Battery life prediction method and system and storage medium

Abstract

The invention provides a battery life prediction method and system and a storage medium, and relates to the technical field of battery management, and the method comprises the steps: obtaining the current actual working condition parameter and actual passing charge quantity of a target battery in the current cycle; charge equivalent parameters of the target battery are determined based on the actual working condition parameters, and the charge equivalent parameters are the ratio of the full-life-cycle charge throughput of the battery cell of the target battery under the reference working condition to the full-life-cycle charge throughput of the battery cell of the target battery under the current working condition; based on the charge equivalent parameters, obtaining the equivalent charge quantity of the actual passing charge quantity equivalent to the reference working condition; acquiring an accumulated charge quantity of the target battery based on the equivalent charge quantity; a target battery SOH is generated as a first prediction result based on the accumulated charge amount. According to the method, the SOH of the target battery is estimated through the calculation principle of the equivalent charge quantity, the relation between the accumulated charge quantity change in the charging and discharging process of the battery and the charge equivalent parameters is established, and good SOH prediction precision is achieved.

Description

Technical Field

[0001] This disclosure belongs to the field of battery management technology, specifically relating to a battery life prediction method, system, and storage medium. Background Technology

[0002] Battery pack life assessment is crucial in applications such as electric vehicles and energy storage systems. The state of health (SOH) of a battery pack, as a key indicator of its lifespan, is of significant research value.

[0003] In related technologies, battery life prediction mainly employs capacity decay methods, internal resistance methods, model-driven methods, and data-driven methods. The capacity decay method, also known as the direct method, directly measures the state of equilibrium (SOH) of the battery pack through a complete charge-discharge test. However, since batteries rarely undergo complete charge-discharge cycles in practical applications, this method is difficult to use online in real time. The internal resistance method, also known as the indirect method, indirectly obtains SOH by measuring changes in the battery's internal resistance. This requires high-precision voltage and current sensors, but the non-linear relationship between internal resistance changes and capacity decay leads to significant errors. The model-driven method simulates the internal state and aging process of the battery based on electrochemical models or equivalent circuit models. This method uses complex models with numerous parameters and high computational demands, resulting in excessively high computational requirements for the battery management system (BMS). The data-driven method uses machine learning algorithms such as support vector machines and neural networks to learn aging patterns from historical data. Because it relies on a large amount of training data, the computational cost of model training and inference is high.

[0004] In summary, the relevant technologies struggle to simultaneously balance computational complexity, prediction accuracy, and real-time performance when predicting battery life. Summary of the Invention

[0005] This disclosure provides a battery life prediction method, system, and storage medium, aiming to at least partially solve the technical problem that related technologies struggle to simultaneously balance computational complexity, prediction accuracy, and real-time performance.

[0006] At least one embodiment of this disclosure provides a battery life prediction method, including: Obtain the target battery's current actual operating parameters and actual charge amount in this cycle; The charge equivalent parameters of the target battery are determined based on the actual operating condition parameters, wherein the charge equivalent parameters are the ratio of the total life-cycle charge throughput of the target battery under the baseline operating condition to the total life-cycle charge throughput of the target battery under the current operating condition corresponding to the actual operating condition parameters; and, The actual amount of charge passing through is obtained based on the charge equivalence parameters, which is equivalent to the amount of charge under the reference operating condition. The cumulative charge of the target battery is obtained based on the equivalent charge; and, The current state of charge (SOH) of the target battery is generated based on the accumulated charge, serving as a first prediction result for characterizing the target battery's lifetime.

[0007] The above solution offers the following technical advantages: It proposes an improved battery life prediction method that estimates the State of Health (SOH) of the target battery based on the calculation principle of equivalent charge. The core idea is to establish an equivalent relationship between the charge change during battery charging and discharging (characterized by cumulative charge) and battery capacity decay (characterized by charge equivalence parameters), resulting in good prediction accuracy. This calculation method offers significant advantages in computational simplicity, requiring only the acquisition of actual operating parameters and actual charge flow during battery charging and discharging. It places extremely low demands on the hardware computing power of the Battery Management System (BMS), eliminating the need for a high-performance processor. Furthermore, since this method does not require a complete cycle and can perform predictions at any point in the current cycle, it is particularly suitable for applications with high real-time requirements, such as automotive battery management systems. It enables online real-time monitoring and evaluation of battery health, providing reliable data support for battery maintenance and life prediction.

[0008] The method provided in at least one embodiment of this disclosure further includes: Based on the charge equivalent parameters, the total charge that the target battery can carry over its entire lifespan under the current operating conditions is obtained, wherein the total charge that can carry over its entire lifespan is negatively correlated with the charge equivalent parameters; and... The predicted cycle number of the target battery is generated based on the amount of charge that can be generated during the entire life cycle and the actual amount of charge that can be generated, and is used as a second prediction result to characterize the life of the target battery.

[0009] The above scheme has the following technical advantages: The total charge transfer experienced by the target battery from its newest state to failure can be characterized by the charge quantity throughout its entire lifespan. The predicted cycle count obtained based on the charge quantity throughout the entire lifespan directly reflects the remaining service life of the battery.

[0010] In at least one embodiment of the method provided in this disclosure, the actual operating condition parameters include charge / discharge rate and cell temperature, and the step of determining the charge equivalent parameters of the target battery based on the actual operating condition parameters includes: A first intermediate parameter acquisition model matching the cell temperature is obtained, wherein the first intermediate parameter acquisition model is configured to generate the first intermediate parameter based on the input charge / discharge rate, and different first intermediate parameter acquisition models are used for different cell temperatures. Input the charge / discharge rate into the first intermediate parameter acquisition model to obtain the first intermediate parameter; A second intermediate parameter acquisition model matching the charge / discharge rate is obtained, wherein the second intermediate parameter acquisition model is configured to generate the second intermediate parameter based on the input cell temperature, and different second intermediate parameter acquisition models are used for different charge / discharge rate matching. The cell temperature is input into the second intermediate parameter acquisition model to obtain the second intermediate parameter; and... The charge equivalent parameter is obtained based on the first intermediate parameter and the second intermediate parameter, wherein the charge equivalent parameter is configured to be related to and positively correlated with both the first intermediate parameter and the second intermediate parameter.

[0011] The above scheme has the following technical effects: the relationship between charge equivalent parameters and charge / discharge rate is established through the first intermediate parameter acquisition model, and the relationship between charge equivalent parameters and cell temperature is established through the second intermediate parameter acquisition model. This model can more comprehensively and accurately reflect the relevant characteristics of the battery, providing key data support for subsequent battery life prediction.

[0012] In the method provided in at least one embodiment of this disclosure, the first intermediate parameter is linearly related to the charge / discharge rate, the second intermediate parameter is nonlinearly related to the cell temperature, and the charge equivalent parameter is the product of the first intermediate parameter and the second intermediate parameter.

[0013] The above solution has the following technical effects: the above relationship closely reflects the influence of charge / discharge rate and cell temperature on battery characteristics under actual conditions, so that the charge equivalent parameters can more comprehensively and accurately reflect the overall characteristics of the battery under the current state.

