Tire pressure adjusting method, equipment, system, storage medium, product and vehicle

Abstract

The invention provides a tire pressure adjusting method, device and system, a storage medium, a product and a vehicle, and belongs to the technical field of vehicle control. The method comprises the following steps: determining a current composite working condition of a vehicle according to multi-modal data of the vehicle, wherein the multi-modal data comprises more of topographic data, vehicle state data and driving operation data; and adjusting the tire pressure of the vehicle according to the current composite working condition. The invention aims to improve the efficiency of adjusting the tire pressure of the vehicle.

Description

Technical Field

[0001] This application relates to the technical field of vehicle control, and more specifically, to a tire pressure regulation method, device, system, storage medium, product, and vehicle. Background Technology

[0002] With the rapid development of automotive technology, users' needs for vehicles in different driving scenarios are becoming more and more diverse. As a key factor affecting driving safety, vehicle performance and tire life, the tire pressure requirements are also different under different driving conditions.

[0003] Currently, tire pressure adjustment for vehicles is still mainly done manually. For example, in sand mode, it is often necessary to manually adjust the tire pressure based on experience. Moreover, when the vehicle exits sand mode, it is also necessary to manually restore the tire pressure. This makes tire pressure adjustment inefficient and greatly reduces the user experience. Summary of the Invention

[0004] This application provides a tire pressure regulation method, device, system, storage medium, product, and vehicle, aiming to improve the efficiency of regulating vehicle tire pressure.

[0005] In a first aspect, embodiments of this application provide a tire pressure regulation method, the method comprising: The current composite operating condition of the vehicle is determined based on the vehicle's multimodal data, which includes multiple of the following: terrain data, vehicle status data, and driving operation data. Adjust the vehicle's tire pressure according to the current combined operating conditions.

[0006] Optionally, the terrain data includes at least one of road surface visual data, tire ground pressure data, vibration data, and road noise data.

[0007] Optionally, the vehicle status data includes at least one of vehicle speed, acceleration, and attitude data.

[0008] Optionally, the driving operation data includes at least one of steering wheel angle data, accelerator pedal data, and brake pedal data.

[0009] Optionally, the current composite operating condition of the vehicle is determined based on the vehicle's multimodal data, including: The multimodal data is input into the composite working condition identification model; The current composite operating condition of the vehicle is determined by the composite operating condition recognition model. The current composite operating condition is used to characterize the driving condition of the vehicle on any road surface under the current driving intention. The composite working condition identification model is trained based on multiple first training samples, which include multimodal sample data and composite working condition labels.

[0010] Optionally, adjusting the tire pressure of the vehicle according to the current combined operating conditions includes: Based on the current combined operating conditions, determine the target tire pressure values ​​for the vehicle's wheels; The tire pressure of the wheel is adjusted according to the target tire pressure value and the current tire pressure value.

[0011] Optionally, determining the target tire pressure values ​​for the vehicle's wheels based on the current combined operating conditions includes: Input the current combined operating condition into the dynamic optimization model; The target tire pressure value corresponding to the wheel is determined by the dynamic optimization model. The dynamic optimization model is obtained by training multiple second training samples, which include composite working condition samples and tire pressure label values ​​of the wheels.

[0012] Optionally, the method further includes: The first tire pressure prediction model predicts the current tire pressure value of the wheel based on the historical tire pressure data of the wheel. The first tire pressure prediction model is trained based on multiple third training samples, which include tire pressure sample data and tire pressure labels. Alternatively, the current tire pressure value of the wheel can be predicted using a second tire pressure prediction model based on the wheel's historical tire pressure data and target information. The second tire pressure prediction model is trained using multiple fourth training samples, which include tire pressure sample data, target information sample data, and tire pressure labels. The target information includes at least one of the following: road surface type, vehicle load information, and driving mode.

[0013] Optionally, adjusting the tire pressure of the wheel based on the target tire pressure value and the current tire pressure value includes: Based on the target tire pressure value and the current tire pressure value corresponding to the wheel, a tire pressure control command is generated through a PID algorithm. The tire pressure control command is used to control the vehicle's tire pressure regulating device to adjust the tire pressure of the wheel. The tire pressure control command includes air source parameters and control parameters of the wheel's inflation / deflation valve.

