Indirect tire pressure monitoring method and system

Abstract

The invention relates to an indirect tire pressure monitoring method and system. The indirect tire pressure monitoring method comprises the following steps: setting a driving distance threshold value or a use time threshold value; when the driving distance of the vehicle does not reach the driving distance threshold value or the use time does not reach the use time threshold value, a local tire pressure prediction model is accessed, and tire pressure estimation and monitoring are conducted through the local tire pressure prediction model based on sensor data and temperature sensor data collected by an ESC control unit; meanwhile, vehicle driving related data collected by a vehicle end and data processed by the local tire pressure prediction model are sent to a cloud server to be used for training a cloud tire pressure monitoring model; and when the driving distance of the vehicle reaches a driving distance threshold value or the use time reaches a use time threshold value, accessing a cloud tire pressure monitoring model, and estimating and monitoring the tire pressure by the cloud tire pressure monitoring model in combination with real-time vehicle driving data uploaded by a vehicle end. According to the invention, accurate and comprehensive monitoring can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tire pressure monitoring, in particular to an indirect tire pressure monitoring method and system. BACKGROUND

[0002] In the automobile safety system, the tire pressure monitoring system (TPMS) is a key component to ensure driving safety. Tire pressure abnormalities, especially under-inflation, can cause many safety hazards, such as increased tire wear, rising fuel consumption, and even tire blowout in severe cases, which can endanger life. Currently, tire pressure monitoring technology is mainly divided into direct and indirect types. Direct type measures pressure directly by installing sensors in the tire, with accurate data and strong real-time performance, but high cost and complex installation and maintenance. Indirect type is widely used in the automobile market due to its advantage of not requiring a dedicated tire pressure sensor and low cost.

[0003] Existing indirect tire pressure monitoring is mostly based on vehicle operating state parameters to determine tire pressure. It collects data such as tire frequency spectrum information, wheel speed sensor pulse count, and tire radius, establishes an associated model with tire pressure to infer whether it is under-inflated. For example, a decrease in tire pressure will cause the tire rolling radius to decrease, and the under-inflated tire will rotate relatively faster, so the difference in wheel speed sensor pulse count can be used to preliminarily determine the tire pressure. This method uses existing vehicle sensors to achieve low-cost monitoring, meeting certain market demand.

[0004] However, the existing indirect tire pressure monitoring technology has obvious deficiencies. In terms of under-inflated tire positioning, the comparison method between wheels is mostly used, which makes it difficult to determine the specific under-inflated tire position when multiple tire states change similarly. In particular, when all four tires are under-inflated, the difference between the tire parameters is small, and the system is difficult to identify, making it impossible to provide accurate information to the driver and increasing the risk of driving. Moreover, as the vehicle is used, factors such as uneven tire wear, load changes, and suspension aging will change the vehicle operating state parameters, interfering with the monitoring system based on fixed models, leading to decreased accuracy and false positives or false negatives.

[0005] The existing technology also lacks a tire leak warning function. Currently, most systems can only alert when the tire pressure is significantly reduced to an under-inflated state, which is a post-monitoring method. However, tire leakage is a gradual process, and if an early warning can be given at the initial stage of leakage, the driver will have time to take measures to avoid accidents such as tire blowout. However, the existing technology cannot monitor and analyze the tire leakage process in real time, making it difficult to meet the demand for early prevention.

[0006] In addition, the vehicle electronic control unit (ECU) has limited computing power. The ECU design needs to consider cost, power consumption, and reliability, and the computing resources are limited. However, the existing indirect tire pressure monitoring requires a large amount of computing and storage resources to analyze vehicle driving history data and analyze tire pressure changes, which far exceeds the capabilities of the ECU. Therefore, the existing system can only perform simple comparative analysis based on real-time data, and cannot fully utilize historical data to improve monitoring accuracy and reliability.

[0007] Therefore, it is necessary to develop a new indirect tire pressure monitoring method and system. Summary of the Invention

[0008] The purpose of this invention is to provide an indirect tire pressure monitoring method and system, which uses a local model to estimate and monitor tire pressure in the early stages of vehicle operation and trains a cloud model, and then switches to the trained cloud model in the later stages to achieve accurate and comprehensive monitoring.

