Battery data processing method and device, equipment, storage medium and program product

Abstract

The invention relates to a battery data processing method and device, equipment, a storage medium and a program product. The method comprises the steps of detecting battery data in a battery charging and discharging process to obtain a detection result of the battery data, and when the detection result is that the battery data comprises at least one abnormal data of a battery data segment corresponding to non-constant-current data, a battery data segment corresponding to constant-voltage data, an outlier data point and an outlier data segment, judging whether the battery data is abnormal or not; and processing the battery data according to the abnormal data to obtain target battery data. The abnormal data in the battery data can be detected, and the battery data is processed according to the abnormal data to obtain the target battery data, so that the quality of the obtained target battery data is improved.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a battery data processing method, apparatus, device, storage medium, and program product. Background Art

[0002] With the widespread use of batteries, users have higher requirements for battery performance, for example, batteries with larger capacity in a smaller size and weight, and longer service life.

[0003] Currently, the initial model is trained using raw battery data, such as the voltage and capacity of a test battery during the charge and discharge phases, to generate a predictive model. Based on the predictive model and design parameters such as the battery's length, width, and anode material, predicted battery data is generated. This predicted battery data can be used to optimize the battery's design parameters, thereby improving battery performance. Therefore, the quality of the battery data required for model training is crucial and impacts the accuracy of the predictive model, and thus battery performance. Therefore, improving the quality of battery data has become a pressing technical issue in this field. Summary of the Invention

[0004] Based on this, it is necessary to provide a battery data processing method, device, equipment, storage medium and program product that can improve the quality of battery data in response to the above technical problems.

[0005] In a first aspect, the present application provides a battery data processing method. The method comprises:

[0006] Detecting battery data during the battery charging and discharging process to obtain a detection result of the battery data;

[0007] When the detection result shows that the battery data includes abnormal data, the battery data is processed according to the abnormal data to obtain target battery data; the abnormal data includes at least one of a battery data segment corresponding to non-constant current data, a battery data segment corresponding to constant voltage data, an outlier data point, and an outlier data segment.

[0008] In this embodiment, battery data during the battery charging and discharging process is detected to obtain a detection result of the battery data. If the detection result shows that the battery data includes at least one of abnormal data selected from a battery data segment corresponding to non-constant current data, a battery data segment corresponding to constant voltage data, an outlier data point, and an outlier data segment, the battery data is processed based on the abnormal data to obtain target battery data. Because the abnormal data in the battery data can be detected and processed based on the abnormal data to obtain the target battery data, the quality of the obtained target battery data is improved.

[0009] In one embodiment, detecting battery data during the battery charging and discharging process to obtain a detection result of the battery data includes:

[0010] Based on the current data corresponding to the battery data during the charging and discharging process of the battery, the battery data is detected to obtain the detection result of the battery data.

[0011] In this embodiment, based on the current data corresponding to the battery data during the charging and discharging process of the battery, the battery data is detected to obtain the detection result in the battery data. When the detection result shows that the abnormal data in the battery data includes the battery data segment corresponding to non-constant current data, there is no need to further detect the battery data segment corresponding to the constant voltage data, the outlier data points, and the outlier data segments, thereby reducing the time cost required for detection.

[0012] In one embodiment, based on the current data corresponding to the battery data during the charging and discharging process of the battery, the battery data is detected to obtain the detection result of the battery data, including:

[0013] Sort the current data according to the magnitude of the current data to obtain the target current data;

[0014] Determine the current window according to the length of the target current data and the preset length ratio;

[0015] Intercept the target current data based on the current window to obtain the current data segment;

[0016] Detect the battery data according to the current data segment to obtain the detection result of the battery data; the detection result includes whether the battery data includes the battery data segment corresponding to non-constant current data.

[0017] In this embodiment, the current data is sorted according to the magnitude of the current data to obtain the target current data, the current window is determined according to the length of the target current data and the preset length ratio, the target current data is intercepted based on the current window to obtain the current data segment, and the battery data is detected according to the current data segment to obtain the detection result of the battery data; the detection result includes whether the battery data includes the battery data segment corresponding to non-constant current data. Since the target current data is the data obtained by sorting the current data according to the magnitude of the current data, therefore, the two current data at both ends of the current data segment are the maximum current data and the minimum current data in the current data segment, saving the time required to determine the maximum current data and the minimum current data from the current data segment, thereby improving the efficiency of determining the maximum current data and the minimum current data, and further improving the efficiency of obtaining the detection result.

[0018] In one embodiment, detecting the battery data according to the current data segment to obtain the detection result of the battery data; the detection result includes whether the battery data includes the battery data segment corresponding to non-constant current data, including:

[0019] Determine the current difference between the maximum current data and the minimum current data in the current data segment;

[0020] When the current difference is greater than or equal to a preset current difference, perform an iterative operation; the iterative operation includes moving the current window according to a preset moving step size, and intercepting target current data based on the moved current window to obtain a new current data segment;

[0021] When the current difference corresponding to the new current data segment is greater than or equal to the preset current difference, return to perform the iterative operation;

[0022] When the current difference corresponding to the new current data segment obtained by the last interception is greater than or equal to the preset current difference, determine that the detection result includes the battery data segment corresponding to the battery data being non-constant current data.

[0023] In this embodiment, when the current difference corresponding to the new current data segment is greater than or equal to the preset current difference, return to perform the iterative operation; when the current difference corresponding to the new current data segment obtained by the last interception is greater than or equal to the preset current difference, determine that the detection result includes the battery data segment corresponding to the battery data being non-constant current data, so as to realize the determination of the battery data segment corresponding to the non-constant current data.

[0024] In one embodiment, the battery data includes a voltage-electricity curve for characterizing the correspondence between voltage data and electricity data, and the method further includes:

[0025] When the abnormal data does not include the battery data segment corresponding to the non-constant current data, obtain the voltage change trend between the current position point and the next position point on the voltage-electricity curve;

[0026] When the voltage change trend does not satisfy the monotonicity corresponding to the battery data, obtain the voltage change trend of the first preset number of position points after the next position point;

[0027] When the voltage change trend of the first preset number of position points does not satisfy the monotonicity, determine the battery data segment corresponding to the constant voltage data in the battery data according to the current position point and the voltage-electricity curve segment after the current position point.

[0028] In this embodiment, based on the voltage change trends of the current position point and the first preset number of position points after the next position point, the battery data segment corresponding to the constant voltage data in the battery data is determined, that is, based on the voltage change trends of a sufficient number of position points, the battery data segment corresponding to the constant voltage data in the battery data is determined, thereby improving the accuracy of the determined battery data segment corresponding to the constant voltage data.

[0029] In one embodiment, determining a battery data segment corresponding to constant voltage data based on a current position point and a voltage - electricity curve segment after the current position point includes:

[0030] Taking the current position point and the voltage - electricity curve segment after the current position point as a first initial data segment corresponding to the constant voltage data;

[0031] Determining a battery data segment corresponding to the constant voltage data in the battery data according to the first initial data segment.

[0032] In this embodiment, by taking the current position point and the voltage - electricity curve segment after the current position point as the first initial data segment corresponding to the constant voltage data, and determining the battery data segment corresponding to the constant voltage data in the battery data according to the first initial data segment, the determination of the battery data segment corresponding to the constant voltage data in the battery data is realized.

[0033] In one embodiment, determining a battery data segment corresponding to the constant voltage data according to the first initial data segment includes:

[0034] Determining a constant - current current data segment on the current - time curve; the current - time curve is used to represent the correspondence between current data and time during the battery charging and discharging process;

[0035] Determining a target position point on the voltage - electricity curve corresponding to the end position point of the constant - current current data segment;

[0036] Taking the target position point and the voltage - electricity curve segment after the target position point as a second initial data segment;

[0037] Taking the union of the first initial data segment and the second initial data segment as the battery data segment corresponding to the constant voltage data.

[0038] In this embodiment, by determining the constant - current current data segment on the current - time curve, determining a target position point on the voltage - electricity curve corresponding to the end position point of the constant - current current data segment, taking the target position point and the voltage - electricity curve segment after the target position point as the second initial data segment, and taking the union of the first initial data segment and the second initial data segment as the battery data segment corresponding to the constant voltage data. Thus, the second initial data segment corresponding to non - constant current is determined based on the current - time curve, and then the union of the second initial data segment and the first initial data segment is taken as the battery data segment corresponding to the constant voltage data, enabling the second initial data segment corresponding to non - constant current to also be used as the battery data segment corresponding to the constant voltage data, and more comprehensively and accurately determining the battery data segment corresponding to the constant voltage data.

[0039] In one embodiment, the battery data includes a voltage - electricity curve for representing the correspondence between voltage data and electricity data, and the method further includes:

[0040] When the abnormal data does not include the battery data segment corresponding to the non-constant current data, obtain the correlation information between the current position point and the next position point on the voltage-electricity curve;

[0041] Determine the outlier data points in the battery data according to the correlation information.

[0042] In this embodiment, when the abnormal data does not include the battery data segment corresponding to the non-constant current data, obtain the correlation information between the current position point and the next position point on the voltage-electricity curve, and determine the outlier data points in the battery data according to the correlation information, so as to detect the outlier data points in the battery data.

[0043] In one embodiment, the correlation information includes the distance and / or the sampling time interval. Determining the outlier data points in the battery data according to the correlation information includes:

[0044] When the distance is greater than or equal to the preset distance, and / or, the sampling time interval is greater than the preset sampling time interval, regard the next position point as the outlier data point in the battery data.

