Driving behavior recognition method, storage medium, and vehicle
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA FAW CO LTD
- Filing Date
- 2023-10-30
- Publication Date
- 2026-06-19
Smart Images
Figure CN117416361B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of vehicle driving, and more specifically, to a driving behavior recognition method, a storage medium, and a vehicle. Background Technology
[0002] Aggressive driving behavior not only affects the normal operation of a vehicle but may also pose safety hazards. Currently, most methods for identifying aggressive driving behavior rely on threshold judgments based on speed changes, lacking feature recognition of the entire driving segment and identification of battery temperature changes. This results in insufficient coverage of aggressive driving situations and low accuracy in identifying vehicle driving behavior.
[0003] There is currently no effective solution to the above problems. Summary of the Invention
[0004] This invention provides a driving behavior recognition method, a storage medium, and a vehicle to at least address the technical problem of low accuracy in recognizing vehicle driving behavior.
[0005] According to one aspect of the present invention, a driving behavior recognition method is provided, comprising: extracting features from vehicle driving data to obtain the vehicle's acceleration change trend, power change trend, and vehicle battery temperature change trend, wherein the driving data includes at least the vehicle's speed information and battery pack information during driving; analyzing the acceleration change trend and power change trend to determine the rapid acceleration time window of the vehicle during driving; analyzing the temperature change trend to determine the rapid temperature rise window of the battery; and performing overlap analysis on the rapid acceleration time window and the rapid temperature rise window to determine whether a target driving behavior exists within the rapid acceleration time window.
[0006] Furthermore, the acceleration and power change trends are analyzed to determine the rapid acceleration time window during vehicle operation. This includes: determining a first time window in the acceleration change trend, wherein the acceleration information corresponding to the first time window is greater than a preset acceleration threshold; determining a second time window based on the first time window, the power change trend, and the power change rate trend, wherein the number of second time windows is less than or equal to the number of first time windows, and the power change rate trend is obtained based on the power change trend; and extending the second time window to obtain the rapid acceleration time window.
[0007] Further, based on the first time window, the power change trend, and the power change rate trend, a second time window is determined, including: determining whether the power change rate within the power change rate trend is greater than a preset power change rate threshold within the first time window, and whether the power change information within the power change trend is greater than a preset power threshold; in response to the first time window where the power change rate within the power change rate trend is greater than the preset power change rate threshold, and the power change information within the power change trend is greater than the preset power threshold, a corresponding second time window is determined.
[0008] Furthermore, the second time window is extended to obtain a rapid acceleration time window, including: extending the second time window based on a preset extension time to obtain a rapid acceleration time window.
[0009] Furthermore, the temperature change trend is analyzed to determine the time corresponding to the battery meeting the preset temperature rise state as the rapid temperature rise window. This includes: identifying temperature change points in the temperature change trend, where each temperature change point satisfies a preset temperature rise sequence and a preset time sequence; determining the temperature rise time length between two adjacent temperature change points; calculating the corresponding temperature rise rate by analyzing the two adjacent temperature rise time lengths; determining the target temperature rise rate within the temperature rise rate, where the target temperature rise rate is greater than the preset temperature rise rate; and using the time corresponding to the target temperature rise rate as the rapid temperature rise window.
[0010] Furthermore, by performing overlap analysis on the rapid acceleration time window and the rapid temperature rise window, it is determined whether the target driving behavior exists within the rapid acceleration time window, including: calculating the time overlap between the rapid acceleration time window and the target temperature rise window to obtain the actual overlap degree, wherein the target temperature rise window is the minimum value within the rapid temperature rise window; in response to the actual overlap degree being greater than the preset overlap degree, it is determined that the target driving behavior exists within the rapid acceleration time window.
[0011] Furthermore, by performing time overlap calculations on the rapid acceleration time window and the target temperature rise window, the actual overlap is obtained, including: determining the overlapping part of the rapid acceleration time window and the target temperature rise window to obtain the actual overlapping window; and obtaining the ratio of the actual overlapping window to the rapid acceleration time window to obtain the actual overlap.
[0012] Further, before feature extraction from the vehicle's driving data, the process includes: marking the collected vehicle data to obtain driving data, wherein the driving data is used to characterize data where the main positive relay state meets a preset relay state and the charging gun connection state meets a preset connection state, and the driving data meets a preset time series; distinguishing the driving data by time frame breakpoints to obtain a first marker point; calculating the time difference between two adjacent frames of the driving data to obtain multiple time differences; determining the target time difference among the multiple time differences and using the position corresponding to the target time difference as a second marker point, wherein the target time difference is greater than a preset time difference; and dividing the driving data based on the first and second marker points to obtain driving segment data, wherein the driving segment data includes a start time and an end time.
[0013] According to another aspect of the present invention, a driving behavior recognition device is also provided, comprising: an extraction module for extracting features from vehicle driving data to obtain the vehicle's acceleration change trend, power change trend, and vehicle battery temperature change trend, wherein the driving data includes at least the vehicle's speed information and battery pack information during driving; a first analysis module for analyzing the acceleration change trend and power change trend to determine the rapid acceleration time window of the vehicle during driving; a second analysis module for analyzing the temperature change trend to determine the battery's rapid temperature rise window; and a recognition module for performing overlap analysis on the rapid acceleration time window and the rapid temperature rise window to determine whether a target driving behavior exists within the rapid acceleration time window.
