CN114280485B - SOC estimation and consistency evaluation method, device, computer equipment - Google Patents

Abstract

The embodiment of the invention provides a method, a device and computer equipment for SOC estimation and consistency estimation, wherein the method comprises the following steps: acquiring SOC estimation data acquired at a plurality of acquisition moments of each single battery in the power battery; sending the SOC estimation data of the single battery at each acquisition time to a pre-trained SOC estimation model to obtain an SOC estimation sequence of each single battery at a plurality of acquisition times; acquiring the charging state of the single battery corresponding to each acquisition time to obtain a charging state sequence; correcting the SOC estimation sequence of the single battery according to the SOC estimation sequence and the charging state sequence of the single battery to obtain a corrected SOC estimation sequence of the single battery; and determining an SOC estimated value of the power battery and a consistency estimated result of each single battery based on the corrected SOC estimated sequence of each single battery in the power battery. And (3) considering the change rule of the SOC in each charging state, obtaining a more accurate SOC estimation result, and pre-warning fault hidden danger according to the result estimation consistency.

Description

SOC estimation and consistency evaluation method, device, computer equipment

technical field

The embodiments of the present invention relate to the technical field of batteries, and in particular to a method, device, and computer equipment for SOC estimation and consistency evaluation.

Background technique

The battery state of charge (State of Charge, SOC) is used to reflect the remaining capacity of the battery. It is numerically defined as the ratio of the remaining capacity to the battery capacity, and is often expressed as a percentage. The battery SOC cannot be measured directly, and its size can only be estimated by parameters such as the battery terminal voltage, charge and discharge current, and internal resistance. These parameters will also be affected by various uncertain factors such as battery aging, ambient temperature changes, and vehicle driving conditions. Therefore, accurate SOC estimation has become an urgent problem to be solved in the development of electric vehicles.

Currently, the existing battery SOC estimation methods mainly include the ampere-hour integration method, the open circuit voltage method, the Kalman filter method, and the data-driven method. The ampere-hour integral method calculates the change of the electric quantity by integrating the current and time of the charging and discharging process, and estimates the SOC in combination with the available capacity. This method ignores the influence of changes inside the battery and does not consider the influence of battery aging; the data-driven method is based on The learning algorithm establishes the mapping relationship between the feature and the SOC based on the battery feature data to estimate the SOC. The model training of this method requires a large amount of feature data, and the parameter adjustment of the model is cumbersome, and for the data with large measurement errors, the measurement is accurate. The open-circuit voltage method estimates the SOC through the mapping relationship between the voltage and the SOC of the battery under long-term static conditions. The estimation conditions of this method are relatively harsh, and the application scenarios have certain limitations. Ignore the SOC fluctuation change law of the battery under different charging states.

Contents of the invention

The embodiment of the present invention proposes a SOC estimation and consistency evaluation method, device, computer equipment, and storage medium, so as to be able to accurately estimate the SOC of the monomer under any working conditions, and perform consistency evaluation according to the SOC of the monomer. Evaluate.

In the first aspect, an embodiment of the present invention provides a SOC estimation and consistency assessment method, including:

Obtain the SOC estimation data collected by each single battery in the power battery at several collection moments;

For each single battery, the SOC estimation data of the single battery at each collection time is sent into the pre-trained SOC estimation model to obtain the SOC estimation data of each single battery at several collection moments The SOC estimation sequence composed of the SOC estimation value;

Acquiring the state of charge of the single battery corresponding to each collection moment, so as to obtain a sequence of state of charge of the single battery;

correcting the SOC estimation sequence of the single battery according to the SOC estimation sequence of the single battery and the state of charge sequence, to obtain a corrected SOC estimation sequence of the single battery;

The estimated SOC value of the power battery and the consistency evaluation result of each single battery are determined based on the corrected SOC estimation sequence of each single battery in the power battery.

In the second aspect, the embodiment of the present invention also provides a method and device for SOC estimation and consistency assessment, including:

The parameter acquisition module is used to obtain the SOC estimation data collected by each single battery in the power battery at several collection moments;

The estimation sequence generation module is used for sending the SOC estimation data of the single battery at each collection time into the pre-trained SOC estimation model for each single battery, so as to obtain the SOC estimation data of each single battery The SOC estimation sequence composed of the SOC estimation values of the body battery at several acquisition moments;

A charge state acquisition module, configured to obtain the state of charge of the single battery corresponding to each collection moment, so as to obtain a sequence of state of charge of the single battery;

An estimation sequence correction module, configured to correct the SOC estimation sequence of the single battery according to the SOC estimation sequence of the single battery and the state of charge sequence, to obtain a corrected SOC estimation of the single battery sequence;

A result generating module, configured to determine the estimated SOC value of the power battery and the consistency evaluation result of each single battery based on the corrected SOC estimation sequence of each single battery in the power battery.

In a third aspect, an embodiment of the present invention also provides a computer device, the computer device comprising:

one or more processors;

memory 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 are made to implement the method for SOC estimation and consistency evaluation as described in the first aspect.

The embodiment of the present invention obtains the SOC estimation data collected by each single battery in the power battery at several collection moments; for each single battery, the SOC estimation data of the single battery at each collection moment is sent to the pre-trained The SOC estimation model of the single battery is obtained to obtain the SOC estimation sequence composed of the SOC estimated value of each single battery at several collection moments; the corresponding charge state of the single battery at each collection moment is obtained to obtain the charge state sequence of the single battery ; Correct the SOC estimation sequence of the single battery according to the SOC estimation sequence and the charging state sequence of the single battery to obtain the corrected SOC estimation sequence of the single battery; determine the power battery based on the corrected SOC estimation sequence of each single battery in the power battery The SOC estimation value of the battery and the consistency evaluation results of each single battery. The embodiment of the present invention can carry out accurate SOC estimation and consistency evaluation in the whole life cycle of the battery, and by considering the battery aging and the change law of SOC in different charging states and other actual conditions, it can be more accurate at the point where the measurement error is large. Accurate estimation, and evaluate the consistency of the power battery according to the SOC estimation result of the monomer, and give an alarm when the consistency is higher than the warning threshold, so as to give early warning of potential failure of the power battery.

