A method and device for estimating the state of health of a retired battery

Abstract

The present application relates to a kind of SOH estimation method and device of retired battery, belong to battery evaluation technical field, wherein the SOH estimation method of retired battery includes: obtaining first test data set and second test data set;First test data set and second test data set are preprocessed, and the pulse charge-discharge characteristics and constant current charge-discharge characteristics of target retired battery are extracted from the first test data and second test data after pre-processing;The pulse charge-discharge characteristics and constant current charge-discharge characteristics of target retired battery are as the input of SOH estimation model, and the SOH estimation value of target retired battery output by SOH estimation model is obtained, SOH estimation model is based on the historical operation data of sample battery of same model with target retired battery to XGBoost model training obtains.The present application effectively improves the accuracy of retired battery SOH estimation.

Description

Technical Field

[0001] This invention relates to the field of battery evaluation technology, and in particular to a method and apparatus for estimating the state of harm (SOH) of retired batteries. Background Technology

[0002] With the rapid development of electric vehicles, more and more electric vehicles are starting to replace their batteries, which has led to a rapid increase in the number of retired batteries. Directly discarding these retired batteries would result in resource waste and environmental pollution, but they still retain a certain capacity and have reuse value (such as energy storage systems, low-speed electric vehicles, etc.).

[0003] However, the reuse of retired batteries requires consideration of safety. The safety of retired batteries is generally assessed through State of Health (SOH), which is typically defined as the ratio of current maximum capacity to rated capacity. However, battery degradation is a complex electrochemical process, influenced by factors such as temperature, charge / discharge rate, and cycle count. Relying solely on single data points like voltage or internal resistance at a particular moment is unreliable. Furthermore, obtaining historical operating data for retired batteries is difficult, further complicating accurate SOH estimation. Current methods for estimating SOH in retired batteries generally involve establishing electrochemical models, but these methods often yield inaccurate results.

[0004] Therefore, accurately estimating the state of harmonics (SOH) of retired batteries has become an urgent technical problem to be solved. Summary of the Invention

[0005] In view of this, it is necessary to provide a method and apparatus for estimating the state of harm (SOH) of retired batteries to solve the problem of insufficient accuracy of existing SOH estimation schemes for retired batteries.

[0006] To address the aforementioned problems, in a first aspect, the present invention provides a method for estimating the state of harm (SOH) of retired batteries, comprising: Acquire a first test dataset and a second test dataset. The first test dataset consists of voltage data obtained after applying a charge-discharge pulse of a preset duration to the target decommissioned battery under various SOC states. The second test dataset consists of voltage data and SOC data obtained after applying a current of a preset magnitude to the target decommissioned battery for charge-discharge testing. The first and second test datasets are preprocessed, and the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery are extracted from the preprocessed first and second test data. The pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery are used as inputs to the SOH estimation model to obtain the SOH estimate of the target retired battery. The SOH estimation model is trained on the XGBoost model based on the historical operating data of sample batteries of the same model as the target retired battery.

[0007] In one possible implementation, the extraction of pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target decommissioned battery from the preprocessed first and second test data includes: The pulse charge-discharge characteristics of the target retired battery are extracted from the pre-processed first test data, and the constant current charge-discharge characteristics of the target retired battery are extracted from the pre-processed second test data.

[0008] In one possible implementation, extracting the pulse charge-discharge characteristics of the target decommissioned battery from the preprocessed first test data includes: The average internal resistance of the target decommissioned battery under various SOC states is extracted from the pre-processed first test data.

[0009] In one possible implementation, extracting the constant current charge-discharge characteristics of the target decommissioned battery from the preprocessed second test data includes: Extract the rate of change of voltage corresponding to the state of charge (SOC) of the target decommissioned battery at a preset current from the preprocessed second test data.

[0010] In one possible implementation, the training process of the SOH estimation model includes: The pulse charge-discharge characteristics and constant current charge-discharge characteristics of the sample batteries were determined based on historical operating data of sample batteries of the same model as the target retired batteries. Using the actual state of charge (SOH) of the sample batteries as labels, the XGBoost model is trained based on the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the sample batteries to obtain the SOH estimation model.

[0011] In one possible implementation, the hyperparameters of the XGBoost model are determined based on a genetic algorithm.

[0012] In one possible implementation, the preprocessing of the first and second test datasets includes: Missing and outlier values ​​were removed from the first and second test datasets, and time alignment was performed.

