Deep-learning-based SLM online quality monitoring and repairing methods and deep-learning-based SLM online quality monitoring and repairing system
US12298750B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 18, 2024 |
| Grant date | May 13, 2025 |
| Priority date | — |
| Expiry date | Jul 18, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30144
- WIPO fieldOther special machines
- WIPO sectorMechanical engineering
Abstract
A deep-learning-based SLM (Selective Laser Melting) online quality monitoring method includes: designing and printing a first defective part; collecting monitoring data of a molten pool of the first defective part in the printing process and performing pre-processing; acquiring defect information distribution of the first defective part and constructing a first data set; training a first convolution neural network model through the first data set; and carrying out online defect information identification on a to-be-tested part by using the trained first convolution neural network model. On the basis of the deep-learning-based SLM online quality monitoring method, the present invention also puts forward a deep-learning-based SLM online repairing method that is used for predicting a repair parameter after identifying a print defect and performing online defect repairing.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.