Description of drawings

FIG. 1 is a flow chart of a SOC estimation and consistency evaluation method provided by Embodiment 1 of the present invention;

Fig. 2 is a flow chart of a method for correcting the SOC estimation sequence of the single battery according to the SOC estimation sequence and the state-of-charge sequence of the single battery according to Embodiment 1 of the present invention;

FIG. 3 is a schematic structural diagram of an SOC estimation and consistency evaluation device provided in Embodiment 2 of the present invention;

FIG. 4 is a schematic structural diagram of a computer device provided by Embodiment 3 of the present invention.

Detailed ways

The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention. In addition, it should be noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings but not all structures.

Embodiment one

Figure 1 is a flowchart of a SOC estimation and consistency assessment method provided by Embodiment 1 of the present invention. This embodiment can accurately estimate the SOC of the monomer under any working conditions, and evaluate the consistency according to the SOC of the monomer. To evaluate, the method can be performed by an SOC estimation and consistency evaluation device, the SOC estimation and consistency evaluation device can be implemented by software and/or hardware, and can be configured in a computer device, such as a server, a personal computer, etc. , including the following steps:

Step 101. Obtain SOC estimation data collected by each single battery in the power battery at several collection times.

The power battery is a power source that provides power for tools, and is mostly used in batteries that provide power for electric vehicles, electric trains, electric bicycles, and golf carts. The power battery contains a number of single cells. The single cells are connected in series and parallel, plus some control units, acquisition systems, and cooling systems to form a complete power battery.

SOC estimation data is characteristic data for estimating the SOC of a cell, at least including reporting time, cell voltage, state of charge, cell temperature, accumulated mileage, current, etc.

The collection time is a set sampling point with the same interval duration within a preset period, which is used to regularly collect the SOC estimation data of several equally spaced points in a period to estimate the SOC within the preset period .

Obtain the SOC estimation data collected by each single battery in the power battery at different collection times.

Exemplarily, a power battery contains 50 single cells, a preset cycle is 1 day, and the SOC estimation data of each single cell is collected every 3 minutes within 1 day, so 50 single cells can be obtained in 1 day The SOC estimation data corresponding to each single battery at 480 collection times, that is to say, 24,000 SOC estimation data can be obtained in one day.

It should be noted that the number of collection times and the number of single cells in one cycle in the above-mentioned embodiment are exemplary descriptions of the embodiments of the present invention. In other embodiments of the present invention, the number of collection times and the number of single cells in one cycle There may also be other different setting methods for the number of bulk batteries, which is not limited in the present invention.

Step 102, for each single battery, send the SOC estimation data of the single battery at each collection time into the pre-trained SOC estimation model, and obtain the composition of the SOC estimation value of each single battery at several collection time SOC estimation sequence.

The collected sample data set is divided into a training set and a test set by a certain ratio, the SOC estimation model is pre-trained using the training set, and the parameters of the model are adjusted using the test set to obtain a pre-trained SOC estimation model.

Before sending the SOC estimation data of a single battery at each collection moment into the pre-trained SOC estimation model, the data needs to be preprocessed to remove missing values and outliers in the data.

Exemplarily, the embodiment of the present invention adopts the XGboost estimation model, divides the pre-collected sample data into a training set and a test set according to a ratio of 7:3, uses the training set to perform model training on the XGboost estimation model, and uses the test set Adjust the parameters of the model to obtain a pre-trained SOC estimation model, which can obtain a rough SOC estimation value based on the SOC estimation data of a single battery at a certain moment.

Exemplarily, the data is preprocessed first, the estimated SOC data containing abnormal cell voltage is eliminated according to the normal operating voltage range, and the estimated SOC data containing abnormal cell temperature is eliminated according to the 3σ criterion. After the preprocessing is completed, the SOC estimation data of multiple single batteries at each acquisition time in one cycle are sent to the pre-trained XGboost estimation model to obtain the SOC estimation values of multiple batteries at each acquisition time.

Send the estimated SOC data of a single battery at several acquisition moments within a preset period into the XGboost estimation model to obtain an estimated SOC value, and these estimated SOC values form the SOC estimation sequence of the single battery within the preset period.

Exemplarily, the SOC estimation data of a certain battery at 480 collection moments in one day are sent to the XGboost estimation model to obtain corresponding 480 SOC estimation values, and these 480 SOC estimation values constitute the SOC estimation of the single battery within one day sequence. If a power battery contains 50 single cells, 50 SOC estimation sequences are generated.

It should be noted that the XGboost estimation model used in the above embodiments and the 3σ criterion used in the process of eliminating missing values and outliers are exemplary descriptions of the embodiments of the present invention. In other embodiments of the present invention, it is also possible to use In the estimation model, other theoretical criteria can be used in the process of eliminating missing values and outliers, such as LightGBM algorithm and lasso algorithm, which are not limited in the present invention.

Step 103 , acquiring the charging state corresponding to each collection time of the single battery, so as to obtain the charging state sequence of the single battery.

The single battery is divided into three different charging states, which are uncharged state, parking charging state, and charging completion state. Different charging states are distinguished through a pre-specified encoding method, and the encodings of the charging states of a single battery at each collection time within a preset period are combined to obtain the charging state sequence of the battery.

Exemplarily, the state of charge adopts a One-Hot encoding method, and a three-dimensional vector is used to represent the state of charge of a single battery, wherein it is specified that the uncharged state is (1, 0, 0), and the parking state is (0, 1, 0 ), the charging completion status is (0, 0, 1).

It should be noted that the One-Hot encoding method and encoding rules used in the above embodiments are exemplary descriptions of the embodiments of the present invention. In other embodiments of the present invention, other encoding methods or encoding rules can also be used. The rules differentiate charging states, which is not limited in the present invention.

Step 104 , correcting the SOC estimation sequence of the single battery according to the SOC estimation sequence and the charging state sequence of the single battery, to obtain the corrected SOC estimation sequence of the single battery.

