Tire pressure state detection method, device, and vehicle

Abstract

The application provides a tire pressure state detection method, device and vehicle. The tire pressure state detection method provided by the application comprises the following steps: in a current reasoning period, when a wheel does not enter a non-slip chain state in a previous reasoning period, determining whether the wheel enters the non-slip chain state in the current reasoning period; when it is determined that the wheel enters the non-slip chain state in the current reasoning period, acquiring first-type multi-source data of the wheel, and for each first-type data in the first-type multi-source data, determining a confidence parameter of the tire pressure of the wheel belonging to an abnormal category according to the first-type data, to obtain a determination result corresponding to the first-type data; the first-type multi-source data comprises wheel speed signals and wheel load data; and according to the determination result corresponding to the first-type data, determining whether the tire pressure of the wheel is abnormal, to obtain a first identification result. The tire pressure state detection method, device and vehicle provided by the application can improve the tire pressure state detection precision in the non-slip chain state.

Description

Technical Field

[0001] This application relates to the field of vehicles, and more particularly to a method, apparatus and vehicle for detecting tire pressure status. Background Technology

[0002] Tire pressure monitoring is crucial for reducing tire-related risks, improving vehicle handling, and ensuring driving safety. As a key component directly in contact with the road surface, tire pressure directly impacts vehicle stability. Abnormal tire pressure can lead to decreased braking performance, reduced handling stability, and in severe cases, compromised driving safety. Therefore, timely and accurate tire pressure monitoring, along with early warnings of abnormal pressure, helps drivers take preventative measures and avoid safety hazards caused by tire pressure issues.

[0003] Existing tire pressure monitoring methods determine whether tire pressure is abnormal by detecting changes in the tire's rolling radius. However, during actual vehicle operation, the tire rolling radius is affected not only by tire pressure but also by factors such as changes in vehicle posture. Especially in special driving scenarios such as when snow chains are installed, the snow chains further alter the contact characteristics between the tire and the road surface, causing changes in the rolling radius and severely affecting the accuracy of tire pressure monitoring. Summary of the Invention

[0004] In view of this, this application provides a tire pressure condition detection method, apparatus and vehicle to improve the accuracy of tire pressure condition detection under snow chain conditions.

[0005] The first aspect of this application provides a method for detecting tire pressure status, the method comprising:

[0006] Within the current inference cycle, for each wheel on the vehicle under test, if the wheel did not enter the anti-skid chain state in the previous inference cycle, it is determined whether the wheel enters the anti-skid chain state in the current inference cycle.

[0007] When it is determined that the wheel enters the anti-skid chain state in the current inference cycle, the first type of multi-source data of the wheel is acquired, and for each type of data in the first type of multi-source data, the confidence parameter of the tire pressure of the wheel belonging to the abnormal category is determined according to the first type of data, and the judgment result corresponding to the first type of data is obtained; wherein, the first type of multi-source data includes multiple types of first type data such as wheel speed signal and wheel load data.

[0008] Based on the judgment result corresponding to the first type of data, it is determined whether the tire pressure of the wheel is abnormal, and a first identification result is obtained.

[0009] A second aspect of this application provides a tire pressure condition detection device, which includes a determination module, a reasoning module, and an identification module; wherein...

[0010] The determining module is used to determine, within the current inference cycle, whether each wheel on the vehicle under test has entered the anti-skid chain state in the current inference cycle if the wheel did not enter the anti-skid chain state in the previous inference cycle.

[0011] The inference module is used to acquire first-type multi-source data of the wheel when it is determined that the wheel has entered the anti-skid chain state in the current inference cycle, and to determine the confidence parameter of the tire pressure of the wheel belonging to the abnormal category based on each first-type data in the first-type multi-source data, thereby obtaining the judgment result corresponding to the first-type data; wherein, the first-type multi-source data includes multiple first-type data such as wheel speed signal and wheel load data.

[0012] The identification module is used to determine whether the tire pressure of the wheel is abnormal based on the judgment result corresponding to the first type of data, and obtain the first identification result.

[0013] A third aspect of this application provides a vehicle including a domain controller, the domain controller including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of any of the methods provided in the first aspect of this application.

[0014] The tire pressure condition detection method, apparatus, and vehicle provided in this application, within the current inference cycle, for each wheel of the vehicle under test, if the wheel was not in the snow chain state in the previous inference cycle, determine whether the wheel has entered the snow chain state in the current inference cycle. If the wheel is determined to be in the snow chain state in the current inference cycle, acquire first-type multi-source data for the wheel, and determine the confidence level of the tire pressure belonging to the abnormal category based on each first-type data in the first-type multi-source data, obtaining the judgment result for each first-type data. Then, based on the judgment results corresponding to multiple first-type data, determine whether the tire pressure is abnormal, obtaining a first identification result. The first-type multi-source data includes wheel speed signals and wheel load data. By selecting wheel speed signals and wheel load data, which are less affected by snow chains and can characterize tire pressure state changes, a comprehensive judgment of tire pressure state can be made. This not only avoids the influence of snow chain vibration on the detection results but also allows different data sources to complement each other, reducing the detection deviation caused by factors such as snow chain installation from a single data source, thereby improving the accuracy and reliability of tire pressure condition detection under snow chain conditions. Attached Figure Description

[0015] Figure 1A flowchart of Embodiment 1 of the tire pressure status detection method provided in this application;

[0016] Figure 2 A flowchart of Embodiment 2 of the tire pressure status detection method provided in this application;

[0017] Figure 3 A flowchart of Embodiment 3 of the tire pressure status detection method provided in this application;

[0018] Figure 4 A flowchart of Embodiment 4 of the tire pressure status detection method provided in this application;

[0019] Figure 5 The hardware structure diagram of a domain controller is shown as an exemplary embodiment of this application;

[0020] Figure 6 This is a schematic diagram of the tire pressure monitoring device provided in this application. Detailed Implementation

[0021] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0022] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used herein are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0023] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0024] The following specific embodiments are given to illustrate the technical solution of this application in detail.

