CN114094218B - Method, device, equipment and medium for evaluating consistency of voltages of battery modules - Google Patents

Abstract

The embodiment of the invention discloses a method, a device, equipment and a medium for evaluating the consistency of voltages of battery modules. The method comprises the following steps: acquiring at least one attribute parameter of a battery module to be tested in at least two time periods; each time period comprises at least one moment; respectively inputting each attribute parameter in different time periods into a pre-trained regression forest model to obtain at least one moment voltage corresponding to each time period; and generating a state sequence corresponding to each time period according to the time voltage, and evaluating the consistency of the voltages of the battery modules to be tested according to the state sequences. According to the scheme provided by the embodiment of the invention, the consistency evaluation of the voltage of the battery module is accurately realized.

Description

Battery module voltage consistency evaluation method, device, equipment and medium

Technical Field

Embodiments of the present invention relate to the field of computer technology, and in particular to a method, device, equipment and medium for evaluating the consistency of voltage of a battery module.

Background Art

With the continuous development of science and technology, various types of power batteries have achieved rapid development; the performance of these batteries directly affects the overall performance of products such as automobiles and motorcycles that require power batteries to provide power. How to evaluate the consistency of battery voltage is a key research topic in the industry; since the power batteries used are usually battery modules composed of multiple battery modules, these power batteries are collectively referred to as battery modules in the embodiments of the present invention.

At present, one method is to evaluate the consistency of the voltage of the battery module based on a single parameter evaluation method based on statistics. For example, the consistency of the battery voltage is characterized by statistics such as the standard deviation and range of the battery cell voltage. This method ignores the impact of operating condition differences on voltage consistency, so it is easy to make incorrect evaluations under certain operating conditions; another method is to evaluate the consistency of the battery module voltage based on a multi-parameter evaluation method based on machine learning. This method is generally modeled based on battery test data. For example, through battery test experiments, the numerical correspondence between the capacity and voltage of the battery module at different temperatures is obtained, and then the voltage consistency is evaluated by comparing the differences in the corresponding relationships of the battery modules to be tested. This method requires a large amount of test data, which increases the test cost dramatically, and cannot be used for online evaluation, so it has weak engineering application significance.

How to accurately evaluate the consistency of battery module voltage is a key research topic in the industry.

Summary of the invention

Embodiments of the present invention provide a method, device, equipment and storage medium for evaluating the consistency of the voltage of a battery module, so as to accurately evaluate the consistency of the voltage of the battery module.

In a first aspect, an embodiment of the present invention provides a method for evaluating the consistency of voltage of a battery module, comprising:

Acquire at least one attribute parameter of the battery module to be tested in at least two time periods; each of the time periods includes at least one moment;

Inputting each attribute parameter in different time periods into a pre-trained regression forest model respectively, and obtaining at least one voltage at a time corresponding to each time period;

A state sequence corresponding to each time period is generated according to the voltage at each moment, and the consistency of the voltage of the battery module to be tested is evaluated according to each state sequence.

In a second aspect, an embodiment of the present invention further provides a battery module voltage consistency assessment device, comprising:

An attribute parameter acquisition module, used to acquire at least one attribute parameter of the battery module to be tested in at least two time periods; each of the time periods includes at least one moment;

A moment voltage determination module is used to input various attribute parameters in different time periods into a pre-trained regression forest model to obtain at least one moment voltage corresponding to each time period;

The consistency evaluation module is used to generate a state sequence corresponding to each time period according to the voltage at each moment, and evaluate the consistency of the voltage of the battery module to be tested according to each state sequence.

In a third aspect, an embodiment of the present invention further provides a battery module voltage consistency evaluation device, the battery voltage consistency evaluation device comprising:

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 method for evaluating the voltage consistency of a battery module as described in any one of the embodiments of the present invention.

In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, characterized in that the computer executable instructions, when executed by a computer processor, are used to execute a method for evaluating the voltage consistency of a battery module as described in any one of the embodiments of the present invention.

