Tire detection method and system, electronic device and storage medium

Abstract

The invention discloses a tire detection method and system, an electronic device and a storage medium. The tire detection method comprises the following steps: collecting measurement data of a tire pressure sensor; identifying a vehicle state using the measured data; adjusting the acquisition frequency of a tire pressure sensor and an awakening mechanism of a microcontroller according to the vehicle state; acquiring tire pressure data by using a tire pressure sensor under the acquisition frequency; and under the awakening mechanism, awakening the microcontroller, and sending the tire pressure data to a receiving end according to a preset sending frequency corresponding to the vehicle state by utilizing the microcontroller. According to the technical scheme, the technical problem that in the prior art, a tire pressure sensor depends on periodic sampling and fixed-frequency communication, and consequently a large amount of invalid power consumption is generated can be solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle data detection, and in particular to a tire detection method and system, an electronic device, and a storage medium. BACKGROUND

[0002] At present, most vehicles are equipped with tire pressure sensors. The main function of the tire pressure sensor is to monitor the key data such as the tire pressure and temperature in real time, and transmit the information to the display screen or control system in the vehicle to provide real-time feedback of the tire state for the driver, thereby ensuring driving safety.

[0003] However, the conventional tire pressure sensor relies on periodic sampling and fixed frequency communication (such as sending once every 60 seconds), which results in a large amount of invalid power consumption regardless of the vehicle state. SUMMARY

[0004] The present application provides a tire detection method, system, electronic device, and storage medium, which aims to effectively solve the technical problem that the tire pressure sensor relies on periodic sampling and fixed frequency communication to produce a large amount of invalid power consumption in the prior art.

[0005] According to a first aspect of the present application, the present application provides a tire detection method, comprising: collecting measurement data of a tire pressure sensor; identifying a vehicle state by using the measurement data; adjusting the collection frequency of the tire pressure sensor and the wake-up mechanism of a microcontroller according to the vehicle state; collecting tire pressure data by using the tire pressure sensor at the collection frequency; and waking up the microcontroller under the wake-up mechanism, and sending the tire pressure data to a receiving end by using the microcontroller according to a preset sending frequency corresponding to the vehicle state.

[0006] In a possible design, other data can also be used to identify the state of the vehicle, such as using the speed sensor of the vehicle, the engine speed signal, and the state of the gearbox to identify that the vehicle is in a parking state, a low-speed driving state, or a high-speed driving state.

[0007] In a possible design, the tire detection method further comprises: inputting the tire pressure data into a pre-trained abnormality identification model, the abnormality identification model being used to perform abnormality classification on the input tire pressure data; and outputting pressure compensation or predictive alarm information of the tire pressure data in the case of different categories of abnormality.

[0008] In a possible design, the measurement data includes centrifugal acceleration; and the identifying the vehicle state according to the measurement data includes: identifying, according to different centrifugal accelerations, that the vehicle is in a parking state, a low-speed driving state or a high-speed driving state; and wherein, when the centrifugal acceleration is 0g, the vehicle is in the parking state; when the centrifugal acceleration is in a preset first range, the vehicle is in the low-speed driving state; and when the centrifugal acceleration is in a preset second range, the vehicle is in the high-speed driving state, wherein any value in the second range is greater than any value in the first range.

[0009] In a possible design, the measurement data includes lateral acceleration, tire pressure change, temperature change and wheel speed difference, longitudinal acceleration, vertical acceleration, tire temperature, wheel speed difference and acceleration noise; and the identifying the vehicle state according to the measurement data includes: identifying, according to the lateral acceleration, the tire pressure change, the temperature change and the wheel speed difference, whether the vehicle is in an over-bend state; or identifying, according to the longitudinal acceleration, the tire pressure change and the temperature change, whether the vehicle is in an emergency acceleration or emergency braking state; or identifying, according to the vertical acceleration, the tire pressure change and the temperature change, whether the vehicle is in a state of a bumpy road section; or identifying, according to the tire temperature, the tire pressure change and the wheel speed difference, whether the vehicle is in a state of an icy road; or identifying, according to the tire temperature, the tire pressure change and the acceleration noise, whether the vehicle is in a state of a high-temperature road.

[0010] In a possible design, the wake-up mechanism of the microcontroller includes: when the tire pressure sensor collects the tire pressure data, or processes or transmits the tire pressure data, the microcontroller is woken up, otherwise the microcontroller is put to sleep.

[0011] It should be noted that other controllers can also be arranged in the vehicle to support other functions of the vehicle.

[0012] In a possible design, the transmitting, by the microcontroller, the tire pressure data to the receiving end according to a preset transmission frequency corresponding to the vehicle state includes: if the tire pressure data is classified as normal by the abnormality identification model, the tire pressure data is transmitted according to a preset first frequency; if the tire pressure data is classified as abnormal by the abnormality identification model, the tire pressure data is transmitted according to a second frequency corresponding to an abnormal type, or in the case that the abnormal type is an environmental pressure and temperature change, the pressure compensation is used to correct the abnormal tire pressure data, and if the difference between the corrected tire pressure data and historical tire pressure data exceeds a preset threshold, a predictive warning information is sent.

