Suspension leveling control method, device, equipment and computer readable storage medium

Abstract

The application relates to a suspension leveling control method, device and equipment and a computer readable storage medium, the suspension leveling control method comprising: inputting a height adjustment level value, a vehicle body height value, a vehicle acceleration value and a vehicle speed value of a current vehicle acquired in real time into a trained neural network model, and outputting a target height level; and controlling the suspension to adjust the current vehicle body height according to the target height level. The neural network model has the advantages of self-learning, automatic optimization and good fault tolerance, can automatically learn the internal characteristics of input data, does not require manual design of a feature extraction algorithm, can continuously adjust the weight of the neural network model in the network training process, so that the neural network model has higher efficiency and accuracy when running, can output optimal target heights of multiple sections, greatly improves the comfort of passengers, and solves the problem that, in a traditional mode, a driver adjusts the suspension height level through a central control screen, and the suspension height cannot be adjusted in real time.

Description

Technical Field

[0001] This application relates to the field of vehicle control, specifically to suspension leveling control methods, devices, equipment, and computer-readable storage media. Background Technology

[0002] With the development of technology, people are paying more and more attention to the comfort of their vehicles. Air suspension can adjust the vehicle height and suspension stiffness based on information such as vehicle speed and suspension travel, thereby providing better ride comfort. Air suspension uses air springs, shock absorbers, and other hardware to adjust the vehicle height and suspension stiffness, providing a smooth ride and improving vehicle stability. The driver can adjust the suspension height level via the central control screen to adapt to different road surfaces.

[0003] In related technologies, drivers can adjust the suspension height using the central control screen to adapt to different road surfaces. However, when driving on special road conditions, such as continuous speed bumps, uneven surfaces, or uphill / downhill sections, manually adjusting the suspension height via the central control screen cannot meet real-time requirements, significantly reducing passenger comfort. Therefore, how to achieve real-time suspension height adjustment and solve the real-time adjustment problem is an urgent issue to be addressed. Summary of the Invention

[0004] This application provides a suspension leveling control method, device, equipment, and computer-readable storage medium, which can solve the technical problem in related technologies where the driver can adjust the suspension height level through the central control screen, but the suspension height cannot be adjusted in real time.

[0005] In a first aspect, embodiments of this application provide a suspension leveling control method, the suspension leveling control method comprising:

[0006] The real-time acquired vehicle height adjustment level, vehicle height, vehicle acceleration, and vehicle speed values ​​are input into the trained neural network model, which outputs the target height level.

[0007] The suspension is adjusted to control the current vehicle height based on the target height level.

[0008] In conjunction with the first aspect, in one implementation, the step of inputting the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value, and vehicle speed value into a trained neural network model, and outputting the target height level, includes:

[0009] The real-time data, including the vehicle's current height adjustment level, vehicle height, vehicle acceleration, vehicle speed, suspension air pump temperature, and suspension air tank pressure, are input into the neural network model to output the target height level.

[0010] In conjunction with the first aspect, in one implementation, the step of inputting the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value, and vehicle speed value into a trained neural network model, and outputting the target height level, includes:

[0011] The real-time values ​​of the vehicle's height adjustment level, vehicle height, vehicle acceleration, and vehicle speed are input into the neural network model.

[0012] The particle swarm optimization algorithm is selected to optimize the weights and thresholds of the neural network model, so that the neural network model outputs the target height level.

[0013] In conjunction with the first aspect, in one implementation, before inputting the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value, and vehicle speed value into the trained neural network model and outputting the target height level, the method further includes:

[0014] Collect multiple sets of vehicle height, acceleration, and speed values ​​while driving on special road surfaces;

[0015] Multiple sets of vehicle height, vehicle acceleration, and vehicle speed values ​​are grouped, numbered, and normalized to obtain normalized data.

[0016] The normalized data is imported into the neural network model to train the neural network model, resulting in a trained neural network model.

[0017] In conjunction with the first aspect, in one implementation, the step of adjusting the current vehicle height by controlling the suspension according to the target height level includes:

[0018] If the neural network model calculates a new target height level during the height adjustment process, the adjustment will be made using the latest target height level.

[0019] In conjunction with the first aspect, in one implementation, before inputting the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value, and vehicle speed value into the trained neural network model and outputting the target height level, the method further includes:

[0020] The vehicle's current height is monitored in real time using four height sensors, which are installed around the vehicle body.

