Vehicle Tire Wear Modeling for Real-Time Traction Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current tire wear prediction methods are inefficient, often requiring weeks of computationally expensive finite element analysis (FEA) simulations, and fail to provide real-time feedback on tire performance and traction capabilities.
Innovation Solution
A computer-implemented method that estimates current tire wear characteristics in real-time using a system with onboard sensors and a cloud server, implementing models such as neural network autoencoders and Bayesian approaches to summarize high-frequency data into lower-frequency data for efficient transmission and processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If finite element analysis (FEA) simulations are used to predict tire wear, then prediction accuracy is improved, but computational time and cost increase significantly (weeks to months)
Solution Approach 1:
The patent creates simplified digital twin models that replicate the essential wear behavior of tires without requiring full FEA simulations. These reduced-order models capture the dominant wear mechanisms and can be executed rapidly, providing near-real-time predictions while maintaining acceptable accuracy for operational decision-making
Solution Approach 2:
The patent transforms the complex FEA simulation parameters into a smaller set of critical wear parameters that drive the simplified models. By identifying and monitoring only the most influential parameters (such as contact pressure distributions, slip ratios, and temperature profiles), the system achieves accurate wear predictions with significantly reduced computational requirements
2Measurement precision
If high-frequency vehicle and tire data are collected continuously, then real-time tire wear estimation accuracy is improved, but data transmission, storage, and processing become overwhelming
Solution Approach 1:
The patent extracts and isolates only the critical data elements needed for wear prediction from the overwhelming stream of high-frequency sensor data. By identifying and extracting key features (such as contact patch characteristics, load variations, and speed profiles) while filtering out redundant information, the system maintains prediction accuracy while dramatically reducing data volumes for transmission and storage
Solution Approach 2:
The patent segments the continuous high-frequency data stream into meaningful operational phases or driving cycles. By dividing the data into discrete, representative segments that capture different driving conditions (acceleration, braking, steady-state, turning), the system can process and analyze wear-relevant information more efficiently without losing temporal resolution
3Reliability
If accurate tread depth prediction is implemented, then traction capability prediction and other performance predictions are improved, but the system complexity increases
Solution Approach 1:
The patent performs preliminary estimation of tread depth and wear characteristics using simplified models before deploying more complex predictive analytics. By first establishing baseline wear rates and current tread depth through reduced-order models, the system prepares essential inputs that enable more sophisticated traction and performance predictions without requiring all complex models to run simultaneously
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
A computer-implemented system and method are provided for vehicle tire performance monitoring, modeling, and feedback. Vehicle data comprising movement data and/or location data are collected for a vehicle and/or at least one tire associated with the vehicle. A current tire wear status is determined in real-time for the at least one tire, based at least in part on the collected data, various particular embodiments of which are disclosed herein. One or more tire performance characteristics, such as for example tire traction, replacement time and/or future tire wear, are predicted based at least in part on the determined tire wear status and the collected data. Real-time feedback is selectively provided based on the predicted one or more tire performance characteristics and/or determined current tire wear status. The feedback may include alerts to an operator or fleet management personnel, or may take the form of automated control invention.