[0014] In at least one embodiment of the method provided in this disclosure, the total lifetime charge throughput is configured as the charge throughput of the target battery when it is cycled to a set state of equilibrium (SOH). Furthermore, the method further includes a process of constructing a first intermediate parameter acquisition model and a second intermediate parameter acquisition model, the process comprising: Determine the baseline operating conditions; The actual operating parameters and cell charge throughput over the entire life cycle of the target battery are obtained under the benchmark operating condition and at least two first-type reference operating conditions and at least two second-type reference operating conditions other than the benchmark operating condition. The charge and discharge rates of the different first-type reference operating conditions are different but the cell temperature is the same, and the cell temperature of the different second-type reference operating conditions is different but the charge and discharge rates are the same. For each of the first type of reference operating conditions, the ratio of the total life cycle charge throughput of the target battery cell under the benchmark operating condition to the total life cycle charge throughput of the target battery cell under the first type of reference operating condition is obtained, and used as the charge equivalent parameter corresponding to the first type of reference operating condition. The first intermediate parameter acquisition model is constructed based on the actual operating parameters and charge equivalent parameters corresponding to each of the first type of reference operating conditions. For each of the second type of reference operating conditions, the ratio of the total life cycle charge throughput of the target battery cell under the baseline operating condition to the total life cycle charge throughput of the target battery cell under the second type of reference operating condition is obtained, and used as the charge equivalent parameter corresponding to the second type of reference operating condition; The second intermediate parameter acquisition model is constructed based on the actual operating parameters and charge equivalent parameters corresponding to each of the second type of reference operating conditions.

[0015] The above solution has the following technical effects: the first intermediate parameter acquisition model and the second intermediate parameter acquisition model can be used to correct and predict battery performance parameters under different operating conditions, so as to improve the accuracy of battery life prediction.

[0016] The method provided in at least one embodiment of this disclosure further includes the following steps: Obtain the charge / discharge rate range corresponding to the first type of reference operating condition; Within the charge / discharge rate range, the number of current first-type reference conditions is expanded based on the charge equivalent parameters corresponding to each of the first-type reference conditions to obtain multiple new charge equivalent parameters corresponding to the first-type reference conditions, which are used to construct the first intermediate parameter acquisition model. Obtain the cell temperature range corresponding to the second type of reference operating condition; and, Within the cell temperature range, the number of current second-type reference conditions is expanded based on the charge equivalent parameters corresponding to each of the second-type reference conditions to obtain multiple new charge equivalent parameters corresponding to the second-type reference conditions, which are used to construct a second intermediate parameter acquisition model.

[0017] The above solution has the following technical effects: it increases the data volume of the reference working condition and improves the comprehensiveness and accuracy of the charge equivalent parameter acquisition model.

[0018] In at least one embodiment of the method provided in this disclosure, the equivalent charge is the product of the actual through charge and the charge equivalence parameter; and, The step of obtaining the cumulative charge of the target battery based on the equivalent charge includes: inputting the equivalent charge into a pre-set cumulative charge acquisition model to obtain the cumulative charge, wherein the cumulative charge acquisition model is configured to generate the cumulative charge based on historical cumulative charge data before the current cycle and the current equivalent charge in the current cycle, and the cumulative charge is positively correlated with both the historical cumulative charge data and the equivalent charge.

[0019] The above solution has the following technical effects: the accumulated charge changes in real time through the above acquisition method, which can truly reflect the charge accumulation of the battery in actual use.

[0020] In at least one embodiment of the method provided in this disclosure, generating the current SOH of the target battery based on the accumulated charge includes: obtaining a first ratio data of the accumulated charge of the target battery in the current cycle and the accumulated charge of the target battery under a reference condition, and generating the current SOH of the target battery based on the first ratio data, wherein the current SOH of the target battery is linearly related to and negatively correlated with the first ratio data; The step of generating the predicted cycle number of the target battery based on the amount of charge that can be passed over the entire life cycle and the actual amount of charge that can be passed over the entire life cycle includes: obtaining a second ratio data of the amount of charge that can be passed over the entire life cycle and the actual amount of charge that can be passed over the target battery in one cycle, and generating the predicted cycle number of the target battery based on the second ratio data, wherein the predicted cycle number is linearly related to the second ratio data and is positively correlated.

[0021] The above scheme has the following technical effects: The first ratio data reflects that when the cumulative charge of the target battery decreases compared to the baseline operating condition, its State of Charge (SOH) also decreases, thus intuitively showing the battery performance degradation trend. By establishing the relationship between the first ratio data and SOH, the accuracy of SOH prediction is improved. The second ratio data reflects the ratio of the charge that the target battery can carry throughout its entire life cycle under current operating conditions to the actual charge carried in a single cycle. By establishing a linear model between the second ratio data and the predicted number of cycles, the cycle life of the battery under current operating conditions can be predicted more accurately.

[0022] At least one embodiment of this disclosure also provides a battery life prediction system, including: The acquisition unit is configured to acquire the target battery's current actual operating parameters and actual charge amount in this cycle. The preprocessing unit is configured to determine the charge equivalent parameters of the target battery based on the actual operating condition parameters, wherein the charge equivalent parameters are the ratio of the total life-cycle charge throughput of the target battery under the reference operating condition to the total life-cycle charge throughput of the target battery under the current operating condition corresponding to the actual operating condition parameters. The first prediction unit is configured to obtain the equivalent charge amount of the actual through charge under the reference operating condition based on the charge equivalence parameter, and to obtain the cumulative charge amount of the target battery based on the equivalent charge amount, and to generate the current SOH of the target battery based on the cumulative charge amount as a first prediction result for characterizing the lifespan of the target battery.

[0023] At least one embodiment of this disclosure also provides a storage medium storing a program or instructions, wherein the program or instructions, when executed by a processor, implement the steps of the method provided in any embodiment of this disclosure.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A flowchart illustrating a battery life prediction method provided for at least one embodiment of this disclosure; Figure 2 A flowchart illustrating a scheme for obtaining charge equivalent parameters provided in at least one embodiment of this disclosure; Figure 3 A flowchart illustrating the modeling of the charge equivalent parameter model provided in at least one embodiment of this disclosure; Figure 4 A flowchart of another battery life prediction method provided for at least one embodiment of this disclosure; Figure 5 A structural block diagram of a battery life prediction system provided in at least one embodiment of this disclosure; Figure 6 A schematic diagram illustrating the composition of a program product provided for at least one embodiment of this disclosure.

[0027] Figure label: 10- Battery life prediction system; 11- Acquisition unit; 12- Preprocessing unit; 13- First prediction unit; 21- Processor; 22- Memory; 23- Input device; 24- Output device. Detailed Implementation

[0028] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be particularly noted that the following embodiments are for illustrative purposes only and do not limit the scope of the disclosure. Similarly, the following embodiments are only some, not all, embodiments of the present disclosure, and all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0029] The terms "first," "second," and "third" used in the embodiments of this disclosure are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first," "second," and "third" may explicitly or implicitly include at least one of that feature.

[0030] In the description of this disclosure, "multiple" means at least two, such as two or three, unless otherwise expressly and specifically limited.

[0031] In this disclosure, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0032] The terms “comprising” and “having”, and any variations thereof, used in this disclosure are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or components inherent to such processes, methods, products, or devices.

[0033] In this disclosure, the term "health status" is short for State of Health (SOH), which reflects the battery's health status and remaining lifespan.

[0034] In the embodiments of this disclosure, the term "charge / discharge rate" refers to the ratio of the actual current of the battery during charging or discharging to the rated current.

