Fuel vehicle simulation driving method and system based on vehicle model parameter library and medium

Abstract

The invention discloses a fuel vehicle simulation driving method and system based on a vehicle model parameter library and a medium, and relates to the technical field of analogue simulation. The method comprises the following steps: constructing a vehicle model parameter library; collecting vehicle operation data in real time; calling a target parameter from a parameter library according to a selected vehicle model, and analyzing to generate a torque and sound control signal; and acquiring a suspension adjustment instruction and a somatosensory feedback instruction, fusing the torque adjustment signal with the sound control signal, the suspension adjustment instruction and the somatosensory feedback instruction to generate a target driving control scheme, and realizing simulated driving of the fuel vehicle through the target driving control scheme. The technical problems that existing automobile driving experience is single, and driving feelings of multiple types of fuel vehicles cannot be truly restored are solved, multiple driving experience dimensions such as power, sound, suspension and somatosensory feedback are deeply fused by constructing and calling an extensible vehicle model parameter library, and the purposes of improving the sense of reality and immersion of driving and improving the driving experience are achieved. And the user experience is optimized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of simulation technology, and particularly relates to a fuel vehicle simulation driving method and system based on a vehicle model parameter library and a medium. BACKGROUND

[0002] With the rapid development of new energy vehicles, although the electric drive system has advantages in power response, it also brings a completely different driving experience from traditional fuel vehicles. In particular, electric vehicles lack the engine sound and mechanical control feeling of traditional fuel vehicles, resulting in varying degrees of loss of immersion in driving for many drivers. In particular, in terms of power output characteristics, gear shift jerk, engine sound and vehicle body dynamics, new energy vehicles usually cannot fully restore the driving pleasure brought by fuel vehicles.

[0003] Existing simulation technologies mostly focus on the driving simulation of a single type of fuel vehicle, and cannot fully simulate the diversified driving experience of multiple types of fuel vehicles. At the same time, some existing systems also have problems such as poor synchronization and insufficient details in terms of power characteristics and sound simulation, resulting in a less-than-satisfactory user experience. For example, a simulation sound system that plays fixed sound effects cannot dynamically adjust according to real-time driving operations, causing the sound to be out of sync with the actual state of the vehicle, further weakening the sense of reality of driving. Therefore, how to improve the driving experience of new energy vehicles through simulation technology has become a problem to be solved. SUMMARY

[0004] The present application provides a fuel vehicle simulation driving method and system based on a vehicle model parameter library, which solves the technical problem of single driving experience and inability to truly restore the driving experience of multiple types of fuel vehicles. By constructing and calling an extensible vehicle model parameter library, multiple driving experience dimensions such as power, sound, suspension and somatosensory feedback are deeply integrated to achieve the technical effect of improving the sense of reality and immersion of driving and optimizing the user experience.

[0005] In a first aspect, the application provides a fuel vehicle simulation driving method based on a vehicle model parameter library, the method comprising: constructing a vehicle model parameter library, the vehicle model parameter library containing power characteristic parameters, sound wave characteristic parameters, virtual gear parameters, gear shift power interruption duration and suspension characteristic parameters of multiple types of fuel vehicles; collecting vehicle operation data in real time, the vehicle operation data including throttle opening, brake opening, vehicle speed and motor speed; calling target vehicle model parameters from the vehicle model parameter library according to a user-selected vehicle model, performing control parameter analysis on the vehicle operation data and the target vehicle model parameters based on a power mapping algorithm and a sound wave synthesis algorithm, generating a torque adjustment signal and a sound wave control signal; obtaining suspension adjustment instructions and somatosensory feedback instructions, fusing the torque adjustment signal and the sound wave control signal, the suspension adjustment instructions and the somatosensory feedback instructions, generating a target driving control scheme, and performing fuel vehicle simulation driving through the target driving control scheme.

[0006] In a second aspect, the application provides a fuel vehicle simulation driving system based on a vehicle model parameter library, the system comprising: a parameter library construction unit: constructing a vehicle model parameter library, the vehicle model parameter library containing power characteristic parameters, sound wave characteristic parameters, virtual gear parameters, gear shift power interruption duration and suspension characteristic parameters of multiple types of fuel vehicles; a data collection unit: collecting vehicle operation data in real time, the vehicle operation data including throttle opening, brake opening, vehicle speed and motor speed; a parameter analysis unit: calling target vehicle model parameters from the vehicle model parameter library according to a user-selected vehicle model, performing control parameter analysis on the vehicle operation data and the target vehicle model parameters based on a power mapping algorithm and a sound wave synthesis algorithm, generating a torque adjustment signal and a sound wave control signal; a simulation driving unit: obtaining suspension adjustment instructions and somatosensory feedback instructions, fusing the torque adjustment signal and the sound wave control signal, the suspension adjustment instructions and the somatosensory feedback instructions, generating a target driving control scheme, and performing fuel vehicle simulation driving through the target driving control scheme.

[0007] In a third aspect, the application provides a computer-readable medium storing a computer program, which, when executed by a processor, implements the fuel vehicle simulation driving method based on a vehicle model parameter library provided by the application.

