A model-experiment collaborative polymer additive manufacturing process parameter optimization method
By employing a model-experiment collaborative approach, XGBoost models and utility functions are used to optimize polymer additive manufacturing process parameters. This addresses the issues of interference from unmodeled physical mechanisms and execution errors, enabling efficient exploration and robustness of high-performance process parameters.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUNAN UNIV
- Filing Date
- 2026-04-22
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies in polymer additive manufacturing suffer from problems such as interference from unmodeled physical mechanisms, errors in input parameter execution, conflicts between theoretical optimization and actual execution costs, and the failure of traditional methods to effectively utilize complex microstructure features.
A model-experiment collaborative approach is adopted. By collecting process parameter vectors, the XGBoost model is used to predict performance, construct a utility function, and combine environmental factor perturbations and physical constraints to iteratively optimize process parameters until the performance prediction results converge and meet the physical regression verification.
It enables efficient exploration of high-performance process parameters, solves the problems of noise resistance mechanism and environmental robustness under small sample conditions, reduces experimental costs, and ensures the robustness and feasibility of optimization results.
Smart Images
Figure CN122401904A_ABST