Tire Tread Image Analysis for Uneven Wear Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to detect uneven tire wear, which can lead to tire damage and safety issues, as they primarily focus on overall tread wear rather than localized wear patterns.
Innovation Solution
A method using machine learning models to analyze tire tread images, estimating uneven wear and recommending tire replacement or rotation based on image analysis of both tread ends, incorporating multiple models for precise wear assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data is used to estimate overall tread wear, then the estimation process is simple and quick, but uneven wear patterns cannot be detected
Solution Approach 1:
The patent replaces complex manual inspection methods with a machine learning-based image analysis system. A camera captures tread images and a trained model automatically detects uneven wear patterns, substituting human visual inspection with automated optical-mechanical-system-intelligence integration that achieves higher precision without proportionally increasing complexity
Solution Approach 2:
The patent creates a digital copy (image) of the physical tire tread and analyzes wear patterns in this replicated form through machine learning. This allows detailed examination of uneven wear without physically touching or complicating the actual tire structure, achieving precise measurement through information copying rather than direct mechanical measurement
2Measurement precision
If tread wear amount is estimated using machine learning models, then overall wear can be quantified, but localized uneven wear patterns remain undetected
Solution Approach 1:
The patent applies local quality analysis by training the machine learning model to recognize specific localized wear patterns (asymmetric wear, center wear, edge wear) rather than just overall wear magnitude. The model analyzes spatial distribution characteristics of wear across different regions of the tread, preserving and detecting local wear information that would be lost in aggregate measurements
Solution Approach 2:
The patent transitions from one-dimensional wear depth measurement to two-dimensional spatial pattern recognition. By analyzing the spatial distribution of wear across the tread surface in images, the system detects uneven wear patterns that cannot be captured by single-point or average wear measurements, adding a spatial dimension to wear assessment
3Reliability
If early stage uneven wear is not detected, then tire damage, slipping, and uncomfortable traveling may occur, but current methods cannot identify wear when amount is below prescribed thresholds
Solution Approach 1:
The patent performs preliminary detection of uneven wear patterns before they progress to dangerous levels. By training the machine learning model to recognize early signs of asymmetric wear, center wear, and edge wear, the system enables preventive maintenance actions before tire damage, slipping, or uncomfortable traveling occurs, acting in advance to maintain reliability
Solution Approach 2:
The patent applies preliminary anti-action by detecting and flagging early uneven wear patterns that would otherwise go unnoticed. The system identifies incipient wear problems and triggers alerts or recommendations for tire rotation/replacement before the wear becomes severe enough to cause safety issues, counteracting potential harm before it materializes
Data Source
AI summary
Provided is a method, etc., for estimating uneven tire wear. This tire state estimation method involves: obtaining an image which includes both ends of the tread of a target tire, and captures said tread from the front in a manner such that said tread is continuous in a prescribed direction; inputting the obtained image into a trained first machine learning model; and deriving an output from the trained first machine learning model. Therein, the output of the trained first machine learning model corresponds to the estimation results for the uneven wear of the target tire.