Vehicle suspension control method, device, equipment, storage medium and program product

Abstract

The present application relates to a kind of vehicle suspension control method, device, equipment, storage medium and program product, relate to vehicle suspension control field.The method comprises: obtaining in-vehicle voice data and vehicle state data, determine driving mode and adjustment parameter according to voice data, and determine correction factor according to vehicle state data and preset rule, again according to driving mode, adjustment parameter and correction factor are operated, and according to the operation result control suspension system.One aspect, user can conveniently adjust suspension system based on voice, reduce the distraction caused by manually switching driving mode when driving, improve safety.On the other hand, it can also be based on fixed driving mode, comprehensive user voice and vehicle state and other multi-source data flexible determination of the adjustment amount of suspension system, so that the adjustment of suspension system can be more in line with actual driving condition and user demand.

Description

Technical Field

[0001] This invention relates to the field of vehicle suspension control, and specifically to a vehicle suspension control method, device, equipment, storage medium, and program product. Background Technology

[0002] The vehicle's suspension system is a crucial component of the vehicle body structure and typically includes elastic elements (such as springs) and shock absorbers. The suspension system supports the vehicle's weight while cushioning impacts transmitted from the road surface to the chassis, reducing vehicle vibration and ensuring a smooth ride.

[0003] Currently, vehicles are equipped with several driving modes (such as off-road mode, sport mode, etc.), each corresponding to a set of basic parameters for the suspension system (such as suspension height, damping, etc.). Switching driving modes can adjust the suspension system, but this method is only suitable for specific terrains and cannot meet the adjustment needs of users in complex road conditions. Furthermore, setting driving modes can easily distract the driver and affect driving safety. Summary of the Invention

[0004] One of the objectives of this invention is to provide a vehicle suspension control method, device, equipment, storage medium, and program product to solve the problem that suspension system adjustments are difficult to meet user needs.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A vehicle suspension control method, the method comprising:

[0007] Acquire in-vehicle voice data and vehicle status data;

[0008] The driving mode and adjustment parameters are determined based on voice data. The adjustment parameters are used to indicate quantitative adjustments to the suspension system.

[0009] The correction factor is determined based on vehicle status data and preset rules;

[0010] The system calculates adjustment parameters and correction factors based on the driving mode and controls the suspension system according to the calculation results.

[0011] Furthermore, the adjustment parameters and correction factors are calculated based on the driving mode, including:

[0012] Obtain basic parameters of the suspension system in driving mode;

[0013] The adjustment parameters, correction factors, and basic parameters are assigned corresponding weight coefficients, and the results are obtained by weighted summation according to the weight coefficients.

[0014] Furthermore, the calculation results include the target suspension height and / or the target damping coefficient. After controlling the suspension system according to the calculation results, the following are also included:

[0015] Obtain the actual parameters of the suspension system, including the actual suspension height and / or the actual damping coefficient;

[0016] Determine whether the deviation between the actual parameters and the calculation result is greater than or equal to a preset threshold. If so, correct the weight coefficient, use the corrected weight coefficient to obtain the calculation result again, and control the suspension system.

[0017] Furthermore, the driving mode and adjustment parameters are determined based on voice data, including:

[0018] Semantic extraction is performed on speech data using a natural language processing model to obtain semantic features that characterize vehicle driving conditions and / or suspension adjustment intentions.

[0019] The semantic features are input into the trained classification model and regression model respectively, and the driving mode output by the classification model and the adjustment parameters output by the regression model are obtained.

[0020] Furthermore, the suspension system includes the suspension itself and the shock absorbers. The regression model's processing of semantic features includes:

[0021] Determine whether the semantic features are related to the suspension height of any driving mode. If they are related, output the default suspension height of the relevant driving mode as the adjustment parameter.

[0022] Determine whether the semantic features are related to the damper damping of any driving mode. If they are related, output the default damping coefficient of the damper in the relevant driving mode as the adjustment parameter.

[0023] Furthermore, correction factors are determined based on vehicle status data and preset rules, including:

[0024] The vehicle status data is matched with preset rules to obtain the matching results. The preset rules include the mapping relationship between the vehicle's force state under different driving conditions and the adjustment amount of the suspension system.

[0025] A correction factor is generated based on the matching results.

[0026] A vehicle suspension control device, comprising:

[0027] The acquisition module is used to acquire in-vehicle voice data and vehicle status data;

[0028] The voice processing module is used to determine the driving mode and adjustment parameters based on voice data. The adjustment parameters are used to indicate quantitative adjustments to the suspension system.

[0029] The correction module is used to determine the correction factor based on vehicle status data and preset rules;

[0030] The control module is used to calculate the adjustment parameters and correction factors according to the driving mode, and control the suspension system according to the calculation results.

[0031] An electronic device includes: a processor, and a memory communicatively connected to the processor;

[0032] The memory stores instructions that the computer executes;

[0033] The processor executes computer-executable instructions stored in memory to implement any of the vehicle suspension control methods described above.