[0035] In the embodiments of this disclosure, the term "charge throughput" refers to the total amount of charge absorbed and released by the battery during charging and discharging.

[0036] In the embodiments of this disclosure, the term "actual charge" refers to the total amount of charge released by the battery under specific discharge conditions.

[0037] In this disclosure, the term "cycle" refers to one complete charge and discharge cycle of the battery under specified conditions. As the number of cycles increases, the state of harmonics (SOH) of the battery gradually decreases, and the remaining service life also decreases accordingly.

[0038] The related technologies face the challenge of simultaneously addressing computational complexity, prediction accuracy, and real-time performance. Specifically, the capacity decay method is problematic in practical applications where batteries rarely undergo complete charge-discharge cycles, making direct capacity measurement difficult. The internal resistance method requires high-precision voltage and current sensors and suffers from significant errors. Model-driven and data-driven methods, on the other hand, require substantial computational resources and excessively long processing times.

[0039] To address the aforementioned technical issues, this disclosure proposes an improved battery life prediction method. This method estimates the state of health (SOH) of the target battery through the calculation principle of equivalent charge. Its core idea is to establish an equivalent relationship between the charge change during battery charging and discharging (characterized by cumulative charge) and battery capacity decay (characterized by charge equivalence parameters), resulting in good prediction accuracy. This calculation method offers significant advantages in computational simplicity, requiring only the acquisition of actual operating parameters and actual charge flow during battery charging and discharging. It places extremely low demands on the hardware computing power of the battery management system (BMS), eliminating the need for a high-performance processor. Furthermore, since this method does not require a complete cycle and can perform predictions at any point in the current cycle, it is particularly suitable for applications with high real-time requirements, such as automotive battery management systems. It enables online real-time monitoring and evaluation of battery health, providing reliable data support for battery maintenance and life prediction.

[0040] Figure 1 A flowchart illustrating a battery life prediction method provided for at least one embodiment of this disclosure. Figure 1 As shown, the method may include the following steps S10-S50.

[0041] Step S10: Obtain the target battery's current actual operating parameters and actual charge amount in this cycle.

[0042] Step S20: Determine the charge equivalent parameters of the target battery based on the actual operating condition parameters, wherein the charge equivalent parameters are the ratio of the total life cycle charge throughput of the target battery cell under the reference operating condition to the total life cycle charge throughput of the target battery cell under the current operating condition corresponding to the actual operating condition parameters.

[0043] Step S30: Based on the charge equivalent parameter, obtain the actual charge passing amount equivalent to the equivalent charge under the reference operating condition.

[0044] Step S40: Obtain the cumulative charge of the target battery based on the equivalent charge.

[0045] Step S50: Based on the accumulated charge, generate the SOH of the target battery as the first prediction result for characterizing the lifetime of the target battery.

[0046] It should be noted that the charge equivalent parameter is a custom parameter of this disclosure, and its physical meaning is equivalent to the release of 1 Ah of charge under actual operating conditions, which is equivalent to the release of charge under reference operating conditions. n The capacity decay of Ah. The formula for calculating the charge equivalent parameter is as follows:

[0047] In the formula, Represents the charge equivalent parameter, This represents the total charge throughput of the target battery cell over its entire lifecycle under baseline operating conditions. This represents the total charge throughput of the target battery cell throughout its entire lifecycle under the current operating conditions corresponding to the actual operating parameters.

[0048] In the above scheme, actual operating parameters include, but are not limited to, charge / discharge rate and cell temperature. For example, actual operating parameters may also include the battery's charge / discharge cut-off voltage. The charge / discharge rate determines the battery's charge throughput per unit time, thus affecting the rate of consumption of the battery's chemically active materials; while cell temperature directly affects the rate of chemical reactions inside the battery. High temperatures accelerate the battery's aging process, while low temperatures may lead to a decline in battery performance. Excessively high charge / discharge cut-off voltage increases internal battery pressure, accelerating electrolyte decomposition and causing rapid capacity decay; conversely, excessively low charge / discharge cut-off voltage may prevent the battery from fully releasing or storing energy, and prolonged exposure to this state will also affect battery performance and lifespan. Therefore, when determining the charge equivalent parameters of the target battery, these actual operating parameters must be fully considered to ensure the accuracy of the prediction results. These parameters accurately reflect the battery's operating state and environmental conditions during actual use and are crucial for determining the target battery's charge equivalent parameters. By comprehensively considering the charge / discharge rate, cell temperature, and charge / discharge cut-off voltage, the battery's performance under actual operating conditions can be more comprehensively evaluated, thereby improving the accuracy and reliability of battery life prediction.

[0049] In the above scheme, this disclosure does not limit the method for obtaining the actual operating parameters and actual charge carried by the target battery in this cycle in step S10. In practical applications, the actual operating parameters and actual charge carried by the target battery in this cycle can be obtained through various means. For example, high-precision sensors can be used to monitor the battery's charge / discharge rate, cell temperature, and other operating parameters in real time, while a dedicated charge metering device can be used to accurately measure the actual charge carried. In addition, an advanced battery management system can be used, which can integrate data from multiple sensors to comprehensively collect and process the battery's actual operating parameters and charge carried, thereby providing accurate and reliable data support for subsequent battery life prediction.

[0050] For different types and specifications of batteries, step S10 can select an appropriate parameter acquisition method based on their characteristics. For some small portable batteries, due to space and cost limitations, lightweight and accurate sensors can be used for parameter monitoring; while for large energy storage batteries, a battery management system with more comprehensive data acquisition can be used to obtain the required information. Through this diversified parameter acquisition approach, it is ensured that the actual operating parameters and actual charge carried by the target battery in the current cycle can be accurately obtained in different application scenarios.

[0051] In the above-described scheme, this disclosure does not limit the method for determining the charge equivalent parameters of the target battery in step S20. This disclosure can utilize various methods to determine the charge equivalent parameters of the target battery. For example, statistical analysis can be performed on historical capacity decay data of a large number of similar batteries under the same or similar usage conditions to infer the potential capacity decay of the target battery; alternatively, simulation calculations can be performed based on the battery's electrochemical model, combined with parameters such as the battery's charge-discharge characteristics and material properties, to obtain the charge equivalent parameters; furthermore, machine learning algorithms can be used to learn and train the battery's operating data under different operating conditions to predict the charge equivalent parameters of the target battery.

[0052] When determining the charge-equivalent parameters of the target battery, step S20 can consider the complementarity between different methods. For example, historical capacity decay data obtained through statistical analysis can be used as an initial reference, and then corrected by combining the simulation calculation results of the electrochemical model to obtain more accurate charge-equivalent parameters. At the same time, the prediction results of machine learning algorithms can also serve as an important supplement, especially when dealing with complex operating conditions or novel batteries, as they can provide more forward-looking parameter predictions. By comprehensively applying the above methods, the accuracy of determining the charge-equivalent parameters can be significantly improved, thus laying a solid foundation for subsequent battery lifetime prediction.

[0053] In the above scheme, this disclosure does not limit the method of obtaining the equivalent charge amount under the reference operating condition based on the charge equivalent parameters in step S30. In actual operation, step S30 can be implemented in various ways. For example, the actual charge amount collected under the actual operating condition can be converted into the equivalent charge amount under the reference operating condition according to the conversion rules specified by the pre-constructed charge conversion model. This conversion model can be fitted based on a large amount of experimental data and can accurately reflect the correspondence of charge amounts under different operating conditions. In addition, advanced algorithms can be used to conduct in-depth analysis and processing of the actual charge amount. By comprehensively considering the battery's operating characteristics, electrochemical parameters and other factors under different operating conditions, specific algorithms can be used to calculate the charge amount equivalent to the reference operating condition. These algorithms can be optimized and adjusted according to actual needs to improve the accuracy and reliability of the calculation.

