期刊
JOURNAL OF MANUFACTURING PROCESSES
卷 35, 期 -, 页码 570-579出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.jmapro.2018.08.038
关键词
Additive manufacturing; Material extrusion; Fused deposition modeling; Fault diagnosis; Process monitoring; Acoustic emission; Dimensionality reduction; Clustering; Machine learning
资金
- China Scholarship Council [201606160048]
- National Natural Science Foundation of China [51175208]
- U.S. National Science Foundation [CMMI 1547102]
The reliability and performance of additive manufacturing (AM) machines affect the product quality and manufacturing cost. Developing effective health monitoring and prognostics methods is critical to AM productivity. Yet limited work is done on machine health monitoring. Recently, the application of acoustic emission sensor (AE) to the fault diagnosis of material extrusion or fused deposition modeling process was demonstrated. One challenge in real-time process monitoring is processing the large amount of data collected by high-fidelity sensors for diagnostics and prognostics. In this paper, the efficiency of machine state identification from AE data is significantly improved with reduced feature space dimension. In the proposed method, features extracted in both time and frequency domains are combined and then reduced with the linear discriminant analysis. An unsupervised density based clustering method is applied to classify and recognize different machine states of the extruder. Experimental results show that the proposed approach can effectively identify machine states of the extruder even within a much smaller feature space.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据