Battery capacity anomaly detection method and device, computer device, and storage medium

Abstract

The application relates to the technical field of battery safety, and discloses a battery capacity abnormality detection method and device, computer equipment and a storage medium, the method comprising the following steps: extracting a full-life-cycle capacity retention rate of a battery to be detected; constructing a sliding time window of the capacity retention rate; and performing battery capacity abnormality detection based on the relationship between the median of the capacity retention rate in the sliding time window and a preset threshold value. The application covers the full life cycle of the battery in the detection data, and the median of the capacity retention rate in the sliding time window and the preset threshold value are used to detect the battery capacity abnormality in the full life cycle of the battery, so that the problem that the evaluation of the on-board power battery of an electric vehicle is easily affected by uneven data with large skewness and deviated is solved.

Description

Technical Field

[0001] This invention relates to the field of battery safety technology, specifically to a method, apparatus, computer equipment, and storage medium for detecting abnormal changes in battery capacity. Background Technology

[0002] The current automotive market suffers from an underdeveloped network of service outlets for the repair and replacement of electric vehicle batteries, as well as an immature mechanism for the collection, transmission, and sharing of relevant information. This makes it difficult for insurance companies to efficiently and cost-effectively obtain records of whether the batteries have been repaired or replaced when conducting electric vehicle insurance business. Consequently, this leads to a series of problems that make it difficult to carry out risk assessment work for insurance business.

[0003] Currently, the evaluation of vehicle power batteries is based on power battery voltage and temperature data. A sliding time window is used to take the average value of the sampled data and the standard deviation of its variation as a state indicator to assess the risk of the vehicle's power battery. However, the average value does not have the property of resisting outlier interference and is easily affected by unbalanced data with large skewness, resulting in bias. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, computer equipment and storage medium for detecting battery capacity variations, in order to solve the problem that the current evaluation of electric vehicle on-board power batteries is easily affected by unbalanced data with large bias.

[0005] In a first aspect, the present invention provides a method for detecting abnormal changes in battery capacity, the method comprising:

[0006] Extract the capacity retention rate of the battery throughout its entire life cycle;

[0007] Construct a sliding time window for capacity retention;

[0008] Battery capacity anomaly detection is performed based on the relationship between the median capacity retention rate and a preset threshold within a sliding time window.

[0009] The battery capacity variation detection method provided in this invention extracts the capacity retention rate of the battery throughout its entire life cycle, constructs a sliding time window of the capacity retention rate, and detects battery capacity variation by comparing the median of the capacity retention rate in the sliding time window with a preset threshold. The detection data covers the entire life cycle of the battery. At the same time, the method uses the relationship between the median of the capacity retention rate in the sliding time window and the preset threshold to detect battery capacity variation throughout the entire life cycle, which solves the problem that the current evaluation of electric vehicle on-board power batteries is easily affected by unbalanced data with large skewness, resulting in deviations.

[0010] In one alternative implementation, before constructing the sliding time window for capacity retention, the method further includes:

[0011] Extract timestamp data of the entire lifecycle of the battery under test;

[0012] Sorting capacity retention rates based on timestamp data;

[0013] Preprocessing is performed on the capacity retention rate after sorting to detect outliers, abnormal values, and duplicate values ​​at the same time.

[0014] The battery capacity variation detection method provided in this invention sorts the capacity retention rate based on the timestamp data of the entire battery life cycle, and performs detection preprocessing to remove outliers and duplicates from the sorted capacity retention rate. This method has high efficiency in acquiring the timestamp data of the entire battery life cycle, saves costs, and makes the capacity retention rate data more complete and accurate.

[0015] In one alternative implementation, constructing the sliding time window for capacity retention includes:

[0016] The grid length is set based on the total amount of data used to maintain capacity; the total amount of data used to maintain capacity is greater than the grid length.

[0017] Set the sliding time window according to the grid length based on the timestamp data.

[0018] The battery capacity variation detection method provided in this embodiment of the invention selects capacity retention rate measurement data within a time range that conforms to the grid length by setting a grid length, and sets a sliding time window according to the grid length using timestamp data, thus providing a detection window for subsequent battery capacity variation detection.

