A control method and system for multi-configuration gearbox

Abstract

The application discloses a control method and system for multi-configuration gearbox, and relates to the technical field of intelligent control, which comprises the following steps: calculating the total driving resistance of a vehicle and converting the total driving resistance into tractive force, multiplying the tractive force by the current vehicle speed to obtain a power estimation value, calculating the instantaneous change rate of the accelerator pedal opening degree signal and converting the instantaneous change rate into driver demand intensity to construct a macro feature vector; converting the demand tractive force into demand torque of the gearbox input shaft to obtain a thermodynamic entropy production rate, calculating a comprehensive cost, and screening a target configuration; and judging the current gearbox configuration based on the target configuration and intelligently controlling the switching of the gearbox configuration. Through the dynamic calculation of the total driving resistance of the vehicle and the driver demand intensity, in combination with real-time road conditions and driving behavior, the configuration selection of the gearbox is optimized, different driving scenarios are matched, the calculation of the thermodynamic entropy production rate and the switching transient excitation potential is utilized, and the comprehensive performance of the gearbox is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to a control method and system for multi-configuration gearboxes. Background Technology

[0002] With the continuous advancement of automotive technology, the design and control methods of transmissions have also undergone significant development. Traditional mechanical transmissions mostly rely on manual or automatic methods for gear switching. Although their technology is relatively mature, they are no longer sufficient to meet the high demands of modern vehicles for efficiency, comfort, and energy efficiency. To improve vehicle power performance and fuel efficiency, electronically controlled transmissions (ECT) have emerged. Through real-time monitoring and control, ECT can automatically adjust the transmission's operating state according to the vehicle's driving conditions, optimizing shift timing and gear ratios, thereby improving the driving experience and energy efficiency.

[0003] Existing transmission control technologies still have shortcomings. Most existing control methods are based on traditional vehicle dynamics models. Although they can achieve basic transmission control, their adaptability in practical applications is poor, especially in terms of adaptability to multi-configuration transmissions and real-time dynamic control. They often cannot meet the high performance requirements of transmissions under complex operating conditions. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a control method and system for multi-configuration transmissions, which solves the problem that existing control methods are mostly based on traditional vehicle dynamics models. Although they can achieve basic speed control, their adaptability in practical applications is poor, especially in terms of adaptability to multi-configuration transmissions and real-time dynamic control. They often cannot meet the high performance requirements of transmissions under complex working conditions.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a control method for a multi-configuration transmission, comprising the following steps:

[0008] Collect and preprocess multi-source data, calculate the total driving resistance of the vehicle and convert it into traction force, multiply it with the current vehicle speed to obtain the power estimate, calculate the instantaneous change rate of the accelerator pedal opening signal and convert it into the driver's demand intensity, and concatenate the power estimate and the driver's demand intensity into a vector to construct a macroscopic feature vector.

[0009] A fully connected neural network model is constructed to evaluate the adaptability score of the gearbox configuration, the gearbox configuration is screened, a set of high-quality candidate configurations is generated, the required traction force is converted into the required torque of the gearbox input shaft, the thermodynamic entropy productivity is obtained, each high-quality candidate configuration in the set of high-quality candidate configurations is extracted, the comprehensive cost is calculated, and the target configuration is screened.

[0010] The current transmission configuration is determined based on the target configuration, and intelligent control is performed to switch transmission configurations. A visual interface is built to display the control results.

[0011] As a preferred embodiment of the control method for multi-configuration transmissions described in this invention, the following steps are included: calculating the total vehicle driving resistance and converting it into traction force, multiplying it by the current vehicle speed to obtain a power estimate, calculating the instantaneous rate of change of the accelerator pedal opening signal and converting it into driver demand intensity, and concatenating the power estimate and driver demand intensity into a vector to construct a macroscopic feature vector, including:

[0012] Based on the vehicle's longitudinal dynamics equations, the total driving resistance experienced by the vehicle is calculated and converted into the total traction force required to maintain the current state of motion. The required traction force is multiplied by the current vehicle speed to obtain a power estimate.