In actual situations, due to the influence of battery aging, charging state, etc., there is a certain degree of fluctuation in the acquisition of SOC estimation data, which further leads to SOC estimation values with large errors in the SOC estimation sequence obtained through the SOC estimation model. Therefore, the SOC estimation sequence obtained by the SOC estimation model needs to be further revised to obtain more accurate SOC estimation results.

The state of charge of a single battery is one of the important factors that affect the accuracy of SOC estimation data during collection. When a single battery is discharged, the measured SOC value will decrease; when the single battery is charged, the measured SOC value will increase. . Correcting the SOC estimation sequence of the single battery according to the SOC estimation sequence and the charging state sequence of the single battery can eliminate the influence of the charging state on the SOC estimation value to a certain extent, and the corrected SOC value is a more accurate estimation result.

In some embodiments of the present invention, step 104 includes:

Step 1041, performing moving average processing on the SOC estimation sequence to obtain a smooth SOC estimation sequence.

The SOC estimation sequence obtained by the SOC estimation model is subjected to sliding average processing, and the moving average is calculated sequentially to eliminate accidental fluctuation factors, smooth out the interference of abnormal values, and obtain a smooth SOC estimation sequence.

Exemplarily, a window with a size of 5 minutes is selected, and all values in the window are arithmetically averaged as the value of the center point of the window, and the window is moved at a point interval of 1 minute, and this averaging method is repeated until the above-mentioned is completed for the entire SOC estimation sequence process.

It should be noted that the window size used in the above embodiment is an exemplary description of the embodiment of the present invention. In other embodiments of the present invention, other values of the window size may also be used, and the present invention is not limited here.

Step 1042, count the number of times of numerical increase and the number of numerical decreases in the smoothed SOC estimation sequence between the i-th acquisition time and the last time when the SOC is corrected. A numerical value is greater than the previous numerical value, and numerical value drop means that the latter numerical value in any adjacent pair of numerical values is smaller than the previous numerical value.

The initial values of the number of times of numerical rise and the number of numerical declines in the smooth SOC estimation sequence are both 0, and the numerical rise means that in the smooth SOC estimation sequence, the SOC estimation value corresponding to the acquisition time i is greater than that corresponding to the previous acquisition time i-1 The estimated value of SOC; the numerical decrease means that in the smoothed SOC estimation sequence, the estimated SOC value corresponding to the acquisition time i is smaller than the estimated SOC value corresponding to the previous acquisition time i-1.

Counting the number of times the value rises and the number of times the value drops in the smoothed SOC estimation sequence between the i-th acquisition time and the last time the SOC is corrected can determine the change trend of the SOC estimate, which is convenient for subsequent SOC adjustments based on the state of charge. Estimated revisions.

In some embodiments of the present invention, step 1042 includes:

Step 10421. Determine whether the estimated SOC value corresponding to the i-th time in the SOC estimation sequence is greater than the estimated SOC value corresponding to the i-1th time; if yes, execute step 10422; if not, execute step 10423.

Judging whether the SOC estimated value corresponding to the i-th time in the SOC estimation sequence is greater than the SOC estimated value corresponding to the i-1-th time, if the SOC estimated value corresponding to the i-th time is greater than the SOC estimated value corresponding to the i-1-th time, then execute the step 10422, accumulatively add 1 to the number of times when the value increases; if the estimated SOC value corresponding to the i-th time is smaller than the estimated SOC value corresponding to the i-1th time, execute step 10423, and add 1 to the number of times when the value decreases.

Exemplarily, the initial values of the times of numerical rise and the number of numerical declines in the smoothed SOC estimation sequence are both 0, and the values of the first 6 acquisition moments are 70, 72, 69, 71, 75, 76 respectively, wherein, the second, The estimated SOC values at the 4th, 5th, and 6th collection times are all greater than the SOC estimates at the previous time, and step 10422 is executed at the 2nd, 4th, 5th, and 6th collection time points to add 1 to the number of times the value increases, so the value increases The number of times is 4; the estimated SOC value at the third moment is less than the estimated SOC value at the previous moment, and at the third acquisition moment, step 10423 is executed to add 1 to the number of times of numerical decline, so the number of numerical declines is 1 time.

It should be noted that the acquisition time and the estimated SOC values in the above embodiments are exemplary descriptions of the embodiments of the present invention. In other embodiments of the present invention, they may also be other values, which are not limited in the present invention. SOC estimates are in %.

Step 10422, add 1 to the number of times the value increases.

Step 10423, add 1 to the number of times the value drops.

Step 1043, determine whether the number of times of numerical rise and the number of numerical declines in the smoothed SOC estimation sequence between the i-th acquisition time and the last time when the SOC is corrected meet the preset SOC correction conditions; if so, execute step 1044 ; If not, execute step 1045 .

The preset SOC correction condition is used to judge the SOC change trend of the smooth SOC estimation sequence between the i-th acquisition time and the last time the SOC is corrected. Correction conditions, the SOC estimated value has a relatively obvious change trend, which may be related to the charge state of the single battery, and step 1044 needs to be executed to further correct the charge state of the single battery, so that the corrected SOC value It is more accurate; when the number of times that the value rises and the number of times that the value drops does not meet the preset SOC correction conditions, then execute step 1045, and use the SOC correction value at the i-1th collection time as the SOC correction value at the i-th collection time, and set the SOC correction value at the i-1th collection time. Accumulatively add 1 to the collection time of i, and return to step 1042.

In some embodiments of the present invention, the preset SOC correction condition is:

The number of times that the numerical value increases is greater than the first preset number of times, or the number of times that the numerical value decreases is greater than the second preset number of times.

When the number of times that the acquired value rises and the number of values decreases satisfies that the number of increases is greater than the first preset number, or the number of decreases is greater than the second preset number, it means that the estimated SOC value has a relatively obvious increase or decrease. The estimated SOC value at the acquisition time is further corrected.

