Vehicle control method and device, vehicle, chip and storage medium

Abstract

The invention provides a vehicle control method and device, a vehicle, a chip and a storage medium, and relates to the field of vehicles, and the method comprises the steps: obtaining the working condition information of the vehicle and the road condition information of a vehicle driving road; determining an air leakage detection result of the air suspension system according to the working condition information, the road condition information and the influence degree on the operation parameters of at least one component in the air suspension system of the vehicle; wherein the air leakage detection result is used for indicating a target air leakage position and / or a target air leakage type in the at least one component. Therefore, parameter fluctuation caused by normal working conditions / road conditions and abnormal attenuation caused by real chronic air leakage can be effectively distinguished, so that the positions and types of progressive and non-abrupt air leakage faults are accurately recognized, the detection rate and diagnosis accuracy of early faults are remarkably improved, and the requirement of the intelligent chassis for high-robustness health monitoring is met.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more particularly to a vehicle control method, device, vehicle, chip, and storage medium. Background Technology

[0002] An air suspension system is a vehicle suspension system that uses compressed air as the elastic element to replace traditional metal springs (such as coil springs or leaf springs). It dynamically controls vehicle height, suspension stiffness, and damping characteristics by adjusting the air pressure in the air spring airbag, thereby improving the vehicle's ride smoothness, handling stability, and ride comfort. Summary of the Invention

[0003] This application proposes a vehicle control method, apparatus, vehicle, chip, and storage medium to at least partially solve one of the technical problems in the related art.

[0004] One embodiment of this application proposes a vehicle control method, including: acquiring the vehicle's operating condition information and the road condition information of the road on which the vehicle travels; determining the air leakage detection result of the air suspension system based on the degree of influence of the operating parameters of at least one component in the vehicle's air suspension system according to the operating condition information and the road condition information; wherein the air leakage detection result is used to indicate the target air leakage location and / or target air leakage type in the at least one component.

[0005] Another embodiment of this application proposes a vehicle control device, including: an acquisition module for acquiring the vehicle's operating condition information and the road condition information of the road on which the vehicle travels; and a determination module for determining the air suspension system's leakage detection result based on the degree of influence of the operating condition information and the road condition information on the operating parameters of at least one component in the vehicle's air suspension system; wherein the leakage detection result is used to indicate the target leakage location and / or target leakage type in the at least one component.

[0006] In another aspect of this application, a vehicle is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the vehicle control method as described in the preceding aspect.

[0007] Another aspect of this application provides a chip including an interface circuit and a processing circuit coupled to each other, the interface circuit being used to input or output signals, and the processing circuit being configured to perform the vehicle control method as described in the foregoing aspect.

[0008] In another aspect of this application, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the vehicle control method as described in the foregoing aspect.

[0009] Another aspect of this application provides a computer program product having a computer program stored thereon, which, when executed by a processor, implements the vehicle control method as described in the foregoing aspect.

[0010] The vehicle control method, device, vehicle, chip, and storage medium proposed in this application comprehensively consider the influence of vehicle operating condition information and road condition information on the operating parameters of at least one component in the air suspension system to determine the air suspension system leakage detection results. This effectively distinguishes between parameter fluctuations caused by normal operating / road conditions and abnormal attenuation caused by genuine chronic leakage, thereby accurately identifying the location and type of progressive, non-abrupt leakage faults and significantly improving the detection rate and diagnostic accuracy of early faults. Therefore, it not only avoids false alarms and missed alarms but also enables early warning of potential risks, enhancing the reliability, driving safety, and proactive maintenance of the air suspension system, meeting the requirements of intelligent chassis for highly robust health monitoring.

[0011] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0012] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A schematic flowchart of a vehicle control method provided for an exemplary embodiment of this application; Figure 2 A schematic flowchart of another vehicle control method provided for an exemplary embodiment of this application; Figure 3 A schematic flowchart of yet another vehicle control method provided for an exemplary embodiment of this application; Figure 4 A schematic flowchart of another vehicle control method provided for an exemplary embodiment of this application; Figure 5 A schematic diagram illustrating the air leakage detection principle of an air suspension system provided for an exemplary embodiment of this application; Figure 6 A schematic diagram of the structure of a vehicle control device provided for an exemplary embodiment of this application; Figure 7 A block diagram illustrating a vehicle according to an exemplary embodiment; Figure 8 This is a schematic diagram of the structure of a chip proposed as an exemplary embodiment of this application. Detailed Implementation

[0013] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0014] In related technologies, health monitoring of air suspension systems is performed based on fixed thresholds. For example, if the air spring pressure in the air suspension system falls below a fixed threshold, an air spring malfunction is identified. This fixed threshold-based fault detection mechanism can only trigger alarm signals when a clear and known fault occurs. It cannot effectively identify and respond to gradual, non-abrupt abnormal operating conditions such as chronic air leakage in the air suspension system, making it difficult to provide timely warnings of potential faults and affecting system reliability and driving safety. Therefore, to address at least one of the problems existing in the aforementioned related technologies, this application proposes a vehicle control method, device, vehicle, chip, and storage medium.

[0015] The vehicle control method, apparatus, vehicle, chip, and storage medium of this application are described below with reference to the accompanying drawings.

[0016] Figure 1 This is a schematic flowchart of a vehicle control method provided for an exemplary embodiment of this application.

[0017] It should be noted that the vehicle control method of this application embodiment can be applied to a vehicle control device. In some possible embodiments, the vehicle control device can be configured in a vehicle or a chip so that the vehicle or chip can perform vehicle control functions. Additionally, in some possible embodiments, the vehicle control device can also be software within the vehicle.

[0018] In any embodiment of this application, the chip can be integrated into a vehicle. The chip includes a Central Processing Unit (CPU), an Image Signal Processing (ISP), an Application-Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Field-Programmable Gate Array (FPGA), a System-on-Chip (SOC), a Reduced Instruction Set Computer (RISC), etc., which will not be listed here.

[0019] The vehicle can be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles, and this application embodiment does not limit this.

[0020] For ease of explanation, the following description will use a vehicle as the executor of this vehicle control method.

[0021] like Figure 1 As shown, the vehicle control method may include the following steps S101 to S102: Step S101: Obtain the vehicle's operating condition information and the road condition information of the road on which the vehicle is traveling.

[0022] Among them, operating condition information is dynamic data used to indicate the actual operating status of the vehicle and environmental conditions.

[0023] In any embodiment of this application, the operating condition information includes, but is not limited to, at least one of the following: The first item: vehicle usage status; wherein, vehicle usage status is used to indicate the load distribution status of the vehicle, and the load distribution status includes at least one of the following: number of occupants, occupant positions, cargo weight, and cargo loading position.

