Machine Learning Composite Laminate Design Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The design and manufacturing of composite laminates for mechanical parts are time-consuming and costly due to the complexity of predicting material properties at various levels, with existing methods relying on simplified models and different approaches, leading to imprecise results.
Innovation Solution
A computer-implemented method using a trained machine learning device to predict material properties of composite laminates based on geometrical models and load conditions, allowing for iterative optimization of material features to achieve desired performance, thereby determining the optimal composite laminate for manufacturing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If simplified semi-empirical models (e.g., Halpin-Tsai equations) are used to predict material properties, then the design process becomes faster and less costly, but the prediction precision deteriorates
Solution Approach 1:
The patent creates a digital twin (virtual model) of the composite laminate that replicates its microstructure, mesostructure, and macrostructure. This digital copy allows for virtual testing and prediction of material properties without physical prototyping, enabling fast iteration while maintaining high accuracy through realistic structural representation.
Solution Approach 2:
The patent performs preliminary computer-aided engineering (CAE) simulations during the design phase to predict material properties before manufacturing. By conducting virtual tests and optimizations in advance, the system eliminates the need for costly and time-consuming physical prototypes while achieving accurate property predictions.
2Manufacturing precision
If detailed design and determination of composite laminate are performed manually, then the design quality improves, but the time and human resources required increase significantly
Solution Approach 1:
The system implements automated design optimization where the computer system performs material property prediction, performance evaluation, and laminate optimization autonomously. The system uses algorithms to automatically adjust material specifications and ply configurations based on performance requirements, reducing manual intervention while maintaining high design quality.
Solution Approach 2:
The patent replaces manual mechanical design processes with computer-aided engineering simulations and automated optimization algorithms. The system uses software to perform tasks that previously required human engineers to manually calculate and evaluate different laminate configurations, dramatically reducing design time while maintaining or improving design quality.
3Adaptability or versatility
If different non-interrelated approaches are used to predict material properties at various levels, then the design flexibility increases, but the overall design accuracy deteriorates
Solution Approach 1:
The patent integrates micro-level, meso-level, and macro-level modeling approaches into a unified multi-scale framework. The digital twin connects these different scales, allowing material properties at the micro-level to influence meso-level behavior, which in turn affects macro-level performance. This unified approach ensures consistency across all levels while maintaining the flexibility to model different material specifications.
Data Source
AI summary
A method and apparatus for obtaining a composite laminate that has plies each composed of a matrix and a filler includes receiving a model and load conditions of a mechanical part to be produced from the composite laminate, predicting properties of a candidate laminate based on features thereof by machine learning, evaluating a performance of the mechanical part produced in accordance with the model from the candidate laminate when subject to the load conditions, based on the predicted properties, optimizing the performance of the mechanical part by varying the features of the candidate laminate and repeating the predicting and evaluating steps until a desired performance is achieved; and determining the candidate laminate thus optimized as the composite laminate for manufacturing the mechanical part, where the method and apparatus can automatically obtain an optimum composite material for a given design task.