[0013] In a possible design, the tire detection method further includes: uploading the tire pressure data, the abnormality classification of the tire pressure data, the pressure compensation, and the predictive alarm information to a cloud, and obtaining tire pressure data, an abnormality classification of tire pressure data, a pressure compensation, and predictive alarm information of a same model vehicle from the cloud; and retraining the abnormality recognition model by using the tire pressure data, the abnormality classification of the tire pressure data, the pressure compensation, and the predictive alarm information of the same model vehicle obtained from the cloud.

[0014] According to a second aspect of the present application, the present application further provides a tire detection system, including: a first data collection module, configured to collect measurement data of a tire pressure sensor; a vehicle state recognition module, configured to recognize a vehicle state by using the measurement data; an adjustment module, configured to adjust a collection frequency of the tire pressure sensor and a wake-up mechanism of a microcontroller according to the vehicle state; a second data collection module, configured to collect tire pressure data by using the tire pressure sensor at the collection frequency; and a data sending module, configured to wake up the microcontroller at the wake-up mechanism, and send the tire pressure data to a receiving end by using the microcontroller according to a preset sending frequency corresponding to the vehicle state.

[0015] According to a third aspect of the present application, the present application further provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the tire detection method in any one of the above is implemented.

[0016] According to another aspect of the present application, the present application further provides a computer readable storage medium, having a computer program stored thereon, and when the computer program is executed by a processor, the tire detection method in any one of the above is implemented.

[0017] By one or more of the above embodiments of the present application, at least the following technical effects can be achieved:

[0018] The present application can recognize a vehicle state, and adjust a collection frequency of a tire pressure sensor and a wake-up mechanism of a microcontroller according to different vehicle states, so that the sampling frequency and the communication frequency of the tire pressure sensor can be adjusted, the collection frequency and the communication frequency can be reduced when the tire is in a normal state, the redundant communication and the collection frequency are reduced, and the power consumption of the tire pressure sensor and the microcontroller is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0019] The technical solutions and other beneficial effects of the present application will be apparent to those skilled in the art through the following detailed description of the specific embodiments of the present application, combined with the accompanying drawings.

[0020] Figure 1 The flowchart of the tire detection method provided by the embodiments of the present application is shown.

[0021] Figure 2 A schematic diagram of the overall process of the tire detection method provided by the embodiments of the present application is shown in the figure.

[0022] Figure 3 A framework diagram of the tire detection system provided by the embodiments of the present application is shown in the figure.

[0023] Figure 4 A schematic block diagram of the structure of the electronic device provided by the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0025] In the description of the present application, it should be noted that, unless otherwise explicitly specified and limited, the term "and / or" in this paper is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the existence of A alone, the existence of A and B together, and the existence of B alone. In addition, the character " / " in this paper generally represents an "or" relationship between the associated objects without special explanation.

[0026] The existing car is generally equipped with a tire pressure sensor. The main function of the tire pressure sensor is to monitor the key data such as tire pressure and temperature in real time, and transmit the information to the display screen or control system in the car to provide real-time feedback of the tire state for the driver, thereby ensuring driving safety.

[0027] However, the traditional tire pressure sensor relies on periodic sampling and fixed frequency communication (such as sending once every 60 seconds), which results in a large amount of invalid power consumption regardless of the state of the vehicle.

[0028] At the same time, the tire pressure sensor is easily affected by temperature, vibration, centrifugal force and other factors during use, resulting in inaccurate pressure measurement.

[0029] In order to solve the above problems, the embodiments of the present application provide a tire detection method, system, electronic device and storage medium.

[0030] Figure 1 The tire detection method provided by the embodiments of the present application is shown in the figure, which comprises:

[0031] S101, collecting the measurement data of the tire pressure sensor.

[0032] In the present embodiment, the measurement data includes at least one of centrifugal acceleration, lateral acceleration, tire pressure variation, temperature variation and wheel speed difference, longitudinal acceleration, vertical acceleration, tire temperature, wheel speed difference, acceleration noise, etc.

[0033] S102, identifying the vehicle state by using the measurement data.

[0034] In some embodiments, the measurement data includes centrifugal acceleration;

[0035] Identifying the vehicle state by using the measurement data includes: identifying that the vehicle is in a parking state, a low-speed driving state or a high-speed driving state according to different centrifugal accelerations; wherein when the centrifugal acceleration is 0g, the vehicle is in the parking state; when the centrifugal acceleration is in a preset first range, the vehicle is in the low-speed driving state; and when the centrifugal acceleration is in a preset second range, the vehicle is in the high-speed driving state, wherein any value in the second range is greater than any value in the first range.

[0036] In the present embodiment, the first range is greater than 0g and less than or equal to 3g, and the second range is greater than 3g and less than or equal to 6g; wherein when the centrifugal acceleration is 0, the vehicle is in the parking state; when 0g < centrifugal acceleration ≤ 3g, the vehicle is in the low-speed driving state; and when 3g < centrifugal acceleration ≤ 6g, the vehicle is in the high-speed driving state.