[0054] In addition to the charge conversion model and advanced algorithms mentioned above, step S30 can also be implemented using machine learning methods. Specifically, a large amount of actual battery charge data under different operating conditions and corresponding equivalent charge data under benchmark operating conditions can be collected, and this data can be used as training samples to be input into the machine learning model for training. A fully trained machine learning model can automatically learn the complex mapping relationship between different operating conditions and equivalent charge. When a new actual charge under a new actual operating condition is input, the model can quickly and accurately output the corresponding equivalent charge under the benchmark operating condition. Furthermore, by continuously collecting new data to update and optimize the model, the accuracy and adaptability of the model's predictions can be further improved, thus better fulfilling the task of obtaining the equivalent charge of the actual charge under the benchmark operating condition in step S30.

[0055] In the above scheme, this disclosure does not limit the scheme of obtaining the cumulative charge of the target battery based on the equivalent charge in step S40. In practical application scenarios, step S40 can be implemented in a variety of ways. One feasible approach is to construct a mathematical relationship model between the equivalent charge and the cumulative charge using historical data of the target battery under different equivalent charge conditions, such as a linear regression model or a multinomial regression model. By analyzing and fitting these historical data, the parameters of the model are determined. Then, when a new equivalent charge is obtained, the value is substituted into the model to calculate the corresponding cumulative charge of the target battery. In addition, intelligent prediction methods based on machine learning can also be used. A large amount of cumulative charge data of different types of batteries under various equivalent charge conditions is collected to form a rich dataset. This data is used to train machine learning models, such as neural network models or decision tree models. The trained model can automatically capture the complex nonlinear relationship between the equivalent charge and the cumulative charge. When the equivalent charge obtained in step S30 is input, the model can quickly and accurately predict the cumulative charge of the target battery. Furthermore, with continuous data accumulation and model optimization, the accuracy and reliability of the prediction will be further improved.

[0056] In addition to the two approaches mentioned above, step S40 can also consider using physical model simulation. By establishing an electrochemical model of the battery's interior, the charge transfer and accumulation processes within the battery under different equivalent charge conditions can be simulated, thereby obtaining the accumulated charge of the target battery. Although this method has higher computational complexity, it allows for a deeper understanding of the battery's internal physical mechanisms, providing a more accurate basis for battery life prediction. Furthermore, multiple methods can be combined to form a comprehensive prediction strategy, further improving the accuracy and robustness of the predictions.

[0057] In the above scheme, this disclosure does not limit the method for generating the SOH of the target battery based on the accumulated charge in step S50. In practical applications, step S50 can generate the SOH of the target battery based on the accumulated charge in various ways. For example, a mathematical model between the accumulated charge and SOH can be constructed, and historical data and experimental results can be used to fit the model to obtain a quantitative correlation between the two. Step S50 can also use machine learning algorithms to automatically learn and predict SOH by training on a large amount of sample data. This method can more effectively adapt to different types and conditions of batteries, improving the accuracy and generalization performance of the prediction.

[0058] In addition to constructing mathematical models and applying machine learning algorithms as described above, step S50 can also consider using methods based on physical characteristics. By conducting in-depth analysis of the physical characteristics of battery electrode materials and battery structure, and combining this with accumulated charge data, physical formulas or models related to SOH can be derived. This method can more directly present the physical change process inside the battery, thus providing a more accurate basis for SOH prediction. Meanwhile, to further improve the accuracy and stability of the prediction, step S50 can also combine multiple methods to conduct comprehensive prediction, and select the most suitable prediction strategy based on the actual application scenario and requirements.

[0059] Through steps S10-S50, this method systematically and comprehensively acquires key parameters of the target battery at different times, and derives the State of Health (SOH) of the target battery at different times based on these parameters. Throughout the process, each step is closely linked, from the accurate acquisition of actual operating parameters and actual charge flow, to the scientific determination of charge equivalence parameters, and then to the accurate calculation of equivalent charge and cumulative charge, ultimately achieving reliable SOH generation. This step-by-step, multi-dimensional comprehensive approach fully considers various complex factors and changes during battery use, effectively avoiding the limitations that may arise from a single method, and significantly improving the accuracy and reliability of battery life prediction. Regardless of the type of battery or the various usage environments and operating conditions, this solution, with its flexibility and adaptability, provides strong support for battery health status assessment, thereby providing a scientific basis for the rational use, maintenance, and replacement decisions of the battery, helping to extend the overall battery life and reduce operating costs.

[0060] Some embodiments of this disclosure also provide systems, storage media, and program products corresponding to the methods described above.

[0061] The method provided by at least one embodiment of this disclosure is applicable to any existing battery application scenario requiring multiple charge-discharge cycles. For example, in the field of electric vehicles, this method can accurately predict battery life degradation under different driving conditions, providing car owners with reasonable charging and usage suggestions to extend the overall battery life. In energy storage power station scenarios, this method can be used to predict the lifespan of a large number of batteries, allowing for advance planning of battery replacement and maintenance, and ensuring the stable operation of the energy storage system. For consumer electronics products, such as mobile phones and tablets, this method can also accurately assess battery life, helping users to rationally schedule device usage and charging times.

[0062] In some embodiments, to improve prediction accuracy, the actual operating condition parameters obtained in step S10 are configured to include charge / discharge rate and cell temperature. In practical applications, the charge / discharge rate has a significant impact on battery lifespan. Higher charge / discharge rates typically accelerate battery aging and reduce cycle life. Cell temperature is also a key factor affecting battery performance; excessively high or low cell temperatures are detrimental to long-term stable battery operation. Excessively high temperatures may exacerbate internal chemical reactions and damage the battery structure; while excessively low temperatures increase internal resistance, affecting charge / discharge efficiency and thus reducing the accuracy of battery life prediction. Therefore, incorporating charge / discharge rate and cell temperature into the actual operating condition parameters as considerations for State of Health (SOH) allows for more accurate acquisition of the target battery's SOH based on charge equivalence parameters, and further generates a more accurate predicted cycle life for the target battery.

[0063] In some embodiments, to improve the accuracy of battery life prediction, the total lifecycle charge throughput in step S20 is configured as the charge throughput of the target battery when it cycles to a set State of Health (SOH). Here, the target battery cycling to the set SOH serves as a metric for the end of the target battery's lifespan. The set SOH is a pre-set health state threshold based on the battery's actual application scenario and performance requirements. The accumulated charge throughput when the target battery cycles to this set SOH is the lifecycle charge throughput. This configuration fully considers the performance degradation of the battery under different usage conditions. By setting a reasonable SOH, the battery's lifecycle boundary can be accurately defined, thereby precisely calculating the lifecycle charge throughput and providing crucial and accurate data support for subsequent battery life prediction.

[0064] Figure 2 A flowchart illustrating a scheme for obtaining charge equivalent parameters provided in at least one embodiment of this disclosure. Figure 1 Based on this, in order to make the prediction results more comprehensively and accurately reflect the relevant characteristics of the battery, such as Figure 2 As shown, step S20 is further refined into sub-steps S201-S205.