[0014] According to a third aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the execution of any of the above-described driving behavior recognition methods in the processor of the device.
[0015] According to a fourth aspect of the present invention, a vehicle is also provided, comprising: one or more processors; a storage device for storing one or more programs; wherein when the one or more programs are executed by the one or more processors, the one or more processors perform any of the above-described driving behavior recognition methods.
[0016] In this embodiment of the invention, by extracting features from the vehicle's driving data, the trends of vehicle acceleration, power, and battery temperature are obtained. The driving data includes at least the vehicle's speed and battery pack information during driving. The acceleration and power trends are analyzed to determine the rapid acceleration time window during driving. The temperature trend is analyzed to determine the rapid temperature rise window of the battery. The rapid acceleration time window and the rapid temperature rise window are overlapped to determine whether the target driving behavior exists within the rapid acceleration time window. It is noteworthy that by performing overlapping analysis on the rapid acceleration time window determined from the acceleration and power change trends and the rapid temperature rise window determined from the temperature change trend, and then determining whether the target driving behavior exists within the rapid acceleration time window based on the actual overlap of the windows, the aim of judging whether the vehicle has violent driving behavior is achieved through three parameters: battery temperature rise, battery power change, and vehicle speed change. This allows the judgment results to comprehensively and realistically reflect the adverse effects of the vehicle's driving behavior on the power battery, thereby achieving the technical effect of identifying vehicle driving behavior based on multiple dimensions, improving the accuracy of vehicle driving behavior identification, and thus solving the technical problem of low accuracy in identifying vehicle driving behavior. Attached Figure Description
[0017] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:
[0018] Figure 1 This is a flowchart of a driving behavior recognition method according to an embodiment of the present invention;
[0019] Figure 2 This is a schematic diagram of an optional rapid acceleration time window calculation method according to an embodiment of the present invention;
[0020] Figure 3 This is a schematic diagram of an optional method for calculating the temperature rise rate according to an embodiment of the present invention;
[0021] Figure 4 This is a schematic diagram of an optional overlap calculation according to an embodiment of the present invention;
[0022] Figure 5 This is a schematic diagram of an optional method for determining temperature change points according to an embodiment of the present invention;
[0023] Figure 6 This is a schematic diagram illustrating an optional method of marking driving data according to an embodiment of the present invention;
[0024] Figure 7This is a schematic diagram of an optional method for marking breakpoints in time difference according to an embodiment of the present invention;
[0025] Figure 8 This is a schematic diagram of an optional segmentation of driving traffic according to an embodiment of the present invention;
[0026] Figure 9 This is a schematic diagram of a driving behavior recognition device according to an embodiment of the present invention. Detailed Implementation
[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0029] Example 1
[0030] According to an embodiment of the present invention, an embodiment of a driving behavior recognition method 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.
[0031] Figure 1 This is a flowchart of a driving behavior recognition method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:
[0032] Step S102: Extract features from the vehicle's driving data to obtain the vehicle's acceleration change trend, power change trend, and battery temperature change trend. The driving data includes at least the vehicle's speed information and battery pack information during driving.
[0033] Specifically, the aforementioned driving data can be used to characterize the vehicle's starting state after high-voltage power is applied. It includes at least the vehicle's speed information during driving and acceleration information determined based on the speed information, as well as the battery pack information in the vehicle. The battery pack information includes at least voltage and current information and battery pack temperature information. Moreover, the aforementioned driving data has a certain time sequence, and typically, the driving data can be sorted in chronological order.
[0034] The aforementioned acceleration change trend can be used to characterize the trend of vehicle acceleration information changing over time by extracting features from driving data acceleration information.
[0035] Generally, the acceleration information corresponding to each time frame can be calculated, and then the acceleration change trend mentioned above can be obtained based on the acceleration information corresponding to each time frame. The acceleration information mentioned above can be calculated using the following formula:
[0036] a i =(v i -v i-1 ) / (t i -t i-1 )
[0037] Where i represents the i-th frame of data, a i v i t i Let v be the acceleration, velocity, and timestamp of the i-th frame of data. i-1 t i-1 The speed and timestamp of the (i-1)th frame of data.
[0038] The aforementioned power change trend can be used to characterize the trend of vehicle power information changing over time by extracting features from driving data.
[0039] Generally, the power information corresponding to each time frame can be calculated, and then the power change trend mentioned above can be obtained based on the power information corresponding to each time frame. The power information mentioned above can be calculated using the following formula:
[0040] P i =U i ×I i
[0041] Among them, U i Ii P represents the total voltage and total current of the i-th frame of data. i Let be the power of the i-th frame of data.
[0042] Furthermore, based on the aforementioned power change trend, the power change rate trend can be calculated using the following formula:
[0043] ΔP i =(P i -P i-1 ) / (t i -t i-1 )
[0044] Among them, P i-1 Let ΔP be the power of the (i-1)th frame of data. i Let be the power change rate of the i-th frame of data.
[0045] Figure 2 This is a schematic diagram of an optional rapid acceleration time window calculation method according to an embodiment of the present invention. Figure 2 As shown, the first line reflects the time-based acceleration trend, the second line reflects the time-based power change rate trend, and the third line reflects the time-based power change trend.
