电弧增材制造温度场预测方法和装置、系统、存储介质
By employing a machine learning method based on physical information, and utilizing finite element analysis and deep learning models, the real-time and accuracy issues of temperature field prediction in arc additive manufacturing were resolved. This enabled rapid and accurate real-time monitoring and prediction of the temperature field during arc additive manufacturing, ensuring high-quality production of parts.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANJING TECH UNIV
- Filing Date
- 2025-02-06
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies for temperature field prediction in electric arc additive manufacturing lack real-time performance and accuracy, making it difficult to achieve rapid real-time monitoring and prediction of the temperature field.
A physical information-based machine learning approach is adopted, which uses finite element analysis to obtain a temperature field dataset, establishes a physical information deep learning model, and extracts spatiotemporal features through ConvLSTM units to perform real-time prediction of the temperature field.
It enables rapid and accurate real-time prediction of the temperature field during electric arc additive manufacturing, meets real-time control requirements, and reduces the risk of part defects and performance instability.
Smart Images
Figure CN120068622B_ABST