Exemplarily, the first preset number of times is set to 3 times, and the second preset number of times is set to 12 times. Assume that between the 100th acquisition time and the last time when the SOC was corrected (that is, the 90th acquisition time), the number of numerical rises in the smooth SOC estimation sequence is 4 times, and the number of numerical declines is 6 times, which meets the preset requirements. For the SOC correction condition, step 1044 can be executed to correct the SOC corresponding to the 100th collection time according to the state of charge.

It should be noted that the specific values of the first preset number of times and the second preset number of times in the above embodiments are exemplary descriptions of the embodiments of the present invention. In other embodiments of the present invention, they can also be other values. The present invention It is not limited here.

Step 1044: Correct the SOC corresponding to the i-th acquisition time in the smoothed SOC estimation sequence to obtain the SOC correction value, and calculate the number of times the values in the smoothed SOC estimation sequence increase between the i-th acquisition time and the last time the SOC is corrected Set the number of times the sum value drops to 0, add 1 to the cumulative value of the i-th collection time, and return to perform statistics on the number of times the value rises and the number of times the value drops in the smoothed SOC estimation sequence between the i-th collection time and the last time the SOC was corrected .

Combined with the state of charge at the i-th moment, the SOC corresponding to the i-th acquisition time in the smoothed SOC estimation sequence is corrected to reduce the influence of the state of charge on the estimated SOC value obtained by measurement and estimation. The corrected correction values of the single battery at each acquisition time constitute the corrected SOC estimation sequence of the single battery.

After correcting the SOC corresponding to the i-th acquisition time in the smoothed SOC estimation sequence in combination with the state of charge at the i-th time, the number of numerical increases in the smoothed SOC estimation sequence between the i-th acquisition time and the last time the SOC was corrected Set the number of times that the sum value drops to 0, add 1 to the i-th time, enter the next time, execute step 1042, and recalculate the number of times of increase and value drop between the next acquisition time and the time when the SOC is corrected this time The number of times is to prepare for the next correction of the SOC value combined with the state of charge.

It should be noted that when i is 1, the SOC estimated value at the first acquisition time in the smoothed SOC estimation sequence is rounded to obtain the SOC correction value corresponding to the first acquisition time in the corrected SOC estimation sequence.

In some embodiments of the present invention, when the number of times the value increases is greater than the first preset number and the number of times the value decreases is greater than the second preset number, step 1044 includes:

Step 10441 , determine whether the corresponding charging states at the i-th acquisition time and the first m acquisition time in the charging state sequence of the single battery are all parking charging states; if not, execute step 10442 .

In the state of charge sequence of the single battery, determine whether the corresponding charge states at the i-th moment and the m collection moments before the i-th moment are all in the parking charging state, if not all are in the parking charging state, then execute step 10442 to smooth the SOC estimation sequence The SOC estimated value at the i-th time in the sequence is corrected to obtain the SOC correction value corresponding to the i-th acquisition time in the corrected SOC estimation sequence. Among them, m is the preset judgment time length, and the user can adjust the value of m according to actual needs.

Exemplarily, the value of m is preset to be 2, and the No. 5 single battery is currently at the 100th acquisition time. According to the charging state sequence of the No. 5 single battery, it can be known that the 98th collection time is in the parking charging state, and the 99th collection time It is in the parking charging state, and the 100th collection time is in the charging completion state. From this, it is known that the 100th collection time of the No. 5 single battery and the corresponding charging states of the first 2 collection times are not all in the parking charging state. Step 10442 is executed. The SOC estimation value at the 100th acquisition time instant in the smoothed SOC estimation sequence is corrected.

It should be noted that the specific values of i and m in the above embodiments are exemplary descriptions of the embodiments of the present invention. In other embodiments of the present invention, i and m can also be other values, and the present invention is not limited here .

Step 10442: Add the first correction value to the SOC correction value corresponding to the i-1th collection time in the correction SOC estimation sequence to obtain the SOC correction value at the i-th collection time.

The first correction value is a preset difference in order to reduce the influence of the charging state on the SOC estimation value, and the SOC correction value corresponding to the i-1th acquisition time in the correction SOC estimation sequence is added to the first correction value to obtain the correction SOC estimation sequence The SOC correction value corresponding to the i-th acquisition time corrects the error caused by the state of charge to a certain extent.

Exemplarily, the preset first correction value is 1, and it is currently at the 100th collection moment, and the SOC correction value corresponding to the 99th collection moment in the corrected SOC estimation sequence is 75, then the corrected SOC correction value corresponding to the 100th collection moment in the SOC estimation sequence is The SOC correction value is 75+1, which is 76, and thus the corrected SOC correction value at the 100th acquisition time is obtained.

It should be noted that the specific value of the first correction value in the above embodiment is an exemplary description of the embodiment of the present invention. In other embodiments of the present invention, the first correction value can also be other values. Do limited. And the unit of SOC is %.

In some embodiments of the present invention, when the number of times the value increases is greater than the first preset number of times and the number of times the value decreases is less than the second preset number of times, step 1044 includes:

Step 10443, determine whether the charge states corresponding to the i-th moment and the first m collection moments in the cell charge state sequence are all parking charge states; if so, execute step 10444.

In the charge state sequence of the single battery, determine whether the charge states corresponding to the i-th moment and the m collection moments before the i-th moment are all in the parking charging state, if all are in the parking charging state, then perform step 10444 to estimate the smoothed SOC The SOC estimated value at the i-th time in the sequence is corrected to obtain the SOC correction value corresponding to the i-th acquisition time in the corrected SOC estimation sequence. Among them, m is the preset judgment time length, and the user can adjust the value of m according to actual needs.

Exemplarily, the value of m is preset to be 2, and the No. 5 single battery is currently at the 100th acquisition time. According to the charging state sequence of the No. 5 single battery, it can be known that the 98th collection time, the 99th collection time, the 100th collection time They are all in the parking charging state at all times. From this, it is known that the 100th acquisition time of the No. 5 battery cell and the corresponding charging states of the first two acquisition moments are all in the parking charging state. Step 10444 is executed to calculate the smooth SOC estimation sequence. The estimated SOC value at the 100th acquisition time is corrected.

