Battery life prediction method and device, equipment, storage medium and program product

Abstract

The invention provides a battery life prediction method and device, equipment, a storage medium and a program product, and the method comprises the steps: determining a characteristic factor of an Nth cycle according to the Nth cycle charge and discharge data of a target battery; inputting the feature factor of the Nth cycle into a feature prediction model to obtain a predicted feature factor; the prediction characteristic factors are input into a capacity prediction model, a target capacity prediction value and a corresponding cycle index are obtained, and the target capacity prediction value is smaller than a preset capacity value; and determining the remaining life of the target battery based on the cycle index. Therefore, the remaining service life of the battery can be predicted only by acquiring the charging and discharging data of the battery, and the battery life prediction efficiency is improved.

Description

Technical Field

[0001] The present application belongs to the field of battery technology, and in particular, relates to a battery life prediction method, device, equipment, storage medium and program product. Background Art

[0002] The life of a lithium-ion battery usually refers to its cycle life, which is the number of charge and discharge cycles that can be performed before the battery capacity reaches 80% of the initial capacity or nominal capacity (i.e. the battery's performance indicators reach the end of life condition). In order to improve the safety of lithium-ion batteries, it is necessary to determine the remaining useful life (RUL) of lithium-ion batteries to avoid damage to lithium-ion batteries when they exceed their cycle life.

[0003] At present, the remaining service life of lithium-ion batteries is mainly determined by predicting the RUL of lithium-ion batteries through battery aging models. Battery aging models usually include mechanism models and data-driven models. Mechanism models require the exploration of the internal failure mechanism of the battery and the establishment of complex models; the accuracy of data-driven models is limited to the amount of model training data, and the acquisition of battery data often requires a lot of time and material costs.

[0004] Therefore, the method for determining the remaining service life of a lithium-ion battery in the prior art is relatively complex, resulting in low efficiency in predicting the remaining service life of the lithium-ion battery. Summary of the invention

[0005] The embodiments of the present application provide a battery life prediction method, device, equipment, storage medium and program product to improve the efficiency of battery life prediction.

[0006] In a first aspect, an embodiment of the present application provides a battery life prediction method, the method comprising:

[0007] Determine a characteristic factor of the Nth cycle according to the Nth cycle charge and discharge data of the target battery, wherein the characteristic factor is used to characterize the attenuation characteristics of the target battery, and N is a positive integer;

[0008] Inputting the characteristic factors of the Nth cycle into the characteristic prediction model to obtain the predicted characteristic factors;

[0009] Inputting the prediction characteristic factor into a capacity prediction model to obtain a target capacity prediction value and a corresponding number of cycles, wherein the target capacity prediction value is less than a preset capacity value;

[0010] Based on the number of cycles, a remaining life of the target battery is determined.

[0011] In some embodiments, determining the characteristic factor of the Nth cycle according to the Nth cycle charge and discharge data of the target battery includes:

[0012] Based on the time series method, the trend characteristics and deformation characteristics of the Nth cycle charge and discharge data are determined to obtain the characteristic factors of the Nth cycle.

[0013] In some embodiments, the method of determining the trend characteristics and deformation characteristics of the Nth cycle charge and discharge data based on the time series method to obtain the characteristic factors of the Nth cycle includes:

[0014] Decomposing each data point in the N-th cycle charge and discharge data based on a time series method to obtain trend characteristics and deformation characteristics of each data point;

[0015] Based on the trend characteristics and deformation characteristics of each of the data points, the characteristic factors of the Nth cycle are determined.

[0016] In some embodiments, the step of inputting the characteristic factor of the Nth cycle into a characteristic prediction model to obtain a predicted characteristic factor; and inputting the predicted characteristic factor into a capacity prediction model to obtain a target capacity prediction value and a corresponding number of cycles includes:

[0017] Inputting the characteristic factor of the Nth cycle into a characteristic prediction model to obtain the characteristic factor of the N+1th cycle;

[0018] Inputting the characteristic factors of the N+1th cycle into a capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle;

[0019] In the case that the battery capacity corresponding to the N+1th cycle is greater than or equal to the preset capacity value, let N=N+1, and return to the execution of: the step of inputting the characteristic factor of the Nth cycle into the characteristic prediction model to obtain the characteristic factor of the N+1th cycle, and the step of inputting the characteristic factor of the N+1th cycle into the capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle;

[0020] Until the battery capacity corresponding to the N+1th cycle is less than the preset capacity value, the target capacity prediction value and the corresponding number of cycles are obtained.

