Mold Design Optimization via Feature Extraction and Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The mold development process in computer-aided engineering (CAE) is time-consuming and costly due to the lack of clear standards for selecting key feature parameters and the complexity of parameters involved, leading to inefficient mold flow analysis and excessive mold testing costs.
Innovation Solution
An optimization method based on feature extraction and machine learning that retrieves historical mold data, performs similarity calculations, and filters mold design parameters to generate representative data for simulation analysis, reducing the need for trial and error and optimizing parameter variation ranges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional CAE mold flow analysis is used with comprehensive parameter consideration, then analysis accuracy is improved, but analysis time and computational cost increase significantly
Solution Approach 1:
The patent extracts and identifies key feature parameters from the comprehensive set of mold design parameters through machine learning analysis of historical data. By separating the critical parameters (such as injection pressure, temperature, and flow rate) from non-critical ones, the system maintains analysis accuracy while reducing the computational burden to a manageable subset of parameters.
Solution Approach 2:
The system performs preliminary analysis by retrieving and analyzing historical mold data before conducting the actual mold flow analysis. This preliminary action identifies patterns and key parameters in advance, allowing the subsequent analysis to focus only on relevant parameters, thereby reducing overall analysis time while maintaining accuracy.
2Manufacturing precision
If comprehensive mold design parameters are considered in mold development, then design quality is improved, but computational process becomes very time consuming
Solution Approach 1:
The patent applies feature extraction techniques to identify and isolate the most influential design parameters from the comprehensive parameter set. By extracting only the critical parameters that significantly impact design quality, the system maintains high design quality standards while reducing computational complexity and processing time.
Solution Approach 2:
The system transforms the comprehensive parameter space into a reduced parameter space by identifying key features and their optimal ranges. This parameter transformation allows the system to maintain design quality by focusing on critical parameters while improving computational efficiency through reduced dimensionality.
3Adaptability or versatility
If large variation range of parameters is maintained for new mold, then parameter coverage is improved, but parameter optimization becomes ineffective and mold testing cost increases
Solution Approach 1:
The patent uses machine learning to analyze historical mold data and identify optimal parameter ranges and relationships. By transforming the broad parameter variation ranges into optimized, constrained ranges based on learned patterns, the system maintains adequate parameter coverage for adaptability while significantly reducing the number of required mold testing iterations.
Solution Approach 2:
The system incorporates feedback from historical mold data and simulation results to continuously refine parameter ranges and optimization strategies. This feedback mechanism allows the system to maintain comprehensive parameter coverage while learning from past experiences to reduce testing costs through more effective parameter optimization.
Data Source
AI summary
An optimization method based on feature extraction and machine learning is provided. At least one input parameter is received. Multiple first historical mold data are retrieved. A similarity calculation is performed according to the input parameter and the first historical mold data. Multiple candidate mold data are selected according to the similarity calculation. The mold design parameters of the candidate mold data corresponding to each input parameter are replaced by the input parameter, and multiple first representative mold data for performing a first simulation analysis are generated. Multiple key feature parameters are found, and multiple second historical mold data are retrieved according to the multiple key feature parameters. An expected data is found, and the mold design parameters of the expected data are filtered and optimized to find multiple second representative mold data for performing a second simulation analysis. At least one set of mold production parameters is generated.