[0024] It is understandable that different load distributions will have varying degrees of impact on the operating parameters of at least one component in the air suspension system. This at least one component in the air suspension system includes, but is not limited to: at least one air spring (e.g., four air springs): a sealed airbag made of composite material, filled with compressed air, which supports the weight of the vehicle body; an air compressor: providing the compressed air source for the air suspension system; an air reservoir: storing compressed air, improving response speed and reducing frequent start-stop of the air compressor; and valves in any air circuit. It should be noted that the air suspension system may also include: a height sensor and electronic control unit (ECU): monitoring the vehicle height in real time and automatically adjusting air pressure according to road conditions, load, or driving mode; and solenoid valves / distribution valves: controlling the inflation / deflation of each air spring for independent adjustment.

[0025] For example, the height of the air spring when the vehicle is unloaded can be higher than the height of the air spring when the vehicle is loaded; the air spring pressure when the vehicle is unloaded can be lower than the air spring pressure when the vehicle is loaded.

[0026] The second item: Vehicle maintenance status; where vehicle maintenance status indicates whether the vehicle is in maintenance mode or in a lifted state.

[0027] It should be understood that when a vehicle is in maintenance mode, air may be deflated or inflated, which may affect the operating parameters of at least one component of the air suspension system. For example, it may affect the height and pressure of the air springs.

[0028] The third item: Fault List (also known as Diagnostic Trouble Code (DTC) list); the fault list includes DTCs that have actually been diagnosed in the vehicle and are associated with the air suspension system. DTCs are used to indicate known fault types.

[0029] For example, known fault types include, but are not limited to, failure to handshake with the ECU in the air suspension system.

[0030] The fourth item: Actual operating information of the air suspension system; wherein, the actual operating information includes the actual operating parameters of at least one component in the air suspension system, such as the pressure, air volume, volume and height of the air spring, the opening and closing status and opening angle of the air circuit valve, and the current and vibration of the gas compressor.

[0031] Fifth item: Actual operating information of other vehicle components associated with the air suspension system; wherein, the actual operating information includes the actual operating parameters of other vehicle components.

[0032] For example, the operating status of a vehicle's braking system may affect the stress on the vehicle body, which in turn affects the operating parameters of at least one component in the air suspension system; the operation of the vehicle's steering system will also change the vehicle's dynamic balance, affecting the adjustment requirements of the air suspension system and the operation of its components.

[0033] Item 6: Environmental information of the environment in which the air suspension system is located; among which, environmental information includes, but is not limited to, ambient temperature and ambient humidity.

[0034] It is understandable that different environmental conditions will have different degrees of impact on the operating parameters of at least one component in the air suspension system. For example, high temperatures will increase the pressure of the air spring, while low temperatures will decrease the pressure of the air spring (because low temperatures will cause the air to contract, resulting in a decrease in the pressure of the compressed air sealed inside the air spring).

[0035] In summary, considering multi-dimensional operating condition information can improve the rationality and accuracy of subsequent leak detection.

[0036] Road condition information refers to data indicating the specific conditions and characteristics of the road on which a vehicle travels. For example, road condition information includes, but is not limited to, road surface slope and altitude.

[0037] It should be noted that different road conditions affect the operating parameters of at least one component in the air suspension system to varying degrees. For example, when a road slope causes the vehicle to tilt to the left, it will affect the height and pressure of the left air spring in the air suspension system; when a road slope causes the vehicle to tilt to the right, it will affect the height and pressure of the right air spring in the air suspension system. Furthermore, high altitude will cause the air spring pressure to decrease because the air is thinner at high altitudes, atmospheric pressure is lower, and the pressure difference between the inside and outside of the air spring is reduced, resulting in a relative decrease in the internal pressure of the air spring.

[0038] Step S102: Based on the operating condition information and road condition information, determine the degree of influence on the operating parameters of at least one component in the vehicle's air suspension system, and determine the air suspension system leakage detection result; wherein, the leakage detection result is used to indicate the target leakage location and / or target leakage type in at least one component.

[0039] The number of target leak locations can be at least one, including but not limited to: air springs, air tanks, valves on the air line, etc.

[0040] The target leakage types include, but are not limited to: no leakage, slow leakage, and fast leakage.

[0041] In this embodiment of the application, the degree of influence of the operating parameters of at least one component in the air suspension system of the vehicle on the vehicle's operating condition information and the road condition information of the road on which the vehicle travels can be used to determine the air suspension system leakage detection result; wherein, the air suspension system leakage is used to indicate whether the air suspension system has leaked, and if leakage has occurred, it further indicates the target leakage location and / or target leakage type in at least one component in the air suspension system.

[0042] The vehicle control method of this application comprehensively considers the impact of vehicle operating condition information and road condition information on the operating parameters of at least one component in the air suspension system to determine the air suspension system leakage detection result. This effectively distinguishes between parameter fluctuations caused by normal operating / road conditions and abnormal attenuation caused by genuine chronic leakage, thereby accurately identifying the location and type of gradual, non-abrupt leakage faults and significantly improving the detection rate and diagnostic accuracy of early faults. Therefore, it not only avoids false alarms and missed alarms but also enables early warning of potential risks, enhancing the reliability, driving safety, and proactive maintenance of the air suspension system, meeting the requirements of intelligent chassis for highly robust health monitoring.

[0043] As one possible implementation method, Figure 2 This is a schematic flowchart illustrating another vehicle control method provided as an exemplary embodiment of this application. It should be noted that this vehicle control method can be executed alone, or it can be executed together with any embodiment or possible implementation thereof in this application, or it can be executed together with any technical solution in related technologies. This application does not impose any limitations on this.

[0044] like Figure 2 As shown, the vehicle control method may include the following steps S201 to S203: Step S201: Obtain the vehicle's operating condition information and the road condition information of the road on which the vehicle is traveling.

[0045] Step S202: Based on the working condition information and road condition information, determine the degree of influence on the operating parameters of at least one component in the vehicle's air suspension system, and determine the air leakage detection result of the air suspension system.

[0046] The leak detection result is used to indicate the target leak location and / or target leak type in at least one component. It should be noted that the explanations of steps S201 to S202 can be found in the relevant descriptions of any embodiment of this application, and will not be repeated here.

[0047] Step S203: In response to the air leak detection result indicating that the air suspension system has leaked, perform at least one of the following: report the warning information to the cloud; send the warning information to the mobile terminal bound to the vehicle; determine the target warning form that matches the target air leak type from multiple warning forms, and use the target warning form to issue a vehicle warning based on the warning information.

