Battery health state assessment method and battery health state assessment device

Abstract

The invention relates to the technical field of battery evaluation, in particular to a battery health state evaluation method and a battery health state evaluation device. The battery health state evaluation method comprises the following steps: collecting complete charging data of charging a battery from a lower limit voltage to an upper limit voltage in different battery health states, wherein the complete charging data comprises the battery voltage, the battery temperature, the environment temperature and the charging current; constructing a battery health estimation model according to a corresponding relation between data nodes in the complete charging data and different battery health states; and collecting effective data of a real-time charging stroke of the vehicle, and transmitting the effective data to the battery health estimation model to calculate a real-time battery health state value. According to the method, online estimation of the SOH of the vehicle and recognition of abnormal attenuation of the SOH of the battery can be achieved, and online estimation of the charging curve and the SOH of the battery can be achieved on the basis of part of charging intervals in the charging process.

Description

Technical Field

[0001] The present application relates to the technical field of battery evaluation, and in particular to a battery health status evaluation method and a battery health status evaluation device. Background Art

[0002] As new energy vehicles continue to penetrate the Chinese automotive market, users are increasingly demanding higher standards for their performance, safety, and service life. Furthermore, as new energy vehicles from earlier generations of the market gradually retire, the reuse of power batteries is becoming a key focus for both the government and the industry. To meet these two requirements, accurately assessing the current health of power batteries is essential. The state of health (SOH) of a power battery is a key indicator for evaluating its performance. It reflects the degree of battery performance degradation. Accurate SOH estimation and prediction can provide a more reliable range prediction for the vehicle, helping to optimize the estimation and strategy of other key battery states and extend the battery's service life.

[0003] In the related art, the evaluation of SOH in pure electric vehicles mainly focuses on the indicator of battery capacity attenuation, that is, the SOH is calculated by the full charge capacity of the battery in its current state and the nominal capacity of the new battery. However, in the actual use of the vehicle, the calculation of SOH in the related art is relatively difficult. Because SOH requires the complete charging process of the vehicle from the lower limit voltage to the upper limit voltage to calculate, but in the actual use of the vehicle, the process of charging from the lower limit voltage to the upper limit voltage rarely occurs. Usually, charging starts at a certain point voltage, and it is not a complete charging process. It is difficult to accurately calculate the full charge capacity of the battery in its current state through only part of the charging interval, which makes it impossible to achieve online estimation of SOH. Summary of the Invention

[0004] In related technologies, it is difficult to accurately calculate the full charge capacity of the battery in its current state using only a partial charging interval, resulting in the inability to achieve online estimation of the battery's health status.

[0005] In a first aspect, an embodiment of the present application provides a battery health status assessment method, characterized in that the battery health status assessment method includes:

[0006] Collect complete charging data of the battery from the lower limit voltage to the upper limit voltage under different battery health states, wherein the complete charging data includes battery voltage, battery temperature, ambient temperature, and charging current;

[0007] Build a battery health estimation model based on the correspondence between data nodes in the complete charging data and different battery health states;

[0008] Collect the effective data of the vehicle's real-time charging journey and transmit the effective data to the battery health estimation model to calculate the real-time battery health status value.

[0009] In conjunction with the first aspect, in one embodiment, building a battery health estimation model based on the correspondence between data nodes in the complete charging data and different battery health states includes:

[0010] Preprocessing and position encoding of complete charging data;

[0011] A time series regression model is constructed and associated with the preprocessed complete charging data to obtain a battery health estimation model.

[0012] In conjunction with the first aspect, in one embodiment, preprocessing and position encoding the complete charging data includes:

[0013] Reconstructing the charging process based on the voltage data in the complete charging data to obtain a reconstructed first complete charging state matrix;

[0014] The first complete state-of-charge matrix is ​​position-encoded.

