Driving behavior abnormity identification method and device, vehicle and storage medium

Abstract

The invention provides a driving behavior abnormity identification method and device, a vehicle and a storage medium, and belongs to the technical field of driving behavior detection.The method comprises the steps that starting process data and a plurality of preset gears of the vehicle are obtained; the starting process data comprises a plurality of gearbox output shaft rotating speeds and a plurality of engine rotating speeds which are in one-to-one correspondence with a plurality of starting time points; based on the multiple preset gears, the multiple gearbox output shaft rotating speeds and the multiple engine rotating speeds, a two-dimensional starting feature map is constructed; inputting the two-dimensional starting feature map into a starting gear recognition model to obtain a starting gear; and determining sliding friction work based on the starting gear, and determining whether the vehicle has an abnormal driving behavior or not based on the sliding friction work. According to the method, a shaft rotating speed sensor does not need to be additionally arranged, driving behavior abnormity recognition can be achieved only by obtaining the vehicle starting process data and the multiple preset gears, the driving behavior abnormity recognition cost is reduced, and the driving behavior abnormity recognition efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of driving behavior detection, and in particular to a method, device, vehicle and storage medium for identifying abnormal driving behavior. Background Art

[0002] The clutch is installed between the engine and the transmission. It is an assembly directly connected to the engine in the automobile transmission system. During actual use, due to the driver's abnormal driving behavior, especially high-end starting behavior, it will cause abnormal wear and burning of the clutch friction plate.

[0003] In order to increase the service life of the clutch, the prior art proposes to determine the abnormal driving behavior by calculating the slipping work, and promptly remind the driver to correct the abnormal driving behavior. However, the calculation of slipping work requires the knowledge of the first shaft speed. The existing vehicles equipped with manual transmissions can only collect the engine speed and output shaft speed, but not the first shaft speed. Therefore, it is necessary to add an additional first shaft speed sensor to collect the first shaft speed. It has the following technical problems: it requires additional function development and is costly.

[0004] Therefore, there is an urgent need to provide a method, device, vehicle and storage medium for identifying abnormal driving behavior, which can be used to accurately identify abnormal driving behavior without adding an axle speed sensor. Summary of the invention

[0005] In view of this, it is necessary to provide a method, device, vehicle and storage medium for identifying abnormal driving behavior, so as to solve the technical problems existing in the prior art of adding an axle speed sensor to identify abnormal driving behavior, resulting in low identification efficiency and high cost.

[0006] On the one hand, in order to solve the above technical problems, the present invention provides a method for identifying abnormal driving behavior, comprising: Acquiring starting process data of the vehicle and a plurality of preset gears; the starting process data comprising a plurality of gearbox output shaft speeds and a plurality of engine speeds corresponding to a plurality of starting time points; constructing a two-dimensional starting characteristic map based on the plurality of preset gears, the plurality of transmission output shaft speeds, and the plurality of engine speeds; Inputting the two-dimensional starting characteristic map into a starting gear position recognition model to obtain a starting gear position; The friction work is determined based on the starting gear, and whether the vehicle has abnormal driving behavior is determined based on the friction work.

[0007] In a possible implementation, the constructing a two-dimensional starting characteristic map based on the plurality of preset gears, the plurality of transmission output shaft speeds, and the plurality of engine speeds includes: determining a plurality of transmission speed ratios based on the plurality of preset gears; determining a plurality of launch coefficients based on the plurality of transmission output shaft speeds, the plurality of transmission speed ratios, and the plurality of engine speeds; A two-dimensional matrix is ​​constructed with the preset gear positions as rows and the starting coefficients as columns, and the two-dimensional matrix is ​​used as the two-dimensional starting characteristic diagram.

[0008] In a possible implementation, the starting coefficient is: SYN i =n bsi ×I k / n fdi In the formula, SYN i is the starting coefficient of the ith starting time point; n bsi is the gearbox output shaft speed at the i-th starting time point; I k is the gearbox speed ratio corresponding to the kth preset gear; n fdi is the engine speed at the i-th starting time point.

[0009] In a possible implementation, the starting gear recognition model includes a first convolutional layer, a first residual module, a second residual module, a third residual module and a fully connected layer connected in sequence, and the first residual module, the second residual module and the third residual module all include a second convolutional layer, a third convolutional layer and a bridge convolutional layer connected in sequence between the input of the second convolutional layer and the output of the third convolutional layer.