[0034] A computer-readable storage medium includes: computer-executable instructions stored in the computer-readable storage medium, which, when executed by a processor, are used to implement a vehicle suspension control method as described above.

[0035] A computer program product includes a computer program that, when executed by a processor, implements a vehicle suspension control method as described above.

[0036] The beneficial effects of this invention are twofold: First, users can conveniently adjust the suspension system via voice commands, reducing distraction caused by manually switching driving modes and improving safety. Second, based on a fixed driving mode, the adjustment amount of the suspension system can be flexibly determined by integrating multi-source data such as user voice commands and vehicle status, making the suspension system adjustment more in line with actual driving conditions and user needs. Attached Figure Description

[0037] Figure 1 A flowchart illustrating a vehicle suspension control method provided as an exemplary embodiment of the present invention;

[0038] Figure 2 An interactive diagram illustrating normal and secure access provided as an exemplary embodiment of the present invention;

[0039] Figure 3 A schematic diagram of a vehicle suspension control process provided as an exemplary embodiment of the present invention;

[0040] Figure 4 A schematic diagram of a vehicle suspension control device provided for an exemplary embodiment of the present invention;

[0041] Figure 5 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present invention.

[0042] The accompanying drawings have illustrated specific embodiments of the invention, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the invention in any way, but rather to illustrate the concept of the invention to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0043] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0044] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0045] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0046] The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, 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 process, method, product, or apparatus. Without further limitation, the presence of other identical or equivalent elements in the process, method, product, or apparatus that includes elements is not excluded. For example, the use of terms such as "first," "second," etc., to indicate names does not imply any particular order.

[0047] Adjusting the suspension system mainly involves adjusting the suspension height and damping coefficient. Adjusting the suspension height changes the vehicle's ground clearance and center of gravity, while adjusting the damping coefficient changes the vehicle's handling stability. Different road conditions place different demands on the suspension system. For example, rough roads with many potholes and protruding rocks require a higher suspension height to avoid scratching the chassis, while small bumps such as speed bumps require a lower damping coefficient to improve vehicle stability.

[0048] Currently, vehicles offer several driving modes (such as off-road mode and sport mode), and suspension adjustments must be made by setting these modes. For example, off-road mode corresponds to higher suspension height and higher damping, aiming to improve the vehicle's passability on complex terrain; comfort mode uses lower damping and moderate suspension height to enhance ride comfort; and sport mode typically sets higher damping and lower suspension height to improve vehicle handling.

[0049] However, real-world road conditions are complex and varied, and the limited number of driving modes available only covers a portion of driving situations, making it difficult to fully meet users' adjustment needs. Furthermore, switching driving modes via buttons or the vehicle's infotainment system in complex road conditions is not only cumbersome but also requires the driver to keep their eyes on the screen, easily distracting them and affecting driving safety.

[0050] Based on this, a technical concept is proposed that by collecting in-vehicle voice data to perceive user intent, analyzing keywords related to suspension system adjustment in the user's voice, and combining vehicle dynamic data to determine correction factors, the subjective needs of users and objective road conditions can be dynamically balanced, supporting independent quantitative adjustment of various parameters of the suspension system (such as suspension height and damping coefficient).

[0051] The application scenarios described above are only partial examples. Those skilled in the art can expand the applications according to specific needs and scenarios, and the embodiments of the present invention do not impose specific limitations in this regard. The method according to an exemplary embodiment of the present invention will now be described with reference to the accompanying drawings.

[0052] Figure 1 This is a flowchart illustrating a vehicle suspension control method provided as an exemplary embodiment of the present invention. Figure 1 As shown, the method may include:

[0053] Step S101: Obtain in-vehicle voice data and vehicle status data.

[0054] The vehicle status data may include driving mode, vehicle speed, steering angle, suspension height, pitch angle, roll angle, and satellite navigation information.

[0055] For example, a high-sensitivity microphone can accurately capture voice signals in the in-vehicle environment. After noise reduction processing, the voice signals are recognized by an ASR (Automatic Speech Recognition) engine, which parses the voice content such as conversations, voice commands, and navigation announcements of people in the vehicle into text data.

[0056] Step S102: Determine the driving mode and adjustment parameters based on the voice data.

[0057] Among them, the adjustment parameters are used to indicate the quantitative adjustment of the suspension system.

[0058] In this embodiment of the invention, the driving mode can be a driving mode provided by the vehicle itself, such as off-road mode, sport mode, etc. The adjustment parameters can include multiple dimensions, corresponding to suspension system-related indicators such as suspension height and damping coefficient. For example, the adjustment parameters can be [H:10, C:0.15], where H can represent suspension height and C can represent damping coefficient. This adjustment parameter can indicate that the overall suspension height is raised by 10mm and the damping coefficient is increased by 15%.

[0059] In some possible implementations, the vehicle's suspension height and damping can support localized adjustment. Accordingly, the adjustment parameters can include adjustments to the suspension height or damping of a specific portion of the vehicle. For example, the vehicle's suspension can be divided into four parts: the left side of the front axle, the right side of the front axle, the left side of the rear axle, and the right side of the rear axle. The adjustment parameters can be adjustments to the suspension height corresponding to one or more of these parts.