[0025] Figure 1 This is a flowchart of an embodiment of the tire pressure status detection method provided in this application. Please refer to... Figure 1 The method provided in this embodiment may include:

[0026] S101. In the current inference cycle, for each wheel on the vehicle under test, if the wheel did not enter the anti-skid chain state in the previous inference cycle, determine whether the wheel enters the anti-skid chain state in the current inference cycle.

[0027] Specifically, the inference cycle value is set according to actual needs, and is not limited in this embodiment. For example, in one possible implementation, the inference cycle is 200ms.

[0028] Furthermore, within the current inference cycle, for each wheel of the vehicle under test, it is first determined whether the wheel was not in the snow chain state in the previous inference cycle. Further, if the wheel was not in the snow chain state in the previous inference cycle, it is determined whether the wheel is in the snow chain state in the current inference cycle.

[0029] Understandably, in each inference cycle, it is determined whether the wheel has entered the snow chain state. For the current inference cycle, the specific state of the wheel in the previous inference cycle can be obtained (the specific state of the wheel includes whether it has entered the snow chain state or not). In addition, when the current inference cycle is the first inference cycle, it is assumed that the wheel did not enter the snow chain state in the previous inference cycle.

[0030] Furthermore, in one possible implementation, after installing snow chains on the wheels, the driver can manually select the corresponding driving mode on the central control screen to indicate whether snow chains are currently installed. At this point, the vehicle can determine whether the wheels are in snow chain mode based on the driver's selected driving mode.

[0031] In another possible approach, vehicle operation data within the current inference cycle can be collected, such as wheel speed signals, vehicle longitudinal acceleration, lateral acceleration, and road condition information. Furthermore, feature extraction can be performed on the collected data to determine whether the wheels have entered the anti-skid chain state based on the extracted features.

[0032] S102. When it is determined that the wheel enters the anti-skid chain state in the current inference cycle, the first type of multi-source data of the wheel is acquired, and for each type of data in the first type of multi-source data, the confidence parameter of the tire pressure of the wheel belonging to the abnormal category is determined according to the first type of data, and the judgment result corresponding to the first type of data is obtained; wherein, the first type of multi-source data includes multiple types of first type of data, namely wheel speed signal and wheel load data.

[0033] Specifically, once it is determined that a wheel of the vehicle under test has entered the anti-skid chain state during the current inference cycle, the first type of multi-source data for that wheel is acquired. This first type of multi-source data includes multiple data sets, including wheel speed signals and wheel load data. The wheel speed signal refers to the wheel rotation speed information collected by wheel speed sensors during vehicle operation, reflecting the instantaneous changes in wheel rotation speed. The wheel load data refers to the magnitude of the vertical load acting on a single wheel during vehicle operation, reflecting the actual pressure state borne by the tire.

[0034] Furthermore, for each type of data, the corresponding detection model can be used to identify the data and obtain the confidence parameter that the tire pressure belongs to the abnormal category, thus obtaining the judgment result corresponding to that type of data. It should be noted that the confidence parameter can include the probability that the tire pressure belongs to the abnormal category, or it can include both the probability and confidence level of the tire pressure belonging to the abnormal category.

[0035] For example, a first detection model and a second detection model are pre-trained. The first detection model takes wheel speed signals as input and outputs confidence parameters indicating whether the tire pressure belongs to an abnormal category. The second detection model takes wheel load data as input and outputs confidence parameters indicating whether the tire pressure belongs to an abnormal category.

[0036] It should be noted that the specific implementation principles and processes of the first and second detection models can be found in the descriptions in the previous embodiments, and will not be repeated here.

[0037] Understandably, since different data sources have varying sensitivities to tire pressure anomalies, independently assessing wheel speed signals and wheel load data allows for multi-dimensional assessments. For example, wheel speed signals primarily reflect dynamic response differences caused by variations in tire rolling radius, while wheel load data focuses on stress differences caused by changes in tire load-bearing capacity. By identifying different data sources separately, valid information from each source can be retained, providing a data foundation for subsequent multi-source data-driven assessments of tire pressure anomalies and improving the accuracy and reliability of tire pressure detection in snow chain usage scenarios.

[0038] Furthermore, under snow chain conditions, the impact vibration generated by the periodic contact between the snow chain and the road surface significantly alters the wheel vibration spectrum data (wheel vibration spectrum data refers to the spectrum data obtained after converting the vibration signal of wheel speed changing with time from the time domain to the frequency domain). If tire pressure status identification is based on wheel vibration spectrum data, the accuracy is low. Therefore, in this application, when the wheel is under snow chain conditions, wheel vibration spectrum data is not used as the basis for judging abnormal tire pressure. Instead, wheel speed signals and wheel load data, which are less affected by snow chains and can characterize changes in tire pressure, are selected for tire pressure status identification. This avoids the influence of snow chain vibration on the detection results, reduces misjudgments caused by snow chain installation, and improves the accuracy of abnormal tire pressure detection results.

[0039] S103. Based on the judgment result corresponding to the first type of data, determine whether the tire pressure of the wheel is abnormal, and obtain the first identification result.

[0040] Specifically, in one possible implementation, the judgment result corresponding to each type of data can be compared with the judgment threshold corresponding to each type of data to obtain the identification result corresponding to each type of data. Then, the identification results of all types of data are combined to obtain the first identification result. For example, in one possible implementation, if the judgment result corresponding to each type of data is greater than the corresponding judgment threshold, the tire pressure is determined to be abnormal; otherwise, the tire pressure is determined to be normal. Furthermore, when combining the identification results of all types of data to obtain the first identification result, the first identification result can be determined to be abnormal tire pressure if at least one type of data identification result indicates abnormal tire pressure; otherwise, the first identification result is determined to be normal tire pressure.