[0015] In conjunction with the first aspect, in one embodiment, reconstructing the charging process based on the voltage data in the complete charging data includes:

[0016] Calculate the relationship curve between the charging capacity and time of each charging process in the complete charging data;

[0017] The complete charging data is divided into multiple voltage intervals V, and the charging capacity corresponding to each voltage point in the voltage interval V is calculated based on the relationship curve between the charging amount and time. The calculation formula is as follows:

[0018]

[0019] Among them, Q(t) is the amount of electricity charged into the battery at time t, V min is the lower limit voltage of the voltage interval V, V max is the upper limit voltage of the voltage interval V;

[0020] A first complete state of charge matrix is ​​obtained according to the corresponding relationship between each voltage point in the voltage interval V and the battery temperature, the ambient temperature and the charging capacity.

[0021] In combination with the first aspect, in one embodiment, obtaining a first complete state of charge matrix according to the correspondence between each voltage point in the voltage interval V and the battery temperature, the ambient temperature, and the charging capacity further includes:

[0022] When a voltage node vi in ​​the voltage interval V does not have corresponding battery temperature, ambient temperature, and charging capacity data, the battery temperature, ambient temperature, and charging capacity data corresponding to point vi are calculated based on the linear difference between the corresponding states of the two voltage nodes adjacent to the voltage node vi.

[0023] In conjunction with the first aspect, in one embodiment, position encoding the first complete state of charge matrix includes:

[0024] Normalizing the first complete state-of-charge matrix to obtain a second complete state-of-charge matrix;

[0025] The second complete state-of-charge matrix is ​​sliced ​​using a sliding window, and each window after slicing is constructed as a time series input and the charging capacity reconstructed after each complete charging process in each window is the target sequence;

[0026] Perform positional encoding on each temporal input and target sequence.

[0027] In conjunction with the first aspect, in one embodiment, constructing a time series regression model and associating the time series regression model with the preprocessed complete charging data includes:

[0028] Build a time series regression model based on the encoder and decoder;

[0029] Define the loss function of the time series regression model;

[0030] The time series input of the second complete state of charge matrix is ​​used as the input of the time series regression model, and the back propagation mechanism is used to screen out the model parameter state with the smallest loss as the battery health estimation model.

[0031] In conjunction with the first aspect, in one embodiment, preprocessing the complete charging data includes:

[0032] Reconstructing the charging process based on the battery state of charge data in the complete charging data to obtain a reconstructed first complete state of charge matrix;

[0033] The first complete state-of-charge matrix is ​​position-encoded.

[0034] In conjunction with the first aspect, in one embodiment, collecting valid data of the vehicle's real-time charging trip and transmitting the valid data to a battery health estimation model to calculate a real-time battery health status value includes:

[0035] The real-time charging data of the vehicle, in which the battery voltage, charging current, battery temperature, ambient temperature and charging time during the charging process are all within the preset effective thresholds, is regarded as valid data;

[0036] Convert valid data into n real-time time series inputs through a sliding window, and input the n real-time time series inputs into the battery health estimation model to obtain n battery health status calculation results;

[0037] The n battery health status calculation results are screened to obtain an array y of valid calculation results. The screening formula is:

[0038] y∈[Q1-1.5ω*IQR,Q3ω+1.5*ωIQR]

[0039] Where Q1 is the 25% quantile of the n calculation results, Q3 is the 75% quantile of the n calculation results, and IQR is the difference between Q3 and Q1;

[0040] Calculate the average of all valid calculation results in array y, and use the average of the three most recent valid calculation results as the battery health status value.