[0009] In a first aspect, the present invention provides an indirect tire pressure monitoring method, comprising: Set a driving distance threshold or a usage time threshold; When the vehicle's driving distance or usage time does not reach the driving distance threshold, the local tire pressure prediction model is accessed. Based on the sensor data and temperature sensor data collected by the ESC control unit, the local tire pressure prediction model is used to estimate and monitor tire pressure. At the same time, the vehicle driving-related data collected by the vehicle terminal and the data processed by the local tire pressure prediction model are sent to the cloud server for training the cloud tire pressure monitoring model. When the vehicle's driving distance reaches the driving distance threshold or the usage time reaches the usage time threshold, the cloud-based tire pressure monitoring model is connected. The cloud-based tire pressure monitoring model combines the real-time vehicle driving data uploaded from the vehicle to estimate and monitor tire pressure.

[0010] Optionally, tire pressure estimation and monitoring are performed using the local tire pressure prediction model, including: During the vehicle's operation, each wheel calculates its own travel distance based on the wheel speed signal integral and accumulates the number of pulses within the first preset distance. At the same time, the number of pulses in each speed range is compensated based on the preset temperature and speed range pulse compensation relationship to obtain the compensated number of pulses. The pulse count of each of the four wheels is calculated pairwise to obtain the pulse difference or difference ratio between each wheel. When any set of pulse differences or difference ratios exceeds the first preset threshold, it is determined that there is an abnormality in the tire pressure and the underpressure alarm mechanism is immediately triggered. At the same time, the difference or ratio of the number of pulses in each round to the preset standard number of pulses is calculated. When the difference or ratio of the difference in all four rounds exceeds the second preset threshold, it is considered that there is a simultaneous undervoltage situation in all four rounds, and the undervoltage alarm mechanism is immediately triggered.

[0011] Optionally, the method for obtaining the standard pulse count of the four wheels and the compensation relationship between the temperature and vehicle speed ranges and the pulses is as follows: The number of pulses is calibrated for the four wheels traveling a first preset distance under different tire pressures, temperatures, and speed ranges. The number of pulses under one preset temperature and speed range is used as the standard number of pulses for the four wheels. Based on the calibration results of the remaining temperatures and speed ranges, polynomial fitting is performed to obtain the compensation relationship between temperature and speed ranges and pulses.

[0012] Optionally, the number of pulses is calibrated to measure the distance traveled by the four wheels under different tire pressures, temperatures, and speed ranges for a first preset distance, specifically as follows: Temperature parameter settings: -25℃, 0℃, 25℃, and 40℃ were selected as the temperature variables for the calibration experiment; Tire pressure parameter settings: For each temperature value, three tire pressure conditions are set respectively: standard tire pressure, 85% of standard tire pressure, and 75% of standard tire pressure; Speed ​​range division: Vehicle speed is divided into eight ranges, specifically: 35 km / h - 45 km / h, 45 km / h - 55 km / h, 55 km / h - 65 km / h, 65 km / h - 75 km / h, 75 km / h - 85 km / h, 85 km / h - 95 km / h, 95 km / h - 105 km / h, and 105 km / h - 120 km / h; Calibration process: Under each temperature-tire pressure combination condition, the vehicle is controlled to travel a first preset distance at each of the eight speed ranges mentioned above, and the number of pulses generated by each of the four wheels is measured and recorded; The number of pulses generated when the temperature is 25℃, the vehicle speed is 65 km / h - 75 km / h, and the tire pressure is at the standard tire pressure, is taken as the standard number of pulses for the four wheels when traveling the first preset distance.

[0013] Optionally, under normal driving conditions, a filtering operation is performed on the vehicle driving data preset for tire pressure monitoring. The filtering conditions are set as follows: the vehicle speed is greater than a preset vehicle speed threshold, and neither the anti-lock braking system nor the traction control system is in an activated state.