[0060] To determine the driving mode and adjustment parameters, a pre-trained neural network model based on deep learning can be used. The acquired voice data is input into the model, which then perceives the user's intention to adjust the suspension system and translates this into a driving mode setting command and quantitative adjustment parameters for the suspension system. If the user's intention cannot be determined from the voice, the model can output the default settings. For example, if the user's voice does not indicate a preference for a specific driving mode, the model output can be to keep the current driving mode unchanged. Alternatively, if the user's voice does not indicate an intention to adjust the suspension height, the model outputs a suspension height adjustment parameter H of 0, indicating that the suspension height remains unchanged.

[0061] Step S103: Determine the correction factor based on vehicle status data and preset rules.

[0062] The preset rules may include the mapping relationship between the force state of the vehicle under different driving conditions and the adjustment amount of the suspension system, which can be obtained through pre-test calibration.

[0063] After acquiring vehicle status data such as speed, steering angle, and pitch angle, the data is matched with preset rules to obtain a matching result, which is then used to generate a correction factor. When processing this data, the vehicle's dynamic balance and stability are comprehensively considered. A suitable adjustment amount (e.g., raising the suspension height by 5mm) is found as the correction factor according to the mapping relationship in the preset rules to ensure that the vehicle experiences relatively balanced forces in all directions.

[0064] For example, based on preset rules, the system can determine whether the vehicle is currently in a turning condition based on its speed and steering wheel angle. Simultaneously, it combines navigation information to predict the geometric curvature of the road ahead and compares this prediction with preset thresholds. A correction factor is then calculated based on this comprehensive analysis. For instance, if the current speed is 90 km / h, which is greater than the preset threshold, the system lowers the suspension height by 10 mm and increases the damping coefficient by 20% to ensure vehicle stability. If the current steering wheel angle is less than the preset threshold, the correction parameters corresponding to the steering wheel angle signal source are a 0 mm change in suspension height and a 0% change in damping. When GPS navigation information indicates an upcoming left turn, the correction parameters corresponding to the GPS signal source are a 15% increase in damping coefficient and a 5 mm increase in suspension height on the right side of the front axle and the right side of the rear axle. Therefore, the final determined correction factor is: a 35% increase in damping coefficient, a 10 mm decrease in suspension height on the left side of the front axle and the left side of the rear axle, and a 5 mm decrease in suspension height on the right side of the front axle and the right side of the rear axle. It should be noted that this example is only one possible implementation of the present invention. In actual working conditions, the correction factor can be determined comprehensively based on multiple vehicle state data such as vehicle speed, steering angle and pitch angle, as well as preset rules.

[0065] Step S104: Calculate the adjustment parameters and correction factors according to the driving mode, and control the suspension system according to the calculation results.

[0066] In this embodiment of the invention, the basic parameters of the suspension system under the driving mode determined by the vehicle manufacturing information and step S102 can be queried first. Then, the basic parameters, adjustment parameters and correction factors are uniformly formatted and weighted and summed. The summation result is used as a control parameter to set the suspension height and damping coefficient of the suspension system.

[0067] Among these, basic parameters can refer to the suspension system parameters of a vehicle in a specific driving mode. For example, if a vehicle's suspension height is 150mm in Sport mode, then 150mm is a basic parameter.

[0068] In the above embodiments, by acquiring in-vehicle voice data and vehicle status data, the driving mode and adjustment parameters can be determined based on the voice data, and a correction factor can be determined based on the vehicle status data and preset rules. Then, the adjustment parameters and correction factor are calculated based on the driving mode, and the suspension system is controlled according to the calculation results. On the one hand, users can conveniently adjust the suspension system based on voice commands, reducing distraction caused by manually switching driving modes while driving and improving safety. On the other hand, based on a fixed driving mode, the adjustment amount of the suspension system can be flexibly determined by comprehensively considering multi-source data such as user voice and vehicle status, making the adjustment of the suspension system more in line with actual driving conditions and user needs.

[0069] In one embodiment, such as Figure 2 As shown, determining the driving mode and adjustment parameters based on voice data can include:

[0070] Semantic extraction is performed on speech data using a natural language processing model to obtain semantic features that characterize vehicle driving conditions and / or suspension adjustment intentions. These semantic features are then input into a pre-trained classification model and a regression model to obtain the driving mode output by the classification model and the adjustment parameters output by the regression model.

[0071] Natural Language Processing (NLP) models, also known as NLP models, are systems that use algorithms and machine learning techniques to enable computers to understand, interpret, and generate human language. In this embodiment of the invention, the NLP model can employ DistilXLM-R (an open-source multilingual processing model) pre-trained language model, which can handle not only languages ​​from different countries but also regional dialects.

