Method, system, electronic device and medium for evaluating health of vehicle battery

Abstract

The application discloses a kind of health condition evaluation method, system, electronic equipment and medium of vehicle battery, wherein evaluation method includes the following steps: obtaining SOH data set of vehicle battery;Normal SOH value and abnormal SOH value are divided from SOH data set;Repair is carried out to abnormal SOH, and the repair SOH value corresponding to abnormal SOH value is obtained;According to the distribution of normal SOH value and repair SOH value, the health condition evaluation result of vehicle battery is obtained.The application is divided from SOH data set normal SOH value and abnormal SOH value, then abnormal SOH value is repaired, and the health condition evaluation result of vehicle battery is obtained based on the data after repair, improve the accuracy of health condition evaluation of vehicle battery, and provide better reference for subsequent operation of vehicle battery.

Description

Technical Field

[0001] This invention belongs to the field of battery health status acquisition technology, and particularly relates to a method, system, electronic device and medium for assessing the health status of automotive batteries. Background Technology

[0002] In the field of battery charging and swapping, batteries need to be repeatedly charged for repeated use, making battery health a key aspect to monitor during operation. Currently, the industry uses different calculation methods to define battery health, all ultimately yielding a value less than 1, representing the battery's health, known as SOH (State of Health). However, anomaly identification of SOH values ​​is currently typically done manually, but the sheer volume of SOH data makes manual identification inefficient. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to overcome the shortcomings of low efficiency in assessing the health status of batteries in the prior art, and to provide a method, system, electronic device and medium for assessing the health status of automotive batteries.

[0004] The present invention solves the above-mentioned technical problems through the following technical solution:

[0005] This invention provides a method for assessing the health status of automotive batteries, comprising the following steps:

[0006] Obtain the SOH dataset for automotive batteries;

[0007] Divide the SOH dataset into normal SOH values ​​and abnormal SOH values;

[0008] The abnormal SOH is repaired to obtain the corresponding repaired SOH value;

[0009] Based on the distribution of normal SOH values ​​and repaired SOH values, the health status assessment results of automotive batteries are obtained.

[0010] In this technical solution, normal and abnormal SOH values ​​are automatically separated from the SOH dataset. Abnormal SOH values ​​are then corrected, and the health status assessment result of the vehicle battery is obtained based on the distribution of the corrected data. This improves the efficiency of vehicle battery health status assessment. Furthermore, correcting abnormal SOH values ​​before conducting the health status assessment improves the accuracy of the results, providing a better reference for subsequent operations of the vehicle battery.

[0011] Preferably, before separating normal and abnormal SOH values ​​from the SOH dataset, the health assessment method for automotive batteries also includes:

[0012] Obtain the dimensionality reduction analysis data corresponding to each SOH value in the SOH dataset to obtain the analysis dataset corresponding to the SOH dataset;

[0013] Determine the number of clusters and principal components of the dataset to be analyzed;

[0014] Cluster the dataset based on the number of clusters and principal components.

[0015] In this technical solution, by obtaining the dimensionality reduction analysis data corresponding to each SOH value, an analysis dataset corresponding to the SOH dataset is obtained. Clustering based on the analysis dataset can improve data processing efficiency. Moreover, by selecting the number of clusters and principal components of the analysis dataset, and clustering the analysis dataset according to the number of clusters and principal components, the accuracy of clustering can be effectively improved, thereby improving the accuracy of classifying normal SOH values ​​and abnormal SOH values ​​based on the clustering results.

[0016] Preferably, the number of clusters and principal components of the dataset to be analyzed are determined, including:

[0017] Candidate components are selected based on the dimensionality reduction analysis data in the dataset.

[0018] Principal components are selected from the candidate components based on the explained variance of the candidate components.

[0019] The dataset was clustered based on the number of clusters and principal components, including:

[0020] Select cluster centers that include principal components and represent the number of clusters.

[0021] Clustering is performed using the cluster center as the cluster center. After clustering, the cluster center of each class is reselected, and the principal component is kept as the cluster center. Then the clustering continues until convergence.

[0022] In this technical solution, principal components are selected based on the explained variance of candidate components, and the principal components are maintained as cluster centers for clustering, which can effectively improve the accuracy of clustering.

[0023] Preferably, normal SOH values ​​and abnormal SOH values ​​are separated from the SOH dataset, including:

[0024] Obtain the distance between a dimensionality reduction analysis data point and its corresponding cluster center, identify the multiple dimensionality reduction analysis data points with the largest corresponding distances as anomalous dimensionality reduction analysis data points, and identify the SOH values ​​corresponding to the anomalous dimensionality reduction analysis data points as anomalous SOH values;

[0025] or,

[0026] Based on the anomaly ratio, abnormal dimensionality reduction analysis data are filtered from each cluster data, and the SOH values ​​corresponding to the abnormal dimensionality reduction analysis data are identified as abnormal SOH values.

[0027] This technical solution provides a specific method for classifying normal and abnormal SOH values ​​based on clustering results. It divides the multiple dimensionality reduction analysis data with the highest dispersion into abnormal dimensionality reduction analysis data, or it filters abnormal dimensionality reduction analysis data from each cluster data according to the abnormality ratio, and then identifies the SOH values ​​corresponding to the abnormal dimensionality reduction analysis data as abnormal SOH values. This can effectively and quickly identify abnormal SOH values ​​from a large number of SOH values.