[0008] The one or more technical solutions provided in the application have at least the following technical effects or advantages: Firstly, a vehicle model parameter library is constructed, the vehicle model parameter library containing power characteristic parameters, sound wave characteristic parameters, virtual gear position parameters, gear shifting power interruption time length and suspension characteristic parameters of multiple types of fuel vehicles; subsequently, vehicle operation data is collected in real time, the vehicle operation data including throttle opening, brake opening, vehicle speed and motor speed; then, target vehicle model parameters are called from the vehicle model parameter library according to a user-selected vehicle model, control parameter analysis is performed on the vehicle operation data and the target vehicle model parameters based on a power mapping algorithm and a sound wave synthesis algorithm, torque adjustment signals and sound wave control signals are generated; finally, suspension adjustment instructions and somatosensory feedback instructions are obtained, the torque adjustment signals and the sound wave control signals, the suspension adjustment instructions and the somatosensory feedback instructions are fused, a target driving control scheme is generated, and the target driving control scheme is used for fuel vehicle simulation driving. The technical problem that the existing automobile driving experience is single and cannot truly restore the driving and riding feelings of multiple types of fuel vehicles is solved, multiple driving experience dimensions such as power, sound wave, suspension and somatosensory feedback are deeply fused by constructing and calling an extensible vehicle model parameter library, and the technical effects of improving driving realism and immersion and optimizing user experience are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0010] Figure 1 A fuel vehicle simulation driving method flowchart based on a vehicle model parameter library is provided for the embodiments of the present application.

[0011] Figure 2 A fuel vehicle simulation driving system structure diagram based on a vehicle model parameter library is provided for the embodiments of the present application.

[0012] Explanation of reference signs: parameter library construction unit 11, data acquisition unit 12, parameter analysis unit 13, simulation driving unit 14. DETAILED DESCRIPTION

[0013] The present application provides a fuel vehicle simulation driving method, system and medium based on a vehicle model parameter library, solves the technical problem that the existing automobile driving experience is single and cannot truly restore the driving and riding feelings of multiple types of fuel vehicles, deeply fuses multiple driving experience dimensions such as power, sound wave, suspension and somatosensory feedback by constructing and calling an extensible vehicle model parameter library, and achieves the technical effects of improving driving realism and immersion and optimizing user experience.

[0014] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0015] It should be noted that the terms “comprising” and “having” are intended to cover the inclusion of not exclusive inclusion, for example, a process, method, system, product or server containing a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0016] Embodiment one, as shown in the present application provides a fuel vehicle simulation driving method based on a vehicle type parameter library, the method comprising: Figure 1 constructing a vehicle type parameter library, the vehicle type parameter library containing power characteristic parameters, sound characteristic parameters, virtual gear parameters, shift power interruption time and suspension characteristic parameters of multiple types of fuel vehicles.

[0017] ​In one embodiment, the construction of a vehicle model parameter library is one of the core steps in realizing a simulated driving experience for multiple types of gasoline-powered vehicles. This parameter library covers various vehicle performance parameters such as the power characteristics, sound characteristics, virtual gears, shift power interruption duration, and suspension characteristics of gasoline-powered vehicles. This data provides the necessary foundation for the system, supporting the simulation of various types of gasoline-powered vehicles, from ordinary family cars to high-performance sports cars, ensuring that the driving experience of different models can be accurately reproduced. Among them, the power characteristic parameters are collected by professional equipment in chassis dynamometers or actual road tests, including torque-speed curves, acceleration response characteristics, engine power output, throttle response curves, etc. for each model under different operating conditions. These parameters are used to describe the power performance of the vehicle under different driving conditions and help the system adjust the power output characteristics during simulation. Acquiring sound characteristic parameters requires a semi-anechoic laboratory environment. This involves the sound characteristics of a vehicle engine at different speeds, such as fundamental frequency, harmonic distribution, and noise attenuation characteristics. By collecting sound data from different vehicle models under various speed conditions, the system can synthesize a sound that matches the current vehicle's operating state. For example, the difference in sound characteristics between a four-cylinder engine and a V8 engine at high speeds needs to be simulated using these sound characteristic parameters. Virtual gear parameters include virtual gear settings for different vehicle models. These virtual gears are designed to simulate the shifting experience of a traditional manual transmission. Each virtual gear's parameters correspond to different gear ratios, power response characteristics during shifting, and shifting timing. The system can automatically select the corresponding virtual gear based on the user's chosen vehicle model, thus providing a more precise shifting experience, including physical phenomena such as shift shock and power loss. The shift power interruption duration refers to the simulated duration of power transmission interruption during gear shifting. Different types of vehicles and transmissions (such as manual, automatic, and dual-clutch transmissions) will have different shift interruption durations. This parameter determines the smoothness of the vehicle's power response during gear shifts in the simulation, simulating the driver's real feeling when shifting gears. Suspension characteristic parameters include the stiffness, travel, and height of the vehicle's suspension. These directly affect the vehicle's handling stability and driving comfort. Based on the selected vehicle's suspension parameters, the system can adjust the suspension stiffness and height in real time to simulate the dynamic performance of a gasoline vehicle under different road conditions. For example, sports cars typically have a stiffer suspension tuning, while family sedans prioritize comfort. The system can adjust the suspension system according to the user's selected vehicle model and driving conditions to obtain a more realistic driving experience. By accurately constructing these parameters and integrating them into the vehicle parameter library, the system can simulate the driving characteristics of different types of gasoline vehicles, meeting the simulation needs of various models from daily family cars to high-performance sports cars, providing drivers with an immersive and diversified driving experience.

[0018] Furthermore, the specific steps for obtaining acoustic characteristic parameters include: Raw sound wave data is collected through an anechoic chamber and a silent drum device; the raw sound wave data is classified and labeled according to the rotation speed information to obtain sound wave data of multiple rotation speed types; feature extraction is performed on the sound wave data of each type to obtain sound wave feature parameters, including fundamental frequency, harmonic distribution and attenuation characteristics.