[0037] In other embodiments, other data can also be used to identify the state of the vehicle, such as using the speed sensor of the vehicle, the engine speed signal, the state of the gearbox, etc. to identify that the vehicle is in the parking state, the low-speed driving state, the high-speed driving state.

[0038] Wherein the low-speed driving state indicates that the vehicle speed of the vehicle is between 10-40Km / h, and the high-speed driving state indicates that the vehicle speed of the vehicle is between 80-120Km / h.

[0039] In some embodiments, the measurement data includes lateral acceleration, tire pressure variation, temperature variation and wheel speed difference, longitudinal acceleration, vertical acceleration, tire temperature, wheel speed difference, acceleration noise;

[0040] Identifying the vehicle state by using the measurement data includes:

[0041] Identifying whether the vehicle is in an over-steering state according to the lateral acceleration, the tire pressure variation, the temperature variation and the wheel speed difference;

[0042] In this embodiment, if the acceleration of the coaxial tires (i.e. the front wheels on both sides or the rear wheels on both sides) is greater than 0.5g and the duration is greater than 1s; and the pressure difference of the coaxial tires is greater than 5% of the standard value; and the temperature difference of the coaxial tires is greater than 5℃; and the wheel speed difference is greater than the preset value, it indicates that the vehicle is in the over-bending state.

[0043] In this embodiment, the lateral acceleration is one of the factors for determining whether to turn, for example, the right tire acceleration rises, the vehicle may turn left, and the left tire acceleration rises, the vehicle may turn right.

[0044] The tire pressure change is one of the factors for determining whether to turn, for example, when the vehicle turns, the outside tire pressure rises (centrifugal force causes the tire pressure wall to be squeezed), and the inside tire pressure drops (load reduction).

[0045] The temperature change is also one of the factors for determining whether to turn, for example, when the vehicle turns, the outside tire temperature rises (friction increases to cause temperature rise).

[0046] The wheel speed difference is also one of the factors for determining whether to turn, for example, when the vehicle turns, the outside tire speed is slightly higher than the inside tire, which can be obtained through ABS (anti-lock braking system) data.

[0047] Alternatively, according to the longitudinal acceleration, the tire pressure change and the temperature change, it is identified whether the vehicle is in the state of rapid acceleration or rapid braking;

[0048] In this embodiment, the tire pressure difference of the front and rear wheels needs to be calculated according to the tire pressure change; and the temperature rise of the front wheel needs to be calculated according to the temperature change.

[0049] If the absolute value of the longitudinal acceleration is continuously greater than 0.5g and the duration is greater than 0.5s, and the tire pressure difference of the front and rear wheels is greater than 3%, and the temperature change of the front wheel rises by more than 5℃ within one minute, it indicates that the vehicle is in the state of rapid acceleration or rapid braking.

[0050] Among them, if the longitudinal acceleration is positive and the peak value is greater than 0.5g, it indicates the state of rapid acceleration, and if the longitudinal acceleration is negative and the negative peak value is less than -0.5g, it indicates the state of rapid braking.

[0051] In the state of rapid acceleration, the front wheel pressure rises due to load transfer, and in the state of rapid braking, the front wheel pressure rises and the rear wheel pressure drops.

[0052] In the state of rapid braking, the friction between the brake pad and the wheel causes the wheel temperature to rise rapidly, and in the state of rapid acceleration, the friction between the wheel and the ground also causes the wheel temperature to rise.

[0053] Or, according to the vertical acceleration, tire pressure changes and temperature changes to identify whether the vehicle is in the state of the bumpy road section;

[0054] In this embodiment, it is also necessary to obtain the suspension vibration;

[0055] Wherein, if the vertical acceleration has multiple peak vibrations within 0.1s, and the tire pressure fluctuation frequency is synchronized with the suspension vibration, and the temperature change is different from the historical temperature change data in the normal state, it indicates that the vehicle is in the state of the bumpy road section.

[0056] In this embodiment, the vertical acceleration also needs to be greater than 1g under high-frequency vibration of more than 5Hz. The instantaneous fluctuation of tire pressure also needs to be more than ±3kpa; the continuous bumping may cause the tire temperature to slowly rise, so it is necessary to combine the historical temperature change data in the normal state to determine whether the vehicle is in the state of the bumpy road section.

[0057] Or, according to the tire temperature, tire pressure changes, and wheel speed difference to identify whether the vehicle is in the state of the ice and snow road surface;

[0058] In this embodiment, it is also necessary to calculate the relationship between the changed tire pressure and the standard tire pressure according to the tire pressure changes;

[0059] If the tire temperature is less than or equal to 5℃ and has no obvious warming trend, and the tire pressure after the change is more than 10% lower than the standard tire pressure, and the ABS signal is triggered, it indicates that the vehicle is in the state of the ice and snow road surface.