[0010] In a possible implementation, obtaining the starting process data of the vehicle includes: Determine the starting point and the starting end point of the vehicle; the starting point is a time point when the vehicle speed is 0 and the throttle opening is greater than 0 within a preset time period, and a neutral signal appears at the starting end point, or a time point when the collection time of the starting process data is equal to the preset collection time period; The starting process data is obtained based on the starting starting point, the starting end point and a preset sampling frequency.

[0011] In a possible implementation, determining the sliding friction work based on the starting gear position includes: determining a transmission starting speed ratio based on the starting gear position; Determining a target transmission output shaft speed that is the latest in time among the plurality of transmission output shaft speeds and a target engine speed that is the latest in time among the plurality of engine speeds; The sliding friction work is determined based on the transmission starting speed ratio, the target transmission output shaft speed and the target engine speed.

[0012] In a possible implementation, determining whether the vehicle has abnormal driving behavior based on the sliding friction work includes: Determining whether the sliding friction work is greater than a preset sliding friction work; If it is greater than, determining whether the transmission starting speed ratio is greater than a preset starting speed ratio; When the starting speed ratio of the transmission is greater than the preset starting speed ratio, there is abnormal driving behavior, and the abnormal driving behavior is that the starting gear is too high; When the starting speed ratio of the transmission is less than or equal to the preset starting speed ratio, there is abnormal driving behavior, and the abnormal driving behavior is that the starting speed is too high.

[0013] On the other hand, the present invention also provides a device for identifying abnormal driving behavior, comprising: A starting process data acquisition unit, used to acquire starting process data of the vehicle and a plurality of preset gears; the starting process data includes a plurality of gearbox output shaft speeds and a plurality of engine speeds corresponding to a plurality of starting time points one by one; a starting characteristic map constructing unit, configured to construct a two-dimensional starting characteristic map based on the plurality of preset gears, the plurality of transmission output shaft speeds and the plurality of engine speeds; A starting gear position recognition unit, used for inputting the two-dimensional starting characteristic map into a starting gear position recognition model to obtain a starting gear position; The abnormal driving behavior determination unit is used to determine the slipping work based on the starting gear position, and determine whether the vehicle has abnormal driving behavior based on the slipping work.

[0014] In another aspect, the present invention further provides a vehicle, comprising a memory and an electronic control unit, wherein: The memory is used to store programs; The electronic control unit is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for identifying abnormal driving behavior described in any one of the possible implementations above.

[0015] On the other hand, the present invention also provides a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by an electronic control unit, the steps in the method for identifying abnormal driving behavior described in any possible implementation method mentioned above are implemented.

[0016] The beneficial effects of the present invention are as follows: the method for identifying abnormal driving behavior provided by the present invention constructs a two-dimensional starting characteristic map, inputs the two-dimensional starting characteristic map into a starting gear recognition model to obtain the starting gear, determines the slipping work based on the starting gear, and judges whether there is abnormal driving behavior based on the determined slipping work, and does not need to add an axle speed sensor. It only needs to obtain the vehicle starting process data and multiple preset gears to realize abnormal driving behavior identification, thereby reducing the cost of identifying abnormal driving behavior, eliminating the installation time of the axle speed sensor, and improving the efficiency of identifying abnormal driving behavior.

[0017] Furthermore, the present invention constructs a two-dimensional starting characteristic map based on multiple preset gears, multiple transmission output shaft speeds and multiple engine speeds, so that the two-dimensional starting characteristic map conforms to the physical laws of vehicle starting, thereby further improving the accuracy of identifying abnormal driving behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for identifying abnormal driving behavior provided by the present invention; Figure 2 For the present invention Figure 1 A schematic flow chart of an embodiment of step S102; Figure 3 A schematic diagram of the structure of an embodiment of a starting gear position recognition model provided by the present invention; Figure 4 This is a flow chart of an embodiment of obtaining starting process data in step S101 of the present invention; Figure 5 It is a flow chart of an embodiment of determining the sliding friction work based on the starting gear position in step S104 of the present invention; Figure 6 This is a flow chart of an embodiment of determining whether a vehicle has abnormal driving behavior based on sliding friction work in step S104 of the present invention; Figure 7 A schematic diagram of the structure of an embodiment of the device for identifying abnormal driving behavior provided by the present invention; Figure 8 A schematic structural diagram of an embodiment of a vehicle provided by the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0021] It should be understood that the schematic drawings are not drawn to scale. The flowchart used in the present invention shows the operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flowchart can be implemented out of order, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present invention, can add one or more other operations to the flowchart, and can also remove one or more operations from the flowchart. Some of the block diagrams shown in the accompanying drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or electronic control unit systems and / or microcontroller systems.