[0028] Preferably, the abnormal SOH value is repaired to obtain the corresponding repaired SOH value, including:

[0029] The abnormal SOH value is repaired by using the normal SOH value adjacent to the abnormal SOH value to obtain the corresponding repaired SOH value;

[0030] or,

[0031] Obtain at least one backup SOH value corresponding to the abnormal SOH value, and when the backup SOH value is the normal SOH value, repair the abnormal SOH value according to the backup SOH value to obtain the corresponding repaired SOH value of the abnormal SOH value; the abnormal SOH value and the corresponding backup SOH value are obtained according to different calculation methods.

[0032] In this technical solution, abnormal SOH values ​​are repaired based on normal SOH values ​​adjacent to the abnormal SOH values, or based on backup SOH values. This can improve the reliability and accuracy of data repair, thereby ensuring the accuracy of the health status assessment of vehicle batteries.

[0033] Preferably, at least one backup SOH value corresponding to the abnormal SOH value is obtained, and when the backup SOH value is a normal SOH value, the abnormal SOH value is repaired based on the backup SOH value to obtain the corresponding repaired SOH value for the abnormal SOH value, including:

[0034] Obtain the backup SOH value corresponding to the abnormal SOH value;

[0035] When there are two backup SOH values, both of which are normal SOH values, obtain the variation range between the two backup SOH values ​​and the adjacent normal SOH values;

[0036] The smaller of the two variation ranges is selected as the corresponding corrective SOH value for the abnormal SOH value.

[0037] This technical solution provides a specific method for repairing abnormal SOH values ​​based on backup SOH values. When there are two backup SOH values, both of which are normal SOH values, the variation range between the two backup SOH values ​​and the adjacent normal SOH values ​​is obtained. The smaller of the two variation ranges is selected as the corresponding repair SOH value for the abnormal SOH value, which can improve the accuracy of data repair and thus ensure the accuracy of the health status assessment of vehicle batteries.

[0038] Preferably, after obtaining the health status assessment results of the vehicle battery based on the distribution of normal SOH values ​​and repaired SOH values, the following further steps are included:

[0039] Perform targeted operations on vehicle batteries that align with the health status assessment results.

[0040] In this technical solution, the target operations that match the health status assessment results of the vehicle battery are performed on the vehicle battery. This can not only handle abnormalities in a timely manner to avoid safety problems, but also make the best use of the battery and avoid waste of resources.

[0041] The present invention also provides a health status assessment system for automotive batteries, including an acquisition unit, a division unit, a repair unit, and an assessment unit;

[0042] The acquisition unit is used to acquire the SOH dataset for automotive batteries;

[0043] The partitioning unit is used to separate normal SOH values ​​and abnormal SOH values ​​from the SOH dataset;

[0044] The repair unit is used to repair abnormal SOH values ​​and obtain the corresponding repaired SOH values.

[0045] The assessment unit is used to obtain the health status assessment results of the vehicle battery based on the distribution of normal SOH value and repaired SOH value.

[0046] In this technical solution, normal and abnormal SOH values ​​are automatically separated from the SOH dataset. Abnormal SOH values ​​are then corrected, and the health status assessment result of the vehicle battery is obtained based on the distribution of the corrected data. This improves the efficiency of vehicle battery health status assessment. Furthermore, correcting abnormal SOH values ​​before conducting the health status assessment improves the accuracy of the results, providing a better reference for subsequent operations of the vehicle battery.

[0047] Preferably, the acquisition unit is also used to acquire the dimensionality reduction analysis data corresponding to each SOH value in the SOH dataset, so as to obtain the analysis dataset corresponding to the SOH dataset;

[0048] The acquisition unit is also used to determine the number of clusters and principal components of the analysis dataset;

[0049] The acquisition unit is also used to cluster the analysis dataset based on the number of clusters and principal components.

[0050] In this technical solution, by obtaining the dimensionality reduction analysis data corresponding to each SOH value, an analysis dataset corresponding to the SOH dataset is obtained. Clustering based on the analysis dataset can improve data processing efficiency. Moreover, by selecting the number of clusters and principal components of the analysis dataset, and clustering the analysis dataset according to the number of clusters and principal components, the accuracy of clustering can be effectively improved, thereby improving the accuracy of classifying normal SOH values ​​and abnormal SOH values ​​based on the clustering results.

[0051] Preferably, the acquisition unit is also used to filter candidate components based on the dimensionality reduction analysis data in the analysis dataset;

[0052] The acquisition unit is also used to screen principal components from candidate components based on the explained variance of the candidate components;

[0053] The acquisition unit is also used to cluster the analysis dataset based on the number of clusters and principal components, including:

[0054] The acquisition unit is also used to select the number of cluster centers that include principal components;

[0055] The acquisition unit is also used to perform clustering with the cluster center as the cluster center, and after clustering, reselect the cluster center of each class and keep the principal component as the cluster center before continuing to cluster until convergence.

[0056] In this technical solution, principal components are selected based on the explained variance of candidate components, and the principal components are maintained as cluster centers for clustering, which can effectively improve the accuracy of clustering.

[0057] Preferably, the partitioning unit is also used to obtain the distance between a dimensionality reduction analysis data and its corresponding cluster center, identify the multiple dimensionality reduction analysis data with the largest corresponding distance as abnormal dimensionality reduction analysis data, and identify the SOH value corresponding to the abnormal dimensionality reduction analysis data as abnormal SOH value;

[0058] or,

[0059] The partitioning unit is also used to filter out abnormal dimensionality reduction analysis data from each cluster data according to the abnormality ratio, and to identify the SOH value corresponding to the abnormal dimensionality reduction analysis data as abnormal SOH value.