[0013] On the other hand, the present invention also provides a SOH estimation device for retired batteries, comprising: The acquisition module is used to acquire a first test dataset and a second test dataset. The first test dataset is the voltage data obtained after applying a charge and discharge pulse of a preset duration to the target retired battery under various SOC states. The second test dataset is the voltage data and SOC data obtained after applying a current of a preset size to the target retired battery for charge and discharge testing. The extraction module is used to preprocess the first test dataset and the second test dataset, and extract the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery from the preprocessed first test data and second test data. The estimation module is used to take the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery as input to the SOH estimation model, and obtain the SOH estimate of the target retired battery output by the SOH estimation model. The SOH estimation model is trained on the XGBoost model based on the historical operating data of sample batteries of the same model as the target retired battery.

[0014] Secondly, the present invention also provides a SOH estimation device, including a memory and a processor, wherein, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the SOH estimation method for decommissioned batteries described in any of the above implementations.

[0015] Thirdly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps in the SOH estimation method for retired batteries described in any of the above implementations.

[0016] The beneficial effects of this invention are as follows: The SOH method and apparatus for retired batteries provided by this invention obtain a first test dataset and a second test dataset by performing charge-discharge tests on the target retired battery. Then, the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery are extracted from the first test dataset and the second test dataset for subsequent SOH estimation. Thus, SOH estimation can be performed based on the actual operating data of the target retired battery without relying on the historical operating data of the retired battery. Finally, the SOH estimation model trained by the XGBoost model is combined with the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery using the historical operating data of sample batteries of the same model as the target retired battery to predict the estimated SOH value of the target retired battery. This invention effectively improves the accuracy of SOH estimation for retired batteries. Attached Figure Description

[0017] Figure 1 A schematic flowchart of an embodiment of the SOH estimation method for retired batteries provided by the present invention; Figure 2 A schematic flowchart of an embodiment of the SOH estimation process for retired batteries provided by the present invention; Figure 3 A schematic diagram of an embodiment of the SOH estimation device for retired batteries provided by the present invention; Figure 4 This is a schematic diagram of an embodiment of the SOH estimation device provided by the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0019] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0020] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] This invention provides a method and apparatus for estimating the state of harm (SOH) of retired batteries, which will be described below.

[0023] Figure 1 A schematic flowchart of an embodiment of the SOH method for decommissioned batteries provided by the present invention is shown below. Figure 1 As shown, the SOH method for retired batteries includes: S101. Obtain the first test dataset and the second test dataset. The first test dataset is the voltage data obtained after applying a preset duration of charge and discharge pulses to the target decommissioned battery under various SOC states. The second test dataset is the voltage data and SOC data obtained after applying a preset current to the target decommissioned battery for charge and discharge testing.

[0024] It should be noted that the SOH method for retired batteries provided by this invention can be applied to scenarios such as health status estimation of retired batteries, for example, health status estimation of retired batteries in electric vehicles or health status estimation of retired batteries in power supply rooms.

[0025] When estimating the State of Charge (SOH) of retired batteries, the target retired battery can first be subjected to charge / discharge pulses of a preset duration (e.g., 10s) at various states of charge (SOC) (e.g., 10% SOC, 30% SOC, 50% SOC, etc.). The pulse magnitudes can be 0.5C, 0.3C, etc., and the resulting voltage data is used as the first test dataset. Next, a preset current (e.g., 0.1C, 0.3C, etc.) can be applied to the target retired battery for charge / discharge testing, and the resulting voltage and SOC data are used as the second test dataset. Historical operating data of retired batteries is often missing. By testing retired batteries to obtain corresponding test datasets for subsequent SOH estimation, it is possible to avoid relying on historical operating data, thereby improving the accuracy of subsequent SOH estimation.

[0026] S102. Preprocess the first test dataset and the second test dataset, and extract the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery from the preprocessed first test data and second test data.

[0027] It should be noted that after obtaining the first and second test datasets, the first and second test datasets can be preprocessed. Then, the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target decommissioned battery can be extracted from the preprocessed first and second test datasets to provide a data basis for subsequent SOH estimation.

[0028] S103. The pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery are used as inputs to the SOH estimation model to obtain the SOH estimate of the target retired battery output by the SOH estimation model. The SOH estimation model is trained on the XGBoost model based on the historical operating data of sample batteries of the same model as the target retired battery.