[0072] For example, after acquiring in-vehicle voice data, it can be converted into text data and input into a pre-trained DistilXLM-R. First, the input text is segmented and embedded. The word embedding results are input into DistilXLM-R, which understands and semantically analyzes the input text, accurately identifying semantic features in the dialogue, such as features indicating vehicle driving conditions like "bumps" and "turning," and features indicating the user's intention to adjust the suspension system like "lower or raise the suspension" and "increase or decrease the damping." After the input information completes forward propagation through DistilXLM-R, it can output a latent state representation containing these semantic features.

[0073] Following DistilXLM-R, a classification model can be added to determine whether the user needs to switch to another driving mode. For example, the classification model could use a fully connected network as follows:

[0074] (1) Input layer: used to receive the hidden state output by DistilXLM-R, the dimension of the hidden state is 768.

[0075] (2) Hidden Layers: ReLU activation function is used. The first hidden layer contains 512 neurons; the input of this layer is a 768-dimensional hidden state, and the output is a 512-dimensional feature representation. The second hidden layer contains 128 neurons; the input of this layer is the output of the first hidden layer, and the output is a 128-dimensional feature representation. The third hidden layer contains 64 neurons; the input of this layer is the output of the second hidden layer, and the output is a 64-dimensional feature representation.

[0076] (3) Output layer: Four neurons are set up (representing the four states of "no switching", "comfort", "sport" and "off-road" respectively), and the softmax activation function is used to output the probability distribution of each mode. Among them, "no switching" means keeping the current driving mode unchanged, "comfort" means switching the driving mode to comfort mode, "sport" means switching the driving mode to sport mode, and "off-road" means switching the driving mode to off-road mode.

[0077] Following DistilXLM-R, a regression model can be added to identify and output adjustment parameters representing the user's adjustment needs for the suspension system. For example, the structure of the regression model may include:

[0078] (1) Input layer: Receives the hidden state output by DistilXLM-R, and the dimension of the hidden state is 768.

[0079] (2) Hidden Layers: Recurrent neural network units are used to capture the dependencies between sequences. The first layer contains 256 neurons; the input to this layer is a 768-dimensional hidden state, and the output is a 256-dimensional feature representation. The second layer contains 128 neurons; the input to this layer is the output of the first hidden layer, and the output is a 128-dimensional feature representation. All hidden layers use linear activation functions.

[0080] (3) Output layer: Contains 8 neurons (representing the suspension height and damping coefficient of "left front / right front / left rear / right rear"), used to output the adjustment parameters of suspension height and damping. "Left front" can refer to the left side of the front axle of the vehicle, and "left rear" can refer to the left side of the rear axle.

[0081] The natural language processing model described above can identify and extract semantic features from user speech related to vehicle operating conditions and user intentions to adjust the suspension system. The extracted semantic features can be input into the trained classification model and regression model, respectively. The classification model can output the driving mode representing the user's intention, and the regression model can output the specific adjustment parameters representing the user's intention (such as raising the height of the left front axle suspension by 5mm).

[0082] In the above embodiments, natural language processing models, classification models, and regression models can be used to perceive the user's intention to adjust the suspension system based on in-vehicle voice commands. These models can handle long dialogue commands, multilingual and unstructured commands, and have fuzzy command and sentiment analysis capabilities, thereby improving the intelligence of suspension adjustment.

[0083] Currently, suspension systems generally use driving mode switching as the standard control method for adjusting suspension height and damping. For example, off-road mode corresponds to higher suspension height and higher damping, comfort mode corresponds to lower damping and moderate suspension height, and sport mode corresponds to higher damping and lower suspension height. This method binds driving mode to suspension height adjustment, which has significant limitations. For example, on gravel roads with varying elevations, a higher suspension can prevent the chassis from scraping, so off-road mode must be selected. However, the high damping in off-road mode reduces the vehicle's grip, making it difficult to simultaneously meet the needs of adjusting suspension height and damping by switching driving modes.

[0084] This invention provides a suspension control method that decouples suspension height adjustment, damping adjustment, and driving mode. Taking a vehicle offering three basic driving modes—off-road mode, comfort mode, and sport mode—as an example, in traditional vehicle suspension control, once the high suspension of off-road mode is selected, only the high damping of off-road mode can be selected simultaneously. However, the regression model in this invention can identify the user's voice requests for adjusting the default parameters of different driving modes and output the corresponding adjustment parameters.

[0085] Optionally, the suspension system includes suspension and shock absorbers, and the regression model's processing of semantic features may include:

[0086] Determine whether the semantic features are related to the suspension height of any driving mode. If they are related, output the default suspension height of the relevant driving mode as the adjustment parameter. Determine whether the semantic features are related to the shock absorber damping of any driving mode. If they are related, output the default damping coefficient of the shock absorber in the relevant driving mode as the adjustment parameter.

[0087] For example, the acquired in-vehicle voice includes "suspension height in off-road mode and damping coefficient in comfort mode". After processing by NLP and regression models, the adjustment parameters output by the regression model can include the suspension height in off-road mode and the damping coefficient in comfort mode.