[0041] In a second aspect, an embodiment of the present application provides a battery health status assessment device, comprising:

[0042] A test data collection module is used to collect complete charging data of the battery from the lower limit voltage to the upper limit voltage under different battery health states. The complete charging data includes battery voltage, battery temperature, ambient temperature, and charging current;

[0043] A model building module is used to build a battery health estimation model based on the correspondence between data nodes in the complete charging data and different battery health states;

[0044] The evaluation module is used to collect effective data of the vehicle's real-time charging journey and transmit the effective data to the battery health estimation model to calculate the real-time battery health status value

[0045] The beneficial effects of the technical solutions provided in the embodiments of the present application include:

[0046] The present invention proposes a data-driven battery SOH estimation method, which establishes a model based on the correspondence between data nodes in the complete charging data and different battery health states, and then inputs the battery status transmitted back during the vehicle's real-time charging process into the model to obtain the corresponding battery health state, thereby realizing an online estimation of the vehicle's SOH and an identification of abnormal battery SOH attenuation. This method can realize online estimation of the battery's complete charging curve and SOH based on partial charging intervals during the charging process. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A flowchart of the battery health status assessment method for this application;

[0048] Figure 2This is the architecture diagram of the time series regression model for this application;

[0049] Figure 3 A schematic diagram of the battery health status assessment process during vehicle driving in this application;

[0050] Figure 4 This is a schematic diagram of the hardware structure of the battery health status assessment device involved in the embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] In related technologies, it is difficult to accurately calculate the full charge capacity of the battery in its current state using only a partial charging interval, resulting in the inability to achieve online estimation of the battery's health status.

[0053] First, as Figure 1 and Figure 3 As shown, the present application provides a battery health status assessment method, which includes the following steps:

[0054] Step S1: Collect complete charging data of a battery charged from a lower voltage limit to an upper voltage limit under different battery health states, wherein the complete charging data includes battery voltage, battery temperature, ambient temperature, and charging current.

[0055] Specifically, step S1 includes obtaining complete charging data of the power battery under different health conditions under an actual charging icon or model on a test bench (i.e., the process of charging from the lower limit voltage Vmin to the upper limit voltage Vmax of the battery). The complete charging data includes battery voltage V, charging current I, battery temperature T1, ambient temperature T2, and SOC (state of charge).

[0056] Step S2: construct a battery health estimation model based on the correspondence between data nodes in the complete charging data and different battery health states.

[0057] Specifically, the above step S2 includes:

[0058] Step a: pre-process and position encode the complete charging data.

[0059] Furthermore, the present application provides two optional embodiments for step a:

[0060] In a first embodiment, step a includes: reconstructing the charging process based on the voltage data in the complete charging data to obtain a reconstructed first complete charge state matrix, and then performing position encoding on the first complete charge state matrix.

[0061] In a second embodiment, step a includes reconstructing the charging process based on the SOC data (battery state of charge data) in the complete charging data to obtain a reconstructed first complete state of charge matrix, and then position encoding the first complete state of charge matrix.

[0062] It's worth noting that for batteries in the fast-charging process, the charging current can fluctuate significantly depending on battery temperature, SOC, and other conditions, causing voltage rebound. Therefore, voltage-based data reconstruction is not suitable in this situation. For full-charge, however, reconstruction can be based on voltage or SOC, depending on the specific application. If the slow-charging current is constant, with no significant fluctuations, and no voltage rebound, voltage-based reconstruction is recommended.

[0063] Furthermore, the first implementation of step a specifically includes:

[0064] Step a1: Calculate the charging capacity.

[0065] Specifically, the relationship curve between the amount of charge and time in each charging process in the complete charging data is calculated, and the calculation formula is as follows:

[0066]

[0067] Where Q(t) is the amount of electricity charged into the battery at time t, I is the current at time t, and △t is the sampling time step.

[0068] Step a2: Divide the complete charging data into multiple voltage intervals V.

[0069] Specifically, the voltage interval [V min ,V ma x] is divided into N+1 equal parts, that is, [vmin,vmin+△v,vmin+2*△v,...,vmax], where △V=(Vmax-Vmin) / N. Here, the voltage array after equal division is recorded as V=[v0,v1,...,vN].

[0070] Step a3: Calculate the charging capacity corresponding to each voltage point in the voltage range V based on the relationship curve between the charging amount and the time. The calculation formula is as follows:

[0071]

[0072] Among them, Q(t) is the amount of electricity charged into the battery at time t, V min is the lower limit voltage of the voltage interval V, V max is the upper limit voltage of the voltage range V.