[0046] The temperature change trend described above can be used to characterize the trend of battery pack temperature information changing over time by extracting features from driving data.
[0047] In one optional embodiment, by collecting temperature information for each time frame and marking the collected temperature data, i.e., marking the data points where the temperature increases, multiple marked temperature change points can be obtained, and then the above-mentioned temperature change trend can be obtained based on the multiple temperature change points.
[0048] Figure 3 This is a schematic diagram of an optional method for calculating the temperature rise rate according to an embodiment of the present invention. Figure 3 As shown, this reflects the temperature change trend from temperature change point 1 to temperature change point 8 based on the time sequence, and the temperature at temperature change point 8 is higher than the temperature at temperature change point 1.
[0049] Step S104: Analyze the trends of acceleration and power changes to determine the rapid acceleration time window of the vehicle during driving.
[0050] Specifically, the aforementioned rapid acceleration time window can be used to characterize the time window corresponding to when a vehicle is in a rapid acceleration state during driving.
[0051] In an optional embodiment, during the process of determining the rapid acceleration time window, an acceleration threshold can be preset, and then, based on the acceleration change trend, the time periods corresponding to the acceleration information exceeding the acceleration threshold can be marked to obtain multiple marked time periods. These can be used as condition windows to determine whether the power change rate in the power change rate trend exceeds a preset power change rate and whether the power information in the power change trend exceeds a preset power. If the above judgment conditions exist, the window corresponding to the judgment conditions in the above multiple condition windows is obtained, and the rapid acceleration time window is obtained based on the window.
[0052] Step S106: Analyze the temperature change trend to determine the rapid temperature rise window of the battery.
[0053] Specifically, the aforementioned rapid temperature rise window can be used to characterize the time window corresponding to a vehicle battery being in a state of rapid temperature rise.
[0054] In an optional embodiment, in the process of determining the rapid temperature rise window, multiple temperature change points marked in the above-mentioned temperature change trend can be calculated to calculate the temperature rise rate between two adjacent temperature change points, thereby obtaining multiple temperature rise rates. Then, a target temperature rise rate greater than a preset temperature rise rate is determined from the multiple temperature rise rates, and the segment corresponding to the target temperature rise rate is marked as the above-mentioned rapid temperature rise window.
[0055] Step S108: Perform an overlap analysis on the rapid acceleration time window and the rapid temperature rise window to determine whether the target driving behavior exists within the rapid acceleration time window.
[0056] Specifically, the aforementioned target driving behavior can be used to characterize a vehicle exhibiting aggressive driving behavior.
[0057] Generally, aggressive driving behavior refers to driving a vehicle on the road at high speeds, with sudden braking, sharp turns, etc. When a vehicle engages in such aggressive driving behavior, it inevitably causes significant changes in the vehicle's speed and the battery pack's temperature. Therefore, by overlaying the rapid acceleration time window corresponding to acceleration and the rapid temperature rise window corresponding to rapid temperature rise, it can be determined whether the target driving behavior exists within the rapid acceleration time window.
[0058] In one optional embodiment, by analyzing the trends of acceleration and power changes, the rapid acceleration time window of the vehicle during driving is determined. Simultaneously, by analyzing the temperature change trend, the rapid temperature rise window of the battery is determined. By performing overlap analysis on the rapid acceleration time window and the rapid temperature rise window, it is determined whether the rapid acceleration time window and the rapid temperature rise window overlap. If the rapid acceleration time window and the rapid temperature rise window overlap, it indicates that both the rapid acceleration state of the vehicle and the rapid temperature rise state of the battery pack exist within the overlapping window. Then, based on the overlapping window, it is determined whether there is a target driving behavior within the rapid acceleration time window. Specifically, it is necessary to determine whether there is a target driving behavior within the rapid acceleration time window by the actual overlap degree corresponding to the overlapping window. If the actual overlap degree is greater than the preset overlap degree, it is determined that there is a target driving behavior within the rapid acceleration time window; otherwise, it is determined that there is no target driving behavior.
[0059] Figure 4 This is a schematic diagram of an optional overlap calculation according to an embodiment of the present invention. Figure 4 As shown, a_len represents the length of the rapid acceleration window, temp_len represents the length of the rapid temperature rise window, and Δr represents the length of the overlapping portion of the rapid acceleration window and the rapid temperature rise window. This indicates that Δr contains both the rapid acceleration state of the vehicle and the rapid temperature rise state of the battery pack.
[0060] In summary, by extracting features from vehicle driving data, we obtain the trends in vehicle acceleration, power, and battery temperature. The driving data includes at least the vehicle's speed and battery pack information during driving. Analysis of the acceleration and power trends identifies the rapid acceleration time window during driving; analysis of the temperature trend identifies the rapid temperature rise window of the battery; and overlapping analysis of the rapid acceleration and rapid temperature rise windows determines whether the target driving behavior exists within the rapid acceleration time window. It is noteworthy that by performing overlapping analysis on the rapid acceleration time window determined from the acceleration and power change trends and the rapid temperature rise window determined from the temperature change trend, and then determining whether the target driving behavior exists within the rapid acceleration time window based on the actual overlap of the windows, the aim of judging whether the vehicle has violent driving behavior is achieved through three parameters: battery temperature rise, battery power change, and vehicle speed change. This allows the judgment results to comprehensively and realistically reflect the adverse effects of the vehicle's driving behavior on the power battery, thereby achieving the technical effect of identifying the vehicle's driving behavior based on multiple dimensions and improving the accuracy of vehicle driving behavior identification. This solves the technical problem of low accuracy in identifying vehicle driving behavior.
