Battery status evaluation method, device, equipment and storage medium

By obtaining the rated and historical discharge information of the battery pack in the energy storage facility, combined with the battery life evaluation model, the battery health status evaluation under actual operating conditions is realized, and the problems of inaccurate evaluation and high accuracy requirements in the existing technology are solved. Improves the accuracy of battery health status assessment.

CN117420468BActive Publication Date: 2024-11-08GUANGDONG POWER GRID CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311486909.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-08
Publication Date
2024-11-08
Estimated Expiration
2043-11-08

AI Technical Summary

Technical Problem

The existing battery status evaluation methods are difficult to accurately evaluate the battery health status under actual operating conditions, and have high requirements for the accuracy of the measurement instrument, which has problems such as non-invasiveness and laboratory environment dependence.

Method used

By obtaining the rated discharge information and historical actual discharge information of the battery pack in the energy storage facility, the battery parameter measurement is performed using a non-invasive method, and combining the pre-constructed battery life evaluation model, the service life prediction value of the battery pack is calculated to evaluate battery health state.

Benefits of technology

Under actual working conditions, the accurate evaluation of the battery health status is achieved, the requirements for the accuracy of the measurement instrument are reduced, the accuracy of the battery health status assessment is improved, and it is suitable for practical applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117420468B_ABST
    Figure CN117420468B_ABST
Patent Text Reader

Abstract

The embodiments of the present invention disclose a battery status assessment method, device, equipment and storage medium. The method includes: obtaining the rated discharge information of the battery pack configured in the energy storage facility and the historical actual discharge information corresponding to the battery pack under the historical discharge event; determining the battery status assessment result corresponding to the battery pack at the set assessment time according to the rated discharge information and the historical actual discharge information. This technical solution can evaluate the battery health status under actual working conditions, does not require high precision for the measuring instrument, and uses non-invasive measurement of battery parameters, which is beneficial to the subsequent operation of the battery and improves the accuracy of the battery health status assessment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of battery management technology, and in particular to a battery status evaluation method, device, equipment and storage medium. Background Art

[0002] With the rise of renewable energy generation in power systems, the penetration rate of renewable energy generation is rising steadily, and the volatility and uncertain behavior of its output bring challenges to the stable operation of power systems. At present, many stabilization strategies for renewable energy generation often require energy storage facilities to implement, and the widespread use of batteries in energy storage facilities can solve the problem of renewable energy volatility.

[0003] However, in long-term operation, the operating status of the battery pack in the energy storage facility affects the operational stability of the energy storage facility, so it is necessary to evaluate the health of the operating status of the battery pack in the energy storage facility in advance to reduce the impact of the battery pack's own status on the stability of the energy storage facility.

[0004] Current battery status assessment methods, such as electrochemical analysis, may be destructive and invasive and are not suitable for status assessment during battery operation. Another example is the ampere-hour method, which requires the battery status to be assessed in a laboratory environment. However, the laboratory environment is quite different from the actual operating environment of the battery, which affects the assessment results. Another example is the impedance method, which has high requirements on the accuracy of the measurement tools used in operating status assessment, and therefore also has limitations. Summary of the invention

[0005] The present invention provides a battery status assessment method, device, equipment and storage medium, which can assess the battery health status under actual working conditions, does not require high precision of the measuring instrument, and adopts non-invasive measurement of battery parameters, which is beneficial to the subsequent operation of the battery and improves the accuracy of the battery health status assessment.

[0006] According to one aspect of the present invention, a battery status evaluation method is provided, comprising:

[0007] Obtaining rated discharge information of battery packs configured in the energy storage facility and historical actual discharge information corresponding to the battery packs under historical discharge events;

[0008] A battery state evaluation result corresponding to the battery pack at a set evaluation time is determined according to the rated discharge information and the historical actual discharge information.

[0009] Optionally, determining a battery status evaluation result corresponding to the battery pack at a set evaluation time according to the rated discharge information and the historical actual discharge information includes:

[0010] Determine, according to the rated discharge information and the historical actual discharge information, the historical battery service life corresponding to the battery pack at different historical detection moments;

[0011] Obtaining a predetermined target battery life assessment model and determining model input data from the historical battery life;

[0012] The model input data is input into the target battery life evaluation model to obtain a predicted service life value of the battery pack at a set evaluation time, and the predicted service life value is used as a battery state evaluation result.

[0013] Optionally, determining the historical battery service life of the battery pack corresponding to different historical detection moments according to the rated discharge information and the historical actual discharge information includes:

[0014] Determining a total effective throughput of the battery pack according to the rated discharge information;

[0015] For each historical detection moment, determine the battery historical operation cycle to which the historical detection moment belongs, and determine the target historical discharge event included in the battery historical operation cycle;

[0016] Determine the effective ampere-hours of the battery pack under the target historical discharge event according to the target historical actual discharge information corresponding to each target historical discharge event;

[0017] The historical battery service life of the battery pack corresponding to the historical detection time is determined according to the total effective throughput and each of the effective ampere hours.

[0018] Optionally, determining the total effective throughput of the battery pack according to the rated discharge information includes:

[0019] Extracting the rated discharge depth, the rated discharge capacity at the rated discharge current, and the number of discharge cycles at the rated discharge depth and the rated discharge current included in the rated discharge information;

[0020] The product value of the rated depth of discharge, the rated discharge capacity and the number of discharge cycles is determined as the total effective throughput of the battery pack.

