Method and apparatus for consistency estimation and visualization of power batteries

Abstract

The invention provides a consistency estimation method for a power battery, the power battery is composed of a plurality of battery cells and is used for providing energy for a vehicle, and the estimation method comprises the following steps: detecting the working voltage of each battery cell in the plurality of battery cells in real time during the operation of the vehicle to obtain a first voltage data set of each battery cell; performing first filtering processing on the first voltage data set to retain voltage data corresponding to the working current smaller than a first threshold value so as to obtain a filtered second voltage data set of each battery cell; calculating an energy fraction of each battery cell based on the second voltage data set; and calculating a first consistency score of the power battery based on the calculated energy score of each battery cell. And providing a visual representation of the energy fraction for each cell as a function of a particular variable.

Description

Technical Field

[0001] The present invention relates to the field of electric vehicles, and more particularly to a method and a device for consistency estimation and visualization of a power battery. Background Art

[0002] As global environmental and energy issues become increasingly severe, new energy vehicles have attracted widespread attention due to their advantages of energy saving, high efficiency, low carbon and environmental protection. In recent years, the electric vehicle industry, such as pure electric vehicles and hybrid electric vehicles, has risen rapidly and has become an inevitable trend in the development of the automotive industry. However, there are still some problems that need to be solved in the field of electric vehicle application technology.

[0003] The power battery is one of the core components of electric vehicles, responsible for storing and releasing electrical energy to provide energy for vehicle driving and other vehicle applications, that is, the power battery serves as the power source of the vehicle. Taking the existing lithium-ion (Li-ion) battery as an example, the power battery is usually a battery pack composed of multiple cells in series and / or parallel. Since the single cell is affected by various factors such as process or environment during the production process, there are inevitably differences in internal resistance, capacity, state of charge (SOC) and other aspects between the cells, and this difference will be further aggravated during the use of the battery, resulting in the inability to achieve complete consistency in performance between the cells, that is, the inconsistency of the power battery. Unfortunately, this inconsistency will lead to problems such as reduced vehicle range, damage to the health of the battery pack, and ultimately cause the reliability of the power battery to decrease or even fail prematurely. Therefore, in order to ensure the delivery of high-quality vehicles to users, it is necessary to accurately estimate and evaluate the consistency of the power battery in the early testing stage of the vehicle.

[0004] In view of the above, there is a need for an improved method for estimating and visualizing power battery consistency, and a device for implementing the above method. Summary of the invention

[0005] According to one aspect of the present disclosure, a method for estimating the consistency of a power battery is provided, the method comprising: detecting the operating voltage of each of a plurality of battery cells in real time during operation of a vehicle to obtain a first voltage data set for each battery cell; performing a first filtering process on the first voltage data set to retain voltage data corresponding to an operating current less than a first threshold value, thereby obtaining a filtered second voltage data set for each battery cell; calculating an energy score for each battery cell based on the second voltage data set; and calculating a first consistency score of the power battery based on the calculated energy score for each battery cell.

[0006] According to an embodiment of the present disclosure, obtaining the filtered second voltage data set for each battery cell further includes: performing a second filtering process on the first voltage data set to retain voltage data corresponding to the state of charge (SOC) in a specific interval.

[0007] According to an embodiment of the present disclosure, calculating the energy score of each battery cell includes: transforming the second voltage data set into a frequency domain data set with amplitude; and calculating the energy score of each battery cell based on the corresponding amplitude of the low frequency component in the frequency domain data set.

[0008] According to an embodiment of the present disclosure, wherein calculating the first consistency score of the power battery includes: normalizing the calculated energy score of each battery cell; determining a limit value according to the statistical data of the historical energy score, the limit value includes at least one of the upper limit value and the lower limit value of the energy score; determining the energy score that exceeds the limit value and reaches the second threshold as an outlier; calculating the Euclidean distance between the outlier and the exceeded limit value as the first consistency score. And wherein, using the principal component analysis (PCA) method, the Euclidean distance of the outlier and the additional parameters during operation are subjected to data dimension reduction processing, and the value subjected to data dimension reduction processing is used as the first consistency score; or using a machine learning-based model, based on the Euclidean distance of the outlier and the additional parameters during operation, the first consistency score of the power battery is calculated; wherein the additional parameters include one of the following: the state of charge (SOC) of the power battery, the service life of the power battery, the temperature of the power battery, the resistance of the power battery, or the current mileage of the vehicle.

[0009] According to another aspect of the present disclosure, a visualization method for the consistency of a power battery is provided, comprising: providing a first visualization representation of the energy score of each battery cell as a function of a specific variable based on the energy score calculated by the above-mentioned estimation method; wherein the specific variable is a variable related to the vehicle's mileage or the usage time of the power battery.

[0010] According to an embodiment of the present disclosure, the visualization method further includes: displaying a first decision line in a first visualization representation, wherein the first decision line is determined based on statistical data of historical energy scores; and indicating a battery cell corresponding to a function that exceeds the first decision line and reaches a third threshold as an abnormal battery cell.

[0011] According to another aspect of the present disclosure, a method for estimating the consistency of a power battery based on a vehicle level is provided, comprising: calculating a first consistency score of the power battery of each vehicle respectively for each vehicle among a plurality of vehicles using the same power battery according to the above estimation method; and calculating a second consistency score of the power battery based on the vehicle level based on the first consistency score of the power battery of each vehicle.