[0061] Optionally, the acceleration change trend and power change trend are analyzed to determine the rapid acceleration time window of the vehicle during driving, including: determining a first time window in the acceleration change trend, wherein the acceleration information corresponding to the first time window is greater than a preset acceleration threshold; determining a second time window based on the first time window, the power change trend, and the power change rate trend, wherein the number of second time windows is less than or equal to the number of first time windows, and the power change rate trend is obtained based on the power change trend; extending the second time window to obtain the rapid acceleration time window.
[0062] Specifically, the aforementioned preset acceleration threshold can be used to characterize a pre-set vehicle acceleration threshold. Here, the preset acceleration threshold is not specifically limited and can be determined according to the actual situation.
[0063] The first time window mentioned above can be used to characterize the window corresponding to acceleration information greater than a preset acceleration threshold.
[0064] The second time window mentioned above can be used to characterize the window in the first time window where the power change rate is greater than a preset power change rate threshold and the power change information is greater than the preset power threshold.
[0065] In one optional embodiment, in the process of analyzing the acceleration change trend and power change trend to determine the rapid acceleration time window of the vehicle during driving, it is necessary to determine the first time window corresponding to the acceleration information in the acceleration change trend that is greater than the preset acceleration threshold based on a preset acceleration threshold. Furthermore, based on the first time window, the power change trend, and the power change rate trend, a second time window in which the vehicle is in a rapid acceleration state is determined.
[0066] In another optional embodiment, in the process of determining the second time window in which the vehicle is in a rapid acceleration state based on the first time window, the power change trend, and the power change rate trend, it is necessary to further determine based on the power change rate in the power change rate trend and the power change information in the power change trend. That is, it is determined that under the first time window, the power change rate is greater than the preset power change rate threshold, and the power change information is greater than the preset power threshold corresponding to the second window, and the above-mentioned rapid acceleration time window is obtained by extending the second window.
[0067] like Figure 2 As shown, a_max corresponds to the aforementioned preset acceleration threshold. The acceleration change trend is filtered using a_max to obtain the first window corresponding to acceleration information greater than a_max. Figure 2The first time window consists of three time windows. Further, it is determined whether any of these three time windows contains a power change rate greater than a preset power change rate threshold, and the power change information is greater than the threshold value. If such a window exists, a second time window that meets the judgment requirements is determined. Figure 2 There are two second time windows, namely the first and the second. The time of each second time window is extended to obtain the above-mentioned rapid acceleration time window.
[0068] Optionally, a second time window is determined based on a first time window, a power change trend, and a power change rate trend, including: determining whether the power change rate within the power change rate trend is greater than a preset power change rate threshold within the first time window, and whether the power change information within the power change trend is greater than a preset power threshold; and determining the corresponding second time window in response to the first time window where the power change rate within the power change rate trend is greater than the preset power change rate threshold and the power change information within the power change trend is greater than the preset power threshold.
[0069] Specifically, the aforementioned preset power change rate threshold can be used to represent a preset power change rate threshold for the battery. The preset power change rate threshold is not specifically limited here and can be adjusted according to the actual situation.
[0070] The aforementioned preset power threshold can be used to represent the threshold for changes in the power information of a pre-set battery. The preset power threshold is not specifically limited here and can be adjusted according to the actual situation.
[0071] In an optional embodiment, during the process of determining the second time window based on the first time window, the power change trend, and the power change rate trend, it is necessary to determine whether the power change rate within the power change rate trend in the first time window is greater than a preset power change rate threshold, and whether the power change information within the power change trend is greater than a preset power threshold. If the power change rate within the power change rate trend in the first time window is greater than the preset power change rate threshold, and the power change information within the power change trend is greater than the preset power threshold, it indicates that there is a sudden change in the battery power information within this time window, and then this time window is determined to be the aforementioned second time window.
[0072] like Figure 2 As shown, determine respectively Figure 2Within the three first time windows, whether the power change rate is greater than the preset power change rate threshold and whether the power change information is greater than the preset power threshold, we can conclude that the power change rate in the first and second first time windows is greater than the preset power change rate threshold and the power change information is greater than the preset power threshold. In the third first time window, the power change rate is greater than the preset power change rate threshold, but the power change information is less than the preset power threshold. Therefore, the third first time window does not meet the judgment requirements, and we only need to determine the first two first time windows as the second time windows.
[0073] Optionally, the second time window is extended to obtain a rapid acceleration time window, including: extending the second time window based on a preset extension time to obtain a rapid acceleration time window.
[0074] Specifically, the aforementioned preset extension time can be used to indicate the pre-set extension time of the second time window, which can be 3 minutes or 4 minutes. There is no specific limitation on the preset extension time here, and it can be adjusted according to the actual situation.