[0088] In the above embodiments, the natural speech processing model and regression model can not only process long voice commands from users, but also decouple suspension height adjustment, damping adjustment and driving mode, and flexibly match suspension height and damping coefficient to adapt to the needs of different road conditions.

[0089] In one embodiment, the calculation of adjustment parameters and correction factors based on the driving mode includes:

[0090] Obtain the basic parameters of the suspension system in driving mode; assign corresponding weight coefficients to the adjustment parameters, correction factors and basic parameters respectively, and perform weighted summation according to the weight coefficients to obtain the calculation result.

[0091] After determining the driving mode and adjustment parameters based on voice data, basic parameters such as suspension height and damping coefficient of the vehicle in this driving mode can be obtained by querying vehicle configuration, etc. Then, the adjustment parameters, correction factors and basic parameters are preprocessed, and the preprocessed parameters are weighted and summed according to the corresponding weight coefficients to obtain the calculation result as the final control parameters of the suspension system.

[0092] Preprocessing may include aligning data according to timestamps and preset data formats, as well as rolling back abnormal states. When rolling back abnormal states, the adjustment parameters, correction factors, and basic parameters are first validated to check if the data values ​​are within the boundary range. If they are out of range, the boundary values ​​are used. If the adjustment parameters exceed the mechanical travel, no rollback is required. If any data item has timed out and not been updated, the previous valid value is automatically loaded.

[0093] The preset data format refers to a specific data structure for adjusting the suspension system. For example, the data format could be [H1,H2,H3,H4,C1,C2,C3,C4], where H1, H2, H3, and H4 represent the suspension heights at the left front (left side of the front axle), right front, left rear, and right rear, respectively, and C1, C2, C3, and C4 represent the damping coefficients at these four locations. If data is missing compared to this data format, the missing parts can be replaced with 0. For example, if the adjustment parameters only have values ​​at H1 and C1, and H2, H3, H4, C2, C3, and C4 have no data, then the adjustment parameters H2, H3, H4, C2, C3, and C4 would all be 0.

[0094] For example, the data format for adjusting the suspension system can be represented as the following matrix:

[0095]

[0096] Where S represents the final control parameter of the suspension system, i.e., the result of the weighted calculation. ΔH represents the adjustment amount of the suspension height, and ΔC represents the adjustment amount of the damping coefficient. The subscripts FL, FR, RL, and RR represent the four parts: left front, right front, left rear, and right rear, respectively. FL This can represent the adjustment amount of the suspension height on the left side of the vehicle's front axle, ΔC. FR This can represent the adjustment amount to the damping coefficient on the right side of the vehicle's front axle. For example, ΔH FL 10mm means that the height of the left side suspension of the front axle of the vehicle will be raised by 10mm.

[0097] For example, when performing weighted calculations, the adjustment parameters determined based on voice data and the basic parameters corresponding to the driving mode can be added together first, and the result can be denoted as P. Then, the correction factor is denoted as Q, and the final control parameters S of the suspension system are calculated using a matrix weighting method according to preset weights. This process can be expressed as S = α*P + β*Q, where α and β are the weight coefficients of P and Q, respectively, and the sum of α and β is 1. If the matrix data format described above is used, then S can be expressed as:

[0098]

[0099] Among them, H FL This indicates the left front basic suspension height, ΔH, corresponding to the driving mode determined based on voice data. UFL This represents the adjustment amount, ΔH, of the left front suspension height among the adjustment parameters determined based on voice data. MFL This indicates the adjustment amount of the left front suspension height in the correction factor.

[0100] By adjusting the values ​​of α and β in the above manner, the user's subjective adjustment intentions and the objective state of the vehicle can be balanced, ensuring that the final control parameters meet both the driver's personalized needs and the actual driving conditions.

[0101] In one embodiment, the calculation result includes a target suspension height and / or a target damping coefficient, and after controlling the suspension system according to the calculation result, it further includes:

[0102] Obtain the actual parameters of the suspension system; determine whether the deviation between the actual parameters and the calculation results is greater than or equal to a preset threshold. If so, correct the weight coefficients, use the corrected weight coefficients to obtain the calculation results again, and control the suspension system.

[0103] The actual parameters include the actual suspension height and / or the actual damping coefficient.

[0104] In this embodiment, the target settings for the suspension system (i.e., target suspension height and target damping coefficient) can be obtained based on the current parameter values ​​of the suspension system and the calculated adjustment amount. For example, if the current suspension height is 150mm, and the adjustment amount for the suspension height is 10mm according to the weighted summation above, then the target suspension height is 160mm.

[0105] After adjusting and controlling the suspension system based on the calculation results, the parameter execution status can be judged by the height sensor and the feedback of the return current. It is determined whether correction is needed based on the deviation between the actual suspension height and the target suspension height, as well as the deviation between the actual damping coefficient and the target damping coefficient. If correction is needed, the weighting coefficients are corrected, the weighted calculation is recalculated, and the suspension system is adjusted and controlled.