[0065] Sub-step S201: Obtain a first intermediate parameter acquisition model that matches the cell temperature, wherein the first intermediate parameter acquisition model is configured to generate the first intermediate parameter based on the input charge / discharge rate, and different first intermediate parameter acquisition models are used for different cell temperatures.

[0066] Sub-step S202: Input the charge / discharge rate into the first intermediate parameter to obtain the model, and obtain the first intermediate parameter.

[0067] Sub-step S203: Obtain a second intermediate parameter acquisition model that matches the charge / discharge rate, wherein the second intermediate parameter acquisition model is configured to generate the second intermediate parameter based on the input cell temperature, and different second intermediate parameter acquisition models are used for different charge / discharge rate matches.

[0068] Sub-step S204: Input the cell temperature into the second intermediate parameter to obtain the model, and obtain the second intermediate parameter.

[0069] Sub-step S205: Obtain the charge equivalent parameter based on the first intermediate parameter and the second intermediate parameter, wherein the charge equivalent parameter is configured to be related to both the first intermediate parameter and the second intermediate parameter and to be positively correlated.

[0070] In this process, sub-step S201 determines a first intermediate parameter acquisition model adapted to the current cell temperature. This model can quickly generate the corresponding first intermediate parameter based on the input charge / discharge rate. Since different cell temperatures correspond to different first intermediate parameter acquisition models, this ensures the accuracy of the first intermediate parameter acquisition. In sub-step S202, the actually measured charge / discharge rate is input into the selected first intermediate parameter acquisition model to successfully obtain the first intermediate parameter. Subsequently, sub-step S203 performs the operation of acquiring a second intermediate parameter acquisition model matching the current charge / discharge rate. This model can generate the second intermediate parameter based on the input cell temperature, and different charge / discharge rates correspond to different second intermediate parameter acquisition models, ensuring the accuracy of the second intermediate parameter acquisition. In sub-step S204, the actually measured cell temperature is input into the corresponding second intermediate parameter acquisition model to obtain the second intermediate parameter. Finally, in sub-step S205, the first and second intermediate parameters are combined, and the charge equivalent parameter is obtained according to a specific algorithm. The charge equivalent parameter is positively correlated with both the first and second intermediate parameters, which can more comprehensively and accurately reflect the relevant characteristics of the battery and provide key data support for subsequent battery life prediction.

[0071] In some embodiments, to accurately establish the relationship between the charge equivalent parameter and actual operating parameters, the first intermediate parameter obtained through the first intermediate parameter acquisition model has a linear relationship with the charge / discharge rate, while the second intermediate parameter obtained through the second intermediate parameter acquisition model has a non-linear relationship with the cell temperature. The charge equivalent parameter is the product of the first and second intermediate parameters. The first intermediate parameter acquisition model ensures that the output of the first intermediate parameter corresponds linearly to the charge / discharge rate at the same cell temperature. This linear relationship allows the charge equivalent parameter to intuitively reflect the impact of the charge / discharge rate on the battery state. The second intermediate parameter acquisition model, on the other hand, fully considers the complexity of cell temperature changes at the same charge / discharge rate. Through complex algorithms and model structures, it accurately captures the non-linear relationship between cell temperature and the second intermediate parameter, thus better reflecting the impact of cell temperature on battery characteristics under actual conditions. Configuring the charge equivalent parameter as the product of the first and second intermediate parameters integrates the influence of two key factors—charge / discharge rate and cell temperature—on the battery. This allows the charge equivalent parameter to more comprehensively and accurately reflect the battery's overall characteristics in the current state, providing a solid and reliable data foundation for subsequent accurate prediction of battery life.

[0072] The model for obtaining the first intermediate parameter can be represented as:

[0073] In the formula, Indicates the first intermediate parameter. and Representing different fitting coefficients, This indicates the charge / discharge rate.

[0074] The model for obtaining the second intermediate parameter can be represented as:

[0075] In the formula, This indicates the second intermediate parameter. Represents the molar gas constant. Indicates activation energy. Indicates the pre-exponential coefficient. This indicates the temperature of the battery cell.

[0076] Charge equivalent parameters It can be represented as:

[0077] Figure 3 A flowchart illustrating the modeling of a charge equivalent parameter model provided in at least one embodiment of this disclosure. The charge equivalent parameter model includes a first intermediate parameter acquisition model and a second intermediate parameter acquisition model. To improve modeling accuracy, in Figure 2 On the basis of, such as Figure 3 As shown, the method also includes a process of constructing a first intermediate parameter acquisition model and a second intermediate parameter acquisition model, which includes the following steps S01-S06.

[0078] Step S01: Determine the baseline operating conditions.

[0079] Step S02: Obtain the actual operating parameters of the target battery and the total charge throughput of the cell throughout its entire life cycle under the baseline operating condition and at least two first-type reference operating conditions and at least two second-type reference operating conditions other than the baseline operating condition. The charge and discharge rates of each first-type reference operating condition are different, but the cell temperature is the same. The cell temperature of each second-type reference operating condition is different, but the charge and discharge rates are the same.

[0080] Step S03: For each first type of reference operating condition, obtain the ratio of the total life cycle charge throughput of the target battery cell under the baseline operating condition to the total life cycle charge throughput of the target battery cell under the first type of reference operating condition, and use it as the charge equivalent parameter corresponding to the first type of reference operating condition.

[0081] Step S04: Construct a first intermediate parameter acquisition model based on the actual operating parameters and charge equivalent parameters corresponding to each first type of reference operating condition.

[0082] Step S05: For each second type of reference operating condition, obtain the ratio of the total life cycle charge throughput of the target battery cell under the baseline operating condition to the total life cycle charge throughput of the target battery cell under the second type of reference operating condition, and use it as the charge equivalent parameter corresponding to the second type of reference operating condition.

[0083] Step S06: Construct a second intermediate parameter acquisition model based on the actual operating parameters and charge equivalent parameters corresponding to each second type of reference operating condition.

[0084] It should be noted that steps S01-S06 can be set before step S10.

[0085] The first and second intermediate parameter acquisition models can be used to correct and predict battery performance parameters under different operating conditions, thereby improving the accuracy of battery life prediction. Specifically, the first intermediate parameter acquisition model can derive battery performance under other similar charge / discharge rates but different specific operating conditions based on the actual operating parameters and charge equivalent parameters under the first type of reference operating condition; while the second intermediate parameter acquisition model can predict battery performance changes under different cell temperatures but the same charge / discharge rate based on the actual operating parameters and charge equivalent parameters under the second type of reference operating condition. The construction of these two models provides more accurate and comprehensive intermediate parameter support for battery life prediction.

[0086] The total charge throughput of a battery cell over its entire lifespan can be estimated by testing the cell's charge throughput at different cell temperatures and charge / discharge rates, and then equating it to the charge throughput under baseline conditions (1C, 25℃). The specific estimation method is as follows: 1) Conduct the following experiment: The first set of tests: The battery cell was cycled to SOH=80% under the baseline conditions of 1C charge / discharge rate and 25℃, and the charge throughput of the battery cell throughout its entire life cycle was recorded. .

[0087] The second set of tests: The battery cell was cycled at a charge / discharge rate of 0.75C and a cell temperature of 25℃ until SOH=80%, and the charge throughput of the battery cell throughout its entire life cycle was recorded. .