[0019] In one optional implementation, battery capacity anomaly detection is performed based on the relationship between the median capacity retention rate within a sliding time window and a preset threshold, including:

[0020] Determine whether the total amount of data with capacity retention after preprocessing is greater than the grid length.

[0021] When the total amount of capacity retention data is greater than the size of the grid length, battery capacity anomaly detection is performed based on the relationship between the median of capacity retention rate and a preset threshold within the sliding time window.

[0022] When the total amount of capacity retention data is less than the grid length, the extracted capacity retention data for the entire life cycle of the battery to be tested will be discarded.

[0023] The battery capacity change detection method provided in this invention compares the total amount of capacity retention rate data with the grid length, discards the full life cycle capacity retention rate of the battery under test that does not meet the detection conditions, and uses the relationship between the median of the capacity retention rate in the sliding time window and a preset threshold to detect the battery capacity change of the battery under test that meets the detection conditions. This achieves dynamic detection, improves detection efficiency, and saves detection costs.

[0024] In one optional implementation, detecting battery capacity anomalies based on the relationship between the median capacity retention rate within a sliding time window and a preset threshold includes:

[0025] Set the midpoint of each sliding time window;

[0026] The median is the median value from the middle time point to the last time point of the sliding time window, and the median value from the start of the sliding time window to the middle time point is the second median.

[0027] The difference between the first median and the second median is used as the first median difference;

[0028] Battery capacity variation is detected based on the relationship between the first median difference and the first preset threshold and the second preset threshold.

[0029] The battery capacity variation detection method provided in this embodiment of the invention extracts the first median and the second median in a sliding time window, and then calculates the difference between the first median and the second median. The battery capacity variation is detected by the relationship between the difference between the first median and the first preset threshold and the second preset threshold. This method can achieve accurate detection of battery capacity variation with high detection efficiency.

[0030] In one optional implementation, detecting battery capacity anomalies based on the relationship between the first median difference and a first preset threshold and a second preset threshold for capacity retention includes:

[0031] When the difference of the first median is greater than the first preset threshold, it is determined that the battery under test has signs of repair or replacement at the center of the sliding time window.

[0032] When the difference in the first median is less than the first preset threshold, it is then determined whether the difference in the first median is less than the second preset threshold.

[0033] When the difference of the first median is less than the second preset threshold, it is determined that the battery under test has a fault or a change in battery capacity at the center of the sliding time window.

[0034] When the difference between the first median and the second preset threshold is greater than the second preset threshold, the battery capacity change is detected by sliding a preset time step backward on the sliding time window according to the timestamp data, and the relationship between the difference between the first median and the first preset threshold and the second preset threshold is used to continue to detect the change.

[0035] The battery capacity variation detection method provided in this invention determines that the battery under test has repair or replacement traces at the center of the sliding time window when the first median difference is greater than the first preset threshold. When the first median difference is less than the second preset threshold, it determines that the battery under test has a fault or battery capacity variation at the center of the sliding time window. When the first median difference is greater than the second preset threshold, the battery capacity variation is detected by sliding a preset time step backward according to the timestamp data on the sliding time window, and the battery capacity variation is detected again according to the relationship between the first median difference and the first and second preset thresholds. This method can detect rust or replacement traces, faults or capacity variations in the battery under test, and achieves dynamic detection, thus achieving the goal of high-efficiency and low-cost identification of the repair or replacement status of the battery under test.

[0036] In an alternative implementation, the method further includes: detecting the time point of occurrence of the battery under test that exhibits a change in battery capacity based on all first median differences determined using a sliding time window.

[0037] In one alternative implementation, detecting the time point of change in the battery under test that shows a capacity change based on all first median differences determined using a sliding time window includes:

[0038] Generate a list of datasets consisting of the first median differences of the sliding time windows;

[0039] Get the first second median difference in the dataset list that is greater than the first preset threshold, and the third median difference that is less than the first preset threshold after the second median difference;

[0040] The largest median difference between the second and third median differences was selected, and the time point of the largest median difference was taken as the time point of the anomaly.

[0041] Record the number of times the battery capacity changes and the time when the changes occur. Based on the timestamp data, slide the dataset list in the sliding time window forward by a preset time step until the last value in the dataset list is reached.

