A method and system for adaptive control of tire inflation and deflation of commercial vehicle

Abstract

The application discloses a kind of commercial vehicle tire inflation adaptive control method and system, belong to vehicle control technical field.Method includes: to each tire execution standardization inflation test, acquisition pressure response data, identification and store each tire at different target tire pressure under the characteristic parameter, establish corresponding inflation time prediction model;When receiving target tire pressure instruction, according to the deviation of current pressure and target pressure select large deviation, medium deviation or small deviation mode to carry out hierarchical control, wherein non-small deviation mode is based on prediction model calculation prediction time and determines pressure measurement point, and small deviation mode adopts pulse fine-tuning closed-loop control;After each operation is completed, according to actual feedback data, the characteristic parameter corresponding to target tire pressure is updated on line iteration.The application shortens inflation time, prolongs valve life, and realizes the adaptive compensation to tire aging and environmental change, avoids the precision attenuation after long-term use.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, specifically to an adaptive control method and system for tire inflation and deflation of commercial vehicles. Background Technology

[0002] The Central Tire Inflation System (CTIS) is an important technology in the field of vehicle engineering, primarily used for tire pressure management in commercial vehicles, military vehicles, and special-purpose vehicles. With the development of vehicle intelligence, tire pressure management systems have evolved from manual adjustment to automatic control systems.

[0003] Currently, tire inflation / deflation control mainly adopts a cyclical working mode of "inflation-measurement-reinflation-remeasurement" or "deflation-measurement-redeflation-remeasurement". The system monitors tire pressure in real time through a pressure sensor. When the pressure deviates from the set value, the inflation or deflation solenoid valve is activated. As the pressure approaches the target value, it switches to low flow or pulse regulation until the target range is reached. This method has the following shortcomings: multiple pressure measurements are required during the inflation / deflation process, and the pressure measurement operation itself requires waiting for the pressure to stabilize, resulting in an excessively long total inflation / deflation time, low control efficiency, and inability to meet the needs of rapid pressure regulation; frequent opening and closing of the solenoid valve shortens the valve's lifespan and increases the system failure rate. Summary of the Invention

[0004] To address the aforementioned issues, this invention provides an adaptive control method and system for inflating and deflating commercial vehicle tires, which shortens inflation and deflation time, extends valve life, and achieves adaptive compensation for tire aging and environmental changes, thus avoiding accuracy degradation after long-term use.

[0005] In a first aspect, the technical solution of the present invention provides an adaptive control method for tire inflation and deflation of commercial vehicles, comprising the following steps: Standardized inflation and deflation tests were performed on each tire, pressure response data were collected, the characteristic parameters of each tire under different target tire pressures were identified, and a prediction model of the initial inflation and deflation time corresponding to each target tire pressure was established based on the characteristic parameters. When a target tire pressure command is received, the current tire pressure is obtained, the pressure deviation between the current tire pressure and the current target tire pressure is calculated, and the corresponding control mode is selected according to the magnitude of the pressure deviation. Inflation and deflation control is performed based on the selected control mode. The control modes include small deviation mode and non-small deviation mode. In response to selecting the non-small deviation mode, the system calculates the predicted time required to reach the target pressure based on the latest inflation / deflation time prediction model, determines the pressure measurement point, controls the solenoid valve to operate according to the predicted time, and collects the current measured pressure at the pressure measurement point; in response to selecting the small deviation mode, the system performs pressure measurement based on a preset frequency and uses pulse fine-tuning closed-loop control based on real-time tire pressure. After each inflation / deflation operation is completed, the characteristic parameters corresponding to the target tire pressure are updated based on the operation data, thereby updating the inflation / deflation time prediction model.

[0006] Secondly, the technical solution of the present invention provides an adaptive control method for tire inflation and deflation of commercial vehicles, comprising: The self-learning modeling module is used to perform standardized inflation and deflation tests on each tire, collect pressure response data, identify the characteristic parameters of each tire under different target tire pressures, and establish a prediction model of the initial inflation and deflation time corresponding to each target tire pressure based on the characteristic parameters. The adaptive predictive control module is used to obtain the current tire pressure when a target tire pressure command is received, calculate the pressure deviation between the current tire pressure and the current target tire pressure, select the corresponding control mode according to the magnitude of the pressure deviation, and perform inflation and deflation control based on the selected control mode; the control modes include small deviation mode and non-small deviation mode. In response to selecting the non-small deviation mode, the system calculates the predicted time required to reach the target pressure based on the latest inflation / deflation time prediction model, determines the pressure measurement point, controls the solenoid valve to operate according to the predicted time, and collects the current measured pressure at the pressure measurement point; in response to selecting the small deviation mode, the system performs pressure measurement based on a preset frequency and uses pulse fine-tuning closed-loop control based on real-time tire pressure. The continuous learning and updating module is used to update the characteristic parameters corresponding to the target tire pressure based on the operation data after each inflation / deflation operation, thereby updating the inflation / deflation time prediction model.

[0007] As can be seen from the above technical solutions, this application has the following advantages: In non-small deviation mode, the predicted time required to reach the target pressure is calculated based on the latest inflation / deflation time prediction model, and the pressure measurement point is determined. Pressure measurement is only performed at key pressure measurement points, avoiding the time consumption caused by frequent pressure measurement and pressure stabilization waiting in the traditional "inflation-measurement" cycle. This significantly shortens the total time of a single inflation / deflation operation, while reducing the frequent opening and closing of solenoid valves, extending valve life, and reducing system failure rate. Based on the magnitude of the deviation between the current pressure and the target pressure, a large deviation mode, medium deviation mode, or small deviation mode is adaptively selected for graded control: when the deviation is large, model prediction-driven rapid coarse adjustment is achieved; when the deviation is small, closed-loop feedback achieves fine-tuning. This balances the needs of wide-range rapid adjustment and final precise control, optimizing overall control efficiency while ensuring control accuracy. After each inflation / deflation operation, the characteristic parameters corresponding to the target tire pressure are updated online based on the actual feedback data of this operation. This updates the inflation / deflation time prediction model, enabling the model to adaptively compensate for characteristic drift caused by factors such as slow tire aging, changes in ambient temperature, and changes in altitude. This maintains high control accuracy and avoids the problem of control accuracy decay after long-term use. Attached Figure Description

[0008] To more clearly illustrate the technical solution of this application, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a schematic flowchart of an adaptive control method for tire inflation and deflation of a commercial vehicle provided in an embodiment of the present invention.

[0010] Figure 2 A schematic diagram of the predictive control process.