[0060] This technical solution provides a specific method for classifying normal and abnormal SOH values ​​based on clustering results. It divides the multiple dimensionality reduction analysis data with the highest dispersion into abnormal dimensionality reduction analysis data, or it filters abnormal dimensionality reduction analysis data from each cluster data according to the abnormality ratio, and then identifies the SOH values ​​corresponding to the abnormal dimensionality reduction analysis data as abnormal SOH values. This can effectively and quickly identify abnormal SOH values ​​from a large number of SOH values.

[0061] Preferably, the repair unit is also used to repair the abnormal SOH value based on the normal SOH value adjacent to the abnormal SOH value, so as to obtain the repaired SOH value corresponding to the abnormal SOH value;

[0062] or,

[0063] The repair unit is also used to obtain at least one backup SOH value corresponding to the abnormal SOH value, and when the backup SOH value is a normal SOH value, to repair the abnormal SOH value according to the backup SOH value, thereby obtaining the repaired SOH value corresponding to the abnormal SOH value; the abnormal SOH value and the corresponding backup SOH value are obtained according to different calculation methods.

[0064] In this technical solution, abnormal SOH values ​​are repaired based on normal SOH values ​​adjacent to the abnormal SOH values, or based on backup SOH values. This can improve the reliability and accuracy of data repair, thereby ensuring the accuracy of the health status assessment of vehicle batteries.

[0065] Preferably, the repair unit is also used to obtain a backup SOH value corresponding to the abnormal SOH value;

[0066] When there are two backup SOH values, both of which are normal SOH values, the repair unit is also used to obtain the change range between the two backup SOH values ​​and the adjacent normal SOH values.

[0067] The repair unit is also used to select the smaller of the two change ranges as the corresponding repair SOH value for the abnormal SOH value.

[0068] This technical solution provides a specific method for repairing abnormal SOH values ​​based on backup SOH values. When there are two backup SOH values, both of which are normal SOH values, the variation range between the two backup SOH values ​​and the adjacent normal SOH values ​​is obtained. The smaller of the two variation ranges is selected as the corresponding repair SOH value for the abnormal SOH value, which can improve the accuracy of data repair and thus ensure the accuracy of the health status assessment of vehicle batteries.

[0069] Preferably, the evaluation unit is also used to perform target operations on the vehicle battery that match the health status assessment results.

[0070] In this technical solution, the target operations that match the health status assessment results of the vehicle battery are performed on the vehicle battery. This can not only handle abnormalities in a timely manner to avoid safety problems, but also make the best use of the battery and avoid waste of resources.

[0071] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for assessing the health status of a vehicle battery of the present invention.

[0072] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method for assessing the health status of a vehicle battery of the present invention.

[0073] The significant advantages of this invention are: it automatically distinguishes between normal and abnormal SOH values ​​from the SOH dataset, then corrects the abnormal SOH values, and finally obtains the health status assessment result of the vehicle battery based on the distribution of the corrected data, thereby improving the efficiency of vehicle battery health status assessment. Furthermore, correcting abnormal SOH values ​​before conducting the health status assessment improves the accuracy of the assessment results, providing a better reference for subsequent operations of the vehicle battery. Attached Figure Description

[0074] Figure 1 This is a flowchart of a method for assessing the health status of a vehicle battery according to Embodiment 1 of the present invention.

[0075] Figure 2 This is a schematic diagram showing the distribution of each SOH value in the SOH dataset of the vehicle battery health status assessment method of Embodiment 1 of the present invention.

[0076] Figure 3 This is a schematic diagram of the Elbow curve for the vehicle battery health status assessment method of Embodiment 1 of the present invention.

[0077] Figure 4 This is a schematic diagram of the cumulative explained variance and independent explained variance of the SOH dataset for the vehicle battery health status assessment method of Embodiment 1 of the present invention.

[0078] Figure 5 This is a schematic diagram illustrating the division of normal and abnormal values ​​in the health status assessment method for vehicle batteries according to Embodiment 1 of the present invention.

[0079] Figure 6 This is a schematic diagram showing the distribution of repaired data in the vehicle battery health status assessment method of Embodiment 1 of the present invention.

[0080] Figure 7This is a schematic diagram of the electronic device according to Embodiment 3 of the present invention.

[0081] Figure 8 This is a schematic diagram of the health status assessment system for automotive batteries according to Embodiment 5 of the present invention. Detailed Implementation

[0082] The present invention will be further illustrated by way of embodiments below, but the present invention is not limited to the scope of the embodiments described herein.

[0083] Example 1

[0084] This embodiment provides a method for assessing the health status of automotive batteries. (Refer to...) Figure 1 The method for assessing the health status of automotive batteries includes the following steps:

[0085] Step S1: Obtain the SOH dataset for automotive batteries.

[0086] Step S2: Divide the SOH dataset into normal SOH values ​​and abnormal SOH values.

[0087] Step S3: Repair the abnormal SOH and obtain the corresponding repaired SOH value.

[0088] Step S4: Based on the distribution of normal SOH value and repaired SOH value, obtain the health status assessment results of the vehicle battery.

[0089] In specific implementation, firstly, in step S1, the SOH dataset of the vehicle battery is obtained.