[0013] The backward difference method is used to calculate the instantaneous rate of change of the accelerator pedal opening signal and convert it into the driver's demand intensity.

[0014] The power estimate and the driver demand intensity are concatenated as vectors to construct a macroscopic feature vector.

[0015] As a preferred embodiment of the control method for multi-configuration transmissions described in this invention, the step of constructing a fully connected neural network model, evaluating the adaptability score of the transmission configuration, screening the transmission configurations, and generating a set of high-quality candidate configurations includes:

[0016] Collect and preprocess historical multi-source data, extract historical macro feature vectors, and generate a training set;

[0017] Construct a fully connected neural network model, train the fully connected neural network model using the training set, and obtain the adaptability score of the gearbox configuration;

[0018] Based on the mechanical design parameters of the gearbox, the allowable operating range of each gearbox configuration is defined, and gearbox configurations that do not meet the allowable operating range are eliminated to obtain a set of mechanically feasible configurations.

[0019] In the set of mechanically feasible configurations, the adaptability scores of the gearbox configurations are sorted in descending order, and the top M configurations with the highest adaptability scores are selected to generate a set of high-quality candidate configurations, where M is the number of selections.

[0020] As a preferred embodiment of the control method for multi-configuration transmissions described in this invention, the step of converting the required traction force into the required torque of the transmission input shaft, obtaining the thermodynamic entropy productivity, extracting each high-quality candidate configuration from the set of high-quality candidate configurations, calculating the comprehensive cost, and screening the target configuration includes:

[0021] By combining the total driving resistance and acceleration, the required traction force acting on the drive wheels is calculated, and the required traction force at the wheel ends is converted into the required torque of the gearbox input shaft. Based on the required torque, the thermodynamic entropy production rate is calculated.

[0022] Extract each high-quality candidate configuration from the set of high-quality candidate configurations, calculate the fundamental frequency of gear meshing, and convert it into a steady-state excitation potential;

[0023] Calculate the switching transient excitation potential based on the required torque;

[0024] The steady-state excitation potential and the switching transient excitation potential are fused to calculate the total modal excitation potential;

[0025] Minimize and maximize the entropy production rate and total modal excitation potential to calculate the overall cost.

[0026] From the set of candidate configurations, select the configuration with the minimum overall cost as the target configuration.

[0027] As a preferred embodiment of the control method for multi-configuration transmissions described in this invention, the step of determining the current transmission configuration based on the target configuration and intelligently controlling the switching of transmission configurations includes:

[0028] If the current transmission configuration is equal to the target configuration, it is determined that no switching is needed and the current state is maintained; otherwise, it is determined to switch the transmission configuration. At the starting point of the switching, the static torque difference is calculated and converted into feedforward compensation torque.

[0029] The expected acceleration is set based on the average of historical accelerations, the deviation between the actual acceleration and the expected acceleration is calculated, and the acceleration deviation is converted into feedback compensation torque.

[0030] The feedforward compensation torque and the feedback compensation torque are superimposed to obtain the total torque correction command for the power source, which is continuously sent to the power source controller.

[0031] After the torque phase ends, the adjusted transmission configuration is compared with the target configuration. If they are equal, the switch is considered successful and monitoring continues. Otherwise, the switch is considered to have timed out and a warning signal is issued.

[0032] As a preferred embodiment of the control method for multi-configuration gearboxes described in this invention, the step of constructing a visual interface to display the control results includes:

[0033] A visualization interface was built using the visualization tool Matplotlib to display the judgment results and total torque correction instructions in real time.

[0034] As a preferred embodiment of the control method for multi-configuration gearboxes described in this invention, the step of acquiring and preprocessing multi-source data includes:

[0035] Multi-source data is collected from the vehicle's central control unit using an API interface, and then denoised and standardized.

[0036] The multi-source data includes road slope angle, vehicle speed, vehicle weight, acceleration, accelerator pedal opening, shaft speed, drive wheel radius, oil temperature, and gear tooth count.