[0042] The battery capacity change detection method provided in this invention uses the difference of all first medians determined by a sliding time window to detect the time point of change in the battery under test that has experienced a capacity change. It can accurately detect the time point of battery capacity change and has the characteristics of high efficiency and low cost in identifying battery repair traces and battery capacity change time points.

[0043] Secondly, the present invention provides a battery capacity change detection device, the device comprising:

[0044] The extraction module is used to extract the capacity retention rate of the battery throughout its entire life cycle.

[0045] A building block for constructing a sliding time window for capacity retention;

[0046] The detection module is used to detect battery capacity anomalies based on the relationship between the median of the capacity retention rate in a sliding time window and a preset threshold.

[0047] Thirdly, the present invention provides a computer device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the battery capacity change detection method of the first aspect or any corresponding embodiment described above.

[0048] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the battery capacity change detection method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0049] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0050] Figure 1 This is a schematic flowchart of a battery capacity change detection method according to an embodiment of the present invention;

[0051] Figure 2 This is a flowchart illustrating another method for detecting battery capacity variations according to an embodiment of the present invention.

[0052] Figure 3 This is a flowchart illustrating another method for detecting abnormal battery capacity according to an embodiment of the present invention;

[0053] Figure 4 This is a flowchart illustrating another method for detecting abnormal battery capacity according to an embodiment of the present invention.

[0054] Figure 5 This is a diagram showing the detection data of the middle value difference in the sliding time window according to an embodiment of the present invention;

[0055] Figure 6 This is a diagram showing the detection results of abnormal capacity changes in the battery to be tested according to an embodiment of the present invention;

[0056] Figure 7 This is a structural block diagram of a battery capacity change detection device according to an embodiment of the present invention;

[0057] Figure 8 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] As described in the background section, related technologies use the average value of sampled data within a sliding time window as a state indicator. However, the average value does not have the property of resisting outlier interference and is easily affected by unbalanced data with large skewness, resulting in deviation.

[0060] In view of this, this invention provides a method for detecting battery capacity anomalies. It utilizes a sliding time window to calculate the median as an evaluation index. The median is a representative value of all capacity retention rates determined by its position among all capacity retention rates, and is unaffected by the maxima or minima in the capacity retention rate distribution series. This improves the representativeness of the median to a certain extent and avoids bias caused by unbalanced data with large skewness. Therefore, when there is a certain error between the sampled data and the true value, and the data exhibits discrete fluctuations, using the median can more effectively avoid the influence of abnormal data on the detection results.

[0061] According to an embodiment of the present invention, a method for detecting changes in battery capacity is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0062] This embodiment provides a method for detecting abnormal changes in battery capacity, which can be used in electric vehicles. Figure 1 This is a flowchart of a battery capacity change detection method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0063] Step S101: Extract the full lifecycle capacity retention rate of the battery under test. Specifically, obtain the vehicle identification number (VIN) of the vehicle under test, and extract the full lifecycle capacity retention rate of the vehicle's battery from the new energy vehicle network operation data. The capacity retention rate refers to the ratio of the current full-charge capacity of the battery under test to its initial charge capacity when it was manufactured. By using the SOC and charge capacity data of the vehicle during each charge in the vehicle network operation data, the relative full-charge capacity is calculated, and then divided by its initial full-charge capacity when it was manufactured, the current capacity retention rate of the vehicle's battery can be obtained. This is equivalent to obtaining the capacity retention rate of the vehicle for each charge. The full lifecycle refers to the period from when the vehicle is put into service until its retirement. Obtaining the full lifecycle data of the vehicle battery refers to all operational record data within the period from when the vehicle battery is put into service until its retirement, meaning the detection range can cover all moments during the vehicle battery's service life. The full lifecycle capacity retention rate forms a distribution series.

[0064] Step S102: Construct a sliding time window for capacity retention rate. Specifically, the sliding time window refers to setting a detection window based on the total capacity retention rate to detect changes in battery capacity. The detection window is set according to a preset grid length, with the grid length measured in frames or rows. The sliding time window is a dynamic time window. For example, to construct the sliding time window for capacity retention rate, the grid length w of the sliding time window can be preset based on the total capacity retention rate over the entire vehicle lifecycle.

