Lithium battery remaining capacity prediction method and system

Abstract

The invention provides a lithium battery remaining capacity prediction method and system. The method comprises the following steps: estimating the service life of a lithium battery sample by using a battery life estimation model; grouping the state parameters of the lithium battery samples according to different service lives of the lithium battery samples to obtain multiple groups of state parameters; the multiple sets of state parameters serve as training samples to be input into different neural network models for training, and lithium battery remaining capacity prediction models under different service lives are obtained; and calculating the residual electric quantity of the target lithium battery under different service lives by using the corresponding prediction model. According to the method, multiple groups of state parameters are used as training samples to be respectively input into different neural network models for training, and the influence of the use loss of the lithium battery on the residual electric quantity of the lithium battery is considered, so that the estimation of the residual electric quantity of the lithium battery can be more accurate.

Description

Technical Field

[0001] This invention belongs to the field of lithium battery technology, and more specifically, relates to a method and system for predicting the remaining power of a lithium battery. Background Technology

[0002] Lithium-ion batteries are a new type of fuel cell with advantages such as high efficiency, environmental friendliness, and low cost, and are widely used in mobile power supplies, drones, smart homes, and other fields. However, the lifespan and efficiency of lithium-ion batteries are limited because their remaining capacity is difficult to measure directly. Therefore, accurately predicting the remaining capacity of lithium-ion batteries is a current research hotspot.

[0003] Currently, the main methods for predicting the remaining capacity of lithium batteries are as follows: Battery model-based prediction methods. This method predicts the remaining capacity by establishing a battery model. However, due to the complexity and uncertainty of battery models, this method is difficult to accurately predict the remaining capacity. Statistical prediction methods. This method predicts the remaining capacity by statistically analyzing historical battery data. However, due to the uncertainty of the working environment and usage of lithium batteries, the prediction accuracy of this method is relatively low. Summary of the Invention

[0004] To address the aforementioned problems, the present invention aims to provide a method and system for predicting the remaining power of a lithium battery.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A method for predicting the remaining capacity of a lithium battery includes the following steps:

[0007] Step 1: Construct a battery life estimation model based on the number of charge-discharge cycles of the lithium battery;

[0008] Step 2: Use the battery life estimation model to estimate the lifespan of the lithium battery sample;

[0009] Step 3: Group the state parameters of the lithium battery samples according to their different lifespans to obtain multiple groups of state parameters; the state parameters include temperature, open-circuit voltage, and operating current;

[0010] Step 4: Input multiple sets of state parameters as training samples into different neural network models to obtain lithium battery remaining power prediction models under different service lives;

[0011] Step 5: Use the corresponding lithium battery remaining capacity prediction model to calculate the remaining capacity of the target lithium battery under different service lives.

[0012] Preferably, step 1: constructing a battery life estimation model based on the charge-discharge cycle number of the lithium battery, includes:

[0013] Step 1.1: Obtain the operating current and maximum output power of the lithium battery at the corresponding time points throughout its entire life cycle;

[0014] Step 1.2: Construct a fitting model, and use the lithium battery's operating current, maximum output power, and charge / discharge cycle count to solve for the parameters of the fitting model to obtain the battery life estimation model; wherein, the fitting model is:

[0015]

[0016] Where AGE represents the remaining lifespan of the lithium battery, N represents the number of charge-discharge cycles of the lithium battery, k1 represents the first model parameter, k2 represents the second model parameter, k3 represents the third model parameter, and Q... max represents the maximum output power of the lithium battery, and i represents the operating current of the lithium battery.

[0017] Preferably, in step 3, the open-circuit voltage is obtained through the following steps:

[0018] Step 3.1: Construct an equivalent circuit based on the discharge process of a lithium battery;

[0019] Step 3.2: Construct the battery voltage equation using Kirchhoff's laws based on the equivalent circuit;

[0020] Step 3.3: Construct the battery operating equation based on the battery voltage equation;

[0021] Step 3.4: Solve the battery working equation to obtain the open-circuit voltage of the lithium battery.