[0021] Optionally, determining the effective ampere-hours of the battery pack under the target historical discharge event according to the target historical actual discharge information corresponding to each target historical discharge event includes:

[0022] For each target historical discharge event, extract the actual discharge depth, the actual discharge capacity, and the actual ampere hours under the actual discharge current from the corresponding target historical actual discharge information;

[0023] Determine a first ratio of the actual discharge depth to the rated discharge depth in the rated discharge information, and determine a second ratio of the actual discharge capacity to the rated discharge capacity in the rated discharge information;

[0024] Substituting the first ratio, the second ratio and the actual ampere-hours into a set relationship equation, the effective ampere-hours under the target historical discharge event are obtained.

[0025] Optionally, the method for determining the target battery life assessment model includes:

[0026] Acquire a pre-built initial battery life assessment model, wherein the initial battery life assessment model includes a model order to be determined and a model parameter to be identified;

[0027] The battery life is used as the model training baseline, and a set number of historical battery lifespans are selected as model training samples;

[0028] Determine a relationship according to the model training sample and a given model order to determine the model order;

[0029] Determining the model parameters according to the autocorrelation function and constraints constructed relative to the model training baseline, in combination with a given recursive algorithm and the model training samples;

[0030] The determined model order and model parameters are substituted into the initial battery life assessment model to obtain the target battery life assessment model.

[0031] Optionally, determining the model input data from the historical battery service life includes:

[0032] Determining a target historical detection time included in the target battery life evaluation model according to the set evaluation time;

[0033] The historical battery life corresponding to each of the target historical detection moments is determined as model input data.

[0034] According to another aspect of the present invention, there is provided a battery status evaluation device, comprising:

[0035] An information acquisition module, used to acquire rated discharge information of a battery pack configured in an energy storage facility and historical actual discharge information corresponding to the battery pack under historical discharge events;

[0036] The evaluation result determination module is used to determine the battery state evaluation result corresponding to the battery pack at the set evaluation time according to the rated discharge information and the historical actual discharge information.

[0037] According to another aspect of the present invention, there is provided an electronic device, comprising:

[0038] one or more processors;

[0039] a storage device for storing one or more programs,

[0040] When the one or more programs are executed by the one or more processors, the one or more processors implement the battery status evaluation method described in any embodiment of the present invention.

[0041] According to another aspect of the present invention, a storage medium containing computer executable instructions is provided. When the computer executable instructions are executed by a computer processor, the battery status evaluation method described in any embodiment of the present invention is executed.

[0042] The technical solution of the embodiment of the present invention obtains the rated discharge information of the battery pack configured in the energy storage facility and the historical actual discharge information corresponding to the battery pack under the historical discharge event; according to the rated discharge information and the historical actual discharge information, the battery status evaluation result corresponding to the battery pack at the set evaluation time is determined. This technical solution can evaluate the battery health status under actual working conditions, does not require high precision of the measuring instrument, and uses non-invasive measurement of battery parameters, which is beneficial to the subsequent operation of the battery and improves the accuracy of the battery health status evaluation.

[0043] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 is a flow chart of a battery status evaluation method provided according to Embodiment 1 of the present invention;

[0046] Figure 2 is a flow chart of a battery status evaluation method provided according to Embodiment 2 of the present invention;

[0047] Figure 3 is a flow chart of a battery status evaluation method provided according to Embodiment 3 of the present invention;

[0048] Figure 4 is an example diagram of a relationship curve between the AIC value and the model order at different discharge times provided in the third embodiment of the present invention;

[0049] Figure 5 is an example diagram of a relationship curve between the AIC value and the model order at different rated powers provided by the third embodiment of the present invention;

[0050] Figure 6 is an example diagram of a process for identifying parameters of an initial battery life assessment model provided in Embodiment 3 of the present invention;

[0051] Figure 7 is a schematic diagram of the structure of a battery status assessment device provided according to a fourth embodiment of the present invention;

[0052] Figure 8 It is a structural schematic diagram of an electronic device provided according to Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0054] It should be noted that the terms "first", "second" and "target" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including", "having" and "etc." and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0055] Embodiment 1

[0056] Figure 1This is a flow chart of a battery status evaluation method provided according to the first embodiment of the present invention. This embodiment is applicable to the situation where the health status of a battery pack in an energy storage facility is evaluated. The method can be performed by a battery status evaluation device. The battery status evaluation device can be implemented in the form of hardware and / or software. The battery status evaluation device can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0057] S110: Acquire rated discharge information of battery packs configured in the energy storage facility and historical actual discharge information of the battery packs corresponding to historical discharge events.

[0058] Among them, the battery pack can be understood as a battery pack configured based on actual needs in the energy storage facility. The battery pack may include multiple batteries. Exemplarily, the battery pack in this embodiment may be a storage battery pack. The rated discharge information in this embodiment may be the rated information configured in the energy storage facility. Specifically, the rated discharge information may include information such as the rated discharge depth of the battery pack, the rated discharge capacity at the rated discharge current, and the number of discharge cycles at the rated discharge depth and rated discharge current. Historical discharge events can be understood as events in which the battery pack was discharged in the past. When the energy storage facility in this embodiment is running, multiple discharge events may occur in the battery pack. Historical actual discharge information may include information such as the actual discharge depth, the actual discharge capacity, and the actual ampere-hours at the actual discharge current.

[0059] The historical actual discharge information in this embodiment can be obtained through sensor collection. In this embodiment, the rated discharge depth, rated discharge capacity at rated discharge current, and discharge cycle number at rated discharge depth and rated discharge current of the battery pack configured in the energy storage facility can be obtained, as well as the actual discharge depth, actual discharge capacity, actual ampere hours at actual discharge current corresponding to the battery pack under historical discharge events.

[0060] S120: Determine a battery status evaluation result corresponding to the battery pack at a set evaluation time according to the rated discharge information and the historical actual discharge information.