[0065] Step S103 involves detecting battery capacity anomalies based on the relationship between the median of the capacity retention rate within a sliding time window and a preset threshold. Specifically, the median of the capacity retention rate within a sliding time window refers to the median value between the first half and the second half of the capacity retention rate data within the sliding time window. The preset threshold needs to be set in advance. The median is obtained through sorting and is not affected by the maximum or minimum extreme values. Changes in some data points do not affect the median; it is often used to describe the central tendency of a set of data when individual data points fluctuate significantly. For example, when using the relationship between the median and the preset threshold to detect battery capacity anomalies, when a battery capacity anomaly causes a significant change in the battery capacity retention rate, the median will reflect the trend of this significant change in the battery capacity retention rate.

[0066] The battery capacity variation detection method provided in this invention extracts the capacity retention rate of the battery throughout its entire life cycle, constructs a sliding time window for the capacity retention rate, and detects data covering the entire life cycle of the battery. At the same time, it uses the relationship between the median of the capacity retention rate in the sliding time window and a preset threshold to detect battery capacity variation throughout the entire life cycle, which solves the problem that the current evaluation of electric vehicle on-board power batteries is easily affected by unbalanced data with large skewness and causes deviations.

[0067] This embodiment provides a method for detecting abnormal changes in battery capacity, which can be used in electric vehicles. Figure 2 This is a flowchart of a battery capacity change detection method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0068] Step S201: Extract the capacity retention rate of the battery throughout its entire lifecycle. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0069] Step S202: Extract the timestamp data for the entire lifecycle of the battery to be tested. Specifically, the timestamp data refers to the time point corresponding to each extracted capacity retention rate. The purpose of the timestamps is to sort the calculated capacity retention rate values ​​in chronological order for subsequent detection of battery capacity anomalies. The timestamp data for the entire lifecycle refers to the time points corresponding to all capacity retention rates from the time the vehicle battery is put into service until its retirement.

[0070] Step S203: Sort the capacity retention rates based on timestamp data; preprocess the sorted capacity retention rates by outlier detection, abnormal value detection, and duplicate value detection at the same time. Specifically, the acquired capacity retention rates are sorted according to the chronological order of the timestamp data. After organizing the capacity retention rate array, outlier detection is performed to identify abnormal data that deviates significantly from the normal capacity retention rate. Then, abnormal value detection and duplicate value detection at the same time are performed to remove outliers and duplicate values.

[0071] Step S204: Construct a sliding time window for capacity retention.

[0072] Specifically, step S204 includes:

[0073] Step S2041: Set the grid length based on the total data volume of the capacity retention rate; the total data volume of the capacity retention rate is greater than the grid length. Specifically, in order to construct the capacity change detection window, the grid length w of the sliding time window is set according to the data volume of the entire vehicle lifecycle. The grid length w must be less than the total data volume of the capacity retention rate so that the sliding time window is a dynamic time window based on the total capacity retention rate.

[0074] Step S2042: Set a sliding time window based on the timestamp data and the grid length. Specifically, the grid length is set according to the time sequence of the acquired timestamp data to form a sliding time window based on the capacity retention rate. The first sliding time window is set on the capacity retention rate of the first timestamp data.

[0075] Step S205: Detect battery capacity anomalies based on the relationship between the median of capacity retention rate and a preset threshold within the sliding time window.

[0076] Specifically, step S205 includes:

[0077] Step S2051: Determine whether the total amount of data for the preprocessed capacity retention rate is greater than the size of the grid length. Specifically, the total amount of the preprocessed capacity retention rate will be smaller due to the removal of outliers and duplicates. Therefore, it is necessary to compare again whether the total amount of data for the preprocessed capacity retention rate is greater than the size of the grid length.

[0078] Step S2052: When the total amount of capacity retention data is greater than the size of the grid length, battery capacity anomaly detection is performed based on the relationship between the median of capacity retention rate and a preset threshold in the sliding time window.