[0011] Figure 3 This is a schematic diagram of the multi-objective value adaptation mechanism.

[0012] Figure 4 This is a schematic block diagram of a commercial vehicle tire inflation / deflation adaptive control system provided in an embodiment of the present invention. Detailed Implementation

[0013] To make the purpose, features, and advantages of this application more apparent and understandable, specific embodiments and accompanying drawings will be used to clearly and completely describe the technical solution protected by this application. Obviously, the embodiments described below are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this application and in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0015] Figure 1 This is a schematic flowchart of an adaptive control method for tire inflation / deflation of a commercial vehicle provided in an embodiment of the present invention. Figure 1 The executing entity can be a commercial vehicle tire inflation / deflation adaptive control system. The commercial vehicle tire inflation / deflation adaptive control method provided in this embodiment of the invention is executed by a computer device; correspondingly, the commercial vehicle tire inflation / deflation adaptive control system runs on the computer device. Depending on different requirements, the order of the steps in this flowchart can be changed, and some steps can be omitted.

[0016] See Figure 1 The method includes a self-learning modeling stage, an adaptive predictive control stage, and a continuous learning and updating stage, specifically including the following steps.

[0017] S1, self-learning modeling stage.

[0018] Standardized inflation and deflation tests are performed on each tire to collect pressure response data and identify the characteristic parameters of each tire under different target tire pressures. Based on these characteristic parameters, a predictive model for the initial inflation and deflation time corresponding to each target tire pressure is established. This allows the system to acquire the personalized characteristic parameters of each tire through an automated, standardized testing process after initial installation or upon receiving a learning command, and to build a model for subsequent predictive control.

[0019] S2, Adaptive Predictive Control Stage.

[0020] When a target tire pressure command is received, the current tire pressure is obtained, the pressure deviation between the current tire pressure and the current target tire pressure is calculated, and the corresponding control mode is selected according to the magnitude of the pressure deviation. Inflation and deflation control is performed based on the selected control mode. The control modes include small deviation mode and non-small deviation mode.

[0021] In response to selecting the non-small deviation mode, the system calculates the predicted time required to reach the target pressure based on the latest inflation / deflation time prediction model, determines the pressure measurement point, controls the solenoid valve to operate according to the predicted time, and collects the current measured pressure at the pressure measurement point; in response to selecting the small deviation mode, the system performs pressure measurement based on a preset frequency and uses pulse fine-tuning closed-loop control based on the real-time tire pressure.

[0022] This step adaptively selects the optimal control strategy based on the degree of deviation between the current pressure and the target pressure. When the deviation is large, it uses model prediction to achieve rapid coarse adjustment, and when the deviation is small, it uses closed-loop feedback to achieve fine adjustment, thus balancing control efficiency and control accuracy.

[0023] S3, the continuous learning and updating phase.

[0024] After each inflation / deflation operation is completed, the characteristic parameters corresponding to the target tire pressure are updated based on the operation data, thereby updating the inflation / deflation time prediction model.

[0025] This step enables the system to use data feedback from each actual operation to iteratively optimize model parameters online, adaptively compensate for the effects of factors such as tire aging and changes in ambient temperature, and improve control accuracy.

[0026] Furthermore, as a refinement and extension of the specific implementation of the above embodiments, in order to fully illustrate the specific implementation process in this embodiment, a specific embodiment of the adaptive control method for tire inflation and deflation of commercial vehicles is provided, which includes the following steps.

[0027] Step S101: System startup.

[0028] The control unit is powered on and initialized, completes self-test, and loads stored tire characteristic parameters and historical data.

[0029] Step S102: Receive the target tire pressure command.

[0030] The target tire pressure command can be manually set by the human-machine interface unit or automatically requested by the vehicle control system.

[0031] Step S103: Determine whether this is the first time working or if relearning is required.

[0032] The control unit checks whether the characteristic parameter database is empty or whether a relearning instruction has been received. If yes, proceed to step S104; if no, proceed to step S105.

[0033] Step S104: Execute self-learning mode.

[0034] For details of this process, please refer to the detailed workflow below. The system automatically performs standard inflation and deflation tests on each tire, identifies and stores its characteristic parameters, and establishes an initial prediction model.

[0035] Step S105: Call the learned model.

[0036] The system retrieves the characteristic parameters of the corresponding tire from the database, including inflation / deflation time constant, volume parameters, and delay parameters.

[0037] Step S106: Perform predictive control calculations.

[0038] Based on the learned model, current pressure, and target pressure, the optimal inflation / deflation control sequence is calculated, including control mode selection, prediction time calculation, and pressure measurement point planning.

[0039] Step S107: Determine whether the pressure is within the target range.

[0040] During the control process, when the predetermined pressure measurement point is reached or the control sequence ends, the actual pressure is measured to determine whether the target range has been reached. If not, return to step S106 and recalculate the control sequence based on the latest pressure; if the target range has been reached, proceed to step S108.

[0041] Step S108: Record the data for this operation.

[0042] Record the actual control time, number of pressure measurements, final error, environmental conditions, etc.

[0043] Step S109: Update the learning model.

[0044] Based on the deviation between the actual data and the predicted data from this operation, the model parameters are fine-tuned and updated.

[0045] Step S110: Control ends.

[0046] Send a control completion signal to the human-computer interaction unit and update the display status.

[0047] The self-learning mode includes performing standardized inflation and deflation tests on each tire, collecting pressure response data, identifying the characteristic parameters of each tire under different target tire pressures, and establishing a prediction model for the initial inflation and deflation time corresponding to each target tire pressure based on the characteristic parameters. Specifically, it includes the following steps.

[0048] Step S201: Obtain vehicle model parameters.

[0049] The vehicle's CAN bus can automatically read or manually input information such as the number of axles, wheelbase, drive type, and standard tire pressure.

[0050] Step S202: Perform a standard inflation / deflation test on each tire.

[0051] Taking the i-th tire as an example, the following standardized testing procedure is performed.

[0052] (1) Inflation test: Control the tire from a safe low pressure Inflate to the rated high pressure The pressure sensor readings, i.e. pressure values, are continuously collected at a preset frequency, typically not lower than 10Hz, to construct a pressure-time curve for the inflation process. .

[0053] (2) Control the tire from the calibrated high pressure Release air and return to safe low pressure Pressure values ​​are collected at a preset frequency to construct a pressure-time curve for the venting process. .