[0012] According to another aspect of the present disclosure, a method for visualizing the consistency of power batteries based on the vehicle level is provided, comprising: based on the first consistency score of the power battery of each vehicle calculated according to the above-mentioned estimation method, providing a second visual representation of the first consistency score of the power battery of each vehicle as a function of a specific variable; wherein the specific variable is a variable related to the mileage of each vehicle or the usage time of the power battery of each vehicle.

[0013] According to an embodiment of the present disclosure, the visualization method further includes: displaying a second decision line in a second visualization representation, the second decision line being determined based on statistical data of historical second consistency scores; and indicating a vehicle corresponding to a function that exceeds the second decision line and reaches a fourth threshold as an abnormal vehicle.

[0014] According to another aspect of the present disclosure, a device for estimating the consistency of a vehicle-level power battery is provided, the device comprising: a processor and a memory, in which computer program instructions are stored, wherein when the computer program instructions are executed by the processor, the processor executes the above-mentioned estimation method.

[0015] According to an embodiment of the present disclosure, the apparatus further includes a device for visualizing the consistency of a power battery, the device being configured to provide the above-mentioned first visual representation of the energy score for each battery cell and the above-mentioned second visual representation of the first consistency score of the power battery for each vehicle.

[0016] Based on the above, according to the method for estimating the consistency of the power battery disclosed in the present invention, the consistency of the power battery can be monitored in real time during the operation of the vehicle, and the consistency of the power battery can be evaluated in a more accurate way, thus providing a more efficient and accurate method for estimating the consistency of the power battery. In addition, according to the method for visualizing the consistency of the power battery disclosed in the present invention, a visual chart related to the consistency of the power battery can be provided to the tester or user of the vehicle in real time, so that the person can understand the performance of the vehicle more intuitively, thereby facilitating the testing and acceptance of the power battery of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] These and / or other aspects and advantages of the present disclosure will become more clear and easier to understand from the following detailed description of the embodiments of the present disclosure in conjunction with the accompanying drawings, in which:

[0018] Figure 1 A flow chart of a method for estimating consistency of a power battery according to an embodiment of the present disclosure is shown;

[0019] Figure 2A schematic diagram showing the visualization of the consistency of a power battery according to an embodiment of the present disclosure is shown;

[0020] Figure 3 A schematic diagram for visualizing consistency of power batteries based on vehicle levels according to an embodiment of the present disclosure is shown;

[0021] Figure 4 Another schematic diagram for visualizing consistency of power batteries based on vehicle levels according to an embodiment of the present disclosure is shown;

[0022] Figure 5 Another schematic diagram for visualizing the consistency of power batteries based on vehicle levels according to an embodiment of the present disclosure is shown; and

[0023] Figure 6 is a block diagram illustrating an example of an apparatus for estimating consistency of a power battery according to an embodiment of the present disclosure.

[0024] It should be understood that these drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification, and are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation of the present invention. In addition, in the drawings, the same reference numerals generally represent the same parts or steps. DETAILED DESCRIPTION

[0025] In order to better illustrate the technical solution of the present disclosure, the present disclosure is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be understood that based on the embodiments described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present invention, and the embodiments described herein are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, which are merely illustrative and exemplary, and therefore should not be interpreted as limiting the scope of the present invention.

[0026] In the following, for the purpose of illustration rather than limitation, the present disclosure will mainly use the power battery of an electric vehicle as an example to explain the technical solution of the present disclosure. The electric vehicle herein can broadly refer to a vehicle that at least partially uses electrical energy as a power source, for example, can include pure electric vehicles and hybrid electric vehicles.

[0027] First, the overall technical concept of the present disclosure and the terms involved are explained.

[0028] As mentioned above, the performance indicators of power batteries include the state of charge (SOC), which is usually expressed as the ratio of the remaining capacity currently available in the power battery to its full capacity after being fully charged. Therefore, in some scenarios, SOC can also be simply regarded as the "remaining power" of the vehicle. The user of the vehicle (such as the driver or passenger) will decide whether to recharge the vehicle and the corresponding driving strategy based on the information related to SOC. For this reason, providing users with information about the SOC of the power battery or related parameters in real time is crucial for driving and using the vehicle. In addition, the consistency of SOC between cells is also a key factor affecting the performance and service life of the power battery. It is necessary to accurately estimate the parameters related to SOC.

[0029] At present, the existing SOC estimation method usually adopts the method based on open circuit voltage (OCV), the principle of which is to determine the SOC value according to the detected OCV value of the battery. Taking a single cell as an example, for example, when fully charged (SOC is about 100%), the voltage can reach about 4V, and when fully discharged (SOC is about 0%), the voltage is about 2.4V. Based on this, the OCV values ​​corresponding to the cells at different SOC values ​​can be detected respectively, and then the SOC-OCV curve can be obtained by data fitting. However, due to the heat generated by the battery during use and the influence of the polarization effect of the battery, the voltage of the battery is not stable for a period of time after the charging and discharging stops, resulting in the existing OCV-based SOC estimation. The battery needs to be left to stand for several hours after use before a usable OCV value can be obtained. Therefore, the existing OCV-based estimation method usually measures the OCV value of the power battery / cell when the vehicle is not running (for example, when the vehicle is turned off at night), so that the OCV data obtained in this way is very limited and offline, and the corresponding SOC-OCV curve is inaccurate, making it difficult to reflect the current real power information of the power battery to the user in real time, and it is not conducive to accurately estimating the consistency of the power battery. In addition, since the OCV value needs to be left for a period of time after each charge and discharge of the power battery to wait for the voltage to stabilize, this method is usually very time-consuming.