[0019] Preferably, the target fuel vehicle or target simulated engine is placed on a silent drum device within a silencing chamber. After the silent drum device is activated, it simulates the actual operating state of the engine and collects exhaust sound at different engine speeds using a high-sensitivity microphone array, forming raw sound data. Subsequently, the engine speed is recorded synchronously, and the raw sound data at different speeds (2000 rpm, 3000 rpm, 5000 rpm, etc.) are stored as independent datasets, forming multi-speed-type sound data. Each speed-type sound data is labeled with a speed tag and associated with operating parameters such as throttle opening and load. Then, the sound data for each speed type is processed by frame segmentation, and time-frequency analysis is performed using Short-Time Fourier Transform (STFT) to generate a spectrogram. Next, the spectrogram is analyzed using the peak spacing, harmonic product method, or autocorrelation function method to locate the main period frequency of the sound wave, thereby obtaining the fundamental frequency of each sound wave signal, which is used as one of the sound wave characteristic parameters. Since harmonics are integer multiples of the fundamental frequency, the harmonic components and their intensities, such as the 2nd, 4th, and 6th harmonics, are obtained through spectral peak detection, forming a harmonic distribution, which is also used as one of the sound wave characteristic parameters. In addition, the Hilbert envelope or short-time energy envelope is used to extract the decay curve of the target harmonic over time for each throttle release or step event, and the envelope is exponentially fitted during the decay phase to obtain the decay time constant. Alternatively, 90% to 10% of the decay time of the envelope can be used as the decay time constant. By calculating the decay time constant for each harmonic separately, the decay characteristics can be quantified to reflect the dissipation characteristics of different frequency components, which is also used as one of the sound wave characteristic parameters. After completing the above steps, the sound characteristic parameters of each speed type sound data can be obtained. These sound characteristic parameters will be stored in the vehicle parameter library as input for subsequent simulated driving, ensuring that the real engine sound can be reproduced and improving the immersion and realism of simulated driving.

[0020] Real-time vehicle operation data is collected, including throttle opening, brake opening, vehicle speed, and motor speed.

[0021] In one embodiment, to achieve a high-fidelity simulation of a gasoline-powered vehicle driving experience, a sensor array deployed at key parts of the vehicle continuously collects highly dynamic vehicle operation data. Specifically, high-precision non-contact throttle and brake pedal pivot sensors, such as Hall effect sensors, are installed at the pivot points of the accelerator and brake pedals, respectively. These sensors measure the position or angle changes of the pedals in real time at a frequency of at least 100Hz and convert them into linear electrical signals representing the driver's power or braking force requests. Vehicle speed sensors, such as magnetoelectric or Hall effect sensors, integrated into the drive axle or wheel speed sensors, continuously detect the vehicle's actual speed. A motor speed sensor embedded in the drive motor assembly provides real-time feedback on the motor rotor's rotational speed; this signal is one of the core parameters for calculating the simulated engine speed and synthesizing the synchronous sound. All the analog signals collected by these sensors are converted into standardized digital data streams through local analog-to-digital conversion and transmitted in real time to the central control module via the vehicle's CAN bus or a higher-bandwidth dedicated network, synchronized with timestamps. This set of high-frequency, multi-parameter, and synchronized real-time data streams forms the perceptual basis for dynamically simulating the driving experience of a fuel-powered vehicle, ensuring the real-time performance and accuracy of closed-loop control from driver operation to vehicle simulation response.

[0022] Based on the vehicle model selected by the user, the target vehicle model parameters are retrieved from the vehicle model parameter library. The vehicle operation data and the target vehicle model parameters are analyzed using a power mapping algorithm and a sound synthesis algorithm to generate torque adjustment signals and sound control signals.

[0023] In one embodiment, when a user selects a target simulated vehicle model through the central control interface, the system retrieves the corresponding vehicle model parameters from the vehicle model parameter library as the target vehicle model parameters. Subsequently, with the central control module as the core processor, it synchronously receives vehicle operation data and target vehicle model parameters. Through the parallel execution of the power mapping algorithm and the sound synthesis algorithm, the system jointly analyzes and fuses the input vehicle operation data and target vehicle model parameters. Specifically, the power mapping algorithm uses the instantaneous throttle opening change rate and current vehicle speed from the vehicle operation data as core input variables, combines them with the virtual gear parameters defined in the target vehicle model parameters, and performs forward calculations using a built-in model to calculate a target torque value in real time. Finally, it encapsulates and generates a torque adjustment signal with a timestamp and torque command. Simultaneously, the sound synthesis algorithm dynamically generates audio waveform data that strictly matches the power state based on the vehicle speed, motor speed, and sound characteristic parameters in the target vehicle model parameters at the same moment, and outputs it as a low-latency sound control signal. The entire analysis and generation process is completed within an extremely short control cycle, ensuring that the torque command and the sound signal are highly synchronized in time, thereby providing a consistent control basis for subsequent steps and enabling the driving experience of each model to be realistically reproduced.

[0024] Furthermore, the generation of torque adjustment signals and sound control signals includes: The power mapping algorithm employs a dual-input single-output model. This model is trained to construct a torque adjustment model. Based on this model, control parameters are analyzed using the throttle opening change rate and current vehicle speed from the vehicle operation data, as well as the virtual gear parameters from the target vehicle model parameters, to generate a torque adjustment signal. Finally, a sound wave control signal is generated using a sound wave synthesis algorithm to analyze the current vehicle speed, motor speed, and sound wave characteristic parameters from the target vehicle model parameters.