[0054] In the above tests, the calibrated high voltage was... This can be the vehicle's commonly used target tire pressure value (such as the full load tire pressure) or the safe low pressure. This is the minimum safe pressure value that the tire is allowed to withstand.

[0055] The pressure-time curve during the inflation process is fitted to a response of a first-order inertial-delay element, and the inflation time constant and inflation delay time are identified. Similarly, the pressure-time curve during the deflation process is fitted to a response of a first-order inertial-delay element, and the deflation time constant and deflation delay time are identified.

[0056] Specifically, the pressure-time curves collected during the inflation process were fitted using a first-order inertial-delay model, the response expression of which is:

[0057] in, Inflation delay time is the pure time lag between the opening of the solenoid valve and the start of tire pressure increase. The inflation time constant represents the rate at which tire pressure increases. A larger value indicates a slower inflation speed, and vice versa. By using fitting algorithms such as the least squares method to identify the parameters of the above model, the inflation speed can be determined. and The optimal estimate.

[0058] Similarly, the pressure-time curve of the venting process is fitted using the following first-order inertial plus delay element model:

[0059] Or equivalently represented as:

[0060] in, To delay the release of gas, The time constant for gas release is denoted as . This was obtained through fitting and identification. and The optimal estimate.

[0061] During the inflation test, the equivalent volume of the tire and related pipelines is estimated based on the air source pressure, the effective cross-sectional area of ​​the valve, and the pressure change rate during inflation. The related pipelines refer to the total volume of all connecting pipelines and valve body flow channels from the air source to the tire valve.

[0062] Specifically, considering the tire and all connecting pipes and valve channels from the air source to the tire valve as an equivalent container, according to the ideal gas law and the law of conservation of mass, the mass of gas flowing into the tire is equal to the increase in the mass of gas inside the tire, expressed as:

[0063] in, The absolute pressure of the tire. For equivalent volume, The gas constant is For temperature, For gas density, Let t be the volumetric flow rate through the valve. During the self-learning process, the solenoid valve is controlled to perform standard inflation, and the pressure change curve is recorded at high speed. The equivalent volume can be calculated by using the above model. . The equivalent volume of tire i is a parameter that reflects the gas-holding capacity of the tire and related piping.

[0064] Step S203: Establish the tire characteristic matrix.

[0065] The characteristics of each tire are represented by a vector, and the characteristic vectors of all tires form a matrix M. The characteristic vector of the i-th tire is:

[0066] The characteristic vectors of all tires are organized using the target tire pressure as an index; that is, each target tire pressure value corresponds to a dataset containing the characteristic vectors of all tires. This dataset can be stored in a matrix structure, where each column corresponds to a characteristic vector of one tire, and each row corresponds to the value of the same parameter on different tires.

[0067] Where m is the total number of tires.

[0068] Step S204: Calculate the vehicle model compensation factor.

[0069] The length of the air path from the air source to each tire varies depending on the chassis layout, and this difference in air path length leads to a systematic deviation in the inflation and deflation response time. Specifically, tires with longer air paths have a greater pressure drop along the path and a longer gas transmission time, resulting in a fixed delay in their actual inflation and deflation response time compared to tires with shorter air paths.

[0070] To compensate for the aforementioned deviations, this method uses the tire with the shortest air passage as a benchmark, estimates the proportion of the air passage length of each of the other tires relative to the benchmark tire based on vehicle model parameters, and calculates the air pressure loss compensation factor for each tire. .

[0071] Specifically, vehicle parameters such as wheelbase, number of axles, and drive type are obtained, and the tire placement on the chassis (e.g., front axle, middle axle, rear axle) is combined to estimate the air path length between each tire and the air source. (Unit: m). Taking the tire with the shortest air passage length (usually the front axle tire) as the reference, its air passage length is... Then the compensation factor of the tire. For other tires, the compensation factor is calculated based on the airway length ratio:

[0072] in, The preset compensation coefficient is determined through experience or experimental calibration. This is used to convert the dimension of gas path length difference into the dimension of time, so as to match the time parameter in the prediction formula.

[0073] This compensation factor is directly added to the delay term in the prediction formula to correct for time deviations caused by differences in air path length. For example, the compensation factor for the left rear wheel with a longer air path is... In the inflation time prediction formula, the predicted time of the tire will be increased by a corresponding compensation amount on top of the base delay.

[0074] Step S205: Generate the initial prediction model.

[0075] By integrating all parameters, an initial model is established to predict inflation and deflation times. Specifically, an initial inflation and deflation time prediction model corresponding to the target tire pressure is generated, including an initial inflation time prediction model and an initial deflation time prediction model.

[0076] The prediction model for the initial inflation time of the i-th tire is expressed as:

[0077] in, Let i be the predicted inflation time for the i-th tire. Let be the inflation time constant for the i-th tire. Let be the inflation delay time for the i-th tire. Let be the pipeline pressure loss compensation factor for the i-th tire. The current target tire pressure, This is the current tire pressure. For gas source pressure; The prediction model for the initial deflation time of the i-th tire is expressed as:

[0078] in, Let be the predicted deflation time for the i-th tire. Let be the deflation time constant of the i-th tire. Let be the deflation delay time for the i-th tire. Atmospheric pressure.

[0079] The above time prediction model treats the tire and related piping as a container with a fixed volume. The inflation and deflation process is driven by a pressure difference, and the pressure change follows an exponential law. The logarithmic term in the formula represents the exponential process time required for the pressure to change from the current pressure to the target pressure, and the time constant is used. Characterized by the magnitude of the inertia and the delay time of the process. and compensation factor Together, we correct for fixed delays and piping discrepancies in the system.

[0080] In this embodiment, the appropriate control mode is selected based on the magnitude of the pressure deviation. Specifically, this includes: calculating the normalized pressure deviation; selecting the large deviation mode when the normalized pressure deviation is greater than a first threshold; selecting the medium deviation mode when the normalized pressure deviation is greater than a second threshold but less than or equal to the first threshold; and selecting the small deviation mode when the normalized pressure deviation is less than or equal to the second threshold. The large deviation mode and the medium deviation mode are non-small deviation modes. See also... Figure 2 The specific steps involved in performing predictive control calculations are as follows.

[0081] Step S301: Input parameters.

[0082] To obtain the input data required for current control, including: current target tire pressure. Current tire pressure And the characteristic parameters of the tire at the current target tire pressure, retrieved from the database.

[0083] Step S302: Calculate the normalized pressure difference.

[0084] Calculate the normalized pressure deviation based on the current pressure and the target pressure. The calculation formula is:

[0085] Normalization eliminates the influence of differences in the absolute values ​​of different target pressures on the deviation judgment.