[0021] The controller determines whether the vehicle needs body adjustment and confirms the current vehicle height adjustment level based on the difference between the values ​​from the four height sensors and the target height value. If body height adjustment is required, the controller proceeds to the next step; otherwise, it returns to the previous step.

[0022] In conjunction with the first aspect, in one implementation, the step of adjusting the current vehicle height by controlling the suspension according to the target height level includes:

[0023] Determine whether the current vehicle requires a Class I height adjustment;

[0024] If so, adjust the vehicle height by controlling the suspension air pump and air tank;

[0025] Otherwise, use the gas storage tank for Class II height adjustment;

[0026] Among them, the vehicle height is divided into several Class I height levels, and the Class I height levels are further divided into several Class II height levels.

[0027] Secondly, embodiments of this application provide a suspension leveling control device, the suspension leveling control device comprising:

[0028] The target height level calculation module is used to input the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value and vehicle speed value into the trained neural network model, and output the target height level;

[0029] A controller is used to control the suspension to adjust the current vehicle height according to the target height level.

[0030] Thirdly, embodiments of this application provide a suspension leveling control device, which includes a processor, a memory, and a suspension leveling control program stored in the memory and executable by the processor. When the suspension leveling control program is executed by the processor, it implements the steps of the suspension leveling control method as described in some of the above embodiments.

[0031] Fourthly, embodiments of this application provide a computer-readable storage medium storing a suspension leveling control program, wherein when the suspension leveling control program is executed by a processor, it implements the steps of the suspension leveling control method as described in some of the above embodiments.

[0032] The beneficial effects of the technical solutions provided in this application include:

[0033] The system can input real-time data on the vehicle's current height adjustment level, vehicle height, acceleration, and speed into a neural network model. Based on this model, a target height level is output, and the air suspension is adjusted accordingly to adjust the vehicle's height. The neural network model boasts advantages such as self-learning, automatic optimization, and high fault tolerance. It can automatically learn the inherent characteristics of the input data without requiring manual feature extraction algorithms. During network training, it continuously adjusts its weights, resulting in higher efficiency and accuracy in outputting the optimal target height for multiple road segments. This significantly improves passenger comfort and solves the problem of real-time suspension height adjustment via the central control screen, a problem inherent in traditional methods. Attached Figure Description

[0034] Figure 1 This is a flowchart illustrating an embodiment of the suspension leveling control method of this application;

[0035] Figure 2 This is a schematic diagram of a neural network model;

[0036] Figure 3 Flowchart for optimizing the neural network model for the particle swarm optimization algorithm;

[0037] Figure 4 This is a flowchart illustrating another embodiment of the suspension leveling control method of this application;

[0038] Figure 5 This is a schematic diagram of the hardware structure of the suspension leveling control device involved in the embodiments of this application. Detailed Implementation

[0039] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0041] In a first aspect, embodiments of this application provide a suspension leveling control method.

[0042] In one embodiment, reference is made to Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the suspension leveling control method of this application. Figure 1As shown, the suspension leveling control method includes:

[0043] The real-time acquired vehicle height adjustment level, vehicle height, vehicle acceleration, and vehicle speed values ​​are input into the trained neural network model, which outputs the target height level.

[0044] The suspension is adjusted to control the current vehicle height based on the target height level.

[0045] In this embodiment, the real-time acquired vehicle height adjustment level, vehicle height, vehicle acceleration, and vehicle speed values ​​can be input into a neural network model. Based on the neural network model, a target height level is output, and the air suspension is adjusted according to this target height level to suit the current vehicle height. The neural network model has advantages such as self-learning, automatic optimization, and good fault tolerance. It can automatically learn the inherent characteristics of the input data without requiring manual feature extraction algorithms. During network training, it continuously adjusts its weights, resulting in higher efficiency and accuracy in outputting the optimal target height for multiple road segments. This significantly improves passenger comfort and solves the problem of the traditional method where the driver adjusts the suspension height level via the central control screen, resulting in the inability to adjust the suspension height in real time.

[0046] Further, in one embodiment, the step of inputting the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value, and vehicle speed value into a trained neural network model to output the target height level includes:

[0047] The real-time data, including the vehicle's current height adjustment level, vehicle height, vehicle acceleration, vehicle speed, suspension air pump temperature, and suspension air tank pressure, are input into the neural network model to output the target height level.