[0021] In some embodiments, inputting the characteristic factor of the N+1th cycle into a capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle includes:

[0022] Inputting the characteristic factor of the N+1th cycle into a first capacity prediction sub-model to obtain a first prediction value, wherein the first capacity prediction sub-model is generated based on a first function, and the first function is a function corresponding to a first stage of battery capacity decay;

[0023] Inputting the characteristic factor of the N+1th cycle into a second capacity prediction sub-model to obtain a second prediction value, wherein the second capacity prediction sub-model is generated based on a second function, and the second function is a function corresponding to the second stage of battery capacity attenuation;

[0024] Inputting the characteristic factor of the N+1th cycle into a third capacity prediction sub-model to obtain a third prediction value, wherein the third capacity prediction sub-model is generated based on a third function, and the third function is a function corresponding to the third stage of battery capacity attenuation;

[0025] The battery capacity corresponding to the N+1th cycle is obtained according to the first predicted value, the second predicted value and the third predicted value.

[0026] In some embodiments, determining the remaining life of the target battery based on the number of cycles includes:

[0027] Obtaining the cumulative number of cycles of the target battery;

[0028] Based on the accumulated number of cycles and the number of cycles corresponding to the target capacity prediction value, the remaining number of cycles of the target battery is obtained.

[0029] Combine a memory window binding operation and an unbinding operation into a binding change operation;

[0030] In a second aspect, an embodiment of the present application provides a battery life prediction device, the device comprising:

[0031] A first determination module, configured to determine a characteristic factor of an Nth cycle according to the Nth cycle charge and discharge data of the target battery, wherein the characteristic factor is used to characterize the attenuation characteristics of the target battery, and N is a positive integer;

[0032] The first prediction module is used to input the characteristic factors of the Nth cycle into the characteristic prediction model to obtain the predicted characteristic factors;

[0033] A second prediction module is used to input the prediction characteristic factor into a capacity prediction model to obtain a target capacity prediction value and a corresponding number of cycles, wherein the target capacity prediction value is less than a preset capacity value;

[0034] The second determination module is used to determine the remaining life of the target battery based on the number of cycles.

[0035] In a third aspect, an embodiment of the present application provides a battery life prediction device, the device comprising:

[0036] A processor and a memory storing programs or instructions;

[0037] The above method is implemented when the processor executes the program or instruction.

[0038] In a fourth aspect, an embodiment of the present application provides a machine-readable storage medium, on which a program or instruction is stored, and the program or instruction implements the above method when executed by a processor.

[0039] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the above method.

[0040] The battery life prediction method, device, equipment, storage medium and program product of the embodiment of the present application can determine the characteristic factor of the Nth cycle according to the Nth cycle charge and discharge data of the target battery; input the characteristic factor of the Nth cycle into the characteristic prediction model to obtain the predicted characteristic factor; input the predicted characteristic factor into the capacity prediction model to obtain the target capacity prediction value and the corresponding number of cycles, and the target capacity prediction value is less than the preset capacity value; based on the number of cycles, determine the remaining life of the target battery. In this way, it is possible to extract the characteristic factor from the battery's cycle charge and discharge data, predict the predicted characteristic factor after the Nth cycle based on the characteristic factor, predict the corresponding battery capacity based on the predicted characteristic factor, and determine the remaining service life of the battery according to the number of cycles corresponding to the battery capacity that is less than the preset power value. Therefore, the remaining service life of the battery can be predicted by only obtaining the battery charge and discharge data, which is simple to operate and improves the efficiency of battery life prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 It is a flowchart of a battery life prediction method provided by an embodiment of the present application;

[0043] Figure 2 This is a schematic diagram of the structure of battery life prediction provided by an embodiment of the present application;

[0044] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0045] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0046] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0047] Lithium batteries are widely used in various electronic devices, automotive energy, and aerospace due to their long life, fast charging, and high energy density. However, during the use of lithium batteries, there is a problem of capacity decay. Usually, the number of cycles corresponding to a capacity decay of 80% of the rated capacity is the cycle life of the lithium battery. However, due to the complex internal reaction mechanism of lithium batteries and many influencing factors, it is not easy to predict the capacity decay of lithium batteries. Among the many prediction methods, the mechanism model-driven method has the problems of high complexity, large amount of calculation, and general accuracy. The mathematical model-driven method has the problem of low accuracy, and the data-driven method has the problem of long-term prediction deviation. The above problems make it very difficult to accurately and efficiently predict the battery capacity decay trend, and it is also difficult to accurately and efficiently predict the life of lithium batteries. This makes the application of lithium battery life prediction technology in real scenarios relatively limited, and there are still many practical difficulties between solving actual demand problems.