[0048] In any embodiment of this application, when the air suspension system is detected to be leaking, the vehicle can report a warning to the cloud. The warning information indicates the target leak location and / or target leak type of the air suspension system. Upon receiving the warning information, the cloud first analyzes the vehicle's historical operating data to pinpoint the cause of the air suspension system leak. The causes include, but are not limited to, leaks due to prolonged service life (or product aging) and improper user operation. Then, the cloud selects a target handling strategy from various leak handling strategies that matches the cause of the leak and executes the target handling strategy on the vehicle to restore the air suspension system from a leaking state to a non-leaking state.

[0049] Using the above example, if the leak is caused by product aging, the cloud can send a product replacement suggestion to the vehicle or owner so that the owner can replace the component at the target leak location. If the leak is caused by improper user operation, the cloud can send product operation suggestions and maintenance suggestions to the vehicle or owner so that the owner can operate the vehicle correctly based on the product operation suggestions and perform timely maintenance on the component at the target leak location based on the maintenance suggestions.

[0050] In summary, when an air suspension system leaks, a warning is reported to the cloud. The cloud then uses historical vehicle operating data to pinpoint the cause of the leak and selects the appropriate solution from various leak handling strategies. This provides targeted solutions for different leak situations, preventing recurrence and effectively improving the reliability and lifespan of the air suspension system. Furthermore, this centralized, intelligent, and personalized approach significantly improves the efficiency and quality of problem-solving for the air suspension system, enhances vehicle reliability and safety, and allows for continuous optimization of handling strategies through big data accumulation, providing strong support for the long-term stable operation of the vehicle.

[0051] In any embodiment of this application, when the air leak detection result indicates that the air suspension system is leaking, a warning message can also be sent to a mobile terminal bound to the vehicle, so that the mobile terminal can visualize and / or broadcast the warning message by voice; wherein, the warning message is used to indicate the target leak location and / or target leak type of the air suspension system.

[0052] A mobile terminal is a user-side entity used to receive or transmit signals, such as a mobile phone. A mobile terminal can also be called a terminal, user equipment (UE), mobile station (MS), or mobile terminal (MT). Mobile terminals can be mobile phones with communication capabilities, wearable devices, tablets, computers with wireless transceiver capabilities, virtual reality (VR) terminals, augmented reality (AR) terminals, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, and so on. The embodiments of this application do not limit the specific technologies or device forms used in the mobile terminals.

[0053] Understandably, when an air suspension system leaks, sending a warning message to a mobile device linked to the vehicle allows the owner to be aware of the problem immediately, regardless of their location. The mobile device supports both visual displays and voice announcements. Visual displays present the location and type of leak using intuitive text, charts, and images, while voice announcements deliver information promptly when the owner cannot view the screen, ensuring the owner can quickly understand the situation in various scenarios. This timely and convenient information delivery method enables owners to proactively participate in vehicle maintenance, take timely measures, effectively prevent the leak from worsening, and safeguard driving safety and vehicle performance.

[0054] In any embodiment of this application, when the air leak detection result indicates that the air suspension system has leaked, a target warning form matching the target leak type can be determined from a variety of warning forms, and the target warning form can be used to issue a vehicle warning based on the warning information; wherein, the warning information is used to indicate the target leak location and / or target leak type of the air suspension system; the warning form includes at least one of the following: text form, graphic form, video form, audio form, light form, vibration form.

[0055] The text format indicates a leak by displaying text information on the vehicle screen, such as "The gas tank is experiencing a chronic leak."

[0056] The graphic forms include, but are not limited to, static graphic forms and dynamic graphic forms (such as animations). Specifically, the graphic form displays the air leak as an image. For example, in the 3D vehicle model within the vehicle's Human-Machine Interface (HMI), the target air leak location and the corresponding target air leak type are marked.

[0057] One option is a video presentation: a short video is played on the vehicle's screen to demonstrate the air leak.

[0058] Among them, the audio form: indicating the gas leak by playing alarm sounds, voice prompts and other audio signals.

[0059] In summary, when an air suspension system leaks, the appropriate warning method is determined based on the type of leak, enabling highly targeted alerts. For example, minor leaks can be communicated concisely and clearly using text or graphics; serious leaks can be addressed with audio, light, or vibration to strongly emphasize the issue and draw the driver's attention. This diverse combination of warning methods fully considers the severity of different leaks and the information needs of drivers in various scenarios, ensuring accurate and timely delivery of warning information. This significantly improves the effectiveness of the warnings, allowing drivers to react quickly, ensuring safe vehicle operation, and enhancing the user experience of the vehicle's warning system.

[0060] It should be noted that the above-mentioned early warning mechanism is only an example of one of the three methods: reporting to the cloud, pushing to mobile terminals, and local vehicle warning. However, this application is not limited to this. In actual application scenarios, at least two of the above early warning mechanisms can be combined to form a more comprehensive, efficient, and flexible early warning system, so as to better deal with various air leakage situations that may occur in the air suspension system and provide users with a more reliable and better user experience.

[0061] The vehicle control method of this application embodiment, through a flexible and integrated approach, utilizes multiple early warning mechanisms such as cloud reporting, mobile terminal push notifications, and local vehicle warnings. This approach leverages the powerful data analysis capabilities of the cloud to accurately pinpoint the cause of air leaks and provide targeted leak handling strategies. It also promptly delivers early warning information to the vehicle owner, ensuring they are aware of the issue regardless of their location. Furthermore, local vehicle warnings can quickly draw the owner's attention based on the type of leak using appropriate warning formats. This multi-faceted and multi-layered approach comprehensively and systematically ensures that air leaks in the air suspension system are detected and properly addressed in a timely manner, effectively improving the safety and reliability of vehicle operation and providing a safety guarantee for the owner's travel.

[0062] As one possible implementation method, Figure 3 This is a schematic flowchart illustrating another vehicle control method provided as an exemplary embodiment of this application. It should be noted that this vehicle control method can be executed alone, or it can be executed together with any embodiment of this application or any possible implementation thereof, or it can be executed together with any technical solution in related technologies. This application does not impose any limitations on this.

[0063] like Figure 3 As shown, the vehicle control method may include the following steps S301 to S305: Step S301: Obtain the vehicle's operating condition information and the road condition information of the road on which the vehicle is traveling.

[0064] It should be noted that the explanation of step S301 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0065] Step S302: Extract features from the working condition information and road condition information to obtain a multi-dimensional feature vector, and perform feature processing on the multi-dimensional feature vector to obtain the target feature vector.

[0066] The target feature vector is used to characterize the degree of influence of operating condition information and road condition information on the operating parameters of at least one component in the air suspension system.