[0048] In this embodiment, by incorporating the suspension air pump temperature value and the suspension air tank pressure value, precise adjustment of the suspension height level can be provided, offering the driver a more comfortable driving experience.

[0049] Further, in one embodiment, the step of inputting the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value, and vehicle speed value into a trained neural network model to output the target height level includes:

[0050] The real-time values ​​of the vehicle's height adjustment level, vehicle height, vehicle acceleration, and vehicle speed are input into the neural network model.

[0051] The particle swarm optimization algorithm is selected to optimize the weights and thresholds of the neural network model, so that the neural network model outputs the target height level.

[0052] In this embodiment, the weights and thresholds of the neural network model are optimized by selecting the particle swarm optimization algorithm, so that the output target height level is more ideal and closer to the actual situation.

[0053] Furthermore, in one embodiment, before inputting the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value, and vehicle speed value into the trained neural network model and outputting the target height level, the method further includes:

[0054] Collect multiple sets of vehicle height, acceleration, and speed values ​​while driving on special road surfaces;

[0055] Multiple sets of vehicle height, vehicle acceleration, and vehicle speed values ​​are grouped, numbered, and normalized to obtain normalized data.

[0056] The normalized data is imported into the neural network model to train the neural network model, resulting in a trained neural network model.

[0057] In this embodiment, the neural network model can be trained in advance to ensure that the trained model will provide experience values ​​for the actual use of the product based on the experience gained from previous training, and output an accurate target height.

[0058] Furthermore, in one embodiment, the step of adjusting the current vehicle height by controlling the suspension according to the target height level includes:

[0059] If the neural network model calculates a new target height level during the height adjustment process, the adjustment will be made using the latest target height level.

[0060] In this embodiment, if the neural network model calculates a new target height level during the height adjustment process, the adjustment is made according to the latest target height level to ensure that the vehicle height adjustment is real-time and effective, thus avoiding delays in vehicle height adjustment that could affect the driving experience.

[0061] Furthermore, in one embodiment, before inputting the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value, and vehicle speed value into the trained neural network model and outputting the target height level, the method further includes:

[0062] The vehicle's current height is monitored in real time using four height sensors, which are installed around the vehicle body.

[0063] The controller determines whether the vehicle needs body adjustment and confirms the current vehicle height adjustment level based on the difference between the values ​​from the four height sensors and the target height value. If body height adjustment is required, the controller proceeds to the next step; otherwise, it returns to the previous step.

[0064] In this embodiment, when a car passes through an uneven road section, the vehicle height will change to varying degrees. This solution is equipped with four height sensors located at the four corners of the vehicle to monitor the vehicle's height information in real time. The controller determines whether the vehicle height needs to be adjusted and confirms the current vehicle height adjustment level based on the difference between the values ​​of the four height sensors and the target height.

[0065] Furthermore, in one embodiment, the step of adjusting the current vehicle height by controlling the suspension according to the target height level includes:

[0066] Determine whether the current vehicle requires a Class I height adjustment;

[0067] If so, adjust the vehicle height by controlling the suspension air pump and air tank;

[0068] Otherwise, use the gas storage tank for Class II height adjustment;

[0069] Among them, the vehicle height is divided into several Class I height levels, and the Class I height levels are further divided into several Class II height levels.

[0070] In this embodiment, the height differences between the different height levels are significant. Current mainstream height adjustment methods determine whether the real-time height value is within the target height error range. If it is, the adjustment is considered successful, and no further leveling is required. However, relying solely on a single height level cannot precisely adjust the vehicle height. Therefore, a second height level is introduced, which adjusts the vehicle height based on the first level, achieving stepless height adjustment. This improves driving comfort and reduces jerking sensations during height adjustment.

[0071] In summary, the suspension leveling control method of this application is described in detail below:

[0072] Hardware requirements for height adjustment: When a car travels over uneven roads, its height changes to varying degrees, making it difficult to guarantee vehicle stability and comfort. This solution uses four height sensors located at the four corners of the vehicle to monitor its height in real time. The controller determines whether to adjust the vehicle height based on the difference between the sensor readings and the target height.