[0014] Secondly, embodiments of this application provide an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the tire pressure regulation method as described in the first aspect of the embodiments.

[0015] Thirdly, embodiments of this application provide a tire pressure regulation system, the system including the electronic equipment described in the second aspect of the embodiments and a tire pressure regulation device for regulating the tire pressure of a vehicle.

[0016] Optionally, the tire pressure regulating device includes a gas generator, an inflation / deflation valve group, and wheel-side mechanisms corresponding to each wheel; The gas generator, the inflation / deflation valve group, and the wheel-side mechanism of each wheel are connected by air pipes. The wheel-side mechanism of each wheel includes an air pipe connected to the tire valve to form an inflation / deflation circuit for each wheel.

[0017] Fourthly, embodiments of this application provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the tire pressure regulation method as described in the first aspect of the embodiments.

[0018] Fifthly, embodiments of this application provide a computer program product, including a computer program / instructions, which, when executed by a processor, implement the tire pressure regulation method described in the first aspect of the embodiments.

[0019] Sixthly, embodiments of this application provide a vehicle for performing the tire pressure regulation method described in the first aspect of the embodiment, or including the electronic equipment described in the second aspect of the embodiment, or including the tire pressure regulation system described in the third aspect of the embodiment.

[0020] Beneficial effects: The tire pressure regulation method provided in this application embodiment acquires multimodal data of the vehicle, including terrain data, vehicle status data, and driving operation data; identifies the current combined operating condition of the vehicle based on the multimodal data, and then adjusts the tire pressure of the vehicle according to the current combined operating condition. This allows for dynamic adjustment of the vehicle's tire pressure based on the current combined operating condition, which can improve the efficiency of tire pressure regulation compared to manual tire pressure adjustment. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the steps of a tire pressure regulation method according to an embodiment of this application; Figure 2 This is a schematic diagram of an electronic device according to an embodiment of this application; Figure 3 This is a schematic diagram of the architecture of a tire pressure regulation system provided in one embodiment of this application; Figure 4 This is a schematic diagram of the tire pressure regulation system proposed in one embodiment of this application; Figure 5 This is a functional block diagram of a tire pressure regulating device according to an embodiment of this application; Figure 6 This is a schematic diagram of a readable storage medium provided in an embodiment of this application; Figure 7 This is a schematic diagram of a computer program product proposed in an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0025] ADAS: Advanced Driver Assistance System; VCU: Vehicle Control Unit; Vehicle controller; IMU: Inertial Measurement Unit; PID stands for Proportional-Integral-Dervivate.

[0026] With the rapid development of automotive technology, users' needs for vehicles in different driving scenarios are becoming more and more diverse. Tire pressure is a key factor affecting driving safety, vehicle performance and tire life, and the required tire pressure varies under different driving conditions.

[0027] For example, cars can now offer users a variety of driving modes for different road conditions, such as mud mode, snow mode, and sand mode, providing users with a more intelligent car experience. In sand mode, users often need to manually adjust the tire pressure based on experience, and when the vehicle exits sand mode, users also need to manually restore the tire pressure, making tire pressure adjustment inefficient and greatly reducing the user experience.

[0028] Traditional tire pressure regulation systems typically rely on manual operation or simple sensor feedback, which cannot dynamically and adaptively adjust according to the vehicle's operating conditions in real time. This results in low tire pressure regulation efficiency and potential safety hazards. Therefore, this application provides a tire pressure regulation method that can improve the efficiency of regulating vehicle tire pressure.

[0029] The tire pressure regulation method provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0030] Reference Figure 1 The diagram illustrates the steps of a tire pressure regulation method provided in this application embodiment. The method specifically includes the following steps: S101: Determine the current composite operating condition of the vehicle based on the vehicle's multimodal data, wherein the multimodal data includes multiple of terrain data, vehicle status data, and driving operation data.

[0031] Specifically, the content of multimodal data can be selected according to the needs of actual applications. For example, the current composite operating condition of a vehicle can be determined based on terrain data and driving operation data, or it can be determined based on terrain data, vehicle status data, and driving operation data at the same time.