The embodiment of the present invention obtains at least one attribute parameter of the battery module to be tested in at least two time periods; each of the time periods includes at least one moment; each attribute parameter in different time periods is input into a pre-trained regression forest model to obtain at least one moment voltage corresponding to each time period; a state sequence corresponding to each time period is generated according to each moment voltage, and the consistency of the voltage of the battery module to be tested is evaluated according to each state sequence, thereby achieving accurate consistency evaluation of the voltage of the battery module.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a flow chart of a method for evaluating the consistency of voltage of a battery module in Embodiment 1 of the present invention;

2 is a flow chart of a method for evaluating the consistency of voltage of a battery module in a second embodiment of the present invention;

3 is a flow chart of a method for evaluating the consistency of voltage of a battery module in Embodiment 2 of the present invention;

4 is a schematic diagram of the structure of a device for evaluating the consistency of voltage of a battery module in Embodiment 3 of the present invention;

FIG5 is a schematic diagram of the structure of a battery module voltage consistency evaluation device in Embodiment 4 of the present invention.

DETAILED DESCRIPTION

The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention, rather than to limit the embodiments of the present invention. It is also necessary to explain that, for ease of description, only parts related to the embodiments of the present invention are shown in the accompanying drawings, rather than all structures.

Embodiment 1

FIG1 is a flow chart of a method for evaluating the voltage consistency of a battery module in a first embodiment of the present invention. This embodiment is applicable to the case of evaluating the voltage consistency of a battery in a vehicle. The method can be executed by a device for evaluating the voltage consistency of a battery module. The device can be implemented by software and/or hardware and integrated in a device for evaluating the voltage consistency of a battery module. In this embodiment, the device for evaluating the voltage consistency of a battery module can be a computer, a server, or a tablet computer. Specifically, referring to FIG1, the method specifically includes the following steps:

Step 110, obtaining at least one attribute parameter of the battery module to be tested in at least two time periods; each of the time periods includes at least one moment.

Among them, each time period can include multiple moments. Usually, the number of moments contained in each time period is the same; for example, the length of time period A can be 10 minutes, including 10 moments in total; the length of time period B is also 10 minutes, including 10 moments in total, which can ensure that the length of the state sequence generated subsequently is consistent, which is convenient for calculation.

In this embodiment, the battery module may be composed of a plurality of battery modules, which may be used in new energy vehicles, electric bicycles, motorcycles or other devices requiring power supply, which is not limited in this embodiment.

In this embodiment, the attribute parameters may include time, state of charge (SOC), charging state, temperature, and voltage.

In this embodiment, the property parameters of the battery module to be tested can be obtained at each moment in multiple time periods; illustratively, the time parameters, SOC parameters, charging state parameters, temperature parameters and voltage parameters from the first moment to the tenth moment in time period A, and the time parameters, SOC parameters, charging state parameters, temperature parameters and voltage parameters from the first moment to the tenth moment in time period B can be obtained respectively.

Step 120: Input each attribute parameter in different time periods into a pre-trained regression forest model to obtain at least one voltage at a time corresponding to each time period.

In an optional implementation of the present embodiment, after obtaining at least one attribute parameter of the vehicle battery to be tested in at least two time periods, the attribute parameters in different time periods can be further input into a pre-trained regression forest model to obtain at least one moment voltage corresponding to each time period.

Exemplarily, in the above example, the time parameters, SOC parameters, charging state parameters, temperature parameters and voltage parameters from the first moment to the tenth moment in time period A can be first input into the regression forest model to obtain the voltages at ten moments; then the time parameters, SOC parameters, charging state parameters, temperature parameters and voltage parameters from the first moment to the tenth moment in time period B can be input into the regression forest model to obtain the voltages at ten moments.

In an optional implementation of the present embodiment, before inputting each attribute parameter in different time periods into a pre-trained regression forest model, it also includes: obtaining at least one attribute parameter of multiple normal battery modules; preprocessing each of the attribute parameters, and dividing each of the attribute parameters into a training set and a test set according to a set ratio; and obtaining the regression forest model by training the training set and the test set.

In a specific implementation, data of a normal vehicle may be collected, that is, attribute parameters of a vehicle battery whose battery voltage remains consistent for a long time (e.g., one month, half a year, or one year, etc.), for example, fields include reporting time, SOC, charging state, cell temperature, current, and cell voltage; the data may be preprocessed, for example, missing values in the data may be removed, abnormal voltages may be removed according to the normal operating voltage range, abnormal temperatures may be removed according to the 3σ criterion, and the charging state may be encoded using One-Hot, wherein the uncharged state may be (1, 0, 0), the parking charging state may be (0, 1, 0), and the charging state completion may be (0, 0, 1); the data set may be divided into a training set and a test set according to a ratio of 7:3 (or 8:2 or 9:1, etc., which is not limited in this embodiment), wherein the training set may be used for model training, and the test set may be used for model parameter adjustment; further, a random forest model may be trained based on the training set, and the model parameters may be adjusted based on the test set, and then a regression forest model may be established based on the optimal random forest model.