[0014] Optionally, when a wheel calculates that the travel distance has reached the first preset distance based on the wheel speed signal integration, the calculation stops and the pulse count of this wheel is locked. This process continues until the travel distance of all wheels has reached the first preset distance, and then the pulse count of the next four wheels for the first preset distance is calculated in the same way.

[0015] Optionally, in the step of sending the vehicle driving-related data collected by the vehicle terminal and the data processed by the local tire pressure prediction model to the cloud server, the uploaded data includes the wheel speed of the four wheels, steering wheel angle, temperature, pulse count, vehicle speed, first preset distance, working status of the anti-lock braking system, working status of the traction control system, and the compensated pulse count after processing by the local tire pressure prediction model.

[0016] Optionally, in the initial stage of accessing the cloud-based tire pressure monitoring model, the compensated pulse count processed by the local tire pressure prediction model is compared with the pulse count predicted by the cloud-based tire pressure monitoring model. When the difference between the compensated pulse count and the predicted pulse count of a certain wheel is greater than a third preset threshold, it is considered that the tire of this wheel has an abnormal air leak, and an air leak alarm for this tire is output.

[0017] Optionally, the cloud-based tire pressure monitoring model is also used to identify scenarios where the tire pressure is low due to natural tire deflation even though there is no tire leak. If the model identifies that the driving distance has reached a second preset distance or that there is no tire leak and no tire inflation or replacement within a preset time, the cloud-based tire pressure monitoring model outputs a tire inflation prompt. The method for determining whether to inflate or change the tire is as follows: If, during the current ignition cycle, the number of pulses after compensation within a first preset distance for a consecutive preset number of times is reduced by a preset number of pulses compared to the number of pulses after compensation at the first preset distance in the previous ignition cycle, then it is considered that a tire inflation event or a tire replacement event has occurred in this tire.

[0018] Secondly, the present invention provides an indirect tire pressure monitoring system, comprising an ESC control unit on the vehicle side, an on-board communication module, an iTPMS indirect tire pressure calculation module, and a cloud server; wherein, the ESC control unit, the on-board communication module, and the iTPMS indirect tire pressure calculation module on the vehicle side establish a communication connection, a local tire pressure prediction mode is deployed on the vehicle side, and a cloud tire pressure monitoring model is deployed on the cloud server, and the indirect tire pressure monitoring system is configured to perform the steps of the indirect tire pressure monitoring method as described in the present invention.

[0019] The beneficial effects of this invention are: Precise tire underinflation location: This invention can accurately indicate the location of tire underinflation, even in complex scenarios where all four tires are underinflated at the same time, and can accurately predict the location, providing drivers with accurate information and effectively reducing driving risks.

[0020] Early warning of air leaks: This invention can indicate the air leak and its specific location in the tire before the tire pressure is low, giving the driver time to take measures in the early stages of the leak and avoid accidents such as tire blowouts, thus meeting the need for early prevention.

[0021] Improved monitoring accuracy: Through the continuous accumulation of big data and iterative updates of large models, this invention can adapt to changes in vehicle operating parameters, making tire pressure monitoring more accurate and effectively reducing missed and false alarms.

[0022] Automatic identification and updating: This invention integrates algorithms from large models to automatically identify tires after tire inflation or replacement based on big data analysis, and outputs updated prediction results based on these parameters without recalibration. This overcomes the limitation of limited ECU computing resources and fully utilizes data to improve monitoring performance. Attached Figure Description

[0023] Figure 1 This is one of the flowcharts of the indirect tire pressure monitoring method system described in the embodiments of this application; Figure 2 This is the second flowchart of the indirect tire pressure monitoring method described in the embodiments of this application. Figure 3 This is a schematic diagram of the indirect tire pressure monitoring system described in the embodiments of this application. Detailed Implementation

[0024] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0025] like Figure 1 As shown in the embodiments of this application, an indirect tire pressure monitoring method includes: Set a driving distance threshold or a usage time threshold.