[0041] Furthermore, in one possible implementation, the specific implementation process of this step may include:

[0042] Based on the first weight set pre-set for the snow chain status and the judgment results corresponding to each of the first type of data, the first comprehensive probability that the tire pressure of the wheel belongs to the abnormal category is determined, and based on the first comprehensive probability and the first alarm threshold pre-set for the snow chain status, it is determined whether the tire pressure of the wheel is abnormal, thus obtaining the first identification result.

[0043] Specifically, the first set of weights pre-defined for the anti-skid chain status includes a first weight corresponding to the wheel speed signal and a second weight corresponding to the load data. The specific values ​​of the first and second weights are set according to actual needs, and are not limited in this embodiment. For example, in one embodiment, the first weight is 0.4 and the second weight is 0.6.

[0044] Furthermore, based on the judgment results corresponding to each type of data and the weight values ​​corresponding to each type of data, the judgment results of each type of data are weighted, and the weighted result is determined as the first comprehensive probability. It can be understood that the first comprehensive probability is used to comprehensively reflect the degree of tire pressure abnormality jointly characterized by multiple types of data.

[0045] Furthermore, the first alarm threshold preset for the anti-skid chain status is set according to actual needs, and is not limited in this embodiment. For example, in one possible implementation, the first alarm threshold is greater than 0.75.

[0046] In practice, the first comprehensive probability is compared with the first alarm threshold to determine whether there is an abnormal tire pressure at the current wheel. Specifically, when the first comprehensive probability is greater than or equal to the first alarm threshold, the tire pressure is determined to be abnormal, and a first identification result indicating abnormal tire pressure is generated; when the first comprehensive probability is less than the first alarm threshold, the tire pressure is determined to be normal, and a first identification result indicating normal tire pressure is generated.

[0047] It should be noted that by pre-setting a first weight set and a first alarm threshold for the snow chain status, the judgment results corresponding to each first type of data can be weighted and fused based on the first weight set to obtain a first comprehensive probability. Then, based on the first comprehensive probability and the first alarm threshold, it can be directly determined whether the tire pressure is abnormal, and a first identification result can be obtained. In this way, since different types of first data contribute differently to the identification of abnormal tire pressure, setting different weights can reflect the reliability differences of each type of first data, reduce the impact of misjudgment of a single data on the final identification result, and thus further improve the accuracy and robustness of the tire pressure abnormality identification result, especially reducing the misidentification caused by changes in tire rolling characteristics under snow chain conditions.

[0048] The method provided in this embodiment, within the current inference cycle, for each wheel of the vehicle under test, if the wheel did not enter the anti-skid chain state in the previous inference cycle, determines whether the wheel has entered the anti-skid chain state in the current inference cycle. If it is determined that the wheel has entered the anti-skid chain state in the current inference cycle, it acquires first-type multi-source data for the wheel. Based on each first-type data in the first-type multi-source data, it determines the confidence parameter for whether the tire pressure belongs to an abnormal category, obtaining the judgment result for each first-type data. Then, based on the judgment results corresponding to multiple first-type data, it determines whether the tire pressure is abnormal, obtaining a first identification result. The first-type multi-source data includes wheel speed signals and wheel load data. By selecting wheel speed signals and wheel load data, which are less affected by the anti-skid chain and can characterize changes in tire pressure, a comprehensive judgment of the tire pressure state can be made. This not only avoids the influence of anti-skid chain vibration on the detection results but also allows different data sources to complement each other, reducing the detection deviation caused by factors such as anti-skid chain installation from a single data source, thus improving the accuracy and reliability of tire pressure state detection under anti-skid chain conditions.

[0049] Figure 2 This is a flowchart of Embodiment 2 of the tire pressure status detection method provided in this application. Please refer to... Figure 2 Based on the above embodiments, in one possible implementation, the method further includes:

[0050] S201. When the wheel entered the anti-skid chain state in the previous inference cycle, determine whether the wheel has exited the anti-skid chain state in the current inference cycle.

[0051] Referring to the preceding description, in one possible implementation, the decision to disengage from the snow chains can be determined based on the driving mode selected by the driver.

[0052] Furthermore, in another possible implementation, vehicle operation data within the current inference cycle can be collected to determine whether the wheels have exited the anti-skid chain state.

[0053] Specifically, the method further includes: when the wheel entered the anti-skid chain state in the previous inference cycle, and the wheel did not enter the anti-skid chain state in the current inference cycle, the method further includes:

[0054] Perform the step of acquiring the first type of multi-source data of the wheel to identify the tire pressure status using the first type of multi-source data.

[0055] If a wheel enters the anti-skid chain state in the previous inference cycle and has not exited the anti-skid chain state in the current inference cycle, it is considered that the wheel is still in the anti-skid chain state in the current inference cycle. At this time, the first type of multi-source data is used to identify the tire pressure status.

[0056] S202. When it is determined that the wheel has exited the anti-skid chain state in the current inference cycle, the second type of multi-source data of the wheel is acquired, and for each second type of data in the second type of multi-source data, the confidence parameter of the tire pressure of the wheel belonging to the abnormal category is determined according to the second type of data, and the judgment result corresponding to the second type of data is obtained; wherein, the second type of multi-source signal includes multiple second type of data such as wheel speed signal, wheel load data and wheel vibration spectrum data.

[0057] It should be noted that after confirming that the wheel has exited the anti-skid chain state, it indicates that the periodic impact vibration interference introduced by the anti-skid chain has been eliminated, and the wheel's operating state has returned to that of a normal tire. At this time, the second type of multi-source data for the wheel is acquired. This second type of multi-source data includes multiple data sets: wheel speed signal, wheel load data, and wheel vibration spectrum data. The wheel vibration spectrum data refers to the spectrum data obtained by converting the wheel speed vibration signal over time from the time domain to the frequency domain.

[0058] Furthermore, tire pressure status detection is performed for each type of second-class data. Referring to the preceding description, a first detection model, a second detection model, and a third detection model are pre-trained. The first detection model takes wheel speed signals as input and outputs confidence parameters indicating whether the tire pressure belongs to an abnormal category. The second detection model takes wheel load data as input and outputs confidence parameters indicating whether the tire pressure belongs to an abnormal category. The third detection model takes wheel vibration spectrum data as input and outputs confidence parameters indicating whether the tire pressure belongs to an abnormal category.