[0060] Wherein, if the vehicle is in the state of the ice and snow road surface, the tire temperature will approach the ambient temperature, such as-10℃ to 0℃, and the low temperature will cause the tire pressure to drop, about 3% per 10℃ drop, and there may be unilateral wheel slip, at this time the ABS of the vehicle will send a signal. Therefore, in this case, it is determined that the vehicle is in the ice and snow road surface.

[0061] Or, according to the tire temperature, tire pressure changes, and acceleration noise to identify whether the vehicle is in the state of the high-temperature road surface.

[0062] In this embodiment, it is necessary to determine whether the tire temperature exceeds the threshold value and the tire pressure rises synchronously; and calculate the relationship between the changed tire pressure and the standard tire pressure according to the tire pressure changes;

[0063] Wherein, if the tire temperature exceeds the threshold value and the tire pressure rises synchronously, and the changed tire pressure is more than 10% greater than the standard tire pressure, and the amplitude of the acceleration noise is reduced, it indicates that the vehicle is in the state of the high-temperature road surface.

[0064] In the embodiment, if the vehicle is on a high-temperature road surface and the ambient temperature is greater than 35℃, the tire temperature will be greater than 70℃; and the gas expansion will cause the tire pressure to rise, specifically, the tire pressure will rise by 3% for every 10℃ rise in temperature; and the acceleration noise is used to determine whether the vehicle is on a highway, if it is on a highway, the vibration of the vehicle will be reduced due to the flat road surface, so the acceleration amplitude will be reduced.

[0065] In the embodiment, the high-temperature road surface refers to a road surface with a temperature greater than 50℃.

[0066] In addition, in other embodiments, the vehicle can also be determined to be on a curve and a wet road surface according to the lateral acceleration, the tire temperature, and the intermittent triggering of ABS, for example, if the lateral acceleration of the tire is greater than 0.6g, the tire temperature is low, and the ABS is intermittently triggered, it indicates that the vehicle is on a curve and a wet road surface.

[0067] In other embodiments, the vehicle can also be determined to be in a high-speed tire burst state according to the pressure drop amplitude and temperature change of a single tire, and the wheel speed difference, for example, if the pressure drop amplitude of a single tire is greater than 20%, the temperature of the tire rises, and there is a wheel speed difference between the tire and other tires, it indicates that the vehicle is in a high-speed tire burst state, and a warning is issued at this time.

[0068] S103, adjusting the collection frequency of the tire pressure sensor and the wake-up mechanism of the microcontroller according to the vehicle state.

[0069] In the embodiment, the collection frequency of the tire pressure sensor and the wake-up mechanism of the microcontroller are different for different vehicle states.

[0070] For example, when the vehicle is in a parking state or a low-speed driving state, the vehicle state is relatively stable, so the tire pressure sensor collects data every 5-10 minutes, and only monitors slow air leakage. For another example, when the vehicle is in a high-speed driving state, the vehicle is stable but the speed changes within a certain range, so the tire pressure sensor collects data every 5-10 minutes. If the vehicle is in a state of sudden acceleration / deceleration / curve / rough road / impact, etc., the tire pressure sensor collects data every second.

[0071] The wake-up mechanism of the microcontroller includes: waking up the microcontroller when the tire pressure sensor collects tire pressure data, or processing or sending tire pressure data, otherwise the microcontroller is put to sleep.

[0072] It should be noted that other controllers can also be provided in the vehicle to support other functions of the vehicle.

[0073] S104, collecting tire pressure data using the tire pressure sensor at the collection frequency.

[0074] In the embodiment, when the tire is in normal state, the acquisition frequency and the communication frequency can be reduced, the redundant communication and acquisition frequency are reduced, and the power consumption of the tire pressure sensor and the microcontroller is reduced.

[0075] In the wake-up mechanism, the microcontroller is woken up, and the tire pressure data is transmitted to the receiving end according to the preset transmission frequency corresponding to the vehicle state by using the microcontroller.

[0076] In the embodiment, the microcontroller also has different transmission frequencies according to different vehicle states.

[0077] For example, when the vehicle is in a parking state or a low-speed driving state, the vehicle is relatively stable, and the tire pressure data is transmitted once every 10-15 minutes; if the vehicle is in an abnormal state, such as a rapid air leakage (tire burst) state, the data is immediately transmitted; if the tire pressure and temperature change exceed the dynamic threshold value due to environmental changes, the data is also immediately transmitted.

[0078] The dynamic threshold value is different according to different environmental parameters, and the greater the value is, the more the environmental parameters exceed the standard parameters. The environmental parameters can be temperature, for example, the dynamic threshold value under the environmental parameter of 50°C is greater than the dynamic threshold value under the environmental parameter of 30°C.

[0079] For example, when the vehicle is in a static state, that is, a parking state, the temperature threshold value is 0-30°C, which is close to the ambient temperature; in the city driving state, the threshold value is increased by 10°C to 30°C compared with the static state, for example, the temperature threshold value in this state is 30°C-60°C; in the high-speed driving state, the threshold value is increased by 30°C to 50°C compared with the static state, for example, 60°C-80°C.

[0080] For example, the tire threshold value of a general automobile is 220kpa-250kpa, and the tire threshold value of a new energy automobile is 240kpa-260kpa.