[0075] In one optional embodiment, after determining the second time window, it is necessary to extend the second time window based on a preset extension time, and use the extended time window as the aforementioned rapid acceleration time window.
[0076] Generally, since power and acceleration changes are instantaneous, while temperature changes are slow, after identifying the location of a sudden change in power or acceleration information, that is, when the vehicle is in a state of rapid acceleration, the current second window needs to be extended for a period of time. Otherwise, the change in temperature rise cannot be detected. Therefore, the second time window needs to be extended to obtain the aforementioned rapid acceleration time window.
[0077] like Figure 2 As shown, by extending the first condition window, which is also the second time window, by ymin, we obtain the first rapid acceleration time window. By extending the second condition window by ymin, we obtain the second rapid acceleration time window.
[0078] In summary, by combining vehicle speed change trends to capture data scenarios of high battery power output caused by rapid vehicle acceleration, we can avoid misjudgments of excessively high output power caused by the use of high-power devices such as air conditioners.
[0079] Optionally, the temperature change trend is analyzed to determine the time corresponding to the battery meeting the preset temperature rise state as the rapid temperature rise window. This includes: determining the temperature change points in the temperature change trend, wherein the temperature change points meet the preset temperature rise sequence and preset time sequence; determining the temperature rise time length between two adjacent temperature change points; obtaining the corresponding temperature rise rate by calculating the two adjacent temperature rise time lengths; determining the target temperature rise rate in the temperature rise rate, wherein the target temperature rise rate is greater than the preset temperature rise rate; and taking the time corresponding to the target temperature rise rate as the rapid temperature rise window.
[0080] Specifically, the aforementioned temperature change points can be used to represent points in the temperature change trend where the temperature rises, and the temperature points after the temperature rises are marked as temperature change points.
[0081] The aforementioned preset temperature rise sequence can be used to represent a pre-defined sequence that satisfies the temperature rise requirement.
[0082] The aforementioned preset time series can be used to represent a pre-defined sequence that satisfies the chronological order.
[0083] Generally, a battery pack consists of m modules, each of which has a temperature sampling signal. That is, each frame of data contains m temperature values. By extracting the maximum value from the m temperature values in each frame of data, the temperature value of each frame can be obtained. Then, the temperature values of each frame are sorted according to a certain time series to obtain the temperature change trend.
[0084] Figure 5 This is a schematic diagram of an optional method for determining a temperature change point according to an embodiment of the present invention, such as... Figure 5 As shown, by filtering points in the temperature change trend that show an increase in temperature, sorting them by time, finding the locations where the temperature increases between two adjacent frames of data, and marking the latter frame as the temperature change point, we obtain temperature change point 1 and temperature change point 2 in the figure.
[0085] The aforementioned temperature rise time length can be used to represent the length obtained by subtracting the time corresponding to the temperature change point in the previous frame from the time corresponding to the temperature change point in the next frame between two adjacent temperature change points.
[0086] like Figure 3 As shown, the temperature rise time t1 is obtained by subtracting the time corresponding to temperature change point 1 from the time corresponding to temperature change point 2, the temperature rise time t2 is obtained by subtracting the time corresponding to temperature change point 2 from the time corresponding to temperature change point 3, and so on, until the temperature change point t3 and so on up to the temperature change point t7.
[0087] The temperature rise rate mentioned above can be used to represent the temperature rise rate between two adjacent temperature rise segments. Generally, it can be calculated using the following formula:
[0088] β i =(t i -t i+1 ) / t i+1
[0089] The i-th temperature rise rate time window is defined as: starting from the midpoint of the i-th temperature rise time period and ending at the midpoint of the (i+1)-th temperature rise time period.
[0090] like Figure 3 As shown, the first temperature rise rate time window is defined as starting from the midpoint of the first temperature rise time period and ending at the midpoint of the second temperature rise time period. The second temperature rise rate time window is defined as starting from the midpoint of the second temperature rise time period and ending at the midpoint of the third temperature rise time period, and so on, until the sixth temperature rise rate time window is determined.
[0091] The aforementioned preset temperature rise rate can be used to represent a pre-set temperature rise rate. There is no specific limitation on the preset temperature rise rate here, and it can be adjusted according to the actual situation.
[0092] The target temperature rise rate mentioned above can be used to represent the rate of temperature rise that is greater than the preset temperature rise rate mentioned above.
[0093] In one optional embodiment, during the process of analyzing the temperature change trend and determining the time corresponding to the battery meeting the preset temperature rise state as the rapid temperature rise window, it is necessary to determine the temperature change points that meet the preset temperature rise sequence and preset time sequence based on the temperature change trend, and calculate the temperature rise time length between two adjacent temperature change points. Then, by calculating the two adjacent temperature rise time lengths, the corresponding temperature rise rate is obtained, and the target temperature rise rate that is greater than the preset temperature rise rate is determined. The segment corresponding to the target temperature rise rate is then used as the rapid temperature rise window.
[0094] In summary, by extracting the rate of temperature change through the duration of temperature rise and converting it into a normalized change curve through a threshold, the trend of temperature change of the power battery in a data segment can be truly reflected. This avoids the problem of slow temperature change and difficulty in extracting the rate of temperature rise through the difference between adjacent data under high-frequency data conditions.