[0067] In this embodiment, feature extraction technology can be used to extract features from working condition information and road condition information to obtain a multi-dimensional feature vector. For example, firstly, the working condition information and road condition information can be processed by time slicing to obtain time slice data under at least one time slice. Then, statistical features, time-domain features, frequency-domain features, and combined features of the time slice data can be obtained; wherein, the combined feature is obtained by combining at least two of the statistical features, time-domain features, and frequency-domain features. Finally, a multi-dimensional feature vector can be generated based on at least two of the statistical features, time-domain features, frequency-domain features, and combined features.

[0068] Understandably, time-slicing of work condition and road condition information can transform continuous and complex data into structured slice data. This not only reduces processing difficulty and improves computational efficiency but also supports parallel operations to meet real-time requirements. Based on this, statistical features, time-domain features, frequency-domain features, and combined features can be obtained. This allows for comprehensive mining of feature information from multiple dimensions, such as overall distribution, changes over time, and frequency components, avoiding feature omissions. The resulting multi-dimensional feature vectors can more accurately represent data characteristics, providing strong support for subsequent analysis and modeling, and significantly improving the accuracy and reliability of model predictions.

[0069] In this embodiment, after extracting the multidimensional feature vector, feature processing can be performed on the multidimensional feature vector to obtain a target feature vector that characterizes the aforementioned degree of influence. For example, feature processing can be performed on the multidimensional feature vector based on convolution mechanisms, gating mechanisms, multi-head attention mechanisms, etc., to obtain the target feature vector.

[0070] Step S303: Classify and predict the type of air leakage on the target feature vector to obtain a first probability distribution; wherein, the first probability distribution is used to indicate the probability that the air suspension system belongs to multiple types of air leakage.

[0071] The types of air leakage include, but are not limited to: no leakage, slow leakage, and fast leakage.

[0072] In this embodiment of the application, a classification technique, such as a leak type classification task head, can be used to classify and predict the leak type of the target feature vector to obtain a first probability distribution; wherein, the first probability distribution is used to indicate the probability that the air suspension system belongs to multiple leak types.

[0073] Step S304: Classify and predict the location of air leaks in the target feature vector to obtain a second probability distribution; wherein, the second probability distribution is used to indicate the probability of air leaks occurring at multiple air leak locations in the air suspension system.

[0074] Leakage locations include, but are not limited to: the four air springs, the air tank, and valves on the air line.

[0075] In this embodiment of the application, a second probability distribution can be obtained by classifying and predicting the leakage location of the target feature vector based on classification technology, such as a leakage location classification task head; wherein, the second probability distribution is used to indicate the probability of air leakage occurring at multiple leakage locations of the air suspension system.

[0076] Step S305: Generate a leak detection result based on a first probability distribution and a second probability distribution; wherein the leak detection result is used to indicate the target leak location and / or target leak type in at least one component.

[0077] In this embodiment of the application, the target air leakage type of the air suspension system can be determined according to a first probability distribution. For example, the air leakage type with the highest probability can be taken as the target air leakage type. For instance, assuming the probability of no leakage is 10%, the probability of slow leakage is 75%, and the probability of fast leakage is 15%, then the target air leakage type of the air suspension system can be determined to be slow leakage.

[0078] In this embodiment, the target leak location in at least one component of the air suspension system can be determined based on a second probability distribution. For example, the leak location with the highest probability can be used as the target leak location, or the leak location with a probability higher than a set probability threshold can be used as the target leak location; this embodiment does not impose any limitations on this.

[0079] The vehicle control method of this application extracts and processes features from vehicle operating condition information and road condition information to generate a target feature vector with high representational capability. Based on this target feature vector, it performs probabilistic classification and prediction of leak type and leak location, outputting a fine-grained first probability distribution (leak type) and a second probability distribution (leak location). This detection mechanism based on multi-source information fusion and probabilistic reasoning not only quantifies the probability of different fault hypotheses, avoiding the risk of misjudgment caused by hard decision-making, but also effectively distinguishes between normal parameter fluctuations caused by complex operating conditions or severe road conditions and real chronic leak signals, thereby significantly improving the sensitivity and positioning accuracy of progressive, weak-signal leak faults. Finally, by jointly analyzing the two probability distributions to generate structured leak detection results, it provides interpretable and traceable diagnostic basis for maintenance decisions, enhancing the fault early warning capability of the air suspension system in actual operating environments.

[0080] As one possible implementation method, Figure 4 This is a schematic flowchart illustrating another vehicle control method provided as an exemplary embodiment of the present application. It should be noted that this vehicle control method can be executed alone, or it can be executed together with any embodiment of the present application or any possible implementation thereof, or it can be executed together with any technical solution in related technologies. The embodiments of the present application do not impose any limitations on this.

[0081] like Figure 4 As shown, the vehicle control method may include the following steps S401 to S408: Step S401: Obtain the vehicle's operating condition information and the road condition information of the road on which the vehicle travels, and extract features from the operating condition information and road condition information to obtain a multi-dimensional feature vector.

[0082] It should be noted that the explanation of step S401 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0083] Step S402: Normalize the multidimensional feature vector to obtain normalized features, and perform convolution operation on the normalized features to extract local features of the target.

[0084] In this embodiment, the multidimensional feature vector can first be normalized to eliminate the influence of differences in dimensions and numerical ranges between different features, resulting in normalized features. Then, a convolution operation can be performed on the normalized features to extract the target local features.

[0085] In any embodiment of this application, the method for extracting the target local features is, for example, to sequentially perform convolution and batch normalization on the normalized features to obtain the first local features, then to perform a nonlinear transformation on the first local features using a nonlinear activation function to obtain the second local features, and then to perform at least one of max pooling, batch normalization, convolution, and nonlinear transformation on the second local features to obtain the target local features.

[0086] Nonlinear activation functions include, but are not limited to, the Rectified Linear Unit (RELU) activation function.

[0087] For example, a one-dimensional convolution (Conv1D) operation can be performed on the normalized features. The convolution kernel slides across the normalized features and calculates the dot product to extract local features. Simultaneously, batch normalization and a non-linear activation function are combined to further process these local features, enhancing the model's non-linear expressive power and training stability. Then, max pooling is performed to reduce the feature dimensionality of the local features, resulting in convolutional features that are aware of local features and have optimized dimensionality. Optionally, a one-dimensional convolution operation, batch normalization, non-linear transformation, and max pooling operation can be sequentially performed on the convolutional features to obtain the target local features.

[0088] Therefore, by performing convolution and batch normalization on the normalized features, the first local features are obtained. The convolution operation can extract features in local regions using the convolution kernel, and the batch normalization can accelerate training and stabilize the network. The first local features are then transformed nonlinearly using a nonlinear activation function, enabling the model to learn complex patterns and obtain the second local features that better fit the data distribution. At least one of max pooling, batch normalization, convolution, and nonlinear transformation is then performed on the second local features. Max pooling can reduce feature dimensionality and enhance translation invariance, while batch normalization, convolution, and nonlinear transformation can further optimize the features. This layered, multi-operation collaborative convolution mechanism can efficiently extract rich and accurate target local features, improving model performance and generalization ability.