[0022] Preferably, step 3.2: constructing the battery voltage equation based on equivalent circuits using Kirchhoff's laws, includes:

[0023] Step 3.2.1: Use the Thevenin equivalent circuit model as the equivalent circuit for the lithium battery;

[0024] Step 3.2.2: Construct the battery voltage equation using Kirchhoff's laws based on the Thevenin equivalent circuit model; wherein, the battery voltage equation is:

[0025] U bat =OCV+U p +R0I bat

[0026] Among them, U bat U represents the terminal voltage of the lithium battery, OCV represents the open-circuit voltage of the lithium battery, and U represents the open-circuit voltage of the lithium battery. pR0 represents the polarization capacitor voltage, and I represents the internal resistance of the lithium battery. bat This indicates the operating current of the lithium battery.

[0027] Preferably, step 3.3: constructing the battery operating equation based on the battery voltage equation includes:

[0028] Formula used:

[0029]

[0030] Construct the battery's operating equation; where R p C represents the polarization internal resistance of a lithium battery. p τ represents the polarization capacitance of a lithium battery. p This represents the time constant.

[0031] Preferably, step 3.4: solving the battery operating equation to obtain the open-circuit voltage of the lithium battery includes:

[0032] Step 3.4.1: Substitute the battery operating equation into the battery voltage equation to obtain the open-circuit voltage equation; wherein, the open-circuit voltage equation is:

[0033]

[0034] Step 3.4.2: Solve the open-circuit voltage equation to obtain the open-circuit voltage of the lithium battery.

[0035] Preferably, after grouping the state parameters of the lithium battery samples according to their different lifespans in step 3, the method further includes:

[0036] Normalize each set of state parameters to obtain normalized state parameters; the normalization formula is as follows:

[0037]

[0038] Where n represents the number of state parameters, x i This represents the i-th state parameter. This represents the i-th state parameter after normalization.

[0039] The present invention also provides a lithium battery remaining power prediction system, comprising:

[0040] The lifespan estimation model building module is used to build a battery lifespan estimation model based on the number of charge-discharge cycles of the lithium battery.

[0041] The lifespan estimation module is used to estimate the lifespan of lithium battery samples using a battery lifespan estimation model.

[0042] The parameter grouping module is used to group the state parameters of lithium battery samples according to their different lifespans, resulting in multiple groups of state parameters; the state parameters include temperature, open-circuit voltage, and operating current;

[0043] The training module is used to input multiple sets of state parameters as training samples into different neural network models to obtain prediction models of the remaining power of lithium batteries under different service lives.

[0044] The remaining power prediction module is used to calculate the remaining power of the target lithium battery under different service lives using the corresponding lithium battery remaining power prediction model.

[0045] The present invention also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are connected via the bus. When the computer program is executed by the processor, it implements the steps in the above-described method for predicting the remaining power of a lithium battery.

[0046] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps in the above-described method for predicting the remaining power of a lithium battery.

[0047] The beneficial effects of the lithium battery remaining power prediction method provided by the present invention are as follows: Compared with the prior art, the present invention takes into account the impact of lithium battery usage loss on the remaining power of the lithium battery by inputting multiple sets of state parameters as training samples into different neural network models for training, thus making the estimation of the remaining power of the lithium battery more accurate. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart of a method for predicting the remaining power of a lithium battery provided in an embodiment of the present invention;

[0050] Figure 2 This is a schematic diagram of a lithium battery remaining power prediction system provided in an embodiment of the present invention. Detailed Implementation

[0051] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0052] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0053] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0054] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0055] Please see Figure 1 A method for predicting the remaining power of a lithium battery includes the following steps:

[0056] Step 1: Construct a battery life estimation model based on the number of charge-discharge cycles of the lithium battery;

[0057] Furthermore, step 1 includes:

[0058] Step 1.1: Obtain the operating current and maximum output power of the lithium battery at the corresponding time points throughout its entire life cycle;

[0059] Step 1.2: Construct a fitting model, and use the lithium battery's operating current, maximum output power, and charge / discharge cycle count to solve for the parameters of the fitting model to obtain the battery life estimation model; wherein, the fitting model is:

[0060]

[0061] Where AGE represents the remaining lifespan of the lithium battery, N represents the number of charge-discharge cycles of the lithium battery, k1 represents the first model parameter, k2 represents the second model parameter, k3 represents the third model parameter, and Q... max represents the maximum output power of the lithium battery, and i represents the operating current of the lithium battery.

[0062] In practical applications, the present invention can input the collected operating current, maximum output power and charge-discharge cycle number into the fitting model, calculate the value of the fitting model and compare it with the actual observed value. By adjusting the value of the model parameters, the output value of the fitting model can be made as close as possible to the actual observed value.

[0063] Step 2: Use the battery life estimation model to estimate the lifespan of the lithium battery sample;

[0064] Step 3: Group the state parameters of the lithium battery samples according to their different lifespans to obtain multiple groups of state parameters; the state parameters include temperature, open-circuit voltage, and operating current;

[0065] In step 3, the open-circuit voltage is obtained through the following steps:

[0066] Step 3.1: Construct an equivalent circuit based on the discharge process of a lithium battery;

[0067] Lithium-ion batteries (new energy batteries) can be broadly divided into four parts: a positive electrode composed of lithium compounds, a negative electrode composed of graphite intercalated with lithium ions, a separator separating the positive and negative electrodes while allowing lithium ions to pass through, and an electrolyte filling the space between the positive and negative electrodes. During operation, complex chemical reactions occur internally. During charging, lithium ions detach from the positive electrode, pass through the separator, and move through the electrolyte to the negative electrode, where they embed themselves. During discharging, lithium ions detach from the negative electrode, pass through the separator, and move through the electrolyte to the positive electrode, where they embed themselves. The charge balance of the electrodes is maintained by the movement of electrons in the external circuit. It can be seen that a battery is a nonlinear system; therefore, to facilitate research on lithium batteries, it is necessary to establish an equivalent circuit for the battery.

[0068] Step 3.2: Construct the battery voltage equation using Kirchhoff's laws based on the equivalent circuit;

[0069] Step 3.2 includes:

[0070] Step 3.2.1: Use the Thevenin equivalent circuit model as the equivalent circuit for the lithium battery;

[0071] Step 3.2.2: Construct the battery voltage equation using Kirchhoff's laws based on the Thevenin equivalent circuit model; wherein, the battery voltage equation is:

[0072] U bat =OCV+U p +R0I bat

[0073] Among them, U bat U represents the terminal voltage of the lithium battery, OCV represents the open-circuit voltage of the lithium battery, and U represents the open-circuit voltage of the lithium battery. p R0 represents the polarization capacitor voltage, and I represents the internal resistance of the lithium battery. bat This indicates the operating current of the lithium battery.

[0074] Step 3.3: Construct the battery operating equation based on the battery voltage equation; whereby the battery operating equation is:

[0075]

[0076] In the formula, R p C represents the polarization internal resistance of a lithium battery. p τ represents the polarization capacitance of a lithium battery. p This represents the time constant.

[0077] Step 3.4: Solve the battery working equation to obtain the open-circuit voltage of the lithium battery;

[0078] In this embodiment of the invention, step 3.4 includes:

[0079] Step 3.4.1: Substitute the battery operating equation into the battery voltage equation to obtain the open-circuit voltage equation; wherein, the open-circuit voltage equation is:

[0080]

[0081] Step 3.4.2: Solve the open-circuit voltage equation using the least squares method to obtain the open-circuit voltage of the lithium battery.

