Output torque control method, control device, control system and readable storage medium

Abstract

The invention discloses an output torque control method, device and system and a readable storage medium. The output torque control method is used for the vehicle and comprises the steps that image data and driving data of the vehicle are obtained; obtaining a road congestion degree according to the image data; obtaining a driving style type according to the driving data; and calculating the current output torque according to the driving data, the road congestion degree and the driving style type. According to the output torque control method provided by the invention, the road congestion degree and the driving style type can be accurately estimated through the image data and the driving data, and the current output torque is calculated according to the road congestion degree and the driving style type. According to the output torque control method, the road congestion degree and the driving style type of the vehicle are analyzed, decision variables are more comprehensive, strategy output can accurately adapt to driving characteristics needed by different driving environments, and the control fineness and the energy consumption optimization rate can be improved.

Description

Technical Field

[0001] This application relates to the field of automotive control technology, and more specifically, to an output torque control method, control device, control system, and readable storage medium. Background Technology

[0002] Existing vehicle output torque control methods set thresholds for vehicle driving data and output corresponding torque control strategies within different threshold ranges. With fewer decision variables, the torque management of the vehicle is relatively coarse, resulting in poor energy optimization performance. Summary of the Invention

[0003] This application provides an output torque control method, control device, control system, and readable storage medium.

[0004] The output torque control method of this application, used in a vehicle, includes:

[0005] Acquire image data and driving data of the vehicle;

[0006] The degree of road congestion is obtained based on the image data;

[0007] The driving style type is obtained based on the driving data;

[0008] The current output torque is calculated based on the driving data, the level of road congestion, and the driving style type.

[0009] The output torque control method provided in this application can accurately estimate road congestion and driving style using image data and driving data, and calculate the current output torque accordingly. This method incorporates analysis of road congestion and driving style, resulting in more comprehensive decision variables. The strategy's output can precisely adapt to the driving characteristics required by different driving environments, thus improving handling precision and energy efficiency.

[0010] In some embodiments, the image data includes images acquired from the front, rear, left, and / or right sides of the vehicle.

[0011] In this way, more comprehensive images can be used to estimate the level of road congestion more accurately.

[0012] In some embodiments, the image data is acquired at a frequency greater than or equal to 50 Hz.

[0013] This allows for more timely updates to image data.

[0014] In some embodiments, the driving data includes hardwired acquisition data and / or CAN network message acquisition data.

[0015] Therefore, using two methods to collect data helps improve the accuracy and stability of driving data acquisition.

[0016] In some embodiments, the acquisition frequency of the hard-wired data acquisition is greater than or equal to 100Hz, and the acquisition frequency of the CAN network message data acquisition is the minimum frequency of the communication network in which the CAN network is located.

[0017] This allows for more timely updates to driving data.

[0018] In some embodiments, the driving data includes long-term data, short-term data, and instantaneous data.

[0019] Thus, data collected at different time scales have different uses, providing the system with more comprehensive and detailed information.

[0020] In some embodiments, the long-term data includes long-term vehicle speed, long-term torque, long-term accelerator pedal opening, long-term accelerator pedal opening rate of change, long-term brake pedal opening, and long-term brake pedal opening rate of change; the short-term data includes short-term vehicle speed, short-term torque, short-term accelerator pedal opening, short-term accelerator pedal opening rate of change, short-term brake pedal opening, and short-term brake pedal opening rate of change; and the instantaneous data includes instantaneous accelerator pedal opening, instantaneous brake pedal opening, instantaneous vehicle speed, instantaneous gear, instantaneous motor torque, and instantaneous motor speed.

[0021] This helps improve control precision and energy efficiency.

[0022] In some embodiments, the long-term data is the vehicle speed collected from a first moment to the current moment, and the short-term data is the vehicle speed collected from a second moment to the current moment, wherein the total duration from the first moment to the current moment is greater than the total duration from the second moment to the current moment.

[0023] In this way, vehicle speed data collected at different time scales can provide the system with more comprehensive and detailed information on vehicle speed changes.

[0024] In some embodiments, the driving style type is related to the rate of change of pedal opening.

[0025] Thus, the driving style type can be accurately quantified based on the rate of change of pedal opening, which is beneficial for calculating the current output torque.

[0026] In some embodiments, when the rate of change of the pedal opening is greater than a first preset rate of change, the driving style type is aggressive.

[0027] When the rate of change of pedal opening is less than the first preset rate of change and greater than the second preset rate of change, the driving style type is stable.

[0028] The first preset rate of change is greater than the second preset rate of change.

[0029] In some embodiments, when the rate of change of the pedal opening is less than a second preset rate of change and greater than a third preset rate of change, the driving style type is mild.

[0030] When the rate of change of pedal opening is less than the third preset rate of change, the driving style type is cautious.

[0031] The second preset rate of change is greater than the third preset rate of change.

[0032] In this way, different driving styles can be defined based on the rate of change in pedal opening, allowing for personalized adjustments to vehicle settings such as power output, suspension system, and steering feedback to meet the driving preferences of different drivers. This helps improve driving comfort and satisfaction.

[0033] In some embodiments, calculating the current output torque based on the driving data, road congestion level, and driving style type includes:

[0034] A first driving condition probability vector is calculated based on the image data, and the first driving condition probability vector is related to the degree of road congestion.

[0035] A second driving condition probability vector is calculated based on the driving data, and the second driving condition probability vector is related to the driving style type;

[0036] The current output torque is calculated based on the driving data, the first driving condition probability vector, and the second driving condition probability vector.

[0037] In this way, by taking into account the degree of road congestion and the type of driving style, a first driving condition probability vector and a second driving condition probability vector are calculated to represent the driving conditions. Finally, the current output torque is calculated using driving data, the first driving condition probability vector, and the second driving condition probability vector, which helps to improve the accuracy of the current output torque.

[0038] In some embodiments, the first driving condition probability vector is a 4×1 column vector, wherein the first row is the probability of the current driving condition being urban congestion, the second row is the probability of the current driving condition being urban smooth traffic, the third row is the probability of the current driving condition being highway congestion, and the fourth row is the probability of the current driving condition being highway smooth traffic. The second driving condition probability vector is a 4×1 column vector, wherein the first row is the probability of the current driving condition being urban congestion, the second row is the probability of the current driving condition being urban smooth traffic, the third row is the probability of the current driving condition being highway congestion, and the fourth row is the probability of the current driving condition being highway smooth traffic.