[0090] In a battery's SOH dataset, under normal circumstances, it consists of most normal SOH values ​​and some abnormal SOH values. Normal SOH values ​​have similar characteristics, while the characteristics of abnormal SOH values ​​differ greatly from those of normal SOH values. Figure 2 The diagram shows the distribution of SOH values ​​in a SOH dataset, where the horizontal axis represents the SOH value and the vertical axis represents the number of data points corresponding to that SOH value. A large portion of the SOH values ​​in this dataset fall between 0.8 and 1.0, which is consistent with normal SOH values; a small portion falls between 0 and 0.8. It can be determined that this small portion of data contains some outliers.

[0091] To identify outliers, we first obtain the dimensionality reduction analysis data corresponding to each SOH value in the SOH dataset, thus obtaining the analysis dataset corresponding to the SOH dataset.

[0092] Then, determine the number of clusters and principal components of the dataset to be analyzed.

[0093] In practice, the number of clusters and principal components of the dataset can be determined by any algorithm that can determine the number of clusters and principal components of the dataset. This embodiment is not specifically limited, and the algorithm can be selected and adjusted according to actual needs.

[0094] For example, the number of clusters can be determined based on the elbow coefficient method. Figure 3 An Elbow curve is shown. When the number of clusters approaches 6, the curve begins to converge. At this point, the number of clusters can be set to 6.

[0095] Then, principal component analysis was used to analyze the principal components in the dataset and the explained variance of each principal component. Figure 4 The graph shows the cumulative explained variance and independent explained variance of the SOH dataset. The horizontal axis represents the principal components, and the vertical axis represents the explained variance ratio. The broken line in the graph corresponds to the cumulative explained variance, and the rectangular blocks correspond to the independent explained variance. The vertical axis represents the explained variance ratio. According to... Figure 4 As shown, the dataset contains two principal components, each of which explains approximately half of the variance; therefore, both principal components should be retained.

[0096] Having determined the number of clusters and the number of principal components, the next step is to standardize the dataset and perform KMeans clustering. The clustering process includes: selecting cluster centers that include the principal components; clustering using these centers as the cluster centers; reselecting cluster centers for each cluster after clustering, while keeping the principal components as the cluster centers, and continuing clustering until convergence.

[0097] By obtaining the dimensionality reduction analysis data corresponding to each SOH value, an analysis dataset corresponding to the SOH dataset is obtained. Clustering based on the analysis dataset can improve data processing efficiency. Moreover, selecting the number of clusters and principal components of the analysis dataset, and clustering the analysis dataset according to the number of clusters and principal components can effectively improve the accuracy of clustering, thereby improving the accuracy of classifying normal SOH values ​​and abnormal SOH values ​​based on the clustering results.

[0098] Selecting principal components based on the explained variance of candidate components and maintaining the principal components as cluster centers can effectively improve the accuracy of clustering.

[0099] After clustering, normal SOH values ​​and abnormal SOH values ​​are separated from the SOH dataset.

[0100] In a first optional implementation, the distance between a dimensionality reduction analysis data point and its corresponding cluster center is obtained, and the multiple dimensionality reduction analysis data points with the largest corresponding distances are identified as abnormal dimensionality reduction analysis data points, and the SOH values ​​corresponding to the abnormal dimensionality reduction analysis data points are identified as abnormal SOH values.

[0101] In a second alternative implementation, outlier dimensionality reduction analysis data is filtered from each cluster based on the outlier ratio, and the SOH values ​​corresponding to these outlier dimensionality reduction analysis data are identified as outlier SOH values. For example, in one case, the outlier_fraction ratio is set to 1%. This is because, under a standard normal distribution (N(0,1)), data outside three standard deviations are generally considered outliers. Data within three standard deviations contains more than 99% of the data in the dataset, so the remaining 1% can be considered outliers.

[0102] This embodiment provides a specific method for classifying normal and abnormal SOH values ​​based on clustering results. It divides the multiple dimensionality reduction analysis data with the highest dispersion into abnormal dimensionality reduction analysis data, or it filters abnormal dimensionality reduction analysis data from each cluster data according to the abnormality ratio, and then identifies the SOH values ​​corresponding to the abnormal dimensionality reduction analysis data as abnormal SOH values. This can effectively and quickly identify abnormal SOH values ​​from a large number of SOH values.

[0103] Figure 5 The normal and outlier values ​​are shown graphically, with the horizontal axis representing time and the vertical axis representing the corresponding SOH value. The dots are used to indicate that the value belongs to an outlier SOH value.

[0104] Then, the abnormal SOH values ​​are repaired to obtain the corresponding repaired SOH values.

[0105] In one optional implementation, the abnormal SOH value is corrected based on the normal SOH value adjacent to the abnormal SOH value to obtain the corresponding corrected SOH value. The normal SOH value of a battery ranges from 0.8 to 1, and its trend is a slow decrease over time. Therefore, in one optional implementation, the nearest normal SOH value to the location of the abnormal SOH value can be selected as the corrected SOH value.

[0106] In this embodiment, the abnormal SOH value is repaired based on the normal SOH value adjacent to the abnormal SOH value, or based on the backup SOH value, which can improve the reliability and accuracy of data repair, thereby ensuring the accuracy of the health status assessment of the vehicle battery.

[0107] After correcting the abnormal SOH values, the health status assessment results of the vehicle battery are obtained based on the distribution of normal SOH values ​​and corrected SOH values. Figure 6 The distribution of the repaired data is shown, where the horizontal axis represents time and the vertical axis represents the SOH value corresponding to the data.