[0061] The evaluation time can be set according to actual needs. The battery status evaluation result can be understood as the predicted value of the service life of the battery pack. In this embodiment, the predicted value of the service life of the battery pack corresponding to the set evaluation time can be evaluated by a set battery life evaluation model based on the rated discharge information and historical actual discharge information of the battery pack.

[0062] In this embodiment, optionally, a battery status evaluation result corresponding to the battery pack at a set evaluation time is determined based on the rated discharge information and the historical actual discharge information, including: determining the historical battery service life of the battery pack at different historical detection times based on the rated discharge information and the historical actual discharge information; obtaining a predetermined target battery life evaluation model, and determining model input data from the historical battery service life; inputting the model input data into the battery life evaluation model to obtain the service life prediction value corresponding to the battery pack at the set evaluation time, and using it as the battery status evaluation result.

[0063] Among them, the historical detection moment can be a pre-set moment or a periodically set detection moment. The historical service life can be understood as the life of the battery during use. In this embodiment, the historical battery service life corresponding to different historical detection moments is different. The battery service life in this embodiment can be characterized by a battery health factor. The historical service life in this embodiment can be calculated according to the rated discharge information of the battery pack and the historical actual discharge information through the corresponding calculation formula to obtain the historical battery service life corresponding to the battery pack at different historical detection moments.

[0064] In this embodiment, the main factors affecting the battery life may include discharge depth, discharge rate, charge and discharge times, etc. Each discharge process of the battery will cause irreversible loss of battery life until the battery life ends.

[0065] The target battery life evaluation model may be a predetermined evaluation model that can be used to evaluate the battery life. The model input data may be data selected from the historical service life of the battery pack. In this embodiment, the model input data determined from the historical battery service life may be input into the acquired predetermined target battery life evaluation model, and a predicted value of the service life of the battery pack corresponding to the set evaluation time may be obtained, and the predicted value of the service life may be used as the battery status evaluation result.

[0066] Through such a setting in this embodiment, the historical battery service life can be input into a predetermined target battery life evaluation model to output the predicted value of the battery service life corresponding to the battery pack at the set evaluation time. This can be suitable for actual working conditions and does not require high precision for the measuring instrument. It can not only evaluate the current health status of the battery, but also predict the battery life, so that the operating status of the battery pack in the energy storage facility can be reasonably arranged.

[0067] The technical solution of the embodiment of the present invention obtains the rated discharge information of the battery pack configured in the energy storage facility and the historical actual discharge information corresponding to the battery pack under the historical discharge event; according to the rated discharge information and the historical actual discharge information, the battery status evaluation result corresponding to the battery pack at the set evaluation time is determined. This technical solution can evaluate the battery health status under actual working conditions, does not require high precision of the measuring instrument, and uses non-invasive measurement of battery parameters, which is beneficial to the subsequent operation of the battery and improves the accuracy of the battery health status evaluation.

[0068] Embodiment 2

[0069] Figure 2 It is a flow chart of a battery status evaluation method provided according to the second embodiment of the present invention, and this embodiment is optimized based on the above embodiment. The specific optimization is: according to the rated discharge information and the historical actual discharge information, the historical battery service life corresponding to the battery pack at different historical detection moments is determined, including: according to the rated discharge information, the total effective throughput of the battery pack is determined; for each historical detection moment, the historical operation cycle of the battery to which the historical detection moment belongs is determined, and the target historical discharge events included in the historical operation cycle of the battery are determined; according to the target historical actual discharge information corresponding to each target historical discharge event, the effective ampere-hours of the battery pack under the target historical discharge event are determined; according to the total effective throughput and each effective ampere-hour, the historical battery service life corresponding to the battery pack at the historical detection moment is determined. Figure 2 As shown, the method includes:

[0070] S210: Obtain rated discharge information of battery packs configured in the energy storage facility and historical actual discharge information corresponding to historical discharge events of the battery packs.

[0071] S220: Determine the total effective throughput of the battery pack according to the rated discharge information.

[0072] The effective throughput may be the electric energy released by the battery at the rated discharge rate and rated discharge depth, and its unit is ampere-hour. The total effective throughput may be understood as the sum of the effective throughputs of each battery in the battery pack. In this embodiment, the total effective throughput of the battery pack may be determined by calculation using the rated discharge information.

[0073] In this embodiment, optionally, the total effective throughput of the battery pack is determined based on the rated discharge information, including: extracting the rated discharge depth included in the rated discharge information, the rated discharge capacity under the rated discharge current, and the number of discharge cycles at the rated discharge depth and the rated discharge current; and determining the product value of the rated discharge depth, the rated discharge capacity and the number of discharge cycles as the total effective throughput of the battery pack.

[0074] In this embodiment, the rated discharge information may include the rated discharge depth, the rated discharge capacity at the rated discharge current, and the number of discharge cycles at the rated discharge depth and the rated discharge current. The extracted rated discharge depth, rated discharge capacity, and number of discharge cycles are multiplied together, and the product value obtained may be determined as the total effective throughput of the battery pack.

[0075] Specifically, the total effective throughput expression can be as follows:

[0076] τ R =N R D R C R

[0077] Among them, τ R is the total effective throughput, N R is the number of cycles at rated discharge depth and rated discharge current; D R is the rated discharge depth; C R It is the rated capacity at the rated discharge current (in Ah).

[0078] In this embodiment, through such a setting, the total effective throughput of the battery pack can be determined by calculation according to the rated discharge information, which is convenient for subsequent determination of the historical service life of the battery.

[0079] S230: For each historical detection moment, determine the battery historical operation cycle to which the historical detection moment belongs, and determine the target historical discharge events included in the battery historical operation cycle.