[0079] In some optional implementations, step S2052 above includes:

[0080] Step a1: Set the midpoint time point of each sliding time window; specifically, the sliding time window is equal to the size w of the grid length, and the midpoint time point is the time point corresponding to the timestamp of the w / 2th value in each sliding time window.

[0081] Step a2: Extract the median value from the middle time point to the last time point of the sliding time window as the first median, and extract the median value from the start point of the sliding time window to the middle time point as the second median; specifically, as follows... Figure 4 As shown, the sliding time window is divided into data segments of 0 to w / 2 and w / 2 to w, with the size equal to the grid length w. The first median is the middle value between the data segments w / 2 and w, and the second median is the middle value between the data segments 0 and w / 2.

[0082] Step a3: The difference between the first median and the second median is used as the first median difference; specifically, the median between the data segments w / 2 and w is used as the first median, and the median between the data segments 0 and w / 2 is used as the second median. The difference between the first median and the second median is used to obtain the first median difference Ki.

[0083] Step a4: Detect battery capacity anomalies based on the relationship between the first median difference and the first preset threshold and the second preset threshold.

[0084] In some alternative implementations, step a4 above includes:

[0085] Step a41: When the difference in the first median is greater than the first preset threshold, it is determined that the battery under test has signs of repair or replacement at the center of the sliding time window; specifically, as follows... Figure 4 As shown, the first preset threshold is set as the upper limit threshold μ1 for capacity retention rate variation. When the first median difference Ki is greater than the first preset threshold μ1, it is determined that the battery under test has signs of repair or replacement at the center of the sliding time window. The first preset threshold μ1 is a pre-set upper limit threshold for capacity retention rate. When the first median difference Ki is greater than the first preset threshold μ1, it means that the current battery capacity retention rate is greater than the pre-set upper limit threshold for capacity retention rate, and the capacity retention rate has reached a new high. At this time, it means that the battery's energy storage function is the energy storage capacity of a newly manufactured battery, so it is determined that the battery has been repaired or replaced, causing the battery capacity retention rate to exceed the pre-set upper limit threshold for capacity retention rate.

[0086] Step a42: When the difference in the first median is less than the first preset threshold, determine whether the difference in the first median is less than the second preset threshold; specifically, as follows... Figure 4 As shown, the second preset threshold is set as the lower limit threshold μ2 of the capacity retention rate variation. When the first median difference Ki is less than the first preset threshold μ1, it is determined whether the first median difference Ki is less than the second preset threshold μ2.

[0087] Step a43: When the difference between the first median and the second preset threshold is less than the second preset threshold, it is determined that the battery under test has malfunctioned or has a change in battery capacity at the center of the sliding time window; specifically, as follows... Figure 4As shown, if the first median difference Ki is less than the second preset threshold μ2, it is determined that the battery under test has malfunctioned or has a capacity change at the center of the sliding time window. The second preset threshold μ2 represents the lower limit threshold for the change in capacity retention rate. When the first median difference Ki is less than the second preset threshold μ2, it means that the current battery capacity retention rate is less than the preset lower limit threshold for capacity retention rate, and the capacity retention rate has reached a new low. This indicates that the battery's energy storage function is malfunctioning or abnormal, so it is determined that a malfunction has occurred or there is a capacity change, causing the battery capacity retention rate to be less than the preset lower limit threshold for capacity retention rate.

[0088] Step a44: When the first median difference is greater than the second preset threshold, slide the time window forward by a preset time step according to the timestamp data, and continue to detect battery capacity anomalies based on the relationship between the first median difference and the first and second preset thresholds. A diagram illustrating the median difference detection data in the sliding time window according to an embodiment of the present invention is shown below. Figure 5 As shown, Figure 5 The horizontal axis represents the total number of capacity retention rates, with a total of 800 capacity retention rate data points. The vertical axis represents the median difference of the sliding time window.

[0089] Step S2053: If the total amount of capacity retention data is less than the grid length, the extracted full-lifecycle capacity retention rate of the battery to be tested is discarded. Specifically, after preprocessing and discarding, if the total amount of capacity retention data for the entire vehicle's lifecycle is less than the grid length w, it indicates that the vehicle's battery has insufficient charge-discharge cycles, belonging to a newly manufactured vehicle, and does not meet the target battery requirements for this battery capacity change detection. After more battery charge-discharge cycles, its battery capacity data can be tested and evaluated again. The full-lifecycle capacity retention rate of the target battery that does not meet the requirements is discarded.