[0059] It should be noted that the specific implementation principles and processes of each detection model can be found in the descriptions in the previous embodiments, and will not be repeated here.

[0060] The method provided in this embodiment introduces wheel vibration spectrum data to jointly detect tire pressure anomalies when it is determined that the wheel has exited the anti-skid chain state in the current inference cycle. This method can fully utilize the wheel vibration spectrum data after the anti-skid chain interference is eliminated, improving the accuracy of tire pressure identification. Specifically, under anti-skid chain conditions, the periodic contact between the anti-skid chain and the road surface generates strong impact vibrations, causing abnormal energy distributions related to the movement of the anti-skid chain in the wheel vibration spectrum data. This results in the wheel vibration spectrum data failing to accurately reflect the tire's own condition. However, when the wheel exits the anti-skid chain state, the aforementioned periodic impact vibrations disappear, and the wheel vibration spectrum data becomes a dynamic response caused by tire structural characteristics, tire pressure changes, and the tire's contact state with the road surface. At this time, the wheel vibration spectrum data can more realistically characterize changes in tire pressure. Therefore, combining wheel speed signals, wheel load data, and wheel vibration spectrum data for tire pressure status detection allows for a comprehensive assessment of tire pressure status from multiple dimensions, including motion characteristics, force characteristics, and vibration characteristics. This overcomes the limitations of a single data source, reduces misjudgments caused by environmental changes and vehicle operating conditions, and further improves the accuracy and reliability of tire pressure status detection.

[0061] S203. Determine whether the tire pressure of the wheel is abnormal based on the judgment result corresponding to the second type of data, and obtain the second identification result.

[0062] Specifically, in one possible implementation, the judgment result corresponding to each type of second-class data can be compared with the judgment threshold corresponding to each type of second-class data to obtain the identification result corresponding to each type of second-class data. Then, the identification results of all types of second-class data are combined to obtain a second identification result. For example, in one possible implementation, if the judgment result corresponding to each type of second-class data is greater than the corresponding judgment threshold, the tire pressure is determined to be abnormal; otherwise, the tire pressure is determined to be normal. Furthermore, in obtaining the second identification result by combining the identification results of all types of second-class data, the second identification result can be determined to be abnormal tire pressure if at least one type of second-class data identification result indicates abnormal tire pressure; otherwise, the second identification result is determined to be normal tire pressure.

[0063] Optionally, in one possible implementation, the specific implementation method of this step may include: determining a second comprehensive probability that the tire pressure of the wheel belongs to the abnormal category based on a second weight set pre-set for the state without anti-skid chains and the judgment results corresponding to each of the second type of signals; and determining whether the tire pressure of the wheel is abnormal based on the second comprehensive probability and a second alarm threshold pre-set for the state without anti-skid chains, thereby obtaining a second identification result.

[0064] Specifically, the second set of weights pre-defined for the anti-skid chain status includes a third weight corresponding to the wheel speed signal, a fourth weight corresponding to the wheel load data, and a fifth weight corresponding to the wheel vibration spectrum data. The specific values ​​of the third, fourth, and fifth weights are set according to actual needs, and are not limited in this embodiment. For example, in one embodiment, the third weight is 0.4, the fourth weight is 0.4, and the fifth weight is 0.3.

[0065] Furthermore, based on the judgment results corresponding to each type of data and the weight values ​​corresponding to each type of data, the judgment results of each type of data are weighted, and the weighted result is determined as the second comprehensive probability. It can be understood that the second comprehensive probability is used to comprehensively reflect the degree of tire pressure abnormality jointly characterized by multiple types of data.

[0066] The second alarm threshold preset for the no-slip chain state is set according to actual needs, and is not limited in this embodiment. For example, in one possible implementation, the second alarm threshold is greater than 0.8.

[0067] Optionally, in one possible implementation, the second alarm threshold is greater than the first alarm threshold, so that the tire pressure status identification in the absence of snow chains is more stringent than the tire pressure status identification in the presence of snow chains.

[0068] In practice, the second comprehensive probability is compared with the second alarm threshold to determine whether there is an abnormal tire pressure at the current wheel. Specifically, when the second comprehensive probability is greater than or equal to the second alarm threshold, the tire pressure is determined to be abnormal, and a second identification result indicating abnormal tire pressure is generated; when the second comprehensive probability is less than the second alarm threshold, the tire pressure is determined to be normal, and a second identification result indicating normal tire pressure is generated.

[0069] It should be noted that by pre-setting a second weight set and a second alarm threshold for the tire pressure abnormality state without anti-skid chains, the judgment results corresponding to each second type of data can be weighted and fused based on the second weight set to obtain a second comprehensive probability. Then, based on the second comprehensive probability and the second alarm threshold, it can be directly determined whether the tire pressure is abnormal, thus obtaining a second identification result. In this way, since different types of second-class data contribute differently to the identification of tire pressure abnormalities, setting different weights can reflect the reliability differences of each type of second-class data, reduce the impact of misjudgment of a single data point on the final identification result, and thus further improve the accuracy and robustness of the tire pressure abnormality identification result in the tire pressure abnormality state without anti-skid chains.

[0070] Optionally, in one possible implementation, the method further includes:

[0071] When the wheel did not enter the anti-skid chain state in the previous inference cycle and the wheel does not enter the anti-skid chain state in the current inference cycle, the step of acquiring the second type of multi-source data of the wheel is executed;

[0072] Specifically, if the wheel did not enter the anti-skid chain state in the previous inference cycle and it also does not enter the anti-skid chain state in the current inference cycle, then the wheel is considered to be in an anti-skid chain state. In this case, the second type of multi-source data is acquired, and the tire pressure status is identified using the second type of multi-source data.