[0086] Step S303: Determine the control mode (large deviation / non-large deviation).

[0087] Normalized pressure deviation With the first threshold Compare them. The preset first threshold is used to distinguish between large deviation mode and non-large deviation mode (including medium deviation mode and small deviation mode).

[0088] like This indicates that the current pressure deviates significantly from the target pressure, and the system proceeds to step S304 to execute the large deviation mode control.

[0089] like This indicates that the deviation has not reached the level of a large deviation, and the system proceeds to step S305 to further determine whether it is a medium deviation or a small deviation.

[0090] In this embodiment, The setting is 10%, a value calibrated based on actual vehicle test data. When the deviation is greater than or equal to 10%, the tire pressure deviates significantly from the target value, and a large deviation mode is used for rapid coarse adjustment.

[0091] Step S304: Execute large deviation mode control.

[0092] After determining that the deviation belongs to the large deviation mode, the system executes the following control logic: First, depending on whether inflation or deflation is required, select the inflation time prediction formula or deflation time prediction formula established in step S205, and calculate the total time required to reach the target pressure. .

[0093] Then, perform one continuous inflation or deflation operation, the duration of which is:

[0094] in, The safety factor ranges from 0.85 to 0.95. The purpose of setting this safety factor is to prevent overcharging or over-discharging by ending continuous operation and performing pressure verification before the predicted time, given the inherent uncertainty in model predictions. A safety factor less than 1.0 ensures that the initial charge / discharge volume is slightly less than the predicted value, preserving room for subsequent fine-tuning and avoiding overshoot.

[0095] During continuous inflation and deflation, the system does not perform pressure measurement and relies entirely on model prediction-driven control, thereby significantly reducing pressure measurement waiting time and improving control efficiency.

[0096] Reaching the duration Afterwards, the system closes the solenoid valve and performs a pressure measurement to obtain the actual pressure. .

[0097] Finally, based on the measured pressure, the deviation between the current pressure and the target pressure is recalculated to determine the control mode range to which the deviation belongs: if the deviation still belongs to the large deviation mode, then the current measured pressure is used. Perform large deviation control again for the latest tire pressure; if the deviation is in medium deviation mode, then use the current measured pressure. The system proceeds to step S306 to update the current tire pressure, implementing medium deviation mode control; if the deviation is in small deviation mode, the current measured pressure is used. The system proceeds to step S307 with the latest current tire pressure, and performs small deviation mode control. If the deviation is within the allowable error range, the control is terminated directly.

[0098] Step S305: Determine the control mode (medium deviation / small deviation).

[0099] When the normalized pressure deviation does not reach the large deviation level, the system will further... With the second threshold Compare them. The second threshold is a preset value used to distinguish between medium deviation mode and small deviation mode. .

[0100] like The system then proceeds to step S306, executing the deviation mode control.

[0101] like The system then proceeds to step S307, executing small deviation mode control.

[0102] In this embodiment, The setting is 2%. When the deviation is between 2% and 10%, the system adopts the medium deviation mode for segmented predictive control; when the deviation is less than or equal to 2%, it directly enters the small deviation mode for pulse fine-tuning.

[0103] Step S306: Execute deviation mode control.

[0104] After determining that the deviation belongs to the medium deviation mode, the system executes the segmented predictive control logic: First, based on the current pressure and target pressure The total remaining time required to reach the target pressure is calculated using a inflation / deflation time prediction model. .

[0105] Then, the total remaining time Divide the data into equal segments according to the preset number N to obtain the first segment of control time:

[0106] Wherein, N is the preset number of segments. In this embodiment, N takes the value of 2 or 3, that is, the total time is divided into 2 or 3 segments.

[0107] The system controls the solenoid valve to operate, continuously opening the first control period. Then close the valve and obtain the current measured pressure through the pressure sensor.

[0108] After obtaining the measured pressure, the system performs the following judgments and operations: It recalculates the deviation between the current pressure and the target pressure based on the measured pressure. If the deviation still falls within the medium deviation range, it uses the measured pressure as the updated current pressure and recalculates the new total remaining time required to reach the target pressure. The new total remaining time is redivided into equal segments N, and the next segment of control is executed. If the deviation is in the small deviation mode, the process proceeds to step S307 to execute the small deviation mode control. If the deviation is within the allowable error range, the control is terminated directly.

[0109] Repeat the above segmented control, pressure measurement, recalculation, and mode determination process until control ends. This segmented control strategy effectively suppresses the accumulation of model prediction errors by decomposing the long prediction time into multiple shorter control segments and introducing measured feedback after each segment, while keeping the number of pressure measurements to a low level.

[0110] Step S307: Execute small deviation mode control.

[0111] After determining that the deviation belongs to the small deviation mode, the system switches to a fine closed-loop control strategy.

[0112] The system employs a pulse control strategy, calculating the width of the next pulse based on a PID algorithm, and performing closed-loop fine-tuning through short-duration pulse inflation or deflation. During the pulse intervals, the system measures pressure at a relatively high frequency, acquiring the current pressure value in real time, and using this value as the feedback input to the PID controller.

[0113] The PID controller calculates the real-time deviation between the current pressure and the target pressure. The output control quantity is calculated according to the proportional-integral-derivative control law, which determines the duration of the next pulse. The pulse width gradually decreases as the deviation decreases, and the control ends when the pressure enters the preset allowable error band (e.g., ±0.1 bar).

[0114] This small deviation control mode achieves high-precision and stable regulation of the target pressure through high-frequency pressure measurement and PID-based pulse fine-tuning, which can compensate for the small-range deviations that may exist in the model prediction under the large deviation mode and medium deviation mode.

[0115] To enable the system to quickly adapt to various target tire pressure values ​​(such as different pressures corresponding to no load, half load, and full load), this embodiment designs a multi-target value adaptation mechanism, see [link to relevant documentation]. Figure 3 In response to the selection of a non-small deviation mode, the following steps are specifically performed before performing charge / discharge control based on the selected control mode.

[0116] Step S401: New target value received.

[0117] The system received a new target tire pressure command. The instruction can come from the driver's manual setting through the human-machine interface, or from an automatic request from the upper control system, such as automatically adjusting tire pressure according to the load status.

[0118] Step S402: Query historical data.

[0119] The system queries the characteristic parameter database to see if the characteristic parameters corresponding to the current target tire pressure value are already stored. The database is organized using the target tire pressure as an index, and each learned target tire pressure value corresponds to a complete set of tire characteristic parameters.