[0090] The battery capacity variation detection method provided in this invention sorts the capacity retention rate based on timestamp data of the battery's entire life cycle, and performs detection preprocessing on the sorted capacity retention rate to remove outliers and duplicates. This method achieves high efficiency in acquiring the timestamp data of the battery's entire life cycle, saves costs, and makes the capacity retention rate data more complete and accurate. By setting a grid length, capacity retention rate measurement values ​​within the grid length's time range are selected. A sliding time window is set according to the grid length using the timestamp data, providing a detection window for subsequent battery capacity variation detection. When detecting battery capacity variations, if the difference in the first median is greater than the first preset threshold, it is determined that the battery under test has signs of repair or replacement at the center of the sliding time window. If the difference in the first median is less than the second preset threshold, it is determined that the battery under test has a fault or a battery capacity variation at the center of the sliding time window. If the difference in the first median is greater than the second preset threshold, the time window is moved forward by a preset time step according to the timestamp data, and the battery capacity variation is detected again based on the relationship between the difference in the first median, the first preset threshold, and the second preset threshold. This method can detect rust or replacement marks, faults, or capacity variations in the battery under test, achieving dynamic detection and high-efficiency, low-cost identification of the repair or replacement status of the battery under test.

[0091] This embodiment provides a method for detecting abnormal changes in battery capacity, which can be used in electric vehicles. Figure 3 This is a flowchart of a battery capacity change detection method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0092] Step S301: Extract the capacity retention rate of the battery throughout its entire lifecycle. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0093] Step S302: Construct a sliding time window for capacity retention. See details below. Figure 2 Step S204 of the illustrated embodiment will not be described again here.

[0094] Step S303: Battery capacity anomaly detection is performed based on the relationship between the median capacity retention rate within the sliding time window and a preset threshold. For details, please refer to [link to relevant documentation]. Figure 2 Step S205 of the illustrated embodiment will not be described again here.

[0095] Step S304: Based on the differences of all first median values ​​determined using a sliding time window, detect the time point at which the battery capacity changes during testing occurs.

[0096] Specifically, step S304 includes:

[0097] Step S3041: Generate a list of datasets consisting of the first median differences of the sliding time window; specifically, as shown in... Figure 4 As shown, all the first median differences Kw / 2 to K(nw / 2) calculated by the sliding time window are sequentially formed into a dataset list L, where n is the total amount of data on vehicle lifecycle capacity retention rate, Kw / 2 is the first first median difference in dataset list L, and K(nw / 2) is the last first median difference in dataset list L.

[0098] Step S3042: Obtain the first second median difference value in the dataset list that is greater than the first preset threshold, and the third median difference values ​​after the second median difference value that are less than the first preset threshold; specifically, as shown... Figure 4 As shown, starting from the first median difference Kw / 2, find the first second median difference Kx1 in the dataset list L that exceeds the first preset threshold μ1, and the first third median difference Kx2 that is lower than the first preset threshold μ1 after the second median difference Kx1.

[0099] Step S3043: Select the largest median difference between the second and third median differences, and take the time point of the largest median difference as the time point of the anomaly; specifically, as follows... Figure 5 As shown, the largest median difference Km1 in the dataset list L, which is between the second median difference Kx1 and the third median difference Kx2, is selected. It is determined that the change in the vehicle's capacity retention rate occurs between the time of the m1th charge and the time of the next charge, that is, the battery capacity changes between the time of the m1th charge and the time of the next charge.

[0100] Step S3044: Record the number of battery capacity changes and the time of each change. Based on the timestamp data, slide the dataset list within the sliding time window forward by a preset time step until the last value in the dataset list is reached. Specifically, as shown... Figure 4 As shown, starting from the third median difference Kx2, steps S4042 and S4043 are repeated to find the location of the next capacity jump point in the dataset list L, i.e., the location of the battery capacity change, until the sliding time window reaches the last first median difference K(nw / 2) in the dataset list L. The detection result of the battery capacity change according to an embodiment of the present invention is shown in the figure below. Figure 6 As shown, Figure 6 The horizontal axis represents the total number of capacity retention rates, with a total of 800 capacity retention rate data points.