[0039] This helps to have a clearer understanding of the driving conditions.

[0040] In some embodiments, calculating the first driving condition probability vector based on the image data includes:

[0041] The image data is used to identify the number of vehicles in front of and behind the vehicle, the number of vehicles passing on the left and right sides, and the probability of road type.

[0042] The degree of road congestion is calculated based on the number of vehicles in front and behind, the number of vehicles passing on the left and right sides, and the probability of the road category.

[0043] The first driving condition probability vector is calculated based on the road category probability and the road congestion level.

[0044] Thus, by analyzing the vehicle's driving environment and obtaining the probability vector of the first driving condition for adaptation, the control method can be adapted to different driving environments.

[0045] In some embodiments, the road category includes asphalt concrete pavement, cement pavement, and masonry pavement.

[0046] Therefore, obtaining various road categories is beneficial for selecting the most suitable control method based on the terrain type.

[0047] In some embodiments, calculating the second driving condition probability vector based on the driving data includes:

[0048] The frequency and speed of pedal opening changes are calculated based on the driving data.

[0049] The driving style type is identified by combining the frequency and speed of pedal opening changes with the driving data;

[0050] Based on the driving data, the distribution characteristics of the pedal opening change frequency and the pedal opening change speed under long-term data and standard cyclic conditions are obtained.

[0051] The second driving condition probability vector is calculated based on the distribution characteristics and the driving style type.

[0052] Thus, by analyzing the vehicle's driving state and obtaining the second driving condition probability vector for adaptation, the control method can be adapted to different driving conditions.

[0053] In some embodiments, the pedal opening change frequency includes the pedal opening change frequency of the accelerator pedal and the pedal opening change frequency of the brake pedal, and the pedal opening change speed includes the pedal opening change speed of the accelerator pedal and the pedal opening change speed of the brake pedal.

[0054] Thus, different pedal opening frequencies and opening speeds correspond to different uses, which helps to obtain more accurate current output torque.

[0055] In some embodiments, calculating the current output torque based on the driving data, the first driving condition probability vector, and the second driving condition probability vector includes:

[0056] The torque correction factor is calculated based on the driving data, the first driving condition probability vector, and the second driving condition probability vector;

[0057] The current output torque is calculated based on the driving data and the torque correction factor.

[0058] Therefore, using the torque correction factor to obtain the output torque is beneficial to improving the precision of control and the energy consumption optimization rate.

[0059] In some embodiments, the torque correction factor includes a target output torque correction factor, a torque loading correction factor, and a torque unloading correction factor.

[0060] Thus, different torque correction factors reflect different information, which helps to obtain a more accurate current output torque.

[0061] In some embodiments, calculating the torque correction factor based on the driving data, the first driving condition probability vector, and the second driving condition probability vector includes:

[0062] The actual driving condition is determined based on the first driving condition probability vector and the second driving condition probability vector.

[0063] Based on the rule base, a target output torque correction factor is output according to the actual driving conditions and the driving data. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained corresponding to one driving condition and one set of driving data in the rule base.

[0064] Therefore, using the probability vectors of the first and second driving conditions to calculate the target output torque correction factor helps to make the target output torque correction factor more accurate.

[0065] In some embodiments, calculating the torque correction factor based on the driving data, the first driving condition probability vector, and the second driving condition probability vector includes:

[0066] Based on the rule base, torque loading correction factors and torque unloading correction factors are output according to the driving style type, the driving condition, and the driving data. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained corresponding to a driving condition and a set of driving data in the rule base.

[0067] Therefore, using the probability vectors of the first and second driving conditions to calculate the torque loading correction factor and the torque unloading correction factor helps to make the torque loading correction factor and the torque unloading correction factor more accurate.

[0068] In some embodiments, calculating the current output torque based on the driving data and the torque correction factor includes:

[0069] Output the vehicle driving status bit based on the driving data;

[0070] Based on the rule base, the basic torque value is obtained according to the driving data and the vehicle driving status. The rule base is formed based on historical driving conditions and historical driving data. In the rule base, one driving condition and a set of driving data can correspondingly obtain a set of torque correction factors.

[0071] The current output torque is obtained based on the vehicle driving status, the basic torque value, the torque correction factor, and the torque at the previous moment.

[0072] This helps to make the torque loading and unloading process smoother, reduce the jerking sensation when the vehicle accelerates and decelerates, and make the driving process more stable and comfortable.

[0073] In some embodiments, the vehicle driving state position includes driving, coasting feedback, and braking feedback.

[0074] In this way, different parameters are used for different vehicle driving states, which helps to obtain more accurate current output torque.

[0075] In some embodiments, the basic torque value includes a target basic torque value, a basic torque loading rate value, and a basic torque unloading rate value.

[0076] In this way, different basic torque values ​​reflect different information, which helps to obtain more accurate current output torque.

[0077] In some embodiments, the target torque base value is determined using the driving data, the vehicle driving status, the drive torque curve, and the feedback torque curve.

[0078] Therefore, obtaining the basic target torque value by combining multiple data sources helps to make the basic target torque value more accurate.

[0079] The output torque control device according to a second embodiment of this application includes:

[0080] The acquisition module is used to acquire image data and driving data of the vehicle;

[0081] The first calculation module is used to obtain the degree of road congestion based on the image data;

[0082] The second calculation module is used to obtain the driving style type based on the driving data;

[0083] The third calculation module is used to calculate the current output torque based on the driving data, the road congestion level, and the driving style type.

[0084] The output torque control system of the third embodiment of this application includes a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, causes the processor to implement instructions for the output torque control method as described in any of the preceding claims.

[0085] The fourth embodiment of this application is a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the output torque control method as described in any of the preceding claims.

[0086] Additional aspects and advantages of embodiments of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of embodiments of this application. Attached Figure Description

[0087] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, wherein:

[0088] Figure 1 This is a schematic flowchart of the output torque control method of the output torque control system according to an embodiment of this application;

[0089] Figure 2This is a schematic diagram of the output torque control device of the output torque control system according to an embodiment of this application;

[0090] Figure 3 This is a schematic diagram of the output torque control system according to an embodiment of this application;

[0091] Figure 4 This is a flowchart illustrating the output torque control method of the output torque control system according to certain embodiments of the present application.

[0092] Figure 5 This is a flowchart illustrating the output torque control method of the output torque control system according to certain embodiments of the present application.

