Deep q-network based directed energy deposition laser power off-line planning method
CN122113539AActive Publication Date: 2026-05-29ZHEJIANG UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG UNIV
- Filing Date
- 2026-04-29
- Publication Date
- 2026-05-29
AI Technical Summary
Technical Problem
In the process of directional energy deposition, existing technologies struggle to achieve efficient offline laser power planning, leading to unstable molten pool conditions and affecting the dimensional accuracy and mechanical properties of the deposited components.
Method used
A deep Q-network is used for offline planning. By constructing a macroscopic temperature field numerical model and a deep reinforcement learning framework, an agent is trained to optimize the laser power sequence and stabilize the molten pool volume.
Benefits of technology
Efficient offline planning of laser power sequence was achieved, which improved the thermal input stability of the directional energy deposition process and enhanced the forming accuracy and quality of the deposited parts.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122113539A_ABST
Abstract
The application discloses a kind of based on deep Q network's directional energy deposition laser power offline planning method, belong to the field of additive manufacturing.The numerical model of macroscopic temperature field based on directional energy deposition process is constructed as interactive environment, the volume of molten pool is extracted as the state feature of heat process, and the target molten pool volume is determined by experiment calibration.The power planning problem is constructed as Markov decision process, the state vector consisting of molten pool volume sequence, discrete power adjustment action set and Gaussian reward function centered on target volume are defined, and the deep reinforcement learning framework is formed.Under this framework, the deep Q network agent is trained to learn the optimal power adjustment strategy.Finally, the laser power sequence of the deposition process is planned offline using the trained agent.The application can plan the optimal laser power sequence offline, stabilize the heat input of directional energy deposition process, effectively suppress defects such as incomplete fusion and cracks, and improve the quality of additive manufacturing.
Need to check novelty before this filing date? Find Prior Art