[0101] After battery maintenance or replacement, the capacity retention rate may exhibit continuous abnormal fluctuations over a prolonged period. Therefore, if the interval between the number of times m2 and m1 of the second maximum median difference Km2 and the maximum median difference Km1 is less than half the grid length w of the sliding time window, the maximum value between Km2 and Km1 is taken as the value of the abnormal capacity jump, and the position of the maximum value is taken as the time node of the capacity jump, i.e., the time point of battery capacity anomaly.

[0102] The battery capacity change detection method provided in this invention uses the difference of all first medians determined by a sliding time window to detect the time point of change in the battery under test that has experienced a capacity change. It can accurately detect the time point of battery capacity change and has the characteristics of high efficiency and low cost in identifying battery repair traces and battery capacity change time points.

[0103] This embodiment also provides a battery capacity change detection device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0104] This embodiment provides a battery capacity change detection device, such as... Figure 7 As shown, it includes:

[0105] The first extraction module 701 is used to extract the capacity retention rate of the battery throughout its entire life cycle.

[0106] Module 702 is used to construct a sliding time window for capacity retention.

[0107] The detection module 703 is used to detect battery capacity anomalies based on the relationship between the median of the capacity retention rate in the sliding time window and a preset threshold.

[0108] The battery capacity variation detection device also includes:

[0109] The second extraction module is used to extract the timestamp data of the entire life cycle of the battery to be tested.

[0110] The preprocessing module is used to sort the capacity retention rate based on timestamp data; and to perform outlier detection, abnormal value detection, and duplicate value detection on the sorted capacity retention rate.

[0111] The second detection module is used to detect the time point of change of the battery under test that has undergone capacity changes based on the differences of all first median values ​​determined by a sliding time window.

[0112] In some alternative implementations, the construction module 702 includes:

[0113] The first setting unit is used to set the grid length based on the total amount of data for capacity retention; the total amount of data for capacity retention is greater than the size of the grid length.

[0114] The second setting unit is used to set the sliding time window according to the grid length based on the timestamp data.

[0115] In some alternative implementations, the detection module 703 includes:

[0116] The judgment unit is used to determine whether the total amount of data with capacity retention after preprocessing is greater than the size of the grid length.

[0117] The detection unit is used to detect battery capacity anomalies based on the relationship between the median of the capacity retention rate and a preset threshold when the total amount of capacity retention rate data is greater than the size of the grid length.

[0118] The discard unit is used to discard the extracted full life cycle capacity retention rate of the battery under test when the total amount of capacity retention rate data is less than the grid length.

[0119] In some alternative implementations, the detection unit includes:

[0120] The first setting sub-unit is used to set the midpoint time point of each sliding time window.

[0121] Extract sub-units to extract the median value from the middle position time point to the last time point of the sliding time window as the first median, and extract the median value from the start point of the sliding time window to the middle position time point as the second median.

[0122] The calculation subunit is used to take the difference between the first median and the second median as the first median difference.

[0123] The detection subunit is used to detect battery capacity changes based on the relationship between the first median difference and the first preset threshold and the second preset threshold.

[0124] In some alternative implementations, the detection subunit includes:

[0125] The first determiner is used to determine that the battery under test has signs of repair or replacement at the center of the sliding time window when the difference of the first median is greater than the first preset threshold.

[0126] The judge is used to determine whether the difference in the first median is less than the second preset threshold when the difference in the first median is less than the first preset threshold.

[0127] The second determiner is used to determine that the battery under test has a fault or a change in battery capacity at the center of the sliding time window when the difference of the first median is less than the second preset threshold.

[0128] The detector is used to slide a preset time step backward on the sliding time window according to the timestamp data when the first median difference is greater than the second preset threshold, and continue to detect battery capacity changes based on the relationship between the first median difference and the first and second preset thresholds.

[0129] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0130] In this embodiment, the battery capacity change detection device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0131] This invention also provides a computer device having the above-described features. Figure 7 The battery capacity change detection device shown.