[0093] Figure 6 This is a flowchart illustrating the output torque control method of the output torque control system according to certain embodiments of the present application.

[0094] Figure 7 This is a flowchart illustrating the output torque control method of the output torque control system according to certain embodiments of the present application.

[0095] Figure 8 This is a flowchart illustrating the output torque control method of the output torque control system according to certain embodiments of the present application.

[0096] Figure 9 This is a flowchart illustrating the output torque control method of the output torque control system in some embodiments of this application.

[0097] Explanation of key component symbols: Output torque control system 100, Output torque control device 10, Acquisition module 11, First calculation module 12, Second calculation module 13, Third calculation module 14, Processor 20, Memory 30. Detailed Implementation

[0098] The embodiments of this application will be further described below with reference to the accompanying drawings. The same or similar reference numerals in the drawings denote the same or similar elements or elements having the same or similar functions throughout.

[0099] Furthermore, the embodiments of this application described below in conjunction with the accompanying drawings are exemplary and are only used to explain the embodiments of this application, and should not be construed as limiting this application.

[0100] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0101] Existing vehicle output torque control methods set thresholds for vehicle driving data and output corresponding torque control strategies within different threshold ranges. With fewer decision variables, the torque management of the vehicle is relatively coarse, resulting in poor energy optimization performance.

[0102] Please see Figure 1 The output torque control method of this application, used in a vehicle, includes:

[0103] Step 01: Acquire vehicle image data and driving data;

[0104] Step 02: Obtain the road congestion level based on image data;

[0105] Step 03: Obtain the driving style type based on driving data;

[0106] Step 04: Calculate the current output torque based on driving data, road congestion level, and driving style type.

[0107] Please see Figure 2 This application provides an output torque control device 10, which includes an acquisition module 11, a first calculation module 12, a second calculation module 13, and a third calculation module 14. The acquisition module 11 is used to acquire image data and driving data of the vehicle. The first calculation module 12 is used to acquire the road congestion level based on the image data. The second calculation module 13 is used to acquire the driving style type based on the driving data. The third calculation module 14 is used to calculate the current output torque based on the driving data, the road congestion level, and the driving style type.

[0108] Please see Figure 3This application provides an output torque control system 100, including a processor 20 and a memory 30. The memory 30 stores a computer program. When the computer program is executed by the processor 20, the processor 20 implements instructions for the output torque control method as described above. Alternatively, the processor 20 can be used to acquire vehicle image data and driving data; obtain road congestion level based on the image data; obtain driving style type based on the driving data; and calculate the current output torque based on the driving data, road congestion level, and driving style type.

[0109] The output torque control method provided in this application can accurately estimate road congestion and driving style using image data and driving data, and calculate the current output torque accordingly. This method incorporates analysis of road congestion and driving style, resulting in more comprehensive decision variables. The strategy's output can precisely adapt to the driving characteristics required by different driving environments, thus improving handling precision and energy efficiency.

[0110] Specifically, in this embodiment, both image data and driving data are collected periodically, and road congestion levels and driving style types also need to be calculated periodically. Furthermore, the calculation period for driving style types is longer than the acquisition period for image data and driving data.

[0111] Furthermore, image data and driving data, obtained through collection, are considered raw data, and the collection period for raw data is called the raw data period. Data such as road congestion levels and driving style types, obtained by calculation from the raw data, are considered derived data, and the calculation period for derived data is called the derived data period. The derived data period is greater than or equal to the raw data period. Generally speaking, the derived data period is equal to the maximum value among all raw data periods.

[0112] In some embodiments, the image data includes images acquired from the front, rear, left, and / or right sides of the vehicle.

[0113] In this way, more comprehensive images can be used to estimate the level of road congestion more accurately.

[0114] Specifically, in this embodiment, it is necessary to simultaneously acquire images of the front, rear, left, and right sides of the vehicle to ensure a comprehensive understanding of the number of vehicles and road conditions on the road where the vehicle is located. It is easy to understand that cameras can be installed on the front, rear, left, and right sides of the vehicle to ensure complete coverage of all directions of the vehicle.

[0115] In some embodiments, the image data acquisition frequency is greater than or equal to 50Hz.

[0116] This allows for more timely updates to image data.

[0117] Specifically, in the embodiments of this application, a higher sampling frequency helps reduce signal distortion or the omission of important information due to insufficient sampling. A sampling frequency of 50Hz matches the power frequency in Europe and most Asian countries, helping to reduce image flickering or ripple problems caused by power frequency interference.

[0118] It's important to note that higher acquisition frequencies require more storage space and faster transmission speeds to save and transmit image data, as well as greater computing power. This places higher demands on hardware, network bandwidth, and the performance of computers or image processing equipment.

[0119] In some embodiments, driving data includes hardwired acquisition data and / or CAN network message acquisition data.

[0120] Therefore, using two methods to collect data helps improve the accuracy and stability of driving data acquisition.

[0121] Specifically, hard-wired data acquisition refers to transmitting signals from field devices directly to a data acquisition system (such as a PLC module or data acquisition card) via cables for processing and analysis. This method typically uses fixed hardwired connections between the controller and automotive electronic components or sensors for signal transmission.

[0122] Hard-wired data acquisition is characterized by low installation and maintenance costs, but its installation is complex. Hard-wired signal installation requires a long time and large installation space, and is not easy to change. The transmission distance of hard-wired signals is limited by factors such as cable length and signal attenuation.

[0123] CAN network message data acquisition refers to the transmission and acquisition of data by connecting the controller and automotive electronic components or sensors via the CAN bus (Controller Area Network). The CAN bus is a serial communication protocol bus used in real-time applications, featuring high reliability and excellent error detection capabilities.

[0124] The advantages of CAN network message data acquisition include flexible installation and an easy-to-expand and modify network topology. However, its software configuration is complex, requiring specialized technical personnel and exhibiting a high degree of software dependency. Furthermore, while the CAN bus can connect multiple nodes, its transmission distance is limited.

[0125] In some embodiments, the acquisition frequency of hardwired data acquisition is greater than or equal to 100Hz, and the acquisition frequency of CAN network message data acquisition is the minimum frequency of the communication network in which the CAN network is located.

[0126] This allows for more timely updates to driving data.

[0127] Specifically, in this embodiment, the frequency of hardwired data acquisition needs to be high enough to ensure that rapidly changing processes can be captured. An acquisition frequency of 100Hz or higher can provide sufficient time resolution to meet these real-time requirements.