[0088] The third set of tests: The battery cell was cycled at a charge / discharge rate of 1.5C and a cell temperature of 25℃ until SOH=80%, and the charge throughput of the battery cell throughout its entire life cycle was recorded. .

[0089] The fourth group of tests: The battery cell was cycled at a charge / discharge rate of 1C and a cell temperature of 35℃ until SOH=80%, and the charge throughput of the battery cell throughout its entire life cycle was recorded. .

[0090] Fifth group of tests: The battery cell was cycled at a charge / discharge rate of 1C and a cell temperature of 45℃ until SOH=80%, and the charge throughput of the battery cell throughout its entire life cycle was recorded. .

[0091] 2) Define the equivalent charge parameter: Charge equivalent parameters The calculation formula is as follows:

[0092] In the formula, Indicates the charge / discharge rate. Indicates the cell temperature. This indicates the total charge throughput of the target battery cell throughout its entire lifecycle under current operating conditions.

[0093] 3) Interpolation calculation: Cell temperature interpolation: The amount of charge released at (35℃, 1C), (45℃, 1C), and (1C, 25℃) were measured respectively, and the equivalent charge parameters for each operating condition were calculated. For cell temperatures between 25℃ and 45℃, the following equation can be used for interpolation, and the specific fitting equation is as follows:

[0094] In the formula, Represents the molar gas constant. Indicates activation energy. The exponent is 298.15K, which represents room temperature.

[0095] Substituting the charge equivalent parameters for each operating condition into the above fitting equation, we can obtain the values ​​at 1C. and .

[0096] Charge / discharge rate interpolation: For Different charge / discharge rates The fitting method used is linear fitting, and the specific fitting equation is as follows:

[0097] In the formula, Indicates the charge / discharge rate. and For different fitting coefficients.

[0098] Will Substituting the equivalent charge parameters for different charge / discharge rates into the above fitting equation yields the following results. Down and .

[0099] In some embodiments, Figure 3 In order to improve the modeling accuracy of the first intermediate parameter acquisition model, the process also includes the following steps S03' and S03'' set between steps S03 and S04.

[0100] Step S03': Obtain the charge / discharge rate range corresponding to the first type of reference operating condition.

[0101] Step S03'': Within the charge / discharge rate range, expand the number of current first-type reference conditions based on the charge equivalent parameters corresponding to each first-type reference condition to obtain multiple new charge equivalent parameters corresponding to the first-type reference conditions, which are used to construct the first intermediate parameter acquisition model.

[0102] The extension method used in step S03'' includes, but is not limited to, linear fitting. Obtaining the charge / discharge rate range through step S03' clarifies the boundary conditions of the first type of reference operating condition, providing a precise parameter range for subsequent steps. In step S03'', the first type of reference operating condition is extended based on the obtained charge equivalent parameters, which not only increases the data volume of the reference operating condition but also improves the comprehensiveness and accuracy of the charge equivalent parameter acquisition model. This extension process ensures the applicability of the model under different charge / discharge rate conditions, providing more reliable parameter support for subsequent battery life prediction.

[0103] In some embodiments, in order to improve the modeling accuracy of the second intermediate parameter acquisition model, the process further includes steps S05' and S05'' set between steps S05 and S06.

[0104] Step S05': Obtain the cell temperature range corresponding to the second type of reference operating condition.

[0105] Step S05'': Within the cell temperature range, expand the number of current second-type reference conditions based on the charge equivalent parameters corresponding to each second-type reference condition to obtain multiple new charge equivalent parameters corresponding to the second-type reference conditions, which are used to construct the second intermediate parameter acquisition model.

[0106] The extension method used in step S05'' includes, but is not limited to, the Arrhenius equation. Obtaining the cell temperature range through step S05' clarifies the temperature boundary conditions of the second type of reference operating condition, providing a precise temperature parameter range for subsequent modeling steps. In step S05'', the second type of reference operating condition is extended using the obtained charge equivalent parameters, which not only increases the data scale of the reference operating condition but also further enhances the adaptability and accuracy of the charge equivalent parameter acquisition model under different temperature conditions. This extension method ensures that the model can cover a wider range of cell temperatures, providing a more comprehensive and reliable parameter basis for battery life prediction.

[0107] In some embodiments, to improve prediction accuracy, in step S30, the equivalent charge is configured as the product of the actual charge passing and the charge equivalence parameter. The charge equivalence parameter reflects the equivalent conversion relationship of charge under different operating conditions. By introducing this parameter, the actual charge passing can be converted into a charge equivalent to that under a baseline operating condition, thus facilitating unified comparison and analysis across different operating conditions. This conversion mode considers both the absolute value of the charge and the impact of different operating conditions on battery performance, providing more accurate and comprehensive data support for battery life prediction.

[0108] In some embodiments, to improve the accuracy of SOH prediction, step S40 is refined to include: inputting the equivalent charge into a pre-set cumulative charge acquisition model to acquire the cumulative charge. This cumulative charge acquisition model is configured to generate the cumulative charge based on historical cumulative charge data from previous cycles and the current equivalent charge in the current cycle, and the cumulative charge is positively correlated with both the historical cumulative charge data and the equivalent charge. The cumulative charge acquisition model comprehensively considers the cumulative effect of the equivalent charge at different usage stages of the battery, as well as the change pattern of the equivalent charge over time. During the calculation process, the model dynamically adjusts the accumulation coefficient based on the magnitude and trend of the equivalent charge, thereby accurately deriving the cumulative charge. This positive correlation ensures that the cumulative charge accurately reflects the charge accumulation of the battery during actual use, providing crucial data for accurate prediction of subsequent battery life.

[0109] As an exemplary implementation, the accumulated charge acquisition model can be represented as:

[0110] In the formula, Indicates the amount of accumulated charge. Indicates the first i The equivalent charge of the current operating condition in the next cycle. This represents the historical data of accumulated charge prior to the current cycle. Indicates the first i The charge equivalent parameters for the current operating condition in the next cycle.

[0111] In some embodiments, to make the State of Charge (SOH) intuitively reflect the degradation trend of battery performance, step S50 is refined to include: obtaining a first ratio of the cumulative charge of the target battery in the current cycle to the cumulative charge of the target battery under a baseline condition; generating the SOH of the target battery based on the first ratio data, wherein the SOH is linearly and negatively correlated with the first ratio data. This step, by introducing the cumulative charge under the baseline condition as a reference standard, can more accurately reflect the actual health status of the target battery in the current cycle. Given the linear negative correlation between SOH and the first ratio data, this indicates that when the cumulative charge of the target battery decreases compared to the baseline condition, its SOH will also decrease accordingly, thus intuitively showing the degradation trend of battery performance. This design not only improves the accuracy of SOH prediction but also provides a more scientific reference for battery maintenance and management.

[0112] In some embodiments, step S50 generates the target battery current value using the following formula. :

[0113] In the formula, Represents the fitting coefficient. This represents the total charge throughput of the target battery cell over its entire lifecycle under baseline operating conditions.

[0114] The formula compares the current accumulated charge of the target battery with the total charge throughput of the cell over its entire life cycle under benchmark conditions, and incorporates fitting coefficients. It can accurately calculate the current health status of the target battery. Fit coefficients. The introduction of this method allows the formula to adapt to the different characteristics of various battery types, further improving the accuracy and applicability of SOH prediction. This calculation method enables real-time monitoring of battery performance degradation, providing a strong basis for battery maintenance and replacement.