[0106] For example, the process of correcting the weighting coefficients can be expressed as the following formulas (1) and (2):

[0107] e = (H Tar -H Act )+(C Tar -C Act (1)

[0108] β′=β+K1*e+K2∫edt (2)

[0109] Among them, H Tar H represents the actual suspension height. Act Indicates the target suspension height, C Tar C represents the actual damping coefficient. Act This represents the target damping coefficient. e represents the deviation between the actual parameter and the target, K1 is the preset threshold (which can be 5%), and K2 is the calculation period (which can be 0.01 seconds).

[0110] To illustrate the application of the vehicle suspension control method in this invention, a specific vehicle suspension control system is provided as an example. This system may include a voice acquisition and parsing module, a natural language understanding module, a vehicle dynamic perception module, a parameter mapping module, and actuators. These modules and mechanisms can work together to implement the vehicle suspension control method in the above embodiments.

[0111] Figure 3 This is a schematic diagram illustrating the operation of a vehicle suspension control system, provided as an example of an embodiment of the present invention.

[0112] like Figure 3 As shown, the voice acquisition and parsing module can accurately capture voice signals such as driver's voice, passenger's voice, and navigation broadcast voice in the in-vehicle environment. The acquired voice data is then denoised to reduce interference from engine and tire noise. The denoised audio data is then parsed by the ASR engine.

[0113] The natural language understanding module can receive parsed text content, analyze and understand it, perceive user intent, and output driving mode and adjustment parameters (H and C represent the values ​​of suspension height and damping coefficient, respectively, and ΔH and ΔC represent the adjustment amount).

[0114] The vehicle dynamic perception module can collect data on vehicle operation in real time, including but not limited to driving mode, vehicle speed, steering angle, suspension height, pitch angle, roll angle, and GPS navigation. When processing this data, the module comprehensively considers the vehicle's dynamic balance and stability to ensure that the vehicle experiences relatively balanced forces in all directions. The collected data will be analyzed and processed in real time according to preset rules, and finally, a correction factor will be output.

[0115] The parameter mapping module can perform weighted calculations on adjustment parameters, correction factors, and basic parameters, and output the calculation results (i.e., the final control parameter S) to the actuator.

[0116] The actuator can precisely control each component of the suspension system based on the final control parameter S, and achieve suspension adjustment through meticulous management of the opening and closing of the oil circuit valve body, the magnitude and direction of the shock absorber current and the hydraulic pump working current.

[0117] For example, regarding suspension height adjustment: based on the suspension height adjustment amount in matrix S and the current actual suspension height, the system determines which cylinder needs adjustment. Then, the corresponding solenoid valve in the hydraulic circuit is opened to ensure that hydraulic fluid flows accurately to the cylinder requiring adjustment. After the hydraulic circuit is connected, the system monitors and adjusts the hydraulic pump current in real time to precisely regulate the motor speed; simultaneously, by changing the voltage polarity of the pump motor, the forward and reverse rotation of the motor can be controlled, thereby achieving the raising or lowering adjustment of the cylinder, ultimately adjusting the suspension height to the target value.

[0118] For damper adjustment: Based on the damping coefficient adjustment in matrix S, the input current of the electronic control unit of the magnetorheological damper is precisely controlled. The system maps the current magnitude corresponding to the target damping based on the relationship curve between damping and current (a larger target damping usually requires a larger current, and vice versa), and accurately transmits this current to the electromagnetic coil of the corresponding damper. The magnetic field strength generated by the electromagnetic coil is proportional to the current magnitude, thus affecting the viscosity change of the magnetorheological fluid inside the damper. Different currents correspond to different fluid viscosities, and different fluid viscosities determine different damping effects. In this way, the damping of the damper can be flexibly adjusted.

[0119] The following provides several specific embodiments based on the aforementioned vehicle suspension control system to demonstrate its application in specific scenarios.

[0120] Example 1: In the scenario of switching basic driving modes via voice commands, the vehicle suspension control system of this invention allows users to switch driving modes via voice commands without manually operating the vehicle's infotainment system or buttons, thereby achieving efficient interaction between the user and the vehicle's suspension system.

[0121] In this scenario, the user expresses their needs via voice, such as "switch from the current mode to off-road mode." The voice acquisition and parsing module captures this dialogue and parses it into text. The natural language understanding module segments and embeds the text "switch from the current mode to off-road mode" and then inputs it into DistilXLM-R. DistilXLM-R deeply understands this content and outputs the hidden states to the classification and regression models. The classification model outputs "off-road mode." In this scenario, the user did not express a specific adjustment need, and the regression model outputs a zero-matrix adjustment parameter matrix.

[0122] The vehicle dynamic perception module collects road condition data and generates a correction factor matrix in real time. If the vehicle is running smoothly and there is no intense driving, the collected data are all within the preset algorithm threshold. Under this condition, the correction factor is a matrix close to all zero. If the collected road condition is (2) an unstable driving condition, such as a large-angle left turn, the correction factor Q is calculated according to the preset algorithm (assuming that the right front / right rear height increases by 10mm, and the left front / left rear / right front / right rear damping increases by 90%). The specific representation of Q is as follows:

[0123]

[0124] Based on the driving mode output by the natural language understanding module, the parameter mapping module determines the height and damping corresponding to the basic parameters of the mode as 25mm and 70% for the front axle and 30mm and 75% for the rear axle. Then, the final control parameters can be calculated according to the preset weighting coefficients.