[0073] Height Level Settings: For example, the vehicle height is set into five primary height levels: Very High (A), High (B), Normal (C), Low (D), and Very Low (E). The height differences between these primary levels are significant. Currently, the mainstream height adjustment method involves determining if the real-time height value is within the target height error range. If it is, the adjustment is considered successful, and no further leveling is required. However, relying solely on a primary height level cannot precisely adjust the vehicle height. Therefore, secondary height levels are set up to provide stepless height adjustment based on the primary levels. For example, the primary height level is further divided into three secondary height levels: X1, X2, and X3. When adjusting a primary height, the primary height adjustment indicator is at position 0, and secondary height adjustment is not performed at this time. Once the primary height adjustment is complete, the indicator position is 1, and secondary height adjustment can begin. Primary adjustment provides a wide range of height adjustment, while secondary adjustment provides a narrower range. Primary height adjustment allows for faster inflation and deflation of the air pump and air tank, resulting in relatively faster height adjustment. However, the individual height adjustment function allows for slower gas filling and discharging speeds of the gas storage tank.

[0074] Method for determining successful height adjustment: When height adjustment is detected, the suspension system begins adjustment. If the current vehicle height is within the Class I error range, the Class I height adjustment is considered successful, and Class II height adjustment begins. If the current vehicle height is within the Class II error range, the Class II height adjustment is considered successful; otherwise, adjustment continues until successful. For example, suppose the height rating of Class E is 5-20mm, which is a Type I error range; E1 is 5mm-10mm, E2 is 10mm-15mm, and E3 is 15mm-20mm, all of which are Type II error ranges. If the vehicle height needs to be adjusted from Class D to Class E, the vehicle height is adjusted in Type I, and it is determined whether the vehicle height is within the Type I error range of Class E. If it is within the Type I error range of Class E, it is further determined whether it is within the required Type II error range of E2 (10mm-15mm). If not, the height rating is adjusted in Type II until the vehicle height is within the Type II error range of E2 (10mm-15mm). If so, the Type II height adjustment is considered successful. Otherwise, the adjustment continues until it is successful.

[0075] Height adjustment requirement determination: There are generally two ways to determine height adjustment requirements: one is when the driver manually sets a new height level on the central control screen, in which case adjustment is required based on the set target height level; the other is when the height sensor detects a height change value greater than an error threshold, in which case a height adjustment level determination is made. An example height level determination method is as follows:

[0076] If the controller does not detect a height change value greater than the set first threshold for height error within the preset time period, it is determined that the height adjustment level is S0 and no height adjustment is required.

[0077] If the controller detects a height change value greater than the first threshold of height error of 5mm within a preset time period, it determines that the height adjustment level is S1-1.

[0078] If the controller detects a height change value greater than the second threshold of height error of 10mm within a preset time period, it determines that the height adjustment level is S1-2 at this time.

[0079] If the controller detects a height change value greater than the third threshold of height error of 15mm within a preset time period, it determines that the height adjustment level is S1-3 at this time.

[0080] If the controller detects two height change values ​​that are greater than the first height error threshold of 5mm within a preset time period, then the height adjustment level is determined to be S2-1.

[0081] If the controller detects two height change values ​​that are greater than the second height error threshold of 10mm within a preset time period, then the height adjustment level is determined to be S2-2.

[0082] If the controller detects two height change values ​​that are greater than the third threshold of height error of 15mm within the preset time period, then the height adjustment level is determined to be S2-3.

[0083] If the controller detects three height change values ​​that are greater than the first threshold of height error of 5mm within a preset time period, then the height adjustment level is determined to be S3-1.

[0084] If the controller detects three height change values ​​that are greater than the second height error threshold of 10mm within a preset time period, then the height adjustment level is determined to be S3-2.

[0085] If the controller detects three height change values ​​that are greater than the third threshold of height error of 15mm within the preset time period, then the height adjustment level is determined to be S3-3.

[0086] If the controller detects four height change values ​​that are greater than the first threshold of height error of 5mm within a preset time period, then the height adjustment level is determined to be S4-1.

[0087] If the controller detects four height change values ​​that are greater than the second height error threshold of 10mm within a preset time period, then the height adjustment level is determined to be S4-2.

[0088] If the controller detects four height change values ​​that are greater than the third height error threshold of 15mm within a preset time period, then the height adjustment level is determined to be S4-3.