[0108] Furthermore, based on the health status assessment results of the vehicle battery, target operations matching the health status assessment results are performed on the vehicle battery. Only by correcting abnormal SOH values ​​can the battery be restored to a state closest to its healthy condition, allowing for a more accurate determination of whether the battery can continue to be used.

[0109] For example, if the SOH distribution after repair is all between 0.8 and 1, then the battery's health is normal and it can continue to be used. If a large number of SOH values ​​are below 0.8, then the battery has clearly aged and can be discarded (scrapped) or used as a battery in other areas (converted to an energy storage battery), and no longer used as a car battery. Performing targeted operations on vehicle batteries based on the health status assessment results, matching the assessment results, can both promptly address anomalies to prevent safety issues and maximize resource utilization to avoid waste.

[0110] The vehicle battery health status assessment method in this embodiment automatically distinguishes between normal and abnormal SOH values ​​from the SOH dataset, then corrects the abnormal SOH values, and finally obtains the vehicle battery health status assessment result based on the distribution of the corrected data, thereby improving the efficiency of vehicle battery health status assessment. Furthermore, correcting abnormal SOH values ​​before conducting the health status assessment improves the accuracy of the results, providing a better reference for subsequent vehicle battery operations.

[0111] Example 2

[0112] This embodiment provides a method for assessing the health status of a vehicle battery. This method is largely the same as the method for assessing the health status of a vehicle battery in Embodiment 1, the difference being the step of repairing abnormal SOH values.

[0113] In one optional implementation, during repair, at least one backup SOH value corresponding to the abnormal SOH value is obtained. When the backup SOH value is a normal SOH value, the abnormal SOH value is repaired based on the backup SOH value to obtain the repaired SOH value corresponding to the abnormal SOH value. The abnormal SOH value and the corresponding backup SOH value are obtained according to different calculation methods. Specifically, the backup SOH value corresponding to the abnormal SOH value is obtained; when there are two backup SOH values, both of which are normal SOH values, the variation range between the two backup SOH values ​​and the adjacent normal SOH values ​​is obtained; the smaller of the two variation ranges is selected as the repaired SOH value corresponding to the abnormal SOH value.

[0114] In one optional implementation, the health status of the vehicle battery is assessed based on the SOH dataset formed by SOH1 (i.e., integral capacity / rated capacity * percentage), and SOH2 (i.e., integral capacity / rated capacity * percentage) and SOH3 (i.e., integral capacity / available capacity * percentage) are used as backup SOH values. If both SOH2 and SOH3 values ​​corresponding to the abnormal SOH value are normal SOH values, the variation range between the two backup SOH values ​​and the adjacent normal SOH values ​​is obtained; the smaller of the two variation ranges is selected as the corresponding repair SOH value for the abnormal SOH value. In specific implementation, the variation range between the SOH2 value corresponding to the abnormal SOH value and the previous normal SOH2 is calculated and denoted as diff2; at the same time, the variation range between the SOH3 value corresponding to the abnormal SOH value and the previous normal SOH3 is calculated and denoted as diff3. The backup SOH value corresponding to the smaller of diff2 and diff3 is selected as the repair value. If only one of the SOH2 and SOH3 values ​​corresponding to the abnormal SOH value is a normal SOH value, then the backup SOH value is used as the corresponding repair SOH value for the abnormal SOH value. If both the SOH2 and SOH3 values ​​corresponding to the abnormal SOH value are abnormal SOH values, then no repair is performed.

[0115] Similarly, in other optional implementations, if the health status of the vehicle battery is assessed based on the SOH dataset formed by SOH2, then SOH1 and SOH3 are used as backup SOH values; if the health status of the vehicle battery is assessed based on the SOH dataset formed by SOH3, then SOH2 and SOH1 are used as backup SOH values. The methods for repairing abnormal SOH values ​​are as described above and will not be repeated here.

[0116] Repairing abnormal SOH values ​​based on backup SOH values ​​can improve the accuracy of data repair, thereby ensuring the accuracy of health status assessment of automotive batteries.

[0117] In this embodiment, a specific method is provided for repairing abnormal SOH values ​​based on backup SOH values. When there are two backup SOH values, both of which are normal SOH values, the variation range between the two backup SOH values ​​and the adjacent normal SOH values ​​is obtained. The smaller of the two variation ranges is selected as the corresponding repair SOH value for the abnormal SOH value, which can improve the accuracy of data repair and thus ensure the accuracy of the health status assessment of the vehicle battery.

[0118] Example 3

[0119] Figure 7This is a schematic diagram of the structure of an electronic device provided in this embodiment. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the vehicle battery health assessment method of Embodiment 1 or Embodiment 2. Figure 7 The electronic device 30 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0120] The electronic device 30 may be in the form of a general-purpose computing device, such as a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including memory 32 and processor 31).

[0121] Bus 33 includes a data bus, an address bus, and a control bus.

[0122] The memory 32 may include volatile memory, such as random access memory (RAM) 321 and / or cache memory 322, and may further include read-only memory (ROM) 323.

[0123] The memory 32 may also include a program / utility 325 having a set (at least one) of program modules 324, 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 an implementation of a network environment.

[0124] The processor 31 executes various functional applications and data processing by running computer programs stored in the memory 32, such as the vehicle battery health assessment method of Embodiment 1 or Embodiment 2 of the present invention.