[0037] Secondly, the present invention provides a control system for multi-configuration transmissions, comprising:

[0038] The data acquisition and processing module is used to collect multi-source data from vehicles and perform noise reduction and standardization processing.

[0039] The vector splicing module is used to calculate the total driving resistance of the vehicle and convert it into traction force. Multiplying it with the current vehicle speed, it obtains a power estimate. It also calculates the instantaneous rate of change of the accelerator pedal opening signal and converts it into driver demand intensity. Finally, it splices the power estimate and driver demand intensity into a vector to construct a macroscopic feature vector.

[0040] The model set module is used to build fully connected neural network models, evaluate the adaptability score of gearbox configurations, screen gearbox configurations, and generate a set of high-quality candidate configurations.

[0041] The cost target module is used to convert the demand traction force into the demand torque of the gearbox input shaft, obtain the thermodynamic entropy productivity, extract each high-quality candidate configuration from the set of high-quality candidate configurations, calculate the comprehensive cost, and screen the target configuration.

[0042] The control and display module is used to determine the current gearbox configuration, intelligently control the switching of gearbox configurations, and build a visual interface to display the control results.

[0043] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the control method for a multi-configuration gearbox as described in the first aspect of the present invention.

[0044] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the control method for a multi-configuration gearbox as described in the first aspect of the present invention.

[0045] The beneficial effects of this invention are as follows: By utilizing the dynamic calculation of the total driving resistance of the vehicle and the intensity of the driver's demand, combined with real-time road conditions and driving behavior, this invention optimizes the configuration selection of the transmission. Compared with the traditional configuration selection method based on static mechanical parameters, our invention can dynamically adapt to different driving scenarios. By utilizing the calculation of thermodynamic entropy production rate and switching transient excitation potential, it can effectively reduce the energy loss and vibration noise of the transmission during the shifting process, thereby improving the overall performance of the transmission. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. 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 effort.

[0047] Figure 1 This is a flowchart of the control method for multi-configuration gearboxes in Example 1.

[0048] Figure 2 This is a schematic diagram of the control system for a multi-configuration gearbox in Example 1. Detailed Implementation

[0049] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0050] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0051] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0052] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a control method for multi-configuration gearboxes, including the following steps:

[0053] S1. Collect multi-source data and preprocess it, calculate the total driving resistance of the vehicle and convert it into traction force, multiply it with the current vehicle speed to obtain the power estimate, calculate the instantaneous change rate of the accelerator pedal opening signal and convert it into the driver's demand intensity, and concatenate the power estimate and the driver's demand intensity into a vector to construct a macroscopic feature vector.

[0054] Specifically, this involves collecting and preprocessing multi-source data, including:

[0055] Multi-source data is collected from the vehicle central control unit (VCU or transmission control unit TCU) using an API interface, and then denoised and standardized.

[0056] The multi-source data includes road slope angle, vehicle speed, vehicle weight, acceleration, accelerator pedal opening, shaft speed, drive wheel radius, oil temperature, and gear tooth count.

[0057] Furthermore, the total vehicle resistance is calculated and converted into traction force, multiplied by the current vehicle speed to obtain a power estimate. The instantaneous rate of change of the accelerator pedal opening signal is calculated and converted into driver demand intensity. The power estimate and driver demand intensity are then concatenated as vectors to construct a macroscopic feature vector, including:

[0058] Based on the classical longitudinal dynamics equations for vehicles, the total resistance force on the vehicle can be calculated using the following formula:

[0059] ,

[0060] in In order to be in The total resistance force experienced by the vehicle at any given moment. Let g be the acceleration due to gravity at time k. In order to be in Road gradient angle at any given time Let be the air density, and be a known environmental constant. , In order to be in The speed of the car at any given moment For the vehicle's curb weight, This refers to the vehicle's drag coefficient. This refers to the projected area of ​​the vehicle's front. The rolling resistance coefficient of the tire is provided by the supplier.