[0073] Step a4: Obtain a first complete charge state matrix based on the corresponding relationship between each voltage point in the voltage interval V in the complete charging data and the battery temperature, ambient temperature and charging capacity.

[0074] Specifically, based on the collected complete charging data, the battery temperature T1 = [t0, t1, ..., tN], the ambient temperature A = [a0, a1, ..., aN] and the charging capacity corresponding to each voltage point V = [v0, v1, ..., vN] are constructed to obtain the first complete charge state matrix H = [V; Q; T; A], and the matrix H is:

[0075]

[0076] It is worth noting that in the above step a4, there will be a situation where the complete charging data sampled cannot be found to correspond to v i The status of each moment (battery temperature, ambient temperature and charging capacity data).

[0077] Preferably, when the above situation occurs that each state cannot be found, the voltage node v i The voltage node v is calculated by the linear difference of the corresponding states of two adjacent voltage nodes i The battery temperature, ambient temperature and charging capacity data corresponding to the point.

[0078] In some specific embodiments, if the i-th voltage in the voltage interval V is 3.56V, then it is necessary to obtain v i =Battery charging capacity q at 3.56V i , battery temperature t i and ambient temperature a i However, at this time, since there is no v in the original data sampling process i =3.56V, so the corresponding charging capacity q cannot be directly obtained i , battery temperature t i and ambient temperature a i At this time, it is necessary to perform a linear difference between the two states corresponding to 3.55V and 3.57V closest to 3.56V to obtain the voltage node v i The corresponding charging capacity q i , battery temperature t i and ambient temperature a i .

[0079] Step a5: Normalize each column of the first complete state of charge matrix H according to the following formula to obtain a normalized second complete state of charge matrix S. The formula is as follows:

[0080]

[0081] Among them, h ij is the element in the first complete state of charge matrix, u j is the average value of the column where the element is located in the first complete charge state matrix, σ j is the standard deviation of the column where the element in the first complete state of charge matrix is ​​located. It is worth noting that normalizing the first complete state of charge matrix H can simplify the subsequent calculation process.

[0082] Step a6: Slice the second complete state of charge matrix using a sliding window, and construct each window after slicing as a time series input X and the charging capacity reconstructed after each complete charging process in each window as a target sequence Y.

[0083] Specifically, step a6 includes:

[0084] The second complete charge state matrix S = [V; Q; T; A], the second complete charge state matrix S is a tensor with a shape of (N+1,4). S is split with a sliding window of fixed width L, and each window after splitting is recorded as x i ,in,

[0085] Each x i is a tensor of shape (L, 4). The total number of N-L+2 windows divided is denoted as X, where X is a tensor of shape (N-L+2, L, 4). Each window after segmentation is represented by the following matrix:

[0086] (where i = 0, 1, 2..., N-L+1)

[0087] The second column of battery capacity q is processed. The processing includes subtracting q1 from each value of the battery capacity q in the second column, as shown in the subordinate matrix 2.

[0088]

[0089] (where i = 0, 1, 2..., N-L+1)

[0090] Among them, each time series input x constructed i , and its corresponding training target sequence y i The battery capacity after each complete charge process.

[0091] Step a7: Enter x for each time series according to the formula i, and its corresponding training target sequence y i Perform position encoding.

[0092] Specifically, the encoding formula in step a7 above is as follows:

[0093]

[0094] Where k represents the kth row in the matrix x, and i represents the ith column in the matrix x. i And the training target sequence y are added with their corresponding encoding positions respectively.

[0095] Step b: construct a time series regression model, and associate the time series regression model with the preprocessed complete charging data to obtain a battery health estimation model.

[0096] Specifically, the above step b includes:

[0097] Step b1: Build a time series regression model based on the encoder and decoder.