[0125] Example 2: A scenario where suspension adjustment is based on ambiguous semantics and emotional states in speech. The vehicle suspension control system of this invention allows users to express their suspension adjustment needs using ambiguous semantics, such as "drive more steadily," "turn," or "this road is too bumpy." These commands do not explicitly provide adjustment parameters, but the vehicle suspension control system can understand these ambiguous semantics and translate them into corresponding adjustment actions. Alternatively, it can express suspension adjustment needs based on emotional words, such as "Be careful!" or "That's scary!" These emotional expressions reflect a certain degree of danger in the driving scenario, requiring the vehicle suspension control system to react quickly to enhance vehicle stability.

[0126] In this scenario, when the user doesn't actively switch driving modes via voice command, they might utter vague semantics like "Caution: Turning" or emotional phrases like "That's terrifying!" The voice acquisition and parsing module can capture these vague semantics or emotional expressions and parse the dialogue into natural language text. The natural language understanding module can understand the user's intentions or emotional state. For example, in the case of the vague semantic expression "Caution: Turning," the goal is to reduce body roll. After understanding the user's adjustment needs, this module increases the damping parameters of the front and rear axles by 50% and 60%, respectively. In the case of "That's terrifying!", the goal is to enhance shock absorber damping and suspension support. The system increases the damping of the front and rear axles by 80% and 90%, respectively, while simultaneously raising the suspension height by 10mm. Finally, these adjustment parameters are output through a matrix. The vehicle dynamic perception module can collect road condition data and generate a correction factor matrix for the current situation.

[0127] In real-world driving conditions, the ambiguous semantic words and emotions expressed in user speech are more diverse. By pre-collecting ambiguous semantic and emotional words from common driving conditions and mapping them to suspension system adjustment parameters, and then using the collected results to train a regression model in the natural language understanding module, the model can be equipped with the ability to recognize ambiguous semantics and emotions, and output the correct adjustment parameters. This method, from ambiguous semantic or emotional recognition to suspension control, can automatically adjust the suspension system based on the user's ambiguous semantic commands or changes in emotional state, combined with real-time vehicle operating data, even without the user actively switching driving modes, thus responding promptly to potential risks.

[0128] Figure 4 This is a schematic diagram of a vehicle suspension control device provided as an exemplary embodiment of the present invention. Figure 4 As shown, the vehicle suspension control device 400 may include:

[0129] Module 401 is used to acquire in-vehicle voice data and vehicle status data;

[0130] The voice processing module 402 is used to determine the driving mode and adjustment parameters based on voice data. The adjustment parameters are used to indicate quantitative adjustments to the suspension system.

[0131] Correction module 403 is used to determine correction factors based on vehicle status data and preset rules;

[0132] The control module 404 is used to calculate the adjustment parameters and correction factors according to the driving mode, and control the suspension system according to the calculation results.

[0133] In some possible implementations, the control module 404 can also be used to: obtain the basic parameters of the suspension system in driving mode; assign corresponding weight coefficients to the adjustment parameters, correction factors and basic parameters respectively, and perform weighted summation according to the weight coefficients to obtain the calculation result.

[0134] In some possible implementations, the control module 404 can also be used to: obtain the actual parameters of the suspension system, including the actual suspension height and / or the actual damping coefficient; determine whether the deviation between the actual parameters and the calculation result is greater than or equal to a preset threshold; if so, correct the weighting coefficient, use the corrected weighting coefficient to obtain the calculation result again, and control the suspension system.

[0135] In some possible implementations, the speech processing module 402 can also be used to: extract semantics from speech data using a natural language processing model to obtain semantic features that characterize the vehicle's driving conditions and / or suspension adjustment intentions; input the semantic features into a trained classification model and a regression model respectively to obtain the driving mode output by the classification model and the adjustment parameters output by the regression model.

[0136] In some possible implementations, the voice processing module 402 can also be used to: determine whether the semantic features are related to the suspension height of any driving mode; if so, output the default suspension height of the relevant driving mode as an adjustment parameter; determine whether the semantic features are related to the shock absorber damping of any driving mode; if so, output the default damping coefficient of the shock absorber in the relevant driving mode as an adjustment parameter.

[0137] In some possible implementations, the correction module 403 can also be used to: match vehicle state data with preset rules to obtain matching results, the preset rules including the mapping relationship between the force state of the vehicle under different driving conditions and the adjustment amount of the suspension system; and generate correction factors based on the matching results.