[0081] In the embodiment, the tire pressure data is also corrected, so that the standard data and the current data are compared in the same environment, and if the current data does not match the historical data, a predictive alarm is given.

[0082] For example, the tire pressure data at 25°C is taken as the standard data, and the tire pressure should be increased by about 3% based on the standard data at a temperature of 35°C. When the standard data and the current data are compared in the same environment, the standard data can be converted into the tire pressure data in the current environment, for example, the product of the standard data and 103% is compared with the tire pressure data in the current environment. The tire pressure data in the current environment can also be compared with the quotient of 103% and the standard data.

[0083] Therefore, the tire pressure detection method provided by the embodiments of the present application can identify the vehicle state and adjust the collection frequency of the tire pressure sensor and the wake-up mechanism of the microcontroller according to different vehicle states, so that the sampling frequency and the communication frequency of the tire pressure sensor can be adjusted. When the tire is in a normal state, the collection frequency and the communication frequency can be reduced, the redundant communication and collection frequency can be reduced, and the power consumption of the tire pressure sensor and the microcontroller can be reduced.

[0084] In some embodiments, the tire detection method further comprises: inputting the tire pressure data into a pre-trained anomaly recognition model, the anomaly recognition model being used for anomaly classification of the input tire pressure data; and outputting pressure compensation or predictive alarm information of the tire pressure data in the case of different categories of anomalies.

[0085] In the embodiments, the anomaly recognition model can be referred to as an anomaly classification model, which is a classification model trained according to sample data. The anomaly recognition model can also be a TinyML (tiny machine learning) model embedded in the tire pressure sensor. The sample data includes the environment in which the vehicle is located, the measurement data collected by the tire pressure sensor, and the abnormal state. Therefore, after the training of the anomaly recognition model is completed, the current vehicle state and the measurement data are input into the anomaly recognition model, and the anomaly recognition model performs anomaly classification to output whether the current measurement data is abnormal and the type of the anomaly.

[0086] In some embodiments, the anomaly recognition model can also output pressure compensation. The compensation principle is similar to the tire pressure correction principle described above. After compensation, the tire pressure value of the current data under the standard environment is obtained, and the compensated tire pressure value is compared with the normal tire pressure value under the standard environment. If the two values are different, the predictive alarm information is output.

[0087] In some embodiments, the microcontroller sends the tire pressure data to the receiving end according to the preset sending frequency corresponding to the vehicle state comprises:

[0088] If the anomaly recognition model classifies the tire pressure data as normal, the tire pressure data is sent according to the preset first frequency.

[0089] If the anomaly recognition model classifies the tire pressure data as abnormal, the tire pressure data is sent according to the second frequency corresponding to the type of the anomaly, or in the case that the type of the anomaly is the change of the pressure and the temperature caused by the environment, the tire pressure data is corrected after pressure compensation. If the difference between the corrected tire pressure data and the historical tire pressure data exceeds the preset threshold, the predictive alarm information is output.

[0090] In the embodiments, the microcontroller has different sending frequencies according to different vehicle states.

[0091] For example, when the vehicle is in a parking state or a low-speed driving state, the vehicle is relatively stable, and the tire pressure data is transmitted at a first frequency, i.e., once every 10-15 minutes; if the vehicle is in an abnormal state, for example, a rapid air leakage (tire burst) state, the data is transmitted at a second frequency, i.e., immediately; if the tire pressure and temperature change caused by environmental changes exceed the dynamic threshold, the data is also immediately transmitted.

[0092] The value of the dynamic threshold can refer to the description of the above embodiments, which will not be repeated here.

[0093] In some embodiments, the tire detection method further comprises:

[0094] Uploading the tire pressure data, the abnormal classification of the tire pressure data, the pressure compensation, and the predictive alarm information to the cloud, and obtaining the tire pressure data, the abnormal classification of the tire pressure data, the pressure compensation, and the predictive alarm information of the same model vehicle from the cloud;

[0095] Using the tire pressure data, the abnormal classification of the tire pressure data, the pressure compensation, and the predictive alarm information of the same model vehicle obtained from the cloud to retrain the abnormal identification model.

[0096] In this embodiment, the data uploaded to the cloud is combined with the Internet of Vehicles to find common problems and tire performance trends of the same model vehicle, and more data is used to train more complex models. The optimized lightweight model parameters or rules are issued to the sensor to continuously improve the accuracy of edge intelligence.

[0097] In some embodiments, the tire detection method further comprises: simulating the tire pressure change law of different types of tires in different environments to generate labeled virtual data; fusing the virtual data with the test data collected, and reducing the dependence on real vehicle data by using a transfer learning algorithm to reduce the distribution difference between the virtual and test data; and training the abnormal identification model using the virtual data.

[0098] In this embodiment, different types of tires such as silent tires and run-flat tires, different environments such as load (empty / full), road surface (asphalt / sand), and climate (high temperature / rain and snow) can generate a large amount of labeled virtual data.