[0022] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] The present invention provides a method, device, vehicle and storage medium for identifying abnormal driving behavior, which are described below respectively.

[0024] The embodiment of the present invention provides a method for identifying abnormal driving behavior. Figure 1 As shown, the method for identifying abnormal driving behavior includes: S101, obtaining starting process data of the vehicle and a plurality of preset gears; the starting process data including a plurality of gearbox output shaft speeds and a plurality of engine speeds corresponding to a plurality of starting time points one by one; S102, constructing a two-dimensional starting characteristic map based on a plurality of preset gear positions, a plurality of transmission output shaft speeds, and a plurality of engine speeds; S103, inputting the two-dimensional starting characteristic map into a starting gear recognition model to obtain a starting gear; S104: Determine the slippage work based on the starting gear position, and determine whether the vehicle has abnormal driving behavior based on the slippage work.

[0025] The multiple preset gears in step S101 refer to all theoretical gears of the vehicle gearbox. For example, the DT14 gearbox has 14 preset gears.

[0026] The transmission output shaft speed and the engine speed in step S101 can be directly acquired through speed sensors installed in the transmission output shaft and the engine, or can be derived from other physical quantities that can be directly acquired.

[0027] Compared with the prior art, the method for identifying abnormal driving behavior provided by the embodiment of the present invention constructs a two-dimensional starting characteristic map, inputs the two-dimensional starting characteristic map into a starting gear recognition model to obtain the starting gear, determines the slipping work based on the starting gear, and judges whether there is abnormal driving behavior based on the determined slipping work. There is no need to add an axle speed sensor, and only needs to obtain vehicle starting process data and multiple preset gears to realize abnormal driving behavior recognition, which reduces the cost of abnormal driving behavior recognition, eliminates the installation time of the axle speed sensor, and improves the efficiency of abnormal driving behavior recognition.

[0028] Furthermore, the embodiment of the present invention constructs a two-dimensional starting characteristic map based on multiple preset gears, multiple transmission output shaft speeds, and multiple engine speeds, so that the two-dimensional starting characteristic map conforms to the physical laws of vehicle starting, thereby further improving the accuracy of identifying abnormal driving behavior.

[0029] In some embodiments of the present invention, Figure 2 As shown, step S102 includes: S201, determining a plurality of gearbox speed ratios based on a plurality of preset gear positions; S202, determining a plurality of starting coefficients based on a plurality of gearbox output shaft speeds, a plurality of gearbox speed ratios, and a plurality of engine speeds; S203, constructing a two-dimensional matrix with the preset gear positions as rows and the starting coefficients as columns, and using the two-dimensional matrix as a two-dimensional starting characteristic map.

[0030] It should be understood that there is a one-to-one correspondence between the preset gear position and the transmission speed ratio, that is, based on this correspondence, the transmission speed ratio can be determined according to the preset gear position.

[0031] The embodiment of the present invention constructs a two-dimensional starting characteristic map with each preset gear as a row, so that the feature data in the two-dimensional starting characteristic map can include all possible starting gear situations of the vehicle, that is, the two-dimensional starting characteristic map is more comprehensive, thereby improving the accuracy of the abnormal driving behavior recognition result determined based on the two-dimensional starting characteristic map.

[0032] Specifically, when there are K preset gears and N starting time points, the two-dimensional starting feature map is a K×N matrix.

[0033] In a specific embodiment of the present invention, the starting coefficient is: SYN i =n bsi ×I k / n fdi In the formula, SYN i is the starting coefficient of the ith starting time point; n bsi is the gearbox output shaft speed at the i-th starting time point; I k is the gearbox speed ratio corresponding to the kth preset gear; n fdi is the engine speed at the i-th starting time point.

[0034] It should be noted that: in order to further improve the efficiency of abnormal driving behavior identification, in some embodiments of the present invention, Figure 3 As shown, the starting gear recognition model includes a first convolutional layer, a first residual module, a second residual module, a third residual module and a fully connected layer connected in sequence, and the first residual module, the second residual module and the third residual module all include a second convolutional layer, a third convolutional layer and a cross-convolutional layer connected in sequence between the second convolutional layer input and the third convolutional layer output.