[0032] In practice, multi-source sensors on the vehicle can be used to collect multimodal data in real time during the vehicle's driving process.

[0033] Specifically, the terrain data includes at least one of road surface visual data, tire contact pressure data, vibration data, and road noise data. For example, road surface visual data of the road surface on which the vehicle is currently traveling can be collected by a camera on the vehicle. The road surface visual data is used to reflect the visual characteristics of the road surface, such as texture, color, and shape. Tire contact pressure data can be detected by setting pressure sensors on the wheels. Vibration data such as vibration intensity and vibration frequency of the vehicle when traveling on different road surfaces can be sensed by vibration sensors deployed on the vehicle. Road noise data of the vehicle when traveling on different road surfaces can be captured by setting microphones on the vehicle.

[0034] To improve the accuracy of road surface recognition, road surface visual data, tire ground pressure data, vibration data, and road noise data can be acquired simultaneously as terrain data.

[0035] Specifically, the vehicle status data includes at least one of vehicle speed, acceleration, and attitude data. For example, attitude data includes, but is not limited to, vehicle attitude angles and suspension height. In actual implementation, vehicle speed, acceleration, and attitude angles can be sensed and obtained through onboard IMU and wheel speed sensors. The attitude angles include at least one of roll angle, pitch angle, and yaw angle. Roll angle can characterize the vehicle's roll angle, and pitch angle can characterize the vehicle's tilt angle when going uphill or downhill. To more comprehensively reflect the vehicle's driving state, the vehicle status data can simultaneously include vehicle speed, acceleration, and attitude data.

[0036] Specifically, the driving operation data includes at least one of steering wheel angle data, accelerator pedal data, and brake pedal data. For example, steering wheel angle data can be obtained through a steering wheel angle sensor; accelerator pedal data can be obtained through an accelerator pedal position sensor; and brake pedal data can be obtained through a brake pedal position sensor.

[0037] This application embodiment uses multimodal data to identify the current composite operating condition of a vehicle, which is used to characterize the driving condition of the vehicle on any road surface under the current driving intention.

[0038] In one feasible implementation, a machine deep learning algorithm can be applied to train a composite operating condition recognition model. The multimodal data is then input into the composite operating condition recognition model, and the current composite operating condition of the vehicle is determined through the composite operating condition recognition model.

[0039] In practical implementation, a composite working condition recognition model can be constructed based on convolutional neural networks and recurrent neural networks. The composite working condition recognition model is a classification model. Then, the composite working condition recognition model is trained. The composite working condition recognition model is obtained by training multiple first training samples, which include multimodal sample data and composite working condition labels.

[0040] In practical applications, if the multimodal sample data includes terrain data and driving operation data, then the multimodal sample data also includes terrain sample data and driving operation sample data. If the multimodal sample data includes terrain data, vehicle status data, and driving operation data, then the multimodal sample data also includes terrain sample data, vehicle status sample data, and driving operation sample data.

[0041] In practical applications, after acquiring multimodal data, data preprocessing can be performed on the multimodal data to obtain fused feature vectors as input to the composite working condition recognition model.

[0042] The data preprocessing process includes data cleaning, noise filtering, and data alignment.

[0043] During the data cleaning process, a normal range is preset for each type of data. If the collected data of a certain type exceeds the normal range, the erroneous data is removed. Alternatively, a change threshold can be preset for each type of data. If the change between the currently collected data of that type and the previous data exceeds the change threshold, the erroneous data is removed. Other erroneous data cleaning methods can also be used according to the needs of actual applications. This application embodiment does not impose any restrictions.

[0044] During the noise filtering process, the noise in the data collected by the sensor can be reduced by using preset filtering techniques. The filtering techniques can be set according to the needs of the actual application, and this application embodiment does not impose any restrictions.

[0045] During the data alignment process, considering that multimodal data needs to be acquired from multiple different sensors to form multimodal data, and that different sensors have different data acquisition frequencies, a target frequency can be preset. Then, data acquired by sensors with frequencies higher than the target frequency is sampled, and data acquired by sensors with frequencies lower than the target frequency is interpolated. This ensures that the data acquired by different sensors are synchronized in time, so as to facilitate subsequent data fusion.