It should be noted that the specific values of i and m in the above embodiments are exemplary descriptions of the embodiments of the present invention. In other embodiments of the present invention, i and m can also be other values, and the present invention is not limited here .

Step 10444: Add the second correction value to the SOC correction value corresponding to the i-1th collection time in the correction SOC estimation sequence to obtain the SOC correction value at the i-th collection time.

The second correction value is a preset difference in order to reduce the influence of the state of charge on the SOC estimation value, and the SOC correction value corresponding to the i-1th acquisition time in the correction SOC estimation sequence is added to the second correction value to obtain the correction SOC estimation sequence The SOC correction value corresponding to the i-th acquisition time can correct the error caused by the charging state to a certain extent.

Exemplarily, the preset second correction value is -1, and it is currently at the 100th collection moment, and the SOC correction value corresponding to the 99th collection moment in the corrected SOC estimation sequence is 75, then the 100th collection moment in the corrected SOC estimation sequence corresponds to The SOC correction value of is 75+(-1), that is, 74, and thus the corrected SOC correction value at the 100th acquisition time is obtained.

It should be noted that the specific value of the second correction value in the above embodiment is an exemplary description of the embodiment of the present invention. In other embodiments of the present invention, the second correction value can also be other values. Do limited. And the unit of SOC is %.

Step 1045, use the SOC correction value at the i-1th collection moment as the SOC correction value at the i-th collection moment, add 1 to the cumulative value of the i-th collection moment, and return to perform statistics on the value rising in the smooth SOC estimation sequence before the i-th collection moment The number of times and the number of times the value drops.

When the times of numerical rise and numerical decline corresponding to the i-th acquisition time in the smooth SOC estimation sequence do not meet the preset SOC correction conditions, the SOC estimated value at the i-th acquisition time is corrected to be equal to the i-th value in the corrected SOC estimation sequence The SOC correction value of -1 collection time is used as the SOC correction value corresponding to the i-th collection time in the corrected SOC estimation sequence, that is, the SOC correction value at the i-th collection time and the SOC correction at the i-1th collection time in the corrected SOC estimation sequence The values are equal. Add 1 cumulatively to the i-th collection time, enter the next collection time, return to step 1042, and continue to count the number of numerical rises and numerical declines in the smoothed SOC estimation sequence before the current collection time.

It should be noted that the correction method for the i-th acquisition time in the above embodiment is an exemplary description of the embodiment of the present invention. In other embodiments of the present invention, other correction methods may also be used, and the present invention is not limited here .

Step 105, based on the corrected SOC estimation sequence of each single battery in the power battery, determine the SOC estimation value of the power battery and the consistency evaluation result of each single battery.

The estimated SOC value of the power battery is the estimated SOC value representing the entire power battery after processing the corrected SOC estimation sequence of multiple single batteries in the power battery. Consistency refers to the situation where the data remains consistent. In a distributed system, it can be understood that the data values in multiple single batteries are consistent.

In some embodiments of the present invention, step 105 includes:

Step 1051 , combining the corrected SOC estimation sequences of several single batteries to form an SOC estimation matrix Y _t×n .

Combine the corrected SOC estimation sequences of all single batteries in the power battery to form an SOC estimation matrix Y _t×n , where t is the number of SOC correction values of a single battery within a preset period T, and n is a power battery Contains the number of single cells. A row of data in the SOC estimation matrix Y _t×n represents the SOC correction value of all single batteries in the power battery at a certain collection time, while a column of data in the SOC estimation matrix Y _t×n represents The SOC correction value of the single battery at each collection time within the preset period.

Exemplarily, there are 480 acquisition moments in a period of 1 day, and there are 50 single batteries in a power battery, then the SOC estimation matrix Y _480×50 is formed, and in the SOC estimation matrix Y _480×50 , there are 50 data in one row , with a total of 480 lines. The first line of data in the SOC estimation matrix Y _t×n represents the SOC correction values of the 50 single batteries in the power battery at the first acquisition moment, while the first row in the SOC estimation matrix Y _t×n The column data represents the SOC correction value corresponding to the 480 acquisition moments of the first single battery within 1 day.

It should be noted that the values of t and n in the above embodiments are exemplary descriptions of the embodiments of the present invention, and may also be other values in other embodiments of the present invention, which are not limited in the present invention.

Step 1052 : Statistically calculate the minimum value of the SOC correction value corresponding to the i-th time in the SOC estimation matrix Y _t×n by row.

Count the minimum value in the current row line by line in the SOC estimation matrix Y _t×n , and record the column number corresponding to the minimum value; that is, count the SOC correction values of several single batteries in the power battery at each moment in the preset cycle minimum value, and record the minimum value corresponding to the serial number of the single battery.

Step 1053, determine the column with the highest occurrence frequency of the minimum value as the target column.

Find the corresponding column number with the most minimum value at all acquisition moments in the preset period, and use the column corresponding to the column number as the target column; that is, find the minimum value of the SOC correction value that occurs at all acquisition moments in the preset period For the single battery with the highest frequency, the corrected SOC estimation sequence of the single battery is used as the target column.

Step 1054: Use the SOC correction estimation sequence corresponding to the single cell in the target column as the SOC sequence of the power battery within a preset period.

The SOC correction estimation sequence corresponding to the single battery with the highest minimum value is used as the SOC sequence of the entire power battery in the preset cycle to represent the SOC estimation of the power battery after correction in this cycle, so that the power battery can be displayed usage.

In some embodiments of the present invention, step 105 includes:

Step 1055 : Statistically calculate the range of t SOC correction values in the SOC estimation matrix Y _t×n by row. Row-by-row statistical SOC estimation matrix Y _t×n The range of the SOC correction value of all single batteries in the power battery at each collection time in the matrix Y _t×n , that is, the maximum SOC correction value and the maximum SOC correction value in each collection time in the matrix Y t×n The smallest SOC correction values are subtracted to obtain the extreme difference at the acquisition time, and there are t extreme differences of SOC correction values in the SOC estimation matrix Y _t×n .