[0089] Step S403: Use a gating mechanism to perform temporal modeling of the target local features to obtain long-term temporal features related to the air suspension system.

[0090] In this embodiment, a gating mechanism can be used to perform temporal modeling of the target's local features to obtain long-term temporal features related to the air suspension system. For example, a Long Short-Term Memory (LSTM) layer can be used to perform temporal modeling of the target's local features. LSTM, with its unique gating mechanism, can effectively capture long-term dependencies in the feature sequence and update its internal state based on the current input and past states, thereby obtaining long-term temporal features containing dynamic temporal information.

[0091] The LSTM layer can include at least one LSTM and at least one random deactivation (Dropout, which randomly "turns off" (a portion of neurons) with a certain probability, i.e., sets their output to 0). LSTM can effectively handle long-term dependencies in time series data. It can remember information over a long period of time and update its internal state based on the current input and past states. Dropout randomly discards a portion of neurons during training to prevent overfitting and improve the model's generalization ability.

[0092] Step S404: Use a multi-head attention mechanism to determine the importance weights of long-term features, and weight the long-term features based on the importance weights to obtain the target weighted features.

[0093] In the embodiments of this application, a multi-head attention mechanism can be used to determine the importance weights of long-term features, and the long-term features can be weighted based on the importance weights to obtain the target weighted features.

[0094] In any embodiment of this application, the target weighted feature is obtained in the following way: First, a multi-head attention mechanism is used to determine the first importance weight of the long-term feature under each attention head, and the long-term feature is weighted based on the first importance weight corresponding to each attention head to obtain the first weighted feature corresponding to each attention head. Then, the first weighted feature of each attention head can be subjected to nonlinear transformation processing to obtain the second weighted feature corresponding to each attention head. For example, the first weighted feature of each attention head can be input into a feedforward network for nonlinear transformation processing to obtain the second weighted feature corresponding to each attention head. Then, the long-term feature and the second weighted feature of each attention head can be residually connected (Add) and then layer normalization (Norm) processing is performed to obtain the third weighted feature. Finally, the target weighted feature can be generated based on the third weighted feature.

[0095] For example, a multi-head attention mechanism can be used to determine the second importance weights of the third weighted feature under multiple attention heads, and then weight the third weighted feature based on the second importance weights corresponding to the multiple attention heads to obtain the fourth weighted feature corresponding to the multiple attention heads. Then, the fourth weighted feature of the multiple attention heads is subjected to nonlinear transformation processing to obtain the fifth weighted feature corresponding to the multiple attention heads. For example, the fourth weighted feature of the multiple attention heads can be input into a feedforward network for nonlinear transformation processing to obtain the fifth weighted feature corresponding to the multiple attention heads. Then, the third weighted feature and the fifth weighted feature of the multiple attention heads can be residually connected and layer normalization processing (Add&Norm) can be performed to obtain the target weighted feature.

[0096] In summary, multi-head attention mechanisms can examine long-term features from multiple perspectives, comprehensively capture the complex relationships and dependencies between features, accurately assess the importance of each feature to the task, and avoid the limitations of a single perspective. Based on importance weighting, key features can be highlighted and irrelevant or secondary features can be suppressed, making the target weighted features more focused on information that plays a decisive role in the task, effectively improving the quality and representativeness of features, thereby enhancing the model's ability to understand and process long-term features, and improving model performance and prediction accuracy.

[0097] Step S405: Perform global average pooling on the target weighted features to obtain the target feature vector.

[0098] The target feature vector is used to characterize the degree of influence of operating condition information and road condition information on the operating parameters of at least one component in the air suspension system.

[0099] In this embodiment of the application, a global average pooling operation can be performed on the target weighted features to obtain a target feature vector that characterizes the aforementioned degree of influence.

[0100] Step S406: Perform air leakage type classification prediction on the target feature vector to obtain a first probability distribution; wherein, the first probability distribution is used to indicate the probability that the air suspension system belongs to multiple air leakage types.

[0101] Step S407: Classify and predict the location of air leaks in the target feature vector to obtain a second probability distribution; wherein, the second probability distribution is used to indicate the probability of air leaks occurring at multiple air leak locations in the air suspension system.

[0102] Step S408: Generate the air leakage detection result of the air suspension system based on the first probability distribution and the second probability distribution.

[0103] The leak detection result is used to indicate the target leak location and / or target leak type in at least one component of the air suspension system. It should be noted that explanations of steps S406 to S408 can be found in the relevant descriptions of any embodiment of this application, and will not be repeated here.

[0104] As an example, the leak detection principle of an air suspension system can be as follows: Figure 5 As shown, it mainly includes the following steps: 1. Acquire multi-source heterogeneous data associated with the actual operating status of the air suspension system. This multi-source heterogeneous data includes: enterprise standard signals (including actual operating information of the air suspension system, actual operating information of other vehicle components associated with the air suspension system, and environmental information of the environment in which the air suspension system is located), DTC fault list, vehicle usage status, vehicle maintenance status, and road condition information (or road information).

[0105] 2. Perform time-slicing processing on multi-source heterogeneous data to obtain time-slice data under at least one time slice, and obtain the statistical characteristics, time-domain characteristics, frequency-domain characteristics and combined characteristics of the time-slice data.

[0106] 3. Generate an N-dimensional feature vector based on statistical characteristics, time-domain characteristics, frequency-domain characteristics, and combined characteristics.

[0107] 4. Input the N-dimensional feature vector into the input layer and feature normalization layer of the air leakage detection model in sequence to eliminate the influence of differences in dimensions and numerical ranges between different features and obtain normalized features.

[0108] 5. Perform one-dimensional convolution (Conv1D) operation on the normalized features through convolutional layers. Use the convolution kernel to slide on the feature sequence and calculate the dot product to extract local feature patterns. At the same time, combine batch normalization (BatchNorm) and ReLU activation function to enhance the non-linear expressive power and training stability of the model. Then, reduce the feature dimension through one-dimensional max pooling (MaxPooling1D) to obtain target local features with local feature awareness and dimension optimization.

[0109] 6. The local features of the target are processed by temporal modeling through LSTM layers to obtain long-term temporal features. Among them, LSTM, with its unique gating mechanism, can effectively capture long-term dependencies in the feature sequence and update the internal state according to the current input and past states, thereby obtaining long-term temporal features containing temporal dynamic information.