[0046] After data preprocessing, the multimodal data are fused to obtain a fused feature vector. Data fusion can be performed using methods such as weighted averaging, feature concatenation, and deep learning models to generate fused feature vectors. This application does not impose any restrictions on the methods used.

[0047] For example, multi-dimensional feature vectors are extracted for each type of data. The feature vectors of all data have the same dimension. The dimension of the feature vectors can be defined according to the needs of actual applications. This application does not impose any restrictions.

[0048] In the weighted average method, corresponding weights can be set for different types of data according to the needs of actual applications. The fusion feature vector of multimodal data can be obtained by weighted averaging.

[0049] In the feature concatenation method, the feature vectors of all data are concatenated according to a preset order to obtain the fused feature vector of multimodal data.

[0050] In the process of obtaining the fused feature vector of multimodal data through a deep learning model, the feature vectors of all data can be input into the deep learning model, and the fused feature vector can be extracted through the deep learning model.

[0051] Finally, the fused feature vector of the obtained multimodal data is input into the composite working condition identification model. The composite working condition identification model is based on the fused feature vector. Since the composite working condition identification model is a classification model, it can output the current composite working condition through the fused feature vector.

[0052] For example, the composite driving condition includes road surface type and driving information representing the driver's current driving intention. Road surface type includes sand, snow, water accumulation, and paved surfaces; driving information representing the driver's current driving intention includes, but is not limited to: high speed, medium speed, low speed, acceleration, deceleration, braking, straight driving, left turn, right turn, uphill, and downhill.

[0053] For example, in compound driving condition 1, the vehicle travels straight at high speed on sandy terrain, and in compound driving condition 2, the vehicle accelerates and turns left on sandy terrain.

[0054] The embodiments of this application identify the current complex operating conditions of a vehicle based on multimodal data and a complex operating condition identification model. This not only allows for a more accurate and detailed determination of the vehicle's operating conditions based on multimodal data, but also improves the efficiency of identifying complex operating conditions.

[0055] In actual implementation, in addition to determining the current composite operating condition of the vehicle through the composite operating condition identification model, the current composite operating condition of the vehicle can also be determined by pre-calibrating the range of multimodal data under different composite operating conditions and matching and comparing the acquired multimodal data with the range of multimodal data.

[0056] Other methods for determining the current composite operating condition of a vehicle based on multimodal data can also be selected according to the needs of actual applications, and the embodiments of this application do not impose any restrictions.

[0057] S102: Adjust the tire pressure of the vehicle according to the current combined operating conditions.

[0058] In actual implementation, the tire pressure of the vehicle can be adjusted in real time according to the current combined working conditions, and the tire pressure of the four wheels of the vehicle can also be adjusted consistently based on the current combined working conditions.

[0059] To improve tire pressure regulation to better adapt to vehicle driving conditions and enhance vehicle performance, the tire pressure of each wheel of the vehicle can be adjusted in real time according to the current combined driving conditions.

[0060] In one feasible implementation, adjusting the vehicle's tire pressure according to the current combined operating conditions may specifically include the following steps: A1: Determine the target tire pressure value corresponding to the wheel based on the current combined working conditions.

[0061] In practice, machine deep learning algorithms can be applied to train a dynamic optimization model. This model can then be used to evaluate the tire pressure requirements of a vehicle under current combined operating conditions, ensuring the optimal match between tire-ground contact area, grip, and driving stability.

[0062] Specifically, the current combined operating condition is input into the dynamic optimization model; the target tire pressure value corresponding to each wheel of the vehicle is determined through the dynamic optimization model.

[0063] The dynamic optimization model is trained using multiple second training samples, which include composite working condition samples and tire pressure label values ​​of the wheels. By training the dynamic optimization model with multiple second training samples, the dynamic optimization model can identify the mapping relationship between different composite working conditions and the tire pressure values ​​of each vehicle. Then, the dynamic optimization model can more efficiently determine the target tire pressure value corresponding to each wheel under the current composite working condition.

[0064] A2: Adjust the tire pressure of the wheel according to the target tire pressure value and the current tire pressure value corresponding to the wheel.