[0026] When the vehicle's driving distance has not reached the driving distance threshold (e.g., driving distance M km) or the usage time has not reached the usage time threshold (e.g., T months), the local tire pressure prediction model is accessed. Based on the sensor data and temperature sensor data collected by the ESC control unit, the local tire pressure prediction model is used to estimate and monitor tire pressure. At the same time, the vehicle driving-related data collected by the vehicle terminal and the data processed by the local tire pressure prediction model are sent to the cloud server for training the cloud tire pressure monitoring model.

[0027] When the vehicle's driving distance reaches the driving distance threshold or the usage time reaches the usage time threshold, the cloud-based tire pressure monitoring model is connected. The cloud-based tire pressure monitoring model combines the real-time vehicle driving data uploaded from the vehicle to estimate and monitor tire pressure.

[0028] like Figure 2 As shown below, the implementation steps of the indirect tire pressure monitoring method are explained in detail: (I) Threshold setting and model selection Before the vehicle starts driving, a driving distance threshold or a usage time threshold is first set. These two thresholds serve as the basis for determining whether to use the local tire pressure prediction model or the cloud-based tire pressure monitoring model. If the vehicle's driving distance or usage time does not reach the driving distance threshold or the usage time does not reach the usage time threshold, the system switches to the local tire pressure prediction model; when the vehicle's driving distance or usage time reaches the driving distance threshold or the usage time reaches the usage time threshold, it switches to the cloud-based tire pressure monitoring model.

[0029] (II) Implementation of the local tire pressure prediction model 1. Data Acquisition and Compensation To ensure data accuracy, the vehicle driving data used for tire pressure monitoring is filtered. The filtering criteria are: vehicle speed greater than a preset speed threshold (e.g., greater than 40 km / h), and both the anti-lock braking system (ABS) and traction control system (TCS) are not activated. In reality, ABS and TCS activation indicates wheel slippage or dragging. To eliminate the influence of slippage and dragging on the data, data from 1 second before ABS or TCS activation to the deactivation period is filtered out.

[0030] After filtering out the above data, during vehicle operation, each wheel integrates its wheel speed signal to calculate its travel distance. Simultaneously, the number of pulses within a first preset distance (usually set according to actual needs, such as 1 km) is accumulated. Considering the influence of vehicle speed and temperature on the pulse count, the pulse count for each speed range is compensated according to a preset temperature and speed range compensation relationship, resulting in a compensated pulse count (the pulse counts for the four wheels are denoted as N1, N2, N3, and N4 respectively).

[0031] Due to factors such as turning, the actual distance traveled by the four wheels will vary. Therefore, when the integrated travel distance of a certain wheel reaches a first preset distance, the calculation stops, and the pulse count N of that wheel is locked. i , i=1,2,3,4. After all wheels have traveled a distance equal to the first preset distance, the number of four-wheel pulses for the next first preset distance is calculated again using the same method.

[0032] 2. Assessment of abnormal tire pressure The pulse counts of the four wheels after compensation are calculated pairwise to obtain the pulse difference or difference ratio between each wheel. When any set of pulse differences or difference ratios exceeds a first preset threshold (which is determined according to factory calibration), an abnormal tire pressure is determined, and an underpressure alarm mechanism is immediately triggered. However, this method is a relative comparison of the pulse counts of the four wheels and cannot monitor scenarios where all four wheels are simultaneously underpressured.

[0033] For scenarios where all four wheels are simultaneously undervoltage, the difference or ratio of the pulse count of each wheel to the preset standard pulse count is calculated. When the difference or ratio of the difference of all four wheels exceeds the second preset threshold (which is determined according to the factory calibration), it is considered that there is a situation where all four wheels are simultaneously undervoltage, and the undervoltage alarm mechanism is immediately triggered.

[0034] The method for obtaining the standard pulse count of the four wheels and the compensation relationship between temperature and vehicle speed ranges and the pulses is as follows: The number of pulses is calibrated for the four wheels traveling a first preset distance under different tire pressures, temperatures, and speed ranges. The number of pulses under one preset temperature and speed range is used as the standard number of pulses for the four wheels. Based on the calibration results of the remaining temperatures and speed ranges, polynomial fitting is performed to obtain the compensation relationship between temperature and speed ranges and pulses.