[0061] According to Newton's second law, the total traction force required to maintain the current state of motion is calculated using the following formula:

[0062] ,

[0063] in In order to be in The traction force constantly acting on the drive wheels In order to be in The longitudinal acceleration of the vehicle at any given moment;

[0064] Multiplying the required traction force by the current vehicle speed yields a power estimate, which represents the estimated instantaneous mechanical power acting on the drive wheels.

[0065] Using the backward difference method, the instantaneous rate of change of the accelerator pedal opening signal is calculated and converted into driver demand intensity. Driver demand intensity is defined as the weighted sum of the current pedal opening and the positive trend of change, as shown in the formula:

[0066] ,

[0067] in In order to be in The intensity of driver demand at any given time In order to be in The accelerator pedal opening at any given moment, The instantaneous rate of change of the accelerator pedal opening signal. This is a time constant used to convert the rate of change (% / s) into an increment with the same dimensions as the standardized opening degree (%). This value is a constant calibrated according to the driver's operating habits and determined through offline calibration tests, for example, set to 0.1.

[0068] By concatenating the power estimate and driver demand intensity into vectors, a macroscopic feature vector is constructed, as shown in the formula:

[0069] ,

[0070] in In order to be in The macroscopic feature vector at time t. In order to be in The estimated power demand of the vehicle at time T is the vector transpose.

[0071] The driving resistance calculation formula used in this invention considers multiple physical factors and can accurately reflect the vehicle's motion state under different road conditions and environments. Especially under conditions such as high slopes and complex terrain, the driving resistance experienced by the vehicle is relatively large. In this case, accurate calculation of traction force can ensure that the vehicle's power system provides sufficient support in a timely manner and prevent insufficient power. In this invention, by calculating the rate of change of the accelerator pedal signal, the control system can more accurately understand the driver's needs. The macroscopic feature vector not only includes the vehicle's power demand (power estimate) but also incorporates the driver's demand intensity information, which can provide an important basis for subsequent transmission control, energy efficiency optimization, etc.

[0072] S2. Construct a fully connected neural network model to evaluate the adaptability score of the gearbox configuration, screen the gearbox configuration, generate a set of high-quality candidate configurations, convert the demand traction force into the demand torque of the gearbox input shaft, obtain the thermodynamic entropy productivity, extract each high-quality candidate configuration from the set of high-quality candidate configurations, calculate the comprehensive cost, and screen the target configuration.

[0073] Specifically, a fully connected neural network model is constructed to evaluate the adaptability score of the gearbox configuration, and the gearbox configurations are screened to generate a set of high-quality candidate configurations, including:

[0074] Collect and preprocess historical multi-source data, extract historical macro feature vectors, and generate a training set;

[0075] Construct a fully connected neural network model, using macroscopic feature vectors as the input format;

[0076] The fully connected neural network model is trained using the training set, and the model parameters are iteratively optimized using the loss function and the Adam optimizer.

[0077] The macroscopic feature vector is input into the trained fully connected neural network model to obtain the adaptability score of the gearbox configuration (the activation function of the output layer of the neural network is Softmax, and the output is the adaptability probability of each configuration, which is normalized or mapped to the score value).

[0078] Based on the mechanical design parameters of the gearbox, the allowable operating range for each gearbox configuration is defined by the following formula:

[0079] ,

[0080] ,

[0081] in and This represents the shaft speed range, indicating the minimum and maximum shaft speeds. and This represents the speed range, indicating the minimum and maximum speeds, based on information provided by the supplier. In order to be in The gearbox shaft speed at any given moment;

[0082] By eliminating gearbox configurations that do not meet the allowable operating range, a set of mechanically feasible configurations is obtained;

[0083] In the set of mechanically feasible configurations, the adaptability scores of the gearbox configurations are sorted in descending order, and the top M configurations with the highest adaptability scores are selected to generate a set of high-quality candidate configurations, where M is the number of selections, which is set using a fixed number method.