[0065] Specifically, the current tire pressure value of each wheel can be obtained from the tire pressure sensor. However, considering the time delay of the tire pressure sensor, in order to reduce the lag of the tire pressure sensor data and improve the efficiency of tire pressure regulation, this application embodiment also provides a method for predicting the current tire pressure value of the wheel.

[0066] Specifically, the current tire pressure value of the wheel can be predicted by the first tire pressure prediction model based on the historical tire pressure data of the wheel. The first tire pressure prediction model is trained based on multiple third training samples, which include tire pressure sample data and tire pressure labels.

[0067] Alternatively, a second tire pressure prediction model can be used to predict the current tire pressure value of the wheel based on the wheel's historical tire pressure data and target information. The second tire pressure prediction model is trained based on multiple fourth training samples, which include tire pressure sample data, target information sample data, and tire pressure labels. The target information includes at least one of road surface type, vehicle load information, and driving mode. By combining the wheel's historical tire pressure data with road surface type, vehicle load information, and driving mode, the current tire pressure value of each wheel can be predicted more accurately.

[0068] After the tire pressure sensor obtains the actual tire pressure value of each tire, the actual tire pressure value of each wheel can be used as the historical tire pressure data of that wheel to calibrate and optimize the first tire pressure prediction model or the second tire pressure prediction model.

[0069] In actual implementation, during the process of adjusting the tire pressure of the wheel according to the target tire pressure value and the current tire pressure value, a tire pressure control command can be generated by using a PID algorithm based on the target tire pressure value and the current tire pressure value. The tire pressure control command is used to control the vehicle's tire pressure regulating device to adjust the tire pressure of each wheel. The tire pressure control command includes air source parameters and control parameters of the wheel's inflation / deflation valve.

[0070] When adjusting tire pressure based on the PID algorithm, the tire pressure of each wheel can be adjusted based on the deviation between the target tire pressure value and the current tire pressure value corresponding to each wheel. In actual implementation, other algorithms can also be used to adjust tire pressure, and this application embodiment does not impose any restrictions.

[0071] In actual implementation, the tire pressure regulating device can inflate and deflate each wheel in real time during vehicle operation to achieve tire pressure regulation. The tire pressure regulating device can be selected according to the actual application requirements, and the embodiments of this application do not impose any restrictions.

[0072] For example, the tire pressure regulating device may include a gas generator, an inflation / deflation valve assembly, and wheel-side mechanisms corresponding to each wheel. The inflation / deflation valve assembly includes inflation / deflation valves for each wheel. The gas generator may use an air pump as the gas source, or it may be a multi-gas combined gas source. The wheel-side mechanisms installed on each wheel can be connected to the tire valve during wheel rotation. The gas generator, the inflation / deflation valve assembly, and the wheel-side mechanisms of each wheel are connected by air pipes to form an inflation / deflation circuit for each wheel, so that the tire pressure of the wheels can be regulated even while the vehicle is in motion.

[0073] The gas source parameters include the operating parameters of the gas generator, including but not limited to the target air pressure value. For example, in the scenario of increasing the tire pressure of a vehicle, the gas source parameters include the target air pressure value of the gas generator as X1; in the scenario of decreasing the tire pressure of a vehicle, the gas source parameters include the target air pressure value of the gas generator as X2.

[0074] The control parameters of the inflation / deflation valves for each wheel include, but are not limited to, the valve opening. For example, in a scenario where the tire pressure of all four wheels of a vehicle needs to be increased, the target tire pressure values ​​for each tire are different. The tire pressure of each wheel can be adjusted by adjusting the valve opening of the inflation / deflation valve corresponding to each wheel.

[0075] In actual implementation, the adjustment effect can be monitored in real time. This is achieved by using tire pressure sensors to monitor the actual tire pressure of each wheel in real time, ensuring the accuracy and stability of the adjustment. During implementation, PID algorithm feedback control can be performed based on the actual tire pressure of each wheel for further optimization and adjustment. Real-time monitoring of the actual tire pressure of each wheel can also help to promptly identify and address inaccurate adjustments, thereby improving the reliability of the system.