[0048] In order to solve the problems of the prior art, the embodiments of the present application provide a battery life prediction method, device, equipment, storage medium and program product. The battery life prediction method provided by the embodiments of the present application is first introduced below.

[0049] Figure 1 FIG. 1 is a flow chart of a battery life prediction method provided by an embodiment of the present application. Figure 1 As shown, the battery life prediction method may include the following S101 to S104:

[0050] S101, determining a characteristic factor of the Nth cycle according to the Nth cycle charge and discharge data of the target battery. The characteristic factor is used to characterize the attenuation characteristics of the target battery, and N is a positive integer.

[0051] Among them, the battery management system (BMS) can be used to obtain the battery's cyclic charge and discharge data, including charging current, discharge current, voltage change, etc. The battery management system can monitor and record the battery's charge and discharge status and performance parameters in real time. The battery's cyclic charge and discharge data can also be obtained through battery management applications or software. The battery's cyclic charge and discharge data refers to the relevant parameters and indicators recorded and measured during a complete charge and discharge cycle (i.e., one cycle) during the battery's charging and discharging process. For example: charging current, discharge current, charging voltage, discharge voltage, time, and other data.

[0052] Optionally, the Nth cycle charge and discharge data of the battery may be charging data and / or discharging data corresponding to the Nth cycle, for example, a charging curve or a discharging curve.

[0053] S102, inputting the characteristic factors of the Nth cycle into the characteristic prediction model to obtain predicted characteristic factors.

[0054] Among them, the feature prediction model is obtained by training the charge and discharge data of multiple different cycles of the battery. The construction of the feature prediction model includes the steps of data collection, data preprocessing, feature factor selection, model selection, model training, model evaluation, model prediction and model optimization. The feature prediction model can be obtained by using the model construction and model training methods in the prior art, which is not limited in this application.

[0055] Specifically, the characteristic factors corresponding to the cycles after the Nth cycle can be predicted based on the characteristic factors of the Nth cycle of the target battery through a pre-trained characteristic prediction model.

[0056] S103, inputting the prediction characteristic factors into the capacity prediction model to obtain the target capacity prediction value and the corresponding number of cycles.

[0057] In S103, after the prediction characteristic factors are obtained, the battery capacity is predicted using a capacity prediction model based on the prediction characteristic factors.

[0058] Among them, the target capacity prediction value is less than the preset capacity value. The preset capacity value can be set according to the attenuation threshold of the battery, that is, it is set according to the actual attenuation of the battery, and this application does not limit it. The battery attenuation threshold refers to the critical point or standard at which the battery capacity is considered to be attenuated when it drops to a certain level. Optionally, the preset capacity value can be set to a preset percentage of the initial capacity of the battery, such as 80% of the initial capacity of the battery / nominal capacity.

[0059] Specifically, the corresponding battery capacity can be predicted based on the characteristic factors of the charge and discharge data of the target battery through the pre-trained capacity prediction model. The battery capacity corresponding to the cycle after the Nth cycle can be predicted by predicting the characteristic factors corresponding to the cycle after the Nth cycle. When the predicted capacity value is less than the preset capacity value, it means that the number of cycles corresponding to the predicted capacity value is the critical number of cycles of the life of the target battery, thereby determining the cycle number threshold for the battery to reach the predetermined life under normal use conditions.

[0060] S104, determining the remaining life of the target battery based on the number of cycles.

[0061] Specifically, the Nth cycle charge and discharge data is the starting point for battery life prediction. The characteristic prediction model is used to predict the characteristic factors corresponding to the cycles after the Nth cycle. The capacity prediction model is then used to further predict the battery capacity corresponding to the cycles after the Nth cycle through the predicted characteristic factors. Finally, the number of cycles corresponding to when the battery capacity of the target battery reaches the attenuation threshold is obtained, thereby determining the remaining service life of the target battery.

[0062] The battery life prediction method of the embodiment of the present application can extract characteristic factors from the battery's cyclic charge and discharge data, predict the predicted characteristic factors after the Nth cycle based on the characteristic factors, predict the corresponding battery capacity based on the predicted characteristic factors, and determine the remaining service life of the battery according to the number of cycles corresponding to the battery capacity that is less than the preset power value. Therefore, the remaining service life of the battery can be predicted by only obtaining the battery's charge and discharge data, which is simple to operate and improves the efficiency of battery life prediction.