[0080] Among them, the historical detection moment can be a specific detection time point. The battery historical operation cycle can be understood as a set battery operation cycle. The historical detection moment in this embodiment can be a detection moment set by a technician, or it can be a periodically set moment, or an irregular moment, and the historical detection moment can be determined according to demand. The battery historical operation cycle in this embodiment can be set according to actual needs, and this embodiment is not limited to this. In this embodiment, the battery historical operation cycle may include multiple historical detection moments. The battery historical operation cycle in this embodiment may include multiple battery discharge events. The target historical discharge event can be understood as a historical discharge event that occurred in the battery pack during the operation cycle.

[0081] In this embodiment, when the energy storage facility is in operation, the battery pack will have multiple discharge events. The historical operation cycle to which the historical detection moment belongs can be determined according to each set historical detection moment, and the historical discharge events of the battery in the historical operation cycle can be used as the target historical discharge events.

[0082] S240: Determine the effective ampere-hours of the battery pack under the target historical discharge event according to the target historical actual discharge information corresponding to each target historical discharge event.

[0083] The target historical actual discharge information may be the actual discharge information corresponding to the target historical discharge event determined at each historical detection moment. Specifically, the target historical actual discharge information may include information such as actual discharge depth, actual discharge capacity, and actual ampere-hours under actual discharge current. The effective ampere-hours may be calculated by setting a relationship through the discharge event of the battery pack.

[0084] In this embodiment, according to the actual discharge depth, actual discharge capacity and actual ampere-hour information under the actual discharge current corresponding to each target historical discharge event, the actual discharge depth, actual discharge capacity and actual ampere-hour information under the actual discharge current can be calculated by setting a relationship to obtain the effective ampere-hours under the target historical discharge event.

[0085] In this embodiment, optionally, the effective ampere-hours of the battery pack under the target historical discharge event are determined based on the target historical actual discharge information corresponding to each target historical discharge event, including: for each target historical discharge event, extracting the actual discharge depth, the actual discharge capacity, and the actual ampere-hours under the actual discharge current from the corresponding target historical actual discharge information; determining a first ratio of the actual discharge depth to the rated discharge depth in the rated discharge information, and determining a second ratio of the actual discharge capacity to the rated discharge capacity in the rated discharge information; substituting the first ratio, the second ratio, and the actual ampere-hours into a set relationship to obtain the effective ampere-hours under the target historical discharge event.

[0086] The first ratio may be a ratio of an actual discharge depth to a rated discharge depth. The second ratio may be a ratio of an actual discharge capacity to a rated discharge capacity. The set relationship may be a pre-set relationship.

[0087] It is understandable that the target actual discharge information corresponding to each target historical discharge time is different. In this embodiment, for each target historical discharge event, the actual discharge depth, the actual discharge capacity, and the actual ampere hours under the actual discharge current can be extracted from the target historical time discharge information corresponding to the target historical discharge time. By taking the ratio of the actual discharge depth to the rated discharge depth in the rated discharge information as the first ratio, and taking the ratio of the actual discharge capacity in the actual discharge information to the rated discharge capacity in the rated discharge information as the second ratio, and then substituting the first ratio, the second ratio, and the actual hours into the set relationship, the effective ampere hours under the target historical discharge event can be calculated.

[0088] Specifically, the setting relationship in this embodiment may be as follows:

[0089]

[0090] Among them, D ef Can be the effective ampere hours, D A is the actual discharge depth; D R is the rated discharge depth; d act is the ampere-hours under the actual discharge current (in Ah); u0 and u1 are fitting parameters, which can be obtained by fitting the relationship curve between discharge depth and failure cycle number provided by the manufacturer; C A is the actual discharge capacity (in Ah); C R It is the rated capacity at rated discharge current.

[0091] Through such a setting in this embodiment, the effective ampere-hours can be calculated based on the actual discharge information and the rated discharge information corresponding to the target historical discharge event by setting a relationship, so that the battery life obtained based on the effective ampere-hours is more accurate and reliable.

[0092] S250: Determine the historical battery service life of the battery pack at the historical detection time according to the total effective throughput and each effective ampere-hour.

[0093] In this embodiment, the historical battery service life of the battery pack at each historical detection moment can be calculated by setting a logical relationship based on the total effective throughput of the battery pack and the effective ampere-hours of the battery pack under the target historical discharge event.

[0094] Specifically, combining the set relationship of effective ampere hours and the total effective throughput expression, if the operation cycle T contains n discharge events, the historical battery life in actual use can be determined as follows:

[0095]

[0096] Where: Y is the historical battery life of the battery pack (in years); τ ef It is the effective ampere-hours of the battery pack during the operating cycle T.

[0097] S260: Obtain a predetermined target battery life assessment model, and determine model input data from historical battery service life.

[0098] In this embodiment, optionally, model input data is determined from historical battery life, including: determining the target historical detection moments included in the target battery life evaluation model according to the set evaluation moment; and determining the historical battery life corresponding to each target historical detection moment as the model input data.

[0099] The set evaluation time may be a set time for evaluation. The target detection time may be determined by the set evaluation time. There may be multiple target detection times. The target historical detection time may be related to the order of the target battery life evaluation model. Specifically, the set evaluation time may be n, and the target historical detection time determined according to the set evaluation time may be three target times: n-1, n-2, and n-3.

[0100] In this embodiment, the target historical detection time included in the target battery life evaluation model can be determined according to the set evaluation time, and the historical battery service life corresponding to each target historical detection time is used as the input data of the target battery life evaluation model. In this embodiment, through such a setting, the input data of the target battery life evaluation model can be determined based on the set evaluation time, making the evaluated battery life more accurate and more convenient.

