基于机器学习的高性能制件的增材制造制备方法
The powder particle size distribution characteristics-process parameters-part performance prediction model established by machine learning solves the problem of insufficient part performance in additive manufacturing technology, realizes efficient and low-cost high-performance part preparation, and improves the density and mechanical properties of the parts.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UNIV OF SCI & TECH BEIJING
- Filing Date
- 2023-05-10
- Publication Date
- 2026-07-17
AI Technical Summary
Existing additive manufacturing technologies are insufficient to meet stringent requirements for the performance of components manufactured in the field of high-end equipment. Traditional research methods are time-consuming and labor-intensive and cannot accurately analyze complex changes. Insufficient research on the adaptability of bimodal powder processes hinders technological progress and application.
A machine learning-based method was used to establish a prediction model of powder particle size distribution characteristics, process parameters, and part performance. The optimal process parameters were quickly determined through GBDT model optimization, and additive manufacturing was carried out using bimodal particle size distribution powder.
It enables efficient fabrication of high-performance parts, reduces R&D time and costs, improves the density, surface quality and mechanical properties of parts, expands the powder particle size range, and improves laser energy absorption rate and processing efficiency.
Smart Images
Figure CN116796630B_ABST