[0120] Step S403: Determine if there are similar historical records. If there are, proceed to step S404; otherwise, proceed to step S405.

[0121] If the database contains a match If the target tire pressure value and its corresponding characteristic parameters are the same, proceed to step S404 and directly call the parameter.

[0122] If the database does not contain the matching... If the record is identical, then further search the database for the same... The two closest historical target tire pressure values ,satisfy That is, the two historical target tire pressure values ​​are less than and greater than the current new target value, respectively, and are consistent with... The distance is the smallest.

[0123] If there are no two historical target tire pressure values ​​in the database that meet the above conditions, that is, there are fewer than two available data points in the database, or the new target value is outside the range of existing data, the system cannot generate initial parameters by interpolation and will directly proceed to step S412 to start the supplementary learning process.

[0124] Step S404: Call the similar target value parameter.

[0125] When the database already contains When the same target tire pressure is recorded, the system directly retrieves all characteristic parameters corresponding to that target tire pressure value from the database, including the inflation time constant of each tire. venting time constant Inflation delay time Degassing delay time Pipeline pressure loss compensation factor After the call is complete, proceed to step S407 to execute the inflation / deflation control.

[0126] Step S405: Parameter interpolation extrapolation.

[0127] When the database does not contain the corresponding... The records are identical, but there are two closest historical target tire pressure values. At that time, the system calculates the initial characteristic parameters under the new target tire pressure value through an interpolation algorithm.

[0128] With inflation time constant For example, the formula for linear interpolation is:

[0129] in, for The corresponding inflation time constant, for The corresponding inflation time constant.

[0130] All characteristic parameters to be interpolated are calculated using the same interpolation method, ultimately yielding the new target tire pressure. The complete set of characteristic parameters.

[0131] Step S406: Generate initial control parameters.

[0132] Based on the characteristic parameters obtained by interpolation in step S405, a method for... The initial control parameter set includes the inflation time constant, deflation time constant, inflation delay time, deflation delay time, pipeline pressure loss compensation factor, etc. for each tire.

[0133] Step S407: Perform inflation / deflation control.

[0134] Using the initial control parameters generated in step S406, the inflation / deflation operation is executed according to the adaptive predictive control process described in steps S301 to S307. During the control process, the system automatically selects a large deviation mode, a medium deviation mode, or a small deviation mode based on the deviation between the current pressure and the target pressure, until the pressure reaches the target range.

[0135] Step S408: Record control process data.

[0136] After the inflation / deflation control is completed, the system records the actual control time t, the number of pressure measurements n, and the pressure error e at the end of the prediction phase, which are dominated by the initial characteristic parameters generated by interpolation.

[0137] The "prediction phase" refers to the period from the start of inflation / deflation until the initial determination of whether to switch to another control mode based on the measured pressure. Specifically: If the large deviation mode is used in this control, the end time of the prediction stage is the end time of continuous charging and discharging. , ; If the medium-deviation mode is used for this control, then the end time of the prediction phase is the end time of the last control segment. , .

[0138] Step S409: Compare with the model prediction and calculate the fitness score S.

[0139] Based on the actual control time t, pressure measurement count n, and pressure error e recorded in step S408, the fitness score S is calculated to comprehensively evaluate the effectiveness of the interpolation parameters. The scoring formula is:

[0140] in, The preset maximum allowable control time, The preset maximum number of pressure tests. The preset maximum allowable pressure error, The weighting coefficients and .

[0141] Step S410: Determine whether the fitness score is higher than the threshold.

[0142] Compare the fitness score S with the preset score threshold A comparison is made. In this embodiment, Set to 0.6.

[0143] like This indicates that the initial characteristic parameters generated by interpolation performed well in this control, and the interpolation parameters are determined to be valid. Proceed to step S411.

[0144] like This indicates that the interpolation parameters are not performing well, so proceed to step S412 to start supplementary learning.

[0145] Step S411: The model parameters are valid and stored in the history database.

[0146] The interpolation parameters are deemed valid when the fitness score exceeds a threshold. The system then sets the current target tire pressure value. The corresponding characteristic parameters are stored as a new valid data point in the historical database for future interpolation calls for similar target tire pressure values, thereby achieving data accumulation and continuous improvement.

[0147] Step S412: Start supplementary learning.

[0148] When the fitness score is lower than or equal to the threshold, the interpolation parameters are deemed invalid. The system initiates a supplementary learning process for the current target tire pressure value, performing a complete standardized inflation / deflation test to obtain accurate characteristic parameters. After the supplementary learning is completed, the obtained accurate characteristic parameters are stored in the historical database, overwriting the original interpolation parameters.

[0149] In the adaptive predictive control of this embodiment, the selection of pressure measurement timing directly affects control efficiency and accuracy. Too many pressure measurements increase waiting time, while too few measurements may lead to excessive control deviation. Therefore, this embodiment introduces a confidence-based pressure measurement decision optimization mechanism, which dynamically adjusts the pressure measurement strategy by evaluating the reliability of the current predictive model. Specifically, this includes the following steps.

[0150] Step S501: Obtain the current state.

[0151] Obtain current tire status information, including: tire characteristic parameters, current control mode (large deviation mode or medium deviation mode), and historical prediction error statistics for the tire. The historical prediction error is a record of the deviation between the pressure expected by the prediction model and the actual measured pressure after the prediction phase in the large deviation mode during each control cycle.

[0152] Step S502: Calculate the confidence level of the current prediction model.

[0153] The confidence level of the current prediction model is calculated based on the statistical results of historical prediction errors. The confidence level characterizes the reliability of the current prediction model in predicting a wide range of inflation and deflation times under large deviation modes. A higher confidence level indicates a more reliable model prediction, reducing the need for pressure measurements; a lower confidence level indicates a less reliable model prediction, requiring increased pressure measurement frequency to ensure control accuracy.

[0154] The confidence level is dynamically updated according to the following recursive formula:

[0155] in: This is the confidence level value stored before this control operation, with the initial value being the initial confidence level after the learning process is completed. This is the updated confidence level value; Forgetting factor, This is used to control the weight between historical confidence levels and the current evaluation result. In this implementation method... The value is 0.7; This represents the pressure error at the end of the most recent large deviation model prediction phase. To be at the end of continuous inflation and deflation The measured actual pressure, For target pressure; This is a predefined maximum permissible pressure error characteristic value used to normalize the error to a suitable scale; This is a scoring function for the predicted performance; the more accurate the prediction (…). (smaller) The closer to 1, the greater the prediction bias. The larger ( The closer it gets to 0.