[0025] Preferably, labeled samples with timestamps are first collected on representative gasoline vehicles under multiple operating conditions, such as idling, constant speed, different throttle steps, dynamic acceleration and deceleration, and gear shift transitions. The samples at least record the throttle opening and its rate of change, vehicle speed, actual output torque, and virtual gear. Then, the dual-input single-output model in the power mapping algorithm is invoked. This model uses the throttle opening rate of change and the current vehicle speed as dual inputs and the target torque as the output. A lightweight, interpretable regressor, such as a regularized piecewise linear model or a small multilayer perceptron, can be used. The training process involves classifying the collected samples according to the virtual gear to form a torque control sample set, normalizing the inputs according to the gear, and dividing the set into training and validation sets. Iterative training is then performed using mean squared error as the primary loss. After training, the accuracy of torque prediction is evaluated on the validation set to determine if it meets the preset accuracy criteria. If not, relevant hyperparameters are adjusted, such as the learning rate, regularization coefficient, and network structure. If the criteria are met, the trained dual-input single-output model is stored as a torque adjustment model. Subsequently, in real-time driving simulation, after the user selects a vehicle model, the system calls the torque adjustment model for that vehicle model in that gear based on the virtual gear parameters in the target vehicle model parameters. The throttle opening change rate and current vehicle speed from the vehicle's operating data are input into this torque adjustment model. Based on its internally learned complex nonlinear mapping relationships, the torque adjustment model calculates a target torque value consistent with the power response characteristics of the target gasoline vehicle under the same operating conditions. This target torque value is then converted into a torque adjustment signal executable by the drive motor controller, thereby accurately reproducing the power response, acceleration feel, and even shift shock of the target gasoline vehicle. Simultaneously, the sound synthesis algorithm relies on the acoustic characteristic parameters of the target vehicle model retrieved from the vehicle model parameter library, including the fundamental frequency, harmonic distribution, and attenuation characteristics of single-cylinder to multi-cylinder engines at different speeds. During simulated driving, the system receives real-time inputs of the vehicle's current speed and motor speed. Based on this, it dynamically retrieves and extracts matching characteristic parameters from the sound signature parameters. Then, it employs audio synthesis techniques, such as additive synthesis, wavetable synthesis, or physical modeling synthesis. Specifically, it uses fundamental frequency parameters to generate a basic oscillation signal, superimposes harmonic components modulated by harmonic distribution parameters, and applies a dynamic envelope controlled by attenuation characteristic parameters to synthesize a continuously changing digital audio stream that perfectly matches the simulated engine operating conditions. This digital audio stream is then encapsulated into a sound signature control signal with precise timestamps and transmitted in real-time to the sound signature simulation module via a high-speed audio bus, such as A2B or MOST, to drive the speakers inside and outside the vehicle. This ensures that the auditory feedback of the sound signature is synchronized with the torque response of the powertrain and the dynamic changes of the vehicle body in human perception, achieving an immersive, high-fidelity simulation.

[0026] Furthermore, generating a torque adjustment signal includes: The power mapping algorithm adopts a dual-input single-output model; the dual-input single-output model is trained for torque control to construct a torque adjustment model; combined with the virtual gear parameters of the target vehicle model parameters, the torque adjustment model is used to analyze the throttle opening change rate and current vehicle speed in the vehicle operation data to generate a torque adjustment signal.

[0027] Optionally, the power mapping algorithm is implemented by employing a dual-input single-output model to accurately simulate the vehicle's power characteristics. This dual-input single-output model can use a lightweight, interpretable regressor, such as a regularized piecewise linear model or a small multilayer perceptron, to fit the nonlinear relationship between the input and output. The input includes two nodes, corresponding to the throttle opening change rate and the current vehicle speed, respectively, and the output is a single node corresponding to the target torque value. During training, the throttle opening change rate and vehicle speed of each frame in the torque control sample set are used as input features, and the actual engine torque collected at the same time is used as the target label. Mean squared error is used as the loss function to perform supervised learning on the model, allowing it to learn the complex, nonlinear mapping function between the driver's operating intention and vehicle state to the torque response that the fuel vehicle engine should have. The trained model is then solidified as a torque adjustment model specific to this vehicle model. Once the torque adjustment model is constructed, the system uses it to analyze the control parameters of the throttle opening change rate and current vehicle speed in the real-time vehicle operation data. At this stage, the model generates a precise torque adjustment signal based on the input throttle opening change rate and vehicle speed, combined with the virtual gear parameters of the target vehicle model. This torque adjustment signal indicates the torque value that the vehicle needs to output, thereby controlling the torque output of the motor so that the vehicle's power response matches the actual performance of the selected vehicle model.

[0028] Furthermore, the torque regulation model is constructed, including: A real-world driving dataset is collected, which includes the rate of change of throttle opening under different virtual gear parameters for each vehicle model and the actual torque output data under different speed combinations. The real-world driving dataset is classified and labeled according to the virtual gear parameters for each vehicle model to obtain a torque control sample set. The dual-input single-output model is trained based on the torque control sample set to construct a torque regulation model.

[0029] Optionally, a real-world driving dataset is first collected. Each data point in this dataset records different combinations of throttle opening change rate and vehicle speed under virtual gear parameters for each vehicle model, along with the corresponding actual torque output data. This data reflects the vehicle's actual power response under different driving conditions. Subsequently, this real-world driving dataset is classified according to the virtual gear parameters. During this process, data is assigned to different categories based on the recorded virtual gear information. Each category corresponds to a specific gear; for example, a particular virtual gear might represent high torque output during acceleration, while another gear might represent low torque output during smooth driving. This classification method forms a structured torque control sample set. This torque control sample set contains data on the throttle opening change rate, vehicle speed, and actual output torque for each virtual gear, providing accurate information about the relationship between the model's input and output under different gears. Subsequently, based on the torque control sample set obtained from classification, the dual-input single-output model is trained. Taking a small multilayer perceptron as an example, the throttle opening change rate and current vehicle speed in the torque control samples enter the model from the input layer and are normalized to avoid training instability due to different units. After the input layer, the normalized samples enter the hidden layer, which consists of multiple neurons. Each neuron receives data from the input layer, weights it, and then performs a nonlinear transformation using an activation function such as ReLU to convert the received data into a new output, which is then passed to the next layer. During training, the weights and biases of the neural network are continuously adjusted using the backpropagation algorithm. The weights and biases of each layer are continuously updated during training, thereby reducing the value of the loss function through multiple iterations and improving the model's prediction accuracy. In the model, the number of hidden layers and the number of neurons in each layer have a significant impact on the model's performance. In a small multilayer perceptron, one or two hidden layers are typically used, each consisting of several neurons. Each neuron is connected to all neurons in the previous layer, so the input of each neuron is the weighted output of all neurons in the previous layer. In this way, the model learns the complex nonlinear relationship between input and output. The weighted output data then flows to the output layer, where the target torque value—the torque the vehicle should output under the current operating conditions—is generated based on the output of the hidden layers. The output layer typically has one neuron, corresponding to the target torque value. At this layer, the model's predicted value is compared to the actual torque, and the error is calculated using mean squared error. A smaller loss value indicates a stronger predictive ability. Next, the gradient of the loss function is calculated and backpropagated to the weights and biases of each layer. The model adjusts the weights and biases using gradient descent. In this way, the model is progressively optimized to minimize the error between the predicted and actual values.The training process is iterative, with backpropagation executed multiple times. During each execution, the model gradually improves its prediction accuracy for the target torque by adjusting parameters. After each training iteration, the model is evaluated on a validation set to check its prediction accuracy. If the error on the validation set is still significant, hyperparameters, such as the learning rate and the number of hidden layer neurons, are further adjusted until the model's prediction error reaches a predetermined accuracy standard. Finally, the training process ends when the model is fully trained and demonstrates sufficiently high accuracy on the validation set. At this point, the trained dual-input single-output model is stored as a torque regulation model and used in actual simulations to generate torque regulation signals in real time, thereby controlling the motor's torque and simulating an accurate driving experience.