[0099] And after generating the virtual data, since there is a difference between the virtual data and the real vehicle data, the embodiment collects a small amount of real vehicle data (for example, only 500 hours of key working condition data per vehicle model) and fuses it with the virtual data, and corrects the virtual data according to the real vehicle data, for example, the deviation correction of the influence coefficient of temperature on tire pressure in the virtual scene and the real vehicle, wherein the transfer learning algorithm can use domain adaptation network, etc., thereby generating a large amount of virtual data with labels, and the use cost of virtual data is obviously much lower than the measurement cost of real vehicle data, so that the training cost of the abnormal identification model can be reduced by using virtual data.

[0100] In some embodiments, the tire detection method further comprises: when training the abnormal identification model, dynamically adjusting the weight of the virtual data / real vehicle data according to the real vehicle feedback to ensure the balance between training efficiency and model accuracy.

[0101] For example, when first deployed, the virtual data accounts for 70%, and as the real vehicle data accumulates, the proportion of virtual data is gradually reduced to 30%.

[0102] In some embodiments, the tire detection method further comprises: obtaining the cumulative mileage of the vehicle to calculate the tire wear degree; and training a "temperature-tire pressure-tire wear degree" three-dimensional mapping model through transfer learning, and inputting the current temperature, tire pressure value and cumulative mileage in real time to output a dynamic compensation coefficient, for example, the compensation coefficient of a tire with a large wear degree at-20°C is 1.2 times higher than that of a new tire.

[0103] In summary, the present application provides a tire detection method, as shown in Figure 2 After collecting air pressure, acceleration, pressure and other data using the tire pressure sensor, the data is processed, and the learning model, i.e., the abnormal identification model described in the above embodiments, is trained at the tire pressure sensor embedded with the learning model. In actual application, after collecting air pressure, acceleration, pressure and other data using the tire pressure sensor, the learning model is inputted to obtain edge intelligent decision communication, i.e., the collection frequency of the tire pressure sensor and the wake-up mechanism of the microcontroller described in the above embodiments, and the edge intelligent decision communication is outputted to the vehicle terminal and the cloud terminal. The present application can also obtain the model parameters issued by the cloud terminal, thereby continuously improving the robustness of the learning model, i.e., improving the accuracy of the edge intelligent decision communication.

[0104] Please refer to Figure 3The embodiment of the application also provides a tire detection system, comprising: a first data acquisition module 11, a vehicle state identification module 12, an adjustment module 13, a second data acquisition module 14 and a data sending module 15; the first data acquisition module 11 is used for acquiring measurement data of a tire pressure sensor; the vehicle state identification module 12 is used for identifying a vehicle state by using the measurement data; the adjustment module 13 is used for adjusting a collection frequency of the tire pressure sensor and a wake-up mechanism of a microcontroller according to the vehicle state; the second data acquisition module 14 is used for collecting tire pressure data by using the tire pressure sensor at the collection frequency; and the data sending module 15 is used for waking up the microcontroller at the wake-up mechanism and sending the tire pressure data to a receiving end by using the microcontroller according to a preset sending frequency corresponding to the vehicle state.

[0105] The tire detection system provided by the embodiment can identify a vehicle state and adjust a collection frequency of a tire pressure sensor and a wake-up mechanism of a microcontroller according to different vehicle states, so that the sampling frequency of the tire pressure sensor and the communication frequency can be adjusted, the collection frequency and the communication frequency can be reduced when the tire is in a normal state, the redundant communication and the collection frequency are reduced, and the power consumption of the tire pressure sensor and the microcontroller is reduced.

[0106] In some embodiments, the tire detection system further comprises an abnormality classification module and a compensation and alarm information output module, the abnormality classification module is used for inputting the tire pressure data into a pre-trained abnormality identification model, the abnormality identification model is used for classifying the input tire pressure data, and the compensation and alarm information output module is used for outputting pressure compensation or predictive alarm information of the tire pressure data in the case of different types of abnormalities.

[0107] In some embodiments, the measurement data comprises centrifugal acceleration; the vehicle state identification module 12 comprises a centrifugal acceleration identification unit, which is used for identifying that the vehicle is in a parking state, a low-speed driving state or a high-speed driving state according to different centrifugal accelerations; when the centrifugal acceleration is 0g, the vehicle is in the parking state; when the centrifugal acceleration is in a preset first range, the vehicle is in the low-speed driving state; and when the centrifugal acceleration is in a preset second range, the vehicle is in the high-speed driving state, wherein any value in the second range is greater than any value in the first range.

[0108] In some embodiments, the measurement data comprises lateral acceleration, tire pressure change, temperature change and wheel speed difference, longitudinal acceleration, vertical acceleration, tire temperature, wheel speed difference and acceleration noise; and the vehicle state identification module 12 further comprises a cornering state identification unit, an abrupt acceleration and abrupt braking state identification unit, a bumpy road section identification unit, an icy road surface identification unit and a high-temperature road surface identification unit.

