- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Semi-supervised deep learning based framework for assessing manufacturability of cellular structures in direct metal laser sintering process
摘要： In recent years, metal cellular structures have drawn attentions in various industrial sectors due to their design freedoms and abilities to achieve multi-functional mechanical properties. However, metal cellular structures are dif?cult to fabricate due to their complex geometries, even with modern additive manufacturing technologies such as the direct metal laser sintering (DMLS) process. Assessing the manufacturability of metal cellular structures via a DMLS process is a challenging task as the geometric features of the structures are complex. Besides, via a DMLS process, the manufacturability also depends on the cumulative deformation of the layers during the manufacturing process. Existing methods on Design for Additive Manufacturing (DFAM) provide design guidelines that are based on past successful printed designs. However, they are not effective in predicting the manufacturability of metal cellular structures. In this paper, we propose a semi-supervised deep learning based manufacturability assessment (SSDLMA) framework to assess whether a metal cellular structure can be successfully manufactured from a given DMLS process. To enable ef?cient learning, we represent the complex cellular structures as 3D binary arrays with a simple yet ef?cient voxelisation method. We then train a deep learning based classi?er using only a small amount of experimental data by adopting a semi-supervised learning approach. By running real experiments and comparing with existing DFAM methods and machine learning models, we demonstrate the advantages of the proposed SSDLMA framework. The proposed framework can be extended to predict the manufacturability of various other complex geometries beyond cellular structure in a reliable way even with a small number of training data.
关键词： Design for additive manufacturing,Manufacturability analysis,Direct metal laser sintering,Semi-supervised deep learning,Cellular structures
更新于2025-09-23 15:21:01
-
Study on process and manufacturability of metal-bonded diamond grinding wheel fabricated by selective laser melting (SLM)
摘要： Selective laser melting (SLM) technology is used to fabricate metal-bonded grinding wheel based on mixed powders consisted of metal powders and diamond abrasives. Taguchi method is adopted to obtain the optimal SLM process parameters for grinding wheel considering laser power, scanning speed and layer thickness. Specimens are fabricated with different SLM process parameters for compression and three-point bending tests. Materials characterization and manufacturing limit test are performed on the specimens fabricated by the optimal SLM process. Results indicate that laser power of 250W, scanning speed of 2.5m/s and layer thickness of 20μm are determined as the optimal SLM process in terms of comprehensive mechanical property and formed surface quality. Moreover, diamond abrasives are firmly embedded into aluminium binder with good bonding condition for SLM-fabricated composite. Furthermore, manufacturability of SLM-fabricated composite is evaluated by manufacturing limits of several common structures. In summary, work in this study fully proves the feasibility of SLM-fabricated metal-bonded grinding wheel and provides a solid basis for the further investigation on the novel grinding wheel with customized porous structures.
关键词： diamond abrasives,metal-bonded grinding wheel,manufacturability,Taguchi method,Selective laser melting (SLM)
更新于2025-09-23 15:19:57