[0138] The vehicle suspension control device provided in this embodiment is used to execute the technical solution in any of the foregoing method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0139] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present invention can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0140] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of the present invention can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0141] Figure 5 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present invention. For example... Figure 5 As shown, the electronic device 50 includes:

[0142] Processor 51, memory 52, and communication interface 53;

[0143] The memory 52 is used to store the executable instructions of the processor 51; the executable instructions can be instructions that the computer can execute.

[0144] The processor 51 is configured to execute the technical solutions in any of the foregoing method embodiments by executing executable instructions.

[0145] Optionally, the memory 52 can be either standalone or integrated with the processor 51.

[0146] Optionally, when the memory 52 is a device independent of the processor 51, the electronic device 50 may further include:

[0147] Bus 54, memory 52 and communication interface 53 are connected to processor 51 through bus 54 and complete communication with each other. Communication interface 53 is used to communicate with other devices.

[0148] Optionally, the communication interface 53 can be implemented using a transceiver. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write databases, and read-only databases). The memory may include random access memory (RAM) and may also include non-volatile memory, such as at least one disk drive.

[0149] Bus 54 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one line is used in the diagram, but this does not imply that there is only one bus or one type of bus.

[0150] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0151] The electronic device is used to execute the technical solutions in any of the foregoing method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0152] This invention also provides a readable storage medium, which can be a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the technical solution provided in any of the foregoing method embodiments.

[0153] This invention also provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the technical solutions provided in any of the foregoing method embodiments.

[0154] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0155] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0156] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0157] The above embodiments are merely preferred embodiments provided to fully illustrate the present invention, and the scope of protection of the present invention is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on the present invention are all within the scope of protection of the present invention.

Claims

1. A vehicle suspension control method, characterized in that, include: Acquire in-vehicle voice data and vehicle status data; The driving mode and adjustment parameters are determined based on the voice data, and the adjustment parameters are used to indicate quantitative adjustments to the suspension system; The correction factor is determined based on the vehicle status data and preset rules. The preset rules include the mapping relationship between the vehicle's force state under different driving conditions and the adjustment amount of the suspension system. Determine the basic parameters of the suspension system in the driving mode; The basic parameters and the adjustment parameters are added together to form the first parameter, and the correction factor is used as the second parameter. Corresponding weight coefficients are assigned to the first parameter and the second parameter respectively, and the first parameter and the second parameter are weighted and summed according to the weight coefficients to obtain the calculation result. The suspension system is controlled according to the calculation result. The calculation result includes the target suspension height and / or the target damping coefficient. If the deviation between the actual parameters of the suspension system and the calculation result is greater than or equal to a preset threshold, the weight coefficient is corrected according to the calculation cycle, and the calculation result is obtained again using the corrected weight coefficient to control the suspension system. The actual parameters include the actual suspension height and / or the actual damping coefficient.

2. The vehicle suspension control method according to claim 1, characterized in that, The step of determining the driving mode and adjustment parameters based on the voice data includes: Semantic extraction is performed on the speech data using a natural language processing model to obtain semantic features that characterize the vehicle's driving conditions and / or suspension adjustment intentions. The semantic features are input into the trained classification model and regression model respectively to obtain the driving mode output by the classification model and the adjustment parameters output by the regression model.

3. The vehicle suspension control method according to claim 2, characterized in that, The suspension system includes a suspension and shock absorbers, and the regression model's processing of the semantic features includes: Determine whether the semantic feature is related to the suspension height of any driving mode. If it is related, output the default suspension height of the relevant driving mode as the adjustment parameter. Determine whether the semantic feature is related to the shock absorber damping of any driving mode. If it is related, output the default damping coefficient of the shock absorber in the relevant driving mode as the adjustment parameter.

4. The vehicle suspension control method according to claim 1, characterized in that, The step of determining the correction factor based on the vehicle status data and preset rules includes: The vehicle status data is matched with preset rules to obtain the matching result; A correction factor is generated based on the matching results.

5. A vehicle suspension control device, characterized in that, include: The acquisition module is used to acquire in-vehicle voice data and vehicle status data; The voice processing module is used to determine the driving mode and adjustment parameters based on the voice data, wherein the adjustment parameters are used to indicate quantitative adjustments to the suspension system; The correction module is used to determine a correction factor based on the vehicle status data and preset rules. The preset rules include the mapping relationship between the force state of the vehicle under different driving conditions and the adjustment amount of the suspension system. The control module is used to determine the basic parameters of the suspension system under the driving mode; add the basic parameters and the adjustment parameters to obtain a first parameter, use the correction factor as a second parameter, assign corresponding weight coefficients to the first parameter and the second parameter respectively, and perform a weighted summation of the first parameter and the second parameter according to the weight coefficients to obtain a calculation result, and control the suspension system according to the calculation result; the calculation result includes a target suspension height and / or a target damping coefficient; If the deviation between the actual parameters of the suspension system and the calculation result is greater than or equal to a preset threshold, the weight coefficient is corrected according to the calculation cycle, and the calculation result is obtained again using the corrected weight coefficient to control the suspension system. The actual parameters include the actual suspension height and / or the actual damping coefficient.

6. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 4.

8. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

Images