[0035] The embodiment of the present invention eliminates the information loss and attrition problems of traditional convolutional networks or fully connected layers during information transmission, and eliminates the problems of gradient vanishing or gradient exploding by setting a cross-convolutional layer that crosses the input of the second convolutional layer and the output of the third convolutional layer. The input of the second convolutional layer is directly transmitted to the output of the third convolutional layer to protect the integrity of the information. The entire network only needs to learn the part of the input and output difference, which simplifies the learning objectives and difficulty, and improves the accuracy of gear recognition based on the starting gear recognition model.

[0036] Furthermore, since the starting gear recognition model eliminates the problem of gradient explosion or gradient vanishing, it is possible to increase the depth of the starting gear recognition model according to the recognition accuracy, thereby further improving the accuracy of gear recognition.

[0037] In a specific embodiment of the present invention, the convolution kernels of the first convolution layer, the second convolution layer, and the third convolution layer are all 3×3, and the convolution kernel of the cross-convolution layer is 1×1. In addition, the number of output feature maps of the first convolution layer is 64, the number of output feature maps of each convolution layer in the first residual module is 128, the number of output feature maps of each convolution layer in the second residual module is 512, and the number of output feature maps of each convolution layer in the third residual module is 1024.

[0038] It should be noted that: before step S103, the initial gear recognition model needs to be trained, tested and verified based on the historical starting process data to obtain the gear recognition model.

[0039] Specifically: a historical two-dimensional starting feature map is constructed based on historical starting process data, and the gear label of the historical two-dimensional starting feature map is determined. The historical two-dimensional starting feature map and the gear label constitute a sample set. The sample set is divided into a training set, a test set and a validation set in a ratio of 6:2:2. The initial gear recognition model is trained, tested and validated based on the training set, the test set and the validation set, respectively, to obtain the gear recognition model.

[0040] Among them, the historical starting process data and gear labels can be obtained by conducting a starting test at a test site.

[0041] In order to avoid using data other than the starting process as the starting process data, which may cause adverse effects on the recognition of abnormal driving behavior, in some embodiments of the present invention, for example Figure 4 As shown, the step S101 of acquiring the starting process data of the vehicle includes: S401, determining the starting point and the starting end point of the vehicle; the starting point is the time point when the vehicle speed is 0 and the throttle opening is greater than 0 within a preset time, and the starting end point has a neutral signal, or the time point when the collection time of the starting process data is equal to the preset collection time; S402: Obtain starting process data based on a starting starting point, a starting end point and a preset sampling frequency.

[0042] The embodiment of the present invention avoids the influence of non-starting process data on the result by accurately determining the starting starting point and the starting end point, thereby ensuring the accuracy of the acquired starting process data.

[0043] In some embodiments of the present invention, the preset time length is 1S to 3S, and the preset collection time length is 25S to 35S. Specifically, the preset time length is 2S, and the preset collection time length is 30S.

[0044] It should be understood that the preset ruler length and the preset collection time can be adjusted according to the actual application scenario and are not limited to the above values.

[0045] It should also be understood that the preset sampling frequency should also be set according to the hardware resources and recognition accuracy of data processing, and no specific limitation is made here.

[0046] In some embodiments of the present invention, Figure 5 As shown, the step S104 of determining the sliding friction work based on the starting gear position includes: S501, determining a starting speed ratio of a transmission based on a starting gear position; S502, determining a target gearbox output shaft speed that is the latest among a plurality of gearbox output shaft speeds and a target engine speed that is the latest among a plurality of engine speeds; S503: Determine the sliding friction work based on the transmission starting speed ratio, the target transmission output shaft speed, and the target engine speed.

[0047] There is a corresponding relationship between the starting gear and the starting speed ratio of the transmission, and based on this corresponding relationship, the starting speed ratio of the transmission can be determined according to the starting gear.

[0048] In a specific embodiment of the present invention, the sliding friction work is: Sliding work = |engine speed - shaft speed| × engine torque / 100 Among them, the speed of one axis is: One shaft speed = gearbox output shaft speed × gearbox starting speed ratio.

[0049] In a specific embodiment of the present invention, Figure 6 As shown, determining whether the vehicle has abnormal driving behavior based on the sliding friction work in step S104 includes: S601, determining whether the sliding friction work is greater than a preset sliding friction work; S602: If it is greater than, determining whether the transmission starting speed ratio is greater than a preset starting speed ratio; S603: When the transmission starting speed ratio is greater than the preset starting speed ratio, there is abnormal driving behavior, and the abnormal driving behavior is that the starting gear is too high; S604: When the transmission starting speed ratio is less than or equal to the preset starting speed ratio, there is abnormal driving behavior, and the abnormal driving behavior is that the starting speed is too high.