[0073] The method provided in this embodiment, within the current inference cycle, for each wheel on the vehicle under test, when the wheel entered the anti-skid chain state in the previous inference cycle, further determines whether the wheel has exited the anti-skid chain state in the current inference cycle. Then, when it is determined that the wheel has exited the anti-skid chain state in the current cycle, the tire pressure state is identified based on wheel speed signal, wheel load data, and wheel vibration spectrum data. This method can comprehensively utilize tire rolling characteristics, force characteristics, and vibration characteristics to detect tire pressure state, improve the information richness of tire pressure anomaly detection, and thus improve the accuracy and reliability of tire pressure anomaly identification.

[0074] Figure 3 This is a flowchart of Embodiment 3 of the tire pressure status detection method provided in this application. Please refer to... Figure 3 In one possible implementation, based on the above embodiments, determining whether the wheel enters the snow chain state in the current inference cycle, or determining whether the wheel exits the snow chain state in the current inference cycle, includes:

[0075] S301. Obtain the wheel vibration spectrum data collected in each of the preset number of sampling periods before the current time.

[0076] Specifically, the specific value of the sampling period is set according to actual needs, and this embodiment does not limit it. Furthermore, the sampling period can be the same as or different from the inference period. When the sampling period and inference period are different, the sampling period can be longer or shorter than the inference period; this embodiment does not limit it. The following explanation uses the example of the sampling period and inference period being the same.

[0077] Specifically, the vehicle periodically collects wheel vibration spectrum data according to a sampling period. In this step, wheel vibration spectrum data collected in each sampling period within a preset number of sampling periods can be obtained, thus acquiring a preset number of wheel vibration spectrum data. The specific value of the preset number is set according to actual needs, and is not limited in this embodiment. For example, in one embodiment, the preset number is 10. In another embodiment, when determining whether the wheel has entered the anti-skid chain state in the current period, the preset number is a first preset value. When determining whether the wheel has exited the anti-skid chain state in the current inference period, the preset number is a second preset value, which is greater than the first preset value. For example, in one embodiment, the first preset value is 10, and the second preset value is 20.

[0078] S302. For the wheel vibration spectrum data collected in each sampling period, determine the first energy value corresponding to the first frequency band in the wheel vibration spectrum data and the second energy value corresponding to the second frequency band in the wheel vibration spectrum data, and determine the ratio of the first energy value and the second energy value to obtain the energy ratio corresponding to the sampling period.

[0079] Specifically, for the wheel vibration spectrum data collected in each sampling period, firstly, the first frequency band and the second frequency band are identified in the wheel vibration spectrum data, and the first energy value of the first frequency band and the second energy value of the second frequency band are calculated respectively.

[0080] It should be noted that both the first and second frequency bands refer to frequency ranges within the wheel vibration spectrum data. The first frequency band reflects the impact vibration characteristics generated by the periodic collisions between the snow chains and the road surface after the installation of snow chains. Specifically, it refers to the frequency band in the wheel vibration spectrum data that characterizes the impact vibration characteristics introduced by the snow chains. Specifically, wheel vibration spectrum data under different operating conditions can be collected through actual vehicle testing, and the energy changes in each frequency range can be compared and analyzed with and without snow chains. It can be determined that after installing snow chains, the vibration spectrum shows a significant energy enhancement in the target frequency band compared to the state without snow chains. Therefore, this target frequency band can be defined as the first frequency band. For example, in one embodiment, the first frequency band is the 80–200 Hz band. This first frequency band can effectively characterize the abnormal vibration energy changes caused by the snow chains.

[0081] Furthermore, the second frequency band serves as a reference band, used to characterize the frequency range corresponding to the wheel's own vibration characteristics in the wheel vibration spectrum data. Specifically, based on a large amount of real-vehicle test data without snow chains, statistical analysis can be performed on the energy distribution within different frequency ranges of the wheel vibration spectrum. The frequency range that is less affected by snow chain impact and can stably reflect the normal vibration state of the wheel can be selected as the second frequency band. The determination of the second frequency band can comprehensively consider the energy stability within the frequency band, the degree of environmental noise influence, and the distinguishability from the first frequency band, to ensure that the energy change within the second frequency band is relatively stable before and after the installation of snow chains.

[0082] It should be noted that when calculating the vibration energy value corresponding to a frequency band, the amplitude corresponding to each frequency component in that frequency band can be integrated, and the integrated value can be determined as the energy value.

[0083] Furthermore, after obtaining the first energy value and the second energy value, the ratio of the first energy value to the second energy value is calculated to obtain the energy ratio corresponding to the current sampling period. This energy ratio is used to characterize the degree of enhancement of vibration energy in the first frequency band relative to vibration energy in the second frequency band.

[0084] It is understandable that when a vehicle is not equipped with snow chains, the wheel vibration energy is usually evenly distributed across all frequency bands. However, after snow chains are installed, the periodic collisions between the snow chains and the road surface generate strong impact vibrations during wheel rotation, causing a significant energy enhancement in the first frequency band of the wheel vibration spectrum data. This results in a significant increase in the first energy value relative to the second energy value, thus causing a significant change in the energy ratio. For example, in one embodiment, without snow chains, the ratio of the first energy value to the second energy value is 0.1 to 0.5, while after snow chains are installed, the ratio is 5 to 30.

[0085] S303. Determine whether the wheel is in anti-skid chain state in each sampling period based on the energy ratio corresponding to each sampling period, and obtain the judgment result corresponding to each sampling period.

[0086] In practice, after obtaining the energy ratio corresponding to the sampling period, the energy ratio corresponding to each sampling period is compared with a pre-calibrated judgment threshold to determine whether the wheel is in anti-skid chain condition during that sampling period. Specifically, for each sampling period, when the energy ratio is greater than or equal to the pre-calibrated judgment threshold, it indicates that the vibration energy in the first frequency band is significantly enhanced compared to the vibration frequency band of the second frequency band, that is, the wheel vibration spectrum data shows an abnormal energy distribution that conforms to the characteristics of anti-skid chain introduction. At this time, it is determined that the wheel is in anti-skid chain condition during that sampling period; when the energy ratio is less than the above judgment threshold, it is considered that there is no significant energy enhancement in the first frequency band, and it is determined that the wheel is in anti-skid chain condition during that sampling period.