Exemplarily, in the SOC estimation matrix Y _480×50, the range of the SOC correction value at each collection time is counted row by row, and a total of 480 ranges of the SOC correction value are obtained.

It should be noted that the values of t and n in the above embodiments are exemplary descriptions of the embodiments of the present invention, and may also be other values in other embodiments of the present invention, which are not limited in the present invention.

Step 1056, calculate the average value of t ranges.

Calculate the average value of t ranges, and the result obtained represents the consistency of the single battery in the power battery. The higher the value, the worse the consistency of the power battery, and the lower the value, the better the consistency of the power battery. good.

It should be noted that the calculation of the average of the t ranges in the above embodiment is an exemplary description of the embodiment of the present invention. In other embodiments of the present invention, other methods can also be used to obtain the consistency of the power battery. The present invention is not limited here.

Step 1057, judge whether the average value is greater than the preset consistency threshold; if yes, execute step 1058; if not, execute step 1059.

Judging whether the average value is greater than the preset one-time threshold, if the average value is greater than the preset consistency threshold, it means that the consistency of the power battery in the preset cycle does not meet the preset requirements, then execute step 1058 to determine the consistency evaluation result If there is a consistency problem, the power battery may have a potential failure; if the average value is less than or equal to the preset consistency threshold, it means that the consistency of the power battery in the preset cycle meets the preset requirements, then execute step 1059 to determine the consistency evaluation The result is that there is no consistency problem, and the power battery can continue to be used normally.

Exemplarily, the preset consistency threshold is 5%, and the calculated average value is 10%. If the value is greater than 5%, step 1058 is executed to determine that the power battery has a consistency problem, and the consistency of the power battery becomes worse. , the power battery may have a potential failure.

Step 1058, determine that the result of the consistency evaluation is that there is a consistency problem.

When the average value is greater than the preset consistency threshold, it means that the consistency of the power battery becomes worse. The consistency evaluation result shows that there is a consistency problem in the power battery. It is possible that the battery pack in the power battery may have potential failures such as inaccurate SOC estimation. .

In some embodiments of the present invention, when it is determined that there is a consistency problem in the consistency evaluation result, the power battery will issue a consistency alarm until the consistency of the power battery is lower than the preset one-time threshold.

The consistency evaluation of the present invention can greatly pre-warn the consistency failure of the power battery, effectively avoid failures and potential safety hazards for users, enable customers to repair or replace in time, and ensure safety and timeliness.

Step 1059, determine that the result of the consistency evaluation is that there is no consistency problem.

When the consistency evaluation result shows that there is no consistency problem, it means that the consistency of the power battery is good, and the power battery can continue to be used normally.

It should be noted that, for the method embodiment, for the sake of simple description, it is expressed as a series of action combinations, but those skilled in the art should know that the embodiment of the present invention is not limited by the described action sequence, because According to the embodiment of the present invention, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

The embodiment of the present invention obtains the SOC estimation data collected by each single battery in the power battery at several collection moments; for each single battery, the SOC estimation data of the single battery at each collection moment is sent to the pre-trained The SOC estimation model of the single battery is obtained to obtain the SOC estimation sequence composed of the SOC estimated value of each single battery at several collection moments; the corresponding charge state of the single battery at each collection moment is obtained to obtain the charge state sequence of the single battery ; Correct the SOC estimation sequence of the single battery according to the SOC estimation sequence and the charging state sequence of the single battery to obtain the corrected SOC estimation sequence of the single battery; determine the power battery based on the corrected SOC estimation sequence of each single battery in the power battery The SOC estimation value of the battery and the consistency evaluation results of each single battery. The embodiment of the present invention can carry out accurate SOC estimation and consistency evaluation in the whole life cycle of the battery, and by considering the battery aging and the change law of SOC in different charging states and other actual conditions, it can be more accurate at the point where the measurement error is large. Accurate estimation, and evaluate the consistency of the power battery according to the SOC estimation result of the monomer, and give an alarm when the consistency is higher than the warning threshold, so as to give early warning of potential failure of the power battery.

Embodiment two

FIG. 3 is a structural block diagram of an SOC estimation and consistency evaluation device provided in Embodiment 2 of the present invention, which may specifically include the following modules:

A parameter acquisition module 201, configured to acquire SOC estimation data collected by each single battery in the power battery at several collection moments;

The estimation sequence generation module 202 is used for sending the SOC estimation data of the single battery at each collection time into the pre-trained SOC estimation model for each single battery, and obtains the SOC estimation data of each single battery. The SOC estimation sequence composed of the SOC estimation values of the single battery at several collection moments;

A charging state acquiring module 203, configured to acquire the corresponding charging state of the single battery at each collection time, so as to obtain the charging state sequence of the single battery;

An estimation sequence correction module 204, configured to correct the SOC estimation sequence of the single battery according to the SOC estimation sequence and the charge state sequence of the single battery, to obtain a corrected SOC of the single battery estimate sequence;

The result generation module 205 is configured to determine the estimated SOC value of the power battery and the consistency evaluation result of each single battery based on the corrected SOC estimation sequence of each single battery in the power battery.

In some embodiments of the present invention, the estimated sequence modification module 204 includes:

The moving average processing submodule is used to perform sliding average processing on the SOC estimation sequence to obtain a smooth SOC estimation sequence;

The counting submodule of the number of times of rise and fall is used to count the number of times of numerical rise and the number of numerical declines in the smooth SOC estimation sequence between the i-th collection moment and the last time the SOC is revised, and the numerical rise is It means that the latter value in any adjacent pair of values is greater than the previous value, and the said value drop means that the latter value in any adjacent pair of values is smaller than the previous value;

The correction condition judgment sub-module is used to judge whether the number of times of numerical rise and the number of numerical declines in the smoothed SOC estimation sequence meet the preset SOC correction conditions between the i-th acquisition time and the last time when the SOC is corrected ;

The correction sub-module is used to correct the SOC corresponding to the i-th acquisition time in the smoothed SOC estimation sequence to obtain a SOC correction value, and to calculate the time between the i-th acquisition time and the last time when the SOC is corrected. In the smooth SOC estimation sequence, set the number of times of numerical rise and the number of numerical declines to 0, add 1 to the accumulative value of the i-th acquisition time, and return the execution statistics of the smooth SOC estimation between the i-th acquisition time and the last time the SOC was corrected the number of times a value rises and the number of times a value falls in a sequence;

The maintenance sub-module is used to use the SOC correction value at the i-1th collection moment as the SOC correction value at the i-th collection moment, add 1 to the i-th collection moment, and return to the smooth SOC estimation sequence before performing statistics on the i-th collection moment The number of times the value in the middle increases and the number of times the value decreases.