[0050] It should be understood that when the sliding friction work is less than or equal to the preset sliding friction work, it indicates that there is no abnormal driving behavior.

[0051] After determining whether there is abnormal driving behavior through sliding friction, the embodiment of the present invention also determines the specific type of abnormal driving behavior by judging the starting speed ratio of the transmission, thereby further improving the refinement of the identification of abnormal driving behavior and can specifically remind the driver to take protective measures.

[0052] It should be noted that the specific type of abnormal driving behavior can be displayed on instruments in the cab through text reminders, so as to visually prompt the driver that abnormal driving behavior has occurred, so that the abnormal driving behavior can be corrected in time and the service life of the clutch friction plate can be extended.

[0053] In order to better implement the driving behavior abnormality identification method in the embodiment of the present invention, based on the driving behavior abnormality identification method, the embodiment of the present invention also provides a driving behavior abnormality identification device, such as Figure 7 As shown, the driving behavior abnormality identification device 700 includes: The starting process data acquisition unit 701 is used to acquire the starting process data of the vehicle and a plurality of preset gears; the starting process data includes a plurality of gearbox output shaft speeds and a plurality of engine speeds corresponding to a plurality of starting time points one by one; A starting characteristic map construction unit 702, configured to construct a two-dimensional starting characteristic map based on a plurality of preset gears, a plurality of transmission output shaft speeds, and a plurality of engine speeds; A starting gear position recognition unit 703, used for inputting the two-dimensional starting characteristic map into a starting gear position recognition model to obtain a starting gear position; The abnormal driving behavior determination unit 704 is used to determine the slipping work based on the starting gear position, and determine whether the vehicle has abnormal driving behavior based on the slipping work.

[0054] It should be noted that the abnormal driving behavior identification device 700 provided in the above embodiment can implement the technical solution described in the above-mentioned abnormal driving behavior identification method embodiment. The specific implementation principles or specific implementation details of the above-mentioned modules or units can refer to the corresponding contents in the above-mentioned abnormal driving behavior identification method embodiment, and will not be described one by one here.

[0055] like Figure 8 As shown, the present invention also provides a vehicle 800 . The vehicle 800 includes an electronic control unit (ECU) 801 , a memory 802 , and a display 803 . Figure 8 Only some of the components of vehicle 800 are shown, but it should be understood that implementation of all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0056] The memory 802 may be an internal storage unit of the vehicle 800 , such as a hard disk or a memory of the vehicle 800 , in some embodiments.

[0057] Furthermore, the memory 802 may include both an internal storage unit of the vehicle 800 and an external storage device. The memory 802 is used to store application software installed in the vehicle 800 and various data.

[0058] In some embodiments, the display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 803 is used to display information of the vehicle 800 and to display a visual user interface. The components 801-803 of the vehicle 800 communicate with each other via a system bus.

[0059] In some embodiments of the present invention, when the electronic control unit 801 executes the abnormal driving behavior recognition program in the memory 802, the following steps may be implemented: Acquiring starting process data of the vehicle and a plurality of preset gears; the starting process data including a plurality of transmission output shaft speeds and a plurality of engine speeds corresponding to a plurality of starting time points; constructing a two-dimensional starting characteristic map based on a plurality of preset gears, a plurality of transmission output shaft speeds, and a plurality of engine speeds; Inputting the two-dimensional starting characteristic map into the starting gear recognition model to obtain the starting gear; The slippage work is determined based on the starting gear position, and whether the vehicle has abnormal driving behavior is determined based on the slippage work.

[0060] It should be understood that: when the electronic control unit 801 executes the driving behavior abnormality identification program in the memory 802, in addition to the above functions, it can also realize other functions. For details, please refer to the description of the corresponding method embodiment above.

[0061] Correspondingly, an embodiment of the present invention also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by an electronic control unit, the steps or functions in the driving behavior abnormality identification method provided in the above-mentioned method embodiments can be implemented.

[0062] Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as electronic control unit, controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0063] The above is a detailed introduction to a method, device, vehicle and storage medium for identifying abnormal driving behavior provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for identifying abnormal driving behavior, characterized in that: include: Obtain vehicle starting process data and multiple preset gears; The starting process data includes a plurality of gearbox output shaft speeds and a plurality of engine speeds corresponding to a plurality of starting time points one by one; constructing a two-dimensional starting characteristic map based on the plurality of preset gears, the plurality of transmission output shaft speeds, and the plurality of engine speeds; Inputting the two-dimensional starting characteristic map into a starting gear position recognition model to obtain a starting gear position; The friction work is determined based on the starting gear, and whether the vehicle has abnormal driving behavior is determined based on the friction work.