[0087] The pre-defined judgment threshold can be obtained through real-vehicle testing. Specifically, wheel vibration spectrum data of the vehicle under different operating conditions can be collected. For example, wheel vibration spectrum data of the vehicle without snow chains and wheel vibration spectrum data of the vehicle after installing different types of snow chains can be collected. Specifically, in the case of no snow chains, wheel vibration spectrum data of the vehicle at different speeds, road conditions, and load conditions can be collected, and the corresponding energy ratio can be calculated to obtain the energy ratio distribution range in the case of no snow chains. In the case of snow chains, wheel vibration spectrum data of the vehicle under the same or similar operating conditions after installing snow chains can be collected, and the corresponding energy ratio can be calculated to obtain the energy ratio distribution range in the case of snow chains. Finally, the judgment threshold can be determined based on the energy ratio distribution range in the case of no snow chains and the energy ratio distribution range in the case of snow chains. For example, the boundary value between the maximum energy ratio statistical value in the case of no snow chains and the minimum energy ratio statistical value in the case of snow chains can be used as the judgment threshold. For example, in one embodiment, the judgment threshold is 3.

[0088] S304. Based on the judgment results corresponding to the preset number of sampling periods, determine whether the wheel enters the anti-skid chain state or exits the anti-skid chain state in the current inference period.

[0089] Specifically, after obtaining the judgment results corresponding to a preset number of sampling periods, statistical analysis can be performed on all judgment results to determine whether the wheel has undergone a change in anti-skid chain status. Specifically, when it is necessary to determine whether the wheel has entered the anti-skid chain state, for the preset number of sampling periods, a first number of judgment results indicating "in anti-skid chain state" is counted, and the ratio of this first number to the preset number is calculated to obtain a first ratio. When the first ratio is greater than or equal to a first threshold, it indicates that the wheel vibration spectrum data shows characteristic changes introduced by the anti-skid chain in multiple consecutive sampling periods. At this time, it is determined that the wheel has entered the anti-skid chain state.

[0090] Similarly, when it is necessary to determine whether a wheel has exited the anti-skid chain state, based on the judgment results corresponding to a preset number of sampling periods, a second number of judgment results indicating "in a no-skid chain state" is counted, and the ratio of the second number to the preset number is calculated to obtain a second ratio. Furthermore, when the second ratio is greater than or equal to a second threshold, it indicates that the characteristic vibration caused by the anti-skid chain has continuously disappeared, and the wheel vibration spectrum data has recovered to the characteristic distribution of the no-skid chain state. At this time, it is determined that the wheel has exited the anti-skid chain state in the current inference period.

[0091] In practice, the preset quantity and the first and second thresholds can be the same when determining whether to enter or exit the anti-skid chain state. For example, the preset quantity is 10, and both the first and second thresholds are 8. Of course, even with the same preset quantity, the first and second thresholds can be different. For example, the first threshold can be 6, and the second threshold can be 8, meaning the criteria for exiting the anti-skid chain state are more stringent.

[0092] It should be noted that by acquiring wheel vibration spectrum data in each sampling period, and extracting the first energy value corresponding to the first frequency band that characterizes the impact vibration introduced by the snow chain, and the second energy value corresponding to the second frequency band that characterizes the normal vibration of the wheel, the energy ratio of each sampling period is determined based on the ratio of the two. The determination of whether the wheel is in a snow chain state in each sampling period is then based on the energy ratio of each sampling period, resulting in a judgment result for each sampling period. This judgment result is then combined with the judgment results of a preset number of sampling periods for a comprehensive judgment. This reduces misjudgments caused by factors such as road disturbances and vehicle attitude changes within a single sampling period, improving the accuracy and stability of snow chain state identification. Therefore, during the process of snow chain state changes, it is possible to more reliably determine whether the wheel has entered or exited the snow chain state, and then adaptively select an appropriate tire pressure detection strategy for tire pressure state detection, further improving the accuracy of tire pressure state detection.

[0093] Optionally, in one possible implementation, when determining whether the wheel has entered the anti-skid chain state, the preset number is a first preset value; determining whether the wheel has entered the anti-skid chain state based on the judgment results corresponding to the preset number of sampling periods includes:

[0094] (1) Find the first target judgment result that satisfies the first condition from the judgment results corresponding to the preset number of sampling periods, and determine the first ratio of the number of the first target judgment results to the preset number; wherein, the first condition is: the judgment result is in the anti-skid chain state.

[0095] (2) When the first ratio is greater than the first threshold, it is determined that the wheel has entered the anti-skid chain state in the current inference cycle; otherwise, it is determined that the wheel has not entered the anti-skid chain state in the current inference cycle.

[0096] In specific implementation, for example, the first preset is 10 and the first threshold is 8. That is, in 10 consecutive sampling periods, the judgment result corresponding to 8 sampling periods is "in anti-skid chain state". Only then is it determined that the wheel has entered the anti-skid chain state in the current inference period.

[0097] Optionally, in one possible implementation, when determining whether the wheel has exited the snow chain state, the preset number is a second preset value, which is greater than the first preset value; determining whether the wheel has exited the snow chain state based on the judgment results corresponding to the preset number of sampling periods includes:

[0098] (1) Find a second target judgment result that satisfies the second condition from the judgment results corresponding to the preset number of sampling periods, and determine the second ratio of the number of the second target judgment results to the preset number; wherein, the second condition is: the judgment result is in a slip chain-free state;

[0099] (2) When the second ratio is greater than the second threshold, it is determined that the wheel has exited the anti-skid chain state in the current inference cycle; otherwise, it is determined that the wheel has not exited the anti-skid chain state in the current inference cycle; wherein, the second threshold is greater than the first threshold.