[0115] As an exemplary implementation, suppose a battery pack is ( , ) through charge ， This indicates the current charge / discharge rate for this cycle. This indicates the current cell temperature during this cycle.

[0116] Charge equivalent parameters Obtain it using the following formula:

[0117] Its equivalent charge at (1C, 25℃) for:

[0118] Charge at (1C, 25℃) for:

[0119] The method for calculating the SOH value of the target battery is as follows:

[0120] Figure 4 A flowchart illustrating another battery life prediction method provided for at least one embodiment of this disclosure. Figure 1 On the basis of, such as Figure 4 As shown, in order to predict the lifespan of the target battery based on the current operating conditions, the method further includes the following steps S60 and S70.

[0121] Step S60: Obtain the amount of charge that can be passed through the target battery throughout its entire life cycle based on the charge equivalent parameters, wherein the amount of charge that can be passed through the entire life cycle is negatively correlated with the charge equivalent parameters.

[0122] Step S70: The predicted number of cycles to generate the target battery based on the amount of charge that can be generated and the actual amount of charge that can be generated throughout the entire life cycle is used as a second prediction result to characterize the life of the target battery.

[0123] It should be noted that steps S60 and S70 can be set after step S20, and are parallel to steps S30-S50.

[0124] The charge transfer volume over the entire lifespan of the target battery characterizes the total charge transfer experienced by the battery from its newest state to failure. In step S70, using the charge transfer volume over the entire lifespan obtained in step S60, combined with the charge transfer volume of the battery in this cycle, the predicted cycle number of the target battery can be generated. This predicted cycle number is a key indicator, directly reflecting the remaining lifespan of the battery. Combining it with the first prediction result provides a more comprehensive and accurate basis for battery life assessment, helping users make more scientific and reasonable battery use and maintenance decisions.

[0125] In some embodiments, to accurately predict the cycle life of the target battery, step S60 is refined to include: obtaining the amount of charge that the target battery can carry throughout its entire life cycle under the current operating condition by using the ratio of the cell's total lifetime charge throughput under a baseline operating condition to the charge equivalent parameter. The charge equivalent parameter encompasses the charge loss characteristics of the cell under different usage conditions. By comparing it with the cell's total lifetime charge throughput under the baseline operating condition, the actual amount of charge that the target battery can carry throughout its entire life cycle under the current operating condition can be accurately calculated. This calculation method fully considers various influencing factors during actual use, making the prediction result closer to the battery's true state. Based on this calculation result, the remaining lifespan of the battery can be further evaluated, providing strong support for the rational use and replacement of the battery.

[0126] In some embodiments, to further accurately predict the cycle life of the target battery, step S70 is refined to include: obtaining a second ratio of the amount of charge that the target battery can carry throughout its entire lifespan under current operating conditions to the actual amount of charge carried in a single cycle; and generating a predicted cycle number for the target battery based on the second ratio data, wherein the predicted cycle number is linearly and positively correlated with the second ratio data. The second ratio data reflects the proportional relationship between the amount of charge that the target battery can carry throughout its entire lifespan under current operating conditions and the actual amount of charge carried in a single cycle. By establishing a linear model between this proportional relationship and the predicted cycle number, the cycle life of the battery under current operating conditions can be predicted more accurately. This model considers the charge carrying characteristics of the battery at different cycle stages, making the prediction results more reliable and practical. Based on the predicted cycle number, users can better plan the battery's usage cycle and prepare for battery replacement or maintenance in advance.

[0127] As an exemplary embodiment, assume that the operating condition of a battery pack is the first... i Each cycle at charge / discharge rate Cell temperature Through charge The method for predicting the number of battery pack cycles based on operating conditions includes the following: 1) Obtain the equivalent charge parameters using the following formula. : , In the formula, and These represent different fitting coefficients, where e represents a constant. Indicates the pre-exponential coefficient. Indicates activation energy. Represents the mole constant; 2) The amount of charge that can be transmitted throughout the entire life cycle of the target battery for: ; 3) Predicted cycle number of the target battery for: .

[0128] This scheme allows for the accurate calculation of the predicted cycle number of a target battery based on the previously obtained charge equivalence parameters and the amount of charge that can be carried over the battery's entire lifespan. This provides crucial data support for predicting battery life. In practical applications, these parameters can be obtained through fitting and analysis of a large amount of experimental data to ensure the accuracy and reliability of the prediction results.

[0129] Figure 5This is a structural block diagram of a battery life prediction system provided in at least one embodiment of the present disclosure. Figure 5 As shown, the battery life prediction system 10 includes an acquisition unit 11, a preprocessing unit 12, and a first prediction unit 13.

[0130] The acquisition unit 11 is configured to acquire the target battery's current actual operating parameters and actual charge amount in this cycle.

[0131] The preprocessing unit 12 is configured to determine the charge equivalent parameters of the target battery based on actual operating condition parameters, wherein the charge equivalent parameters are the ratio of the total life cycle charge throughput of the target battery cell under the reference operating condition to the total life cycle charge throughput of the target battery cell under the current operating condition corresponding to the actual operating condition parameters.

[0132] The first prediction unit 13 is configured to obtain the equivalent charge amount of the actual through charge amount under the reference operating condition based on the charge equivalent parameter, and to obtain the cumulative charge amount of the target battery based on the equivalent charge amount, and to generate the SOH of the target battery based on the cumulative charge amount as a first prediction result for characterizing the life of the target battery.

[0133] The specific execution methods of each unit in the above system embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0134] In some embodiments, the acquisition unit 11 can be implemented by a sensor, and the preprocessing unit 12 and the first prediction unit 13 can be implemented by a controller or control module with corresponding programs.

[0135] In some embodiments, Figure 5 Based on this, the battery life prediction system 10 further includes a second prediction unit 14, which is configured to obtain the amount of charge that can be passed through the target battery throughout its entire life cycle based on the charge equivalence parameter, wherein the amount of charge that can be passed through the target battery throughout its entire life cycle is negatively correlated with the charge equivalence parameter, and to generate the predicted number of cycles of the target battery based on the amount of charge that can be passed through the target battery throughout its entire life cycle and the actual amount of charge that can be passed through, as a second prediction result used to characterize the life of the target battery.

[0136] This disclosure also provides a storage medium storing a program or instructions that, when executed by a processor, implement the steps of the method embodiments described above.

[0137] This disclosure also provides a program product, such as... Figure 6 As shown, the program product includes one or more processors 21 and memory 22. Figure 6 Take a processor 21 as an example.

[0138] The controller may also include an input device 23 and an output device 24.

[0139] The processor 21, memory 22, input device 23, and output device 24 can be connected via a bus or other means. Figure 6 Taking the example of a connection between China and Israel via a bus.

[0140] The processor 21 can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips. The general-purpose processor can be a microprocessor or any conventional processor.

[0141] The memory 22, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 21 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions, and modules stored in the memory 22, thereby implementing the steps of the above-described method embodiments.

[0142] The memory 22 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the use of the processing device operated by the server. Furthermore, the memory 22 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 22 may optionally include memory remotely located relative to the processor 21, and these remote memories may be connected to a network connection device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0143] Input device 23 can receive input digital or character information, and generate key signal inputs related to driver settings and function control of the server's processing unit. Output device 24 may include display devices such as a display screen.