[0035] For example, the standard pulse count for four wheels is obtained through calibration: It should be noted that tire inflation pressure is directly related to the wheel radius. Abnormal tire pressure is monitored by comparing the radii of each wheel. When the vehicle travels the same distance, the wheel radius r and the number of pulses N from the wheel speed sensor are inversely proportional, i.e., r = ZS / (2πN), where Z is the number of toothed rings of the wheel speed sensor and S is the distance. Furthermore, considering that the wheel radius is affected not only by tire pressure but also by vehicle speed and temperature, and since significant differences only occur with large temperature variations, -25℃, 0℃, 25℃, and 40℃ were selected as temperature variables when calibrating the standard pulse count for the four wheels and fitting the compensation relationship between temperature and vehicle speed ranges and the pulses. For each temperature value, three tire pressure conditions were set: standard tire pressure, 85% of standard tire pressure, and 75% of standard tire pressure. Vehicle speed was divided into eight speed ranges (35 km / h - 45 km / h, 45 km / h - 55 km / h, 55 km / h - 65 km / h, 65 km / h - 75 km / h, 75 km / h - 85 km / h, 85 km / h - 95 km / h, 95 km / h - 105 km / h, 105 km / h - 120 km / h). Under each temperature-tire pressure combination, the vehicle was controlled to travel a first preset distance within each of the eight speed ranges, and the number of pulses generated by each of the four wheels was measured and recorded. Finally, the number of pulses generated by the four wheels traveling the first preset distance at a temperature of 25℃, a speed range of 65 km / h - 75 km / h, and standard tire pressure was taken as the standard pulse count for the four wheels (denoted as N for all four wheels). S1、 N S2、 N S3、 N S4 The value of the first preset distance is determined according to specific needs, and is usually 1km.

[0036] The calibration results for the remaining temperature and speed ranges obtained from the calibration are subjected to polynomial fitting to obtain the compensation relationship between the temperature and speed ranges and the pulse.

[0037] 3. Data Upload Vehicle driving-related data collected at the vehicle end, along with data processed by the local tire pressure prediction model, are sent to the cloud. The uploaded data includes wheel speeds, steering wheel angle, temperature, pulse count, vehicle speed, first preset distance, anti-lock braking system (ABS) status, traction control system (TCS) status, and compensated pulse counts (N1, N2, N3, N4) processed by the local tire pressure prediction model. This data will be used to train the cloud-based tire pressure monitoring model, improving its accuracy and adaptability.

[0038] Local tire pressure monitoring (TPMS) prediction models can accurately predict underinflation in all four tires when the vehicle leaves the factory. However, as the vehicle's mileage increases, various components experience wear and tear, and the parameters of various sensors and actuators change. Using the factory-calibrated standard pulse count can lead to misjudgments. Recalibrating the model is labor-intensive and requires specialized personnel. To address this issue, this method deploys a cloud-based TPMS model on a cloud server, estimating the pulse count using this model.

[0039] (III) Implementation of cloud-based tire pressure monitoring model 1. Data collection and analysis During normal vehicle operation, the cloud server continuously collects a large amount of driving data uploaded from the vehicle, as well as information such as the duration of vehicle operation and parking. This data is then analyzed in depth using big data analytics methods such as neural network algorithms. During the analysis, it is necessary to determine whether a tire inflation event has occurred. If the number of pulses in the current ignition cycle of a particular wheel is significantly lower than that of the previous ignition cycle, and this decrease is continuous, then this tire is considered to have experienced an inflation event or a tire replacement event, and this event is used as one of the input factors for data analysis. For example, if, in the current ignition cycle, the number of compensated pulses within a first preset distance (e.g., 1 km) for a consecutive preset number of times (e.g., 3-5 times) is lower than the number of compensated pulses at the first preset distance in the previous ignition cycle by a preset number of pulses (e.g., approximately 100 pulses, the exact number depending on the actual situation), then this tire is considered to have experienced an inflation event or a tire replacement event.