[0063] In some embodiments, the above S101 may include the following steps:

[0064] Based on the time series method, the trend characteristics and deformation characteristics of the Nth cycle charge and discharge data are determined, and the trend characteristics and deformation characteristics of the Nth cycle are obtained.

[0065] Battery discharge data usually belongs to continuous time series. In a continuous time series, time is continuous and data points can be observed at any time point. Battery charge and discharge data are usually sampled at certain time intervals, such as every second or every minute. These sampling points can be used to construct the battery charge and discharge curve and perform time series analysis, modeling and prediction on it.

[0066] Among them, the trend feature is used to characterize the upward or downward trend of the time series as a whole, representing the overall changing trend of the curve over time; the deformation term is used to characterize the repetitive pattern caused by a specific time period.

[0067] Therefore, time series analysis can be performed on the Nth cycle to extract the trend characteristics and deformation characteristics of the Nth cycle.

[0068] In this embodiment, according to the time series characteristics of the charge and discharge data, the time series analysis of the N-th cycle charge and discharge data can be performed to obtain the trend characteristics and deformation characteristics of the N-th cycle charge and discharge data.

[0069] In some embodiments, the above-mentioned method based on time series is used to determine the trend characteristics and deformation characteristics of the Nth cycle charge and discharge data to obtain the characteristic factors of the Nth cycle, which may specifically include the following steps:

[0070] Based on the time series method, each data point in the Nth cycle charge and discharge data is decomposed to obtain the trend characteristics and deformation characteristics of each data point;

[0071] Based on the trend characteristics and deformation characteristics of each data point, the trend characteristics and deformation characteristics of the Nth cycle are determined.

[0072] Specifically, based on the time series analysis method, each data point in the Nth cycle charge and discharge data can be decomposed to obtain the trend characteristics and deformation characteristics of each data point; then, the trend characteristics and deformation characteristics of the Nth cycle can be determined based on the trend characteristics and deformation characteristics of each data point.

[0073] Optionally, the trend characteristics and deformation characteristics of the charging and discharging data can be extracted through time series methods. Moving average or exponentially weighted moving average can be used to obtain the overall trend, seasonal decomposition or wavelet transform can be used to extract periodic deformation characteristics, and linear regression or autocorrelation function can help determine the slope and change pattern of the overall trend.

[0074] Optionally, the discharge curve is decomposed into trend features and deformation features, and a time series decomposition method may be used, wherein a commonly used method is an “addition model” or a “multiplication model”.

[0075] In one example, assuming that the Nth cycle charge and discharge data includes the Nth cycle discharge data, that is, the Nth cycle discharge curve, the trend characteristics and deformation characteristics of the Nth cycle discharge curve can be decomposed and extracted by the following steps:

[0076] For the i-th data point U in the discharge curve of the N-th cycle i , decomposed using the following format (1):

[0077] U i =T i +S i +R i (1)

[0078] Among them, T i is the trend characteristic, S i is the deformation feature, R i is the residual term. For several T i , assuming that there is a linear trend relationship, the following formula (2) is satisfied:

[0079] T i =k(i-0)+U0 (2)

[0080] Among them, U0 represents the initial voltage, and 0 represents the origin of the discharge curve;

[0081] The trend characteristic of the discharge data of the Nth cycle is the linear downward slope of the trend characteristic of each data point, which is expressed as the following formula (3):

[0082]

[0083] For S i +R i =U i -T i Finally, the difference result is smoothed to treat R as i Item, we get the following formula (4):

[0084] S i =U i -T i (4)

[0085] The deformation characteristics of the discharge curve of the Nth cycle are obtained by the following formula (5):

[0086]

[0087] In this embodiment, through feature factor decomposition and extraction, many data points in a cycle can be converted into two features of the cycle, which is beneficial to subsequent analysis and application.

[0088] In some embodiments, the above S102 to S103 may include the following steps:

[0089] Input the characteristic factors of the Nth cycle into the characteristic prediction model to obtain the characteristic factors of the N+1th cycle;

[0090] The characteristic factors of the N+1th cycle are input into the capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle;

[0091] When the battery capacity corresponding to the N+1th cycle is greater than or equal to the preset capacity value, set N=N+1, and return to the steps of: inputting the characteristic factor of the Nth cycle into the characteristic prediction model to obtain the characteristic factor of the N+1th cycle, and inputting the characteristic factor of the N+1th cycle into the capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle;

[0092] Until the battery capacity corresponding to the N+1th cycle is less than the preset capacity value, the target capacity prediction value and the corresponding number of cycles are obtained.