[0144] One or more modules are stored in memory 22, and when executed by one or more processors 21, they perform actions such as... Figure 1 The method shown.

[0145] Those skilled in the art will understand that all or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory (FM), hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0146] Although embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

[0147] Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for predicting battery life, characterized in that, include: Obtain the target battery's current actual operating parameters and actual charge amount in this cycle; The charge equivalent parameters of the target battery are determined based on the actual operating condition parameters, wherein the charge equivalent parameters are the ratio of the total life cycle charge throughput of the target battery cell under the reference operating condition to the total life cycle charge throughput of the target battery cell under the current operating condition corresponding to the actual operating condition parameters. The actual amount of charge passing through is obtained based on the charge equivalence parameters, which is equivalent to the amount of charge under the reference operating condition. The cumulative charge of the target battery is obtained based on the equivalent charge; and, The current state of charge (SOH) of the target battery is generated based on the accumulated charge, serving as a first prediction result for characterizing the target battery's lifetime.

2. The method according to claim 1, characterized in that, Also includes: Based on the charge equivalent parameters, the total charge that the target battery can carry over its entire lifespan under the current operating conditions is obtained, wherein the total charge that can carry over its entire lifespan is negatively correlated with the charge equivalent parameters; and... The predicted cycle number of the target battery is generated based on the amount of charge that can be generated during the entire life cycle and the actual amount of charge that can be generated, and is used as a second prediction result to characterize the life of the target battery.

3. The method according to claim 1 or 2, characterized in that, The actual operating condition parameters include charge / discharge rate and cell temperature, and determining the charge equivalent parameters of the target battery based on the actual operating condition parameters includes: A first intermediate parameter acquisition model matching the cell temperature is obtained, wherein the first intermediate parameter acquisition model is configured to generate the first intermediate parameter based on the input charge / discharge rate, and different first intermediate parameter acquisition models are used for different cell temperatures. Input the charge / discharge rate into the first intermediate parameter acquisition model to obtain the first intermediate parameter; A second intermediate parameter acquisition model matching the charge / discharge rate is obtained, wherein the second intermediate parameter acquisition model is configured to generate the second intermediate parameter based on the input cell temperature, and different second intermediate parameter acquisition models are used for different charge / discharge rate matching. The cell temperature is input into the second intermediate parameter acquisition model to obtain the second intermediate parameter; and... The charge equivalent parameter is obtained based on the first intermediate parameter and the second intermediate parameter, wherein the charge equivalent parameter is configured to be related to and positively correlated with both the first intermediate parameter and the second intermediate parameter.

4. The method according to claim 3, characterized in that, The first intermediate parameter has a linear relationship with the charge / discharge rate, the second intermediate parameter has a non-linear relationship with the cell temperature, and the charge equivalent parameter is the product of the first intermediate parameter and the second intermediate parameter.

5. The method according to claim 3, characterized in that, The total lifetime charge throughput is configured as the charge throughput of the target battery when it cycles to a set state of equilibrium (SOH). Furthermore, the method further includes a process of constructing the first intermediate parameter acquisition model and the second intermediate parameter acquisition model, the process comprising: Determine the baseline operating conditions; The actual operating parameters and cell charge throughput over the entire life cycle of the target battery are obtained under the benchmark operating condition and at least two first-type reference operating conditions and at least two second-type reference operating conditions other than the benchmark operating condition. The charge and discharge rates of each first-type reference operating condition are different but the cell temperature is the same, and the cell temperature of each second-type reference operating condition is different but the charge and discharge rates are the same. For each of the first type of reference operating conditions, the ratio of the total life cycle charge throughput of the target battery cell under the benchmark operating condition to the total life cycle charge throughput of the target battery cell under the first type of reference operating condition is obtained, and used as the charge equivalent parameter corresponding to the first type of reference operating condition. The first intermediate parameter acquisition model is constructed based on the actual operating parameters and charge equivalent parameters corresponding to each of the first type of reference operating conditions. For each of the second type of reference operating conditions, the ratio of the total life cycle charge throughput of the target battery cell under the baseline operating condition to the total life cycle charge throughput of the target battery cell under the second type of reference operating condition is obtained, and used as the charge equivalent parameter corresponding to the second type of reference operating condition; The second intermediate parameter acquisition model is constructed based on the actual operating parameters and charge equivalent parameters corresponding to each of the second type of reference operating conditions.

6. The method according to claim 5, characterized in that, The process also includes: Obtain the charge / discharge rate range corresponding to the first type of reference operating condition; Within the charge / discharge rate range, the number of current first-type reference conditions is expanded based on the charge equivalent parameters corresponding to each of the first-type reference conditions to obtain multiple new charge equivalent parameters corresponding to the first-type reference conditions, which are used to construct the first intermediate parameter acquisition model. Obtain the cell temperature range corresponding to the second type of reference operating condition; and, Within the cell temperature range, the number of current second-type reference operating conditions is expanded based on the charge equivalent parameters corresponding to each of the second-type reference operating conditions to obtain multiple new charge equivalent parameters corresponding to the second-type reference operating conditions, which are used to construct the second intermediate parameter acquisition model.

7. The method according to claim 1 or 2, characterized in that, The equivalent charge is the product of the actual passing charge and the equivalent charge parameter; and, The step of obtaining the cumulative charge of the target battery based on the equivalent charge includes: inputting the equivalent charge into a pre-set cumulative charge acquisition model to obtain the cumulative charge, wherein the cumulative charge acquisition model is configured to generate the cumulative charge based on historical cumulative charge data before the current cycle and the current equivalent charge in the current cycle, and the cumulative charge is positively correlated with both the historical cumulative charge data and the equivalent charge.

8. The method according to claim 2, characterized in that, The step of generating the current SOH of the target battery based on the accumulated charge includes: obtaining a first ratio of the accumulated charge of the target battery in the current cycle to the accumulated charge of the target battery under the reference condition, and generating the current SOH of the target battery based on the first ratio data, wherein the current SOH of the target battery is linearly related to and negatively correlated with the first ratio data; The step of generating the predicted cycle number of the target battery based on the amount of charge that can be passed over the entire life cycle and the actual amount of charge that can be passed over the entire life cycle includes: obtaining a second ratio data of the amount of charge that can be passed over the entire life cycle and the actual amount of charge that can be passed over the target battery in one cycle, and generating the predicted cycle number of the target battery based on the second ratio data, wherein the predicted cycle number is linearly related to the second ratio data and is positively correlated.

9. A battery life prediction system, characterized in that, include: The acquisition unit is configured to acquire the target battery's current actual operating parameters and actual charge amount in this cycle. The preprocessing unit is configured to determine the charge equivalent parameters of the target battery based on the actual operating condition parameters, wherein the charge equivalent parameters are the ratio of the total life-cycle charge throughput of the target battery under the reference operating condition to the total life-cycle charge throughput of the target battery under the current operating condition corresponding to the actual operating condition parameters. as well as, The first prediction unit is configured to obtain the equivalent charge amount of the actual through charge under the reference operating condition based on the charge equivalence parameter, and to obtain the cumulative charge amount of the target battery based on the equivalent charge amount, and to generate the current SOH of the target battery based on the cumulative charge amount as a first prediction result for characterizing the lifespan of the target battery.

10. A storage medium, characterized in that, The storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 8.

Images