[0101] S270: Input the model input data into the target battery life assessment model to obtain a predicted service life value of the battery pack at the set assessment time, and use it as a battery status assessment result.

[0102] The technical solution of the embodiment of the present invention obtains the rated discharge information of the battery pack configured in the energy storage facility and the historical actual discharge information corresponding to the battery pack under the historical discharge event; determines the total effective throughput of the battery pack according to the rated discharge information; determines the battery historical operation cycle to which the historical detection moment belongs for each historical detection moment, and determines the target historical discharge event included in the battery historical operation cycle; determines the effective ampere-hours of the battery pack under the target historical discharge event according to the target historical actual discharge information corresponding to each target historical discharge event; determines the historical battery service life corresponding to the battery pack at the historical detection moment according to the total effective throughput and each effective ampere-hour; obtains a predetermined target battery life evaluation model, and determines the model input data from the historical battery service life; inputs the model input data into the target battery life evaluation model, obtains the service life prediction value corresponding to the set evaluation moment of the battery pack, and uses it as the battery status evaluation result. This technical solution can evaluate the battery health status under actual working conditions, does not require high precision for the measuring instrument, and uses non-invasive measurement of battery parameters, which is beneficial to the subsequent operation of the battery and improves the accuracy of the battery health status evaluation.

[0103] Embodiment 3

[0104] Figure 3 It is a flow chart of a battery status assessment method provided according to the third embodiment of the present invention, and this embodiment is optimized based on the above embodiment. The specific optimization is as follows: the method for determining the target battery life assessment model includes: obtaining a pre-constructed initial battery life assessment model, the initial battery life assessment model includes a model order to be determined and model parameters to be identified; using the battery life as a model training baseline, and selecting a set number of historical battery life as model training samples; determining the model order according to the model training samples and the given model order; determining the model parameters according to the autocorrelation function and constraints constructed relative to the model training baseline, combined with the given recursive algorithm and model training samples; substituting the determined model order and model parameters into the initial battery life assessment model to obtain the target battery life assessment model. Figure 3 As shown, the method includes:

[0105] S310: Acquire a pre-built initial battery life assessment model, where the initial battery life assessment model includes a model order to be determined and model parameters to be identified.

[0106] Among them, the initial battery life evaluation model can be an evaluation model built based on the battery service life. The initial battery life evaluation model in this embodiment can be an autoregressive battery life model. The model order can be understood as the specific order of the model. In this embodiment, the model order can be determined by commonly used setting criteria. The setting criteria can be commonly used criteria such as the final prediction error criterion (Final Prediction Error Criterian, FPE), the variance homogeneity test criterion (F-test, F) and the Akaike information criterion (AIC), etc. The model parameters to be identified can be determined by the selected model training samples and the recursive algorithm. In this embodiment, the optimal model order and model parameters can be obtained by training with model training samples and setting algorithms.

[0107] Furthermore, since the degree of fit of the battery life assessment model in this embodiment to the measured baseline data is usually determined by the likelihood function, the larger the likelihood function value, the more accurate the model's description of the data; on the other hand, the computational complexity of the model. Since this model predicts battery life data for real-time transmission alignment, the fewer model parameters the better while improving the model's ability to describe the data.

[0108] Specifically, in this embodiment, the battery life at the current evaluation moment is associated with the battery life at several historical moments. The battery SOH can be measured and evaluated using sensors, and then the discrete strain data is converted into baseline data through the modal reconstruction method. Based on this, the service life X(n) at the time to be estimated can be obtained using the initial battery life evaluation model, and its initial battery life evaluation model expression can be:

[0109]

[0110] Where X(n) represents the predicted x(n), x(n) is the actual measured reference value of the battery life evaluation model at the evaluation time n, and a i is the parameter to be identified in the battery life evaluation model, p represents the model order to be determined in the battery life evaluation model, and e n To satisfy E(e n )=0 and The white noise sequence is , where Q is the white noise variance. This formula reflects the influence relationship between flexible baselines, and the baseline is reasonably predicted based on the autocorrelation of the data before and after the baseline.

[0111] This embodiment can obtain a pre-built initial battery life assessment model including a model order to be determined and model parameters to be identified.

[0112] S320: Use the battery life as a model training baseline, and select a set number of historical battery life as model training samples.

[0113] The model training baseline may be the battery life. The set number may be a set number, which may be set based on actual needs. Exemplarily, the set number may be 50. The model training samples may be used to train the initial battery life assessment model. In this embodiment, the battery life may be used as the model training baseline, and 50 historical battery lifespans may be selected as model training samples.

[0114] S330, determining a relationship according to the model training sample and a given model order, and determining the model order.

[0115] The model order determination relationship may be a set relationship for determining the model order. Exemplarily, in this embodiment, the AIC criterion may be used as a given model order determination relationship. In this embodiment, the model order may be trained and calculated based on the model training sample and the given model order determination relationship to obtain the best model order.

[0116] Specifically, in this embodiment, since the AIC criterion is applicable to the case of less sample data, the premise of the battery life assessment model to predict the battery life is to use the historical battery life data to determine the model parameters to be identified, so initialization time is required, and the initialization time depends on the length of the sample data used to determine the model parameters, so the sample data is generally not too much. Adding free parameters improves the goodness of fitting. While encouraging the goodness of data fitting, the AIC criterion tries to avoid overfitting, so the model that is given priority should satisfy the minimum value of AIC.

[0117] Therefore, the relationship between the model order given by the AIC criterion is as follows:

[0118] AIC(p)=Nlnσ 2 +2p

[0119]

[0120] Where N is the length of the model baseline data sequence, and S is the residual sum of squares of the baseline data used for modeling.