[0093] In this embodiment, the following steps are specifically included:

[0094] (1) Using the feature prediction model, the feature factor of the Nth cycle is used as input to predict the feature factor of the N+1th cycle;

[0095] (2) Using the capacity prediction model, the characteristic factor of the N+1th cycle is used as input to obtain the battery capacity value corresponding to the N+1th cycle;

[0096] (3) Determine whether the battery capacity corresponding to the N+1th cycle is less than a preset capacity value. If the battery capacity corresponding to the N+1th cycle is greater than or equal to the preset capacity value, perform the following steps:

[0097] a) Let N=N+1: Update the number of loops N to N+1, indicating the next loop.

[0098] b) Return to the steps of performing feature prediction and capacity prediction, that is, input the feature factors of the Nth cycle into the feature prediction model to obtain the feature factors of the N+1th cycle, and then input the feature factors of the N+1th cycle into the capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle.

[0099] (4) Repeat steps 3 and 4 until the battery capacity corresponding to the N+1th cycle is less than the preset capacity value:

[0100] In this step, it is continuously determined whether the battery capacity corresponding to the N+1th cycle is less than the preset capacity value. If so, the cycle is exited.

[0101] Finally, when the condition for exiting the loop is met, the target capacity prediction value and the corresponding number of cycles are obtained. This process can be carried out by continuously iterating feature prediction and capacity prediction until a target capacity prediction value less than the preset capacity value is obtained, and the number of cycles of the target capacity prediction value is determined.

[0102] Optionally, the above-mentioned capacity prediction model can be obtained by training a machine learning model, and the machine learning model includes at least one of a linear regression analysis model, a logistic regression analysis model, a support vector machine, a nearest neighbor algorithm model, a K-means clustering algorithm model, a decision tree model, a naive Bayes model, a random forest model, a dimensionality reduction algorithm model, a gradient enhancement algorithm model, a feedforward neural network, a convolutional neural network and a recurrent neural network.

[0103] In some embodiments, the characteristic factors of the N+1th cycle are input into the capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle, including:

[0104] Inputting the characteristic factor of the N+1th cycle into the first capacity prediction sub-model to obtain a first prediction value, wherein the first capacity prediction sub-model is generated based on a first function, and the first function is a function corresponding to the first stage of battery capacity attenuation;

[0105] Inputting the characteristic factor of the N+1th cycle into the second capacity prediction sub-model to obtain a second prediction value, the second capacity prediction sub-model is generated based on a second function, and the second function is a function corresponding to the second stage of battery capacity attenuation;

[0106] Inputting the characteristic factor of the N+1th cycle into the third capacity prediction sub-model to obtain a third prediction value, the third capacity prediction sub-model is generated based on a third function, and the third function is a function corresponding to the third stage of battery capacity attenuation;

[0107] According to the first predicted value, the second predicted value and the third predicted value, the battery capacity corresponding to the N+1th cycle is obtained.

[0108] The capacity prediction model may include a first capacity prediction sub-model, a second capacity prediction sub-model and a second capacity prediction sub-model. The three capacity prediction sub-models correspond to the three stages of the battery capacity decay process, namely, initial decay, linear decay and limit decay.

[0109] Specifically, the battery capacity decay process can usually be divided into three stages: initial decay, linear decay and limit decay. Initial decay: In the initial stage of battery use, the battery capacity may decrease rapidly. This is because there are some imperfect factors in the production process and the initial use stage of the battery, such as activation materials, self-discharge, etc. Initial decay is usually nonlinear, but the decay trend gradually stabilizes over time. Linear decay: In the mid-term stage of battery use, the decay trend of battery capacity becomes relatively stable and proceeds in a linear manner. That is, after a certain number of cycles or use time, the battery capacity will decrease at a constant rate. The linear decay stage is the most common and predictable decay mode, which can be predicted and estimated by a simple mathematical model. End-of-Life Decay: When the battery has been cycled a lot or used for a long time, it will enter the limit decay stage. At this stage, the decay rate of the battery capacity may accelerate or even drop sharply. This is caused by the irreversible changes of chemical reactions and materials inside the battery. The extreme attenuation stage means that the battery is approaching the end of its life. When the capacity attenuation reaches a certain level, it may no longer provide sufficient energy and needs to be replaced.

[0110] Therefore, the battery degradation process can be decomposed into different stages, and description functions can be constructed for different stages. Based on the above construction of capacity prediction sub-models corresponding to each stage, the characteristic factors of the N+1th cycle are predicted respectively through each capacity prediction sub-model.