[0156] Step S503: Select a pressure measurement strategy based on confidence level.

[0157] Compare the current confidence level with the preset confidence threshold. A comparison is made. In this embodiment, Set to 0.6.

[0158] (a) High confidence level situation ( ) When the confidence level is higher than the threshold, it indicates that the current prediction model has high reliability. The system executes the first stress testing strategy: Large deviation mode: only at the end of continuous inflation / deflation Perform one pressure measurement, and do not perform any pressure measurements during continuous inflation and deflation. The control process is entirely driven by model predictions until the predicted time point is reached; In medium deviation mode: only at the end of each segment control... Pressure testing is performed, but no additional pressure testing is performed during segmented control.

[0159] This strategy achieves control with the fewest possible pressure measurements, minimizing the total control time.

[0160] (ii) Low confidence level situation ( ) When the confidence level is lower than or equal to the threshold, it indicates that the current prediction model lacks sufficient reliability. The system then executes the second stress testing strategy: Under large deviation mode: increase the safety factor Adjust to a more conservative value ,in This allows the first continuous inflation / deflation to end earlier and be verified sooner; and at least one intermediate pressure measurement is added during the continuous inflation / deflation process, with the remaining inflation / deflation time dynamically adjusted based on the intermediate pressure measurement results. In medium deviation mode: increase the number of segments N and correspondingly increase the pressure measurement points to make the control process more granular and obtain measured feedback at more nodes.

[0161] Step S504: Update the confidence level.

[0162] After each prediction phase of the large deviation model ends, the pressure error generated in that phase is considered. Update the confidence score by using the calculated score. Store in the database for use in the next control operation. use.

[0163] Step S505: Model mismatch judgment and relearning trigger.

[0164] When the confidence level remains below the preset lower confidence limit This indicates that the model has deviated significantly from the actual system state and cannot be repaired through normal update mechanisms. In this embodiment, The confidence level is set to 0.3. When the confidence level falls below this lower limit multiple times consecutively, it is determined to be a model mismatch. The system will automatically trigger a relearning process, perform a complete standardized inflation / deflation test, re-identify the tire characteristic parameters, and update the prediction model.

[0165] It should be noted that, as another implementation method, a cyclic control method that directly selects to measure pressure immediately after a single inflation or deflation, i.e., the traditional "inflation-measurement" or "deflation-measurement" cycle, is used until the pressure reaches the target range.

[0166] After each inflation / deflation control operation is completed, the system enters a continuous learning and updating phase. This phase utilizes feedback data obtained from the actual operation to iteratively optimize the characteristic parameters of the prediction model online, allowing the model to gradually adapt to the effects of long-term factors such as tire aging, changes in ambient temperature, and altitude.

[0167] Step S601: Collect the data for this operation.

[0168] After each inflation / deflation operation, the system collects the actual data for that operation. The collected data includes at least the total time of the entire control process. (Total time from solenoid valve opening to reaching the target pressure), tire pressure at the start of this control. and the final measured pressure at the end of this control period. .

[0169] In addition, the system also retrieves the tire's known delay time parameters (inflation delay time) from the database. Or the time of deflation delay ), which serves as a known constant for subsequent reverse calculations.

[0170] In this embodiment, if the current operation is an inflation operation, the inflation delay time is invoked. If this operation is a venting operation, then the venting delay time will be invoked. .

[0171] Step S602: Back-calculate the estimated value of the time constant.

[0172] Based on the actual data collected in step S601, and combined with the first-order inertial plus delay model, the estimated value of the time constant reflected in this operation is calculated in reverse.

[0173] (a) Inverse calculation of the time constant of the inflation operation If this operation is an inflation operation, the total time of this operation will be... Initial pressure Final measured pressure Known inflation delay time and gas source pressure Substituting the analytical expression of the first-order inertial-delay model:

[0174] exist time, Substitute into the above equation and solve inversely. The estimated value of the inflation time constant is obtained as follows:

[0175] (ii) Deduction of the time constant for venting operation If this operation is a venting operation, similarly, the total time of this operation will be... Initial pressure Final measured pressure Known venting delay time and atmospheric pressure Substituting the analytical expression of the first-order inertial-delay model:

[0176] exist time, Substitute into the above equation and solve inversely. The estimated value of the venting time constant is obtained as follows:

[0177] The actual performance of this inflation / deflation operation (total time and final pressure) implicitly contains information about the tire's response speed under the current operating conditions. This information can be extracted through model inverse kinematics and used as a new estimate of the time constant. This estimate reflects the actual inflation / deflation response characteristics of the tire under its current aging state and environmental conditions.

[0178] In this embodiment, if the operation is an inflation operation, then If this operation is a venting operation, then .

[0179] Step S603: Update the time constant using a weighted recursive method.

[0180] The weighted recursive update algorithm is used to update the estimated time constant obtained in step S602. Compared with the time constant value stored before this operation The fusion is performed to obtain the updated time constant value. The updated formula is:

[0181] in, Forgetting factor, This is used to control the weighting between historical parameters and the current estimate.

[0182] If this operation is an inflation operation, then update the inflation time constant. If this operation is a venting operation, then update the venting time constant. .

[0183] The calculated and updated time constant value is written to the database, replacing the original time constant corresponding to the target tire pressure. This incremental update method allows the model parameters to smoothly track factors such as slow tire aging and seasonal changes in ambient temperature, gradually and adaptively adjusting. The updated model will be used in the next inflation / deflation control cycle.

[0184] The above text provides a detailed description of an embodiment of an adaptive control method for tire inflation and deflation of commercial vehicles. Based on the adaptive control method for tire inflation and deflation of commercial vehicles described in the above embodiment, this invention also provides an adaptive control system for tire inflation and deflation of commercial vehicles corresponding to the method.

[0185] Figure 4 This is a schematic block diagram of a commercial vehicle tire inflation / deflation adaptive control system provided in an embodiment of the present invention. In this embodiment, the commercial vehicle tire inflation / deflation adaptive control system performs its functions. The module referred to in this invention is a series of computer program segments that can be executed by at least one processor and perform a fixed function, and is stored in memory.

[0186] The self-learning modeling module is used to perform standardized inflation and deflation tests on each tire, collect pressure response data, identify the characteristic parameters of each tire under different target tire pressures, and establish a prediction model for the initial inflation and deflation time corresponding to each target tire pressure based on the characteristic parameters.