[0045] In this embodiment, when the distance is greater than or equal to the preset distance, and / or, the sampling time interval is greater than the preset sampling time interval, regard the next position point as the outlier data point existing in the battery data. Since the distance and / or the sampling time interval between the current position point and the next position point is directly judged, this method is relatively simple and fast, so as to improve the efficiency of determining the outlier data points.

[0046] In one embodiment, the battery data includes a voltage-electricity curve for characterizing the correspondence between voltage data and electricity data. The method further includes:

[0047] When the abnormal data does not include the battery data segment corresponding to the non-constant current data, obtain the voltage change trend between the current position point and the next position point of the current position point on the voltage-electricity curve;

[0048] When the voltage change trend does not satisfy the monotonicity corresponding to the battery data, determine the outlier data segment in the battery data according to the voltage change trend of the second preset number of position points after the next position point.

[0049] In this embodiment, when the abnormal data does not include the battery data segment corresponding to the non-constant current data, the voltage change trend between the current position point and the next position point on the voltage-electricity curve is obtained. When the voltage change trend does not satisfy the monotonicity corresponding to the battery data, the outlier data segment in the battery data is determined according to the voltage change trend of the second preset number of position points after the next position point, so as to detect the outlier data segment in the battery data, and then process the battery data based on the outlier data segment to obtain the target battery data, improving the quality of the obtained target battery data.

[0050] In one embodiment, determining the outlier data segment in the battery data according to the voltage change trend of the second preset number of position points after the next position point includes:

[0051] When the voltage change trend of the second preset number of position points satisfies monotonicity, the voltage-electricity curve segment between the current position point and the first position point among the second preset number of position points is used as the outlier data segment;

[0052] When there is a voltage change trend that does not satisfy monotonicity in the voltage change trend of the second preset number of position points, obtain the voltage change trend of the second preset number of position points after the last position point that does not satisfy monotonicity until the voltage change trend of the second preset number of position points obtained most recently satisfies monotonicity, and use the voltage-electricity curve segment between the current position point and the first position point among the second preset number of position points obtained most recently as the outlier data segment.

[0053] In this embodiment, the outlier data segment is determined by determining the voltage change trend of the second preset number of position points, that is, by determining the outlier data segment based on the voltage change trend of a sufficient number of position points, so as to improve the accuracy of determining the outlier data segment.

[0054] In one embodiment, the battery data includes the battery data generated during multiple battery charge and discharge processes. Processing the battery data according to the abnormal data to obtain the target battery data includes:

[0055] For the battery data generated during each battery charge and discharge process, when the abnormal data corresponding to the battery data does not include the battery data segment corresponding to the non-constant current data and includes other abnormal data, the abnormal data in the battery data is removed to obtain the remaining battery data; the other abnormal data includes at least one of the battery data segment corresponding to the constant voltage data, the outlier data point, and the outlier data segment;

[0056] Perform smoothing processing on the remaining battery data to obtain the intermediate battery data;

[0057] Data filling processing is performed on the missing data in the intermediate battery data to obtain target battery data.

[0058] In this embodiment, when the abnormal data corresponding to the battery data does not include the battery data segment corresponding to the non-constant current data and includes other abnormal data, the abnormal data in the battery data is removed to obtain the remaining battery data. The remaining battery data is smoothed to obtain the intermediate battery data, and data filling processing is performed on the missing data in the intermediate battery data to obtain the target battery data, thereby improving the quality of the obtained target battery data.

[0059] In a second aspect, the present application also provides a battery data processing device. The device includes:

[0060] A detection module for detecting the battery data during the charging and discharging process of the battery to obtain a detection result of the battery data;

[0061] A processing module for, when the detection result is that the battery data includes abnormal data, processing the battery data according to the abnormal data to obtain target battery data; the abnormal data includes at least one of a battery data segment corresponding to non-constant current data, a battery data segment corresponding to constant voltage data, an outlier data point, and an outlier data segment.

[0062] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of any of the above methods are implemented.

[0063] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0064] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0065] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the specific embodiments of the present application are specifically exemplified below. Description of the Drawings

[0066] Upon reading the following detailed description of the preferred embodiments, various other advantages and benefits will become apparent to those of ordinary skill in the art. The drawings are only for the purpose of illustrating the preferred embodiments and are not considered to be a limitation of the present application. Also, in all the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0067] Figure 1 is the internal structure diagram of a computer device in an embodiment;

[0068] Figure 2 is a schematic flowchart of a battery data processing method provided by an embodiment of the present application;

[0069] Figure 3 is one of the schematic flowcharts of an abnormal data detection method provided by an embodiment of the present application;

[0070] Figure 4 is a schematic diagram of a current fluctuating within a small range provided by an embodiment of the present application;

[0071] Figure 5 is two of the schematic flowcharts of an abnormal data detection method provided by an embodiment of the present application;

[0072] Figure 6 is three of the schematic flowcharts of an abnormal data detection method provided by an embodiment of the present application;

[0073] Figure 7 is one of the schematic diagrams of the voltage and power curve during the battery charging process provided by an embodiment of the present application;

[0074] Figure 8 is four of the schematic flowcharts of an abnormal data detection method provided by an embodiment of the present application;

[0075] Figure 9 is five of the schematic flowcharts of an abnormal data detection method provided by an embodiment of the present application;

[0076] Figure 10 is a schematic diagram of the current-time curve during the battery charging process and the corresponding voltage-power curve provided by an embodiment of the present application;

[0077] Figure 11 is six of the schematic flowcharts of an abnormal data detection method provided by an embodiment of the present application;

[0078] Figure 12 is seven of the schematic flowcharts of an abnormal data detection method provided by an embodiment of the present application;

[0079] Figure 13 is two of the schematic diagrams of the voltage and power curve during the battery charging process provided by an embodiment of the present application;

[0080] Figure 14 It is the third schematic diagram of the voltage and power curve during the battery charging process provided by the embodiments of the present application;

[0081] Figure 15 It is a schematic flowchart of a method for obtaining target battery data provided by the embodiments of the present application;

[0082] Figure 16 It is a schematic overall flowchart of a method for processing battery data provided by the embodiments of the present application;

[0083] Figure 17 It is a schematic structural diagram of a device for processing battery data provided by the embodiments of the present application. Detailed implementation manners

[0084] Next, embodiments of the technical solutions of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present application, so they are only examples and cannot be used to limit the protection scope of the present application.

[0085] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion.

[0086] In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity, specific order or primary-secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "a plurality" is more than two, unless otherwise specifically defined.

[0087] Referring to "embodiments" herein means that specific features, structures or characteristics described in connection with the embodiments can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0088] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.

[0089] In the description of the embodiments of the present application, the term "plurality" means two or more (including two). Similarly, "multiple groups" means two or more groups (including two groups), and "multiple pieces" means two or more pieces (including two pieces).

[0090] In the description of the embodiments of the present application, for technical terms such as "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., the orientation or positional relationship indicated is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the embodiments of the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the embodiments of the present application.

[0091] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installation", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can also be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to specific situations.

[0092] With the wide application of batteries, users have higher requirements for the performance of batteries. For example, a battery with a larger capacity can be obtained with a smaller volume and weight, and it has a longer service life, etc.

[0093] Currently, an initial model is trained using original battery data such as the voltage and capacity of a test battery during the charge and discharge stages to obtain a prediction model. Based on the prediction model and design parameters of the battery such as length, width, and anode material, predicted battery data is obtained. Based on the predicted battery data, the design parameters of the battery can be optimized, thereby improving the performance of the battery. It can be seen that based on the prediction model and the design parameters of the battery, the more accurate the predicted battery data obtained, the more accurate the optimization of the design parameters, and thus the performance of the battery can be improved. The accuracy of the predicted battery data is affected by the accuracy of the prediction model, that is, the more accurate the prediction model, the more accurate the predicted battery data. Therefore, the quality of the battery data required for model training is crucial, which is related to the accuracy of the prediction model and thus related to the performance of the battery.

[0094] However, in practical applications, raw battery data often contains many types of abnormal data due to objective factors such as time, cost, and measurement errors. This introduces biases in model training and limits the accuracy and reliability of modeling. Therefore, improving the quality of battery data has become a pressing technical issue in this field.

[0095] In order to solve the above technical problems, the present invention provides a battery data processing method, which can be applied to Figure 1 The computer device shown may be a terminal. The computer device includes a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal via wired or wireless communication. Wireless communication can be achieved via Wi-Fi, a mobile cellular network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a battery data processing method. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device of the computer device may be a touchscreen covering the display, buttons, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse.

[0096] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0097] The present application is described below with reference to an embodiment. In one embodiment, Figure 2 As shown, Figure 2 This is a flow chart of a battery data processing method provided by an embodiment of the present application, in which the method is applied to Figure 1 Taking the computer device in the example as an example, the method includes the following steps S201-S202:

[0098] S201 , detecting battery data during the battery charging and discharging process to obtain a detection result of the battery data.

[0099] It should be noted that the battery data in this embodiment may include voltage data and the state of charge data corresponding to the voltage data. Alternatively, the battery data may include voltage data and the power data corresponding to the voltage data. The corresponding relationship between the voltage data and the power data may be characterized in the form of a curve or in the form of a data table. The battery data may be the battery data during the charging process or the battery data during the discharging process.

[0100] Since the model training is expected to obtain the battery data corresponding to the constant current data, training the model based on the battery data corresponding to the constant current data can obtain a more accurate prediction model. However, the battery data during the battery charging and discharging process may be the battery data corresponding to non-constant current data. Therefore, it is necessary to detect the battery data to determine whether the battery data is a battery data segment corresponding to the constant current data.