In some embodiments of the present invention, the statistics submodule of the number of rises and falls includes:

A rise and fall judging unit, configured to judge whether the estimated SOC value corresponding to the i-th moment in the SOC estimation sequence is greater than the SOC estimated value corresponding to the i-1th moment;

The number of times of decline unit is used to add 1 to the number of times that the value rises;

The rising times changing unit is used for accumulatively adding 1 to the number of falling times of the value.

In some embodiments of the present invention, the preset SOC correction condition is:

The number of times that the numerical value increases is greater than the first preset number of times, or the number of times that the numerical value decreases is greater than the second preset number of times.

In some embodiments of the present invention, the correction submodule includes:

A state of charge determination unit, configured to determine whether the state of charge corresponding to the i-th acquisition time and the first m acquisition moments in the state of charge sequence of the single battery is a parking state of charge;

The first correction unit is configured to add a first correction value to the SOC correction value corresponding to the i-1th collection time in the correction SOC estimation sequence to obtain the SOC correction value at the i-th collection time.

In some embodiments of the present invention, the correction submodule includes:

A charging state determining unit, configured to determine whether the charging states corresponding to the i-th moment in the battery charging state sequence and the first m collection moments are all parking charging states;

The second correction unit is configured to add a second correction value to the SOC correction value corresponding to the i-1th collection time in the correction SOC estimation sequence to obtain the SOC correction value at the i-th collection time.

In some embodiments of the present invention, the result generation module 205 includes:

The estimation matrix production sub-module is used to combine the corrected SOC estimation sequences of several single batteries to form an SOC estimation matrix Y _t×n , where t is the SOC of a single battery within a preset period T The number of SOC correction values, n is the number of single cells contained in one of the power batteries;

The minimum value statistics sub-module is used to count the minimum value of the SOC correction value corresponding to the i-th moment in the SOC estimation matrix Y _t×n by row;

A target column determination submodule, configured to determine the column with the highest occurrence frequency of the minimum value as the target column;

The power battery SOC estimation sub-module is used to use the target column corresponding to the SOC correction estimation sequence of the single cell as the SOC sequence of the power battery within the preset period.

In some embodiments of the present invention, the result generation module 205 includes:

The extreme difference statistics submodule is used to count the extreme differences of the t SOC correction values in the SOC estimation matrix Y _t×n by row;

The average value calculation sub-module is used to calculate the average value of the t ranges;

Threshold comparison sub-module for judging whether the average value is greater than a preset consistency threshold;

The first result generating submodule is used to determine that the consistency evaluation result indicates that there is a consistency problem;

The second result generation sub-module is configured to determine that there is no consistency problem in the consistency evaluation result.

The SOC estimation and consistency evaluation device provided by the embodiment of the present invention can execute the SOC estimation and consistency evaluation method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

Embodiment three

FIG. 4 is a schematic structural diagram of a computer device provided by Embodiment 3 of the present invention. Figure 4 shows a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in FIG. 4 is only an example, and should not limit the functions and scope of use of this embodiment of the present invention.

As shown in FIG. 4, computer device 12 takes the form of a general-purpose computing device. Components of computer device 12 may include, but are not limited to: one or more processors or processing units 16 , system memory 28 , bus 18 connecting various system components including system memory 28 and processing unit 16 .

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures. These architectures include, by way of example, but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect ( PCI) bus.

Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12 and include both volatile and nonvolatile media, removable and non-removable media.

System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and/or cache memory 32 . Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 4, commonly referred to as a "hard drive"). Although not shown in Figure 4, a disk drive for reading and writing to removable non-volatile disks (e.g. "floppy disks") may be provided, as well as for removable non-volatile optical disks (e.g. CD-ROM, DVD-ROM or other optical media) CD-ROM drive. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including but not limited to an operating system, one or more application programs, other program modules, and program data , each or some combination of these examples may include implementations of network environments. Program modules 42 generally perform the functions and/or methodologies of the described embodiments of the invention.

The computer device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the computer device 12, and/or with Any device (eg, network card, modem, etc.) that enables the computing device 12 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interface 22 . Also, the computer device 12 can also communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN) and/or a public network, such as the Internet) through the network adapter 20 . As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18 . It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.

The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28 , such as implementing the SOC estimation and consistency evaluation methods provided by the embodiments of the present invention.

Embodiment four

Embodiment 4 of the present invention also provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each process of the above-mentioned SOC estimation and consistency assessment method is implemented, and can achieve The same technical effects are not repeated here to avoid repetition.

Wherein, the computer-readable storage medium may include, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any combination thereof. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections with one or more leads, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

Note that the above are only preferred embodiments of the present invention and applied technical principles. 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, rearrangements and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention, and the present invention The scope is determined by the scope of the appended claims.