[0111] In one example, the capacity prediction sub-model may be constructed and generated through the following steps.

[0112] The attenuation process is split, and descriptive equations are designed for each process. The initial cycle data is combined to learn the equation parameters, and a capacity prediction sub-model is constructed based on the descriptive equations of each stage. The initial cycle data can be cycle data collected for the same model of battery, or it can be the historical cycle data of the target battery before.

[0113] The capacity decay process of lithium batteries can be divided into the coupling of multiple processes. Based on the idea of ​​process decomposition, the capacity decay process can be roughly described as a set of mathematical equations, as shown in the following formula (6):

[0114]

[0115] Where Cap is the capacity, -k2x, The description equations corresponding to the three decay stages are as follows: x is the number of cycles, and c is the constant term. k1, k2, k3, a, b, and c are the six parameters that need to be learned. The above parameters can be used to construct loss functions such as MSE, and the parameters can be learned through the optimization algorithm using the data from the early stage of the cycle.

[0116] Optionally, the learning method of the above parameters includes at least one of optimization algorithms such as direct optimization algorithm, heuristic optimization algorithm, indirect optimization algorithm, etc.

[0117] According to the description equation corresponding to each decay stage in the above formula (6), the capacity prediction sub-model corresponding to each stage can be constructed.

[0118] The parameter learning method may include at least one of the optimization algorithms such as direct optimization algorithm, heuristic optimization algorithm, indirect optimization algorithm, etc.

[0119] In some embodiments, obtaining the battery capacity corresponding to the N+1th cycle according to the first predicted value, the second predicted value, and the third predicted value may include:

[0120] Obtaining a first capacity prediction sub-model, a second capacity prediction sub-model, and a weight coefficient corresponding to the first capacity prediction sub-model;

[0121] According to the weight coefficient, the first prediction value, the second prediction value and the third prediction value are weighted and accelerated to obtain the capacity prediction value.

[0122] In an example, the first capacity prediction sub-model, the second capacity prediction sub-model, and the weight coefficient corresponding to the first capacity prediction sub-model can be determined according to the above formula 6, as follows:

[0123] The weights of each decay stage corresponding to the Nth cycle can be obtained by the following formula (7):

[0124]

[0125] Among them, w Ni :w Nj :w Nk is the weight ratio of the above three processes in the Nth cycle, and the three terms on the right side of the equation are the gradient ratios corresponding to the above three processes in the Nth cycle (i.e., the weights of each attenuation stage corresponding to the Nth cycle).

[0126] In the embodiments of the present application, the data of the battery charge and discharge curve can be recorded, the attenuation characteristics can be extracted from it, and the mechanism characteristics can be combined to use machine learning methods to accurately and efficiently predict the long-term capacity attenuation trend, and then predict the life. The capacity attenuation trend prediction performed by the above method is accurate and efficient, which directly determines the accuracy and efficiency of the above method in predicting the life of lithium batteries, and can meet the requirements for lithium battery life prediction in most real scenarios.

[0127] In some embodiments, the above S104 may further include the following steps:

[0128] Get the cumulative number of cycles of the target battery;

[0129] Based on the accumulated number of cycles and the number of cycles corresponding to the target capacity prediction value, the remaining number of cycles of the target battery is obtained.

[0130] Optionally, the remaining number of cycles = the number of cycles corresponding to the target capacity prediction value - the current accumulated number of cycles.

[0131] Based on the battery life prediction method provided in the above embodiment, the present application also provides an embodiment of a battery life prediction device.

[0132] Figure 2 A schematic diagram of the structure of a battery life prediction device provided in another embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0133] Reference Figure 2 , the battery life prediction device 200 may include:

[0134] A first determination module 201 is used to determine a characteristic factor of the Nth cycle according to the Nth cycle charge and discharge data of the target battery, where the characteristic factor is used to characterize the attenuation characteristics of the target battery, and N is a positive integer;

[0135] The first prediction module 202 is used to input the characteristic factors of the Nth cycle into the characteristic prediction model to obtain the predicted characteristic factors;

[0136] The second prediction module 203 is used to input the prediction characteristic factor into the capacity prediction model to obtain a target capacity prediction value and a corresponding number of cycles, wherein the target capacity prediction value is less than a preset capacity value;

[0137] The second determination module 204 is configured to determine the remaining life of the target battery based on the number of cycles.

[0138] In some embodiments, the first determining module 201 includes:

[0139] The first determination submodule is used to determine the trend characteristics and deformation characteristics of the Nth cycle charge and discharge data based on a time series method to obtain the trend characteristics and deformation characteristics of the Nth cycle.