[0101] In one embodiment, it is determined whether the battery data is a battery data segment corresponding to the constant current data according to the monotonicity during the current charging and discharging process. Exemplarily, taking the battery data during the charging process including voltage data and the power data corresponding to the voltage data, and taking the corresponding relationship between the voltage data and the power data characterized in the form of a curve as an example for introduction, the curve characterizing the corresponding relationship between the voltage data and the power data may be called the voltage-power curve. The ordinate of the voltage-power curve is the voltage, and the abscissa is the power. After the charging starts, the voltage shows an increasing trend. When the voltage reaches a certain target voltage value, the voltage fluctuates very little and is almost constant, that is, it enters the constant voltage stage at the position point where the voltage reaches the target voltage value.

[0102] Since after the constant current charging starts, the voltage-power curve shows a monotonically increasing trend, the voltage increases as the charging time continues. When the voltage reaches a certain target voltage value, the voltage increases very little or is almost unchanged. Therefore, based on the monotonically increasing characteristic of the voltage-power curve during the constant current charging process, the curve segment before the voltage reaches the target voltage value can be detected, and this curve segment can be used as the battery data segment corresponding to the constant current data. If the ratio of the length of this curve segment to the total length of this voltage-power curve is greater than or equal to the preset ratio, it can be determined that this voltage-power curve is the battery data segment corresponding to the constant current data; if the ratio of the length of this curve segment to the total length of this voltage-power curve is less than the preset ratio, it can be determined that this voltage-power curve is the battery data segment corresponding to the non-constant current data, that is, the detection result is that the battery data includes the battery data segment corresponding to the non-constant current data. In this case, this voltage-power curve can be used as the battery data segment corresponding to the non-constant current data.

[0103] In one embodiment, the battery data can also be detected in combination with the current data corresponding to the battery data during the charge and discharge process to determine whether the battery data is the battery data corresponding to the constant current data. Among them, when it is determined that the current data is constant current data, it can be determined that the battery data is the battery data segment corresponding to the constant current data, that is, the voltage and power curve is the battery data segment corresponding to the constant current data; when it is determined that the current data is non-constant current data, it can be determined that the battery data is the battery data segment corresponding to the non-constant current data, that is, the obtained detection result is that the battery data includes abnormal data, and the abnormal data is the battery data segment corresponding to the non-constant current data. In this case, this voltage and power curve can be used as the battery data segment corresponding to the non-constant current data.

[0104] Among them, when the battery data is not the battery data segment corresponding to the non-constant current data, that is, when this voltage and power curve is not the battery data segment corresponding to the non-constant current data, the battery data can be further detected for constant voltage data, outlier data points, and outlier data segments. Among them, by further detecting the battery data for constant voltage data, it can be determined whether there is a battery data segment corresponding to the constant voltage data in the battery data; by further detecting the battery data for outlier data points, it can be determined whether there are outlier data points in the battery data; by further detecting the battery data for outlier data segments, it can be determined whether there are outlier data segments in the battery data.

[0105] The detection of the battery data during the discharge process is similar to the detection of the battery data during the above-mentioned charging process, and will not be elaborated here. The difference is that during the discharge process, after the discharge starts, the voltage data shows a monotonically decreasing trend. After the voltage data drops to a certain extent, the voltage approaches 0 and the decrease is very small or almost unchanged.

[0106] S202. When the detection result is that the battery data includes abnormal data, the battery data is processed according to the abnormal data to obtain the target battery data.

[0107] Among them, the abnormal data includes at least one of the battery data segment corresponding to the non-constant current data, the battery data segment corresponding to the constant voltage data, the outlier data points, and the outlier data segments.

[0108] To facilitate a clearer introduction of the embodiments of the present application, the battery data segment corresponding to the non-constant current data is called the first type of abnormal data; the battery data segment corresponding to the constant voltage data is called the second type of abnormal data; the outlier data points existing in the battery data are called the third type of abnormal data, and the outlier data segments existing in the battery data are called the fourth type of abnormal data.

[0109] It should be noted that the order of detecting the first type of abnormal data, the second type of abnormal data, the third type of abnormal data, and the fourth type of abnormal data is not limited. Therefore, there may be four types of abnormal data, or only some of the four types of abnormal data may exist. The four types of abnormal data can be detected simultaneously, or one type of abnormal data can be detected first, and then the next type of abnormal data can be detected.

[0110] In one embodiment, the first type of abnormal data detection can be performed on the battery data first. In the case where the abnormal data does not include the first type of abnormal data, the constant voltage data detection can be performed on the battery data to detect the battery data segment corresponding to the constant voltage data existing in the battery data. The outlier data point detection can also be performed on the battery data to detect the outlier data points existing in the battery data. The outlier data segment detection can also be performed on the battery data to detect the outlier data segments existing in the battery data. That is, in the case where the abnormal data does not include the first type of abnormal data, at least one of the battery data segment corresponding to the constant voltage data, the outlier data points, and the outlier data segments may exist in the battery data. In the case where the abnormal data includes the first type of abnormal data, since the model training is expected to obtain the battery data corresponding to the constant current data, and training the model with the battery data corresponding to the constant current data can obtain a more accurate prediction model. Therefore, in the embodiments of the present application, the battery data segment corresponding to the non-constant current data can be regarded as data without utilization value. For the battery data containing the battery data segment corresponding to the non-constant current data, the battery data can be removed subsequently. Therefore, it is not necessary to continue the detection of the second type of abnormal data, the third type of abnormal data, and the fourth type of abnormal data, thereby improving the efficiency of abnormal detection.

[0111] Among them, processing the battery data according to the abnormal data to obtain the target battery data may include:

[0112] In a possible implementation manner, in the case where the abnormal data includes the first type of abnormal data, since the model training is expected to obtain the battery data corresponding to the constant current data, and training the model with the battery data corresponding to the constant current data can obtain a more accurate prediction model. Therefore, in the embodiments of the present application, for the case where the battery data includes the first type of abnormal data, the battery data can be directly regarded as data without utilization value, and the battery data can be removed.

[0113] In another possible implementation, when the abnormal data includes at least one type of abnormal data among the second type of abnormal data, the third type of abnormal data, and the fourth type of abnormal data, the abnormal data in the battery data can be removed to obtain the remaining battery data, the remaining battery data can be smoothed to obtain the intermediate battery data, and the missing data in the intermediate battery data can be filled to obtain the target battery data. Among them, the missing data includes the data missing due to the removal of abnormal data, or the missing data includes the data missing due to the removal of abnormal data and some missing data existing in the collected battery data itself.

[0114] In yet another possible implementation, when the abnormal data includes at least one type of abnormal data among the second type of abnormal data, the third type of abnormal data, and the fourth type of abnormal data, the abnormal data in the battery data can be removed to obtain the remaining battery data, and the missing data in the remaining battery data can be filled to obtain the target battery data.

[0115] The following is an exemplary introduction to the process of processing the battery data to obtain the target battery data according to the abnormal data when the detection result is that the battery data includes abnormal data:

[0116] If the battery data includes the battery data generated during 100 battery charge and discharge processes, and the battery data generated during one battery charge and discharge process is characterized by a curve, that is, the battery data includes 100 curves. Among them, for the curve corresponding to the first battery charge and discharge process, this curve includes the first type of abnormal data; for the curves corresponding to the 2nd - 80th battery charge and discharge processes, if each of these 79 curves includes at least one type of abnormal data among the second type of abnormal data, the third type of abnormal data, and the fourth type of abnormal data; for the curves corresponding to the 81st - 100th battery charge and discharge processes, the detection result of these 20 curves is that the battery data does not include abnormal data.

[0117] In the above situation, the curve corresponding to the first battery charge and discharge process can be directly discarded, and the abnormal data in the 79 curves corresponding to the 2nd - 80th battery charge and discharge processes can be removed to obtain the remaining curve segments of each of the 79 curves. The remaining curve segments of each are smoothed to obtain the intermediate curve segments, and the missing data in each intermediate curve segment is filled to obtain 79 target curves, thereby realizing the processing of the battery data for these 80 times based on the abnormal data in the battery data for the 1st - 80th times. Since the battery data generated during the first battery charge and discharge process is discarded, the finally obtained target battery data includes the 79 target curves obtained by processing the 79 curves generated during the 2nd - 80th battery charge and discharge processes. These 79 target curves and the above 20 curves that do not include abnormal data can be used to train the model.

[0118] It is understandable that if 5 out of the above 100 curves include the first type of abnormal data, and each of the remaining 95 curves has at least one type of abnormal data among the second type of abnormal data, the third type of abnormal data, and the fourth type of abnormal data, then the 5 curves including the first type of abnormal data can be discarded, and the final target battery data is the 95 target curves obtained after processing the remaining 95 curves.

[0119] In this embodiment, by detecting the battery data during the charging and discharging process of the battery, the detection result of the battery data is obtained. When the detection result indicates that the battery data includes at least one type of abnormal data such as a battery data segment corresponding to non-constant current data, a battery data segment corresponding to constant voltage data, an outlier data point, and an outlier data segment, the battery data is processed according to the abnormal data to obtain the target battery data. Since the abnormal data in the battery data can be detected and the battery data is processed according to the abnormal data to obtain the target battery data, the quality of the obtained target battery data is improved.

[0120] In one embodiment, the above S201, detecting the battery data during the charging and discharging process of the battery to obtain the detection result of the battery data, can be implemented in the following manner:

[0121] Detect the battery data according to the current data corresponding to the battery data during the charging and discharging process of the battery to obtain the detection result of the battery data.