[0098] Specifically, the encoder-decoder architecture is established as follows Figure 2 The temporal regression model shown. The encoder layer input is the temporal input x i , timing input x i After n layers of encoding operations, the result e i Passed to the decoding layer, the decoding layer input is [xi; p0] and the result of the encoder layer e i , where p0 is a full 0 proof of shape (N+1,4), pred indicates the length of the sequence to be predicted, and after m decoding operations, the result d i Pass it to a fully connected layer to output the prediction result.

[0099] Preferably, the encoder is composed of multiple encoding operations. In each encoding operation, the time sequence input x i First, the self-attention mechanism is operated, and then the 1D convolutional network is performed. The decoder in the above is composed of multiple decoding operations. i First perform self-attention operation, and then i Perform cross-attention operation.

[0100] Step b2: Define the loss function of the time series regression model.

[0101] Specifically, MSE is used as the loss function of the model, and its formula is as follows:

[0102]

[0103] Step b3: Input x with the timing of the second complete charge state matrix S i As the input of the time series regression model, the back propagation mechanism is used to screen out the model parameter state with the smallest loss as the battery health estimation model.

[0104] In some preferred embodiments, the above-mentioned step b3 also includes: optimizing and correcting the battery health estimation model, and the correction process includes: after obtaining the complete charging process status of the vehicle during vehicle maintenance, the data will be input into the model to evaluate the loss of the model. When the loss is higher than the set value lmax, the historical data will be brought into the model for training and fine-tuning.

[0105] It is worth noting that the historical data includes the test data collected in step S1 or the charging data during the vehicle's driving. At the same time, the battery health estimation model is deployed in the cloud, which can receive real-time data from the vehicle.

[0106] Step S3: Collect valid data of the vehicle's real-time charging journey, and transmit the valid data to the battery health estimation model to calculate the real-time battery health status value.

[0107] Specifically, the above step S3 includes:

[0108] Step S3a: The charging data of the vehicle in real-time charging process, in which the battery voltage, charging current, battery temperature, ambient temperature and charging time are all within the preset effective threshold value, is regarded as effective data.

[0109] It's worth noting that while testing a battery's SOH is relatively easy under laboratory conditions, in practice, battery operating conditions can vary widely, such as temperature and charging rate. These factors can affect the battery's capacity and performance, leading to discrepancies between laboratory test results and actual SOH. Therefore, in step S3a above, the vehicle's real-time charging data is filtered and then transmitted back to the cloud for processing and calculation.

[0110] Step S3b: After inputting the valid data into the cloud, the valid data is converted into n real-time time series inputs through a sliding window, and the n real-time time series inputs are input into the battery health estimation model to obtain n battery health status calculation results.

[0111] Specifically, step S3b includes: the cloud reconstructs the valid data uploaded by the vehicle using the resampling method described in step S2. Then, using a sliding window method, it is converted into n inputs identical to xi (n is related to the length of the data collected during charging). These are then fed into the model to obtain n battery health status calculation results. The average of the m valid ones is taken to obtain the current battery health status of the vehicle. The centralized valid calculation result y is defined as y∈[Q1ω-ω1.5ω*IQR,Q3ω+1.5*IQR]

[0112] Where Q1 is the 25th percentile of the n results, Q3 is the 75th percentile of the n results, and IQR = Q3 - Q1. Finally, the average of the vehicle's three most recent battery health status calculation results is taken as the final real-time battery health status calculation result fed back to the vehicle in the cloud.

[0113] In a second aspect, an embodiment of the present application also provides a battery health status assessment device.

[0114] In one embodiment, the battery health status assessment device includes: a test data collection module, a model building module and an assessment module; wherein,

[0115] The test data collection module is used to collect complete charging data of the battery from the lower limit voltage to the upper limit voltage under different battery health states. The complete charging data includes battery voltage, battery temperature, ambient temperature, and charging current. The model construction module is used to construct a battery health estimation model based on the correspondence between data nodes in the complete charging data and different battery health states. The evaluation module is used to collect valid data of the vehicle's real-time charging journey and transmit the valid data to the battery health estimation model to calculate the real-time battery health state value.