[0084] Compared with traditional transmission configuration selection methods based on empirical rules and preset parameters, neural networks can adaptively adjust their evaluation criteria and optimize results according to changes in actual data. By introducing strict screening of mechanical parameters, neural networks ensure that the transmission operates under reasonable working conditions, avoiding system damage, inefficiency, or safety issues caused by unsuitable mechanical design.

[0085] Furthermore, the demand traction force is converted into the demand torque of the gearbox input shaft to obtain the thermodynamic entropy productivity. Each high-quality candidate configuration is extracted from the set of high-quality candidate configurations, the comprehensive cost is calculated, and the target configuration is selected, including:

[0086] The formula for converting the required traction force into the required torque on the gearbox input shaft is:

[0087] ,

[0088] in In order to be in The required torque of the gearbox input shaft at any given time. The driving wheel's rolling radius, For the current configuration in The estimated transmission efficiency at the operating point (shaft speed and input torque) at a given time. For the current configuration in Transmission ratio at any moment, The main reduction ratio is set by rules of thumb or experimental standards.

[0089] Based on the second law of thermodynamics, the ratio of system power dissipation to thermodynamic temperature is the entropy production rate. The thermodynamic entropy production rate is calculated based on the demand torque using the following formula:

[0090] ,

[0091] in For high-quality candidate configurations in Thermodynamic entropy yield at time t. Transmission efficiency for high-quality candidate configurations. In order to be in The speed of the gearbox input shaft at any given moment. In order to be in Transmission oil temperature at all times For absolute temperature reference value, take This is used to convert Celsius temperature to Kelvin temperature;

[0092] For each high-quality candidate configuration extracted from the set of high-quality candidate configurations, the fundamental frequency of gear meshing is calculated and converted into a steady-state excitation potential, as shown in the formula:

[0093] ,

[0094] ,

[0095] in For high-quality candidate configurations in The fundamental frequency of gear meshing at any given moment. For high-quality candidate configurations in The number of teeth on the shaft driving gear at any given time. For high-quality candidate configurations in Steady-state excitation potential at time t, The steady-state excitation coefficient represents the vibration excitation risk of the gearbox during continuous operation in the candidate configuration. This risk mainly stems from two aspects: (a) the periodic excitation of the structure's natural frequency by the gear meshing force; and (b) the broadband excitation caused by transmission power loss (mainly converted into heat and vibration), obtained through gearbox bench NVH testing calibration. Let be the nth natural frequency of the gearbox housing under the optimal candidate configuration. It is a very small positive number, used to prevent the denominator from being zero;

[0096] Based on the required torque, the transient excitation potential during switching is calculated using the following formula:

[0097] ,

[0098] ,

[0099] in The transient excitation potential for switching from the current gearbox configuration to a superior candidate configuration represents the risk of impact vibration excitation caused by sudden torque changes and mechanism actions during the transient process of switching from the current configuration to the candidate configuration. The torque step represents the theoretical increase in the torque required by the transmission input shaft when switching from the current configuration to a candidate configuration. The time required to switch from the current gearbox configuration to a superior candidate configuration. The first-order natural frequency of the high-quality candidate configuration. For the current gearbox configuration The required torque of the gearbox input shaft at any given time. As a high-quality candidate configuration, In order to be in When the transmission is already in the candidate configuration under the current vehicle requirements, the corresponding transmission input shaft torque is required.

[0100] Calculate the transient excitation potential during switching: assess the excitation risk to the housing vibration caused by the transient shock caused by the torque step and the switching action itself during the switching from the current configuration to the target configuration. This risk is proportional to the amount of torque step and the speed of the switching action (inversely proportional to the standard switching time), and inversely proportional to the first natural frequency (high-frequency structures are more sensitive to shocks).

[0101] The steady-state excitation potential and the switching transient excitation potential are fused to calculate the total modal excitation potential;

[0102] The calculation of the total modal excitation potential includes converting the switching transient excitation potential into an equivalent steady-state excitation intensity based on the time-intensity equivalence method. Within a set evaluation time window, the excitation dose generated by the steady-state excitation potential and the converted transient excitation dose are calculated respectively. The two doses are added together to obtain the total excitation dose, which is defined as the total modal excitation potential.