[0128] CAN network is a broadcast-based serial communication protocol bus, and its communication rate (i.e., baud rate) is determined by all nodes in the network. To ensure that each node can correctly receive and send data, all nodes must use the same communication rate. Therefore, the data acquisition frequency of CAN network messages is limited by the minimum frequency (i.e., minimum baud rate) of the communication network to which the network belongs.

[0129] In some embodiments, driving data includes long-term data, short-term data, and instantaneous data.

[0130] Thus, data collected at different time scales have different uses, providing the system with more comprehensive and detailed information.

[0131] Specifically, long-term data refers to data collected or accumulated over a relatively long period of time.

[0132] Short-term data refers to data collected or processed within a short period of time, and is typically used to capture short-term changes or responses.

[0133] Instantaneous data refers to data points captured in an extremely short period of time (usually at the millisecond or microsecond level), reflecting the state or change at a particular instant.

[0134] In some embodiments, long-term data includes long-term vehicle speed, long-term torque, long-term accelerator pedal opening, long-term accelerator pedal opening rate of change, long-term brake pedal opening, and long-term brake pedal opening rate of change; short-term data includes short-term vehicle speed, short-term torque, short-term accelerator pedal opening, short-term accelerator pedal opening rate of change, short-term brake pedal opening, and short-term brake pedal opening rate of change; and instantaneous data includes instantaneous accelerator pedal opening, instantaneous brake pedal opening, instantaneous vehicle speed, instantaneous gear, instantaneous motor torque, and instantaneous motor speed.

[0135] This helps improve control precision and energy efficiency.

[0136] Specifically, in the embodiments of this application, the accelerator pedal opening refers to the angle or displacement of the pedal relative to its initial position (usually the position when it is not pressed) when the driver presses the accelerator pedal.

[0137] Brake pedal opening refers to the vertical distance the pedal travels from its normal stop position to its fully depressed position when the driver presses the brake pedal. It can also be understood as the extent to which the brake pedal sinks during this process.

[0138] In some embodiments, long-term data refers to the vehicle speed collected from the first moment to the current moment, and short-term data refers to the vehicle speed collected from the second moment to the current moment. The total duration from the first moment to the current moment is greater than the total duration from the second moment to the current moment.

[0139] In this way, vehicle speed data collected at different time scales can provide the system with more comprehensive and detailed information on vehicle speed changes.

[0140] Specifically, in this embodiment of the application, the long-term vehicle speed is the vehicle speed collected from the current time to 180 seconds ago, and the short-term vehicle speed is the vehicle speed collected from the current time to 60 seconds ago.

[0141] In some embodiments, the driving style type is related to the rate of change of pedal opening.

[0142] Thus, the driving style type can be accurately quantified based on the rate of change of pedal opening, which is beneficial for calculating the current output torque.

[0143] In some embodiments, when the rate of change of pedal opening is greater than a first preset rate of change, the driving style type is aggressive; when the rate of change of pedal opening is less than the first preset rate of change but greater than a second preset rate of change, the driving style type is stable; the first preset rate of change is greater than the second preset rate of change.

[0144] In some embodiments, when the rate of change of pedal opening is less than a second preset rate of change but greater than a third preset rate of change, the driving style type is mild; when the rate of change of pedal opening is less than the third preset rate of change, the driving style type is cautious; the second preset rate of change is greater than the third preset rate of change.

[0145] In this way, different driving styles can be defined based on the rate of change in pedal opening, allowing for personalized adjustments to vehicle settings such as power output, suspension system, and steering feedback to meet the driving preferences of different drivers. This helps improve driving comfort and satisfaction.

[0146] Specifically, in the embodiments of this application, the driving style types include aggressive, stable, mild, and cautious.

[0147] Furthermore, let η1 be the percentage of data segments where the accelerator pedal opening increases by more than 50% within 0.5 seconds when accelerating from low speed (starting speed less than 40% of the current road speed limit), and let η2 be the percentage of data segments where the brake pedal opening increases by more than 50% within 0.5 seconds when decelerating from high speed (starting speed greater than 80% of the current road speed limit). Based on the relationship between (η1+η2) / 2 and the first, second, and third preset change rates, determine the current driving style type, where the first preset change rate is 65%, the second is 50%, and the third is 30%. The method for determining the current driving style type is as follows:

[0148] When (η1+η2) / 2>65%, the driving style type is determined to be aggressive.

[0149] When 65% > (η1 + η2) / 2 > 50%, the driving style type is determined to be stable.

[0150] When 50% > (η1 + η2) / 2 > 30%, the driving style is determined to be mild.

[0151] When 30% > (η1 + η2) / 2, the driving style type is determined to be cautious.

[0152] Please see Figure 4 In some embodiments, step 04 includes:

[0153] 041: Calculate the probability vector of the first driving condition based on the image data. The probability vector of the first driving condition is related to the degree of road congestion.

[0154] 042: Calculate the second driving condition probability vector based on driving data. The second driving condition probability vector is related to the driving style type.

[0155] 043: Calculate the current output torque based on driving data, the probability vector of the first driving condition, and the probability vector of the second driving condition.

[0156] In this way, by taking into account the degree of road congestion and the type of driving style, a first driving condition probability vector and a second driving condition probability vector are calculated to represent the driving conditions. Finally, the current output torque is calculated using driving data, the first driving condition probability vector, and the second driving condition probability vector, which helps to improve the accuracy of the current output torque.

[0157] In some embodiments, sub-steps 041, 042, and 043 can be implemented by the third calculation module 14, or the third calculation module 14 can be used to calculate a first driving condition probability vector based on image data, calculate a second driving condition probability vector based on driving data, and calculate the current output torque based on driving data, the first driving condition probability vector, and the second driving condition probability vector.

[0158] In some embodiments, the processor 20 may be used to calculate a first driving condition probability vector based on image data, calculate a second driving condition probability vector based on driving data, and calculate the current output torque based on driving data, the first driving condition probability vector, and the second driving condition probability vector.

[0159] Specifically, the driving condition probability vector is a key parameter describing the probability distribution of a vehicle under different driving conditions. It is usually associated with statistical models such as the Hidden Markov Model (HMM). In driving condition research, the probability vector can help us understand the driving characteristics of vehicles under different conditions (such as smooth traffic in the city, congested traffic in the city, and suburban areas), thereby providing decision support for vehicle control, performance optimization, and energy conservation and emission reduction.