[0095] Optionally, by performing an overlap analysis on the rapid acceleration time window and the rapid temperature rise window, it is determined whether the target driving behavior exists within the rapid acceleration time window, including: calculating the time overlap between the rapid acceleration time window and the target temperature rise window to obtain the actual overlap degree, wherein the target temperature rise window is the minimum value in the rapid temperature rise window; in response to the actual overlap degree being greater than a preset overlap degree, it is determined that the target driving behavior exists within the rapid acceleration time window.
[0096] Specifically, the aforementioned actual overlap can be used to represent the ratio of the actual overlap window of the rapid acceleration time window and the target temperature rise window to the rapid acceleration time window.
[0097] The aforementioned preset overlap can be used to represent the ratio of the actual overlap window to the rapid acceleration time window. The preset overlap is not specifically limited here and can be adjusted according to the actual situation.
[0098] In one optional embodiment, in the process of determining whether there is a target driving behavior within the rapid acceleration time window by performing overlap analysis on the rapid acceleration time window and the rapid temperature rise window, it is necessary to determine the minimum value in the rapid temperature rise window, mark it as the target temperature rise window, and perform time overlap calculation on the rapid acceleration time window and the target temperature rise window to obtain the actual overlap degree. Then, based on the actual overlap degree and the preset overlap degree, it is determined whether there is a target driving behavior within the rapid acceleration time window.
[0099] Optionally, if the actual overlap is greater than a preset overlap, it is determined that the target driving behavior exists within the rapid acceleration time window; otherwise, if the actual overlap is less than or equal to the preset overlap, it is determined that the target driving behavior does not exist within the rapid acceleration time window.
[0100] Optionally, the actual overlap is obtained by performing time overlap calculation on the rapid acceleration time window and the target temperature rise window, including: determining the overlapping part of the rapid acceleration time window and the target temperature rise window to obtain the actual overlapping window; and obtaining the ratio of the actual overlapping window to the rapid acceleration time window to obtain the actual overlap.
[0101] Specifically, in the process of calculating the time overlap between the rapid acceleration time window and the target temperature rise window to obtain the actual overlap, it is necessary to determine the overlapping part of the rapid acceleration time window and the target temperature rise window, mark the overlapping part as the actual overlapping window, and then calculate the ratio of the actual overlapping window to the rapid acceleration time window to obtain the above-mentioned actual overlap.
[0102] Alternatively, it can be calculated using the following formula:
[0103]
[0104] Where δ represents the actual overlap, Δr represents the time length of the overlap between the rapid acceleration window and the rapid temperature rise window, i.e., the actual overlap window mentioned above, and a_len represents the time length of the rapid acceleration window. If the calculated δ for a certain overlap region is greater than x% (x is the preset overlap mentioned above), then this overlap region is considered to meet the conditions for severe driving.
[0105] Optionally, before feature extraction of the vehicle's driving data, the process includes: marking the collected vehicle data to obtain driving data, wherein the driving data is used to characterize data where the main positive relay state meets a preset relay state and the charging gun connection state meets a preset connection state, and the driving data meets a preset time series; distinguishing the driving data by time frame breakpoints to obtain a first marker point; calculating the time difference between two adjacent frames of the driving data to obtain multiple time differences; determining a target time difference among the multiple time differences and using the position corresponding to the target time difference as a second marker point, wherein the target time difference is greater than a preset time difference; and dividing the driving data based on the first marker point and the second marker point to obtain driving segment data, wherein the driving segment data includes a start time and an end time.
[0106] Specifically, the aforementioned preset relay state can be used to indicate that the preset main positive relay state is a high-voltage energized state.
[0107] The aforementioned preset connection status can be used to indicate that the preset charging gun is in an unconnected state.
[0108] The first marker point mentioned above can be used to mark the points that mark discontinuous line headers in the driving data.
[0109] Figure 6 This is a schematic diagram illustrating an optional method of marking driving data according to an embodiment of the present invention. Figure 6 As shown, the data within the two boxes represents the main positive relay state meeting the preset relay state, and the charging gun connection state meeting the preset connection state. There is a section of data between the two boxes that does not meet the marking conditions for driving data. Therefore, the row header of the driving data is broken. The broken position needs to be marked to obtain the first marking point mentioned above. Based on the first marking point, the driving data is segmented to obtain... Figure 6 The driving segment marker in the video.
[0110] The aforementioned preset time difference can be used to represent the time difference between two adjacent frames in advance. There is no specific limitation on the preset time difference here. It can be 5 minutes or 6 minutes.
[0111] The aforementioned second marker point can be used to mark the line headers in the driving data where the time difference between two adjacent frames is greater than a preset time difference.
[0112] Figure 7 This is a schematic diagram illustrating an optional method for marking breakpoints in time differences according to an embodiment of the present invention. Figure 7As shown, the time difference at 13:45:04 is 730, which far exceeds the preset time interval mentioned above. Therefore, it is necessary to mark the row header at that time to obtain the second marker point. Based on the second marker point, the driving data is segmented to obtain... Figure 7 Time difference breakpoint markers in the data.
[0113] The aforementioned driving segment data can be used to represent data obtained by segmenting driving data.
