model is any one of a CNN-LSTM model, a GRU-Attention model or a CNN-BILSTM model.
7. The SOC calculation method of a rechargeable battery according to claim 5, characterized in that: The network training model uses a CNN-LSTM network with an Attention mechanism to train the training set data.
8. The SOC calculation method of a rechargeable battery according to claim 7, characterized in that: The training of the training set data by using a network training model includes: The training set data is processed by CNN to extract features with local spatial invariance to form a local feature set; By using Attention to dynamically focus on different parts of the local feature set, the importance weight of each feature is calculated, the features are weighted, and the important features are highlighted; LSTM is used to capture and model the dependencies in time series and to handle long-term and short-term memory problems in sequence data.
9. The SOC calculation method of a rechargeable battery according to claim 1, characterized in that: There is a corresponding relationship between the rechargeable battery to be tested and the SOC calculation strategy; Before calculating the SOC of the rechargeable battery to be tested according to the SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested and combining the voltage information, current information and pressure information of the rechargeable battery to be tested, the method further includes: Obtain an SOC calculation strategy corresponding to the rechargeable battery to be tested.
10. A detection component, characterized in that: The detection component calculates the SOC of the rechargeable battery to be tested by the SOC calculation method of the rechargeable battery according to any one of claims 1 to 9; The detection component includes a data acquisition unit and a detection unit, and the data acquisition unit is in communication connection with the detection unit; the data acquisition unit at least includes a thin film pressure sensor, a voltage collector and a current collector, the thin film pressure sensor is used to collect pressure information of the rechargeable battery to be tested, the voltage collector is used to collect voltage information of the rechargeable battery to be tested, and the current collector is used to collect current information of the rechargeable battery to be tested; The detection unit at least includes an SOC calculation unit, which calculates the SOC of the rechargeable battery to be tested according to an SOC calculation strategy corresponding to the state information of the rechargeable battery to be tested, combined with voltage information, current information and pressure information of the rechargeable battery to be tested.
11. A SOC calculation system for a rechargeable battery, characterized in that: The system calculates the SOC of the rechargeable battery to be tested by using the SOC calculation method of the rechargeable battery according to any one of claims 1-9.
12. A SOC calculation device for a rechargeable battery, characterized in that: The device comprises a rechargeable battery to be tested and the detection component according to claim 10, wherein the detection component is used to calculate the SOC of the rechargeable battery to be tested.
Citation Information
Patent Citations
Method for estimating state of charge of soft package lithium-ion battery
CN105759216A
Soft package lithium ion battery state-of-charge estimation method and device and storage medium
CN116224074A
Battery electric quantity calibration method and device, computer equipment and storage medium
CN117007980A
KR20210155518A
