Search results
1 – 2 of 2Yingjie Zhang, Wentao Yan, Geok Soon Hong, Jerry Fuh Hsi Fuh, Di Wang, Xin Lin and Dongsen Ye
This study aims to develop a data fusion method for powder-bed fusion (PBF) process monitoring based on process image information. The data fusion method can help improve process…
Abstract
Purpose
This study aims to develop a data fusion method for powder-bed fusion (PBF) process monitoring based on process image information. The data fusion method can help improve process condition identification performance, which can provide guidance for further PBF process monitoring and control system development.
Design/methodology/approach
Design of reliable process monitoring systems is an essential approach to solve PBF built quality. A data fusion framework based on support vector machine (SVM), convolutional neural network (CNN) and Dempster-Shafer (D-S) evidence theory are proposed in the study. The process images which include the information of melt pool, plume and spatters were acquired by a high-speed camera. The features were extracted based on an appropriate image processing method. The three feature vectors corresponding to the three objects, respectively, were used as the inputs of SVM classifiers for process condition identification. Moreover, raw images were also used as the input of a CNN classifier for process condition identification. Then, the information fusion of the three SVM classifiers and the CNN classifier by an improved D-S evidence theory was studied.
Findings
The results demonstrate that the sensitivity of information sources is different for different condition identification. The feature fusion based on D-S evidence theory can improve the classification performance, with feature fusion and classifier fusion, the accuracy of condition identification is improved more than 20%.
Originality/value
An improved D-S evidence theory is proposed for PBF process data fusion monitoring, which is promising for the development of reliable PBF process monitoring systems.
Details
Keywords
Qiqiang Cao, Jiong Zhang, Shuai Chang, Jerry Ying Hsi Fuh and Hao Wang
This study aims to further the understanding of support structures and the likely impacts on maraging steel MS1 parts fabricated by selective laser melting (SLM) at 45°, 60° and…
Abstract
Purpose
This study aims to further the understanding of support structures and the likely impacts on maraging steel MS1 parts fabricated by selective laser melting (SLM) at 45°, 60° and 75° building angles.
Design/methodology/approach
Two groups of samples, one group with support structures and the other group without support structures, were designed with the same specifications and printed under the same conditions by SLM at 45°, 60° and 75° building angles. Differences in dimensional accuracy, surface roughness, Vickers microhardness, residual stress and microstructure were compared between groups.
Findings
The results showed that with support structures, more accurate dimension and slightly higher Vickers microhardness could be obtained. Larger compressive stress dominated and was more uniformly distributed on the supporting surface. Without support structures, the dimension became more precise as the building angle increased and alternating compressive and tensile stress was unevenly distributed on the supporting surface. In addition, the surface roughness of the outer surface decreased with the increase of the built angle, regardless of the support structures. Furthermore, whether the building angle was 45°, 60° or 75°, the observed microstructures revealed that the support structures altered the orientation of the molten pool and the direction of grain growth.
Originality/value
This paper studies the influence of support structures on the workpieces printed at different building angles. Support structures affect the residual stress distribution, heat dissipation rate and microstructure of the parts, and thus affecting the printing quality. Therefore, it is necessary to balance the support strategy and printing quality to better apply or design the support structures in SLM.
Details