[0029] It should be noted that after extracting the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery, these characteristics can be used as input to the SOH estimation model. The SOH estimate of the target retired battery is then determined based on the SOH estimation model. The SOH estimation model can be trained using historical operating data from sample batteries of the same model as the target retired battery.

[0030] In summary, the SOH method for retired batteries provided in this invention obtains a first test dataset and a second test dataset by performing charge-discharge tests on the target retired battery. Then, it extracts the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery from the first and second test datasets for subsequent SOH estimation. This allows for SOH estimation based on the actual operating data of the target retired battery, without relying on historical operating data. Finally, it uses historical operating data from sample batteries of the same model as the target retired battery to train an SOH estimation model based on the XGBoost model, combined with the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery, to predict the estimated SOH value of the target retired battery. This invention effectively improves the accuracy of SOH estimation for retired batteries.

[0031] In some embodiments of the present invention, the extraction of pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target decommissioned battery from the preprocessed first and second test data includes: The pulse charge-discharge characteristics of the target retired battery are extracted from the pre-processed first test data, and the constant current charge-discharge characteristics of the target retired battery are extracted from the pre-processed second test data.

[0032] It should be noted that: in extracting the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery from the pre-processed first test data and the second test data, the pulse charge-discharge characteristics of the target retired battery can be extracted from the pre-processed first test data, and the constant current charge-discharge characteristics of the target retired battery can be extracted from the pre-processed second test data.

[0033] In some embodiments of the present invention, the step of extracting the pulse charge-discharge characteristics of the target decommissioned battery from the preprocessed first test data includes: The average internal resistance of the target decommissioned battery under various SOC states is extracted from the pre-processed first test data.

[0034] It should be noted that: when extracting the pulse charge and discharge characteristics of the target retired battery from the preprocessed first test data, the average internal resistance of the target retired battery under various SOC states can be extracted from the preprocessed first test data. The average internal resistance can be calculated from the charge and discharge current values ​​and corresponding voltage values ​​in the test data.

[0035] In some embodiments of the present invention, the step of extracting the constant current charge-discharge characteristics of the target decommissioned battery from the preprocessed second test data includes: Extract the rate of change of voltage corresponding to the state of charge (SOC) of the target decommissioned battery at a preset current from the preprocessed second test data.

[0036] It should be noted that when extracting the constant current charge and discharge characteristics of the target retired battery from the preprocessed second test data, the rate of change of voltage corresponding to the SOC of the target retired battery under a preset current can be extracted from the preprocessed second test data. The rate of change of voltage corresponding to the SOC can be calculated from the SOC difference and voltage difference between two adjacent sampling points.

[0037] In some embodiments of the present invention, the training process of the SOH estimation model includes: The pulse charge-discharge characteristics and constant current charge-discharge characteristics of the sample batteries were determined based on historical operating data of sample batteries of the same model as the target retired batteries. Using the actual state of charge (SOH) of the sample batteries as labels, the XGBoost model is trained based on the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the sample batteries to obtain the SOH estimation model.

[0038] It should be noted that when training the SOH estimation model, the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the sample battery can be determined by the historical operating data of the sample battery of the same model as the target retired battery. Then, the real SOH of the sample battery is used as a label, and the XGBoost model is trained by the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the sample battery, thereby obtaining the SOH estimation model.

[0039] In some embodiments of the present invention, the hyperparameters of the XGBoost model can be determined based on a genetic algorithm.

[0040] In some embodiments of the present invention, the preprocessing of the first test dataset and the second test dataset includes: Missing and outlier values ​​were removed from the first and second test datasets, and time alignment was performed.

[0041] It should be noted that when preprocessing the first and second test datasets, missing and outlier values ​​can be removed first to ensure data accuracy. Then, the first and second test datasets can be time-aligned to ensure consistent sampling frequency of the test data.

[0042] Combination Figure 2The SOH estimation process provided by this invention specifically includes the following steps: 1. Perform pulse charge-discharge tests and constant current charge-discharge tests on the target retired batteries respectively.

[0043] 2. Based on the test results, obtain the first test dataset and the second test dataset.

[0044] 3. Remove missing and outlier values ​​from the first and second test datasets and align them by time.

[0045] 4. Extract the average internal resistance of the target decommissioned battery under various SOC states from the preprocessed first test dataset, and extract the rate of change of voltage corresponding to the SOC of the target decommissioned battery under a preset current from the preprocessed second test dataset.