[0089] The height adjustment level is divided into four levels, and each level is further divided into three sub-levels, for a total of 12 levels. The level intensity gradually increases from top to bottom, and the need for height adjustment gradually increases.

[0090] Model Data Collection: Data was collected from 20,000 vehicles traveling on various terrains including speed bumps, gravel roads, mountain roads, muddy roads, and water crossings. This included four elevation values, four acceleration values, vehicle speed, suspension air tank pressure, and suspension air pump temperature. The data was grouped, numbered, and normalized using the following formula: Using MATLAB, 10,000 sets of data were randomly selected as the training set, and the remaining 10,000 sets were used as the test set. The training set was primarily used to train the neural network model. Based on the training with these 10,000 sets of data, the neural network model will gain experience from past data. For example, if the current input data is similar to a set of data from these 10,000 sets, the output target height level will be referenced to the output height level of that set. This is similar to a user adjusting their driving height to a satisfactory level on a similar road segment (this segment is the training set), and then driving on the same segment a second time with a high probability of referencing the first height level. The remaining 10,000 sets of data served as the test set to validate the training effect of the first 10,000 sets, observe the difference between the actual and expected results, and determine the quality of the model's training.

[0091] Model Selection: A neural network model was chosen as the base model. This model is an error feedback neural network, consisting of an input layer, hidden layers, and an output layer. The model operation involves two processes: forward propagation and backward propagation. During forward propagation, the input signal is processed by weighting and activation functions and then passed layer by layer until the output layer. During backward propagation, the error signal between the actual output and the expected output is propagated layer by layer to correct the weights of neurons in each layer. Through continuous iteration, the model output continuously approaches the expected output, achieving a training effect. Figure 2 This is a diagram of the neural network model structure. In the neural network model, X1, X2, ..., X... n For the input layer, n is the number of nodes in the input layer, and w ij w jk These represent the weights from the input layer to the hidden layer and the weights from the hidden layer to the output layer, Y1, Y2, ..., Y... m For the output layer, m is the number of nodes in the output layer. The number of nodes in the input layer, hidden layer, and output layer, as well as the learning rate, are set according to the number of input parameters.

[0092] in, Figure 3The flowchart illustrates the process of optimizing a neural network model using the Particle Swarm Optimization (PSO) algorithm. Besides the basic neural network model, PSO can be used to optimize it. Single neural network models may suffer from poor prediction performance and a tendency to get trapped in extreme values, resulting in the output target height not being the optimal target height, or even showing a significant discrepancy. Based on these issues, PSO is incorporated into the single neural network model to optimize its relevant parameters, aiming for better height prediction. PSO is an optimization algorithm that simulates bird predation behavior, finding the optimal value within a given space through information interaction between individuals. The global search capability of PSO is used to optimize the weights and thresholds of the neural network model. The weights and thresholds are used as particle position information, and the network's output error is used as the fitness function of PSO. Through continuous iteration, the optimal values ​​of weights and thresholds are obtained within a finite number of iterations. These optimal values ​​are then fed back into the neural network model to optimize it, yielding the most suitable target height value for adjustment. Similar to the neural network model, network parameters are initialized, limiting particle velocity, position, and initial population size. In essence, PSO optimizes the parameters (weights and thresholds) of the neural network model. There are two optimization methods: one is to optimize the model parameters in advance and use the previously optimized parameters when importing parameters later, which is more efficient; the other is to optimize the parameters while importing them, which is less efficient but more effective and produces a target height level that is closer to the actual situation.

[0093] Particle velocity update formula:

[0094] v im (r+1)=wv im (r)+c1l1[b im (r)-y im (r)]+c2l2[g im (r)-y im (r)]

[0095] Particle position update formula:

[0096] v im (r+1)=v im (r)+y im (r)

[0097] Inertia weight update formula:

[0098]

[0099] Among them, v im (r+1) is the velocity of the i-th particle in the m-th iteration, w is the algorithm's inertia weight, and b im (r) represents the best historical position of the i-th particle, gim (r) represents the best position in the history of all particles, y im (r) represents the position of the i-th particle in the m-th iteration, c1c2 is the algorithm learning factor, and l1l2 is a random number between 0 and 1. max and w min The maximum and minimum values ​​of the inertial weight are set. The larger the weight, the stronger the particle's global search capability; the smaller the weight, the stronger the particle's local search capability.