[0125] Electronic device 30 can also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). This communication can be performed via input / output (I / O) interface 35. Furthermore, the model-generated device 30 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public network, such as the Internet) via network adapter 36. As shown, network adapter 36 communicates with other modules of the model-generated device 30 via bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0126] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0127] Example 4

[0128] This embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle battery health status assessment method of Embodiment 1 or Embodiment 2.

[0129] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0130] In a possible implementation, the present invention can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the method for assessing the health status of a vehicle battery according to Embodiment 1 or Embodiment 2.

[0131] The program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0132] Example 5

[0133] This embodiment provides a health status assessment system for automotive batteries. (Refer to...) Figure 8 The vehicle battery health status assessment system includes an acquisition unit 201, a division unit 202, a repair unit 203, and an assessment unit 204.

[0134] The acquisition unit 201 is used to acquire the SOH dataset of the vehicle battery; the partitioning unit 202 is used to partition the normal SOH value and abnormal SOH value from the SOH dataset; the repair unit 203 is used to repair the abnormal SOH value and obtain the corresponding repaired SOH value; the evaluation unit 204 is used to obtain the health status evaluation result of the vehicle battery based on the distribution of normal SOH value and repaired SOH value.

[0135] In practice, firstly, unit 201 acquires the SOH dataset of the vehicle battery. Under normal circumstances, the SOH dataset of a battery consists of mostly normal SOH values ​​and some abnormal SOH values. Normal SOH values ​​have similar characteristics, while the characteristics of abnormal SOH values ​​differ significantly from those of normal SOH values. Figure 2 The diagram shows the distribution of SOH values ​​in a SOH dataset, where the horizontal axis represents the SOH value and the vertical axis represents the number of data points corresponding to that SOH value. A large portion of the SOH values ​​in this dataset fall between 0.8 and 1.0, which is consistent with normal SOH values; a small portion falls between 0 and 0.8. It can be determined that this small portion of data contains some outliers.

[0136] To identify outliers, firstly, partitioning unit 202 obtains the dimensionality reduction analysis data corresponding to each SOH value in the SOH dataset, thus obtaining the analysis dataset corresponding to the SOH dataset.

[0137] Then, partitioning unit 202 determines the number of clusters and principal components of the analysis dataset.

[0138] In practice, the number of clusters and principal components of the dataset can be determined by any algorithm that can determine the number of clusters and principal components of the dataset. This embodiment is not specifically limited, and the algorithm can be selected and adjusted according to actual needs.

[0139] For example, the number of clusters in partitioning unit 202 can be determined based on the elbow coefficient method. Figure 3 An Elbow curve is shown. When the number of clusters approaches 6, the curve begins to converge. At this point, the number of clusters can be set to 6.

[0140] Then, the partitioning unit 202 analyzes the principal components in the dataset and the explained variance of each principal component based on principal component analysis. Figure 4 The cumulative explained variance and independent explained variance of the SOH dataset are shown, where the horizontal axis represents the principal components and the vertical axis represents the explained variance rate. According to Figure 4 As shown, the dataset contains two principal components, each of which explains approximately half of the variance; therefore, both principal components should be retained.

[0141] Having determined the number of clusters and the number of principal components, the next step is to divide the dataset into units 202, standardize the dataset, and perform KMeans clustering. The clustering process includes: selecting cluster centers that include the principal components; clustering using these centers as the cluster centers; reselecting cluster centers for each cluster after clustering, while maintaining the principal components as cluster centers, and continuing clustering until convergence.

[0142] By obtaining the dimensionality reduction analysis data corresponding to each SOH value, an analysis dataset corresponding to the SOH dataset is obtained. Clustering based on the analysis dataset can improve data processing efficiency. Moreover, selecting the number of clusters and principal components of the analysis dataset, and clustering the analysis dataset according to the number of clusters and principal components can effectively improve the accuracy of clustering, thereby improving the accuracy of classifying normal SOH values ​​and abnormal SOH values ​​based on the clustering results.

[0143] Selecting principal components based on the explained variance of candidate components and maintaining the principal components as cluster centers can effectively improve the accuracy of clustering.

[0144] After clustering is completed, partitioning unit 202 separates normal SOH values ​​and abnormal SOH values ​​from the SOH dataset.

[0145] In a first optional implementation, the partitioning unit 202 obtains the distance between a dimensionality reduction analysis data and its corresponding cluster center, identifies the multiple dimensionality reduction analysis data with the largest corresponding distance as abnormal dimensionality reduction analysis data, and identifies the SOH value corresponding to the abnormal dimensionality reduction analysis data as an abnormal SOH value.

[0146] In a second optional implementation, the partitioning unit 202 filters out outlier dimensionality reduction analysis data from each cluster based on the outlier ratio, and identifies the SOH values ​​corresponding to the outlier dimensionality reduction analysis data as outlier SOH values. For example, in one case, the outliers_fraction ratio is set to 1%. This is because, under a standard normal distribution (N(0,1)), data outside three standard deviations are generally considered outliers. Data within three standard deviations contains more than 99% of the data in the dataset, so the remaining 1% can be considered outliers.

[0147] This embodiment provides a specific method for classifying normal and abnormal SOH values ​​based on clustering results. It divides the multiple dimensionality reduction analysis data with the highest dispersion into abnormal dimensionality reduction analysis data, or it filters abnormal dimensionality reduction analysis data from each cluster data according to the abnormality ratio, and then identifies the SOH values ​​corresponding to the abnormal dimensionality reduction analysis data as abnormal SOH values. This can effectively and quickly identify abnormal SOH values ​​from a large number of SOH values.