[0046] 5. Using historical data of sample batteries of the same model as the target retired battery, and the true SOH labels of the sample batteries, the XGBoost model is trained to obtain the SOH estimation model.

[0047] 6. The average internal resistance of the target decommissioned battery under various SOC states and the rate of change of voltage corresponding to SOC under a preset current are used as inputs to the SOH estimation model.

[0048] 7. Use the output of the SOH estimation model as the SOH estimate of the target decommissioned battery.

[0049] This invention estimates the state of harm (SOH) of retired batteries by obtaining data through testing, avoiding inaccurate SOH estimation caused by the lack of historical operating data of retired batteries, effectively improving the accuracy of SOH estimation of retired batteries, and providing support for the reuse of retired batteries.

[0050] To better implement the SOH estimation method for decommissioned batteries in this embodiment of the invention, based on the SOH estimation method for decommissioned batteries, the corresponding method is as follows: Figure 3 As shown, this embodiment of the invention also provides a SOH estimation device for retired batteries. The SOH estimation device 300 for retired batteries includes: The acquisition module 301 is used to acquire a first test dataset and a second test dataset. The first test dataset is the voltage data obtained after applying a charge and discharge pulse of a preset duration to the target retired battery under various SOC states. The second test dataset is the voltage data and SOC data obtained after applying a current of a preset size to the target retired battery for charge and discharge testing. Extraction module 302 is used to preprocess the first test dataset and the second test dataset, and extract the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery from the preprocessed first test data and second test data; The estimation module 303 is used to take the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery as input to the SOH estimation model, and obtain the SOH estimated value of the target retired battery output by the SOH estimation model. The SOH estimation model is trained on the XGBoost model based on the historical operating data of sample batteries of the same model as the target retired battery.

[0051] The SOH estimation device 300 for retired batteries provided in the above embodiments can realize the technical solutions described in the embodiments of the SOH estimation method for retired batteries. The specific implementation principles of each module or unit can be found in the corresponding content in the embodiments of the SOH estimation method for retired batteries, and will not be repeated here.

[0052] like Figure 4 As shown, the present invention also provides a SOH estimation device 400. The SOH estimation device 400 includes a processor 401, a memory 402, and a display 403. Figure 4 Only a portion of the components of the SOH estimation device 400 are shown; however, it should be understood that implementation of all shown components is not required, and more or fewer components may be implemented instead.

[0053] In some embodiments, processor 401 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 402 or process data, such as the SOH estimation method for retired batteries in this invention.

[0054] In some embodiments, processor 401 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 401 may be local or remote. In some embodiments, processor 401 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0055] In some embodiments, memory 402 may be an internal storage unit of the SOH estimation device 400, such as a hard disk or memory of the SOH estimation device 400. In other embodiments, memory 402 may also be an external storage device of the SOH estimation device 400, such as a pluggable hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., provided on the SOH estimation device 400.

[0056] Furthermore, the memory 402 may include both internal storage units of the SOH estimation device 400 and external storage devices. The memory 402 is used to store the application software and various types of data for which the SOH estimation device 400 is installed.

[0057] In some embodiments, display 403 may be an LED display, a liquid crystal display, a touch-screen liquid crystal display, or an organic light-emitting diode (OLED) touchscreen, etc. Display 403 is used to display information from the SOH estimation device 400 and to display a user interface for visualization. Components 401-403 of the SOH estimation device 400 communicate with each other via a system bus.

[0058] In one embodiment, when processor 401 executes the SOH estimation program for retired batteries in memory 402, the following steps can be implemented: Acquire a first test dataset and a second test dataset. The first test dataset consists of voltage data obtained after applying a charge-discharge pulse of a preset duration to the target decommissioned battery under various SOC states. The second test dataset consists of voltage data and SOC data obtained after applying a current of a preset magnitude to the target decommissioned battery for charge-discharge testing. The first and second test datasets are preprocessed, and the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery are extracted from the preprocessed first and second test data. The pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery are used as inputs to the SOH estimation model to obtain the SOH estimate of the target retired battery. The SOH estimation model is trained on the XGBoost model based on the historical operating data of sample batteries of the same model as the target retired battery.