[0114] Figure 8 This is a schematic diagram illustrating an optional method of dividing a driving segment according to an embodiment of the present invention. Figure 8 As shown, after segmenting the driving data using the first and second marker points, driving segment 1, driving segment 2, and driving segment 3 are obtained, and then subsequent feature extraction and other processing are performed on the obtained driving segment data.
[0115] In one optional embodiment, before feature extraction of vehicle driving data, it is necessary to distinguish the time frame breakpoints of the driving data to obtain the first marker point. At the same time, the time difference between two adjacent frames of the driving data is calculated to obtain multiple time differences, and the target time difference among the multiple time differences is determined. The position corresponding to the target time difference is used as the second marker point. Then, the driving data is divided into driving segment data through the first marker point and the second marker point.
[0116] In addition, during the extraction of driving segment data, the driving segment data needs to be sorted by time, paying attention to the cases of driving across days, and merging them into a single driving segment to avoid secondary calculation (if the last driving segment of a vehicle on a given day ends at 23:59:50, it should be marked and concatenated with the first driving segment of the same day).
[0117] Generally, since vehicle network data cannot directly distinguish between the charging process and the driving process, specific signals are needed to make the distinction. At the same time, in order to extract driving segment data, the driving data needs to be segmented to facilitate subsequent driving behavior analysis.
[0118] In summary, by comprehensively analyzing three parameters—battery temperature rise, battery power change, and vehicle speed change—we can determine whether a vehicle is engaging in aggressive driving behavior. This approach considers a wide range of dimensions, and the results can comprehensively and accurately reflect the adverse effects of driving behavior on the power battery.
[0119] Example 2
[0120] According to an embodiment of the present invention, a driving behavior recognition device is also provided. This device can execute a driving behavior recognition method provided in Embodiment 1 above. The specific implementation method and preferred application scenario are the same as those in Embodiment 1 above, and will not be described in detail here.
[0121] Figure 9 This is a schematic diagram of a driving behavior recognition device according to an embodiment of the present invention, such as... Figure 9 As shown, the device includes:
[0122] The extraction module 902 is used to extract features from the vehicle's driving data to obtain the vehicle's acceleration change trend, power change trend, and vehicle battery temperature change trend. The driving data includes at least the vehicle's speed information and battery pack information during the driving process.
[0123] The first analysis module 904 is used to analyze the trends of acceleration and power changes to determine the rapid acceleration time window of the vehicle during driving.
[0124] The second analysis module 906 is used to analyze the temperature change trend and determine the rapid temperature rise window of the battery.
[0125] The identification module 908 is used to perform overlap analysis on the rapid acceleration time window and the rapid temperature rise window to determine whether the target driving behavior exists within the rapid acceleration time window.
[0126] Optionally, the first analysis module includes: a first time window determination module, used to determine a first time window in the acceleration change trend, wherein the acceleration information corresponding to the first time window is greater than a preset acceleration threshold; a second time window determination module, used to determine a second time window based on the first time window, the power change trend, and the power change rate trend, wherein the number of second time windows is less than or equal to the number of first time windows, and the power change rate trend is obtained based on the power change trend; and a rapid acceleration time window obtaining module, used to extend the second time window to obtain a rapid acceleration time window.
[0127] Optionally, the second time window determination module includes: a judgment module, used to judge whether the power change rate within the power change rate trend is greater than a preset power change rate threshold and whether the power change information within the power change rate trend is greater than a preset power threshold; and a second time window determination module, used to determine the corresponding second time window in response to the fact that the power change rate within the power change rate trend is greater than the preset power change rate threshold and the power change information within the power change rate trend is greater than the preset power threshold.
[0128] Optionally, the rapid acceleration time window obtaining module includes: an extension module, used to extend the second time window based on a preset extension time to obtain the rapid acceleration time window.
[0129] Optionally, the second analysis module includes: a temperature change point determination module, used to determine temperature change points in a temperature change trend, wherein the temperature change points satisfy a preset temperature rise sequence and a preset time sequence; a temperature rise time length determination module, used to determine the temperature rise time length between two adjacent temperature change points; a temperature rise rate acquisition module, used to obtain the corresponding temperature rise rate by calculating two adjacent temperature rise time lengths; a target temperature rise rate determination module, used to determine the target temperature rise rate in the temperature rise rate, wherein the target temperature rise rate is greater than the preset temperature rise rate; and a rapid temperature rise window acquisition module, used to use the time corresponding to the target temperature rise rate as the rapid temperature rise window.
[0130] Optionally, the identification module includes: a calculation module, used to obtain the actual overlap by performing time overlap calculation on the rapid acceleration time window and the target temperature rise window, wherein the target temperature rise window is the minimum value in the rapid temperature rise window; and a determination module, used to determine that the target driving behavior exists within the rapid acceleration time window in response to the actual overlap being greater than a preset overlap.
[0131] Optionally, the calculation module includes: an actual overlap window acquisition module, used to determine the overlapping portion of the rapid acceleration time window and the target temperature rise window to obtain the actual overlap window; and a ratio acquisition module, used to acquire the ratio of the actual overlap window and the rapid acceleration time window to obtain the actual overlap degree.