[0122] To improve the accuracy and efficiency of the obtained detection result, the battery data can be detected according to the current data corresponding to the battery data during the charging and discharging process of the battery to obtain the detection result in the battery data.

[0123] For the detection of the first type of abnormal data, the current data can be sorted according to the magnitude of the current data to obtain the target current data, the current window can be determined according to the length of the target current data and the preset length ratio, the target current data is intercepted based on the current window to obtain the current data segment, and the battery data is detected according to the current data segment to obtain the detection result of the battery data; the detection result includes whether the battery data includes a battery data segment corresponding to non-constant current data. Alternatively, the current window can be determined according to the length of the current data and the preset length ratio, the current data is intercepted based on the current window to obtain the current data segment, and the battery data is detected according to the current data segment to obtain the detection result of the battery data; the detection result includes whether the battery data includes a battery data segment corresponding to non-constant current data.

[0124] Among them, the battery data is detected according to the current data segment, and the detection result of the battery data is obtained; the detection result including whether the battery data includes the battery data segment corresponding to the non-constant current data may include: when the current difference between the maximum current data and the minimum current data in the current data segment is greater than or equal to the preset current difference, the battery data is used as the battery data segment corresponding to the non-constant current data existing in the battery data; when the current difference is less than the preset current difference, the battery data is used as the battery data segment corresponding to the constant current data.

[0125] For the detection of the second type of abnormal data, the third type of abnormal data, and the fourth type of abnormal data, it can be detected when it is determined that there is no battery data segment corresponding to the non-constant current data in the battery data, that is, based on the current data, when the battery data is determined to be the battery data segment corresponding to the constant current data; when the detection result is that the abnormal data in the battery data includes the battery data segment corresponding to the non-constant current data, there is no need to detect the second type of abnormal data, the third type of abnormal data, and the fourth type of abnormal data, thereby improving the abnormal detection efficiency.

[0126] In this embodiment, according to the current data corresponding to the battery data during the charging and discharging process of the battery, the battery data is detected to obtain the detection result in the battery data. When the detection result is that the abnormal data in the battery data includes the battery data segment corresponding to the non-constant current data, there is no need to detect the battery data segment corresponding to the constant voltage data, the outlier data points, and the outlier data segments, thereby reducing the time cost required for detection.

[0127] In one embodiment, as Figure 3 shown, Figure 3 FIG. is one of the schematic flowcharts of the abnormal data detection method provided by the embodiment of the present application. This embodiment relates to a possible implementation manner of how to detect the battery data according to the current data corresponding to the battery data during the charging and discharging process of the battery to obtain the detection result of the battery data. On the basis of the above embodiment, the method includes the following steps S301-S304:

[0128] S301, sort the current data according to the magnitude of the current data to obtain the target current data.

[0129] Considering that the constant current data will fluctuate around a fixed current value within a small range. As Figure 4 shown, Figure 4It is a schematic diagram of a current fluctuating within a small range provided by an embodiment of the present application. At the same time, since the current data obtained during the charge and discharge process does not provide the standard value of the current, it is difficult to detect the constant current data. To achieve the detection of constant current data, in this embodiment, it is considered that when the proportion of a certain section of current data concentrated near a certain value reaches a threshold, it is considered that there is a constant current data section in the current data, and then the battery data corresponding to the current data can be determined as the data obtained under the constant current condition. Therefore, in this embodiment, the current data is sorted according to the magnitude of the current data to obtain the target current data, and then it is determined whether the current data is constant current data according to the length of the target current data and a preset length. <>< / <>< /

[0130] S302. Determine a current window according to the length of the target current data and the preset length ratio. <>< / <>< /

[0131] Determining a current window according to the length of the target current data and the preset length ratio may use the product of the length of the target current data and the preset length ratio as a current window. Exemplarily, if the target current data is 100 and the preset length ratio is 80%, then 80 data can be used as a current window. <>< / <>< /

[0132] S303. Intercept the target current data based on the current window to obtain current data segments. <>< / <>< /

[0133] The target current data can represent the correspondence between current and time in the form of a table, or the correspondence between current and time in the form of a current-time curve. Taking the target current data including a current-time curve as an example, a data segment can be intercepted on the current-time curve based on the current window as a current data segment, and the length of this current data segment is the same as the length of the current window. It should be noted that in the case of intercepting the target current data for the first time, the leftmost end of the current window can be aligned with the leftmost end of the current-time curve for interception. Step S304 can be executed once for each obtained current data segment, or multiple current data segments can be intercepted from the target current data based on the current window and a moving step length, and then step S304 is executed based on each current data segment. <>< / 0> <>< /

[0134] S304. Detect the battery data according to the current data segment to obtain the detection result of the battery data; the detection result includes whether the battery data includes a battery data segment corresponding to non-constant current data. <>< / <>< /

[0135] In one embodiment, every time a current data segment is intercepted, the battery data can be detected based on this current data segment, and the detection result can be determined based on this current data segment. When the detection result includes the battery data segment corresponding to the constant current data, the interception can be stopped. When the detection result determined based on this current data segment includes the battery data segment corresponding to the non-constant current data, the current window can be moved according to the moving step size, and the target current data can be intercepted based on the moved current window to obtain a new current data segment. When the battery data segment corresponding to the non-constant current data is determined based on the new current data segment, return to execute the step of moving the current window according to the moving step size and intercepting the target current data based on the moved current window to obtain a new current data segment. When the new current data segment is the last intercepted segment and the battery data segment corresponding to the non-constant current data is determined based on this new current data segment, it can be determined that the detection result includes the battery data segment corresponding to the non-constant current data.

[0136] Exemplarily, the target current data includes 100 data, the current window is 80 data, and the moving step size is 1. The first intercepted current data segment includes the 1st - 80th data, denoted as current data segment 1. When it is determined that the battery data segment corresponding to the constant current data based on current data segment 1, the interception can be stopped, and it can be determined that the detection result includes the battery data segment corresponding to the constant current data.

[0137] It should be noted that if the current difference between the maximum current value and the minimum current value in current data segment 1 is less than the preset current difference, it means that current data segment 1 is constant current data. Since the length of current data segment 1 accounts for a relatively large proportion of the total length of the target current data, the battery data corresponding to the target current data can be regarded as the battery data segment corresponding to the constant current data first, that is, the target current data can be regarded as constant current data first, and subsequent constant voltage data detection can be performed to detect the battery data segment corresponding to the non-constant current data through the constant voltage data detection.

[0138] When it is determined that the battery data segment corresponding to the battery data is non-constant current data based on the current data segment 1, the current window is moved according to the moving step size, and the target battery data is intercepted for the second time based on the moved current window. The current data segment intercepted for the second time includes the 2nd to 81st data, denoted as the current data segment 2. When it is determined that the battery data segment corresponding to the battery data is non-constant current data based on the current data segment 2, the current window is moved according to the moving step size, and the target battery data is intercepted for the third time based on the moved current window. The current data segment intercepted for the third time includes the 3rd to 82nd data, denoted as the current data segment 3. This process of repeatedly intercepting the target current data to obtain current data segments is performed. When it is determined that the battery data segment corresponding to the battery data is non-constant current data based on the current data segment obtained from the last interception, it can be determined that the detection result includes the battery data segment corresponding to the non-constant current data.

[0139] In one embodiment, based on the current window and the moving step size, the target current data can be intercepted first to obtain multiple current data segments, and the current difference between the maximum current data and the minimum current data in each current data segment can be determined. When there is at least one current difference less than the preset current difference, it is determined that the detection result includes the battery data segment corresponding to the constant current data. When there is no current difference less than the preset current difference, it is determined that the detection result includes the battery data segment corresponding to the non-constant current data.

[0140] Exemplarily, in combination with the above example, if 21 current data segments are obtained by intercepting the target current data, and there is at least one current difference less than the preset current difference among the current differences corresponding to the 21 current data segments, it can be determined that the detection result includes the battery data segment corresponding to the constant current data. If there is no current difference less than the preset current difference among the current differences corresponding to the 21 current data segments, it is determined that the detection result includes the battery data segment corresponding to the non-constant current data.

[0141] In this embodiment, the current data is sorted according to the magnitude of the current data to obtain target current data. An current window is determined based on the length of the target current data and a preset length ratio. The target current data is intercepted based on the current window to obtain a current data segment. The battery data is detected based on the current data segment to obtain a detection result of the battery data. The detection result includes whether the battery data includes a battery data segment corresponding to non-constant current data. Since the target current data is the data obtained by sorting the current data according to the magnitude of the current data, the two current data at both ends of the current data segment are the maximum current data and the minimum current data in the current data segment, saving the time required to determine the maximum current data and the minimum current data from the current data segment, thereby improving the efficiency of determining the maximum current data and the minimum current data, and further improving the efficiency of obtaining the detection result.

[0142] In one embodiment, as Figure 5 shown, Figure 5 FIG. 2 is a second schematic flowchart of an abnormal data detection method provided by an embodiment of the present application. This embodiment relates to a possible implementation manner of detecting battery data based on a current data segment to obtain a detection result of the battery data. The detection result includes whether the battery data includes a battery data segment corresponding to non-constant current data. Based on the above embodiment, the method includes the following steps S501-S504:

[0143] S501, determine the current difference between the maximum current data and the minimum current data in the current data segment.

[0144] S502, in the case where the current difference is greater than or equal to a preset current difference, perform an iterative operation. The iterative operation includes moving the current window according to a preset moving step length, and intercepting the target current data based on the moved current window to obtain a new current data segment.