[0103] The entropy production rate and the total modal excitation potential are minimized and maximized to calculate the overall cost, as shown in the formula:

[0104] ,

[0105] ,

[0106] ,

[0107] in For high-quality candidate configurations in The overall cost of time, and For the normalized entropy yield and total modal excitation potential, and These are the weighting coefficients for the normalized entropy yield and the total modal excitation potential. and The base weights and weight adjustment ranges, for example, 0.5 and 0.3, are set through experimental calibration.

[0108] From the set of candidate configurations, select the configuration with the minimum overall cost as the target configuration.

[0109] This invention can more comprehensively consider the actual motion state and load conditions of the vehicle, thereby significantly improving the adaptability and response speed of the power system to complex road conditions. It can accurately calculate the required traction force at the wheel ends and convert it into the required torque of the transmission input shaft. By calculating the thermodynamic entropy production rate, it can evaluate the energy efficiency of the transmission under different operating conditions. The calculation of the gear meshing fundamental frequency can further evaluate the vibration characteristics of the transmission under different operating conditions. Vibration and noise issues are particularly important under high load and high speed. By introducing weighting coefficients, this method can flexibly adjust the evaluation criteria according to different application scenarios, thereby meeting the diverse requirements of different driving needs.

[0110] S3. Based on the target configuration, determine the current transmission configuration, intelligently control the switching of transmission configuration, and build a visual interface to display the control results;

[0111] Specifically, based on the target configuration, the current transmission configuration is determined, and intelligent control is performed to switch transmission configurations, including:

[0112] If the current transmission configuration is equal to the target configuration, then no switching is required, and the current state is maintained. Otherwise, the transmission configuration is switched. At the start of the switch, due to the change in the transmission ratio, there is a difference in the theoretical input shaft torque required to maintain the same vehicle requirements. The static torque difference is calculated using the following formula:

[0113] ,

[0114] in This is the static torque difference. and In order to be in At any given moment, the required torque of the transmission input shaft when the transmission is in its current configuration and candidate configuration;

[0115] To actively offset The potential impact is addressed by sending a feedforward torque command to the power source controller at a fixed pre-compensation time (e.g., 50ms) before the start of the torque phase.

[0116] The static torque difference is converted into feedforward compensation torque using the following formula:

[0117] ,

[0118] in To provide feedforward pre-compensation torque, the power source adjusts its output in advance, ensuring that the net torque change transmitted to the wheels is as smooth as possible when torque switching occurs. The feedforward compensation coefficient is a constant determined through calibration, ranging between 0 and 1 (e.g., 0.7), reflecting the dynamic response characteristics of the system to torque step changes;

[0119] During the torque phase time, the desired longitudinal acceleration is set to the actual acceleration value at the moment of switching on. This setting aims to maintain the vehicle's original motion state as much as possible during torque exchange.

[0120] The expected acceleration is set based on the average of historical accelerations. The deviation between the actual acceleration and the expected acceleration is calculated. A PID control algorithm is used to convert the acceleration deviation into feedback compensation torque, as shown in the formula:

[0121] ,

[0122] in To compensate for torque feedback, a proportional-integral controller formula is used to eliminate steady-state errors and improve dynamic response. The proportional control gain for the torque phase was determined through experimental calibration. The acceleration deviation (error) at time t;

[0123] The feedforward compensation torque and the feedback compensation torque are superimposed to obtain the total torque correction command for the power source, which is continuously sent to the power source controller.

[0124] After the torque phase ends, the adjusted transmission configuration is compared with the target configuration. If they are equal, the switch is considered successful and monitoring continues. Otherwise, the switch is considered to have timed out and a warning signal is issued.

[0125] Furthermore, a visual interface is constructed to display the control results, including:

[0126] A visualization interface was built using the visualization tool Matplotlib to display the judgment results and total torque correction instructions in real time.