[0148] Figure 5 The normal and outlier values ​​are shown in the diagram. The horizontal axis “Data TimeInteger” represents time, and the vertical axis “SOH1” represents the SOH value corresponding to the data.

[0149] Then, the repair unit 203 repairs the abnormal SOH value and obtains the corresponding repaired SOH value.

[0150] In one optional embodiment, the repair unit 203 repairs the abnormal SOH value based on the normal SOH value adjacent to the abnormal SOH value, thereby obtaining a repaired SOH value corresponding to the abnormal SOH value. The normal SOH value of the battery is distributed between 0.8 and 1, and its trend is a slow decrease during use. Therefore, in one optional embodiment, the nearest normal SOH value to the location of the abnormal SOH value can be selected as the repair value for the abnormal SOH value.

[0151] In this embodiment, the abnormal SOH value is repaired based on the normal SOH value adjacent to the abnormal SOH value, or based on the backup SOH value, which can improve the reliability and accuracy of data repair, thereby ensuring the accuracy of the health status assessment of the vehicle battery.

[0152] After the abnormal SOH value is repaired, the evaluation unit 204 obtains the health status assessment result of the vehicle battery based on the distribution of normal SOH value and repaired SOH value. Figure 6 The distribution of the repaired data is shown, where the horizontal axis represents time and the vertical axis represents the SOH value corresponding to the data.

[0153] Furthermore, the evaluation unit 204 performs target operations on the vehicle battery that match the health status assessment results. Only by correcting abnormal SOH values ​​can the battery's health status be restored to a state closest to its actual condition, allowing for a more accurate determination of whether the battery can continue to be used. For example, if the corrected SOH distribution is between 0.8 and 1, then the battery's health status is normal and it can continue to be used. If a large number of SOH values ​​are below 0.8, the battery is clearly aged and can be discarded or used as a battery elsewhere, no longer suitable for automotive use. Performing target operations on the vehicle battery based on its health status assessment results not only addresses anomalies promptly to prevent safety issues but also maximizes resource utilization and avoids waste.

[0154] The vehicle battery health status assessment system in this embodiment automatically distinguishes between normal and abnormal SOH values ​​from the SOH dataset, then corrects the abnormal SOH values, and finally obtains the vehicle battery health status assessment result based on the distribution of the corrected data, thereby improving the efficiency of vehicle battery health status assessment. Furthermore, correcting abnormal SOH values ​​before conducting the health status assessment improves the accuracy of the results, providing a better reference for subsequent vehicle battery operations.

[0155] Example 6

[0156] This embodiment provides a health status assessment system for automotive batteries. This system is largely the same as the health status assessment system for automotive batteries in Embodiment 5, except that the repair unit 203 performs a repair process on abnormal SOH values.

[0157] In one optional implementation, during repair, the repair unit 203 acquires at least one backup SOH value corresponding to the abnormal SOH value. If the backup SOH value is a normal SOH value, the abnormal SOH value is repaired based on the backup SOH value to obtain a repaired SOH value corresponding to the abnormal SOH value. The abnormal SOH value and the corresponding backup SOH value are obtained according to different calculation methods. Specifically, the repair unit 203 acquires the backup SOH value corresponding to the abnormal SOH value. When there are two backup SOH values, both of which are normal SOH values, the repair unit 203 acquires the variation range between the two backup SOH values ​​and the adjacent normal SOH values. The repair unit 203 selects the smaller of the two variation ranges as the repaired SOH value corresponding to the abnormal SOH value.

[0158] In one optional implementation, the health status of the vehicle battery is assessed based on the SOH dataset formed by SOH1 (i.e., integral capacity / rated capacity * percentage), and SOH2 (i.e., integral capacity / rated capacity * percentage) and SOH3 (i.e., integral capacity / available capacity * percentage) are used as backup SOH values. If both SOH2 and SOH3 values ​​corresponding to the abnormal SOH value are normal SOH values, the repair unit 203 obtains the change range between the two backup SOH values ​​and the adjacent normal SOH values; the repair unit 203 selects the smaller of the two change ranges as the repair SOH value corresponding to the abnormal SOH value. In specific implementation, the repair unit 203 calculates the change range between the SOH2 value corresponding to the abnormal SOH value and the previous normal SOH2, denoted as diff2; at the same time, the repair unit 203 calculates the change range between the SOH3 value corresponding to the abnormal SOH value and the previous normal SOH3, denoted as diff3. The repair unit 203 selects the backup SOH value corresponding to the smaller of diff2 and diff3 as the repair value. If only one of the SOH2 and SOH3 values ​​corresponding to the abnormal SOH value is a normal SOH value, then the repair unit 203 uses the backup SOH value as the corresponding repair SOH value for the abnormal SOH value. If both the SOH2 and SOH3 values ​​corresponding to the abnormal SOH value are abnormal SOH values, then the repair unit 203 does not perform repair.

[0159] Similarly, in other optional implementations, if the health status of the vehicle battery is assessed based on the SOH dataset formed by SOH2, then SOH1 and SOH3 are used as backup SOH values; if the health status of the vehicle battery is assessed based on the SOH dataset formed by SOH3, then SOH2 and SOH1 are used as backup SOH values. The methods for repairing abnormal SOH values ​​are as described above and will not be repeated here.