The advantage of this setting is that at least one voltage at a time corresponding to each time period can be determined quickly and accurately, providing a basis for subsequent consistency evaluation of the voltage of the battery module to be tested, thereby improving the execution efficiency of the algorithm.

It should be noted that in this embodiment, training the random forest model based on the training set, adjusting the model parameters based on the test set, and establishing the regression forest model based on the optimal random forest model are conventional technical means in this field and will not be described in detail in this embodiment.

Step 130 : generating a state sequence corresponding to each time period according to the voltage at each moment, and evaluating the consistency of the voltage of the battery module to be tested according to each state sequence.

In an optional implementation of this embodiment, after obtaining at least one moment voltage corresponding to each time period, a state sequence corresponding to each time period can be further generated based on the voltage at each moment, and the voltage consistency of the battery module to be tested can be evaluated based on each state sequence.

In this embodiment, generating a state sequence corresponding to each time period according to the voltage at each time moment may include: obtaining a state code corresponding to the voltage at each time moment of the target time period, and forming a state sequence corresponding to the target time period according to each state code. The target time period may be any time period, such as time period A or time period B involved in the above example, which is not limited in this embodiment.

Exemplarily, if the target time period includes ten moments, after obtaining the moment voltages corresponding to these ten moments, the state code corresponding to the voltage at each moment can be determined in turn, and the state codes can be spliced in chronological order to form a state sequence corresponding to the target time period.

In an optional implementation of this embodiment, obtaining the status code corresponding to the voltage at each moment in the target time period may include: if the voltage at the target moment is within a preset voltage confidence interval, the status code corresponding to the voltage at the target moment is 1, otherwise it is 0.

Among them, the preset voltage confidence interval can be set by setting the significance level. For example, the significance level can be set to 0.05, and the confidence interval of the voltage estimate [y _0.025 ,y _0.975 ] can be further obtained, wherein y _0.025 and y _0.975 are the predicted values of the regression forest model at quantiles of 0.025 and 0.975, respectively.

Furthermore, if the voltage at the target time is within the confidence interval [y _0.025 ,y _0.975 ], the state code corresponding to the voltage at the target time is 1, otherwise it is 0; wherein the target time may be any time within the target time period, which is not limited in this embodiment.

It can be understood that, in this embodiment, the state sequence corresponding to each time period is a sequence whose internal elements are 0 or 1.

Furthermore, the consistency of the voltage of the battery module to be tested can be evaluated based on each state sequence generated. Exemplarily, if two state sequences are generated, the similarity between the two state sequences can be calculated, and the consistency of the voltage of the battery module to be tested can be evaluated based on the similarity result; Exemplarily, if the similarity calculation result is greater than a set threshold (for example, 0.9, 0.8 or 0.85, etc., which is not limited in this embodiment), it can be determined that the battery voltage of the vehicle to be tested meets the consistency requirement; If 10 state sequences are generated, the similarity between each two state sequences can be calculated, and the consistency of the voltage of the battery module to be tested can be evaluated based on the similarity result, that is, when the similarity between each two state sequences is greater than the set threshold, it can be determined that the battery voltage of the vehicle to be tested meets the consistency requirement.

The solution of this embodiment obtains at least one attribute parameter of the battery module to be tested in at least two time periods; each of the time periods includes at least one moment; each attribute parameter in different time periods is input into a pre-trained regression forest model to obtain at least one moment voltage corresponding to each time period; a state sequence corresponding to each time period is generated according to each moment voltage, and the consistency of the voltage of the battery module to be tested is evaluated according to each state sequence, thereby achieving accurate consistency evaluation of the voltage of the battery module.

Embodiment 2

FIG2 is a flow chart of a method for evaluating the voltage consistency of a battery module in Embodiment 2 of the present invention. This embodiment is a further refinement of the above-mentioned technical solutions. The technical solution in this embodiment can be combined with each optional solution in one or more of the above-mentioned embodiments. As shown in FIG2, the method for evaluating the voltage consistency of a battery module may include the following steps:

Step 210, obtaining at least one attribute parameter of a plurality of normal battery modules; preprocessing each of the attribute parameters, and dividing each of the attribute parameters into a training set and a test set according to a set ratio; and obtaining the regression forest model by training the training set and the test set.