[0076] This method uses multimodal data to more accurately and meticulously identify the current combined operating conditions of a vehicle, and then adjusts the tire pressure of the vehicle according to the current combined operating conditions. It can also adjust the tire pressure of each wheel of the vehicle separately. Compared with the manual tire pressure adjustment method, it can not only improve the accuracy of tire pressure adjustment, but also make the tire pressure more suitable for the vehicle's operating conditions, thereby improving the vehicle's driving performance and safety.

[0077] In practical implementation, in addition to determining the current composite working condition based on multimodal data through a trained composite working condition recognition model and then determining the target tire pressure value of the wheel based on the current composite working condition through a trained dynamic optimization model, it is also possible to determine the target tire pressure value of the wheel based on multimodal data using a single model, thereby achieving end-to-end tire pressure prediction. For example, the target tire pressure value of the wheel can be determined based on multimodal data using a pre-trained AI large model. This application does not impose any limitations on this embodiment.

[0078] Reference Figure 2 The diagram illustrates an electronic device provided in an embodiment of this application. The electronic device includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the various processes of the tire pressure regulation method embodiment described above and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0079] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0080] Reference Figure 3 The diagram shows a schematic of the architecture of a tire pressure regulation system provided in an embodiment of this application. The system includes the electronic equipment and tire pressure regulation device described in the embodiment of this application.

[0081] Specifically, the electronic device is used to determine the current combined operating condition of the vehicle based on the vehicle's multimodal data, which includes multiple of terrain data, vehicle status data, and driving operation data; and to adjust the tire pressure of the vehicle based on the current combined operating condition.

[0082] The tire pressure regulating device is used to regulate the tire pressure of the vehicle.

[0083] In one feasible implementation, the tire pressure regulating device includes a gas generator, an inflation / deflation valve assembly, and wheel-side mechanisms corresponding to each wheel.

[0084] The gas generator can use an air pump as the gas source, or it can choose a gas source that combines multiple gases.

[0085] The inflation and deflation valves of each wheel are modularly integrated into an inflation and deflation valve assembly. The inflation and deflation valve assembly includes an inflation function valve assembly and a deflation function valve assembly. Each inflation function valve assembly and the deflation function valve assembly consists of four air valves. By modularly integrating the inflation and deflation valve assembly, the overall volume of the tire pressure regulating device can be reduced.

[0086] Each wheel of the vehicle can be equipped with a wheel-side mechanism. The gas generator, the inflation / deflation valve group, and the wheel-side mechanism of each wheel are connected by air pipes to form an inflation / deflation circuit for each wheel. The wheel-side mechanism can remain connected to the tire valve of the wheel during wheel rotation, so that the tire pressure of the wheel can be adjusted during vehicle operation.

[0087] Reference Figure 4 The diagram shows a structural schematic of a tire pressure regulation system provided in an embodiment of this application. The tire pressure regulation system may include the operating condition identification module, the tire pressure control module, and the tire pressure regulation device.

[0088] The operating condition identification module is used to determine the current composite operating condition of the vehicle based on the vehicle's multimodal data, which includes multiple of the following: terrain data, vehicle status data, and driving operation data.

[0089] The tire pressure control module is used to adjust the tire pressure of the vehicle according to the current combined operating conditions.

[0090] The tire pressure regulating device is used to regulate the tire pressure of the vehicle.

[0091] The operating condition identification module can be integrated into the ADAS domain controller, the tire pressure control module can be integrated into the vehicle's VCU, and the four wheel-side mechanisms of the tire pressure adjustment device are respectively located at the four wheels of the vehicle.

[0092] After acquiring multimodal data, such as terrain data, vehicle status data, and driving operation data, the condition recognition module integrated in ADAS domain control performs data preprocessing, fuses the multimodal data to obtain a fused feature vector, and then inputs the fused feature vector into the composite condition recognition model. The composite condition recognition model determines the current composite condition and sends it to the tire pressure control module integrated in VCU.

[0093] The tire pressure control module is used to input the current combined working condition into the dynamic optimization model to determine the target tire pressure value corresponding to each wheel; and to obtain the current tire pressure value corresponding to each wheel through the first tire pressure prediction model or the second tire pressure prediction model; then, based on the target tire pressure value and the current tire pressure value, a tire pressure control command is generated by the PID algorithm and sent to the tire pressure regulating device. The tire pressure control command includes air source parameters and control parameters of the inflation and deflation valves of each wheel.