Claims (8)

1. An SOC estimation and consistency estimation method, comprising:

acquiring SOC estimation data acquired at a plurality of acquisition moments of each single battery in the power battery;

sending the SOC estimation data of each single battery at each acquisition time to a pre-trained SOC estimation model for each single battery to obtain an SOC estimation sequence formed by SOC estimation values of each single battery at a plurality of acquisition times;

acquiring the charging state of the single battery corresponding to each acquisition time to obtain a charging state sequence of the single battery;

Correcting the SOC estimation sequence of the single battery according to the SOC estimation sequence and the charging state sequence of the single battery to obtain a corrected SOC estimation sequence of the single battery;

determining an SOC estimated value of the power battery and a consistency estimated result of each single battery based on a corrected SOC estimated sequence of each single battery in the power battery;

correcting the SOC estimation sequence of the single battery according to the SOC estimation sequence and the charging state sequence of the single battery to obtain a corrected SOC estimation sequence of the single battery, wherein the method comprises the following steps:

carrying out moving average processing on the SOC estimation sequence to obtain a smooth SOC estimation sequence;

counting the number of times of numerical value rising and the number of times of numerical value falling in the smooth SOC estimation sequence between the ith acquisition time and the last time of correcting the SOC, wherein the numerical value rising refers to that the latter numerical value in any adjacent pair of numerical values is larger than the former numerical value, and the numerical value falling refers to that the latter numerical value in any adjacent pair of numerical values is smaller than the former numerical value;

judging whether the number of times of numerical value rising and the number of times of numerical value falling in the smooth SOC estimation sequence meet preset SOC correction conditions or not between the ith acquisition time and the last time of correcting the SOC;

If yes, correcting the SOC corresponding to the ith acquisition time in the smooth SOC estimation sequence to obtain an SOC correction value, setting 0 the number of times of numerical value rising and the number of times of numerical value falling in the smooth SOC estimation sequence between the ith acquisition time and the last time of correcting the SOC, adding 1 to the accumulation of the ith acquisition time, and returning to execute statistics on the number of times of numerical value rising and the number of times of numerical value falling in the smooth SOC estimation sequence between the ith acquisition time and the last time of correcting the SOC;

if not, taking the SOC correction value at the i-1 acquisition time as the SOC correction value at the i acquisition time, adding 1 to the accumulation of the i acquisition time, and returning to the statistics of the number of times of numerical value rise and the number of times of numerical value fall in the smooth SOC estimation sequence before the i acquisition time;

the preset SOC correction conditions are:

the number of numerical rises is greater than a first preset number, or the number of numerical drops is greater than a second preset number.

2. The method of claim 1, wherein the counting the number of numerical increases and the number of numerical decreases in the smoothed SOC estimation sequence between the i-th acquisition time and the time at which the SOC was last corrected, comprises:

Judging whether the SOC estimation value corresponding to the ith moment in the SOC estimation sequence is larger than the SOC estimation value corresponding to the (i-1) th moment or not;

if yes, adding 1 to the number of times of the numerical value rise;

if not, the number of times of the numerical value drop is added by 1.

3. The method of claim 1, wherein when the number of times the value rises is greater than a first preset number of times and the number of times the value falls is greater than a second preset number of times, correcting the SOC corresponding to the i-th acquisition time in the smoothed SOC estimation sequence includes:

determining whether the charging states corresponding to the ith acquisition time and the last m acquisition times in the charging state sequence of the single battery are parking charging states or not;

if not, adding the first correction value to the SOC correction value corresponding to the ith acquisition time in the corrected SOC estimation sequence to obtain the SOC correction value of the ith acquisition time.

4. A method according to claim 1 or 3, wherein when the number of times the value rises is greater than a first preset number of times and the number of times the value falls is less than a second preset number of times, correcting the SOC corresponding to the i-th acquisition time in the smoothed SOC estimation sequence includes:

Determining whether the charging states corresponding to the ith moment and the previous m acquisition moments in the charging state sequence of the single battery are parking charging states or not;

if yes, adding a second correction value to the SOC correction value corresponding to the ith acquisition time in the corrected SOC estimation sequence to obtain the SOC correction value of the ith acquisition time.

5. A method according to any one of claims 1-3, wherein determining an SOC estimate for the power battery based on a modified SOC estimate sequence for each cell in the power battery comprises:

combining the corrected SOC estimation sequences of a plurality of single batteries to form an SOC estimation matrix Y _t×n Wherein T is the number of the SOC correction values of one single battery in a preset period T, and n is the number of the single batteries contained in one power battery;

counting the SOC estimation matrix Y by row _t×n The minimum value of the SOC correction value corresponding to the ith moment in (i);

determining the column with the highest occurrence frequency of the minimum value as a target column;

and taking the SOC correction estimation sequence of the single battery corresponding to the target column as the SOC sequence of the power battery in the preset period.

6. The method of claim 5, wherein determining a uniformity evaluation result for each cell based on a corrected SOC estimation sequence for each cell in the power cell comprises:

Counting the SOC estimation matrix Y by row _t×n The range of t SOC correction values;

calculating the average value of t polar differences;

judging whether the average value is larger than a preset consistency threshold value or not;

if yes, determining that the consistency evaluation result is that a consistency problem exists;

if not, determining that the consistency evaluation result is that the consistency problem does not exist.

7. An SOC estimation and consistency estimation apparatus, comprising:

the parameter acquisition module is used for acquiring SOC estimation data acquired at a plurality of acquisition moments of each single battery in the power battery;

the estimation sequence generation module is used for sending the SOC estimation data of each single battery at each acquisition time into a pre-trained SOC estimation model to obtain an SOC estimation sequence formed by SOC estimation values of each single battery at a plurality of acquisition times;

the charging state acquisition module is used for acquiring the charging state of the single battery corresponding to each acquisition time so as to obtain a charging state sequence of the single battery;

the estimation sequence correction module is used for correcting the SOC estimation sequence of the single battery according to the SOC estimation sequence and the charging state sequence of the single battery to obtain a corrected SOC estimation sequence of the single battery;

The result generation module is used for determining an SOC estimated value of the power battery and a consistency evaluation result of each single battery based on the corrected SOC estimated sequence of each single battery in the power battery;

the SOC estimation and uniformity evaluation apparatus is configured to execute the SOC estimation and uniformity evaluation method of any one of claims 1 to 6.

8. A computer device, the computer device comprising:

one or more processors;

a memory for storing one or more programs,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the SOC estimation and consistency assessment method of any of claims 1-6.