[0116] Among them, the functional implementation of each module in the above-mentioned battery health status assessment device corresponds to the various steps in the above-mentioned battery health status assessment method embodiment, and their functions and implementation processes are not repeated here one by one.

[0117] In a third aspect, an embodiment of the present application provides a battery health status assessment device, which may be a device with data processing capabilities, such as a personal computer (PC), a laptop computer, or a server.

[0118] Reference Figure 4 , Figure 4 Schematic diagram of the hardware structure of the battery health status assessment device involved in the embodiment of the present application. In the embodiment of the present application, the battery health status assessment device may include a processor, a memory, a communication interface and a communication bus.

[0119] The communication bus may be of any type and is used to interconnect the processor, memory, and communication interface.

[0120] Communication interfaces include input / output (I / O) interfaces, physical interfaces, and logical interfaces, which interconnect components within an AAAA device and connect the AAAA device to other devices (such as other computing devices or user devices). Physical interfaces can include Ethernet, fiber, or ATM interfaces; user devices can include displays and keyboards.

[0121] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0122] The processor may be a general-purpose processor that can call the AAAA program stored in the memory and execute the AAAA method provided in the embodiments of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the AAAA program is called can refer to the various embodiments of the AAAA method of the present application and will not be repeated here.

[0123] Those skilled in the art will understand that Figure 4 The hardware structure shown in the figure does not constitute a limitation to the present application and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0124] In a fourth aspect, an embodiment of the present application also provides a readable storage medium.

[0125] The readable storage medium of the present application stores a battery health status assessment program, wherein when the battery health status assessment program is executed by a processor, the steps of the battery health status assessment method as described above are implemented.

[0126] Among them, the method implemented when the battery health status assessment program is executed can refer to the various embodiments of the battery health status assessment method of this application, and will not be repeated here.

[0127] In summary, the present invention proposes a data-driven battery SOH estimation method, which establishes a model based on the correspondence between the data nodes in the complete charging data and different battery health states, and then inputs the battery status transmitted back during the real-time charging process of the vehicle into the model to obtain the corresponding battery health state, thereby realizing an online estimation of the vehicle SOH and an identification method of abnormal battery SOH attenuation. This method can realize online estimation of the battery completion charging curve and SOH based on partial charging intervals during the charging process.

[0128] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0129] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device to execute the methods described in each embodiment of the present application.

[0130] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit the "first", "second" and "third" to different types.

[0131] In the description of the embodiments of this application, the words "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0132] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0133] In some processes described in the embodiments of the present application, multiple operations or steps are included that appear in a specific order. However, it should be understood that these operations or steps may not be performed in the order in which they appear in the embodiments of the present application or may be performed in parallel. The sequence numbers of the operations are only used to distinguish between different operations, and the sequence numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations or steps may be performed in sequence or in parallel, and these operations or steps may be combined.

[0134] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A battery health status assessment method, characterized in that: The battery health status assessment method comprises: Collect complete charging data of the battery from the lower limit voltage to the upper limit voltage under different battery health states, wherein the complete charging data includes battery voltage, battery temperature, ambient temperature, and charging current; A battery health estimation model is constructed based on the correspondence between data nodes in the complete charging data and different battery health states; Collect the effective data of the vehicle's real-time charging journey, and transmit the effective data to the battery health estimation model to calculate the real-time battery health status value.

2. The battery health status assessment method according to claim 1, characterized in that: The battery health estimation model is constructed according to the correspondence between the data nodes in the complete charging data and different battery health states, including: Preprocess and position encode the complete charging data; A time series regression model is constructed and associated with the preprocessed complete charging data to obtain a battery health estimation model.

3. The battery health status assessment method according to claim 2, characterized in that: The preprocessing and position encoding of the complete charging data includes: Reconstructing the charging process based on the voltage data in the complete charging data to obtain a reconstructed first complete charging state matrix; The first complete state-of-charge matrix is ​​position-encoded.