Step 220, obtaining at least one attribute parameter of the battery module to be tested in at least two time periods; each of the time periods includes at least one moment.

Step 230: Input each attribute parameter in different time periods into a pre-trained regression forest model to obtain at least one voltage at a time corresponding to each time period.

Step 240: Generate a state sequence corresponding to each time period according to the voltage at each moment.

Step 250, calculating the similarity between every two state sequences, and calculating the consistency score of the voltage of the battery module to be tested according to each similarity calculation result; and evaluating the consistency of the voltage of the battery module to be tested according to the consistency score.

In an optional implementation of the present embodiment, after generating a state sequence corresponding to each time period, the similarity between every two state sequences can be further calculated, and the consistency score of the voltage of the battery module to be tested can be calculated based on the similarity calculation results; and the consistency of the voltage of the battery module to be tested can be evaluated based on the consistency score.

In an optional implementation of the present embodiment, evaluating the consistency of the voltage of the battery module to be tested based on the consistency score may include: determining whether the number of consistency scores that meet a preset one-time standard meets a consistency pass standard within a set time; if so, determining that the voltage of the battery module to be tested meets the consistency evaluation.

In this embodiment, the similarity between every two state sequences can be calculated according to the following formula:

Wherein, Similarity(i,j) represents the cosine similarity between monomer (i.e., time period) i and monomer j, si _,k represents the state of monomer i in the kth frame in the calculation window, and _Si represents the state sequence of monomer i.

Furthermore, the consistency score of the voltage of the battery module to be tested may be calculated according to the similarity calculation result. In this embodiment, the consistency score of the voltage of the battery module to be tested may be calculated by the following formula:

Wherein, Consistency(i) represents the voltage consistency score of cell i.

Furthermore, the consistency of the voltage of the battery module to be tested can be evaluated based on the consistency score. In this embodiment, the consistency score of the cells in the same statistical window can be judged based on the 3σ criterion. If the consistency score of cell i is Consistency(i)<80 and Consistency(i)<μ-3σ, it is judged as failing the consistency test, otherwise it fails the consistency test, where μ is the mean of all the consistency scores of the cells in the statistical window, and σ is the standard deviation;

In another specific example of this embodiment, the consistency score of the voltage of the battery module may also be calculated on a daily basis, and the calculation formula may be as follows:

Wherein, Consistency(i,T _j ) represents the voltage consistency score of cell i at time T _j , and m is the number of statistical windows divided on that day.

Correspondingly, the consistency test pass rate of all monomers is counted daily. If the pass rate is in the interval [0, 0.3], the monomer is judged to be seriously inconsistent. If the pass rate is in the interval (0.3, 0.6], the monomer is judged to be slightly inconsistent. If the pass rate is in the interval (0.6, 0.9], the monomer is judged to be basically consistent. If the pass rate is in the interval (0.9, 1], the monomer is judged to be completely consistent.

The solution of this embodiment calculates the similarity between every two state sequences, and calculates the consistency score of the voltage of the battery module to be tested according to the similarity calculation results; and evaluates the consistency of the voltage of the battery module to be tested according to the consistency score. The voltage of the battery module to be tested can be accurately evaluated, which provides a guarantee for the safe use of the battery module.

In order to enable those skilled in the art to better understand the voltage consistency evaluation method of the battery module of this embodiment, FIG3 is a flow chart of a voltage consistency evaluation method of a battery module in Embodiment 2 of the present invention. Referring to FIG3, the specific process includes:

Step 310: Data collection.

Step 311: data preprocessing.

Step 312: random forest model training and parameter adjustment.

Step 313: Obtain a regression forest model.

Step 320: input the data to be evaluated into the regression forest model.

Step 330: predict confidence intervals and obtain state sequences.

Step 340: Calculate the cell voltage consistency score.

Step 341: Calculate the battery voltage consistency score.

Step 342: Identify abnormal monomers.

Step 350: output the battery voltage consistency evaluation result.

In the solution of this embodiment, the core algorithm of the evaluation model is a machine learning algorithm, the training data contains various actual working condition data, the model has high accuracy, strong applicability, and can accurately evaluate consistency; the evaluation input data is completely consistent with the training data field and can be used for online evaluation; no battery cell test data support is required, and the modeling cost is low.