[0100] Model pre-training: A particle swarm optimization algorithm-neural network model was written in MATLAB, and the corresponding parameters of the model were set. 10,000 sets of data were randomly selected from the 20,000 sets of normalized data collected previously as the test set. This data was imported into the model, which trained the neural network based on these initial data values. The trained model was then compiled into the controller.

[0101] In summary, as Figure 4 As shown, during vehicle operation, the central control screen displays the vehicle's real-time height level. When the height sensor detects that the height adjustment level is not S0, the vehicle needs to adjust its height. The height adjustment level, vehicle height, acceleration, speed, suspension air pump temperature, and suspension air tank pressure are input into a neural network model. The model outputs a target height level in real time, and the vehicle adjusts its height accordingly. The output target height is derived from parameters pre-trained in the neural network model, and the target height level is based on similar input parameters from the training data. For example, when the vehicle passes over consecutive speed bumps, the vehicle height changes according to the height of the speed bumps. In this case, relevant parameters are input into the neural network model, and the model, based on pre-trained data and other similar data, determines the optimal height level and outputs it. The controller receives the target height level in real time. Upon receiving the target height level, it adjusts the current real-time vehicle height. First, it determines whether a Class I height adjustment is needed. If so, it performs a Class I height adjustment by comparing the four vehicle heights with the target height level. If the vehicle height is greater than the target height, the corresponding air spring is deflated; otherwise, it is inflated. After the Class I height adjustment is completed, a Class II height adjustment is performed, using a similar method. If a new target height level is calculated during the height adjustment process, the adjustment is based on the latest target height level.

[0102] Height Information Feedback: The suspension adjustment system transmits the current height level information to the central control screen in real time via the CAN bus. If adjustment is in progress, a special indicator is added to distinguish it. The height bar on the central control screen also changes according to the real-time changes in vehicle height.

[0103] Secondly, this application embodiment also provides a suspension leveling control device, which includes: a target height level calculation module, which is used to input the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value and vehicle speed value into a trained neural network model and output the target height level; and a controller, which is used to control the suspension to adjust the current vehicle height according to the target height level.

[0104] The target height level calculation module can input real-time data on the vehicle's current height adjustment level, vehicle height, vehicle acceleration, and speed into a neural network model. Based on this model, it outputs the target height level and controls the air suspension to adjust accordingly. The neural network model possesses advantages such as self-learning, automatic optimization, and good fault tolerance. It can automatically learn the inherent characteristics of the input data without requiring manual feature extraction algorithms. During network training, it continuously adjusts its weights, resulting in higher efficiency and accuracy in outputting the optimal target height for multiple road segments. This significantly improves passenger comfort and solves the problem of the traditional method where drivers adjust suspension height via the central control screen, resulting in the inability to adjust the suspension height in real time.

[0105] Thirdly, embodiments of this application provide a suspension leveling control device, which can be a personal computer (PC), laptop computer, server, or other device with data processing capabilities.

[0106] Reference Figure 5 , Figure 5 This is a schematic diagram of the hardware structure of the suspension leveling control device involved in the embodiments of this application. In the embodiments of this application, the suspension leveling control device may include a processor, a memory, a communication interface, and a communication bus.

[0107] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0108] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting components within the suspension leveling control device, as well as interfaces used for interconnecting the suspension leveling control device with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0109] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0110] The processor can be a general-purpose processor, which can call the suspension leveling control program stored in the memory and execute the suspension leveling control method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the suspension leveling control program is called can be referred to in the various embodiments of the suspension leveling control method of this application, and will not be repeated here.

[0111] Those skilled in the art will understand that Figure 5 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0112] Fourthly, embodiments of this application also provide a readable storage medium.

[0113] The present application has a storage medium that stores a suspension leveling control program, wherein when the suspension leveling control program is executed by a processor, it implements the steps of the suspension leveling control method as described above.

[0114] The method implemented when the suspension leveling control program is executed can be referred to in various embodiments of the suspension leveling control method of this application, and will not be repeated here.