[0121] In this embodiment, the relationship and the selected model training samples can be determined according to the given model order, the effect of the model order under different dimensional conditions can be observed, and the most appropriate model order can be selected.

[0122] Exemplarily, the relationship between the AIC value and the model order at different discharge times and the relationship between the AIC value and the model order at different discharge powers can be obtained through training samples to determine the optimal model order. In this embodiment, 50 historical battery service lives can be preliminarily selected as model training samples to determine the model order to be determined and the model parameters to be identified. The historical battery service life data between the battery's factory state and the two measuring points where the battery actually runs for 180 days can be selected. Battery service life data when the battery discharge time is 10 minutes, 20 minutes, and 30 minutes respectively can be selected, and the order can be determined using the AIC criterion. Among them, an example curve of the relationship between the AIC value and the model order at different discharge times is shown in the figure below. Figure 4 shown. Figure 4 The three lines A, B and C represent the battery discharge time of 10 minutes, 20 minutes and 30 minutes respectively. Figure 4 It can be seen that the decrease rate of the AIC value slows down when the model order is 3rd, 5th and 19th, and the change trend is consistent under various discharge time conditions. Therefore, different discharge times have little effect on the model order.

[0123] In this embodiment, according to the AIC criterion, the model order calculated when AIC takes the minimum value is the optimal value. Table 1 below lists the time consumption corresponding to different model orders. It can be seen from Table 1 that the larger the model order, the longer the time consumption.

[0124] Table 1

[0125]

[0126] Furthermore, the battery life data when the battery discharge power is 2 times, 3 times and 4 times the rated power are selected, and the order is determined using the AIC criterion. The relationship curve between the AIC value and the model order at different rated powers is shown in the figure below: Figure 5 shown. Figure 5 The three lines a, b and c represent 2 times the rated power, 3 times the rated power and 4 times the rated power respectively. Figure 5 It can be seen that when the rated power is doubled, the AIC value changes slowly, the change range is not large, and the minimum value appears at the 16th order; when the rated power is tripled, the AIC value changes slowly at the 3rd, 5th and 19th order models. Under the condition that the estimation speed allows, the 19th order model is better, followed by the 3rd and 5th order models; and when the rated power is tripled, the AIC value changes slowly at the 3rd and 13th order models. Without considering the prediction speed, the 13th order model is better, followed by the 3rd order.

[0127] In this embodiment, the expression of a battery life evaluation model with a model order of 3 can be established based on 50 historical battery lifespans as model training samples, and the expression can be as follows:

[0128] X(n)=1.3054x(n-1)-0.4387x(n-2)-0.0357x(n-3)

[0129] Based on the above analysis, it can be seen in this embodiment that the charging and discharging power of the battery during operation has a certain degree of influence on the model order, and there is basically no overfitting of the model. However, under the condition that the data length used for model parameter identification is the same, it is obvious that the more parameters to be estimated in the model, the lower the accuracy of the estimation of each parameter. This requires comprehensive consideration of the relationship between the number of sample data for determining the parameters to be identified and the model order. For a time series with a monotonically decreasing AIC value, the point where the AIC value decreases slowly with increasing order can be considered, and then factors such as modeling complexity and estimation speed are comprehensively considered, and adjustments are made later based on the predicted battery life effect.

[0130] S340, determining model parameters according to the autocorrelation function and constraints constructed relative to the model training baseline, combined with a given recursive algorithm and model training samples.

[0131] Among them, the autocorrelation function can be an autocorrelation function constructed based on the model training baseline data. The constraint condition can be a constraint condition set for the model training baseline, which can be set according to actual needs. Usually, the criterion for judging the accuracy of the prediction result is to minimize the sum of squares of the prediction errors. Therefore, in this embodiment, the minimum square error of the prediction can be used as a constraint condition. The recursive algorithm can be a pre-set algorithm and can be set according to actual needs. The recursive algorithm given in this embodiment can be the Levinson-Durbin recursive algorithm. In this embodiment, the model parameters can be obtained by training and recursive calculation based on the autocorrelation function and constraints constructed according to the model training baseline through a given recursive algorithm and model training samples.

[0132] An exemplary process diagram of the initial battery life assessment model parameter identification is as follows: Figure 6 As shown. This embodiment uses a baseline data sequence based on a measured model training, calculates the autocorrelation function, takes the minimum prediction square error as a constraint condition, finds the relationship between the model parameters and the autocorrelation function, and solves the matrix equation with the help of the Levinson-Durbin recursive algorithm to identify the model parameters to obtain each model parameter. The expression of the prediction square error in this embodiment can be:

[0133]

[0134] In order to minimize the prediction square error R, the coefficient a i The following conditions should be met:

[0135]

[0136] According to the prediction square error formula and the coefficient satisfying conditions, the following expression can be obtained:

[0137]

[0138] Simplifying the above formula again, we can get:

[0139]

[0140] Since the simplified formula is a system of equations with p unknown variables, solving the system of equations can obtain the coefficients a1, a2, a3…a p .

[0141] In this embodiment, the method for solving the equation group is to set the value of x(n) outside the range of 0≤n≤N-1 to 0. The autocorrelation function of x(n) after windowing is:

[0142]

[0143] The autocorrelation function of the above formula can be rewritten as:

[0144]

[0145] The above matrix equation is solved using the Levinson-Durbin recursive algorithm to obtain a1, a2, a3…a p The value of the model parameter can be identified.

[0146] S350: Substitute the determined model order and model parameters into the initial battery life assessment model to obtain a target battery life assessment model.

[0147] In this embodiment, the model order can be determined by the model training baseline, model training samples and a given model order relationship, as well as the autocorrelation function and constraints constructed based on the model training baseline, and the model parameters calculated by the recursive algorithm and model training samples are substituted into the initial battery life evaluation model to obtain the target battery life evaluation model.