[0030] In view of this, the present disclosure proposes a method for estimating the consistency of a power battery and a device for implementing the method to solve the above and other problems existing in the existing methods.

[0031] Figure 1 FIG. 1 is a flow chart showing a method for estimating the consistency of a power battery according to an embodiment of the present disclosure. Figure 1 As shown, the exemplary method 100 of the present disclosure may include the following steps:

[0032] In step S101 , the operating voltage of each battery cell among a plurality of battery cells is detected in real time during operation of a vehicle to obtain a first voltage data set of each battery cell.

[0033] Specifically, during the operation of the vehicle refers to the operating state of the vehicle after it is started, for example, the vehicle is driving, charging, or parked but not turned off / powered off, in which the power battery of the vehicle is in a corresponding working state and has a corresponding working voltage / current. During the operation of the vehicle, the current working voltage of each cell in the power battery, such as the discharge voltage when the power battery is discharged or the charging voltage when the power battery is charged, can be detected / measured / read (or other means of directly or indirectly obtaining the voltage) in real time by means of sensors or other suitable types of detection equipment, thereby obtaining a set of voltage values ​​of each cell in a continuous time series as a first voltage data set for further analysis and processing.

[0034] According to the embodiments of the present disclosure, depending on the corresponding application scenario, corresponding time intervals and cycles can be selected for detecting the voltage data of the battery cell, as well as the amount of voltage data to be detected (such as size and / or quantity). For example, for situations where the vehicle state or environmental parameters are relatively stable, a relatively large time interval can be selected to ensure the stability and accuracy of the data. For situations where the vehicle and environment are more complex or are in dynamic change at any time, a relatively small time interval can be selected to ensure the sensitivity of the data and avoid loss of details. In addition, the amount of data that needs to be detected in one cycle can be determined by weighing factors such as the amount of data computation, storage cost, and performance requirements.

[0035] In step S102, the obtained first voltage data set is filtered to obtain a filtered second voltage data set.

[0036] Specifically, after a plurality of voltage data as the first voltage data set is obtained, these data are screened through filtering processing to obtain more effective voltage data.

[0037] For example, according to an embodiment of the present disclosure, a first filtering process is performed on a first voltage data set to retain voltage data corresponding to an operating current less than a first threshold value. Specifically, when the operating current value of the power battery of the vehicle is small, for example, the vehicle may currently be in a low speed, stopped or low power state, and the heat and other adverse effects of the power battery caused by internal resistance are also at an extremely low level. In this case, the corresponding voltage data obtained in real time can also have high stability and accuracy. Based on the above, the above embodiments of the present disclosure can filter the obtained voltage data by limiting the current with a charge / discharge rate less than a specific value (for example, 0.1) to retain the voltage data corresponding to the smaller operating current. In this way, the feasibility of battery consistency estimation using real-time detected operating voltage is realized.

[0038] In addition, as described above, due to factors such as the polarization effect of the power battery, the voltage data has good stability only in a specific interval (such as 30% to 80%) of the SOC, making it have a good correlation with the SOC. Therefore, according to another embodiment of the present disclosure, the first voltage data set can also be subjected to a second filtering process, that is, the detected voltage data is filtered by limiting the range of the SOC to retain the voltage data corresponding to the state of charge (SOC) in the specific interval.

[0039] It can be seen that through the above-mentioned first filtering process and the second filtering process, the detected real-time data can be optimized, so that the optimized real-time voltage data helps to more accurately estimate the state of the battery. In addition, the order of the above-mentioned filtering process is not particularly limited, and the detected voltage data can be filtered in a parallel manner.

[0040] In step S103 , the energy score of each battery cell is calculated based on the filtered second voltage data set.

[0041] Specifically, after the above steps, the operating voltage of each cell in the power battery is measured and collected, and a filtered second voltage data set is obtained, which is a set of voltage data in a time series, corresponding to the voltage value measured for each cell in a specific time period. As mentioned above, the voltage value of the battery / cell can be related to the SOC of the battery / cell and other performance indicators, so the second voltage data set can be used to calculate a score indicating the working condition of each cell.