Embodiment 3

FIG4 is a schematic diagram of a battery module voltage consistency evaluation device in Embodiment 3 of the present invention, which can execute the battery module voltage consistency evaluation method involved in the above embodiments. Referring to FIG4 , the device includes: an attribute parameter acquisition module 410, a moment voltage determination module 420, and a consistency evaluation module 430.

The attribute parameter acquisition module 410 is used to acquire at least one attribute parameter of the battery module to be tested in at least two time periods; each of the time periods includes at least one moment;

The moment voltage determination module 420 is used to input each attribute parameter in different time periods into a pre-trained regression forest model to obtain at least one moment voltage corresponding to each time period;

The consistency evaluation module 430 is used to generate a state sequence corresponding to each time period according to the voltage at each moment, and evaluate the consistency of the voltage of the battery module to be tested according to each state sequence.

The solution of this embodiment is to obtain at least one attribute parameter of the battery module to be tested in at least two time periods through an attribute parameter acquisition module; each of the time periods includes at least one moment; each attribute parameter in different time periods is input into a pre-trained regression forest model through a moment voltage determination module to obtain at least one moment voltage corresponding to each time period; a state sequence corresponding to each time period is generated according to each moment voltage through a consistency evaluation module, and the consistency of the voltage of the battery module to be tested is evaluated according to each state sequence, thereby realizing accurate consistency evaluation of the voltage of the battery module.

In an optional implementation of this embodiment, the attribute parameter includes at least one of the following:

Time, charging ratio SOC, charging state, temperature and voltage.

In an optional implementation of this embodiment, the battery module voltage consistency assessment device further includes: a regression forest model training module, used to obtain at least one attribute parameter of a plurality of normal battery modules;

Preprocessing each of the attribute parameters, and dividing each of the attribute parameters into a training set and a test set according to a set ratio;

The regression forest model is obtained by training according to the training set and the test set.

In an optional implementation of this embodiment, the consistency evaluation module 430 includes: a state sequence generation submodule, which is used to obtain the state code corresponding to the voltage at each moment in the target time period, and form a state sequence corresponding to the target time period according to each state code.

In an optional implementation of this embodiment, the state sequence generation submodule is specifically configured to: if the voltage at the target moment is within a preset voltage confidence interval, then the state code corresponding to the voltage at the target moment is 1, otherwise it is 0.

In an optional implementation of this embodiment, the consistency evaluation module 430 further includes an evaluation submodule, which is used to calculate the similarity between every two state sequences, and calculate the consistency score of the voltage of the battery module to be tested according to the similarity calculation results;

And the consistency of the voltage of the battery module to be tested is evaluated according to the consistency score.

In an optional implementation of this embodiment, the evaluation submodule is further specifically used to determine whether the number of consistency scores that meet the preset one-time standard meets the consistency passing standard within a set time;

If so, it is determined that the voltage of the battery module to be tested satisfies the consistency assessment.

The battery module voltage consistency assessment device provided in the embodiment of the present invention can execute the battery module voltage consistency assessment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

Embodiment 4

Figure 5 is a structural schematic diagram of a battery module voltage consistency evaluation device provided in Embodiment 4 of the present invention. As shown in Figure 5, the battery module voltage consistency evaluation device includes a processor 50, a memory 51, an input device 52 and an output device 53; the number of processors 50 in the battery module voltage consistency evaluation device may be one or more, and Figure 5 takes one processor 50 as an example; the processor 50, memory 51, input device 52 and output device 53 in the battery module voltage consistency evaluation device may be connected via a bus or other means, and Figure 5 takes connection via a bus as an example.

The memory 51, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions/modules corresponding to the voltage consistency evaluation method of the battery module in the embodiment of the present invention (for example, the attribute parameter acquisition module 410, the moment voltage determination module 420 and the consistency evaluation module 430 in the voltage consistency evaluation device of the battery module). The processor 50 executes various functional applications and data processing of the voltage consistency evaluation device of the battery module by running the software programs, instructions and modules stored in the memory 51, that is, realizes the voltage consistency evaluation method of the battery module mentioned above.

The memory 51 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 51 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 51 may further include a memory remotely arranged relative to the processor 50, and these remote memories may be connected to a voltage consistency evaluation device of the battery module via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The input device 52 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the battery module voltage consistency evaluation device. The output device 53 may include a display device such as a display screen.

