Tire Contact Patch Control Using ML and Driver Preferences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tire contact patches are not optimized for driver preferences or current driving conditions, affecting tire wear, friction, comfort, and fuel economy.
Innovation Solution
A multi-phase machine learning process using two algorithms to determine the optimum tire contact patch based on vehicle information and driver preferences, adjusting tire pressure and suspension for optimal performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If tire contact patches are not optimized for driver preferences or current driving conditions, then the system is simple and requires no complex control, but fuel economy, tire wear, comfort, and performance are degraded
Solution Approach 1:
The system dynamically adjusts tire pressure and suspension settings based on real-time driving conditions and driver preferences. The machine learning model continuously processes sensor data and modifies vehicle parameters to optimize fuel economy, tire wear, and ride comfort for each specific driving scenario rather than using fixed settings.
Solution Approach 2:
The system uses the vehicle's existing sensors and onboard computer to automatically determine and adjust tire contact patch optimization parameters. The machine learning model processes available vehicle data (accelerometer, gyroscope, steering angle, throttle position) and autonomously controls tire pressure and suspension without requiring external intervention or complex additional hardware.
2Reliability
If tire contact patches are not optimized, then fewer sensors and processing are needed, but tire wear and performance are adversely affected
Solution Approach 1:
The system uses existing vehicle sensors (accelerometer, gyroscope, steering angle sensor, throttle position sensor) for multiple purposes - both for their original functions and for determining tire contact patch optimization parameters. The onboard computer processes this data for both standard vehicle operations and for the machine learning model that optimizes tire and suspension settings, eliminating the need for dedicated additional sensors.
Solution Approach 2:
The system optimizes tire wear and performance by dynamically changing physical parameters - specifically tire pressure and suspension settings - based on processed sensor data. The machine learning model determines optimal parameter values for each driving condition, adjusting these parameters in real-time to extend tire life and maintain performance without requiring complex mechanical modifications.
3Ease of operation
If tire contact patches are not optimized for current driving conditions, then the control system remains simple, but comfort and performance are reduced
Solution Approach 1:
The system dynamically adjusts suspension settings and tire pressure based on real-time driving conditions detected by sensors. The machine learning model continuously processes data from accelerometers, gyroscopes, and other sensors to determine optimal comfort and performance settings for each specific driving scenario, adapting the vehicle characteristics to match current conditions rather than using static configurations.
Solution Approach 2:
The system uses feedback from vehicle sensors (accelerometer, gyroscope, steering angle, throttle position) to continuously monitor driving conditions and driver behavior. The machine learning model processes this feedback information and adjusts tire pressure and suspension settings accordingly, creating a closed-loop control system that optimizes comfort and performance based on actual vehicle operation and driver preferences.
Data Source
Figure 1~3
Figure 4
Figure 5
AI summary
Systems, methods, and computer-readable storage media for using multi-stage machine learning algorithms to optimize tire contact patches on a vehicle. Vehicle sensors first collect vehicle information for the vehicle, and input that data into a first machine learning algorithm. The first machine learning algorithm then outputs a lateral dimension, a longitudinal dimension, and a diagonal dimension, which together identify a tire contact patch of at least one tire on the vehicle. The operator of the vehicle provides a human preference for how the vehicle operates, and a second machine learning algorithm is executed. The second machine learning algorithm inputs can include the plurality of vehicle information, the first machine learning algorithm outputs, and the human preference, and the second machine learning algorithm outputs can include a desired tire pressure of the at least one tire and an air suspension adjustment for the normal load of the vehicle.