[0160] In some embodiments, the first driving condition probability vector is a 4×1 column vector, where the first row is the probability of the current driving condition being urban congestion, the second row is the probability of the current driving condition being urban smooth traffic, the third row is the probability of the current driving condition being highway congestion, and the fourth row is the probability of the current driving condition being highway smooth traffic. The second driving condition probability vector is a 4×1 column vector, where the first row is the probability of the current driving condition being urban congestion, the second row is the probability of the current driving condition being urban smooth traffic, the third row is the probability of the current driving condition being highway congestion, and the fourth row is the probability of the current driving condition being highway smooth traffic.

[0161] This helps to have a clearer understanding of the driving conditions.

[0162] Specifically, in this embodiment, the first driving condition probability vector and the second driving condition probability vector are both 4×1 column vectors. In other embodiments, if there are other driving conditions, the first driving condition probability vector and the second driving condition probability vector can be set to other forms of column vectors or row vectors. The specific selection and adjustment can be made according to actual needs, which will not be elaborated here.

[0163] Please see Figure 5 In some embodiments, sub-step 041 includes:

[0164] 0411: Identify the number of vehicles in front of and behind the vehicle, the number of vehicles passing on the left and right sides, and the probability of road category based on image data;

[0165] 0412: Calculate the degree of road congestion based on the number of vehicles in front and behind, the number of vehicles passing on the left and right sides, and the probability of road type;

[0166] 0413: Calculate the probability vector of the first driving condition based on the road category probability and the road congestion level.

[0167] Thus, by analyzing the vehicle's driving environment and obtaining the probability vector of the first driving condition for adaptation, the control method can be adapted to different driving environments.

[0168] In some embodiments, sub-steps 0411, 0412, and 0413 can be implemented by the third calculation module 14, or the third calculation module 14 can be used to identify the number of vehicles in front and behind the vehicle, the number of vehicles passing on the left and right sides, and the road category probability based on image data; calculate the road congestion level based on the number of vehicles in front and behind the vehicle, the number of vehicles passing on the left and right sides, and the road category probability; and calculate the first driving condition probability vector based on the road category probability and the road congestion level.

[0169] In some embodiments, the processor 20 may be used to identify the number of vehicles in front of and behind the vehicle, the number of vehicles passing on the left and right sides, and the road category probability based on image data; calculate the road congestion level based on the number of vehicles in front of and behind the vehicle, the number of vehicles passing on the left and right sides, and the road category probability; and calculate a first driving condition probability vector based on the road category probability and the road congestion level.

[0170] Specifically, in this embodiment, calculating the probability vector of the first driving condition based on the road category probability and the degree of road congestion helps improve the accuracy of driving decisions. By comprehensively considering the road category (such as main roads, secondary roads, and side roads) and the degree of congestion, the current driving environment can be judged more accurately, thereby making more reasonable driving decisions. For example, on congested urban roads, drivers may choose a smoother driving style to avoid frequent lane changes and sudden acceleration and deceleration.

[0171] In addition, accurate driving condition probability vectors can provide drivers with more comprehensive road condition information, helping them to anticipate and adjust their driving behavior in advance, thereby reducing traffic accidents and improving driving safety and comfort.

[0172] In some embodiments, road categories include asphalt concrete pavement, cement pavement, and masonry pavement.

[0173] Therefore, obtaining various road categories is beneficial for selecting the most suitable control method based on the terrain type.

[0174] Specifically, in this embodiment, the road categories only include several common types, such as asphalt concrete pavement, cement pavement, brick pavement, and others. In other embodiments, when the vehicle's usage location is more special and a certain type of road accounts for a larger proportion, the road categories can be added, removed, or modified. Specific additions, removals, and modifications can be made according to actual needs, which will not be elaborated upon here.

[0175] Please see Figure 6 In some embodiments, sub-step 042 includes:

[0176] 0421: Calculate the pedal opening change frequency and pedal opening change speed based on driving data;

[0177] 0422: Identify driving style type based on the frequency and speed of pedal opening changes combined with driving data;

[0178] 0423: Combine driving data to obtain the distribution characteristics of pedal opening change frequency and pedal opening change speed under long-term data and standard cycle conditions;

[0179] 0424: Calculate the probability vector of the second driving condition based on the distribution characteristics and driving style type.

[0180] Thus, by analyzing the vehicle's driving state and obtaining the second driving condition probability vector for adaptation, the control method can be adapted to different driving conditions.

[0181] In some embodiments, sub-steps 0421, 0422, 0423, and 0424 can be implemented by the third calculation module 14. In other words, the third calculation module 14 can be used to calculate the pedal opening change frequency and pedal opening change speed based on driving data; identify the driving style type based on the pedal opening change frequency and pedal opening change speed in combination with driving data; obtain the distribution characteristics of the pedal opening change frequency and pedal opening change speed under long-term data and standard cyclic conditions in combination with driving data; and calculate the second driving condition probability vector based on the distribution characteristics and driving style type.

[0182] In some embodiments, the processor 20 can be used to calculate the frequency and speed of change of the accelerator pedal and brake pedal opening based on driving data; identify driving style type based on the frequency and speed of change of pedal opening combined with driving data; the processor 20 can also be used to calculate the frequency and speed of change of pedal opening based on driving data; identify driving style type based on the frequency and speed of change of pedal opening combined with driving data; obtain the distribution characteristics of the frequency and speed of change of pedal opening under long-term data and standard cyclic conditions based on driving data; and calculate a second driving condition probability vector based on the distribution characteristics and driving style type.

[0183] Specifically, in this embodiment, the frequency and speed of change of the accelerator pedal and brake pedal opening are calculated based on long-term vehicle speed, short-term vehicle speed, accelerator pedal opening and brake pedal opening data.

[0184] The frequency and speed of pedal opening change refer to how quickly and frequently the pedal opening changes over time when the driver operates the accelerator pedal (or brake pedal). This change reflects the driver's driving intentions and the vehicle's power requirements.

[0185] Furthermore, based on the distribution characteristics of the pedal opening change frequency and speed under long-term data and standard cyclic conditions, a second driving condition probability vector is calculated. By analyzing the change frequency and speed of pedal opening in detail, the driver's driving behavior and intentions under different conditions can be captured more accurately. This precision allows the calculated second driving condition probability vector to more accurately reflect actual driving situations.

