Non-Pneumatic Tire Spoke Topology for Stiffness and Damage Resistance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Non-Pneumatic Tire (NPT) spoke designs lack flexibility and have limited stiffness and poor damage performance, which affects overall tire performance and manufacturing efficiency.
Innovation Solution
A processor-implemented method and system for generating optimized spoke designs using random interpolation points, finite element method (FEM) analysis, and machine learning models to select candidate spoke designs based on parameters like stiffness and damage resistance, ensuring volume equivalency and optimal properties such as tensile strength and compressive strength.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Strength
If existing NPT spoke designs are used, then the tire structure is simple and easy to manufacture, but the stiffness and damage resistance are insufficient
Solution Approach 1:
The patent implements a dynamic optimization system that generates multiple candidate spoke designs with varying geometries and evaluates them using FEM analysis and machine learning models. The system dynamically selects optimal designs based on performance criteria such as stiffness and damage resistance, transforming the static spoke design into an adaptive optimization process that balances structural performance with manufacturing considerations
Solution Approach 2:
The patent systematically varies key geometric parameters of the spoke design including curve profiles, thickness distributions, and structural configurations. By changing these parameters and evaluating their impact through FEM analysis and machine learning predictions, the system identifies optimal parameter combinations that enhance stiffness and damage resistance while maintaining manufacturability
2Reliability
If optimized spoke designs are generated through FEM analysis and machine learning, then the tire performance is improved, but the design and analysis time increases
Solution Approach 1:
The patent employs machine learning models that have been pre-trained on extensive FEM analysis data to predict the performance of candidate spoke designs. This preliminary action allows the system to quickly evaluate multiple design options without performing full FEM analysis on each candidate, significantly reducing the overall design and analysis time while maintaining high prediction accuracy for tire performance
Solution Approach 2:
The system implements a feedback mechanism where FEM analysis results from evaluated designs are fed back into the machine learning model to continuously improve its predictions. This iterative feedback process allows the system to learn from actual performance data and refine its optimization criteria, enabling faster and more accurate identification of optimal spoke designs in subsequent iterations
3Adaptability or versatility
If multiple candidate spoke designs are generated, then the flexibility and customization options increase, but the complexity of selection and validation increases
Solution Approach 1:
The patent replaces manual design selection and validation processes with an automated computer-based system that uses machine learning models to evaluate and rank multiple candidate spoke designs. The system automatically compares designs against performance criteria, predicts optimal configurations, and identifies the best candidates for manufacturing, eliminating the need for complex manual assessment and enabling efficient handling of numerous design variations
Data Source
AI summary
Non-Pneumatic Tire (NPT) has been widely used due to their various advantages. Existing solutions/approaches provide limited flexibility on the overall tire performance and have less stiffness and poor damage performance. Embodiments of the present disclosure provides systems and methods that generate optimized spoke design for non-pneumatic tires. More specifically, the system of the present disclosure can generate optimized topology with customized property/performance outcomes for NPTs. The variety of spoke designs have been created using a computer generative method. The performance of these generative spoke designs has been investigated using a finite element method (FEM) technique, wherein output of the FEM technique is used for training machine learning model(s) that enable selection of optimal spoke design for tire manufacturing.