[0042] In order to quantify the working condition of each cell in the power battery, according to the embodiment of the present disclosure, the following operations can be performed: first, the second voltage data set is transformed into a discrete data set in the frequency domain by, for example, discrete Fourier transform (DFT), and the discrete data set is composed of a group of discrete frequency domain data with corresponding amplitudes. For example, taking cell 1 in the power battery as an example, after the above steps, 100 voltage data (V t1 ,V t2 ,…,V t100 ) as the second voltage data set, and convert the second voltage data set into 100 pixels with corresponding amplitudes (A1, A2, …, A 100 ) frequency domain data set (V f1 ,V f2 ,…,V f100 ), and then filter the high-frequency components of the noise data through an appropriate filter (for example, filter the components with frequencies higher than a certain threshold), and correspondingly obtain the low-frequency components in the frequency domain data set for subsequent processing. For example, select the 25 frequency domain data with the lowest frequencies in the filtered low-frequency components, and use their corresponding amplitudes to calculate the energy score of the battery cell 1 to indicate the working condition of the battery cell 1. For example, according to a preferred embodiment of the present disclosure, the amplitudes of these frequency domain data can be squared and then added (A1 2 +A2 2 +A3 2 +…+A 25 2 ) as the energy score of the battery cell 1. It should be noted that the calculation of the energy score is not limited to the above method. For example, the amplitudes of multiple frequency components or the voltage data in the time domain can be simply added, or their average values ​​can be calculated. Similarly, the energy score of each battery cell in the power battery can be calculated in this way.

[0043] In step S104, a first consistency score of the power battery is calculated based on the calculated energy score of each battery cell.

[0044] Specifically, after the above steps, the energy score of each cell in the power battery is calculated based on the voltage data detected in real time during the operation of the vehicle. On this basis, the difference in energy scores between the cells can be further compared to estimate the consistency of the power battery.

[0045] In order to quantify the working condition of each battery cell in the power battery, according to the embodiment of the present disclosure, the following operations can be performed: first, the energy score of each battery cell is normalized. Specifically, since the voltage data detected in real time may be obtained under various conditions (for example, the above-mentioned filtering conditions), the range of the voltage data under various conditions is unified into a limited interval by performing normalization processing, so as to avoid excessive numerical differences under different conditions and adversely affect the overall evaluation results, so that the performance and stability of the evaluation model are relatively high. In addition, the limit value is determined according to the statistical data of the historical energy score. For example, according to sufficient historical test data and / or usage data collected for the same model of power battery, the upper and lower limits of the energy score corresponding to the battery cell within the normal working range can be determined, so that the energy score exceeding the upper or lower limit can be determined as an abnormal value, and the battery cell corresponding to the abnormal value is an abnormal battery cell. For example, the statistical data of the historical energy score is represented in quartiles, and the maximum value of the quartile (Q max ) and minimum value (Q min ) as the above limit value, and in order to ensure the rigor of the data, the value exceeding Q max or Q min The energy scores reaching a certain threshold are determined as outliers (X), that is, the range of the limit value is appropriately increased, for example, the traditional quartile Q max or Q min They can be expressed as interquartile range (IQR) + / - k*IQR, where parameter k = 1.5. The limit value is calculated by appropriately increasing the value of k (such as 1.7) to more strictly determine the outliers. After determining the outliers in the energy scores of all cells, the Euclidean distance between the outliers and the corresponding limit values ​​they exceed is calculated, that is, the distance of outliers (DOO) for the power battery, which can be expressed as the following formula:

[0046]

[0047] Among them, X i represents the i-th outlier, Q i Indicates the limit value exceeded by the i-th outlier.

[0048] The DOO obtained through the above calculation can indicate the difference between the cells in the power battery and the normal value, and can be used as a score for evaluating the consistency of the power battery.

[0049] In addition, based on the calculated DOO, other additional parameters during the operation of the vehicle can be further considered to accurately evaluate the consistency of the power battery using more comprehensive data. For example, the additional parameters may include one of the following: the state of charge (SOC) of the power battery, the use time of the power battery, the temperature of the power battery, the resistance of the power battery, or the current mileage of the vehicle.

[0050] According to one embodiment of the present disclosure, the principal component analysis (PCA) method is used to perform data dimension reduction processing on DOO and additional parameters during operation, and the value after data dimension reduction processing is used as a score for evaluating the consistency of the power battery. Specifically, through the method described above, the DOO of the power battery can be calculated based on the voltage data set detected in real time, and the DOO is associated with other parameters of the vehicle in the current detection cycle, for example, the above additional parameters of the vehicle at the first time point or the last time point or other key time points in the corresponding detection cycle. Taking the SOC of the power battery as an example of an additional parameter, it is used together with the DOO calculated in a specific detection cycle as a two-dimensional data, and a two-dimensional data set consisting of the above two parameters is collected through multiple detection cycles, and a projection matrix corresponding to the principal component is constructed using the PCA method, and the original two-dimensional data is multiplied by the established projection matrix to project the two-dimensional data onto the principal component, thereby obtaining the reduced-dimensional data, which is equivalent to the fusion of DOO and SOC to form a new parameter, as a score for evaluating the consistency of the power battery (for example, it can be called DOC).

[0051] Alternatively, according to another embodiment of the present disclosure, a model based on machine learning is used, for example, based on machine learning algorithms such as XGBoost, random forest, logistic regression, support vector machine (SVM), based on DOO and multiple other additional parameters, to calculate a score for evaluating the consistency of the power battery. For example, in addition to DOO and SOC, the current mileage of the vehicle, that is, the cumulative mileage corresponding to the vehicle in the corresponding detection cycle (such as 1,000 kilometers), can also be considered, the above-mentioned parameters are used as input features, and the consistency score is used as the target variable. The classifier model is trained by using a training set, and the model parameters are optimized by iteration, so that a model based on machine learning is used to fuse DOO, SOC and the mileage of the vehicle to calculate a score (for example, which can be called DCM) for evaluating the consistency of the power battery.