[0110] 7. The attention module employs a multi-head attention mechanism to perform attention weight allocation on long-term features. The multi-head attention mechanism calculates the importance weight of features from multiple different perspectives, enabling the leak detection model to focus on key feature information. After residual connection and normalization operations, the feature representation that has been attention-weighted and highlights important features is obtained, which is referred to as target weighted feature in this application.

[0111] 8. Input the target weighted features into the global average pooling layer and the fully connected layer in sequence to obtain the target feature vector output by the fully connected layer.

[0112] 9. Input the target feature vector into the leak type classification task head to predict the leak type and obtain the first probability distribution. Then input the target feature vector into the leak location classification task head to predict the leak location and obtain the second probability distribution.

[0113] 10. Generate the air leakage detection results of the air suspension system based on the first probability distribution and the second probability distribution.

[0114] The leak detection model is a trained neural network model. For example, the leak detection model can be trained using the following steps: 1) Obtain training samples; wherein the training samples include sample operating condition information of the sample vehicle and sample road condition information of the road on which the sample vehicle travels, and the training samples are labeled with a first air leak detection result, which is used to indicate the location and / or type of air leak in at least one component of the air suspension system of the sample vehicle. 2) Extract features from the sample working condition information and sample road condition information to obtain multi-dimensional feature vectors, and use the air leakage detection model to process the multi-dimensional feature vectors to obtain sample feature vectors; 3) The air leakage detection model is used to classify and predict the leakage type of the sample feature vector to obtain the first prediction probability distribution, and the air leakage location of the sample feature vector is classified and predicted to obtain the second prediction probability distribution; wherein, the first prediction probability distribution is used to indicate the probability that the air suspension system of the sample vehicle belongs to multiple leakage types; the second prediction probability distribution is used to indicate the probability that the air suspension system of the sample vehicle leaks at multiple leakage locations. 4) Based on the first and second predicted probability distributions, generate the second air leakage detection result of the air suspension system of the sample vehicle; 5) Based on the difference between the first and second leak detection results, supervised training is performed on the leak detection model.

[0115] The vehicle control method of this application performs normalization processing on multi-dimensional feature vectors, which can eliminate differences in the dimensions of different features and enhance data stability and comparability. Performing convolution operation on the normalized features can effectively extract target local features and capture the fine patterns and correlations of local data. Using a gating mechanism to perform temporal modeling on the target local features can fully explore the dynamic change patterns of local features in the time dimension and obtain long-term features closely related to the air suspension system. Using a multi-head attention mechanism to determine the importance weights of long-term features and weighting them can highlight key features, suppress irrelevant information, and improve feature quality. Performing global average pooling operation on the target weighted features to obtain the target feature vector can reduce the feature dimension while retaining key information, making the final generated target feature vector more representative and discriminative, which helps to improve the accuracy of subsequent air leak detection.

[0116] To achieve the above embodiments, this application also proposes a vehicle control device. Figure 6 This is a schematic diagram of the structure of a vehicle control device provided for an exemplary embodiment of this application.

[0117] like Figure 6 As shown, the vehicle control device 600 may include an acquisition module 610 and a determination module 620.

[0118] The acquisition module 610 is used to acquire the vehicle's operating condition information and the road condition information of the road on which the vehicle travels; the determination module 620 is used to determine the air leakage detection result of the air suspension system based on the degree of influence of the operating parameters of at least one component in the vehicle's air suspension system on the operating condition information and the road condition information; wherein the air leakage detection result is used to indicate the target air leakage location and / or target air leakage type in at least one component.

[0119] In one implementation of this application, the operating condition information includes at least one of the following: vehicle usage status; wherein the vehicle usage status is used to indicate the load distribution status of the vehicle, and the load distribution status includes at least one of the following: number of occupants, occupant positions, cargo weight, and cargo loading position; vehicle maintenance status; fault list; wherein the fault list includes diagnostic fault codes (DTCs) that have been actually diagnosed by the vehicle and are associated with the air suspension system, and the DTCs are used to indicate known fault types; actual operating information of the air suspension system; actual operating information of other vehicle components associated with the air suspension system; and environmental information of the environment in which the air suspension system is located.

[0120] In one implementation of this application, the vehicle control device 600 may further include: a reporting module for reporting warning information to the cloud; wherein the warning information is used to indicate the target air leak location and / or target air leak type of the air suspension system; the warning information is used to perform the following on the cloud: based on the vehicle's historical operating condition information, locate the cause of the air leak in the air suspension system, determine a target processing strategy matching the cause of the leak from a variety of leak handling strategies, and execute the target processing strategy on the vehicle to restore the air suspension system from a leaking state to a non-leaking state.

[0121] In one implementation of this application, the vehicle control device 600 may further include at least one of the following modules: a sending module, configured to send warning information to a mobile terminal bound to the vehicle, so that the mobile terminal can visualize and / or voice broadcast the warning information; wherein the warning information is used to indicate the target air leak location and / or target air leak type of the air suspension system; a warning module, configured to determine a target warning form matching the target air leak type from a variety of warning forms, and use the target warning form to issue a vehicle warning based on the warning information; wherein the warning form includes at least one of the following: text form, graphic form, video form, audio form, light form, and vibration form.

[0122] In one implementation of this application, the determining module 620 is configured to: extract features from the operating condition information and road condition information to obtain a multi-dimensional feature vector; perform feature processing on the multi-dimensional feature vector to obtain a target feature vector that characterizes the degree of influence; perform leakage type classification prediction on the target feature vector to obtain a first probability distribution; and perform leakage location classification prediction on the target feature vector to obtain a second probability distribution; wherein, the first probability distribution is used to indicate the probability that the air suspension system belongs to multiple leakage types; the second probability distribution is used to indicate the probability that the air suspension system leaks at multiple leakage locations; and generate a leakage detection result based on the first probability distribution and the second probability distribution.

[0123] In one implementation of this application, the determining module 620 is used to: perform time-slicing processing on the working condition information and road condition information to obtain time-slice data under at least one time slice; acquire statistical features, time-domain features, frequency-domain features and combined features of the time-slice data; wherein, the combined features are obtained by combining at least two of the statistical features, time-domain features and frequency-domain features; and generate a multi-dimensional feature vector based on at least two of the statistical features, time-domain features, frequency-domain features and combined features.

[0124] In one implementation of this application, the determining module 620 is configured to: normalize the multidimensional feature vector to obtain normalized features, and perform a convolution operation on the normalized features to extract target local features; use a gating mechanism to perform temporal modeling on the target local features to obtain long-term features related to the air suspension system; use a multi-head attention mechanism to determine the importance weights of the long-term features, and weight the long-term features based on the importance weights to obtain target weighted features; and perform a global average pooling operation on the target weighted features to obtain the target feature vector.