[0145] In the case where the current difference is less than the preset current difference, the battery data can be regarded as a battery data segment corresponding to constant current data. That is, as long as the current difference corresponding to one current data segment is less than the preset current difference, the battery data can be regarded as a battery data segment corresponding to constant current data.

[0146] S503, in the case where the current difference corresponding to the new current data segment is greater than or equal to the preset current difference, return to perform the iterative operation.

[0147] When the current difference corresponding to the new current data segment is less than the preset current difference, the battery data can be used as the battery data segment corresponding to the constant current data. Combining the above example, when it is determined that the battery data is the battery data segment corresponding to the non-constant current data based on the current data segment 1, the current window is moved according to the moving step, and the target battery data is intercepted for the second time based on the moved current window. The current data segment intercepted for the second time, that is, the new current data segment, includes the 2nd to 81st data, denoted as the current data segment 2. When the current difference corresponding to the current data segment 2 is less than the preset current difference, the battery data is used as the battery data segment corresponding to the constant current data, and there is no need to perform iterative operations, thereby shortening the excessive time occupied by the interception operation and improving the determination efficiency of the detection result.

[0148] S504. When the current difference corresponding to the new current data segment obtained by the last interception is greater than or equal to the preset current difference, it is determined that the detection result includes the battery data segment corresponding to the non-constant current data.

[0149] Among them, the detection result in this step is that the abnormal data in the battery data includes the battery data segment corresponding to the non-constant current data.

[0150] In this embodiment, when the current difference corresponding to the new current data segment is greater than or equal to the preset current difference, the iterative operation is returned. When the current difference corresponding to the new current data segment obtained by the last interception is greater than or equal to the preset current difference, it is determined that the detection result includes the battery data segment corresponding to the non-constant current data, thereby realizing the determination of the battery data segment corresponding to the non-constant current data.

[0151] In one embodiment, when the abnormal data in the detection result does not include the first type of abnormal data, that is, when the abnormal data does not include the battery data segment corresponding to the non-constant current data, the battery data can also be detected for the second type of abnormal data. In this embodiment, the battery data includes a voltage-electricity curve for characterizing the corresponding relationship between voltage data and electricity data, such as Figure 6 shown Figure 6 is the third schematic diagram of the abnormal data detection method flow provided by the embodiment of the present application. The method includes the following steps S601 - S603:

[0152] S601. When the abnormal data does not include the battery data segment corresponding to the non-constant current data, obtain the voltage change trend between the current position point and the next position point on the voltage-electricity curve.

[0153] Exemplarily, as Figure 7 shown Figure 7 is the first schematic diagram of the voltage-electricity curve during the battery charging process provided by the embodiment of the present application. AsFigure 7 As shown Figure 7 Among them, the battery data includes a voltage - charge curve 71. Taking the battery data segment corresponding to the voltage - charge curve 71 not being the battery data segment corresponding to non - constant current data as an example. For example, the point at position B1 is the current position point, and the point at position B2 is the next position point after the point at position B1. The point at position B1 and the point at position B2 can be adjacent position points, and there can also be a preset number of position points between the point at position B1 and the point at position B2. Among them, when the point at position B1 and the point at position B2 are adjacent position points, it is to judge whether the point at position B1 and the point at position B2 are strictly monotonic; when there is a preset number of position points between the point at position B1 and the point at position B2, it is to judge whether the point at position B1 and the point at position B2 conform to non - strict monotonicity, that is, to judge whether the point at position B1 and the point at position B2 satisfy monotonicity in a broad sense.

[0154] The voltage difference between the current position point and the next position point can be calculated, and based on the voltage difference, it is determined whether the voltage change trend satisfies the monotonicity corresponding to the battery data. If the absolute value of the voltage difference is less than a positive preset value, it can be considered that the voltage change trend does not satisfy the monotonicity and enters the constant - voltage stage. As Figure 7 shown, since the voltage at the point at position B2 is equal to the voltage at the point at position B1, the voltage change trend between the point at position B1 and the point at position B2 does not satisfy the monotonicity corresponding to the battery data. Among them, the monotonicity corresponding to the battery data during the battery charging process is a monotonically increasing characteristic. It can be seen from the voltage - charge curve 71 that the voltage change trend of the position points before the point at position B1 satisfies the monotonically increasing characteristic.

[0155] S602. When the voltage change trend does not satisfy the monotonicity corresponding to the battery data, obtain the voltage change trend of the first preset number of position points after the next position point.

[0156] When the voltage change trend between the point at position B1 and the point at position B2 does not satisfy the monotonicity corresponding to the battery data, that is, the voltage change trend between the point at position B1 and the point at position B2 does not satisfy the monotonically increasing characteristic, then the voltage change trend of the first preset number of position points after the point at position B2 can be obtained.

[0157] S603. When the voltage change trend of the first preset number of position points does not satisfy the monotonicity, determine the battery data segment corresponding to the constant - voltage data in the battery data according to the current position point and the voltage - charge curve segment after the current position point.

[0158] It can be seen from the voltage - charge curve 71 that the voltage change trend of the first preset number of position points after the point at position B2 does not satisfy the monotonically increasing characteristic, then the point at position B1 and the voltage - charge curve segment after the point at position B1 can be used as the battery data segment corresponding to the constant - voltage data.

[0159] In this embodiment, based on the voltage change trend of the first preset number of position points after the current position point and the next position point, the battery data segment corresponding to the constant voltage data in the battery data is determined, that is, based on the voltage change trend of a sufficient number of position points, the battery data segment corresponding to the constant voltage data in the battery data is determined, thereby improving the accuracy of the battery data segment corresponding to the determined constant voltage data.

[0160] In one embodiment, as Figure 8 shown, Figure 8 FIG. 4 is a schematic flow chart of an abnormal data detection method provided by an embodiment of the present application. This embodiment relates to a possible implementation manner of determining the battery data segment corresponding to the constant voltage data in the battery data according to the current position point and the voltage and power curve segment after the current position point. On the basis of the above embodiment, "determining the battery data segment corresponding to the constant voltage data in the battery data according to the current position point and the voltage and power curve segment" in S603 above includes the following steps S801-S802:

[0161] S801, taking the current position point and the voltage and power curve segment after the current position point as the first initial data segment corresponding to the constant voltage data.

[0162] S802, determining the battery data segment corresponding to the constant voltage data in the battery data according to the first initial data segment.

[0163] In a possible implementation manner, the first initial data segment may be used as the battery data segment corresponding to the constant voltage data in the battery data. Exemplarily, as Figure 7 shown, the voltage and power curve segment after the B1 position point and the B1 position point may be used as the battery data segment corresponding to the constant voltage data in the battery data.

[0164] In another possible implementation manner, based on the current data corresponding to the battery data, the second initial data segment corresponding to the constant voltage data may be determined from the voltage and power curve, and the union of the first initial data segment and the second initial data segment is used as the battery data segment corresponding to the constant voltage data.

[0165] The constant current data segment in the current data can be determined, the end data point in the constant current data segment can be determined, the position point corresponding to the end data point can be determined on the voltage and power curve, and the voltage and power curve segment after the position point and the position point is used as the second initial data segment, and then the union of the first initial data segment and the second initial data segment is used as the battery data segment corresponding to the constant voltage data.

[0166] In this embodiment, by taking the current position point and the voltage and power curve segment after the current position point as the first initial data segment corresponding to the constant voltage data, the battery data segment corresponding to the constant voltage data in the battery data is determined, thereby realizing the determination of the battery data segment corresponding to the constant voltage data in the battery data.

[0167] In one embodiment, as Figure 9 shown, Figure 9 FIG. 5 is a schematic flowchart of an abnormal data detection method provided by an embodiment of the present application. This embodiment relates to a possible implementation manner of how to determine the battery data segment corresponding to the constant voltage data in the battery data according to the first initial data segment. On the basis of the above embodiment, the above S802 includes the following steps S901-S904:

[0168] S901, determine the constant current data segment on the current-time curve; the current-time curve is used to characterize the correspondence between the current data and time during the charging and discharging process of the battery.

[0169] After starting to charge the battery with a constant charging current, under normal circumstances, the collected voltage shows an increasing trend. After the battery power reaches a certain level, the charging current begins to decrease, and the voltage fluctuates very little and is almost constant, that is, the voltage begins to enter the constant voltage stage. The process of discharging the battery is opposite to the above charging process. During the discharging process, the voltage shows a decreasing trend. After the battery power reaches a certain level, the discharging current begins to approach 0, and the voltage fluctuates very little and is almost constant, that is, the voltage begins to enter the constant voltage stage. Therefore, the battery data segment corresponding to the constant voltage data in the battery data can be determined in combination with the charging current.

[0170] As Figure 10 shown, Figure 10 FIG. 20 is a schematic diagram of a current-time curve during the charging process of a battery and a voltage-power curve corresponding to the current-time curve provided by an embodiment of the present application. To introduce this embodiment more clearly, it will be introduced in Figure 10 in combination with Figure 7 the voltage-power curve 71. The current-time curve 101 is a curve corresponding to the above voltage-power curve 71, that is, during the charging process of the battery, voltage data, power data, and current data can be obtained. The voltage-power curve is determined based on the voltage data and the power data corresponding to the voltage data, and the current-time curve is determined based on the current data corresponding to the voltage data.

[0171] In a possible implementation, the current difference between two adjacent position points in any current data point group on the current-time curve 101 can be determined. When the absolute value of the current difference is less than or equal to a preset current difference, it is determined that the current corresponding to the current data point group is a constant current. In this way, it can be determined whether the current of each current data point group is a constant current, and the current data segment corresponding to a continuous plurality of current data point groups of the constant current is used as the constant-current data segment. Herein, a current data point group includes two adjacent position points.