[0187] The adaptive predictive control module is used to obtain the current tire pressure when a target tire pressure command is received, calculate the pressure deviation between the current tire pressure and the current target tire pressure, select the corresponding control mode according to the magnitude of the pressure deviation, and perform inflation and deflation control based on the selected control mode; the control modes include small deviation mode and non-small deviation mode.

[0188] In response to selecting the non-small deviation mode, the system calculates the predicted time required to reach the target pressure based on the latest inflation / deflation time prediction model, determines the pressure measurement point, controls the solenoid valve to operate according to the predicted time, and collects the current measured pressure at the pressure measurement point; in response to selecting the small deviation mode, the system performs pressure measurement based on a preset frequency and uses pulse fine-tuning closed-loop control based on the real-time tire pressure.

[0189] The continuous learning and updating module is used to update the characteristic parameters corresponding to the target tire pressure based on the operation data after each inflation / deflation operation, thereby updating the inflation / deflation time prediction model.

[0190] The commercial vehicle tire inflation / deflation adaptive control system of this embodiment is used to implement the aforementioned commercial vehicle tire inflation / deflation adaptive control method. Therefore, the specific implementation of this system can be found in the embodiment section of the commercial vehicle tire inflation / deflation adaptive control method above. Thus, the specific implementation can be referred to the description of the corresponding embodiments, and will not be elaborated here.

[0191] Furthermore, since the commercial vehicle tire inflation / deflation adaptive control system of this embodiment is used to implement the aforementioned commercial vehicle tire inflation / deflation adaptive control method, its function corresponds to the function of the above method, and will not be repeated here.

[0192] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An adaptive control method for tire inflation and deflation of commercial vehicles, characterized in that, Includes the following steps: Standardized inflation and deflation tests were performed on each tire, pressure response data were collected, the characteristic parameters of each tire under different target tire pressures were identified, and a prediction model of the initial inflation and deflation time corresponding to each target tire pressure was established based on the characteristic parameters. When a target tire pressure command is received, the current tire pressure is obtained, the pressure deviation between the current tire pressure and the current target tire pressure is calculated, and the corresponding control mode is selected according to the magnitude of the pressure deviation. Inflation and deflation control is performed based on the selected control mode. The control modes include small deviation mode and non-small deviation mode. In response to the selection of the non-small deviation mode, the predicted time required to reach the target pressure is calculated based on the latest inflation / deflation time prediction model, and the pressure measurement point is determined. The solenoid valve is controlled to operate according to the predicted time, and the current measured pressure is collected at the pressure measurement point. In response to the selection of the small deviation mode, pressure is measured based on a preset frequency, and pulse fine-tuning closed-loop control is adopted based on real-time tire pressure; After each inflation / deflation operation is completed, the characteristic parameters corresponding to the target tire pressure are updated based on the operation data, thereby updating the inflation / deflation time prediction model.

2. The adaptive control method for tire inflation / deflation of commercial vehicles according to claim 1, characterized in that, Standardized inflation and deflation tests were performed on each tire to collect pressure response data and identify the characteristic parameters of each tire under different target tire pressures, specifically including: The tire is inflated from a safe low pressure to a calibrated high pressure, and pressure values ​​are collected at a preset frequency to construct a pressure-time curve of the inflation process; the calibrated high pressure is the target tire pressure. Control the tire to deflate from the calibrated high pressure back to the safe low pressure, collect pressure values ​​at a preset frequency, and construct a pressure-time curve for the deflation process; The pressure-time curve during the inflation process is fitted to the response of a first-order inertial plus delay element, and the inflation time constant and inflation delay time are identified. The pressure-time curve of the venting process is fitted to the response of a first-order inertial plus delay element, and the venting time constant and venting delay time are identified. The equivalent volume of the tire and related pipelines is estimated based on the air source pressure, the effective cross-sectional area of ​​the valve, and the pressure change rate during the inflation process; the related pipelines refer to the total volume of all connecting pipelines and valve body flow channels from the air source to the tire valve. The characteristic parameters of a tire include inflation time constant, inflation delay time, deflation time constant, deflation delay time, and equivalent volume; the characteristics of each tire are represented by a vector, and the characteristic vectors of all tires are combined into a matrix.

3. The adaptive control method for tire inflation / deflation of commercial vehicles according to claim 2, characterized in that, Based on characteristic parameters, a prediction model for the initial inflation / deflation time corresponding to each target tire pressure is established, specifically including: Obtain vehicle model parameters, including the number of axles, wheelbase, drive type, and standard tire pressure; Using the tire with the shortest air passage as a benchmark, estimate the air passage length ratio of each other tire relative to the benchmark tire based on vehicle parameters, and calculate the pipeline pressure loss compensation factor for each tire. Generate an initial inflation / deflation time prediction model corresponding to the target tire pressure, including an initial inflation time prediction model and an initial deflation time prediction model; The prediction model for the initial inflation time of the i-th tire is expressed as follows: in, Let i be the predicted inflation time for the i-th tire. Let be the inflation time constant for the i-th tire. Let be the inflation delay time for the i-th tire. Let be the pipeline pressure loss compensation factor for the i-th tire. The current target tire pressure, This is the current tire pressure. For gas source pressure; The prediction model for the initial deflation time of the i-th tire is expressed as: in, Let be the predicted deflation time for the i-th tire. Let be the deflation time constant of the i-th tire. Let be the deflation delay time for the i-th tire. Atmospheric pressure.

4. The adaptive control method for tire inflation / deflation of commercial vehicles according to claim 1, characterized in that, The appropriate control mode is selected based on the magnitude of the pressure deviation, specifically including: Calculate the normalized pressure deviation; When the normalized pressure deviation is greater than the first threshold, the large deviation mode is selected; When the normalized pressure deviation is greater than the second threshold and less than or equal to the first threshold, select the medium deviation mode; When the normalized pressure deviation is less than or equal to the second threshold, select the small deviation mode; Among them, the large deviation mode and the medium deviation mode are non-small deviation modes.

5. The adaptive control method for tire inflation / deflation of commercial vehicles according to claim 4, characterized in that, Based on the selected large deviation mode, the inflation / deflation control specifically includes: Based on the current tire pressure and the current target tire pressure, the total time required to reach the target tire pressure is predicted using the latest inflation / deflation time prediction model. ; Perform one continuous inflation / deflation operation, duration ,in, For safety factor; exist Always perform initial pressure testing for verification. Based on the initial pressure measurement results, determine whether to switch to medium deviation mode or small deviation mode, or to terminate control directly.