[0109] The over-bending state recognition unit is configured to recognize whether the vehicle is in an over-bending state according to lateral acceleration, tire pressure change, temperature change, and wheel speed difference; or

[0110] The sudden acceleration and sudden braking state recognition unit is configured to recognize whether the vehicle is in a sudden acceleration or sudden braking state according to longitudinal acceleration, tire pressure change, and temperature change; or

[0111] The bumpy road section recognition unit is configured to recognize whether the vehicle is in a bumpy road section state according to vertical acceleration, tire pressure change, and temperature change; or

[0112] The ice and snow road surface recognition unit is configured to recognize whether the vehicle is in an ice and snow road surface state according to tire temperature, tire pressure change, and wheel speed difference; or

[0113] The high-temperature road surface recognition unit is configured to recognize whether the vehicle is in a high-temperature road surface state according to tire temperature, tire pressure change, and acceleration noise.

[0114] In some embodiments, the adjustment module 13 adjusts the wake-up mechanism of the microcontroller, specifically, wakes up the microcontroller when the tire pressure sensor collects tire pressure data, or processes or transmits the tire pressure data, and otherwise puts the microcontroller to sleep.

[0115] In some embodiments, the data transmission module 15 includes a normal transmission unit and an abnormal transmission unit. The normal transmission unit is configured to transmit the tire pressure data at a preset first frequency if the abnormality recognition model classifies the tire pressure data as normal. The abnormal transmission unit is configured to transmit the tire pressure data according to a second frequency corresponding to the type of abnormality if the abnormality recognition model classifies the tire pressure data as abnormal, or in the case of an environmental pressure and temperature change, after correcting the abnormal tire pressure data using pressure compensation, if the corrected tire pressure data and historical tire pressure data differ by more than a preset threshold, a predictive warning message is issued.

[0116] In some embodiments, the tire detection system further includes a cloud interaction module configured to upload the tire pressure data, the abnormal classification of the tire pressure data, the pressure compensation, and the predictive warning information to the cloud, and configured to obtain tire pressure data, abnormal classification of tire pressure data, pressure compensation, and predictive warning information of the same model vehicle from the cloud; and retrain the abnormality recognition model using the tire pressure data, the abnormal classification of the tire pressure data, the pressure compensation, and the predictive warning information of the same model vehicle obtained from the cloud.

[0117] In some embodiments, the tire detection system further comprises a virtual data generation module and a virtual data training module, the virtual data generation module is used to simulate the tire pressure change rule of different models of tires in different environments, and generate labeled virtual data; the virtual data is fused with the test driving data, and the distribution difference of the virtual data and the test driving data is learned through a transfer learning algorithm, so that the dependence on real vehicle data is reduced; the virtual data training module is used to train the abnormality recognition model by using the virtual data.

[0118] In some embodiments, the tire detection system further comprises a weight adjustment module, which is used to dynamically adjust the weight of virtual data / real vehicle data according to real vehicle feedback when training the abnormality recognition model, so as to ensure the balance between training efficiency and model accuracy.

[0119] In some embodiments, the tire detection system further comprises a dynamic compensation coefficient generation module, which is used to obtain the cumulative mileage of the vehicle to calculate the tire wear degree; and a three-dimensional mapping model of temperature-tire pressure-tire wear degree is trained through deep learning, the current temperature, tire pressure value and cumulative driving mileage are input in real time, and the dynamic compensation coefficient is output.

[0120] Embodiments of the present application provide an electronic device, please refer to Figure 4 The electronic device comprises a memory 601, a processor 602, and a computer program stored in the memory 601 and executable on the processor 602, and when the processor 602 executes the computer program, the tire detection method described in the foregoing is realized.

[0121] Further, the electronic device further comprises at least one input device 603 and at least one output device 604.

[0122] The above-mentioned memory 601, processor 602, input device 603 and output device 604 are connected through a bus 605.

[0123] The input device 603 can be a camera, a touch panel, a physical button or a mouse, etc. The output device 604 can be a display screen.

[0124] The memory 601 can be a high-speed random access memory (RAM, Rom Access Memory) memory, or a non-volatile memory such as a disk memory. The memory 601 is used to store a set of executable program codes, and the processor 602 is coupled with the memory 601.

[0125] Further, the application also provides a computer readable storage medium, which can be arranged in the electronic device in the above embodiments, and the computer readable storage medium can be the memory 601 in the above embodiments. The computer readable storage medium stores a computer program, and the program is executed by the processor 602 to implement the tire detection method described in the above method embodiments.

[0126] Further, the computer readable storage medium can also be a U disk, a mobile hard disk, a read-only memory (ROM), a RAM, a magnetic disk or an optical disk, and various media that can store program codes.

[0127] In several embodiments provided in the application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed modules can be indirect coupling or communication connection through some interfaces, devices or modules, and can be electrical, mechanical or other forms.

[0128] The modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical modules, that is, they can be located in one place, or can be distributed on a plurality of network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0129] In addition, the function modules in each embodiment of the application can be integrated into a processing module, or each module can exist physically, or two or more modules can be integrated into one module. The integrated module can be realized in the form of hardware or in the form of a software function module.