[0172] Exemplarily, if the currents corresponding to the 1st current data point group to the 100th current data point group are constant currents, then the current data segment corresponding to the 1st current data point group to the 100th current data point group is used as the constant-current data segment.

[0173] In another possible implementation, the absolute value of the current difference between two current data points in the current current data point group on the current-time curve can also be determined. When the absolute value is greater than or equal to a preset value, the absolute values of the current differences between two current data points in the previous current data point group of the current current data point group are determined until the determined absolute value is less than the preset threshold, and the current data point group corresponding to the absolute value less than the preset threshold and the current data segment before this current data point group are used as the constant-current data segment. Herein, the current current data point group includes the current data point corresponding to the current position point and the previous current data point of the current data point.

[0174] Exemplarily, if the current position point on the voltage-electric quantity curve 71 is B1, then the current current data point group on the current-time curve 101 includes the C1 current data point and the C2 current data point. The absolute value of the current difference between the C1 current data point and the C2 current data point is greater than or equal to the preset value, that is, the current fluctuations between the C1 current data point and the C2 current data point are still relatively large and it is not a constant current. Therefore, then the absolute value of the current difference between the C2 current data point and the C3 current data point is determined. Herein, the C2 current data point and the C3 current data point form the previous current data point group of the current current data point group. As shown in the current-time curve 101, the absolute value of the current difference between the C2 current data point and the C3 current data point is greater than or equal to the preset value, and the current of the C2 current data point and the C3 current data point shows a monotonically decreasing characteristic. By analogy, continue to determine the current difference between the C3 current data point and the previous current data point of the C3 current data point. Assume that the absolute value of the current difference between the C10 current data point and the C11 current data point is less than the preset value, which means that the current data segment before the C10 current data point is the constant-current data segment, the current data segment after the C10 current data point is the non-constant-current data segment, and the current data segment before the C10 current data point is used as the constant-current data segment.

[0175] S902. Determine a target position point on the voltage - electricity curve corresponding to the end - position point of the constant - current data segment.

[0176] Exemplarily, the end - position point of the constant - current data segment is C10, and the target position point on the voltage - electricity curve corresponding to C10 is B10.

[0177] S903. Take the target position point and the voltage - electricity curve segment after the target position point as the second initial data segment.

[0178] Combined with the above example, the position point B10 and the voltage - electricity curve segment after the position point B10 can be taken as the second initial data segment.

[0179] S904. Take the union of the first initial data segment and the second initial data segment as the battery data segment corresponding to the constant - voltage data.

[0180] Exemplarily, combined with the above example, the union of the first initial data segment and the second initial data segment is B10 and the voltage - electricity curve segment after B10, and B10 and the voltage - electricity curve segment after B10 are taken as the battery data segment corresponding to the constant - voltage data.

[0181] In this embodiment, by determining the constant - current data segment on the current - time curve, determining a target position point on the voltage - electricity curve corresponding to the end - position point of the constant - current data segment, taking the target position point and the voltage - electricity curve segment after the target position point as the second initial data segment, and taking the union of the first initial data segment and the second initial data segment as the battery data segment corresponding to the constant - voltage data. Thus, it realizes determining the second initial data segment corresponding to non - constant current based on the current - time curve, and then taking the union of the second initial data segment and the first initial data segment as the battery data segment corresponding to the constant - voltage data, which can take the second initial data segment corresponding to non - constant current as the battery data segment corresponding to the constant - voltage data, and more comprehensively and accurately determine the battery data segment corresponding to the constant - voltage data.

[0182] In one embodiment, when the abnormal data in the detection result does not include the first - type abnormal data, the battery data can also be detected for the third - type abnormal data. In this embodiment, the battery data includes a voltage - electricity curve for characterizing the corresponding relationship between voltage data and electricity data, as Figure 11 shown Figure 11 is the sixth schematic diagram of the abnormal data detection method flow provided by the embodiment of the present application. The method includes the following steps S1101 - S1102:

[0183] S1101. When the abnormal data does not include the battery data segment corresponding to non - constant - current data, obtain the association information between the current position point and the next position point on the voltage - electricity curve.

[0184] S1102. Determine the outlier data points in the battery data according to the associated information.

[0185] In a possible implementation, the associated information includes the distance between the current position point and the next position point. When the distance is greater than or equal to the preset distance, the outlier data points existing in the battery data of the next position point can be determined.

[0186] In another possible implementation, the associated information includes the sampling time interval between the current position point and the next position point. When the sampling time interval is greater than or equal to the preset sampling time interval, the outlier data points existing in the battery data of the next position point can be determined.

[0187] In yet another possible implementation, the associated information includes the distance and the sampling time interval between the current position point and the next position point. When the distance is greater than or equal to the preset distance and the sampling time interval is greater than the preset sampling time interval, the next position point is taken as the outlier data point existing in the battery data.

[0188] In this embodiment, when the abnormal data does not include the battery data segment corresponding to the non-constant current data, the associated information between the current position point and the next position point on the voltage-electricity curve is obtained, and the outlier data points in the battery data are determined according to the associated information.

[0189] In one embodiment, the associated information includes the distance and / or the sampling time interval. For the above S1002, to determine the outlier data points in the battery data according to the associated information, it can be implemented in the following manner:

[0190] When the distance is greater than or equal to the preset distance, and / or, the sampling time interval is greater than the preset sampling time interval, the next position point is taken as the outlier data point existing in the battery data.

[0191] In this embodiment, when the distance is greater than or equal to the preset distance, and / or, the sampling time interval is greater than the preset sampling time interval, the next position point is taken as the outlier data point existing in the battery data. Since the distance and / or the sampling time interval between the current position point and the next position point is directly judged, this method is relatively simple and fast, thus improving the efficiency of determining the outlier data points.

[0192] In one embodiment, when the abnormal data does not include the battery data segment corresponding to the non-constant current data, the battery data can also be detected for the fourth type of abnormal data. This embodiment is for detecting the fourth type of abnormal data. In this embodiment, the battery data includes a voltage-electricity curve for characterizing the correspondence between voltage data and electricity data, such as Figure 12 shown Figure 12It is the seventh schematic flowchart of the abnormal data detection method provided by the embodiments of the present application. The method includes the following steps S1201 - S1202:

[0193] S1201, when the abnormal data does not include the battery data segment corresponding to the non - constant current data, obtain the voltage change trend between the current position point and the next position point on the voltage - electricity curve.

[0194] Among them, the current position point and the next position point on the voltage - electricity curve can be two adjacent data points, or two data points with a preset number of data points in between.

[0195] S1202, when the voltage change trend does not satisfy the monotonicity corresponding to the battery data, determine the outlier data segment in the battery data according to the voltage change trend of the second preset number of position points after the next position point.

[0196] When the voltage change trend of the second preset number of position points satisfies the monotonicity, take the voltage - electricity curve segment between the current position point and the first position point among the second preset number of position points as the outlier data segment.

[0197] Exemplarily, the position points in Table 1 include position point 1 to position point 6. The voltage of position point 1 is 5, and the voltage of position point 2 is 4. The voltages of each position point are shown in Table 1 below. If the current position point is position point 1 and the next position point is position point 2, since the voltage change trend between position point 1 and position point 2 does not satisfy the monotonically increasing characteristic, it is necessary to continue to judge the voltage change trend of the second preset number of position points after position point 2. Taking the second preset number equal to 4 as an example, it can be seen from Table 1 that the voltage change trend of 4 position points after position point 2 satisfies the monotonicity, that is, the voltage change trend of position point 3 to position point 6 satisfies the monotonically increasing characteristic. Therefore, the data segment between position point 1 and position point 3 can be taken as the outlier data segment.

[0198]

[0199] Table 1

[0200] When there is a voltage change trend that does not satisfy the monotonicity in the voltage change trend of the second preset number of position points, obtain the voltage change trend of the second preset number of position points after the last position point that does not satisfy the monotonicity until the voltage change trend of the second preset number of position points obtained most recently satisfies the monotonicity, and take the voltage - electricity curve segment between the current position point and the first position point among the second preset number of position points obtained most recently as the outlier data segment.

[0201] Exemplarily, the position points in Table 2 include position point 1 to position point 11. The voltage of position point 1 is 3, and the voltage of position point 2 is 4. The voltages of each position point are shown in Table 1 below. If the current position point is position point 1 and the next position point is position point 2, since the voltage change trend between position point 1 and position point 2 does not satisfy the monotonically increasing characteristic, it is necessary to continue to judge the voltage change trend of the second preset number of position points after position point 2. Taking the second preset number equal to 4 as an example, it can be seen from Table 2 that the voltage change trend between position point 2 and position point 3 satisfies the monotonically increasing characteristic, and the voltage change trend between position point 3 and position point 4 satisfies the monotonically increasing characteristic. However, the voltage change trend between position point 4 and position point 5 does not satisfy the monotonically increasing characteristic, where position point 5 is the last position point that does not satisfy the monotonicity of the battery data. In this case, it is necessary to then determine the voltage change trend between position point 5 and position point 6. It can be seen from Table 2 that the voltage change trend between position point 5 and position point 6 satisfies the monotonically increasing characteristic. Then, determine the voltage change trend between position point 6 and position point 7. The voltage change trend between position point 6 and position point 7 does not satisfy the monotonically increasing characteristic. Then, determine the voltage change trend of the second preset number of position points after position point 7. Since the voltage change trends between position point 7 and position point 8, between position point 8 and position point 9, between position point 9 and position point 10, and between position point 10 and position point 11 all satisfy the monotonically increasing characteristic, the battery data between position point 1 and position point 8 can be used as the outlier data segment. Or the battery data between position point 2 and position point 7 can be used as the outlier data segment.