[0115] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0116] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0117] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0118] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0119] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0120] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0121] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A suspension leveling control method, characterized in that, The suspension leveling control method includes: The real-time acquired vehicle height adjustment level, vehicle height, vehicle acceleration, and vehicle speed values ​​are input into the trained neural network model, which outputs the target height level. The suspension is adjusted to control the current vehicle height based on the target height level. Before outputting the target height level in the trained neural network model, which inputs the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value, and vehicle speed value, the following steps are also included: The vehicle's current height is monitored in real time using four height sensors, which are installed around the vehicle body. The controller determines whether the vehicle needs body adjustment and confirms the current vehicle height adjustment level based on the difference between the values ​​of the four height sensors and the target height value. If body height adjustment is required, the controller proceeds to the next step; otherwise, it returns to the previous step. The method of adjusting the suspension to adjust the current vehicle height according to the target height level includes: Determine whether the current vehicle requires a Class I height adjustment; If so, adjust the vehicle height by controlling the suspension air pump and air tank; Otherwise, use the gas storage tank for Class II height adjustment; Among them, the vehicle height is divided into several Class I height levels, and the Class I height level is further divided into several Class II height levels; When the system detects that height adjustment is needed, it begins to adjust the height. If the current vehicle height is within the Class I error range, the Class I height adjustment is considered successful, and the Class II height adjustment begins. If the current vehicle height is within the Class II error range, the Class II height adjustment is considered successful; otherwise, the adjustment continues until successful. The Class I error range is greater than the Class II error range. The confirmation of the current vehicle height adjustment level includes: The height error includes a first threshold, a second threshold, and a third threshold that increase sequentially. If the height sensor does not detect a height change value greater than the set first height error threshold within a preset time period, it is determined that no height adjustment is required. If the height change value is detected to be greater than the set first, second, or third height error threshold, the corresponding height adjustment level is determined based on the number of height change values ​​exceeding the corresponding threshold.

2. The suspension leveling control method as described in claim 1, characterized in that, The process involves inputting the real-time acquired vehicle height adjustment level, vehicle height, vehicle acceleration, and vehicle speed into a trained neural network model to output the target height level, including: The real-time data, including the vehicle's current height adjustment level, vehicle height, vehicle acceleration, vehicle speed, suspension air pump temperature, and suspension air tank pressure, are input into the neural network model to output the target height level.

3. The suspension leveling control method as described in claim 1, characterized in that, The process involves inputting the real-time acquired vehicle height adjustment level, vehicle height, vehicle acceleration, and vehicle speed into a trained neural network model to output the target height level, including: The real-time values ​​of the vehicle's height adjustment level, vehicle height, vehicle acceleration, and vehicle speed are input into the neural network model. The particle swarm optimization algorithm is selected to optimize the weights and thresholds of the neural network model, so that the neural network model outputs the target height level.

4. The suspension leveling control method as described in claim 1, characterized in that, Before outputting the target height level, the model inputs the real-time acquired vehicle height adjustment level, vehicle height, vehicle acceleration, and vehicle speed into the trained neural network model. Collect multiple sets of vehicle height, acceleration, and speed values ​​while driving on special road surfaces; Multiple sets of vehicle height, vehicle acceleration, and vehicle speed values ​​are grouped, numbered, and normalized to obtain normalized data. The normalized data is imported into the neural network model to train the neural network model, resulting in a trained neural network model.

5. The suspension leveling control method as described in claim 1, characterized in that, The method of adjusting the suspension to adjust the current vehicle height according to the target height level includes: If the neural network model calculates a new target height level during the height adjustment process, the adjustment will be made using the latest target height level.

6. A suspension leveling control device, further comprising executing the suspension leveling control method as described in claim 1, characterized in that, The suspension leveling control device includes: The target height level calculation module is used to input the real-time acquired current vehicle height adjustment level value, vehicle height value, vehicle acceleration value and vehicle speed value into the trained neural network model, and output the target height level; A controller is used to control the suspension to adjust the current vehicle height according to the target height level.

7. A suspension leveling control device, characterized in that, The suspension leveling control device includes a processor, a memory, and a suspension leveling control program stored in the memory and executable by the processor, wherein when the suspension leveling control program is executed by the processor, it implements the steps of the suspension leveling control method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a suspension leveling control program, wherein when the suspension leveling control program is executed by a processor, it implements the steps of the suspension leveling control method as described in any one of claims 1 to 5.

Images