[0040] In this way, the cloud server can predict the number of pulses N1', N2', N3', and N4' for each wheel after traveling the first preset distance under the current driving conditions.

[0041] Meanwhile, the cloud server also stores all calibration-related parameters.

[0042] 2. Anomaly detection and alarm In the initial stage of connecting to the cloud-based tire pressure monitoring model, the compensated pulse counts (N1, N2, N3, N4) processed by the local tire pressure prediction model are compared with the pulse counts predicted by the cloud-based tire pressure monitoring model (denoted as N1', N2', N3', N4', respectively). When the difference between the compensated pulse count and the predicted pulse count of a certain tire exceeds a third preset threshold (determined based on factory calibration), it is considered that the tire has an abnormal air leak, and an air leak alarm message for that tire is output to promptly remind the driver to take appropriate measures.

[0043] Once a period of time has elapsed and no abnormal data has been accumulated, it is used as training data to update the weights and parameters of the cloud-based tire pressure monitoring model.

[0044] 3. Qi replenishment reminder function The cloud-based tire pressure monitoring model also has the ability to identify scenarios where tire pressure is low due to natural tire deflation even when there is no actual leak. Based on big data analysis, if the vehicle has traveled a second preset distance (e.g., 5000km) or has not experienced a leak within a preset time (e.g., 3 months) without needing to inflate or replace the tire, the cloud-based tire pressure monitoring model will output an inflation reminder for that tire, reminding the user to inflate the tire in time to avoid underinflation caused by prolonged natural deflation and ensure driving safety.

[0045] (iv) Fusion strategy of the two algorithms In the initial stage after the vehicle leaves the factory, the calibration parameters are highly accurate, especially the standard pulse number N of the four wheels. S1、 N S2、 N S3、 N S4 Relatively accurate, the local tire pressure monitoring model primarily monitors tire pressure when the vehicle's mileage or usage time is below the threshold, while the cloud server mainly collects data without making predictions. As vehicle mileage increases and time passes, various vehicle components experience wear and tear, and the parameters of various sensors and actuators change. At this point, the factory-calibrated standard pulse count may lead to misjudgments. Once the data covers all driving conditions, the cloud server begins to predict the pulse count using the collected data. As the cloud-based tire pressure monitoring model is continuously trained with new data to improve its accuracy, the local model no longer uses the standard pulse count as a comparison for pinpointing specific under-inflation locations and determining under-inflation in all four tires. Instead, it uses the cloud-based tire pressure monitoring model on the cloud server to identify specific leaking tires and provide inflation prompts, achieving an organic integration of the two algorithms and improving the accuracy and reliability of tire pressure monitoring.

[0046] In this embodiment, an indirect tire pressure monitoring device includes an ESC control unit, an in-vehicle communication module, an iTPMS indirect tire pressure calculation module, and a cloud server. The iTPMS indirect tire pressure calculation module can be integrated into the ESC control unit or other ECU control units. The ESC control unit, iTPMS indirect tire pressure calculation module, and in-vehicle communication module communicate and exchange data via CAN. The in-vehicle communication module and the cloud server exchange data via 4 / 5G wireless communication. The ESC control unit calculates wheel speed signals, pulse counts for each tire, vehicle speed signals, wheel slippage, wheel spin, and other status flags based on data from its connected sensors. The iTPMS indirect tire pressure calculation module calculates the driving status of each wheel based on data provided by the ESC control unit, ambient temperature from a temperature sensor, and data from the cloud server, and estimates whether the tires are underinflated. If underinflation is detected, an underinflation alarm is issued. The in-vehicle communication module is responsible for packaging and processing vehicle-side data and uploading it to the cloud server. The cloud server performs big data tire pressure change analysis based on the data uploaded from the vehicle and sends the analysis results back to the in-vehicle communication module. The iTPMS indirect tire pressure calculation module includes a local tire pressure prediction model deployed on the vehicle and a cloud-based tire pressure monitoring model deployed on a cloud server. The indirect tire pressure monitoring system is configured to perform the steps of the indirect tire pressure monitoring method as described in the embodiments of this application.