[0202]

[0203] Table 2

[0204] As Figure 13 shown Figure 13 is the second schematic diagram of the voltage-electricity curve during the battery charging process provided by the embodiment of the present application, Figure 14 is the third schematic diagram of the voltage-electricity curve during the battery charging process provided by the embodiment of the present application. Figure 13 and Figure 14 the data segments boxed by the rectangular frames in are the outlier data segments.

[0205] In this embodiment, when the abnormal data does not include the battery data segment corresponding to non-constant current data, the voltage change trend between the current position point and the next position point on the voltage-electricity curve is obtained. When the voltage change trend does not satisfy the monotonicity corresponding to the battery data, the outlier data segment in the battery data is determined according to the voltage change trend of the second preset number of position points after the next position point, so as to detect the outlier data segment in the battery data, and then process the battery data based on the outlier data segment to obtain the target battery data, improving the quality of the obtained target battery data.

[0206] In one embodiment, the "determining the outlier data segment in the battery data according to the voltage change trend of the second preset number of position points after the next position point" in S1202 above can be implemented in the following manner:

[0207] When the voltage change trend of the second preset number of position points satisfies monotonicity, the voltage-electricity curve segment between the current position point and the first position point among the second preset number of position points is used as the outlier data segment;

[0208] When there is a voltage change trend that does not satisfy monotonicity in the voltage change trend of the second preset number of position points, obtain the voltage change trend of the second preset number of position points after the last position point that does not satisfy monotonicity until the voltage change trend of the second preset number of position points obtained most recently satisfies monotonicity, and use the voltage-electricity curve segment between the current position point and the first position point among the second preset number of position points obtained most recently as the outlier data segment.

[0209] In this embodiment, the outlier data segment is determined by determining the voltage change trend of the second preset number of position points, that is, by determining the outlier data segment based on the voltage change trend of a sufficient number of position points, so as to improve the accuracy of determining the outlier data segment.

[0210] In one embodiment, as Figure 15 shown, Figure 15 is a schematic flowchart of a method for obtaining target battery data provided by an embodiment of the present application. This embodiment relates to a possible implementation manner of how to process battery data according to abnormal data to obtain target battery data. On the basis of the above embodiment, the "processing the battery data according to abnormal data to obtain target battery data" in S202 above may include the following steps S1501-S1503:

[0211] S1501. For the battery data generated during each charge and discharge process of the battery, when the abnormal data corresponding to the battery data does not include the battery data segment corresponding to the non-constant current data and includes other abnormal data, the abnormal data in the battery data is removed to obtain the remaining battery data; the other abnormal data includes at least one of the battery data segment corresponding to the constant voltage data, the outlier data points, and the outlier data segments.

[0212] S1502. Smooth the remaining battery data to obtain intermediate battery data;

[0213] The remaining battery data can be smoothed using methods such as the Kalman filter method, the linear smoothing method, the median filter method, etc. to obtain intermediate battery data.

[0214] S1503. Perform data completion processing on the missing data in the intermediate battery data to obtain the target battery data.

[0215] Interpolation methods such as the B-spline interpolation method, the K-Nearest Neighbors (KNN) method, the neighboring value interpolation method, and the linear interpolation method can be used to perform data completion processing on the missing data in the intermediate battery data to obtain the target battery data.

[0216] In this embodiment, by removing the abnormal data in the battery data to obtain the remaining battery data when the abnormal data corresponding to the battery data does not include the battery data segment corresponding to the non-constant current data and includes other abnormal data, smoothing the remaining battery data to obtain intermediate battery data, and performing data completion processing on the missing data in the intermediate battery data to obtain the target battery data, the quality of the obtained target battery data is improved.

[0217] Refer to Figure 16 , Figure 16It is a schematic diagram of the overall process of a battery data processing method provided by an embodiment of the present application. The battery data processing method includes two parts: abnormal curve detection and abnormal curve repair. Abnormal curve detection includes extracting voltage data and power data from the test data during the charging and discharging process of the battery, obtaining a voltage-power curve based on the voltage data and power data, and performing non-constant current data detection on the voltage-power curve based on the current window and current data to determine whether the voltage-power curve is a curve corresponding to non-constant current data; in the case where the voltage-power curve is not a curve corresponding to non-constant current data, constant voltage data detection can be performed on the voltage-power curve to detect the battery data segment corresponding to the constant voltage data in the voltage-power curve; and in the case where the voltage-power curve is not a curve corresponding to non-constant current data, outlier data point detection can also be performed on the voltage-power curve to detect outlier data points in the voltage-power curve; in the case where the voltage-power curve is not a curve corresponding to non-constant current data, outlier data segment detection can also be performed on the voltage-power curve to detect outlier data segments in the voltage-power curve. Through abnormal curve detection, normal voltage-power curves in multiple voltage-power curves can be identified, the normal voltage-power curves are called normal data, and voltage-power curves including abnormal data can be identified, and the voltage-power curves including abnormal data are denoted as abnormal voltage-power curves. The abnormal voltage-power curves are data to be repaired.

[0218] Abnormal curve repair refers to repairing the data to be repaired. For abnormal voltage-power curves including battery data segments corresponding to non-constant current data, such abnormal voltage-power curves can be directly discarded. For abnormal voltage-power curves that do not include battery data segments corresponding to non-constant current data, abnormal curve repair includes removing abnormal data in the abnormal voltage-power curve to obtain remaining battery data, smoothing the remaining battery data to obtain intermediate battery data, and performing data completion processing on the missing data in the intermediate battery data to obtain target battery data. The target battery data and the normal voltage-power curves are processed data obtained by detecting and processing the test data, and can be provided for model training.

[0219] It should be understood that although the steps in the flowcharts involved in the above embodiments are sequentially shown according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0220] Based on the same inventive concept, an embodiment of the present application further provides a battery data processing device for implementing the battery data processing method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the battery data processing device provided below can refer to the limitations on the battery data processing method in the above text, and will not be repeated here.

[0221] In one embodiment, as Figure 17 shown, Figure 17 FIG. is a schematic structural diagram of a battery data processing device provided by an embodiment of the present application. The device 1700 includes:

[0222] A detection module 1701, configured to detect battery data during the charging and discharging process of the battery to obtain a detection result of the battery data;

[0223] A processing module 1702, configured to, when the detection result indicates that the battery data includes abnormal data, process the battery data according to the abnormal data to obtain target battery data; the abnormal data includes at least one of a battery data segment corresponding to non-constant current data, a battery data segment corresponding to constant voltage data, an outlier data point, and an outlier data segment.

[0224] In one embodiment, the detection module 1701 is specifically configured to detect the battery data according to the current data corresponding to the battery data during the charging and discharging process of the battery to obtain a detection result of the battery data.

[0225] In one embodiment, the detection module 1701 includes:

[0226] A sorting unit, configured to sort the current data according to the magnitude of the current data to obtain target current data;

[0227] A first determination unit, configured to determine a current window according to the length of the target current data and a preset length ratio;

[0228] An interception unit, configured to intercept the target current data based on the current window to obtain a current data segment;

[0229] A detection unit, configured to detect the battery data according to the current data segment to obtain a detection result of the battery data; the detection result includes whether the battery data includes a battery data segment corresponding to non-constant current data.

[0230] In one embodiment, the detection unit is specifically configured to determine the current difference between the maximum current data and the minimum current data in the current data segment; in the case where the current difference is greater than or equal to a preset current difference, perform an iterative operation; the iterative operation includes moving the current window according to a preset moving step, and intercepting target current data based on the moved current window to obtain a new current data segment; in the case where the current difference corresponding to the new current data segment is greater than or equal to the preset current difference, return to perform the iterative operation; in the case where the current difference corresponding to the new current data segment obtained by the last interception is greater than or equal to the preset current difference, determine that the detection result includes the battery data segment corresponding to the battery data being non-constant current data.

[0231] In one embodiment, the battery data includes a voltage-electricity curve for characterizing the correspondence between voltage data and electricity data. The detection module 1701 is further configured to, in the case where the abnormal data does not include the battery data segment corresponding to non-constant current data, obtain the voltage change trend between the current position point and the next position point on the voltage-electricity curve; in the case where the voltage change trend does not satisfy the monotonicity corresponding to the battery data, obtain the voltage change trend of the first preset number of position points after the next position point; in the case where the voltage change trend of the first preset number of position points does not satisfy the monotonicity, determine the battery data segment corresponding to the constant voltage data in the battery data according to the current position point and the voltage-electricity curve segment after the current position point.

[0232] In one embodiment, the detection module 1701 is specifically configured to use the current position point and the voltage-electricity curve segment after the current position point as the first initial data segment corresponding to the constant voltage data; determine the battery data segment corresponding to the constant voltage data in the battery data according to the first initial data segment.

[0233] In one embodiment, the detection module 1701 is specifically configured to determine the constant current data segment on the current-time curve; the current-time curve is used to characterize the correspondence between the current data and time during the battery charging and discharging process; determine the target position point corresponding to the end position point of the constant current data segment on the voltage-electricity curve; use the target position point and the voltage-electricity curve segment after the target position point as the second initial data segment; use the union of the first initial data segment and the second initial data segment as the battery data segment corresponding to the constant voltage data.