[0052] By calculating the score for evaluating the consistency of the power battery in the above manner, the multi-dimensional factors affecting the power battery can be compressed and comprehensively considered, thereby achieving a more comprehensive estimation of the consistency of the power battery.

[0053] Combination of the above Figure 1 , a method for estimating the consistency of a power battery is described through various exemplary embodiments. Through the estimation method disclosed in the present invention, the consistency of the power battery can be estimated by utilizing voltage data detected in real time, and this method is more efficient and accurate than traditional methods, providing important data support for performance analysis and fault diagnosis.

[0054] In addition, according to another aspect of the present disclosure, a visualization method for the consistency of a power battery is provided, which is used to visualize the energy score calculated according to the above-mentioned estimation method, and specifically involves providing a first visualization representation of the energy score of each battery cell as a function of a specific variable. For example, the specific variable may be a variable related to the vehicle's mileage or the usage time of the power battery.

[0055] Figure 2 A schematic diagram for visualizing the consistency of a power battery according to an embodiment of the present disclosure is shown.

[0056] like Figure 2 As shown, a curve chart of energy score as a function of vehicle mileage is provided, wherein the horizontal axis of the curve chart is the vehicle mileage, indicating the cumulative distance traveled by the vehicle (for example, in kilometers); the vertical axis is the energy score of each cell in the vehicle's power battery, for example, the energy score of each cell can be calculated by the above estimation method, and different colors and line segment types are used to distinguish the energy scores of each cell. Ideally, the energy score of each cell should be consistent when in use. In this way, the fluctuation of each cell as the mileage increases can be provided to the vehicle tester or user, so as to facilitate intuitive viewing of the change trend of the consistency of the power battery.

[0057] In addition, if Figure 2 As shown, one or more decision lines for defining abnormal cells can also be displayed in the above-mentioned visual representation. The decision line is determined based on the statistical data of the historical energy score. For example, as mentioned above, based on the historical test data and / or usage data of the power battery, the upper and lower limits of the energy score corresponding to the cell within the normal working range can be determined, and then the decision line on the corresponding mileage can be determined. Therefore, the decision line can be composed of points corresponding to the limit values, which define the interval within the normal working range. On this basis, the cell corresponding to the function that exceeds the decision line to a certain threshold (for example, the exceeded portion is greater than 50%, and the exceeded distance is greater than a specific value) is indicated as an abnormal cell. For example, in Figure 2In the figure, more than 90% of the function of cell 1 exceeds the decision line 1 corresponding to the upper limit value, and all the functions of cell 6 exceed the decision line 2 corresponding to the lower limit value. Therefore, cell 1 and cell 6 are indicated as abnormal cells, for example, by a specific color, line type, text prompt, etc.

[0058] In addition, in this field, the existing consistency of power batteries is limited to a single vehicle or battery pack, and the consistency of power batteries is not monitored and evaluated at the vehicle level. That is, the prior art does not focus on whether the power batteries of multiple vehicles using battery packs with the same parameters (for example, the same battery model, the same materials, or the same supplier) are consistent in performance.

[0059] In view of this, the present disclosure also proposes to collect statistics on the consistency of battery packs of the same model of vehicle or multiple vehicles using the same power battery (for example, the same model of electric vehicles) to obtain a consistency estimate of the power battery at the vehicle level. The specific method involves using the above-mentioned combination Figure 1 The described estimation method calculates the consistency score of the power battery of each of the multiple vehicles using the same power battery (which may be referred to as the first consistency score), and then calculates the consistency score of the power battery of the group of these vehicles based on the calculated consistency score of the power battery of each vehicle, that is, the consistency score of the power battery based on the vehicle level (which may be referred to as the second consistency score). For example, the consistency of the power batteries of these vehicles can be estimated by comparing the differences in the consistency scores of the power batteries between the vehicles. For example, the mean and variance or standard deviation of the consistency scores of the power batteries of all vehicles are calculated to evaluate the consistency of the power batteries of this group of vehicles. In addition, the calculation method of the first consistency score and the calculation method of the second consistency score based on the vehicle level may be similar, and both quantify the discreteness of the data. Therefore, the method described above can be used to calculate the consistency scores of the two, which will not be repeated here.

[0060] In addition, according to another aspect of the present disclosure, a method for visualizing the consistency of power batteries based on the vehicle level is also provided, which is used to visualize the consistency score of the power battery of each vehicle calculated according to the above-mentioned estimation method, and specifically involves providing a second visual representation of the first consistency score of the power battery of each vehicle as a function of a specific variable. For example, the specific variable may be a variable related to the vehicle's mileage or the usage time of the power battery.

[0061] Figure 3 A schematic diagram for visualizing consistency of power batteries based on vehicle level according to an embodiment of the present disclosure is shown.