[0082] Following step 3, the following is also included:

[0083] Normalize each set of state parameters to obtain normalized state parameters; the normalization formula is as follows:

[0084]

[0085] Where n represents the number of state parameters, x i This represents the i-th state parameter. This represents the i-th state parameter after normalization.

[0086] This invention improves the convergence speed, stability, and generalization ability of the model by normalizing the state parameters.

[0087] Step 4: Input multiple sets of state parameters as training samples into different neural network models to obtain lithium battery remaining power prediction models under different service lives;

[0088] In step 4, a label is assigned to the remaining power corresponding to the state parameters under different lifespans, forming calibrated samples under different lifespans; different neural network models, such as BP neural network models and LSTM (Long Short-Term Memory network), are trained using the calibrated samples under different lifespans, and the training effect is quantified using a loss function. Training is completed when the value of the loss function is within the set range.

[0089] Step 5: Use the corresponding lithium battery remaining capacity prediction model to calculate the remaining capacity of the target lithium battery under different service lives.

[0090] This invention uses multiple sets of state parameters as training samples and inputs them into different neural network models for training. It takes into account the impact of lithium battery usage loss on the remaining lithium battery capacity, thus making the estimation of the remaining lithium battery capacity more accurate.

[0091] Please see Figure 2 The present invention also provides a lithium battery remaining power prediction system, comprising:

[0092] The lifespan estimation model building module is used to build a battery lifespan estimation model based on the number of charge-discharge cycles of the lithium battery.

[0093] The lifespan estimation module is used to estimate the lifespan of lithium battery samples using a battery lifespan estimation model.

[0094] The parameter grouping module is used to group the state parameters of lithium battery samples according to their different lifespans, resulting in multiple groups of state parameters; the state parameters include temperature, open-circuit voltage, and operating current;

[0095] The training module is used to input multiple sets of state parameters as training samples into different neural network models to obtain prediction models of the remaining power of lithium batteries under different service lives.

[0096] The remaining power prediction module is used to calculate the remaining power of the target lithium battery under different service lives using the corresponding lithium battery remaining power prediction model.

[0097] Compared with the prior art, the beneficial effects of the lithium battery remaining power prediction system provided by the present invention are the same as those of the lithium battery remaining power prediction method described in the above technical solution, and will not be repeated here.

[0098] The present invention also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are connected via the bus. When the computer program is executed by the processor, it implements each process in the above-described method for predicting the remaining power of a lithium battery and achieves the same technical effect. To avoid repetition, it will not be described in detail here.

[0099] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements the various processes of the above-described method for predicting the remaining power of a lithium battery and achieves the same technical effect. To avoid repetition, it will not be described in detail here.

[0100] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method of predicting the remaining capacity of a lithium battery, characterized by, The method comprises the following steps: Step 1: constructing a battery life estimation model according to the number of charge-discharge cycles of the lithium battery; Step 2: estimating the service life of the lithium battery sample using the battery life estimation model; Step 3: grouping the state parameters of the lithium battery sample according to the different service lives of the lithium battery sample to obtain multiple groups of state parameters; the state parameters include temperature, open-circuit voltage and working current; Step 4: inputting the multiple groups of state parameters as training samples into different neural network models for training to obtain lithium battery remaining capacity prediction models under different service lives; Step 5: calculating the remaining capacity of the target lithium battery under different service lives using the corresponding lithium battery remaining capacity prediction model.

2. The method for predicting the remaining capacity of a lithium battery as described in claim 1, characterized in that, The step 1: constructing a battery life estimation model according to the number of charge-discharge cycles of the lithium battery comprises: Step 1.1: obtaining the working current and maximum output power of the lithium battery at corresponding time points in the entire life cycle; Step 1.2: constructing a fitting model and solving the parameters of the fitting model to obtain the battery life estimation model using the working current, maximum output power and number of charge-discharge cycles of the lithium battery; wherein the fitting model is: Wherein, AGE represents the remaining life of the lithium battery, N represents the number of charge and discharge cycles of the lithium battery, k1 represents a first model parameter, k2 represents a second model parameter, k3 represents a third model parameter, Q max represents the maximum output power of the lithium battery, and i represents the working current of the lithium battery.