[0100] In specific implementation, for example, the second preset is 20 and the first threshold is 18. That is, in 20 consecutive sampling periods, the judgment result corresponding to 18 sampling periods is "in a slip chain-free state". Only then is it determined that the wheel has exited the slip chain state in the current inference period.

[0101] As described above, it's understandable that different criteria are used to determine whether a wheel has entered or exited the snow chain condition. The number of sampling periods used for exiting the snow chain condition is greater than that used for entering, and the threshold for exiting is higher than that for entering, making the criteria for determining whether a wheel has exited the snow chain condition more stringent. By raising the exit threshold, misjudgments of exiting the snow chain condition due to brief fluctuations in vibration characteristics can be avoided, thus reducing frequent switching between snow chain entry and exit, improving the stability and reliability of snow chain condition identification, and consequently reducing the interference caused by changes in snow chain condition to the subsequent tire pressure monitoring process.

[0102] Figure 4 This is a flowchart of Embodiment 4 of the tire pressure status detection method provided in this application. Please refer to... Figure 4 In one possible implementation, based on the above embodiments, after determining that the wheel enters the anti-skid chain state in the current inference cycle, the method further includes:

[0103] S401. Obtain the energy ratio corresponding to each sampling period within a preset time period, and determine the energy ratio change trend based on the energy ratio corresponding to each sampling period within the preset time period.

[0104] Specifically, the specific value of the preset duration is set according to actual needs, and is not limited in this embodiment. For example, in one embodiment, the preset duration is the duration corresponding to a preset number of sampling periods before the current time.

[0105] In practice, the energy ratios of multiple consecutive sampling periods within a preset time period can be arranged in chronological order to form an energy ratio change sequence.

[0106] Furthermore, the trend of energy ratio change is determined based on the energy ratio change sequence. For example, by calculating the difference in energy ratio between adjacent sampling periods, the sequence of all differences is determined as the trend of energy ratio change.

[0107] S402. Determine whether the anti-skid chain is worn based on the energy ratio corresponding to each sampling period within the preset time and the trend of the energy ratio change, and obtain the wear identification result.

[0108] Optionally, in one possible implementation, the wear of the anti-skid chain is determined when the energy ratio corresponding to at least one sampling period is less than a preset threshold, and / or when the energy ratio change trend indicates that the energy ratio is gradually decreasing.

[0109] The method provided in this embodiment, after determining that the wheel has entered the anti-skid chain state in the current inference cycle, acquires the energy ratio corresponding to each sampling cycle within a preset time period, and determines the energy ratio change trend based on the energy ratio corresponding to each sampling cycle within the preset time period. Then, based on the energy ratio corresponding to each sampling cycle within the preset time period and the energy ratio change trend, it determines whether the anti-skid chain is worn, thus obtaining a wear identification result. In this way, the gradual change in vibration characteristics during the anti-skid chain wear process can be utilized to achieve continuous monitoring of the anti-skid chain state.

[0110] Corresponding to the aforementioned embodiment of a tire pressure condition detection method, this application also provides an embodiment of a tire pressure condition detection device.

[0111] An embodiment of the tire pressure monitoring device disclosed in this application can be applied to a domain controller. The device embodiment can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor of its domain controller reading the corresponding computer program instructions from non-volatile memory into memory and executing them. From a hardware perspective, such as... Figure 5 As shown, Figure 5 The hardware structure diagram of the domain controller shown in this exemplary embodiment of the application, except for Figure 5 In addition to the processor, memory, network interface, and non-volatile memory shown, other hardware may also be included, which will not be described in detail here.

[0112] Figure 6 This is a schematic diagram of the tire pressure monitoring device provided in this application. Please refer to... Figure 6 The apparatus provided in this embodiment includes a determining module 610, a reasoning module 620, and an identification module 630; wherein,

[0113] The determining module 610 is used to determine, within the current inference cycle, whether each wheel on the vehicle under test has entered the anti-skid chain state in the current inference cycle if the wheel did not enter the anti-skid chain state in the previous inference cycle.

[0114] The inference module 620 is used to acquire first-type multi-source data of the wheel when it is determined that the wheel has entered the anti-skid chain state in the current inference cycle, and to determine the confidence parameter of the tire pressure of the wheel belonging to the abnormal category based on each first-type data in the first-type multi-source data, thereby obtaining the judgment result corresponding to the first-type data; wherein, the first-type multi-source data includes multiple first-type data such as wheel speed signal and wheel load data;

[0115] The identification module 630 is used to determine whether the tire pressure of the wheel is abnormal based on the judgment result corresponding to the first type of data, and obtain the first identification result.

[0116] The apparatus of this embodiment can be used to perform... Figure 1 The steps of the method embodiment shown are similar in principle and process, and will not be repeated here.

[0117] Please continue to refer to Figure 5 This application also provides a vehicle that includes a domain controller, the domain controller including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of any of the methods provided in the first aspect of this application.

[0118] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0119] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0120] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for detecting tire pressure status, characterized in that, The method includes: Within the current inference cycle, for each wheel on the vehicle under test, if the wheel did not enter the anti-skid chain state in the previous inference cycle, it is determined whether the wheel enters the anti-skid chain state in the current inference cycle. When it is determined that the wheel enters the anti-skid chain state in the current inference cycle, the first type of multi-source data of the wheel is acquired, and for each type of data in the first type of multi-source data, the confidence parameter of the tire pressure of the wheel belonging to the abnormal category is determined according to the first type of data, and the judgment result corresponding to the first type of data is obtained; wherein, the first type of multi-source data includes multiple types of first type data such as wheel speed signal and wheel load data. Based on the judgment result corresponding to the first type of data, it is determined whether the tire pressure of the wheel is abnormal, and a first identification result is obtained.