[0234] In one embodiment, the battery data includes a voltage-electricity curve for characterizing the correspondence between voltage data and electricity data. The detection module 1701 is further configured to, in the case where the abnormal data does not include the battery data segment corresponding to non-constant current data, obtain the association information between the current position point and the next position point on the voltage-electricity curve; determine the outlier data points in the battery data according to the association information. [[ID=]14]

[0235] In one embodiment, the association information includes a distance and / or a sampling time interval. The detection module 1701 is specifically configured to use the next position point as an outlier data point in the battery data when the distance is greater than or equal to a preset distance and / or the sampling time interval is greater than a preset sampling time interval.

[0236] In one embodiment, the battery data includes a voltage-electricity curve for characterizing the correspondence between voltage data and electricity quantity data. The detection module 1701 is further configured to obtain the voltage change trend between the current position point and the next position point on the voltage-electricity curve when the abnormal data does not include a battery data segment corresponding to non-constant current data; and determine an outlier data segment in the battery data according to the voltage change trend of the second preset number of position points after the next position point when the voltage change trend does not satisfy the monotonicity corresponding to the battery data.

[0237] In one embodiment, the detection module 1701 is specifically configured to use the voltage-electricity curve segment between the current position point and the first position point among the second preset number of position points as the outlier data segment when the voltage change trend of the second preset number of position points satisfies monotonicity; and obtain the voltage change trend of the second preset number of position points after the last position point that does not satisfy monotonicity until the voltage change trend of the second preset number of position points obtained most recently satisfies monotonicity, and use the voltage-electricity curve segment between the current position point and the first position point among the second preset number of position points obtained most recently as the outlier data segment when there is a voltage change trend that does not satisfy monotonicity in the voltage change trend of the second preset number of position points.

[0238] In one embodiment, the battery data includes battery data generated during multiple battery charge and discharge processes. The processing module 1702 is specifically configured to, for the battery data generated during each battery charge and discharge process, remove the abnormal data in the battery data to obtain remaining battery data when the abnormal data corresponding to the battery data does not include a battery data segment corresponding to non-constant current data and includes other abnormal data; where the other abnormal data includes at least one of a battery data segment corresponding to constant voltage data, an outlier data point, and an outlier data segment; perform smoothing processing on the remaining battery data to obtain intermediate battery data; and perform data completion processing on the missing data in the intermediate battery data to obtain target battery data.

[0239] Each module in the above battery data processing device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in hardware form or be independent of it, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to the above respective modules.

[0240] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps of any of the above method embodiments are implemented. The technical principle and technical effect are similar, and will not be elaborated here.

[0241] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above method embodiments are implemented. The technical principle and technical effect are similar, and will not be elaborated here.

[0242] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps of any of the above method embodiments are implemented. The technical principle and technical effect are similar, and will not be elaborated here.

[0243] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0244] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memories can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0245] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0246] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and they should all be covered within the scope of the claims and the description of the present application. In particular, as long as there is no structural conflict, the technical features mentioned in each embodiment can be combined in any way. The present application is not limited to the specific embodiments disclosed in the text, but includes all technical solutions falling within the scope of the claims.

Claims

1. A battery data processing method, characterized in that, The method includes: Detecting battery data during the charging and discharging process of the battery to obtain a detection result of the battery data; In the case where the detection result indicates that the battery data includes abnormal data, processing the battery data according to the abnormal data to obtain target battery data; the abnormal data includes at least one of a battery data segment corresponding to non-constant current data, a battery data segment corresponding to constant voltage data, an outlier data point, and an outlier data segment.

2. The method according to claim 1, characterized in that The detecting battery data during the charging and discharging process of the battery to obtain a detection result of the battery data includes: Detecting the battery data according to the current data corresponding to the battery data during the charging and discharging process of the battery to obtain a detection result of the battery data.

3. The method according to claim 2, wherein The detecting the battery data according to the current data corresponding to the battery data during the charging and discharging process of the battery to obtain a detection result of the battery data includes: Sorting the current data according to the magnitude of the current data to obtain target current data; Determining a current window according to the length of the target current data and a preset length ratio; Intercepting the target current data based on the current window to obtain a current data segment; Detecting the battery data according to the current data segment to obtain a detection result of the battery data; the detection result includes whether the battery data includes a battery data segment corresponding to non-constant current data.

4. The method according to claim 3, wherein The detecting the battery data according to the current data segment to obtain a detection result of the battery data includes: Determining a current difference between the maximum current data and the minimum current data in the current data segment; In the case where the current difference is greater than or equal to a preset current difference, performing an iterative operation; the iterative operation includes moving the current window according to a preset moving step length, and intercepting the target current data based on the moved current window to obtain a new current data segment; In the case where the current difference corresponding to the new current data segment is greater than or equal to the preset current difference, returning to perform the iterative operation; In the case where the current difference corresponding to the new current data segment obtained by the last interception is greater than or equal to the preset current difference, determining that the detection result includes that the battery data is a battery data segment corresponding to non-constant current data.

5. The method according to any one of claims 1 to 4, characterized in that The battery data includes a voltage-electricity curve for characterizing the correspondence between voltage data and electricity data, and the method further includes: In the case where the abnormal data does not include a battery data segment corresponding to non-constant current data, obtaining a voltage change trend between the current position point and the next position point on the voltage-electricity curve; In the case where the voltage change trend does not satisfy the monotonicity corresponding to the battery data, obtaining a voltage change trend of a first preset number of position points after the next position point; In the case where the voltage change trend of the first preset number of position points does not satisfy the monotonicity, determining a battery data segment corresponding to constant voltage data in the battery data according to the current position point and the voltage-electricity curve segment after the current position point.

6. The method according to claim 5, wherein Determining the battery data segment corresponding to the constant voltage data according to the current position point and the voltage-electricity curve segment after the current position point includes: Taking the current position point and the voltage-electricity curve segment after the current position point as the first initial data segment corresponding to the constant voltage data; Determining the battery data segment corresponding to the constant voltage data in the battery data according to the first initial data segment.

7. The method according to claim 6, wherein The determining the battery data segment corresponding to the constant voltage data in the battery data according to the first initial data segment includes: Determining the constant current data segment on the current-time curve; the current-time curve is used to characterize the correspondence between the current data and time during the charging and discharging process of the battery; Determining a target position point on the voltage-electricity curve corresponding to the end position point of the constant current data segment; Taking the target position point and the voltage-electricity curve segment after the target position point as the second initial data segment; Taking the union of the first initial data segment and the second initial data segment as the battery data segment corresponding to the constant voltage data.

8. The method according to any one of claims 1 to 4, characterized in that The battery data includes a voltage-electricity curve for characterizing the correspondence between voltage data and electricity data, and the method further includes: When the abnormal data does not include the battery data segment corresponding to non-constant current data, obtaining the association information between the current position point and the next position point on the voltage-electricity curve; Determining the outlier data points in the battery data according to the association information.

9. The method according to claim 8, wherein The association information includes distance and / or sampling time interval, and the determining the outlier data points in the battery data according to the association information includes: When the distance is greater than or equal to the preset distance, and / or, the sampling time interval is greater than the preset sampling time interval, taking the next position point as the outlier data point in the battery data.

10. The method according to any one of claims 1 to 4, characterized in that The battery data includes a voltage-electricity curve for characterizing the correspondence between voltage data and electricity data, and the method further includes: When the abnormal data does not include the battery data segment corresponding to non-constant current data, obtaining the voltage change trend between the current position point and the next position point on the voltage-electricity curve; When the voltage change trend does not satisfy the monotonicity corresponding to the battery data, determining the outlier data segment in the battery data according to the voltage change trend of the second preset number of position points after the next position point.

11. The method according to claim 10, characterized in that, The determining the outlier data segment in the battery data according to the voltage change trend of the second preset number of position points after the next position point includes: When the voltage change trend of the second preset number of position points satisfies the monotonicity, taking the voltage-electricity curve segment between the current position point and the first position point among the second preset number of position points as the outlier data segment; In the case that there is a voltage change trend that does not satisfy the monotonicity among the voltage change trends of the second preset number of position points, the voltage change trends of the second preset number of position points after the last position point that does not satisfy the monotonicity are obtained, until the voltage change trend of the second preset number of position points obtained most recently satisfies the monotonicity, and the voltage and power curve segment between the current position point and the first position point of the second preset number of position points obtained most recently is used as the outlier data segment.

12. The method according to any one of claims 1 to 4, characterized in that The battery data includes battery data generated during multiple battery charge and discharge processes, and the processing of the battery data according to the abnormal data to obtain target battery data includes: For the battery data generated during each battery charge and discharge process, if the abnormal data corresponding to the battery data does not include the battery data segment corresponding to the non-constant current data and includes other abnormal data, the abnormal data in the battery data is removed to obtain remaining battery data; the other abnormal data includes at least one of a battery data segment corresponding to the constant voltage data, an outlier data point, and an outlier data segment; Smoothing the remaining battery data to obtain intermediate battery data; The target battery data is obtained by performing data completion processing on the missing data in the intermediate battery data.

13. A battery data processing device, characterized in that, The device comprises: A detection module, configured to detect battery data during the battery charging and discharging process and obtain a detection result of the battery data; a processing module for processing the battery data according to the abnormal data to obtain target battery data when the detection result indicates that the battery data includes abnormal data; the abnormal data includes at least one of a battery data segment corresponding to non-constant current data, a battery data segment corresponding to constant voltage data, an outlier data point, and an outlier data segment.

14. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 12 are implemented.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

16. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images