2. The method for identifying abnormal driving behavior according to claim 1, characterized in that: The constructing of a two-dimensional starting characteristic map based on the plurality of preset gears, the plurality of transmission output shaft speeds and the plurality of engine speeds comprises: determining a plurality of transmission speed ratios based on the plurality of preset gears; determining a plurality of launch coefficients based on the plurality of transmission output shaft speeds, the plurality of transmission speed ratios, and the plurality of engine speeds; A two-dimensional matrix is ​​constructed with the preset gear positions as rows and the starting coefficients as columns, and the two-dimensional matrix is ​​used as the two-dimensional starting characteristic diagram.

3. The method for identifying abnormal driving behavior according to claim 2, characterized in that: The starting coefficient is: SYN i =n bsi ×I k / n fdi In the formula, SYN i is the starting coefficient of the ith starting time point; n bsi is the gearbox output shaft speed at the i-th starting time point; I k is the gearbox speed ratio corresponding to the kth preset gear; n fdi is the engine speed at the i-th starting time point.

4. The method for identifying abnormal driving behavior according to claim 1, characterized in that: The starting gear recognition model includes a first convolutional layer, a first residual module, a second residual module, a third residual module and a fully connected layer connected in sequence, and the first residual module, the second residual module and the third residual module all include a second convolutional layer, a third convolutional layer and a cross-connected convolutional layer between the second convolutional layer input and the third convolutional layer output connected in sequence.

5. The method for identifying abnormal driving behavior according to claim 1, characterized in that: Get the vehicle's starting process data, including: Determine the starting point and the starting end point of the vehicle; the starting point is a time point when the vehicle speed is 0 and the throttle opening is greater than 0 within a preset time period, and a neutral signal appears at the starting end point, or a time point when the collection time of the starting process data is equal to the preset collection time period; The starting process data is obtained based on the starting starting point, the starting end point and a preset sampling frequency.

6. The method for identifying abnormal driving behavior according to claim 1, characterized in that: The determining of the sliding friction work based on the starting gear position comprises: determining a transmission starting speed ratio based on the starting gear position; Determining a target transmission output shaft speed that is the latest in time among the plurality of transmission output shaft speeds and a target engine speed that is the latest in time among the plurality of engine speeds; The sliding friction work is determined based on the transmission starting speed ratio, the target transmission output shaft speed and the target engine speed.

7. The method for identifying abnormal driving behavior according to claim 6, characterized in that: The determining whether the vehicle has abnormal driving behavior based on the sliding friction work includes: Determining whether the sliding friction work is greater than a preset sliding friction work; If it is greater than, determining whether the transmission starting speed ratio is greater than a preset starting speed ratio; When the starting speed ratio of the transmission is greater than the preset starting speed ratio, there is abnormal driving behavior, and the abnormal driving behavior is that the starting gear is too high; When the starting speed ratio of the transmission is less than or equal to the preset starting speed ratio, there is abnormal driving behavior, and the abnormal driving behavior is that the starting speed is too high.

8. A device for identifying abnormal driving behavior, characterized in that: include: A starting process data acquisition unit, used to acquire starting process data of the vehicle and a plurality of preset gear positions; The starting process data includes a plurality of gearbox output shaft speeds and a plurality of engine speeds corresponding to a plurality of starting time points one by one; a starting characteristic map constructing unit, configured to construct a two-dimensional starting characteristic map based on the plurality of preset gears, the plurality of transmission output shaft speeds and the plurality of engine speeds; A starting gear position recognition unit, used for inputting the two-dimensional starting characteristic map into a starting gear position recognition model to obtain a starting gear position; The abnormal driving behavior determination unit is used to determine the slipping work based on the starting gear position, and determine whether the vehicle has abnormal driving behavior based on the slipping work.

9. A vehicle, characterized in that: comprising a memory and an electronic control unit, wherein: The memory is used to store programs; The electronic control unit is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for identifying abnormal driving behavior as described in any one of claims 1 to 7 above.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or instruction, and when the program or instruction is executed by the electronic control unit, the steps in the method for identifying abnormal driving behavior described in any one of claims 1 to 7 are implemented.

Images