[0127] Example 2, refer to Figure 2 As a second embodiment of the present invention, a control system for a multi-configuration gearbox includes:

[0128] The data acquisition and processing module is used to collect multi-source data from vehicles and perform noise reduction and standardization processing.

[0129] The vector splicing module is used to calculate the total driving resistance of the vehicle and convert it into traction force. Multiplying it with the current vehicle speed, it obtains a power estimate. It also calculates the instantaneous rate of change of the accelerator pedal opening signal and converts it into driver demand intensity. Finally, it splices the power estimate and driver demand intensity into a vector to construct a macroscopic feature vector.

[0130] The model set module is used to build fully connected neural network models, evaluate the adaptability score of gearbox configurations, screen gearbox configurations, and generate a set of high-quality candidate configurations.

[0131] The cost target module is used to convert the demand traction force into the demand torque of the gearbox input shaft, obtain the thermodynamic entropy productivity, extract each high-quality candidate configuration from the set of high-quality candidate configurations, calculate the comprehensive cost, and screen the target configuration.

[0132] The control and display module is used to determine the current gearbox configuration, intelligently control the switching of gearbox configurations, and build a visual interface to display the control results.

[0133] This embodiment also provides a computer device applicable to a control method for multi-configuration gearboxes, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the control method for multi-configuration gearboxes as proposed in the above embodiment.

[0134] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0135] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the control method for a multi-configuration gearbox as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0136] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A control method for a multi-configuration gearbox, characterized in that: The method comprises the following steps: Collecting multi-source data and preprocessing, calculating the total driving resistance of the vehicle and converting it into demand traction, multiplying the current vehicle speed to obtain the power estimation value, calculating the instantaneous change rate of the accelerator pedal opening signal and converting it into the driver's demand intensity, vector splicing the power estimation value and the driver's demand intensity to construct a macro feature vector; A fully connected neural network model is constructed, the adaptability score of the gearbox configuration is evaluated, the gearbox configuration is screened, and a high-quality candidate configuration set is generated, the demand traction is converted into the demand torque of the input shaft of the gearbox, the thermodynamic entropy production rate is obtained, each high-quality candidate configuration in the high-quality candidate configuration set is extracted, the comprehensive cost is calculated, and the target configuration is screened; Based on the target configuration, the current gearbox configuration is judged, the switching gearbox configuration is intelligently controlled, and a visual interface is constructed to display the control results.

2. The control method for a multi-configuration-oriented transmission according to claim 1, characterized by: The total driving resistance of the vehicle is calculated and converted into demand traction, the current vehicle speed is multiplied to obtain the power estimation value, the instantaneous change rate of the accelerator pedal opening signal is calculated and converted into the driver's demand intensity, the power estimation value and the driver's demand intensity are vector spliced to construct a macro feature vector, comprising: According to the vehicle longitudinal dynamics equation, the total driving resistance of the vehicle is calculated, and the demand traction required to maintain the current motion state is converted, and the demand traction is multiplied by the current vehicle speed to obtain the power estimation value; The instantaneous change rate of the accelerator pedal opening signal is calculated using the backward difference method, and the driver's demand intensity is converted; The power estimation value and the driver's demand intensity are vector spliced to construct a macro feature vector.

3. The control method for a multi-configuration-oriented transmission according to claim 2, characterized by: The fully connected neural network model is constructed, the adaptability score of the gearbox configuration is evaluated, the gearbox configuration is screened, and a high-quality candidate configuration set is generated, comprising: Collecting historical multi-source data and preprocessing, extracting historical macro feature vectors, and generating a training set; A fully connected neural network model is constructed, and the training set is used to train the fully connected neural network model to obtain the adaptability score of the gearbox configuration; According to the mechanical design parameters of the gearbox, the allowed working interval of each gearbox configuration is defined, the gearbox configurations that do not meet the allowed working interval are removed, and a mechanically feasible configuration set is obtained; In the mechanically feasible configuration set, the adaptability scores of the gearbox configurations are arranged in descending order, and the top M configurations with the highest adaptability scores are selected to generate a high-quality candidate configuration set, where M is the number of screening.

