Tire Capacity Identification Model Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to accurately identify tire capacity across linear and nonlinear regions and under all conditions, including pure and combined slip conditions, which is crucial for active safety systems like ABS and ESP.
Innovation Solution
A method involving obtaining tire test data, calculating total slip ratio and normalized tire force, and using a machine learning algorithm to model and identify tire capacity, enabling the creation of an identification model that can classify tire capacity under various conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to identify tire capacity, then the identification process is simple, but the accuracy of tire capacity identification across all conditions deteriorates
Solution Approach 1:
The patent segments the tire capacity identification process into distinct operational regions (linear region, nonlinear region, saturation region) and develops specific modeling approaches for each region. This segmentation allows the system to achieve high accuracy across all conditions by applying region-specific models rather than attempting a single universal model, thereby resolving the contradiction between measurement precision and model complexity.
Solution Approach 2:
The patent implements a dynamic identification model that adapts to different tire operating conditions in real-time. The system dynamically determines the current operational region based on measured parameters and switches between different modeling approaches accordingly. This dynamic adaptation enables accurate tire capacity identification across varying conditions without requiring an overly complex static model.
2Adaptability or versatility
If a comprehensive model covering all slip conditions is developed, then the adaptability improves, but the difficulty of detecting and measuring increases
Solution Approach 1:
The patent applies local quality by developing specialized measurement and modeling approaches for different slip conditions (pure longitudinal slip, pure lateral slip, combined slip). Each condition has its own characteristic measurement requirements and modeling parameters. This localized approach enables comprehensive coverage of all working conditions while managing measurement complexity by focusing on condition-specific parameters rather than attempting to measure everything simultaneously.
Solution Approach 2:
The patent utilizes parameter changes to simplify detection and measurement across different slip conditions. By transforming raw sensor data into normalized parameters and identifying characteristic parameter patterns for each operational region, the system achieves comprehensive adaptability while reducing measurement complexity. The model monitors changes in key parameters to determine operational state and switch between modeling approaches.
3Measurement precision
If machine learning algorithms are used for modeling, then the identification accuracy under complex conditions improves, but the loss of time for training and computation increases
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models during the offline phase using extensive tire test data covering all possible operating conditions. The models are pre-trained to recognize patterns and characteristics of different slip conditions and operational regions. During real-time operation, the pre-trained models require minimal computation time, as they only need to evaluate the current state against the pre-established models rather than performing complex training computations. This resolves the contradiction by shifting computational burden to the offline training phase.
Data Source
AI summary
A method for modeling an identification model of a tire capacity, including: obtaining tire test data, wherein the tire test data comprises a tire angular velocity, a wheel effective radius, a tire slip angle, a wheel center velocity, a tire longitudinal force, a tire lateral force and a tire vertical force; obtaining a total slip ratio and a normalized tire force according to the tire test data; obtaining a tire capacity corresponding to the total slip ratio and the normalized tire force according to the tire test data; and performing training using the total slip ratio, the normalized tire force, and the tire capacity through a machine learning algorithm to complete the modeling of the identification model of the tire capacity.