[0148] In addition, in this embodiment, through the obtained target battery life evaluation model, three groups of batteries were selected as experimental objects. According to the comparison between the discharge SOH detected in real time and the autoregressive model, it was found that the target battery life evaluation model can effectively evaluate the battery health status, and the evaluation results and SOH fit are both above 95%. The battery life evaluation method of this embodiment can effectively shorten the test time and verify the effectiveness of the health evaluation index. It has better SOH fit and smaller error than the existing one, and is more accurate in battery health evaluation.

[0149] The technical solution of the embodiment of the present invention is to obtain a pre-built initial battery life evaluation model, which includes a model order to be determined and a model parameter to be identified; the battery life is used as a model training baseline, and a set number of historical battery lifespans are selected as model training samples; the relationship is determined according to the model training samples and the given model order, and the model order is determined; the model parameters are determined according to the autocorrelation function and constraints constructed relative to the model training baseline, combined with the given recursive algorithm and model training samples; the determined model order and model parameters are substituted into the initial battery life evaluation model to obtain the target battery life evaluation model. In this technical solution, the determined target battery life model can effectively shorten the test time, has a better fit, a smaller error, and a more accurate battery health assessment. It can also evaluate the battery health status under actual working conditions, and there is no high-precision requirement for the measuring instrument. The non-invasive measurement of battery parameters is beneficial to the subsequent operation of the battery and improves the accuracy of the battery health status assessment.

[0150] Embodiment 4

[0151] Figure 7 is a schematic diagram of the structure of a battery status evaluation device provided according to Embodiment 4 of the present invention. Figure 7 As shown, the device comprises:

[0152] The information acquisition module 710 is used to obtain the rated discharge information of the battery pack configured in the energy storage facility and the historical actual discharge information corresponding to the battery pack under the historical discharge events.

[0153] The evaluation result determination module 720 is used to determine the battery state evaluation result corresponding to the battery pack at the set evaluation time according to the rated discharge information and the historical actual discharge information.

[0154] Optionally, the evaluation result determination module 720 includes:

[0155] A historical battery service life determination unit, used to determine the historical battery service life corresponding to the battery pack at different historical detection moments according to the rated discharge information and the historical actual discharge information;

[0156] An input data determination unit, configured to obtain a predetermined target battery life assessment model and determine model input data from historical battery life;

[0157] The service life prediction value acquisition unit is used to input the model input data into the target battery life evaluation model, obtain the service life prediction value corresponding to the battery pack at the set evaluation time, and use it as the battery state evaluation result.

[0158] Optional, historical battery life determination unit, including:

[0159] A total effective throughput determination subunit, used for determining a total effective throughput of the battery pack according to the rated discharge information;

[0160] A discharge event determination subunit, used to determine, for each historical detection moment, the battery historical operation cycle to which the historical detection moment belongs, and determine a target historical discharge event included in the battery historical operation cycle;

[0161] An effective ampere-hour determination subunit, used to determine the effective ampere-hour of the battery pack under the target historical discharge event according to the target historical actual discharge information corresponding to each target historical discharge event;

[0162] The historical battery service life determination subunit is used to determine the historical battery service life corresponding to the battery group at the historical detection time according to the total effective throughput and each effective ampere-hour.

[0163] Optionally, a total effective throughput determination subunit is specifically used to extract the rated discharge depth, the rated discharge capacity at the rated discharge current, and the number of discharge cycles at the rated discharge depth and the rated discharge current included in the rated discharge information; and determine the product value of the rated discharge depth, the rated discharge capacity and the number of discharge cycles as the total effective throughput of the battery pack.

[0164] Optionally, an effective ampere-hour determination subunit is specifically used to extract, for each target historical discharge event, the actual discharge depth, the actual discharge capacity, and the actual ampere-hours under the actual discharge current from the corresponding target historical actual discharge information; determine a first ratio of the actual discharge depth to the rated discharge depth in the rated discharge information, and determine a second ratio of the actual discharge capacity to the rated discharge capacity in the rated discharge information; substitute the first ratio, the second ratio, and the actual ampere-hours into a set relationship to obtain the effective ampere-hours under the target historical discharge event.

[0165] Based on the above solution, optionally, the evaluation result determination module may further include the following units to determine the target battery life evaluation model;

[0166] An initial model acquisition unit, used to acquire a pre-built initial battery life assessment model, wherein the initial battery life assessment model includes a model order to be determined and a model parameter to be identified;

[0167] A model training sample selection unit, used to use the battery life as a model training baseline and select a set number of historical battery life as model training samples;

[0168] A model order determination unit, used to determine a relationship according to a model training sample and a given model order, and determine the model order;

[0169] A model parameter determination unit, used to determine the model parameters according to the autocorrelation function and constraint conditions constructed relative to the model training baseline, combined with a given recursive algorithm and model training samples;

[0170] The target model determination unit is used to substitute the determined model order and model parameters into the initial battery life evaluation model to obtain the target battery life evaluation model.

[0171] Optionally, an input data determination unit is specifically used to determine a target historical detection moment included in the target battery life evaluation model according to the set evaluation moment;

[0172] The historical battery life corresponding to each target historical detection moment is determined as the model input data.

[0173] A battery status evaluation device provided in an embodiment of the present invention can execute a battery status evaluation method provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0174] Embodiment 5

[0175] Figure 8 1 is a schematic diagram of the structure of an electronic device provided according to Embodiment 5 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0176] like Figure 8 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0177] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0178] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, processors, microprocessors, etc. The processor 11 executes the various methods and processes described above, such as a battery state evaluation method.