2. The method according to claim 1, characterized in that, The method further includes: When the wheel entered the anti-skid chain state in the previous inference cycle, determine whether the wheel has exited the anti-skid chain state in the current inference cycle; When it is determined that the wheel has exited the anti-skid chain state in the current inference cycle, the second type of multi-source data of the wheel is acquired, and for each second type of data in the second type of multi-source data, the confidence parameter of the tire pressure of the wheel belonging to the abnormal category is determined according to the second type of data, and the judgment result corresponding to the second type of data is obtained; wherein, the second type of multi-source data includes multiple second type of data such as wheel speed signal, wheel load data and wheel vibration spectrum data; Based on the judgment result corresponding to the second type of data, determine whether the tire pressure of the wheel is abnormal, and obtain the second identification result.

3. The method according to claim 1, characterized in that, The step of determining whether the tire pressure of the wheel is abnormal based on the judgment result corresponding to the first type of data, and obtaining the first identification result, includes: Based on the first weight set pre-set for the anti-skid chain status and the judgment results corresponding to each of the first type of data, the first comprehensive probability that the tire pressure of the wheel belongs to the abnormal category is determined; Based on the first comprehensive probability and the first alarm threshold preset for the anti-skid chain status, it is determined whether the tire pressure of the wheel is abnormal, and a first identification result is obtained; And / or, The step of determining whether the tire pressure of the wheel is abnormal based on the judgment result corresponding to the second type of data, and obtaining the second identification result, includes: Based on the second weight set pre-set for the state without anti-skid chains and the judgment results corresponding to each of the second type of data, the second comprehensive probability that the tire pressure of the wheel belongs to the abnormal category is determined; Based on the second comprehensive probability and the second alarm threshold preset for the state without anti-skid chains, it is determined whether the tire pressure of the wheel is abnormal, and a second identification result is obtained.

4. The method according to claim 2, characterized in that, The method further includes: When the wheel did not enter the anti-skid chain state in the previous inference cycle and the wheel does not enter the anti-skid chain state in the current inference cycle, the step of acquiring the second type of multi-source data of the wheel is executed; And / or, When the wheel enters the anti-skid chain state in the previous inference cycle and the wheel has not exited the anti-skid chain state in the current inference cycle, the step of acquiring the first type of multi-source data of the wheel is executed.

5. The method according to claim 2, characterized in that, Determining whether the wheel has entered the snow chain state in the current inference cycle, or determining whether the wheel has exited the snow chain state in the current inference cycle, includes: Obtain the wheel vibration spectrum data collected in each of the preset number of sampling periods before the current moment; For the wheel vibration spectrum data collected in each sampling period, a first energy value corresponding to the first frequency band in the wheel vibration spectrum data and a second energy value corresponding to the second frequency band in the wheel vibration spectrum data are determined, and the ratio of the first energy value to the second energy value is determined to obtain the energy ratio corresponding to the sampling period. Based on the energy ratio corresponding to each sampling period, determine whether the wheel is in anti-skid chain condition in each sampling period, and obtain the judgment result corresponding to each sampling period; Based on the judgment results corresponding to the preset number of sampling periods, it is determined whether the wheel enters the anti-skid chain state or exits the anti-skid chain state in the current inference period.

6. The method according to claim 5, characterized in that, When determining whether the wheel has entered the anti-skid chain state in the current inference cycle, the preset number is a first preset value; The step of determining whether the wheel has entered the anti-skid chain state in the current inference cycle based on the judgment results corresponding to the preset number of sampling cycles includes: From the judgment results corresponding to the preset number of sampling periods, find a first target judgment result that satisfies the first condition, and determine a first ratio between the number of the first target judgment results and the preset number; wherein, the first condition includes: the judgment result is in the anti-skid chain state; If the first ratio is greater than the first threshold, it is determined that the wheel has entered the anti-skid chain state in the current inference cycle; otherwise, it is determined that the wheel has not entered the anti-skid chain state in the current inference cycle.

7. The method according to claim 6, characterized in that, When determining whether the wheel has exited the anti-skid chain state in the current reasoning cycle, the preset number is a second preset value, which is greater than the first preset value; The step of determining whether the wheel has exited the anti-skid chain state based on the judgment results corresponding to the preset number of sampling periods includes: From the judgment results corresponding to the preset number of sampling periods, find the second target judgment result that satisfies the second condition, and determine the second ratio of the number of the second target judgment results to the preset number; wherein, the second condition includes: the judgment result is in a slip chain-free state; When the second ratio is greater than the second threshold, it is determined that the wheel has exited the anti-skid chain state in the current inference cycle; otherwise, it is determined that the wheel has not exited the anti-skid chain state in the current inference cycle; wherein, the second threshold is greater than the first threshold.

8. The method according to claim 6, characterized in that, After determining that the wheel has entered the anti-skid chain state in the current inference cycle, the method further includes: Obtain the energy ratio corresponding to each sampling period within a preset time period, and determine the energy ratio change trend based on the energy ratio corresponding to each sampling period within the preset time period; Based on the energy ratio corresponding to each sampling period within the preset time period and the trend of the energy ratio change, it is determined whether the anti-skid chain is worn, and the wear identification result is obtained.

9. A tire pressure monitoring device, characterized in that, The tire pressure monitoring device includes a determination module, a reasoning module, and an identification module; wherein... The determining module is used to determine, within the current inference cycle, whether each wheel on the vehicle under test has entered the anti-skid chain state in the current inference cycle if the wheel did not enter the anti-skid chain state in the previous inference cycle. The inference module is used to acquire first-type multi-source data of the wheel when it is determined that the wheel has entered the anti-skid chain state in the current inference cycle, and to determine the confidence parameter of the tire pressure of the wheel belonging to the abnormal category based on each first-type data in the first-type multi-source data, thereby obtaining the judgment result corresponding to the first-type data; wherein, the first-type multi-source data includes multiple first-type data such as wheel speed signal and wheel load data. The identification module is used to determine whether the tire pressure of the wheel is abnormal based on the judgment result corresponding to the first type of data, and obtain the first identification result.

10. A vehicle, characterized in that, The vehicle includes a domain controller, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.

Images