Tire Characteristic Trend Modeling for Wear And Load Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tire estimation systems fail to accurately predict tire wear state and load due to neglecting changes in tire characteristics over the tire's life, leading to reduced accuracy and reliability.
Innovation Solution
A method that extracts selected tire characteristics from sensors, stores them in a historical data log, applies a time series decomposition model to separate exogenous inputs from underlying trends, and uses a learning model to predict tire conditions, accounting for changes in tire characteristics over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If indirect estimation techniques are used to predict tire conditions, then the system complexity is reduced compared to direct measurement, but the accuracy of tire condition prediction deteriorates due to not accounting for changes in tire characteristics over the tire's life
Solution Approach 1:
The system performs preliminary actions by collecting and storing tire characteristic data over the tire's life before making predictions. Historical data on tire characteristics (pressure, temperature, vibration) is accumulated and used to establish baseline patterns that account for tire degradation, enabling more accurate predictions without requiring complex real-time measurements of wear state or load directly
Solution Approach 2:
The system implements feedback by continuously monitoring tire characteristics and comparing them against historical data and expected degradation patterns. This feedback loop allows the system to adjust predictions based on actual tire behavior over time, accounting for changes in tire characteristics while maintaining a relatively simple sensor configuration
2Measurement precision
If direct measurement techniques are used to measure tire characteristics, then measurement accuracy is improved, but the device complexity and cost increase due to requiring multiple sensors
Solution Approach 1:
The system extracts only the essential tire characteristic data needed for prediction (pressure, temperature, vibration) using a minimal sensor set, rather than attempting to directly measure all tire conditions. By extracting and monitoring these key characteristics over time, the system infers wear state and load without requiring direct measurement sensors for those parameters
Solution Approach 2:
The system uses measurable tire characteristics (pressure, temperature, vibration) as intermediary variables that correlate with the desired tire conditions (wear state, load). These intermediaries serve as proxies that can be measured with simple sensors but provide information about conditions that would be difficult or expensive to measure directly
Data Source
AI summary
A method for extracting changes in characteristics of a tire supporting a vehicle is provided. The method includes extracting selected tire characteristics from at least one sensor mounted on the tire. The selected tire characteristics are transmitted to a remote processor and are stored in a historical data log that is in communication with the remote processor. At least one tire characteristic of interest is selected, and a time series decomposition model is applied to data from the historical data log to delineate exogenous inputs from an underlying trend in the selected tire characteristic of interest. A learning model is applied to the underlying trend in the selected tire characteristic of interest to model a relationship between the selected tire characteristic of interest and a condition of the tire. A prediction value for a condition of the tire is output from the learning model.