[0186] In some embodiments, the pedal opening change frequency includes the pedal opening change frequency of the accelerator pedal and the pedal opening change frequency of the brake pedal, and the pedal opening change speed includes the pedal opening change speed of the accelerator pedal and the pedal opening change speed of the brake pedal.

[0187] Thus, different pedal opening frequencies and opening speeds correspond to different uses, which helps to obtain more accurate current output torque.

[0188] Specifically, pedal opening frequency refers to how quickly the opening of a foot pedal (such as the accelerator or brake pedal) changes over time during driving. It is usually measured by the number of opening changes per unit time or the percentage change in opening. This parameter reflects the frequency of the driver's intention to accelerate or decelerate the vehicle.

[0189] The rate of change of pedal opening refers to how quickly the pedal opening changes over time during driving. It measures the magnitude of increase or decrease in pedal opening per unit of time.

[0190] Both the frequency and speed of pedal opening changes reflect driver intent, driving style, vehicle dynamics, and safety. Both can be used to optimize vehicle design and control systems to improve vehicle dynamics and driving safety.

[0191] Please see Figure 7 In some embodiments, sub-step 043 includes:

[0192] 0431: Calculate the torque correction factor based on driving data, the probability vector of the first driving condition, and the probability vector of the second driving condition;

[0193] 0432: Calculate the current output torque based on driving data and torque correction factor.

[0194] Therefore, using the torque correction factor to obtain the output torque is beneficial to improving the precision of control and the energy consumption optimization rate.

[0195] In some embodiments, sub-steps 0431 and 0432 can be implemented by the third calculation module 14, or the third calculation module 14 can be used to calculate the torque correction factor based on driving data, the first driving condition probability vector and the second driving condition probability vector; and calculate the current output torque based on driving data and the torque correction factor.

[0196] In some embodiments, the processor 2020 can be used to calculate a torque correction factor based on driving data, a first driving condition probability vector, and a second driving condition probability vector; and to calculate the current output torque based on driving data and the torque correction factor.

[0197] Specifically, the torque correction factor is a parameter used to correct the torque measurement value of the engine at different speeds. It can improve the accuracy of testing and optimize engine performance. In the embodiments of this application, the torque correction factor includes a variety of factors.

[0198] In some embodiments, the torque correction factor includes a target output torque correction factor, a torque loading correction factor, and a torque unloading correction factor.

[0199] Thus, different torque correction factors reflect different information, which helps to obtain a more accurate current output torque.

[0200] The target output torque correction factor is a coefficient or parameter used to adjust or correct the target torque of a vehicle. It is dynamically adjusted based on various factors such as the vehicle's actual operating conditions, environmental conditions, and driver needs to ensure that the vehicle's power output meets driving requirements while also complying with economic, safety, and emission standards.

[0201] Furthermore, adjusting the target output torque correction factor can optimize the engine's torque output under different operating conditions, thereby improving the vehicle's power performance.

[0202] The torque loading correction factor refers to the factor that corrects for the deviation between the actual torque transmitted and the theoretical value when torque is applied to a component or system, due to various factors such as friction, material elasticity, and thermal expansion. It is typically a coefficient based on experimental or theoretical calculations, used to adjust the torque value during loading to more closely approximate the actual transmitted torque.

[0203] Similarly, the torque unloading correction factor refers to the coefficient used to correct for torque deviations that may occur when torque is unloaded from a component or system. Its function is to adjust the torque value during unloading to ensure measurement accuracy or system stability.

[0204] Please see Figure 8 In some embodiments, sub-step 0431 includes:

[0205] 04311: Determine the actual driving condition based on the probability vector of the first driving condition and the probability vector of the second driving condition;

[0206] 04312: Based on the rule base, the target torque correction factor is output according to the actual driving conditions and driving data. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained for a certain driving condition and a set of driving data in the rule base.

[0207] Therefore, using the probability vectors of the first and second driving conditions to calculate the target output torque correction factor helps to make the target output torque correction factor more accurate.

[0208] In some embodiments, sub-steps 04311 and 04312 can be implemented by the third calculation module 14, or the third calculation module 14 can be used to determine the actual driving condition based on the first driving condition probability vector and the second driving condition probability vector; based on the rule base, the target output torque correction factor is output according to the actual driving condition and driving data. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained corresponding to a driving condition and a set of driving data in the rule base.

[0209] In some embodiments, the processor 20 can be used to determine the actual driving condition based on the first driving condition probability vector and the second driving condition probability vector; based on the rule base, output the target output torque correction factor according to the actual driving condition and driving data. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained corresponding to a driving condition and a set of driving data in the rule base.

[0210] Specifically, a rule base is a collection of production rules describing knowledge within a certain domain; it is the foundation upon which a production system solves problems. In this embodiment, the target output torque correction factor is directly obtained from the driving conditions and the current torque, accelerator pedal opening, and brake pedal opening.

[0211] Please see Figure 8 In some embodiments, sub-step 0431 includes:

[0212] 04313: Based on the rule base, output torque loading correction factor and torque unloading correction factor according to driving style type, driving conditions and driving data. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained for a certain driving condition and a set of driving data in the rule base.

[0213] Therefore, using the probability vectors of the first and second driving conditions to calculate the torque loading correction factor and the torque unloading correction factor helps to make the torque loading correction factor and the torque unloading correction factor more accurate.

[0214] In some embodiments, sub-step 04313 can be implemented by the third calculation module 14, or the third calculation module 14 can be used to output torque loading correction factors and torque unloading correction factors based on the rule base, according to the driving style type, driving conditions and driving data. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained corresponding to a driving condition and a set of driving data in the rule base.

[0215] In some embodiments, the processor 20 can be used to output torque loading correction factors and torque unloading correction factors based on a rule base, according to driving style type, driving conditions and driving data. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained corresponding to a driving condition and a set of driving data in the rule base.

[0216] Specifically, in the embodiments of this application, torque loading correction factors and torque unloading correction factors are output according to driving style type, driving conditions, current speed, accelerator pedal opening and brake pedal opening.

[0217] Please see Figure 9 In some embodiments, sub-step 0432 includes:

[0218] 04321: Output the vehicle's driving status bit based on driving data;

[0219] 04322: Based on the rule base, the basic torque value is obtained according to driving data and the overall vehicle driving status. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained for a certain driving condition and a set of driving data in the rule base.

[0220] 04323: Obtain the current output torque based on the vehicle's driving status, basic torque value, torque correction factor, and torque at the previous moment.