[0030] The system acquires suspension adjustment commands and haptic feedback commands, fuses the torque adjustment signal with the sound control signal, the suspension adjustment commands and haptic feedback commands to generate a target driving control scheme, and performs simulated driving of a fuel vehicle using the target driving control scheme.

[0031] In one embodiment, suspension adjustment commands are generated based on suspension characteristic parameters from the target vehicle model's specifications. These commands ensure accurate simulation of the dynamic handling performance and driving comfort of different vehicle models. For example, for sports sedans, the suspension stiffness is adjusted to be higher to enhance support and grip during cornering; for family sedans, the suspension is adjusted to be softer to improve driving comfort. Simultaneously, haptic feedback commands are generated through gear shift lever force feedback and seat vibration feedback to simulate the driving feedback of a real vehicle. For instance, when the driver shifts gears, the gear shift lever provides a mechanical damping feel and a "click" sound, allowing the driver to perceive the power interruption during gear shifts; seat vibration simulates engine vibration based on torque changes, enhancing the immersion and realism of the driving experience. Through these feedbacks, the driver can obtain a driving feel closer to real-world driving in the virtual driving environment. During simulation, the system encapsulates and aligns the generated torque adjustment signal with the sound control signal, suspension adjustment command, and haptic feedback command within a unified time frame. This fusion generates a target driving control scheme that is strictly synchronized in time and logically consistent. Specifically, the torque adjustment signal is combined with the sound control signal to ensure that the engine sound and vehicle power output changes synchronously during acceleration, deceleration, or gear shifting, thereby enhancing the auditory and dynamic driving experience. Next, the suspension adjustment command and haptic feedback command work in conjunction with the aforementioned signals to comprehensively adjust the vehicle's dynamic handling and the driver's perceptual feedback, further enhancing vehicle stability, comfort, and driving pleasure during the simulation. By effectively fusing these signals, a target driving control scheme can be generated. This scheme integrates control commands from multiple dimensions, including the powertrain, sound simulation, suspension adjustment, and haptic feedback. It enables simulated driving of a gasoline-powered vehicle based on the power adjustment module and sound simulation module, ensuring that the simulation system can synchronously adjust the output of each subsystem under different driving conditions. This provides the driver with a personalized and realistic driving experience, enhancing driving immersion.

[0032] Furthermore, acquiring suspension adjustment commands and haptic feedback commands includes: The suspension stiffness and height are adjusted in real time based on the suspension characteristic parameters of the target vehicle model, generating suspension adjustment commands; shift lever force feedback commands and seat vibration commands are obtained; and haptic feedback commands are generated based on the shift lever force feedback commands and seat vibration commands.

[0033] Preferably, after the user selects a target simulated vehicle model, the system retrieves the suspension characteristic parameters of that model from the vehicle parameter library. These parameters quantify the chassis dynamic characteristics of the target gasoline vehicle, such as the roll stiffness coefficient describing anti-roll capability, the pitch stiffness coefficient describing pitch suppression capability, the damping force-speed mapping table describing damping force changes under different driving modes, and the vehicle height setting value. During vehicle operation, real-time vehicle operation data, such as lateral acceleration, longitudinal acceleration, steering angular velocity, and vehicle speed, are continuously received. The system then calls the roof control algorithm to perform calculations based on this real-time data and the suspension characteristic parameters of the target vehicle model. For example, when the system detects that the vehicle is starting to corner and generating lateral acceleration, it calculates the instantaneous increase in damping force required to suppress body roll based on the roll stiffness coefficient of the target vehicle model. When the vehicle accelerates rapidly, it calculates the rear axle damping force based on the pitch stiffness coefficient to suppress the "nose-up" phenomenon. Simultaneously, based on the preset or user-selected driving mode, the system may call the corresponding mapping table to adjust the vehicle height to a lower value. Ultimately, these calculated target damping force and height values ​​are encapsulated into specific suspension adjustment commands that can be parsed by the suspension actuators. These commands are then sent to the suspension control units of each wheel via the vehicle bus, enabling real-time, dynamic adjustment of the suspension stiffness and height. When the system determines that the driver has shifted gears based on the virtual gear logic, it simulates the power characteristics of a gasoline vehicle, such as gear shift interruption and torque decay, and generates a shift lever force feedback command via a micro-motor. Simultaneously, a vibration module installed in the driver's seat simulates engine vibration characteristics based on torque adjustment signals, generating a seat vibration command. By synchronizing and integrating the shift lever force feedback command and the seat vibration command, and packaging them into a unified tactile feedback command, which is then distributed to the corresponding actuators, the system provides the driver with a tactile experience synchronized with visual, auditory, and power feedback, completing the closed loop of immersive simulation.