6. The adaptive control method for tire inflation / deflation of commercial vehicles according to claim 5, characterized in that, Based on the selected control mode being the medium deviation mode, the inflation / deflation control specifically includes: Step 1: Based on the latest current tire pressure and the current target tire pressure, use the latest inflation / deflation time prediction model to predict the total time required to reach the target tire pressure. ; Step 2, total time The control time is divided equally according to the preset number of segments N to obtain the first segment of control time. ; Step 3: Control the solenoid valve to operate, continuously maintaining the first control period. Then close the valve and obtain the current measured pressure; Step 4: Based on the pressure deviation between the current measured pressure and the target tire pressure, determine whether to maintain the medium deviation mode, switch to the small deviation mode, or directly end control; if the medium deviation mode is maintained, the current measured pressure is used as the updated current tire pressure, and return to step 1.

7. The adaptive control method for tire inflation / deflation of commercial vehicles according to claim 5 or 6, characterized in that, In response to the selection of a non-small deviation mode, before performing charge / discharge control based on the selected control mode, the following also includes: Check if the characteristic parameters corresponding to the current target tire pressure are stored; If not stored, find the characteristic parameters corresponding to the two target tire pressures that are closest to the current target tire pressure, where the current target tire pressure is between the two closest target tire pressures; Based on the characteristic parameters corresponding to the two closest target tire pressures, the characteristic parameters of the current target tire pressure are calculated using an interpolation algorithm. Based on the calculated characteristic parameters, a prediction model for the inflation and deflation time of the current target tire pressure is established, and inflation and deflation control is carried out based on this model. After this inflation / deflation control is completed, the following steps are also included: Record the actual control time t, the number of pressure measurements n, and the pressure error e at the end of the prediction phase. The prediction phase refers to the period from the start of the charging / discharging process until the first determination of whether to switch to another control mode based on the measured pressure. If the large deviation mode is used in this control, the end time of the prediction phase is the end time of the continuous charging / discharging process. , If the control adopts the medium deviation mode, the end time of the prediction stage is the end time of the last control segment. , ; The fitness score S is calculated based on the actual control time, the number of pressure measurements, and the final pressure error. The calculation formula is as follows: in, The preset maximum allowable control time, The preset maximum number of pressure tests. The preset maximum allowable pressure error, The weighting coefficients and ; When the fitness score S is higher than the preset score threshold, the characteristic parameter is determined to be valid, and the current target tire pressure value and its corresponding characteristic parameter are stored as valid data points. When the fitness score S is lower than or equal to the preset score threshold, the characteristic parameter is deemed invalid, and a supplementary learning process is initiated for the current target tire pressure value.

8. The adaptive control method for tire inflation / deflation of commercial vehicles according to claim 6, characterized in that, The method also includes: Obtain the historical prediction error statistics of the current tire. The historical prediction error is the deviation record between the pressure expected by the prediction model and the actual measured pressure after the prediction stage of the large deviation mode is completed in each control cycle. The confidence level of the current prediction model is calculated based on the historical prediction error statistics, and the confidence level is dynamically updated according to the following formula: in, Forgetting factor, ; This represents the pressure error at the end of the most recent large deviation model prediction phase. To be at the end of continuous inflation and deflation The measured actual pressure, The current target tire pressure, This is a predefined maximum permissible pressure error characteristic value; For the updated confidence level, The confidence level before the update; When the current confidence level is higher than the preset confidence level threshold, the first pressure measurement strategy is executed: in large deviation mode, it is only performed at the end of continuous inflation and deflation. Perform a pressure test only once, and do not perform pressure tests during continuous inflation and deflation; in medium deviation mode, perform a pressure test only at the end of segment control, and do not perform additional pressure tests during segment control. When the current confidence level is lower than or equal to a preset confidence threshold, a second pressure measurement strategy is executed: in large deviation mode, the safety factor is... Adjustment ,in In addition, at least one intermediate pressure measurement is added during continuous inflation and deflation, and the remaining inflation and deflation time is dynamically adjusted based on the intermediate pressure measurement results; in medium deviation mode, the number of segments is increased; When the confidence level is lower than or equal to the preset lower confidence level several times in a row, the inflation / deflation time prediction model is deemed to have failed, triggering a relearning process.

9. The adaptive control method for tire inflation / deflation of commercial vehicles according to claim 1, characterized in that, The characteristic parameters corresponding to the target tire pressure are updated based on the operational data, specifically including: Collect actual data for this operation, including at least the total time of this control process. Tire pressure at the start of this control The final measured pressure at the end of this control period. And the known delay time of the tire; The estimated value of the time constant is derived by working backward from the actual data from this operation; if this was an inflation operation, then the estimated value of the inflation time constant is derived backward. The calculation formula is: If this is a venting operation, then the estimated value of the venting time constant should be calculated by reverse calculation. The calculation formula is: in, These are the inflation delay time and deflation delay time determined when performing standardized inflation and deflation tests on each tire, respectively. For gas source pressure, Atmospheric pressure; The time constant is updated using a weighted recursive update algorithm, and the calculation formula is as follows: in, Forgetting factor, ; This is the time constant value stored before this operation; This is an estimate of the time constant derived from the data from this operation. Updated time constant Replace the original time constant corresponding to the target tire pressure with the stored data to complete this learning update.

10. An adaptive control method for tire inflation and deflation of commercial vehicles, characterized in that, include: The self-learning modeling module is used to perform standardized inflation and deflation tests on each tire, collect pressure response data, identify the characteristic parameters of each tire under different target tire pressures, and establish a prediction model of the initial inflation and deflation time corresponding to each target tire pressure based on the characteristic parameters. The adaptive predictive control module is used to obtain the current tire pressure when a target tire pressure command is received, calculate the pressure deviation between the current tire pressure and the current target tire pressure, select the corresponding control mode according to the magnitude of the pressure deviation, and perform inflation and deflation control based on the selected control mode; the control modes include small deviation mode and non-small deviation mode. In response to the selection of the non-small deviation mode, the predicted time required to reach the target pressure is calculated based on the latest inflation / deflation time prediction model, and the pressure measurement point is determined. The solenoid valve is controlled to operate according to the predicted time, and the current measured pressure is collected at the pressure measurement point. In response to the selection of the small deviation mode, pressure is measured based on a preset frequency, and pulse fine-tuning closed-loop control is adopted based on real-time tire pressure; The continuous learning and updating module is used to update the characteristic parameters corresponding to the target tire pressure based on the operation data after each inflation / deflation operation, thereby updating the inflation / deflation time prediction model.

Images