[0125] In one implementation of this application, the determining module 620 is configured to: sequentially perform convolution and batch normalization operations on the normalized features to obtain a first local feature; perform a nonlinear transformation on the first local feature using a nonlinear activation function to obtain a second local feature; and perform at least one of max pooling, batch normalization, convolution, and nonlinear transformation on the second local feature to obtain a target local feature.

[0126] In one implementation of this application, the determining module 620 is configured to: employ a multi-head attention mechanism to determine the first importance weight of the long-time-series feature under each attention head, and weight the long-time-series feature based on the first importance weight corresponding to each attention head to obtain the first weighted feature corresponding to each attention head; perform nonlinear transformation processing on the first weighted feature of each attention head to obtain the second weighted feature corresponding to each attention head; perform residual connection between the long-time-series feature and the second weighted feature of each attention head, and then perform layer normalization processing to obtain the third weighted feature; and generate the target weighted feature based on the third weighted feature.

[0127] In one implementation of this application, the determining module 620 is configured to: employ a multi-head attention mechanism to determine the second importance weights of the third weighted feature under multiple attention heads, and weight the third weighted feature based on the second importance weights corresponding to the multiple attention heads to obtain a fourth weighted feature corresponding to the multiple attention heads; perform nonlinear transformation processing on the fourth weighted feature of the multiple attention heads to obtain a fifth weighted feature corresponding to the multiple attention heads; and perform layer normalization processing after residual connection of the third weighted feature and the fifth weighted feature of the multiple attention heads to obtain the target weighted feature.

[0128] It should be noted that the explanation of the vehicle control method embodiment performed on the vehicle described above also applies to the vehicle control device of this embodiment, and will not be repeated here.

[0129] In the vehicle control device of this application embodiment, the degree of influence of the vehicle's operating condition information and the road condition information on the operating parameters of at least one component in the air suspension system is considered to determine the air suspension system's leak detection result. This can effectively distinguish between parameter fluctuations caused by normal operating conditions / road conditions and abnormal attenuation caused by actual chronic leaks, thereby accurately identifying the location and type of gradual, non-abrupt leak faults and significantly improving the detection rate and diagnostic accuracy of early faults. Therefore, not only can false alarms and missed alarms be avoided, but early warning of potential risks can also be achieved, enhancing the reliability, driving safety, and proactive maintenance of the air suspension system, and meeting the requirements of intelligent chassis for highly robust health monitoring.

[0130] To implement the above embodiments, this application also proposes a vehicle, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the vehicle control method as described in any of the foregoing embodiments.

[0131] Figure 7 This is a block diagram illustrating a vehicle 700 according to an exemplary embodiment. For example, vehicle 700 can be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicle. Vehicle 700 can be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0132] Reference Figure 7 The vehicle 700 may include various subsystems, such as an infotainment system 710, a perception system 720, a decision control system 730, a drive system 740, and a computing platform 750. The vehicle 700 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of the vehicle 700 can be interconnected via wired or wireless means.

[0133] In some embodiments, the infotainment system 710 may include a communication system, an entertainment system, and a navigation system, etc.

[0134] The perception system 720 may include several sensors for sensing information about the environment surrounding the vehicle 700. For example, the perception system 720 may include a global positioning system (which may be GPS, BeiDou, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0135] The decision control system 730 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0136] The drive system 740 may include components that provide powered motion to the vehicle 700. In one embodiment, the drive system 740 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0137] Some or all of the functions of the vehicle 700 are controlled by a computing platform 750. The computing platform 750 may include at least one processor 751 and a memory 752, the processor 751 being able to execute instructions 753 stored in the memory 752.

[0138] The processor 751 can be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processing unit (GPU), a field-programmable gate array (FPGA), a system on a chip (SOC), an application-specific integrated circuit (ASIC), or a combination thereof.

[0139] The memory 752 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0140] In addition to instruction 753, memory 752 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 752 can be used by computing platform 750.

[0141] In this embodiment of the application, processor 751 may execute instruction 753 to complete all or part of the steps of any of the above method embodiments.

[0142] To implement the above embodiments, this application also proposes a chip, wherein the chip includes an interface circuit and a processing circuit coupled to each other. The interface circuit is used to input or output signals, and the processing circuit is configured to execute the vehicle control method provided in any of the foregoing embodiments.

[0143] Figure 8 This is a schematic diagram of a chip structure proposed as an exemplary embodiment of this application. See also... Figure 8 The diagram shown is a schematic representation of the structure of chip 800, but is not limited to this.

[0144] Chip 800 includes processing circuitry 801, which is configured to execute any of the above vehicle control methods.

[0145] In some embodiments, the chip 800 further includes one or more interface circuits 802. Optionally, the interface circuit 802 is connected to the memory 803, and the interface circuit 802 can be used to receive signals from the memory 803 or other devices, and the interface circuit 802 can be used to send signals to the memory 803 or other devices. For example, the interface circuit 802 can read instructions stored in the memory 803 and send the instructions to the processing circuit 801.

[0146] In some embodiments, the interface circuit 802 performs at least one of the communication steps such as sending and / or receiving in the above method, and the processing circuit 801 performs other steps.

[0147] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, etc., can be used interchangeably.

[0148] In some embodiments, chip 800 further includes one or more memories 803 for storing instructions. Optionally, all or part of the memories 803 may be located outside of chip 800.

[0149] To implement the above embodiments, this application also proposes a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the vehicle control method as described in any of the foregoing method embodiments.

[0150] To implement the above embodiments, this application also proposes a computer program product having a computer program stored thereon, which, when executed by a processor, implements the vehicle control method as described in any of the foregoing method embodiments.

[0151] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0152] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0153] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0154] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and compact disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0155] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0156] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0157] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0158] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A vehicle control method, characterized in that, include: Obtain the vehicle's operating condition information and the road condition information of the road on which the vehicle travels; Based on the operating condition information and the road condition information, the degree of influence on the operating parameters of at least one component in the air suspension system of the vehicle is used to determine the air suspension system leakage detection result; wherein, the leakage detection result is used to indicate the target leakage location and / or target leakage type in the at least one component.

2. The method according to claim 1, characterized in that, The operating condition information includes at least one of the following: Vehicle usage status; wherein, the vehicle usage status is used to indicate the load distribution status of the vehicle, and the load distribution status includes at least one of the following: number of occupants, occupant positions, cargo weight, and cargo loading position; Vehicle maintenance status; Fault list; wherein the fault list includes diagnostic codes (DTCs) that have been diagnosed in relation to the air suspension system of the vehicle, and the DTCs are used to indicate known fault types; The actual operating information of the air suspension system; Actual operating information of other vehicle components associated with the air suspension system; The environmental information of the environment in which the air suspension system is located.