[0130] The integrated module, if realized in the form of a software function module and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the application essentially or the part of the prior art that contributes to the technical solutions or all or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the application.

[0131] It should be noted that, for the foregoing method embodiments, the acts described in the specification are merely provided as examples for purposes of simplification and are not limitation. A person skilled in the art should know that, according to the present application, certain steps can be performed in other sequences or simultaneously, and the present application is not limited to the sequence of acts described. In addition, a person skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the acts and modules involved are not necessarily essential to the present application.

[0132] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0133] In summary, although the present application has been disclosed with the above preferred embodiments, the above preferred embodiments are not intended to limit the present application. Those skilled in the art can make various modifications and improvements without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application is defined by the scope of the claims.

Claims

1. A tire inspection method, characterized in that, include: Collect measurement data from the tire pressure sensor; The vehicle status is identified using the measurement data; The tire pressure sensor's sampling frequency and the microcontroller's wake-up mechanism are adjusted according to the vehicle's status. At the specified acquisition frequency, tire pressure data is acquired using the tire pressure sensor; Under the wake-up mechanism, the microcontroller is woken up, and the microcontroller is used to send the tire pressure data to the receiving end according to the preset transmission frequency corresponding to the vehicle status.

2. The tire testing method as described in claim 1, characterized in that, The tire testing method also includes: The tire pressure data is input into a pre-trained anomaly detection model, which is used to classify the input tire pressure data as anomalies. In different categories of abnormal situations, pressure compensation or predictive alarm information is output based on the tire pressure data.

3. The tire testing method as described in claim 1, characterized in that, The measurement data includes centrifugal acceleration; The process of identifying the vehicle status using the measurement data includes: The vehicle is identified as being in a stopped state, a low-speed driving state, or a high-speed driving state based on the different centrifugal accelerations. Wherein, when the centrifugal acceleration is 0g, the vehicle is in the stopped state; when the centrifugal acceleration is within a preset first range, the vehicle is in the low-speed driving state; when the centrifugal acceleration is within a preset second range, the vehicle is in the high-speed driving state, wherein any value in the second range is greater than any value in the first range.

4. The tire testing method as described in claim 1, characterized in that, The measurement data includes lateral acceleration, tire pressure change, temperature change and wheel speed difference, longitudinal acceleration, vertical acceleration, tire temperature, wheel speed difference, and acceleration noise; The process of identifying the vehicle status using the measurement data includes: The vehicle's cornering status is determined based on the lateral acceleration, tire pressure change, temperature change, and wheel speed difference; or... The system identifies whether the vehicle is in a state of rapid acceleration or sudden braking based on the longitudinal acceleration, tire pressure change, and temperature change; or... The vehicle is identified as being on a bumpy road based on the vertical acceleration, tire pressure change, and temperature change; or... The vehicle's condition on icy or snowy roads is identified based on the tire temperature, tire pressure changes, and wheel speed differences; or... The vehicle is identified as being on a hot road surface based on the tire temperature, tire pressure changes, and acceleration noise.

5. The tire testing method as described in claim 1, characterized in that, The wake-up mechanism of the microcontroller includes: The microcontroller is woken up when the tire pressure sensor collects, processes, or sends the tire pressure data; otherwise, the microcontroller is put into sleep mode.

6. The tire testing method as described in claim 2, characterized in that, The step of using the microcontroller to send the tire pressure data to the receiving end according to a preset transmission frequency corresponding to the vehicle status includes: If the anomaly identification model classifies the tire pressure data as normal, then the tire pressure data is sent at a preset first frequency. If the anomaly identification model classifies the tire pressure data as abnormal, the tire pressure data is sent according to the second frequency corresponding to the anomaly type. Alternatively, if the anomaly type is caused by environmental changes in pressure and temperature, the abnormal tire pressure data is corrected using the pressure compensation. If the difference between the corrected tire pressure data and the historical tire pressure data exceeds a preset threshold, a predictive alarm is issued.

7. The tire testing method as described in claim 6, characterized in that, The tire testing method also includes: The tire pressure data, tire pressure data anomaly classification, pressure compensation, and predictive alarm information are uploaded to the cloud, and the tire pressure data, tire pressure data anomaly classification, pressure compensation, and predictive alarm information of the same vehicle model are obtained from the cloud. The anomaly recognition model is retrained using tire pressure data of the same vehicle model obtained from the cloud, anomaly classification of tire pressure data, pressure compensation, and predictive alarm information.

8. A tire inspection system, characterized in that, include: The first data acquisition module is used to collect measurement data from the tire pressure sensor; A vehicle status recognition module is used to identify the vehicle status using the measurement data; An adjustment module is used to adjust the sampling frequency of the tire pressure sensor and the wake-up mechanism of the microcontroller according to the vehicle status. The second data acquisition module is used to acquire tire pressure data using the tire pressure sensor at the acquisition frequency. The data transmission module is used to wake up the microcontroller under the wake-up mechanism and use the microcontroller to send the tire pressure data to the receiving end according to a preset transmission frequency corresponding to the vehicle status.

9. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images