[0034] Furthermore, acquiring shift lever force feedback commands and seat vibration commands includes: The system simulates the power characteristics of a gasoline vehicle using virtual gear shifting logic, including gear shift interruption and torque decay. A micro motor generates a gear shift lever force feedback command based on these power characteristics. A vibration module installed in the driver's seat simulates engine vibration characteristics based on the torque adjustment signal, generating a seat vibration command.

[0035] Optionally, the system first simulates the power characteristics of a gasoline-powered vehicle based on virtual gear logic, including shift interruptions and torque decay. Each virtual gear corresponds to a specific gear ratio, power characteristics during shifting, and corresponding power response. When the driver performs a shift operation, the system dynamically determines the current virtual gear based on the current vehicle speed, motor speed, and the driver's throttle input, referring to a predefined shift graph in the vehicle parameter library, i.e., the speed-vehicle speed correspondence. When a shift is deemed necessary, the system strictly simulates the power characteristics of a real gasoline-powered vehicle. That is, during the shift, a torque adjustment signal with a duration of a specific value (e.g., 50-200ms) is generated, instructing the drive motor to instantly reduce the output torque to zero or an extremely low value to simulate the power interruption and jerkiness during traditional gearbox shifts. In addition, when simulating specific operating conditions such as low engine speed and high load, the system actively controls the torque output curve to present a gradual increase rather than the instantaneous response inherent in the motor, in order to mimic the torque decay characteristics of an internal combustion engine. Based on the real-time state of the aforementioned virtual dynamic characteristics, a micro-motor is driven to generate a reverse torque simulating mechanical resistance. The force curve of this torque is designed according to the shift feel parameters of the target vehicle model (e.g., heavier for sports cars, lighter for family cars). At the instant the virtual gear engages, a command triggers a short, high-frequency micro-motion and sound simulation, generating a clear "click" sound, which is transmitted to the driver's hand via the gear shift lever. This series of actions is encoded into a real-time, low-latency gear shift lever force feedback command to ensure the driver can perceive a realistic shifting experience. Subsequently, a vibration module installed in the driver's seat designs vibration feedback based on the changing characteristics of the torque adjustment signal. The engine's vibration characteristics are typically related to its speed, torque output, and workload. During acceleration, the engine produces stronger vibrations, while during deceleration, the vibrations are relatively weaker. Based on the torque adjustment signal, the system calculates its amplitude and frequency to map a low-frequency vibration pattern that matches the engine's vibration characteristics. Next, based on the simulated vibration characteristics, seat vibration commands are generated. This includes converting the vibration pattern into specific control signals to drive the vibration module or subwoofer in the seat to produce vibrations of different intensities and frequencies, ensuring that the driver can experience vibrations in virtual driving that are highly consistent with the dynamic changes of a real vehicle.

[0036] Furthermore, simulating driving a gasoline-powered vehicle using the target driving control scheme includes: A power adjustment module and a sound simulation module are constructed; based on the power adjustment module and the sound simulation module, the target driving control scheme is simulated for driving a fuel vehicle.

[0037] Preferably, a power adjustment module and a sound simulation module are constructed. The power adjustment module receives the torque adjustment signal from the target driving control scheme. This torque adjustment signal contains a precise target torque value and may include shift power interruption commands. The motor controller within the power adjustment module, such as a VCU or MCU, parses this signal and converts it into the current or voltage control commands required by the drive motor. Subsequently, through pulse width modulation (PWM) technology or other advanced control algorithms, the magnitude and phase of the current input to the drive motor are adjusted in real time and precisely, so that the output torque of the drive motor can strictly follow the current scheme, thereby simulating the linear torque rise and fall of a fuel vehicle. It can also create a torque zero or trough lasting 50-200ms during virtual shifts, accurately reproducing the shift shock feeling. The sound simulation module synchronously receives the sound control signal from the target driving control scheme. This sound control signal is a digital audio stream synthesized in real time by an algorithm and strictly matched with the current simulated engine operating conditions. The audio processor of the sound simulation module decodes and amplifies the signal. The in-car stereo system plays decoded and amplified sound waves into the cabin, creating an immersive auditory environment. Simultaneously, waterproof external speakers radiate sound waves outwards to reproduce the realistic sound field propagation effect of a gasoline-powered vehicle. The key to this module lies in its ultra-high real-time performance and synchronization. It ensures that the frequency, volume, and harmonic components of the sound waves change instantaneously with the simulated engine speed, and precisely inserts special effects such as "backfire" or "inhalation" during gear shifts. The overall latency is strictly controlled within 50ms, ensuring complete synchronization between auditory feedback, power response, and vehicle dynamics. Ultimately, under the unified scheduling of the central control module, the power adjustment module and the sound simulation module synchronously transform the digital target driving control scheme into the actual acceleration, push-back feeling, and jerking sensations of the engine roar and exhaust sounds. These, along with the suspension system and force feedback device, which also receive commands, work together to construct a multi-dimensional, high-fidelity gasoline-powered vehicle simulation driving experience covering auditory, tactile, and kinematic senses, achieving a seamless transition from data to perception.