[0160] In this embodiment, a specific method is provided for repairing abnormal SOH values ​​based on backup SOH values. When there are two backup SOH values, both of which are normal SOH values, the variation range between the two backup SOH values ​​and the adjacent normal SOH values ​​is obtained. The smaller of the two variation ranges is selected as the corresponding repair SOH value for the abnormal SOH value, which can improve the accuracy of data repair and thus ensure the accuracy of the health status assessment of the vehicle battery.

[0161] While specific embodiments of the present invention have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of the present invention is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but all such changes and modifications fall within the scope of protection of the present invention.

Claims

1. A method for assessing the health status of a vehicle battery, characterized in that, Includes the following steps: Obtain the SOH dataset for automotive batteries; The SOH dataset is divided into normal SOH values ​​and abnormal SOH values; The abnormal SOH is repaired to obtain the corresponding repaired SOH value; Based on the distribution of the normal SOH value and the repaired SOH value, the health status assessment result of the vehicle battery is obtained; The step of repairing the abnormal SOH value to obtain the corresponding repaired SOH value includes: The abnormal SOH value is repaired based on the normal SOH value adjacent to the abnormal SOH value to obtain the corresponding repaired SOH value; or, Obtain at least one backup SOH value corresponding to the abnormal SOH value, and when the backup SOH value is a normal SOH value, repair the abnormal SOH value according to the backup SOH value to obtain the corresponding repaired SOH value of the abnormal SOH value; the abnormal SOH value and the corresponding backup SOH value are obtained according to different calculation methods.

2. The method for assessing the health status of a vehicle battery as described in claim 1, characterized in that, Before separating normal and abnormal SOH values ​​from the SOH dataset, the method for assessing the health status of automotive batteries further includes: Obtain the dimensionality reduction analysis data corresponding to each SOH value in the SOH dataset to obtain the analysis dataset corresponding to the SOH dataset; Determine the number of clusters and principal components of the dataset to be analyzed; The analysis dataset is clustered based on the number of clusters and the principal components.

3. The method for assessing the health status of a vehicle battery as described in claim 2, characterized in that, Determining the number of clusters and principal components of the analysis dataset includes: Based on the dimensionality reduction analysis data in the dataset, candidate components are screened. Based on the explained variance of the candidate components, principal components are selected from the candidate components; The step of clustering the analysis dataset based on the number of clusters and the principal components includes: Select the number of cluster centers that include the principal components; Clustering is performed using the cluster center points as the cluster centers. After clustering, the cluster center points of each class are reselected, and the principal components are kept as the cluster center points. Clustering continues until convergence.

4. The method for assessing the health status of a vehicle battery as described in claim 2, characterized in that, The step of dividing the SOH dataset into normal SOH values ​​and abnormal SOH values ​​includes: Obtain the distance between a dimensionality reduction analysis data point and its corresponding cluster center, identify the multiple dimensionality reduction analysis data points with the largest corresponding distances as abnormal dimensionality reduction analysis data points, and identify the SOH values ​​corresponding to the abnormal dimensionality reduction analysis data points as abnormal SOH values; or, Based on the anomaly ratio, abnormal dimensionality reduction analysis data is filtered from each cluster data, and the SOH value corresponding to the abnormal dimensionality reduction analysis data is identified as an abnormal SOH value.

5. The method for assessing the health status of a vehicle battery as described in claim 1, characterized in that, The step of obtaining at least one backup SOH value corresponding to the abnormal SOH value, and when the backup SOH value is a normal SOH value, repairing the abnormal SOH value according to the backup SOH value to obtain the repaired SOH value corresponding to the abnormal SOH value, includes: Obtain the backup SOH value corresponding to the abnormal SOH value; When there are two backup SOH values, both of which are normal SOH values, the variation range between the two backup SOH values ​​and the adjacent normal SOH values ​​is obtained. The smaller of the two changes is selected as the corresponding corrected SOH value for the abnormal SOH value.

6. The method for assessing the health status of a vehicle battery as described in any one of claims 1-5, characterized in that, After obtaining the health status assessment result of the vehicle battery based on the distribution of the normal SOH value and the repaired SOH value, the method further includes: Perform target operations on the vehicle battery that match the health status assessment results.

7. A health status assessment system for automotive batteries, characterized in that, It includes acquisition units, division units, repair units, and evaluation units; The acquisition unit is used to acquire the SOH dataset of the vehicle battery; The partitioning unit is used to partition the SOH dataset into normal SOH values ​​and abnormal SOH values; The repair unit is used to repair the abnormal SOH and obtain the repaired SOH value corresponding to the abnormal SOH value; The evaluation unit is used to obtain the health status evaluation result of the vehicle battery based on the distribution of the normal SOH value and the repaired SOH value; The repair unit is also used to repair the abnormal SOH value based on the normal SOH value adjacent to the abnormal SOH value, so as to obtain the repaired SOH value corresponding to the abnormal SOH value. or, The repair unit is also used to obtain at least one backup SOH value corresponding to the abnormal SOH value, and when the backup SOH value is a normal SOH value, to repair the abnormal SOH value according to the backup SOH value, thereby obtaining the repaired SOH value corresponding to the abnormal SOH value; the abnormal SOH value and the corresponding backup SOH value are obtained according to different calculation methods.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for assessing the health status of a vehicle battery as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for assessing the health status of a vehicle battery as described in any one of claims 1-6.

Images