[0047] This invention combines a local tire pressure prediction model and a cloud-based tire pressure monitoring model, fully considering the impact of various factors such as vehicle speed and temperature on tire pressure monitoring. Through advanced technologies such as multinomial fitting and neural network algorithms, it achieves accurate monitoring of tire condition, effectively reducing the false alarm rate. The local tire pressure prediction model can quickly estimate and monitor tire pressure in the early stages of vehicle operation, issuing timely warnings. The cloud-based tire pressure monitoring model utilizes big data analytics to continuously optimize the prediction algorithm, providing more comprehensive and accurate tire pressure monitoring services as vehicle driving data accumulates. Simultaneously, it flexibly switches algorithms based on vehicle mileage and time, ensuring reliable tire pressure monitoring at different stages. By uploading vehicle-side data to a cloud server and using big data analytics to continuously train and optimize the cloud-based tire pressure monitoring model, it can adapt to wear and tear on vehicle components, changes in sensor parameters, and other factors, achieving self-optimization and upgrades, thus improving the system's adaptability and stability. This invention can not only detect the underinflation and leakage of a single tire in a timely manner, but also effectively identify scenarios such as simultaneous underinflation of all four tires and spontaneous tire deflation, and provide corresponding alarms and tire inflation prompts, providing drivers with comprehensive tire pressure monitoring services and effectively ensuring driving safety.

[0048] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the protection scope of the present invention.

Claims

1. An indirect tire pressure monitoring method, characterized in that, include: Set a driving distance threshold or a usage time threshold; When the vehicle's driving distance or usage time does not reach the driving distance threshold, the local tire pressure prediction model is accessed. Based on the sensor data and temperature sensor data collected by the ESC control unit, the local tire pressure prediction model is used to estimate and monitor tire pressure. At the same time, the vehicle driving-related data collected by the vehicle terminal and the data processed by the local tire pressure prediction model are sent to the cloud server for training the cloud tire pressure monitoring model. When the vehicle's driving distance reaches the driving distance threshold or the usage time reaches the usage time threshold, the cloud-based tire pressure monitoring model is connected. The cloud-based tire pressure monitoring model combines the real-time vehicle driving data uploaded from the vehicle to estimate and monitor tire pressure.

2. The indirect tire pressure monitoring method according to claim 1, characterized in that, Tire pressure estimation and monitoring using the local tire pressure prediction model includes: During the vehicle's operation, each wheel calculates its own travel distance based on the wheel speed signal integral and accumulates the number of pulses within the first preset distance. At the same time, the number of pulses in each speed range is compensated based on the preset temperature and speed range pulse compensation relationship to obtain the compensated number of pulses. The pulse count of each of the four wheels is calculated pairwise to obtain the pulse difference or difference ratio between each wheel. When any set of pulse differences or difference ratios exceeds the first preset threshold, it is determined that there is an abnormality in the tire pressure and the underpressure alarm mechanism is immediately triggered. At the same time, the difference or ratio of the number of pulses in each round to the preset standard number of pulses is calculated. When the difference or ratio of the difference in all four rounds exceeds the second preset threshold, it is considered that there is a simultaneous undervoltage situation in all four rounds, and the undervoltage alarm mechanism is immediately triggered.

3. The indirect tire pressure monitoring method according to claim 2, characterized in that, The method for obtaining the standard pulse count of the four wheels and the compensation relationship between the temperature and vehicle speed ranges and the pulses is as follows: The number of pulses is calibrated for the four wheels traveling a first preset distance under different tire pressures, temperatures, and speed ranges. The number of pulses under one preset temperature and speed range is used as the standard number of pulses for the four wheels. Based on the calibration results of the remaining temperatures and speed ranges, polynomial fitting is performed to obtain the compensation relationship between temperature and speed ranges and pulses.