4. The control method for a multi-configuration-oriented transmission according to claim 3, characterized by: The demand traction is converted into the demand torque of the input shaft of the gearbox, the thermodynamic entropy production rate is obtained, each high-quality candidate configuration in the high-quality candidate configuration set is extracted, the comprehensive cost is calculated, and the target configuration is screened, comprising: The demand traction is converted into the demand torque of the input shaft of the gearbox, and the thermodynamic entropy production rate is calculated based on the demand torque; Each high-quality candidate configuration in the high-quality candidate configuration set is extracted, the gear meshing fundamental frequency is calculated, and it is converted into a steady-state excitation potential; Based on the demand torque, the switching transient excitation potential is calculated; The steady-state excitation potential and the switching transient excitation potential are fused to calculate the total modal excitation potential; The entropy production rate and the total modal excitation potential are normalized by minimum and maximum to calculate the comprehensive cost; From the candidate configuration set, the configuration with the minimum comprehensive cost is selected as the target configuration.

5. The control method for a multi-configuration-oriented transmission according to claim 4, characterized by: The target configuration is used to judge the current transmission configuration and intelligently control the switching of the transmission configuration, including: If the current transmission configuration is equal to the target configuration, it is determined that there is no need to switch, and the current state is maintained, otherwise it is determined to switch the transmission configuration, and at the switching starting point, the static torque difference is calculated, and the static torque difference is converted into a feedforward compensation torque; The expected acceleration is set based on the mean value of the historical acceleration, the deviation between the actual acceleration and the expected acceleration is calculated, and the acceleration deviation is converted into a feedback compensation torque; The feedforward compensation torque and the feedback compensation torque are superimposed to obtain a total torque correction instruction for the power source, and the total torque correction instruction is continuously sent to the power source controller; After the torque phase ends, the adjusted transmission configuration is compared with the target configuration, if they are equal, it is determined that the switching is successful, and the monitoring continues, otherwise it is determined that the switching is timed out, and a warning signal is issued.

6. The control method for a multi-configuration-oriented transmission according to claim 5, characterized by: The visual interface displays the control results, including: The visual interface is constructed using the visualization tool Matplotlib to display the judgment results and the total torque correction instruction in real time.

7. The control method for a multi-configuration-oriented transmission according to Claim 1, characterized by: The multiple source data is collected and preprocessed, including: Multiple source data is collected from the vehicle central control unit using the API interface, and denoising and standardization processing is performed; The multiple source data includes road slope angle, vehicle speed, vehicle weight, acceleration, accelerator pedal opening, shaft speed, drive wheel radius, oil temperature, and gear tooth number data.

8. A control system for a multi-configuration gearbox, for implementing the control method for a multi-configuration gearbox according to any one of claims 1 to 7, characterized in that: It includes: The acquisition and processing module is used to collect multiple source data of the vehicle and perform denoising and standardization processing; The splicing vector module is used to calculate the total driving resistance of the vehicle and convert it into the required traction, multiply it by the current speed to obtain the power estimate, calculate the instantaneous change rate of the accelerator pedal opening signal, convert it into the driver demand intensity, and splice the power estimate and the driver demand intensity to construct a macro feature vector; The model set module is used to construct a fully connected neural network model, evaluate the adaptability score of the transmission configuration, filter the transmission configuration, and generate a high-quality candidate configuration set; The cost target module is used to convert the required traction to the required torque of the transmission input shaft, obtain the thermodynamic entropy production rate, extract each high-quality candidate configuration in the high-quality candidate configuration set, calculate the comprehensive cost, and select the target configuration; The control display module is used to judge the current transmission configuration and intelligently control the switching of the transmission configuration, and construct a visual interface to display the control results. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The processor executes the computer program to realize the steps of the control method for the multi-configuration transmission of any one of claims 1 to 7.

10. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the control method for the multi-configuration transmission of any one of claims 1 to 7.

Images