[0038] In summary, the embodiments of this application have at least the following technical effects: First, a vehicle parameter library is constructed, containing power characteristic parameters, sound characteristic parameters, virtual gear parameters, shift power interruption duration, and suspension characteristic parameters for various types of gasoline vehicles. Then, real-time vehicle operation data is collected, including throttle opening, brake opening, vehicle speed, and motor speed. Next, based on the user-selected vehicle model, target vehicle parameters are retrieved from the parameter library. Using a power mapping algorithm and a sound synthesis algorithm, control parameters are analyzed from the vehicle operation data and target vehicle parameters to generate torque adjustment signals and sound control signals. Finally, suspension adjustment commands and haptic feedback commands are acquired. The torque adjustment signal, sound control signal, suspension adjustment commands, and haptic feedback commands are fused to generate a target driving control scheme, which is then used to simulate driving a gasoline vehicle. This solves the technical problem of existing automotive driving experiences being monotonous and unable to realistically reproduce the driving experience of various types of gasoline vehicles. By constructing and calling an expandable vehicle parameter library, multiple driving experience dimensions such as power, sound, suspension, and haptic feedback are deeply integrated, achieving the technical effect of improving driving realism and immersion, and optimizing the user experience.

[0039] Example 2 is based on the same inventive concept as the fuel vehicle simulation driving method based on the vehicle model parameter library in the previous examples, such as... Figure 2 As shown, this application provides a fuel vehicle simulation driving system based on a vehicle model parameter library. The system includes: a parameter library construction unit 11: constructing a vehicle model parameter library, which contains power characteristic parameters, sound characteristic parameters, virtual gear parameters, shift power interruption duration, and suspension characteristic parameters for multiple types of fuel vehicles; a data acquisition unit 12: acquiring vehicle operation data in real time, including throttle opening, brake opening, vehicle speed, and motor speed; a parameter parsing unit 13: calling target vehicle model parameters from the vehicle model parameter library according to the user-selected vehicle model, and performing control parameter parsing on the vehicle operation data and the target vehicle model parameters based on a power mapping algorithm and a sound synthesis algorithm to generate torque adjustment signals and sound control signals; and a simulation driving unit 14: acquiring suspension adjustment commands and haptic feedback commands, fusing the torque adjustment signal with the sound control signal, the suspension adjustment commands, and the haptic feedback commands to generate a target driving control scheme, and performing fuel vehicle simulation driving through the target driving control scheme.

[0040] Furthermore, the parameter library construction unit 11 is used to perform the following method: Raw sound wave data is collected through an anechoic chamber and a silent drum device; the raw sound wave data is classified and labeled according to the rotation speed information to obtain sound wave data of multiple rotation speed types; feature extraction is performed on the sound wave data of each type to obtain sound wave feature parameters, including fundamental frequency, harmonic distribution and attenuation characteristics.

[0041] Furthermore, the parameter parsing unit 13 is used to perform the following method: The power mapping algorithm employs a dual-input single-output model. This model is trained to construct a torque adjustment model. Based on this model, control parameters are analyzed using the throttle opening change rate and current vehicle speed from the vehicle operation data, as well as the virtual gear parameters from the target vehicle model parameters, to generate a torque adjustment signal. Finally, a sound wave control signal is generated using a sound wave synthesis algorithm to analyze the current vehicle speed, motor speed, and sound wave characteristic parameters from the target vehicle model parameters.

[0042] Furthermore, the parameter parsing unit 13 is used to perform the following method: The power mapping algorithm adopts a dual-input single-output model; the dual-input single-output model is trained for torque control to construct a torque adjustment model; combined with the virtual gear parameters of the target vehicle model parameters, the torque adjustment model is used to analyze the throttle opening change rate and current vehicle speed in the vehicle operation data to generate a torque adjustment signal.

[0043] Furthermore, the parameter parsing unit 13 is used to perform the following method: A real-world driving dataset is collected, which includes the rate of change of throttle opening under different virtual gear parameters for each vehicle model and the actual torque output data under different speed combinations. The real-world driving dataset is classified and labeled according to the virtual gear parameters for each vehicle model to obtain a torque control sample set. The dual-input single-output model is trained based on the torque control sample set to construct a torque regulation model.

[0044] Furthermore, the simulated driving unit 14 is used to perform the following methods: The suspension stiffness and height are adjusted in real time based on the suspension characteristic parameters of the target vehicle model, generating suspension adjustment commands; shift lever force feedback commands and seat vibration commands are obtained; and haptic feedback commands are generated based on the shift lever force feedback commands and seat vibration commands.

[0045] Furthermore, the simulated driving unit 14 is used to perform the following methods: The system simulates the power characteristics of a gasoline vehicle using virtual gear shifting logic, including gear shift interruption and torque decay. A micro motor generates a gear shift lever force feedback command based on these power characteristics. A vibration module installed in the driver's seat simulates engine vibration characteristics based on the torque adjustment signal, generating a seat vibration command.

[0046] Furthermore, the simulated driving unit 14 is used to perform the following methods: A power adjustment module and a sound simulation module are constructed; based on the power adjustment module and the sound simulation module, the target driving control scheme is simulated for driving a fuel vehicle.

[0047] Example 3: Based on the same inventive concept as the fuel vehicle simulation driving method based on the vehicle model parameter library in the previous examples, this application provides a medium storing a computer program. When the processor executes the computer program, it performs the following steps: constructing a vehicle model parameter library, which includes power characteristic parameters, sound characteristic parameters, virtual gear parameters, shift power interruption duration, and suspension characteristic parameters of various types of fuel vehicles; collecting vehicle operation data in real time, including throttle opening, brake opening, vehicle speed, and motor speed; calling target vehicle parameters from the vehicle model parameter library according to the user-selected vehicle model; performing control parameter parsing on the vehicle operation data and the target vehicle parameters based on a power mapping algorithm and a sound synthesis algorithm to generate torque adjustment signals and sound control signals; acquiring suspension adjustment commands and haptic feedback commands; fusing the torque adjustment signals and sound control signals, the suspension adjustment commands and haptic feedback commands to generate a target driving control scheme; and performing fuel vehicle simulation driving through the target driving control scheme.