[0062] like Figure 3 As shown, a curve chart of the first consistency score of the power battery of each vehicle as a function of the mileage of the vehicle is provided, wherein the horizontal axis of the curve chart is the mileage of the vehicle, indicating the cumulative distance traveled by the vehicle (for example, in kilometers); the vertical axis is the consistency score of each vehicle, and the DOO of the power battery described above is used as the consistency score in this embodiment, and different colors and line segment types are used to distinguish the consistency scores of the power batteries corresponding to each vehicle. Ideally, the consistency scores of the power batteries of vehicles using the same power battery should be consistent. In this way, the fluctuations in the power battery of a specific model of vehicle or vehicle group with the increase of mileage can be provided to the vehicle tester or user, so as to facilitate intuitive viewing of the changing trend of the consistency of the power battery based on the vehicle level.

[0063] In addition, if Figure 3 As shown, one or more decision lines for defining abnormal cells can also be displayed in the above-mentioned visual representation. The decision line is determined based on the statistical data of the historical consistency score of the power battery. For example, as mentioned above, based on the historical test data and / or usage data of the power battery, the limit value of the consistency score corresponding to the power battery within the normal working range can be determined, and then the decision line at the corresponding mileage can be determined. Therefore, the decision line can be composed of points corresponding to the limit values, which define the interval within the normal working range. On this basis, the vehicle corresponding to the function that exceeds the decision line to a certain threshold (for example, the exceeded portion is greater than 50%, and the exceeded distance is greater than a specific value) is indicated as an abnormal vehicle. For example, in Figure 3 In the example, vehicle 1 exceeds the decision line corresponding to the upper limit value, so vehicle 1 is indicated as an abnormal vehicle, for example, by a specific color, line type, text prompt, etc.

[0064] In addition, according to an embodiment of the present disclosure, the consistency score of the power battery is not limited to the DOO in the above example, and may also include a consistency score calculated by performing data dimensionality reduction processing using the PCA method, or a consistency score calculated based on a machine learning model. Figure 4 and Figure 5 1 and 2 show other schematic diagrams for visualizing the consistency of power batteries based on vehicle levels according to embodiments of the present disclosure. Figure 4 In , the horizontal axis is the vehicle's mileage, and the vertical axis uses the DOC of the power battery as described above as the consistency score; Figure 5In the example, the consistency of the power battery based on the vehicle level is visualized by a classification result diagram, wherein the points representing vehicles within the normal range are clustered to the left of the decision boundary (equivalent to the decision line), and the points representing abnormal vehicles are clustered to the right of the decision boundary. In addition, according to other embodiments of the present disclosure, the calculated energy score and the consistency of the power battery can also be visualized using methods such as box plots or bar graphs.

[0065] Combination of the above Figures 2 to 5 , a method for visualizing the consistency of a power battery is described through various exemplary embodiments. Through the visualization method disclosed in the present invention, various parameters related to the consistency of the power battery are presented as functions of different variables, thereby providing a more intuitive presentation for consistency evaluation and facilitating testers to observe the relationship and trend between different variables. In addition, for a data set containing multiple variables, the consistency score curve can be visualized and the high-dimensional data can be compressed, thereby intuitively presenting the relationship between the parameters and facilitating the discovery of outliers.

[0066] Next, we will refer to Figure 6 An example of an apparatus for estimating consistency of a power battery according to an embodiment of the present disclosure is described.

[0067] like Figure 6 As shown, the device 600 for estimating the consistency of the power battery includes: a processor 610 and a memory 620. The device 600 may be a computer integrated in the vehicle or a remote server. It should be understood that the structure shown is only exemplary and not restrictive, and in addition to these units, the device 600 may also include other components, however, since these components are irrelevant to the content of the embodiment of the present invention, their illustration and description are omitted herein.

[0068] In addition, since the specific details of the operations performed by the apparatus 600 for estimating the consistency of a power battery according to an embodiment of the present disclosure are different from those described above with reference to Figure 1-5 The details described are generally similar, and therefore, some descriptions of the same details are omitted herein for the sake of brevity.

[0069] The processor 610 may be a central processing unit (CPU), a microcontroller unit (MCU), a digital signal processor (DSP), or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may utilize computer program instructions stored in the memory 620 to perform desired functions, wherein when the computer program instructions are executed by the processor 610, the following steps for estimating the consistency of the power battery are performed:

[0070] During the operation of the vehicle, the operating voltage of each battery cell in the plurality of battery cells is detected in real time to obtain a first voltage data set for each battery cell; the first voltage data set is subjected to a first filtering process to retain voltage data corresponding to an operating current less than a first threshold value, thereby obtaining a filtered second voltage data set for each battery cell; based on the second voltage data set, an energy score of each battery cell is calculated; and based on the calculated energy score of each battery cell, a first consistency score of the power battery is calculated.

[0071] A second filtering process is performed on the first voltage data set to retain voltage data corresponding to a state of charge (SOC) in a specific interval.

[0072] The second voltage data set is transformed into a frequency domain data set having amplitudes; and the energy score of each battery cell is calculated based on the corresponding amplitudes of the low frequency components in the frequency domain data set.

[0073] The calculated energy score of each battery cell is normalized; a limit value is determined based on statistical data of historical energy scores, the limit value including at least one of an upper limit value and a lower limit value of the energy score; an energy score that exceeds the limit value and reaches a second threshold is determined as an outlier; and a Euclidean distance between the outlier and the exceeded limit value is calculated as a first consistency score.