[0221] This helps to make the torque loading and unloading process smoother, reduce the jerking sensation when the vehicle accelerates and decelerates, and make the driving process more stable and comfortable.

[0222] In some embodiments, sub-steps 04321, 04322, and 04323 can be implemented by the third calculation module 14, or in other words, the third calculation module 14 can be used to output the vehicle driving status position based on driving data; based on the rule base, obtain the basic torque value according to the driving data and the vehicle driving status position, the rule base is formed based on historical driving conditions and historical driving data, and a set of torque correction factors can be obtained corresponding to a driving condition and a set of driving data in the rule base; obtain the current output torque according to the vehicle driving status position, the basic torque value, the torque correction factors, and the torque at the previous moment.

[0223] In some embodiments, the processor 20 can be used to output the vehicle driving status position based on driving data; based on a rule base, obtain the basic torque value according to the driving data and the vehicle driving status position, the rule base is formed based on historical driving conditions and historical driving data, and a set of torque correction factors can be obtained corresponding to a driving condition and a set of driving data in the rule base; and obtain the current output torque according to the vehicle driving status position, the basic torque value, the torque correction factors and the torque at the previous moment.

[0224] In some embodiments, the vehicle driving state position includes driving, coasting feedback, and braking feedback.

[0225] In this way, different parameters are used for different vehicle driving states, which helps to obtain more accurate current output torque.

[0226] Specifically, in the embodiments of this application, the vehicle driving state includes three types: driving, coasting feedback, and braking feedback.

[0227] Furthermore, coasting feedback and braking feedback are related to the brake pedal opening. When the car brakes, coasting feedback is triggered, while braking feedback is generated as the brake pedal opening increases, and coasting feedback gradually fades out.

[0228] In some embodiments, the target torque base value is determined using driving data, vehicle driving status, drive torque curve, and feedback torque curve.

[0229] Therefore, obtaining the basic target torque value by combining multiple data sources helps to make the basic target torque value more accurate.

[0230] Specifically, the drive torque curve is a graphical representation used to describe the changes in output torque of a drive system (such as a motor, engine, etc.) under different conditions (such as speed, load, etc.).

[0231] Feedback torque curves typically involve the relationship between torque and a certain variable (such as speed, time, position, etc.) and are represented in graphical form.

[0232] In this embodiment, the target torque base value is determined by driving data, vehicle driving status, drive torque curve and feedback torque curve, which is beneficial to improving driving safety and comfort, optimizing energy utilization efficiency, enhancing vehicle performance and response speed, extending vehicle service life and improving intelligence and adaptive capabilities.

[0233] In some embodiments, the basic torque value includes a target basic torque value, a basic torque loading rate value, and a basic torque unloading rate value.

[0234] In this way, different basic torque values ​​reflect different information, which helps to obtain more accurate current output torque.

[0235] Specifically, the target torque is one of the important standards for measuring the working performance of a rotating device, representing the torque level that the device needs to achieve during normal operation.

[0236] The torque loading rate baseline refers to the rate at which the output torque of a motor or engine increases over time.

[0237] The torque unloading rate baseline refers to the rate at which the output torque of a motor or engine decreases over time.

[0238] Furthermore, in this embodiment, the vehicle driving status position is output based on vehicle speed, motor speed, accelerator pedal opening, and brake pedal opening. Based on the vehicle speed, torque, accelerator pedal opening, brake pedal opening, and vehicle driving status position, the target torque base value, torque loading rate base value, and torque unloading rate base value can be obtained from the rule base. These are then used to calculate the target output torque correction factor, torque loading correction factor, and torque unloading correction factor.

[0239] Furthermore, the formula for obtaining the current output torque based on the basic torque value, the basic torque loading rate value, the basic torque unloading rate value, the target output torque correction factor, the torque loading correction factor, the torque unloading correction factor, and the torque at the previous moment is as follows:

[0240]

[0241] Among them, T t For the current output torque target, T t-1 T represents the torque at the previous moment. b η is the basic value of the target torque. u η is the base value for torque loading rate. d σ1 is the base value for torque unloading rate, σ2 is the target output torque correction factor, σ3 is the torque loading correction factor, and σ4 is the torque unloading correction factor.

[0242] The embodiments of this application also include a non-volatile computer-readable storage medium storing a computer program that, when executed by the processor 20, implements the output torque control method of any of the above claims.

[0243] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any other combination. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0244] In the description of this specification, the references to "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples" refer to specific features, structures, materials, or characteristics described in connection with the described embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0245] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the stated features. In the description of this application, "multiple" means at least two, such as two or three, unless otherwise explicitly specified.

[0246] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application, the scope of which is defined by the claims and their equivalents.

Claims

1. An output torque control method for a vehicle, characterized in that, include: Acquire image data and driving data of the vehicle; The degree of road congestion is obtained based on the image data; The driving style type is obtained based on the driving data; The current output torque is calculated based on the driving data, the level of road congestion, and the driving style type.

2. The output torque control method according to claim 1, characterized in that, The image data includes images acquired from the front, rear, left, and / or right sides of the vehicle.

3. The output torque control method according to claim 1, characterized in that, The image data acquisition frequency is greater than or equal to 50Hz.

4. The output torque control method according to claim 1, characterized in that, The driving data includes hard-wired acquisition data and / or CAN network message acquisition data.

5. The output torque control method according to claim 4, characterized in that, The acquisition frequency of the hard-wired data is greater than or equal to 100Hz, and the acquisition frequency of the CAN network message data is the minimum frequency of the communication network in which the CAN network is located.

6. The output torque control method according to any one of claims 1-4, characterized in that, The driving data includes long-term data, short-term data, and instantaneous data.

7. The output torque control method according to claim 6, characterized in that, The long-term data includes long-term vehicle speed, long-term torque, long-term accelerator pedal opening, long-term accelerator pedal opening rate of change, long-term brake pedal opening, and long-term brake pedal opening rate of change. The short-term data includes short-term vehicle speed, short-term torque, short-term accelerator pedal opening, short-term accelerator pedal opening rate of change, short-term brake pedal opening, and short-term brake pedal opening rate of change. The instantaneous data includes instantaneous accelerator pedal opening, instantaneous brake pedal opening, instantaneous vehicle speed, instantaneous gear, instantaneous motor torque, and instantaneous motor speed.

