Vehicle tire pressure learning system and method
Methods and systems may provide for technology to collect data related to tire pressure of a vehicle via one or more tire pressure monitoring sensors (TPMS), and provide a warning for a low or high tire pressure based on weather patterns determined by a historic weather data subsystem. The weather patterns may include fluctuations and steady states of temperature. A TPMS machine learning subsystem may use tire pressure data and weather data to provide an alert as to whether an indicator associated with the one or more TPMS sensors was activated due to changing weather. The TPMS machine learning subsystem may also determine a probable accuracy of the TPMS alert based on the TPMS data and weather-related data including checking for outliners in the weather patterns.
1. A vehicle tire pressure learning system comprising:
a processor;
one or more tire pressure monitoring sensors (TPMS), in communication with the processor, to:
collect data related to a pressure of one or more tires of a vehicle, and
provide a TPMS alert for a low or high tire pressure;
a weather data subsystem, in communication with the one or more TPMS, to determine weather patterns based on weather-related data received from one or more weather sensors, wherein the weather patterns include fluctuations and steady states of temperature; and
a TPMS machine learning subsystem in communication with the one or more TPMS and the weather data subsystem, wherein the TPMS machine learning subsystem includes a processor and memory having a set of instructions, which when executed by the processor, cause the TPMS machine learning subsystem to determine a probable accuracy of the TPMS alert based on the TPMS data and the weather-related data,
wherein the TPMS machine learning subsystem is to predict when running over debris will cause a flat.
2. A vehicle tire pressure learning system comprising:
a processor;
one or more tire pressure monitoring sensors (TPMS), in communication with the processor, to:
collect data related to a pressure of one or more tires of a vehicle, and
provide a TPMS alert for a low or high tire pressure;
a weather data subsystem, in communication with the one or more TPMS, to determine weather patterns based on weather-related data received from one or more weather sensors, wherein the weather patterns include fluctuations and steady states of temperature; and
a TPMS machine learning subsystem in communication with the one or more TPMS and the weather data subsystem, wherein the TPMS machine learning subsystem includes a processor and memory having a set of instructions, which when executed by the processor, cause the TPMS machine learning subsystem to determine a probable accuracy of the TPMS alert based on the TPMS data and the weather-related data,
wherein the weather data subsystem is further to:
provide, when the weather is determined to be substantially fluctuating, an alert that an indicator associated with the one or more TPMS may have been activated due to changing weather, and
provide, when the weather is determined to be substantially steady, an alert that an indicator associated with the one or more TPMS may not have been activated due to weather.
3. The system of claim 1 , further comprising one or more cameras to provide an input to the TPMS machine learning subsystem related to road data, wherein the road data includes information related to a pothole or other road hazard.
4. The system of claim 3 , wherein the TPMS machine learning subsystem is further to determine a probability that a tire hit a pothole or other road hazard within a defined period of time, wherein determining the probability includes checking saved road and torque data.
5. The system of claim 3 , wherein the TPMS machine learning subsystem is further to determine a cause and a severity of a changing tire pressure.
6. The system of claim 3 , wherein the TPMS machine learning subsystem is to share information with one or more other machine learning systems associated with one or more other vehicles.
7. A method of operating a vehicle tire pressure learning system comprising:
collecting, via one or more tire pressure monitoring sensors (TPMS), data related to a pressure of one or more tires of a vehicle;
providing a TPMS alert for a low or high tire pressure;
determining, via a weather data subsystem, weather patterns based on weather-related data received from one or more weather sensors, wherein the weather patterns include fluctuations and steady states of temperature;
determining, via a TPMS machine learning subsystem, a probable accuracy of the TPMS alert based on the TPMS data and the weather-related data; and
predicting, via the TPMS machine learning subsystem, when running over debris will cause a flat.
8. A method of operating a vehicle tire pressure learning system comprising:
collecting, via one or more tire pressure monitoring sensors (TPMS), data related to a pressure of one or more tires of a vehicle;
providing a TPMS alert for a low or high tire pressure;
determining, via a weather data subsystem, weather patterns based on weather-related data received from one or more weather sensors, wherein the weather patterns include fluctuations and steady states of temperature;
determining, via a TPMS machine learning subsystem, a probable accuracy of the TPMS alert based on the TPMS data and the weather-related data;
providing, when the weather is determined to be substantially fluctuating, an alert that an indicator associated with the one or more TPMS may have been activated due to changing weather, and
providing, when the weather is determined to be substantially steady, an alert that an indicator associated with the one or more TPMS may not have been activated due to weather.
9. The method of claim 7 , further including providing, via one or more cameras, an input related to road data, wherein the road data includes information related to a pothole or other road hazard.
10. The method of claim 9 , further including determining a probability that a tire hit a pothole or other road hazard within a defined period of time, wherein determining the probability includes checking saved road data and torque data.
11. The method of claim 9 , further including determining a cause and a severity of a changing tire pressure.
12. The method of claim 7 , wherein the TPMS machine learning subsystem is to share information with one or more other machine learning systems associated with one or more other vehicles.
13. At least one non-transitory computer readable storage medium comprising a set of instructions, when executed by a processor, cause the processor to:
collect, via one or more tire pressure monitoring sensors (TPMS), data related to a pressure of one or more tires of a vehicle;
provide a TPMS alert for a low or high tire pressure;
determine, via a weather data subsystem, weather patterns based on weather-related data received from one or more weather sensors, wherein the weather patterns include fluctuations and steady states of temperature;
determine, via a TPMS machine learning subsystem, a probable accuracy of the TPMS alert based on the TPMS data and the weather-related data; and
predict, via the TPMS machine learning subsystem, when running over debris will cause a flat.
14. At least one non-transitory computer readable storage medium comprising a set of instructions, when executed by a processor, cause the processor to:
collect, via one or more tire pressure monitoring sensors (TPMS), data related to a pressure of one or more tires of a vehicle;
provide a TPMS alert for a low or high tire pressure;
determine, via a weather data subsystem, weather patterns based on weather-related data received from one or more weather sensors, wherein the weather patterns include fluctuations and steady states of temperature; and
determine, via a TPMS machine learning subsystem, a probable accuracy of the TPMS alert based on the TPMS data and the weather-related data,
wherein the instructions, when executed, further cause the processor to:
provide, when the weather is determined to be substantially fluctuating, an alert that an indicator associated with the one or more TPMS may have been activated due to changing weather, and
provide, when the weather is determined to be substantially steady, an alert that an indicator associated with the one or more TPMS may not have been activated due to weather.
15. The at least one non-transitory computer readable storage medium of claim 13 , wherein the instructions, when executed, further cause the processor to determine a probability that a tire hit a pothole or other road hazard within a defined period of time, wherein determining the probability includes checking saved road data and torque data.
16. The at least one non-transitory computer readable storage medium of claim 13 , wherein the instructions, when executed, further cause the processor to determine a cause and a severity of a changing tire pressure.
17. The at least one non-transitory computer readable storage medium of claim 13 , wherein the instructions, when executed, further cause the processor to share information with one or more other machine learning systems associated with one or more other vehicles.