Embodiment 5

Embodiment 5 of the present invention further provides a storage medium including computer executable instructions, wherein the computer executable instructions are used to execute a method for evaluating the consistency of voltage of a battery module when executed by a computer processor, the method comprising:

Acquire at least one attribute parameter of the battery module to be tested in at least two time periods; each of the time periods includes at least one moment;

Inputting each attribute parameter in different time periods into a pre-trained regression forest model respectively, and obtaining at least one voltage at a time corresponding to each time period;

A state sequence corresponding to each time period is generated according to the voltage at each moment, and the consistency of the voltage of the battery module to be tested is evaluated according to each state sequence.

Of course, the computer executable instructions of a storage medium including computer executable instructions provided in an embodiment of the present invention are not limited to the method operations described above, and can also execute related operations in the battery module voltage consistency evaluation method provided in any embodiment of the present invention.

Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk or an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

It is worth noting that in the embodiment of the above-mentioned battery module voltage consistency evaluation device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims (7)

1. A method for evaluating the consistency of voltage of a battery module, comprising: Obtain at least one attribute parameter of the battery module to be tested in at least two time periods; each of the time periods includes at least one moment; wherein the attribute parameter includes at least one of the following: time, charging ratio SOC, charging state, temperature and voltage; Inputting each attribute parameter in different time periods into a pre-trained regression forest model respectively, and obtaining at least one voltage at a time corresponding to each time period; Generating a state sequence corresponding to each time period according to the voltage at each time moment, and evaluating the consistency of the voltage of the battery module to be tested according to each state sequence; The step of generating a state sequence corresponding to each time period according to the voltage at each time moment includes: obtaining a state code corresponding to the voltage at each time moment of the target time period, and forming a state sequence corresponding to the target time period according to each state code; The evaluation of the consistency of the voltage of the battery module to be tested according to each of the state sequences includes: calculating the similarity between every two state sequences, and calculating the consistency score of the voltage of the battery module to be tested according to each similarity calculation result; and evaluating the consistency of the voltage of the battery module to be tested according to the consistency score. 2. The method according to claim 1, characterized in that before inputting the attribute parameters in different time periods into the pre-trained regression forest model respectively, it also includes: Obtain at least one attribute parameter of multiple normal battery modules; Preprocessing each of the attribute parameters, and dividing each of the attribute parameters into a training set and a test set according to a set ratio; The regression forest model is obtained by training according to the training set and the test set. 3. The method according to claim 1, characterized in that the step of obtaining the state code corresponding to the voltage at each moment in the target time period comprises: If the voltage at the target moment is within the preset voltage confidence interval, the status code corresponding to the voltage at the target moment is 1, otherwise it is 0. 4. The method according to claim 1, characterized in that the step of evaluating the consistency of the voltage of the battery module to be tested according to the consistency score comprises: Determine within a set time whether the number of consistency scores that meet the preset one-time standard meets the consistency passing standard; If so, it is determined that the voltage of the battery module to be tested satisfies the consistency assessment. 5. A battery module voltage consistency assessment device, comprising: The attribute parameter acquisition module is used to acquire at least one attribute parameter of the battery module to be tested in at least two time periods; each of the time periods includes at least one moment; wherein the attribute parameter includes at least one of the following: time, charging ratio SOC, charging state, temperature and voltage; A moment voltage determination module is used to input various attribute parameters in different time periods into a pre-trained regression forest model to obtain at least one moment voltage corresponding to each time period; A consistency evaluation module, used to generate a state sequence corresponding to each time period according to the voltage at each time moment, and evaluate the consistency of the voltage of the battery module to be tested according to each state sequence; The consistency evaluation module includes: a state sequence generation submodule, which is used to obtain the state code corresponding to the voltage at each moment in the target time period, and form a state sequence corresponding to the target time period according to each state code; The consistency evaluation module includes: an evaluation submodule, which is used to calculate the similarity between every two state sequences, and calculate the consistency score of the voltage of the battery module to be tested according to each similarity calculation result; and evaluate the consistency of the voltage of the battery module to be tested according to the consistency score. 6. A battery module voltage consistency evaluation device, characterized in that the battery module voltage consistency evaluation device comprises: 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 method for evaluating the voltage consistency of a battery module as described in any one of claims 1 to 4. 7. A storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute the voltage consistency evaluation method of a battery module as described in any one of claims 1 to 4 when executed by a computer processor.