3. The method of claim 2, wherein the step of determining the remaining capacity of the lithium battery is performed by using a model of the lithium battery. In the step 3, the open-circuit voltage is obtained by the following steps: Step 3.1: constructing an equivalent circuit according to the discharge process of the lithium battery; Step 3.2: constructing a battery voltage equation based on the equivalent circuit using Kirchhoff's law; Step 3.3: constructing a battery working equation based on the battery voltage equation; Step 3.4: solving the battery working equation to obtain the open-circuit voltage of the lithium battery.

4. The method for predicting the remaining capacity of a lithium battery as described in claim 3, characterized in that, The step 3.2: constructing a battery voltage equation based on the equivalent circuit using Kirchhoff's law comprises: Step 3.2.1: using the thevenin equivalent circuit model as the equivalent circuit of the lithium battery; Step 3.2.2: constructing a battery voltage equation based on the thevenin equivalent circuit model using Kirchhoff's law; wherein the battery voltage equation is: U bat = OCV + U p + R0I bat wherein U bat represents the terminal voltage of the lithium battery, OCV represents the open circuit voltage of the lithium battery, U p represents the polarization capacitance voltage, R0 represents the internal resistance of the lithium battery, I bat represents the working current of the lithium battery.

5. The method of claim 4, wherein the step of predicting the remaining capacity of the lithium battery is performed by using a model of the lithium battery. The step 3.3: constructing a battery working equation based on the battery voltage equation comprises: Using the formula: Constructing the battery working equation; wherein, R p represents the polarization resistance of lithium battery, C p represents the polarization capacitance of lithium battery, τ p represents the time constant.

6. The method of claim 5, wherein the remaining capacity of the lithium battery is predicted by the following equation: ###0001### where, C is the remaining capacity of the lithium battery, C0 is the initial capacity of the lithium battery, t is the time, and k is the rate constant. The step 3.4: solving the battery working equation to obtain the open-circuit voltage of the lithium battery comprises: Step 3.4.1: bringing the battery working equation into the battery voltage equation to obtain an open-circuit voltage equation; wherein the open-circuit voltage equation is: Step 3.4.2: solving the open-circuit voltage equation to obtain the open-circuit voltage of the lithium battery.

7. The method of claim 1, wherein the remaining capacity of the lithium battery is predicted by using a model based on a lithium battery characteristic. After step 3: grouping the state parameters of the lithium battery sample according to the different service lives of the lithium battery sample to obtain multiple groups of state parameters, further comprising: Normalizing each group of state parameters to obtain normalized state parameters; wherein the normalization formula is: wherein n represents the number of state parameters, x i represents the i-th state parameter, represents the i-th state parameter after normalization.

8. A lithium battery remaining capacity prediction system, characterized by, Comprising: A life estimation model construction module for constructing a battery life estimation model according to the number of charge-discharge cycles of the lithium battery; A service life estimation module for estimating the service life of the lithium battery sample using the battery life estimation model; A parameter grouping module for grouping the state parameters of the lithium battery sample according to the different service lives of the lithium battery sample to obtain multiple groups of state parameters; the state parameters include temperature, open-circuit voltage and working current; The training module is configured to input multiple groups of state parameters as training samples into different neural network models respectively to obtain lithium battery residual capacity prediction models under different service lives. The residual capacity prediction module is configured to calculate the residual capacity of the target lithium battery under different service lives by using the corresponding lithium battery residual capacity prediction model.

9. An electronic device comprising a bus, a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected by the bus, characterized in that, The computer program, when executed by the processor, implements the steps of the lithium battery residual capacity prediction method according to any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the lithium battery residual capacity prediction method according to any one of claims 1-7.

Images