3. The method according to claim 1, characterized in that, The method further includes: Reporting early warning information to the cloud; wherein, the early warning information is used to indicate the target leak location and / or target leak type of the air suspension system; the early warning information is used by the cloud to perform the following steps: Based on the vehicle's historical operating information, the cause of the air leakage in the air suspension system was located. From a variety of leak handling strategies, determine the target handling strategy that matches the cause of the leak; The target processing strategy is executed on the vehicle to restore the air suspension system from a leaking state to a non-leaking state.

4. The method according to claim 1, characterized in that, The method further includes at least one of the following: Send a warning message to a mobile terminal bound to the vehicle, so that the mobile terminal can visualize and / or broadcast the warning message by voice; wherein the warning message is used to indicate the target air leak location and / or the target air leak type of the air suspension system; A target warning form matching the target air leak type is determined from multiple warning forms, and the target warning form is used to issue a vehicle warning based on the warning information; wherein the warning form includes at least one of the following: text form, graphic form, video form, audio form, light form, and vibration form.

5. The method according to claim 1, characterized in that, Based on the operating condition information and road condition information, the degree of influence on the operating parameters of at least one component in the vehicle's air suspension system is determined, and the air suspension system leakage detection result is determined, including: Feature extraction is performed on the working condition information and the road condition information to obtain a multi-dimensional feature vector, and feature processing is performed on the multi-dimensional feature vector to obtain a target feature vector used to characterize the degree of influence. The target feature vector is classified and predicted for leakage type to obtain a first probability distribution, and the target feature vector is classified and predicted for leakage location to obtain a second probability distribution; wherein, the first probability distribution is used to indicate the probability that the air suspension system belongs to multiple leakage types; the second probability distribution is used to indicate the probability that the air suspension system leaks at multiple leakage locations; The leak detection result is generated based on the first probability distribution and the second probability distribution.

6. The method according to claim 5, characterized in that, The step of extracting features from the working condition information and the road condition information to obtain a multi-dimensional feature vector includes: The working condition information and the road condition information are processed by time slicing to obtain time slice data under at least one time slice. The statistical features, time-domain features, frequency-domain features, and combined features of the time-slice data are obtained; wherein the combined features are obtained by combining at least two of the statistical features, the time-domain features, and the frequency-domain features. The multidimensional feature vector is generated based on at least two of the statistical features, the time-domain features, the frequency-domain features, and the combined features.

7. The method according to claim 5, characterized in that, The step of performing feature processing on the multidimensional feature vector to obtain a target feature vector for characterizing the degree of influence includes: The multidimensional feature vector is normalized to obtain normalized features, and a convolution operation is performed on the normalized features to extract local features of the target. A gating mechanism is used to perform temporal modeling of the target's local features to obtain long-term temporal features related to the air suspension system; A multi-head attention mechanism is used to determine the importance weights of the long-term features, and the long-term features are weighted based on the importance weights to obtain the target weighted features; A global average pooling operation is performed on the target weighted features to obtain the target feature vector.

8. The method according to claim 7, characterized in that, The step of performing a convolution operation on the normalized features to extract local features of the target includes: The normalized features are sequentially subjected to convolution and batch normalization to obtain the first local features; The first local feature is nonlinearly transformed using a nonlinear activation function to obtain the second local feature; The target local features are obtained by performing at least one of the following operations on the second local features: max pooling, batch normalization, convolution, and nonlinear transformation.

9. The method according to claim 7, characterized in that, The step of employing a multi-head attention mechanism to determine the importance weights of the long-term features, and then weighting the long-term features based on these importance weights to obtain the target weighted features, includes: A multi-head attention mechanism is adopted to determine the first importance weight of the long-term feature under each attention head, and the long-term feature is weighted based on the first importance weight corresponding to each attention head to obtain the first weighted feature corresponding to each attention head. A nonlinear transformation is performed on the first weighted features of each attention head to obtain the second weighted features corresponding to each attention head. After performing residual connection between the long-time features and the second weighted features of each attention head, layer normalization is performed to obtain the third weighted features. The target weighted feature is generated based on the third weighted feature.

10. The method according to claim 9, characterized in that, The step of generating the target weighted feature based on the third weighted feature includes: Using the multi-head attention mechanism, the second importance weights of the third weighted feature under multiple attention heads are determined respectively, and the third weighted feature is weighted based on the second importance weights corresponding to the multiple attention heads to obtain the fourth weighted feature corresponding to the multiple attention heads; The fourth weighted features of the plurality of attention heads are subjected to nonlinear transformation to obtain the fifth weighted features corresponding to the plurality of attention heads; After performing residual connection between the third weighted feature and the fifth weighted feature of the multiple attention heads, layer normalization is performed to obtain the target weighted feature.

11. A vehicle control device, characterized in that, include: The acquisition module is used to acquire the vehicle's operating condition information and the road condition information of the road on which the vehicle travels; The determining module is used to determine the air leakage detection result of the air suspension system based on the degree of influence of the operating parameters of at least one component in the air suspension system of the vehicle on the operating condition information and the road condition information; wherein the air leakage detection result is used to indicate the target air leakage location and / or target air leakage type in the at least one component.

12. The apparatus according to claim 11, characterized in that, The operating condition information includes at least one of the following: Vehicle usage status; wherein, the vehicle usage status is used to indicate the load distribution status of the vehicle, and the load distribution status includes at least one of the following: number of occupants, occupant positions, cargo weight, and cargo loading position; Vehicle maintenance status; Fault list; wherein the fault list includes diagnostic codes (DTCs) that have been diagnosed for the vehicle and are associated with the air suspension system, the DTCs being for known fault types; The actual operating information of the air suspension system; Actual operating information of other vehicle components associated with the air suspension system; The environmental information of the environment in which the air suspension system is located.

13. The apparatus according to claim 11, characterized in that, The device further includes: The reporting module is used to report early warning information to the cloud; wherein, the early warning information is used to indicate the target air leak location and / or target air leak type of the air suspension system; the early warning information is used by the cloud to perform: based on the historical operating information of the vehicle, locate the cause of the air leak in the air suspension system, determine the target processing strategy matching the cause of the air leak from multiple air leak handling strategies, and execute the target processing strategy on the vehicle to restore the air suspension system from a leaking state to a non-leaking state.

14. A vehicle, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured as follows: The steps of implementing the method as described in any one of claims 1 to 10.

15. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When executed by a processor, the program instructions implement the steps of the method according to any one of claims 1 to 10.

16. A chip, characterized in that, The chip includes an interface circuit and a processing circuit that are coupled to each other. The interface circuit is used to input or output signals, and the processing circuit is used to implement the method of any one of claims 1 to 10.

17. A computer program product, characterized in that, It includes a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 10.

Images