[0059] It should be understood that when the processor 401 executes the SOH estimation program for the retired battery in the memory 402, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0060] Furthermore, this embodiment of the invention does not specifically limit the type of SOH estimation device 400 mentioned. SOH estimation device 400 can be a portable electronic device such as a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, or laptop computer. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic devices can also be other portable electronic devices, such as laptop computers with touch-sensitive surfaces (e.g., touch panels). It should also be understood that in some other embodiments of the invention, SOH estimation device 400 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0061] Accordingly, this application also provides a computer-readable storage medium for storing a computer-readable program or instruction. When the program or instruction is executed by a processor, it can implement the steps or functions in the SOH estimation method for retired batteries provided in the above-described method embodiments.

[0062] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0063] The SOH estimation method and apparatus for retired batteries provided by the present invention have been described in detail above. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for estimating the state of harm (SOH) of retired batteries, characterized in that, include: Acquire a first test dataset and a second test dataset. The first test dataset consists of voltage data obtained after applying a preset duration of charge and discharge pulses to the target decommissioned battery under various SOC states. The second test dataset consists of voltage data and SOC data obtained after applying a preset current to the target decommissioned battery for charge and discharge testing. The first and second test datasets are preprocessed, and the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery are extracted from the preprocessed first and second test data. The pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery are used as inputs to the SOH estimation model to obtain the SOH estimate of the target retired battery output by the SOH estimation model. The SOH estimation model is trained on the XGBoost model based on the historical operating data of sample batteries of the same model as the target retired battery. The extraction of pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target decommissioned battery from the preprocessed first and second test data includes: The pulse charge-discharge characteristics of the target retired battery are extracted from the pre-processed first test data, and the constant current charge-discharge characteristics of the target retired battery are extracted from the pre-processed second test data. The extraction of pulse charge-discharge characteristics of the target decommissioned battery from the preprocessed first test data includes: The average internal resistance of the target decommissioned battery under various SOC states was extracted from the pre-processed first test data. The extraction of the constant current charge-discharge characteristics of the target decommissioned battery from the preprocessed second test data includes: Extract the rate of change of voltage corresponding to the state of charge (SOC) of the target decommissioned battery at a preset current from the preprocessed second test data.

2. The SOH estimation method for retired batteries according to claim 1, characterized in that, The training process of the SOH estimation model includes: The pulse charge-discharge characteristics and constant current charge-discharge characteristics of the sample batteries were determined based on historical operating data of sample batteries of the same model as the target retired batteries. Using the actual state of charge (SOH) of the sample batteries as labels, the XGBoost model is trained based on the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the sample batteries to obtain the SOH estimation model.

3. The SOH estimation method for retired batteries according to claim 2, characterized in that, The hyperparameters of the XGBoost model are determined based on a genetic algorithm.

4. The SOH estimation method for retired batteries according to claim 1, characterized in that, The preprocessing of the first and second test datasets includes: Missing and outlier values ​​were removed from the first and second test datasets, and time alignment was performed.

5. A device for estimating the state of harm (SOH) of a retired battery, characterized in that, include: The acquisition module is used to acquire a first test dataset and a second test dataset. The first test dataset is the voltage data obtained after applying a charge and discharge pulse of a preset duration to the target retired battery under various SOC states. The second test dataset is the voltage data and SOC data obtained after applying a current of a preset size to the target retired battery for charge and discharge testing. The extraction module is used to preprocess the first test dataset and the second test dataset, and extract the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery from the preprocessed first test data and second test data. The estimation module is used to take the pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target retired battery as input to the SOH estimation model, and obtain the SOH estimate of the target retired battery output by the SOH estimation model. The SOH estimation model is trained on the XGBoost model based on the historical operating data of sample batteries of the same model as the target retired battery. The extraction of pulse charge-discharge characteristics and constant current charge-discharge characteristics of the target decommissioned battery from the preprocessed first and second test data includes: The pulse charge-discharge characteristics of the target retired battery are extracted from the pre-processed first test data, and the constant current charge-discharge characteristics of the target retired battery are extracted from the pre-processed second test data. The extraction of pulse charge-discharge characteristics of the target decommissioned battery from the preprocessed first test data includes: The average internal resistance of the target decommissioned battery under various SOC states was extracted from the pre-processed first test data. The extraction of the constant current charge-discharge characteristics of the target decommissioned battery from the preprocessed second test data includes: Extract the rate of change of voltage corresponding to the state of charge (SOC) of the target decommissioned battery at a preset current from the preprocessed second test data.

6. A SOx estimation device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the SOH estimation method for retired batteries according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the SOH estimation method for retired batteries according to any one of claims 1 to 4.

Images