4. The battery health status assessment method according to claim 3, characterized in that: The reconstructing the charging process based on the voltage data in the complete charging data includes: Calculate the relationship curve between the charging capacity and time of each charging process in the complete charging data; The complete charging data is divided into multiple voltage intervals V, and the charging capacity corresponding to each voltage point in the voltage interval V is calculated according to the relationship curve between the charging amount and time. The calculation formula is as follows: Where Q(t) is the amount of electricity charged into the battery at time t, V min is the lower limit voltage of the voltage interval V, V max is the upper limit voltage of the voltage interval V; A first complete charging state matrix is ​​obtained according to the corresponding relationship between each voltage point in the voltage interval V and the battery temperature, the ambient temperature and the charging capacity.

5. The battery health status assessment method according to claim 4, characterized in that: The first complete charging state matrix is ​​obtained according to the corresponding relationship between each voltage point in the voltage interval V and the battery temperature, the ambient temperature and the charging capacity, and further includes: When a voltage node vi in ​​the voltage interval V has no corresponding battery temperature, ambient temperature and charging capacity data, the battery temperature, ambient temperature and charging capacity data corresponding to point vi are calculated based on the linear difference of the corresponding states of the two voltage nodes adjacent to the voltage node vi.

6. The battery health status assessment method according to claim 3, characterized in that: The position encoding of the first complete charge state matrix comprises: Normalizing the first complete state-of-charge matrix to obtain a second complete state-of-charge matrix; The second complete state-of-charge matrix is ​​sliced ​​using a sliding window, and each window after slicing is constructed as a time series input and the charging capacity reconstructed after each complete charging process in each window is a target sequence; Positional encoding is performed on each temporal input and target sequence.

7. The battery health status assessment method according to claim 6, characterized in that: The step of constructing a time series regression model and associating the time series regression model with the preprocessed complete charging data includes: Build a time series regression model based on the encoder and decoder; Define the loss function of the time series regression model; The time series input of the second complete state of charge matrix is ​​used as the input of the time series regression model, and the back-propagation mechanism is used to screen out the model parameter state with the smallest loss as the battery health estimation model.

8. The battery health status assessment method according to claim 7, characterized in that: The method collects the effective data of the vehicle's real-time charging trip and transmits the effective data to the battery health estimation model to calculate the real-time battery health status value, including: The charging data of the vehicle in real-time charging process, in which the battery voltage, charging current, battery temperature, ambient temperature and charging time are all within the preset effective threshold value, is regarded as effective data; Convert valid data into n real-time time series inputs through a sliding window, and input the n real-time time series inputs into a battery health estimation model to obtain n battery health status calculation results; The n battery health status calculation results are screened to obtain an array y of valid calculation results, and the screening formula is: y∈[Q1-1.5*IQR,Q3+1.5*IQR] Where Q1 is the 25% quantile of the n calculation results, Q3 is the 75% quantile of the n calculation results, and IQR is the difference between Q3 and Q1; Calculate the average of all valid calculation results in array y, and use the average of the three most recent valid calculation results as the battery health status value.

9. The battery health status assessment method according to claim 2, characterized in that: The preprocessing and position encoding of the complete charging data includes: Reconstructing the charging process based on the battery state of charge data in the complete charging data to obtain a reconstructed first complete state of charge matrix; The first complete state-of-charge matrix is ​​position-encoded.

10. A battery health status assessment device, characterized in that: The battery health status assessment device comprises: A test data collection module, which is used to collect complete charging data of the battery from the lower limit voltage to the upper limit voltage under different battery health states, wherein the complete charging data includes battery voltage, battery temperature, ambient temperature, and charging current; A model building module, which is used to build a battery health estimation model based on the correspondence between data nodes in the complete charging data and different battery health states; The evaluation module is used to collect valid data of the vehicle's real-time charging journey and transmit the valid data to the battery health estimation model to calculate the real-time battery health status value.

Images