[0179] In some embodiments, the battery state evaluation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the battery state evaluation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the battery state evaluation method in any other appropriate manner (e.g., by means of firmware).

[0180] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0181] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0182] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0183] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0184] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0185] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0186] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0187] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A battery status assessment method, characterized in that: include: Obtaining rated discharge information of battery packs configured in the energy storage facility and historical actual discharge information corresponding to the battery packs under historical discharge events; Determine a battery status evaluation result corresponding to the battery pack at a set evaluation time according to the rated discharge information and the historical actual discharge information; The determining, according to the rated discharge information and the historical actual discharge information, a battery status evaluation result corresponding to the battery pack at a set evaluation time includes: Determine, according to the rated discharge information and the historical actual discharge information, the historical battery service life corresponding to the battery pack at different historical detection moments; Obtaining a predetermined target battery life assessment model and determining model input data from the historical battery life; Inputting the model input data into the target battery life assessment model to obtain a predicted service life value of the battery pack at a set assessment time as a battery state assessment result; The determining, according to the rated discharge information and the historical actual discharge information, the historical battery service life corresponding to the battery pack at different historical detection moments includes: Determining a total effective throughput of the battery pack according to the rated discharge information; For each historical detection moment, determine the battery historical operation cycle to which the historical detection moment belongs, and determine the target historical discharge event included in the battery historical operation cycle; Determine the effective ampere-hours of the battery pack under the target historical discharge event according to the target historical actual discharge information corresponding to each target historical discharge event; Determine, according to the total effective throughput and each of the effective ampere hours, a historical battery service life corresponding to the battery pack at the historical detection time; The determining, according to the target historical actual discharge information corresponding to each target historical discharge event, the effective ampere-hours of the battery pack under the target historical discharge event includes: For each target historical discharge event, extract the actual discharge depth, the actual discharge capacity, and the actual ampere hours under the actual discharge current from the corresponding target historical actual discharge information; Determine a first ratio of the actual discharge depth to the rated discharge depth in the rated discharge information, and determine a second ratio of the actual discharge capacity to the rated discharge capacity in the rated discharge information; The first ratio, the second ratio and the actual ampere-hours are substituted into a set relationship to obtain the effective ampere-hours under the target historical discharge event.

2. The method according to claim 1, characterized in that The determining the total effective throughput of the battery pack according to the rated discharge information includes: Extracting the rated discharge depth, the rated discharge capacity at the rated discharge current, and the number of discharge cycles at the rated discharge depth and the rated discharge current included in the rated discharge information; The product value of the rated depth of discharge, the rated discharge capacity and the number of discharge cycles is determined as the total effective throughput of the battery pack.

3. The method according to claim 1, characterized in that The method for determining the target battery life evaluation model includes: Acquire a pre-built initial battery life assessment model, wherein the initial battery life assessment model includes a model order to be determined and a model parameter to be identified; The battery life is used as the model training baseline, and a set number of historical battery lifespans are selected as model training samples; Determine a relationship according to the model training sample and a given model order, and determine the model order; Determining the model parameters according to the autocorrelation function and constraints constructed relative to the model training baseline, in combination with a given recursive algorithm and the model training samples; The determined model order and model parameters are substituted into the initial battery life assessment model to obtain the target battery life assessment model.

4. The method according to claim 1, characterized in that: The determining of model input data from the historical battery service life comprises: Determining a target historical detection time included in the target battery life evaluation model according to the set evaluation time; The historical battery life corresponding to each of the target historical detection moments is determined as model input data.

5. A battery status evaluation device, characterized in that: include: An information acquisition module, used to acquire rated discharge information of a battery pack configured in an energy storage facility and historical actual discharge information corresponding to the battery pack under historical discharge events; An evaluation result determination module, used to determine a battery state evaluation result corresponding to the battery pack at a set evaluation time according to the rated discharge information and the historical actual discharge information; The evaluation result determination module comprises: A historical battery service life determination unit, used to determine the historical battery service life corresponding to the battery pack at different historical detection moments according to the rated discharge information and the historical actual discharge information; an input data determination unit, configured to obtain a predetermined target battery life assessment model and determine model input data from the historical battery life; A service life prediction value acquisition unit, used to input the model input data into the target battery life evaluation model, obtain the service life prediction value corresponding to the battery pack at the set evaluation time, and use it as the battery state evaluation result; The historical battery service life determination unit comprises: A total effective throughput determination subunit, used to determine the total effective throughput of the battery pack according to the rated discharge information; A discharge event determination subunit, used to determine, for each historical detection moment, the battery historical operation cycle to which the historical detection moment belongs, and determine a target historical discharge event included in the battery historical operation cycle; An effective ampere-hour determination subunit, configured to determine the effective ampere-hour of the battery pack under the target historical discharge event according to the target historical actual discharge information corresponding to each target historical discharge event; A historical battery service life determination subunit, used to determine the historical battery service life corresponding to the battery pack at the historical detection time according to the total effective throughput and each effective ampere-hour; The effective ampere-hour determination subunit is specifically used to extract, for each target historical discharge event, the actual discharge depth, the actual discharge capacity, and the actual ampere-hours under the actual discharge current from the corresponding target historical actual discharge information; determine a first ratio of the actual discharge depth to the rated discharge depth in the rated discharge information, and determine a second ratio of the actual discharge capacity to the rated discharge capacity in the rated discharge information; substitute the first ratio, the second ratio, and the actual ampere-hours into a set relationship to obtain the effective ampere-hours under the target historical discharge event.

6. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the battery status evaluation method as described in any one of claims 1 to 4.

7. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the battery status evaluation method as claimed in any one of claims 1 to 4 when executed by a computer processor.