[0074] Using principal component analysis (PCA) method, data dimension reduction is performed on the Euclidean distance of the outlier value and the additional parameters during operation, and the value after data dimension reduction is used as the first consistency score; or using a machine learning-based model, the first consistency score of the power battery is calculated based on the Euclidean distance of the outlier value and the additional parameters during operation; wherein the additional parameters include one of the following: the state of charge (SOC) of the power battery, the usage time of the power battery, the temperature of the power battery, the resistance of the power battery, or the current mileage of the vehicle.

[0075] In addition, when the computer program instructions are executed by the processor 610, the following steps for estimating the consistency of the power battery based on the vehicle level are also performed:

[0076] For each of the plurality of vehicles using the same power battery, a first consistency score of the power battery of each vehicle is calculated respectively; and based on the first consistency score of the power battery of each vehicle, a second consistency score of the power battery based on the vehicle level is calculated.

[0077] The memory 620 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. One or more computer program instructions may be stored on the computer-readable storage medium, so that the processor 610 may run the program instructions to implement the above functions and / or other desired functions of the embodiments of the present invention, and / or may execute the above methods according to the embodiments of the present invention. Various applications and various data may also be stored in the computer-readable storage medium.

[0078] In addition, the apparatus 600 for estimating the consistency of the power battery according to the embodiment of the present disclosure further includes a device 630 for visualizing the consistency of the power battery, which is configured to provide the above combination Figures 2 to 5 The described visualization of the consistency of the power battery, for example, provides a first visualization representation of the energy score of each battery cell as a function of a specific variable, and provides a second visualization representation of the first consistency score of the power battery of each vehicle as a function of a specific variable; wherein the specific variable is a variable related to the vehicle's mileage or the usage time of the power battery; and, in the first visualization, a first decision line is displayed, and the battery cell corresponding to the function that exceeds the first decision line to reach a third threshold is indicated as an abnormal battery cell; and in the second visualization, a second decision line is displayed; and the vehicle corresponding to the function that exceeds the second decision line to reach a fourth threshold is indicated as an abnormal vehicle.

[0079] In addition, the device for estimating the consistency of the power battery and the device for estimating the consistency of the power battery based on the vehicle level can be the same device or different devices. For example, they can be used as a vehicle computer and a platform system for testing the vehicle respectively.

[0080] Next, a computer-readable storage medium according to an embodiment of the present invention will be described. The present invention also provides a computer-readable storage medium having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the steps performed by the processor described above are implemented, and in combination with the above Figure 1-6 In addition, it should be understood that each component or module in the above device can be implemented by hardware, can also be implemented by software, and can also be implemented by a combination of hardware and software.

[0081] The above has been fully described in conjunction with the accompanying drawings for the method and device for estimating and visualizing the consistency of the power battery according to the embodiments of the present disclosure. Through the various aspects and embodiments of the present disclosure, the consistency of the power battery can be monitored in real time during the operation of the vehicle, and the consistency of the power battery can be evaluated in a more accurate way; in addition, a visual chart related to the consistency of the power battery can be provided to the vehicle tester or user in real time, so that the personnel can understand the performance of the vehicle more intuitively, thereby facilitating the testing and acceptance of the vehicle's power battery.

[0082] In addition, the basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the embodiments of the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, rather than limitation, and the above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0083] The block diagrams of the devices, equipment, devices, and systems involved in the embodiments of the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by operators in the art, these devices, equipment, devices, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0084] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0085] It should also be noted that in the device and method of the present disclosure, each component or each step can be decomposed and / or reassembled. Such decomposition and / or reassembly should be regarded as an equivalent solution of the present disclosure.

[0086] For ordinary operators in the art, it is understood that all or any part of the methods and devices disclosed herein can be implemented in hardware, firmware, software or a combination thereof in any computing device (including processors, storage media, etc.) or a network of computing devices. Hardware can be a general-purpose processor, digital signal processor (DSP), ASIC, field programmable gate array signal (FPGA) or other programmable logic device (PLD), discrete gate or transistor logic, discrete hardware components or any combination thereof designed to perform the functions described herein. The general-purpose processor can be a microprocessor, but as an alternative, the processor can be any commercially available processor, controller, microcontroller or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors cooperating with a DSP core, or any other such configuration. The software can be present in any form of computer-readable tangible storage medium. By way of example and not limitation, such computer-readable tangible storage media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage devices or any other tangible media that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer. As used herein, disc includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc.

[0087] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0088] The above description of the disclosed aspects is provided to enable any operator in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to operators in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0089] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for estimating the consistency of a power battery, wherein the power battery is composed of a plurality of cells and is used to provide energy for a vehicle, the method comprising: detecting an operating voltage of each of the plurality of battery cells in real time during operation of the vehicle to obtain a first voltage data set of each of the battery cells; Performing a first filtering process on the first voltage data set to retain voltage data corresponding to an operating current less than a first threshold, thereby obtaining a filtered second voltage data set for each battery cell; Calculating the energy score of each battery cell based on the second voltage data set; as well as Based on the calculated energy score of each battery cell, a first consistency score of the power battery is calculated.