[0140] In some embodiments, the first determining submodule includes:

[0141] A decomposition unit, used to decompose each data point in the N-th cycle charge and discharge data based on a time series method to obtain trend characteristics and deformation characteristics of each data point;

[0142] The first determining unit is used to determine the trend feature and the deformation feature of the Nth cycle based on the trend feature and the deformation feature of each data point.

[0143] In some embodiments, the second prediction module 203 includes:

[0144] A first prediction unit is used to input the characteristic factor of the Nth cycle into the characteristic prediction model to obtain the characteristic factor of the N+1th cycle;

[0145] A second prediction unit is used to input the characteristic factor of the N+1th cycle into the capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle;

[0146] A cycle unit, used for, when the battery capacity corresponding to the N+1th cycle is greater than or equal to the preset capacity value, setting N=N+1, and returning to execute: inputting the characteristic factor of the Nth cycle into the characteristic prediction model to obtain the characteristic factor of the N+1th cycle, and inputting the characteristic factor of the N+1th cycle into the capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle;

[0147] Until the battery capacity corresponding to the N+1th cycle is less than the preset capacity value, the target capacity prediction value and the corresponding number of cycles are obtained.

[0148] In some embodiments, the first prediction unit includes:

[0149] A first prediction sub-unit is used to input the characteristic factor of the N+1th cycle into a first capacity prediction sub-model to obtain a first prediction value, wherein the first capacity prediction sub-model is generated based on a first function, and the first function is a function corresponding to the first stage of battery capacity attenuation;

[0150] A second prediction sub-unit is used to input the characteristic factor of the N+1th cycle into a second capacity prediction sub-model to obtain a second prediction value, where the second capacity prediction sub-model is generated based on a second function, where the second function is a function corresponding to the second stage of battery capacity attenuation;

[0151] A third prediction subunit is used to input the characteristic factor of the N+1th cycle into a third capacity prediction submodel to obtain a third prediction value, where the third capacity prediction submodel is generated based on a third function, where the third function is a function corresponding to the third stage of battery capacity attenuation;

[0152] The first determining subunit is used to obtain the battery capacity corresponding to the N+1th cycle according to the first predicted value, the second predicted value and the third predicted value.

[0153] In some embodiments, the second determining module 204 includes:

[0154] An acquisition unit, used to acquire the cumulative number of cycles of the target battery;

[0155] The second determining unit is used to obtain the remaining cycle number of the target battery based on the accumulated cycle number and the cycle number corresponding to the target capacity prediction value.

[0156] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application, and are devices corresponding to the above-mentioned battery life prediction method. All implementation methods in the above-mentioned method embodiment are applicable to the embodiments of the device. Its specific functions and technical effects can be found in the method embodiment part, which will not be repeated here.

[0157] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0158] Figure 3 A schematic diagram of the hardware structure of an electronic device provided in yet another embodiment of the present application is shown.

[0159] The device may include a processor 301 and a memory 302 storing programs or instructions.

[0160] When the processor 301 executes the program, the steps in any of the above method embodiments are implemented.

[0161] Exemplarily, the program may be divided into one or more modules / units, one or more modules / units are stored in the memory 302, and executed by the processor 301 to complete the present application. One or more modules / units may be a series of program instruction segments capable of completing a specific function, and the instruction segments are used to describe the execution process of the program in the device.

[0162] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0163] The memory 302 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 302 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 302 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 302 is a non-volatile solid-state memory.

[0164] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) machine-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0165] The processor 301 implements any one of the methods in the above embodiments by reading and executing the program or instruction stored in the memory 302 .

[0166] In one example, the electronic device may further include a communication interface 303 and a bus 304. The processor 301, the memory 302, and the communication interface 303 are connected via the bus 304 and communicate with each other.

[0167] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0168] Bus 304 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 304 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0169] In addition, in combination with the method in the above embodiment, the embodiment of the present application may provide a machine-readable storage medium for implementation. The machine-readable storage medium stores a program or instruction; when the program or instruction is executed by a processor, any one of the methods in the above embodiment is implemented. The machine-readable storage medium can be read by a machine such as a computer.

[0170] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0171] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0172] An embodiment of the present application provides a computer program product, which is stored in a machine-readable storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0173] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0174] The functional modules shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. Code segments can be downloaded via computer grids such as the Internet, intranets, etc.