[0048] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0049] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0050] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for simulating driving a gasoline-powered vehicle based on a vehicle model parameter library, characterized in that, The method includes: A vehicle parameter library is constructed, which includes power characteristic parameters, sound characteristic parameters, virtual gear parameters, shift power interruption duration and suspension characteristic parameters for various types of fuel vehicles. Real-time collection of vehicle operation data, including throttle opening, brake opening, vehicle speed, and motor speed; Based on the vehicle model selected by the user, the target vehicle model parameters are retrieved from the vehicle model parameter library. Based on the power mapping algorithm and the sound synthesis algorithm, the vehicle operation data and the target vehicle model parameters are analyzed to generate torque adjustment signals and sound control signals. The system acquires suspension adjustment commands and haptic feedback commands, fuses the torque adjustment signal with the sound control signal, the suspension adjustment commands and haptic feedback commands to generate a target driving control scheme, and performs simulated driving of a fuel vehicle using the target driving control scheme.

2. The method for simulating driving a fuel-powered vehicle based on a vehicle model parameter library as described in claim 1, characterized in that, The specific steps for obtaining acoustic wave characteristic parameters include: Raw sound wave data was collected using an anechoic chamber and a silent rotary drum device; The original sound wave data is classified and labeled according to the rotation speed information to obtain sound wave data of multiple rotation speed types; Feature extraction is performed on the multi-speed type sound wave data to obtain sound wave feature parameters, which include fundamental frequency, harmonic distribution and attenuation characteristics.

3. The method for simulating driving a gasoline-powered vehicle based on a vehicle model parameter library as described in claim 1, characterized in that, Generate torque adjustment signals and sound control signals, including: The power mapping algorithm adopts a dual-input single-output model, and the dual-input single-output model is trained to construct a torque regulation model. Based on the torque regulation model, the control parameters of the throttle opening change rate and current vehicle speed in the vehicle operation data, as well as the virtual gear parameters in the target vehicle model parameters, are analyzed to generate a torque regulation signal. Based on the sound wave synthesis algorithm, the current vehicle speed, motor speed and sound wave characteristic parameters in the vehicle operation data and the target vehicle model parameters are analyzed to generate a sound wave control signal.

4. The method for simulating driving a gasoline-powered vehicle based on a vehicle model parameter library as described in claim 3, characterized in that, Generate a torque adjustment signal, including: The dynamic mapping algorithm adopts a dual-input single-output model; The dual-input single-output model is trained for torque control to construct a torque regulation model; By combining the virtual gear parameters of the target vehicle model parameters, and based on the torque adjustment model, the throttle opening change rate and current vehicle speed in the vehicle operation data are analyzed to generate a torque adjustment signal.

5. The method for simulating driving a fuel-powered vehicle based on a vehicle model parameter library as described in claim 4, characterized in that, Constructing a torque regulation model includes: Collect a real-world driving dataset, which includes the rate of change of throttle opening under different virtual gear parameters for each vehicle model and the actual torque output data under vehicle speed combinations. The actual driving dataset is classified and labeled according to the virtual gear parameters of each vehicle model to obtain the torque control sample set; Based on the torque control sample set, the dual-input single-output model is trained to construct a torque regulation model.

6. The method for simulating driving a gasoline-powered vehicle based on a vehicle model parameter library as described in claim 1, characterized in that, Obtain suspension adjustment commands and haptic feedback commands, including: The suspension stiffness and height are adjusted in real time based on the suspension characteristic parameters of the target vehicle model, and suspension adjustment commands are generated. Obtain shift lever force feedback commands and seat vibration commands; Based on the shift lever force feedback command and the seat vibration command, a haptic feedback command is generated.

7. The method for simulating driving a fuel-powered vehicle based on a vehicle model parameter library as described in claim 6, characterized in that, Obtain shift lever force feedback commands and seat vibration commands, including: The power characteristics of a gasoline vehicle are simulated according to virtual gear logic, including gear shift interruption and torque decay. Based on the power characteristics of the fuel vehicle, a micro motor generates a shift lever force feedback command. A vibration module is installed inside the driver's seat to simulate engine vibration characteristics based on the torque adjustment signal, and generate seat vibration commands.

8. The method for simulating driving a gasoline-powered vehicle based on a vehicle model parameter library as described in claim 1, characterized in that, Simulated driving of a fuel-powered vehicle using the target driving control scheme includes: Construct a power adjustment module and a sound simulation module; Based on the power adjustment module and the sound simulation module, the target driving control scheme is simulated for driving a fuel vehicle.

9. A fuel-powered vehicle simulation driving system based on a vehicle model parameter library, characterized in that, The system is used to implement the fuel vehicle simulation driving method based on a vehicle model parameter library as described in any one of claims 1-8, the system comprising: Parameter library construction unit: Constructs a vehicle parameter library, which includes power characteristic parameters, sound characteristic parameters, virtual gear parameters, shift power interruption duration and suspension characteristic parameters for various types of fuel vehicles; Data acquisition unit: collects vehicle operation data in real time, including throttle opening, brake opening, vehicle speed and motor speed; Parameter parsing unit: Based on the vehicle model selected by the user, it retrieves the target vehicle model parameters from the vehicle model parameter library, and performs control parameter parsing on the vehicle operation data and the target vehicle model parameters based on the power mapping algorithm and the sound synthesis algorithm to generate torque adjustment signal and sound control signal; Simulation driving unit: acquires suspension adjustment commands and haptic feedback commands, fuses the torque adjustment signal with the sound control signal, the suspension adjustment commands and haptic feedback commands to generate a target driving control scheme, and performs simulated driving of a fuel vehicle through the target driving control scheme.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the fuel vehicle simulation driving method based on the vehicle model parameter library as described in any one of claims 1-8.

Images