[0094] The tire pressure regulating device controls the gas generator to increase or decrease the air pressure in the air circuit according to the air source parameters in the tire pressure control command, and adjusts the valve opening of the inflation / deflation valve of each wheel according to the control parameters of the inflation / deflation valve of each wheel, thereby realizing the tire pressure regulation of each wheel.

[0095] Reference Figure 5 The diagram illustrates a functional block diagram of a tire pressure regulating device according to an embodiment of this application. The device includes: The identification module 100 is used to determine the current composite operating condition of the vehicle based on the vehicle's multimodal data, wherein the multimodal data includes multiple of terrain data, vehicle status data, and driving operation data. The adjustment module 200 is used to adjust the tire pressure of the vehicle according to the current combined operating conditions.

[0096] Optionally, the terrain data includes at least one of road surface visual data, tire ground pressure data, vibration data, and road noise data.

[0097] Optionally, the vehicle status data includes at least one of vehicle speed, acceleration, and attitude data.

[0098] Optionally, the driving operation data includes at least one of steering wheel angle data, accelerator pedal data, and brake pedal data.

[0099] Optionally, the identification module is used for: The multimodal data is input into the composite working condition identification model; The current composite operating condition of the vehicle is determined by the composite operating condition recognition model. The current composite operating condition is used to characterize the driving condition of the vehicle on any road surface under the current driving intention. The composite working condition identification model is trained based on multiple first training samples, which include multimodal sample data and composite working condition labels.

[0100] Optionally, the adjustment module includes: The target tire pressure value determination unit is used to determine the target tire pressure value of the vehicle's wheels based on the current combined operating conditions. The adjustment subunit is used to adjust the tire pressure of the wheel according to the target tire pressure value and the current tire pressure value.

[0101] Optionally, the target tire pressure value determining unit is used for: Input the current combined operating condition into the dynamic optimization model; The target tire pressure value corresponding to the wheel is determined by the dynamic optimization model. The dynamic optimization model is obtained by training multiple second training samples, which include composite working condition samples and tire pressure label values ​​of the wheels.

[0102] Optionally, the device further includes a current tire pressure prediction module, used for: The first tire pressure prediction model predicts the current tire pressure value of the wheel based on the historical tire pressure data of the wheel. The first tire pressure prediction model is trained based on multiple third training samples, which include tire pressure sample data and tire pressure labels. Alternatively, the current tire pressure value of the wheel can be predicted using a second tire pressure prediction model based on the wheel's historical tire pressure data and target information. The second tire pressure prediction model is trained using multiple fourth training samples, which include tire pressure sample data, target information sample data, and tire pressure labels. The target information includes at least one of the following: road surface type, vehicle load information, and driving mode.

[0103] Optionally, the adjustment subunit is configured to include: Based on the target tire pressure value and the current tire pressure value corresponding to the wheel, a tire pressure control command is generated through a PID algorithm. The tire pressure control command is used to control the vehicle's tire pressure regulating device to adjust the tire pressure of the wheel. The tire pressure control command includes air source parameters and control parameters of the wheel's inflation / deflation valve.

[0104] The tire pressure regulating device in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal; the device can be a mobile electronic device or a non-mobile electronic device; this application embodiment does not make specific limitations.

[0105] One tire pressure regulating device in this application embodiment can be a device with an operating system. The operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit the specific operating system.

[0106] Reference Figure 6 The diagram illustrates a readable storage medium provided in an embodiment of this application. The readable storage medium stores a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the tire pressure regulation method embodiment described above and achieve the same technical effect. To avoid repetition, the details will not be repeated here.

[0107] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0108] Reference Figure 7 The diagram illustrates a computer program product provided in an embodiment of this application, including a computer program / instruction. When the computer program / instruction is executed by a processor, it implements the various processes of the tire pressure regulation method embodiment described above and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0109] This application also provides a vehicle for performing the various processes of the above-described tire pressure regulation method embodiments, or including the tire pressure regulation system described in this application embodiment, or including the tire pressure regulation device provided in this application embodiment, or including the electronic equipment described in this application embodiment, and achieving the same technical effect. To avoid repetition, it will not be described again here.