8. The output torque control method according to claim 6, characterized in that, The long-term data refers to the vehicle speed collected from the first moment to the current moment, and the short-term data refers to the vehicle speed collected from the second moment to the current moment. The total duration from the first moment to the current moment is greater than the total duration from the second moment to the current moment.

9. The output torque control method according to any one of claims 1-4, characterized in that, The driving style type is related to the rate of change of pedal opening.

10. The output torque control method according to any one of claims 9, characterized in that, When the rate of change of pedal opening is greater than a first preset rate of change, the driving style type is aggressive. When the rate of change of pedal opening is less than the first preset rate of change and greater than the second preset rate of change, the driving style type is stable. The first preset rate of change is greater than the second preset rate of change.

11. The output torque control method according to any one of claims 9, characterized in that, When the rate of change of pedal opening is less than the second preset rate of change and greater than the third preset rate of change, the driving style type is mild. When the rate of change of pedal opening is less than the third preset rate of change, the driving style type is cautious. The second preset rate of change is greater than the third preset rate of change.

12. The output torque control method according to any one of claims 1-4, characterized in that, The calculation of the current output torque based on the driving data, road congestion level, and driving style type includes: A first driving condition probability vector is calculated based on the image data, and the first driving condition probability vector is related to the degree of road congestion. A second driving condition probability vector is calculated based on the driving data, and the second driving condition probability vector is related to the driving style type; The current output torque is calculated based on the driving data, the first driving condition probability vector, and the second driving condition probability vector.

13. The output torque control method according to claim 12, characterized in that, The first driving condition probability vector is a 4×1 column vector, where the first row is the probability of the current driving condition being urban congestion, the second row is the probability of the current driving condition being urban smooth traffic, the third row is the probability of the current driving condition being highway congestion, and the fourth row is the probability of the current driving condition being highway smooth traffic. The second driving condition probability vector is a 4×1 column vector, where the first row is the probability of the current driving condition being urban congestion, the second row is the probability of the current driving condition being urban smooth traffic, the third row is the probability of the current driving condition being highway congestion, and the fourth row is the probability of the current driving condition being highway smooth traffic.

14. The output torque control method according to claim 12, characterized in that, The step of calculating the first driving condition probability vector based on the image data includes: The image data is used to identify the number of vehicles in front of and behind the vehicle, the number of vehicles passing on the left and right sides, and the probability of road type. The degree of road congestion is calculated based on the number of vehicles in front and behind, the number of vehicles passing on the left and right sides, and the probability of the road category. The first driving condition probability vector is calculated based on the road category probability and the road congestion level.

15. The output torque control method according to any one of claims 13, characterized in that, The road categories include asphalt concrete pavement, cement pavement, and stone brick pavement.

16. The output torque control method according to any one of claims 13-15, characterized in that, The step of calculating the second driving condition probability vector based on the driving data includes: The frequency and speed of pedal opening changes are calculated based on the driving data. The driving style type is identified by combining the frequency and speed of pedal opening changes with the driving data; Based on the driving data, the distribution characteristics of the pedal opening change frequency and the pedal opening change speed under long-term data and standard cyclic conditions are obtained. The second driving condition probability vector is calculated based on the distribution characteristics and the driving style type.

17. The output torque control method according to claim 16, characterized in that, The pedal opening change frequency includes the pedal opening change frequency of the accelerator pedal and the pedal opening change frequency of the brake pedal, and the pedal opening change speed includes the pedal opening change speed of the accelerator pedal and the pedal opening change speed of the brake pedal.

18. The output torque control method according to any one of claims 16, characterized in that, The step of calculating the current output torque based on the driving data, the first driving condition probability vector, and the second driving condition probability vector includes: The torque correction factor is calculated based on the driving data, the first driving condition probability vector, and the second driving condition probability vector; The current output torque is calculated based on the driving data and the torque correction factor.

19. The output torque control method according to claim 18, characterized in that, The torque correction factor includes the target output torque correction factor, the torque loading correction factor, and the torque unloading correction factor.

20. The output torque control method according to claim 19, characterized in that, The step of calculating the torque correction factor based on the driving data, the first driving condition probability vector, and the second driving condition probability vector includes: The actual driving condition is determined based on the first driving condition probability vector and the second driving condition probability vector. Based on the rule base, a target output torque correction factor is output according to the actual driving conditions and the driving data. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained corresponding to one driving condition and one set of driving data in the rule base.

21. The output torque control method according to any one of claims 17-20, characterized in that, The step of calculating the torque correction factor based on the driving data, the first driving condition probability vector, and the second driving condition probability vector includes: Based on the rule base, torque loading correction factors and torque unloading correction factors are output according to the driving style type, the driving condition, and the driving data. The rule base is formed based on historical driving conditions and historical driving data. A set of torque correction factors can be obtained corresponding to a driving condition and a set of driving data in the rule base.

22. The output torque control method according to any one of claims 18-20, characterized in that, The step of calculating the current output torque based on the driving data and the torque correction factor includes: Output the vehicle driving status bit based on the driving data; Based on the rule base, the basic torque value is obtained according to the driving data and the vehicle driving status. The rule base is formed based on historical driving conditions and historical driving data. In the rule base, one driving condition and a set of driving data can correspondingly obtain a set of torque correction factors. The current output torque is obtained based on the vehicle driving status, the basic torque value, the torque correction factor, and the torque at the previous moment.

23. The output torque control method according to claim 22, characterized in that, The vehicle driving status includes drive, coasting feedback, and braking feedback.

24. The output torque control method according to claim 22, characterized in that, The basic torque values ​​include the target torque basic value, the torque loading rate basic value, and the torque unloading rate basic value.

25. The output torque control method according to claim 24, characterized in that, The target torque value is determined by the driving data, the vehicle driving status, the drive torque curve, and the feedback torque curve.

26. An output torque control device for a vehicle, characterized in that, The control device includes: The acquisition module is used to acquire image data and driving data of the vehicle; The first calculation module is used to obtain the degree of road congestion based on the image data; The second calculation module is used to obtain the driving style type based on the driving data; The third calculation module is used to calculate the current output torque based on the driving data, the road congestion level, and the driving style type.

27. An output torque control system, characterized in that, It includes a processor and a memory, the memory storing a computer program that, when executed by the processor, causes the processor to implement the instructions of the output torque control method as described in any one of claims 1-25.

28. A non-volatile computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the output torque control method as described in any one of claims 1-25.

Images