4. The indirect tire pressure monitoring method according to claim 3, characterized in that, The number of pulses used to calibrate the first preset distance traveled by the four wheels under different tire pressures, temperatures, and speed ranges is as follows: Temperature parameter settings: -25℃, 0℃, 25℃, and 40℃ were selected as the temperature variables for the calibration experiment; Tire pressure parameter settings: For each temperature value, three tire pressure conditions are set respectively: standard tire pressure, 85% of standard tire pressure, and 75% of standard tire pressure; Speed ​​range division: Vehicle speed is divided into eight ranges, specifically: 35 km / h - 45 km / h, 45 km / h - 55 km / h, 55 km / h - 65 km / h, 65 km / h - 75 km / h, 75 km / h - 85 km / h, 85 km / h - 95 km / h, 95 km / h - 105 km / h, and 105 km / h - 120 km / h; Calibration process: Under each temperature-tire pressure combination condition, the vehicle is controlled to travel a first preset distance at each of the eight speed ranges mentioned above, and the number of pulses generated by each of the four wheels is measured and recorded; The number of pulses generated when the temperature is 25℃, the vehicle speed is 65 km / h - 75 km / h, and the tire pressure is at the standard tire pressure, is taken as the standard number of pulses for the four wheels when traveling the first preset distance.

5. The indirect tire pressure monitoring method according to claim 2, characterized in that, Under normal driving conditions, the vehicle driving data preset for tire pressure monitoring is filtered. The filtering conditions are set as follows: the vehicle speed is greater than the preset vehicle speed threshold, and the anti-lock braking system and traction control system are not in the activated trigger state.

6. The indirect tire pressure monitoring method according to claim 2, characterized in that, Once a wheel has traveled a distance equal to the first preset distance based on the integral of its wheel speed signal, the calculation stops and the pulse count for that wheel is locked. This process continues until all wheels have traveled a distance equal to the first preset distance. Then, the pulse count for the next four wheels at the first preset distance is calculated using the same method.

7. The indirect tire pressure monitoring method according to claim 2, characterized in that, In the step of sending the vehicle driving-related data collected by the vehicle terminal and the data processed by the local tire pressure prediction model to the cloud server, the uploaded data includes the wheel speed of the four wheels, steering wheel angle, temperature, pulse count, vehicle speed, first preset distance, working status of the anti-lock braking system, working status of the traction control system, and the compensated pulse count after processing by the local tire pressure prediction model.

8. The indirect tire pressure monitoring method according to claim 2, characterized in that, In the initial stage of connecting to the cloud-based tire pressure monitoring model, the compensated pulse count processed by the local tire pressure prediction model is compared with the pulse count predicted by the cloud-based tire pressure monitoring model. When the difference between the compensated pulse count and the predicted pulse count of a certain wheel is greater than the third preset threshold, it is considered that the tire of this wheel has an abnormal air leak, and an air leak alarm for this tire is output.

9. The indirect tire pressure monitoring method according to claim 8, characterized in that, The cloud-based tire pressure monitoring model is also used to identify scenarios where the tire pressure is low due to natural tire deflation even though there is no leak. If the model identifies that the driving distance has reached a second preset distance or that there is no leak and no tire inflation or replacement within a preset time, the cloud-based tire pressure monitoring model will output a tire inflation prompt. The method for determining whether to inflate or change the tire is as follows: If, during the current ignition cycle, the number of pulses after compensation within a first preset distance for a consecutive preset number of times is reduced by a preset number of pulses compared to the number of pulses after compensation at the first preset distance in the previous ignition cycle, then it is considered that a tire inflation event or a tire replacement event has occurred in this tire.

10. An indirect tire pressure monitoring system, characterized in that: The system includes an ESC control unit on the vehicle side, an on-board communication module, an iTPMS indirect tire pressure monitoring module, and a cloud server. The ESC control unit, on-board communication module, and iTPMS indirect tire pressure monitoring module on the vehicle side establish a communication connection. A local tire pressure prediction mode is deployed on the vehicle side, and a cloud-based tire pressure monitoring model is deployed on the cloud server. The indirect tire pressure monitoring system is configured to perform the steps of the indirect tire pressure monitoring method as described in any one of claims 1 to 9.

Images