[0110] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0111] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0112] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. The description of the embodiments above is only for the purpose of helping to understand the method and core idea of ​​this application. Those skilled in the art can make many forms under the guidance of this application without departing from the spirit and scope of protection of the claims, and all of these are within the protection scope of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for regulating tire pressure, characterized in that, The method includes: The current composite operating condition of the vehicle is determined based on the vehicle's multimodal data, which includes multiple of the following: terrain data, vehicle status data, and driving operation data. Adjust the vehicle's tire pressure according to the current combined operating conditions.

2. The method according to claim 1, characterized in that, The terrain data includes at least one of the following: road surface visual data, tire ground pressure data, vibration data, and road noise data.

3. The method according to claim 1, characterized in that, The vehicle status data includes at least one of vehicle speed, acceleration, and attitude data.

4. The method according to claim 1, characterized in that, The driving operation data includes at least one of the following: steering wheel angle data, accelerator pedal data, and brake pedal data.

5. The method according to any one of claims 1-4, characterized in that, Determining the current combined operating condition of the vehicle based on its multimodal data includes: The multimodal data is input into the composite working condition identification model; The current composite operating condition of the vehicle is determined by the composite operating condition recognition model. The current composite operating condition is used to characterize the driving condition of the vehicle on any road surface under the current driving intention. The composite working condition identification model is trained based on multiple first training samples, which include multimodal sample data and composite working condition labels.

6. The method according to claim 1, characterized in that, Adjusting the vehicle's tire pressure according to the current combined operating conditions includes: Based on the current combined operating conditions, determine the target tire pressure values ​​for the vehicle's wheels; The tire pressure of the wheel is adjusted according to the target tire pressure value and the current tire pressure value.

7. The method according to claim 6, characterized in that, Based on the current combined operating conditions, determine the target tire pressure values ​​for the vehicle's wheels, including: Input the current combined operating condition into the dynamic optimization model; The target tire pressure value corresponding to the wheel is determined by the dynamic optimization model. The dynamic optimization model is obtained by training multiple second training samples, which include composite working condition samples and tire pressure label values ​​of the wheels.

8. The method according to claim 6, characterized in that, The method further includes: The first tire pressure prediction model predicts the current tire pressure value of the wheel based on the historical tire pressure data of the wheel. The first tire pressure prediction model is trained based on multiple third training samples, which include tire pressure sample data and tire pressure labels. Alternatively, the current tire pressure value of the wheel can be predicted using a second tire pressure prediction model based on the wheel's historical tire pressure data and target information. The second tire pressure prediction model is trained using multiple fourth training samples, which include tire pressure sample data, target information sample data, and tire pressure labels. The target information includes at least one of the following: road surface type, vehicle load information, and driving mode.

9. The method according to any one of claims 6-8, characterized in that, Adjusting the tire pressure of the wheel based on the target tire pressure value and the current tire pressure value includes: Based on the target tire pressure value and the current tire pressure value corresponding to the wheel, a tire pressure control command is generated through a PID algorithm. The tire pressure control command is used to control the vehicle's tire pressure regulating device to adjust the tire pressure of the wheel. The tire pressure control command includes air source parameters and control parameters of the wheel's inflation / deflation valve.

10. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the tire pressure regulation method as described in any one of claims 1-9.

11. A tire pressure regulation system, characterized in that, The system includes the electronic device of claim 10 and a tire pressure regulating device for regulating the tire pressure of a vehicle.

12. The system according to claim 11, characterized in that, The tire pressure regulating device includes a gas generator, an inflation / deflation valve group, and wheel-side mechanisms corresponding to each wheel. The gas generator, the inflation / deflation valve group, and the wheel-side mechanism of each wheel are connected by air pipes. The wheel-side mechanism of each wheel includes an air pipe connected to the tire valve to form an inflation / deflation circuit for each wheel.

13. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the tire pressure regulation method as described in any one of claims 1-9.

14. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the tire pressure regulation method according to any one of claims 1-9.

15. A vehicle, characterized in that, The vehicle is used to perform the tire pressure regulation method according to any one of claims 1-9, or includes the electronic device according to claim 10, or includes the tire pressure regulation system according to any one of claims 11-12.

Images