2. The estimation method according to claim 1, wherein: The obtaining of the filtered second voltage data set of each battery cell further comprises: A second filtering process is performed on the first voltage data set to retain voltage data corresponding to a state of charge (SOC) in a specific interval.

3. The estimation method according to claim 1 or 2, wherein: Calculating the energy score of each battery cell includes: transforming the second voltage data set into a frequency domain data set having magnitudes; and The energy score of each battery cell is calculated based on the corresponding amplitude of the low-frequency component in the frequency domain data set.

4. The estimation method according to claim 1 or 2, wherein: Calculating the first consistency score of the power battery includes: Normalizing the calculated energy score of each battery cell; determining a limit value according to statistical data of historical energy scores, the limit value comprising at least one of an upper limit value and a lower limit value of the energy score; determining an energy fraction exceeding the limit value to reach a second threshold as an abnormal value; The Euclidean distance between the outlier and the exceeded limit value is calculated as the first consistency score.

5. The estimation method according to claim 4, wherein: Calculating the first consistency score of the power battery further includes: Using a principal component analysis (PCA) method, performing data dimension reduction processing on the Euclidean distance of the outlier value and the additional parameter during the operation, and using the value after the data dimension reduction processing as the first consistency score; The additional parameter includes one of the following: the state of charge (SOC) of the power battery, the usage time of the power battery, the temperature of the power battery, the resistance of the power battery, or the current mileage of the vehicle.

6. The estimation method according to claim 4, wherein: Calculating the first consistency score of the power battery includes: Calculating, using a machine learning-based model, a first consistency score for the power battery based on a Euclidean distance of the outlier and an additional parameter during the operation; The additional parameter includes one of the following: the state of charge (SOC) of the power battery, the usage time of the power battery, the temperature of the power battery, the resistance of the power battery, or the current mileage of the vehicle.

7. A method for visualizing the consistency of a power battery, comprising: Based on the energy score calculated by the estimation method according to any one of claims 1 to 6, providing a first visual representation of the energy score of each battery cell as a function of a specific variable; The specific variable is a variable related to the mileage of the vehicle or the usage time of the power battery.

8. The visualization method according to claim 7, further comprising: displaying a first decision line in the first visual representation, the first decision line being determined based on the statistical data of the historical energy scores; as well as The battery cell corresponding to the function that exceeds the first decision line and reaches a third threshold value is indicated as an abnormal battery cell.

9. A method for estimating consistency of a power battery based on vehicle level, comprising: The estimation method according to any one of claims 1 to 6, wherein for each vehicle among a plurality of vehicles using the same power battery, a first consistency score of the power battery of each vehicle is calculated respectively; as well as Based on the first consistency score of the power battery of each vehicle, a second consistency score of the power battery based on the vehicle level is calculated.

10. A method for visualizing consistency of a power battery based on a vehicle level, comprising: Based on the first consistency score of the power battery of each vehicle calculated by the estimation method according to claim 9, providing a second visual representation of the first consistency score of the power battery of each vehicle as a function of a specific variable; The specific variable is a variable related to the mileage of each vehicle or the usage time of the power battery of each vehicle.

11. The visualization method according to claim 10, further comprising: displaying a second decision line in the second visual representation, the second decision line being determined based on statistical data of historical second consistency scores; as well as A vehicle corresponding to the function that exceeds the second decision line and reaches a fourth threshold is indicated as an abnormal vehicle.

12. A device for estimating the consistency of a power battery, the device comprising: processor; and a memory having computer program instructions stored therein, Wherein, when the computer program instructions are executed by the processor, the processor is enabled to perform the estimation method according to any one of claims 1 to 6.

13. The apparatus according to claim 12, further comprising a device for visualizing the consistency of the power battery, the device being configured to: Based on the calculated energy score, providing a first visual representation of the energy score of each battery cell as a function of a specific variable, wherein: The specific variable is a variable related to the mileage of the vehicle or the usage time of the power battery; displaying a first decision line in the first visual representation, the first decision line being determined based on the statistical data of the historical energy scores; and The battery cell corresponding to the function that exceeds the first decision line and reaches a third threshold value is indicated as an abnormal battery cell.

14. A device for estimating consistency of a power battery based on vehicle level, the device comprising: processor; and a memory having computer program instructions stored therein, Wherein, when the computer program instructions are executed by the processor, the processor executes the estimation method according to any one of claims 1 to 6, and for each of a plurality of vehicles using the same power battery, respectively calculates a first consistency score of the power battery of each vehicle; as well as Based on the first consistency score of the power battery of each vehicle, a second consistency score of the power battery based on the vehicle level is calculated.

15. The apparatus according to claim 14, further comprising a device for visualizing the consistency of the power battery, the device being configured to: Based on the calculated first consistency score of the power battery of each vehicle, a second visual representation of the first consistency score of the power battery of each vehicle as a function of a specific variable is provided, wherein: The specific variable is a variable related to the mileage of each vehicle or the usage time of the power battery of each vehicle; displaying a second decision line in the second visual representation, the second decision line being determined based on statistical data of historical second consistency scores; and A vehicle corresponding to the function that exceeds the second decision line and reaches a fourth threshold is indicated as an abnormal vehicle.

16. A computer-readable storage medium having computer program instructions stored thereon, wherein: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images