[0175] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0176] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by a computer program or instruction. These programs or instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0177] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A battery life prediction method, characterized in that: The method comprises: Determine a characteristic factor of the Nth cycle according to the Nth cycle charge and discharge data of the target battery, wherein the characteristic factor is used to characterize the attenuation characteristics of the target battery, and N is a positive integer; Inputting the characteristic factors of the Nth cycle into the characteristic prediction model to obtain the predicted characteristic factors; Inputting the prediction characteristic factor into a capacity prediction model to obtain a target capacity prediction value and a corresponding number of cycles, wherein the target capacity prediction value is less than a preset capacity value; Based on the number of cycles, a remaining life of the target battery is determined.

2. The method according to claim 1, characterized in that The determining the characteristic factor of the Nth cycle according to the Nth cycle charge and discharge data of the target battery includes: Based on the time series method, the trend characteristics and deformation characteristics of the Nth cycle charge and discharge data are determined to obtain the characteristic factors of the Nth cycle.

3. The method according to claim 2, characterized in that The method of determining the trend characteristics and deformation characteristics of the N-th cycle charge and discharge data based on the time series method to obtain the characteristic factors of the N-th cycle includes: Decomposing each data point in the N-th cycle charge and discharge data based on a time series method to obtain trend characteristics and deformation characteristics of each data point; Based on the trend characteristics and deformation characteristics of each of the data points, the characteristic factors of the Nth cycle are determined.

4. The method according to claim 1, characterized in that: The step of inputting the characteristic factor of the Nth cycle into the characteristic prediction model to obtain the predicted characteristic factor; and inputting the predicted characteristic factor into the capacity prediction model to obtain the target capacity prediction value and the corresponding number of cycles comprises: Inputting the characteristic factor of the Nth cycle into a characteristic prediction model to obtain the characteristic factor of the N+1th cycle; Inputting the characteristic factors of the N+1th cycle into a capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle; In the case that the battery capacity corresponding to the N+1th cycle is greater than or equal to the preset capacity value, let N=N+1, and return to the execution of: the step of inputting the characteristic factor of the Nth cycle into the characteristic prediction model to obtain the characteristic factor of the N+1th cycle, and the step of inputting the characteristic factor of the N+1th cycle into the capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle; Until the battery capacity corresponding to the N+1th cycle is less than the preset capacity value, the target capacity prediction value and the corresponding number of cycles are obtained.

5. The method according to claim 4, characterized in that The step of inputting the characteristic factor of the N+1th cycle into a capacity prediction model to obtain the battery capacity corresponding to the N+1th cycle includes: Inputting the characteristic factor of the N+1th cycle into a first capacity prediction sub-model to obtain a first prediction value, wherein the first capacity prediction sub-model is generated based on a first function, and the first function is a function corresponding to a first stage of battery capacity decay; Inputting the characteristic factor of the N+1th cycle into a second capacity prediction sub-model to obtain a second prediction value, wherein the second capacity prediction sub-model is generated based on a second function, and the second function is a function corresponding to the second stage of battery capacity attenuation; Inputting the characteristic factor of the N+1th cycle into a third capacity prediction sub-model to obtain a third prediction value, wherein the third capacity prediction sub-model is generated based on a third function, and the third function is a function corresponding to the third stage of battery capacity attenuation; The battery capacity corresponding to the N+1th cycle is obtained according to the first predicted value, the second predicted value and the third predicted value.

6. The method according to claim 1, characterized in that Determining the remaining life of the target battery based on the number of cycles includes: Obtaining the cumulative number of cycles of the target battery; Based on the accumulated number of cycles and the number of cycles corresponding to the target capacity prediction value, the remaining number of cycles of the target battery is obtained.

7. A battery life prediction device, characterized in that: The device comprises: A first determination module, configured to determine a characteristic factor of an Nth cycle according to the Nth cycle charge and discharge data of a target battery, wherein the characteristic factor is used to characterize the attenuation characteristics of the target battery, and N is a positive integer; The first prediction module is used to input the characteristic factors of the Nth cycle into the characteristic prediction model to obtain the predicted characteristic factors; A second prediction module is used to input the prediction characteristic factor into a capacity prediction model to obtain a target capacity prediction value and a corresponding number of cycles, wherein the target capacity prediction value is less than a preset capacity value; The second determination module is used to determine the remaining life of the target battery based on the number of cycles.

8. An electronic device, characterized in that: The device comprises: a processor and a memory storing programs or instructions; When the processor executes the program or instruction, the method according to any one of claims 1 to 6 is implemented.

9. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the method according to any one of claims 1 to 6.

Images