[0132] Optionally, the device further includes: a marking module, used to mark the collected vehicle data to obtain driving data, wherein the driving data is used to characterize the main positive relay state satisfying a preset relay state and the charging gun connection state satisfying a preset connection state, and the driving data satisfying a preset time sequence; a first marking point obtaining module, used to distinguish the time frame breakpoints of the driving data to obtain a first marking point; a multiple time difference obtaining module, used to calculate the time difference between two adjacent frames of the driving data to obtain multiple time differences; a second marking point obtaining module, used to determine the target time difference among the multiple time differences and use the position corresponding to the target time difference as the second marking point, wherein the target time difference is greater than the preset time difference; and a driving segment data obtaining module, used to divide the driving data based on the first marking point and the second marking point to obtain driving segment data, wherein the driving segment data includes a start time and an end time.
[0133] Example 3
[0134] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the processor of the device to execute any of the above-described driving behavior recognition methods.
[0135] Example 4
[0136] According to an embodiment of the present invention, a vehicle is also provided, comprising: one or more processors; a storage device for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to perform any of the above-described driving behavior recognition methods.
[0137] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0138] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0139] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.
[0140] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0141] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0142] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0143] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.
Claims
1. A driving behavior recognition method characterized by, include: Feature extraction is performed on the vehicle's driving data to obtain the vehicle's acceleration change trend, power change trend, and battery temperature change trend. The driving data includes at least the vehicle's speed information and battery pack information during driving. The acceleration and power change trends are analyzed to determine the rapid acceleration time window of the vehicle during driving. The temperature change trend is analyzed to determine the rapid temperature rise window of the battery; Overlap analysis is performed on the rapid acceleration time window and the rapid temperature rise window to determine whether the target driving behavior exists within the rapid acceleration time window.
2. The driving behavior recognition method according to claim 1, characterized in that, Analyzing the trends of acceleration and power changes to determine the rapid acceleration time window of the vehicle during operation includes: A first time window is determined in the acceleration change trend, wherein the acceleration information corresponding to the first time window is greater than a preset acceleration threshold; A second time window is determined based on the first time window, the power change trend, and the power change rate trend, wherein the number of second time windows is less than or equal to the number of first time windows, and the power change rate trend is obtained based on the power change trend; The second time window is extended to obtain the rapid acceleration time window.
3. The driving behavior recognition method according to claim 2, characterized in that, Determining a second time window based on the first time window, the power change trend, and the power change rate trend includes: Determine whether the power change rate within the power change rate trend is greater than a preset power change rate threshold within the first time window, and whether the power change information within the power change trend is greater than a preset power threshold. In response to the fact that within the first time window, the power change rate within the power change rate trend is greater than the preset power change rate threshold, and the power change information within the power change trend is greater than the preset power threshold, a corresponding second time window is determined.
4. The driving behavior recognition method according to claim 2, characterized by, The second time window is extended to obtain the rapid acceleration time window, including: Based on a preset extension time, the second time window is extended to obtain the rapid acceleration time window.
5. The driving behavior recognition method according to claim 1, characterized by, Analyzing the temperature change trend, the time corresponding to the battery meeting the preset heating state is determined as the rapid heating window, including: Determine the temperature change points in the temperature change trend, wherein the temperature change points satisfy a preset temperature rise sequence and a preset time sequence; Determine the duration of temperature rise between two adjacent temperature change points; The corresponding temperature rise rate is obtained by calculating the lengths of two adjacent temperature rise times. Determine a target temperature rise rate in the temperature rise rate, wherein the target temperature rise rate is greater than a preset temperature rise rate; The time corresponding to the target temperature rise rate is taken as the rapid temperature rise window.
6. The driving behavior recognition method according to claim 1, characterized by, By performing overlap analysis on the rapid acceleration time window and the rapid temperature rise window, it is determined whether target driving behavior exists within the rapid acceleration time window, including: The actual overlap is obtained by performing time overlap calculation on the rapid acceleration time window and the target temperature rise window, wherein the target temperature rise window is the minimum value in the rapid temperature rise window; In response to the actual overlap being greater than a preset overlap, it is determined that a target driving behavior exists within the rapid acceleration time window.
7. The driving behavior recognition method according to claim 6, characterized by, The actual overlap is obtained by performing time overlap calculations on the rapid acceleration time window and the target temperature rise window, including: The overlapping portion of the rapid acceleration time window and the target temperature rise window is determined to obtain the actual overlapping window; The actual overlap is obtained by comparing the ratio of the actual overlap window to the rapid acceleration time window.
8. The driving behavior recognition method according to claim 1, characterized by, Before extracting features from vehicle driving data, the following steps are required: By labeling the collected vehicle data, driving data is obtained. The driving data is used to characterize the data where the main positive relay state meets the preset relay state and the charging gun connection state meets the preset connection state, and the driving data meets the preset time series. The driving data is divided into time frame breakpoints to obtain the first marker point; The time difference between two adjacent frames of the driving data is calculated to obtain multiple time differences; Determine the target time difference among the plurality of time differences, and use the position corresponding to the target time difference as a second marker point, wherein the target time difference is greater than a preset time difference; Based on the first marker point and the second marker point, the driving data is divided to obtain driving segment data, wherein the driving segment data includes start time and end time.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the execution of the driving behavior recognition method according to any one of claims 1 to 8 in the processor of the device.
10. A vehicle characterized by comprising: include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors perform the driving behavior recognition method according to any one of claims 1 to 8.