[0132] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 8 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 Take a processor 10 as an example.

[0133] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0134] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0135] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0136] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0137] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 20 can be connected via a bus or other means. Figure 8 Taking the example of a connection between China and Israel via a bus.

[0138] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0139] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0140] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for detecting abnormal changes in battery capacity, characterized in that, The method includes: Extract the capacity retention rate of the battery throughout its entire life cycle; Construct a sliding time window for the capacity retention rate; Battery capacity anomaly detection is performed based on the relationship between the median of the capacity retention rate within the sliding time window and a preset threshold, including: Set the midpoint of each sliding time window; The median is the median value from the middle time point to the last time point of the sliding time window, and the median value from the start of the sliding time window to the middle time point is the second median. The difference between the first median and the second median is used as the first median difference; Battery capacity variations are detected based on the relationship between the first median difference and the first and second preset thresholds.

2. The method according to claim 1, characterized in that, Before constructing the sliding time window for the capacity retention rate, the method further includes: Extract timestamp data of the entire lifecycle of the battery under test; The capacity retention rate is sorted based on the timestamp data; Preprocessing is performed on the capacity retention rate after sorting to detect outliers, abnormal values, and duplicate values ​​at the same time.

3. The method according to claim 2, characterized in that, The process of constructing the sliding time window for the capacity retention rate includes: The grid length is set based on the total amount of data for the capacity retention rate; the total amount of data for the capacity retention rate is greater than the grid length. Set the sliding time window according to the grid length based on the timestamp data.

4. The method according to claim 3, characterized in that, Battery capacity anomaly detection is performed based on the relationship between the median of the capacity retention rate within the sliding time window and a preset threshold, including: Determine whether the total amount of data with preprocessed capacity retention is greater than the grid length. When the total amount of data on the capacity retention rate is greater than the size of the grid length, battery capacity anomaly detection is performed based on the relationship between the median of the capacity retention rate in the sliding time window and a preset threshold. When the total amount of data on capacity retention rate is less than the size of the grid length, the extracted capacity retention rate of the battery throughout its entire life cycle will be discarded.

5. The method according to claim 1, characterized in that, Detecting battery capacity anomalies based on the relationship between the first median difference and the first and second preset thresholds for capacity retention includes: When the difference of the first median is greater than the first preset threshold, it is determined that the battery under test has signs of repair or replacement at the center of the sliding time window. When the first median difference is less than the first preset threshold, it is determined whether the first median difference is less than the second preset threshold. When the difference of the first median is less than the second preset threshold, it is determined that the battery under test has a fault or a change in battery capacity at the center of the sliding time window. When the first median difference is greater than the second preset threshold, the battery capacity change is detected by sliding a preset time step backward on the sliding time window according to the timestamp data, and the relationship between the first median difference and the first and second preset thresholds is used to continue to detect the battery capacity change.

6. The method according to claim 5, characterized in that, Also includes: The time point at which the battery under test exhibits a capacity change is detected based on all the first median differences determined using a sliding time window.

7. The method according to claim 6, characterized in that, The step of detecting the time point of change in the battery under test based on the difference of all first medians determined by a sliding time window includes: Generate a list of datasets consisting of the first median differences of the sliding time windows; Obtain the first second median difference in the dataset list that is greater than the first preset threshold, and the third median difference that is less than the first preset threshold after the second median difference; The largest median difference between the second and third median differences is selected, and the time point of the largest median difference is taken as the time point of the anomaly. Record the number of times the battery capacity changes and the time when the changes occur. Based on the timestamp data, slide the dataset list in the sliding time window forward by a preset time step until the last value in the dataset list is reached.

8. A battery capacity variation detection device, characterized in that, The apparatus used in the battery capacity change detection method according to any one of claims 1 to 7 includes: The extraction module is used to extract the capacity retention rate of the battery throughout its entire life cycle. A construction module is used to construct the sliding time window of the capacity retention rate; The detection module is used to detect battery capacity anomalies based on the relationship between the median of the capacity retention rate in the sliding time window and a preset threshold.

9. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the computer instructions to perform the battery capacity change detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the battery capacity change detection method according to any one of claims 1 to 7.

Images