Continuous Eulerian tool path strategies for wire-arc additive manufacturing of rib-web structures with machine-learning-based adaptive void filling

2020 ◽  
Vol 35 ◽  
pp. 101265 ◽  
Author(s):  
Lam Nguyen ◽  
Johannes Buhl ◽  
Markus Bambach
Keyword(s):  
Machine Learning ◽  
Additive Manufacturing ◽  
Tool Path ◽  
Wire Arc Additive Manufacturing

scholarly journals DECOMPOSITION ALGORITHM FOR TOOL PATH PLANNING FOR WIRE-ARC ADDITIVE MANUFACTURING

2018 ◽  
Vol Vol.18 (No.1) ◽  
pp. 96-107 ◽  
Author(s):  
Lam NGUYEN ◽  
Johannes BUHL ◽  
Markus BAMBACH
Keyword(s):  
Additive Manufacturing ◽  
Path Planning ◽  
Computer Aided Design ◽  
Tool Path ◽  
Heuristic Method ◽  
Support Material ◽  
Build Time ◽  
Cad Models ◽  
Aided Design ◽  
Wire Arc Additive Manufacturing

Three-axis machines are limited in the production of geometrical features in powder-bed additive manufacturing processes. In case of overhangs, support material has to be added due to the nature of the process, which causes some disadvantages. Robot-based wire-arc additive manufacturing (WAAM) is able to fabricate overhangs without adding support material. Hence, build time, waste of material, and post-processing might be reduced considerably. In order to make full use of multi-axis advantages, slicing strategies are needed. To this end, the CAD (computer-aided design) model of the part to be built is first partitioned into sub-parts, and for each sub-part, an individual build direction is identified. Path planning for these sub-parts by slicing then enables to produce the parts. This study presents a heuristic method to deal with the decomposition of CAD models and build direction identification for sub-entities. The geometric data of two adjacent slices are analyzed to construct centroidal axes. These centroidal axes are used to navigate the slicing and building processes. A case study and experiments are presented to exemplify the algorithm.

scholarly journals Stable honeycomb structures and temperature based trajectory optimization for wire-arc additive manufacturing

2020 ◽  
Author(s):  
Martin Bähr ◽  
Johannes Buhl ◽  
Georg Radow ◽  
Johannes Schmidt ◽  
Markus Bambach ◽  
...  
Keyword(s):  
Additive Manufacturing ◽  
Trajectory Optimization ◽  
Tool Path ◽  
Honeycomb Structure ◽  
Mixed Integer ◽  
Voronoi Tesselation ◽  
Integer Linear Programming Problem ◽  
Mathematical Problems ◽  
Wire Arc Additive Manufacturing

Abstract We consider two mathematical problems that are connected and occur in the layer-wise production process of a workpiece using wire-arc additive manufacturing. As the first task, we consider the automatic construction of a honeycomb structure, given the boundary of a shape of interest. In doing this, we employ Lloyd’s algorithm in two different realizations. For computing the incorporated Voronoi tesselation we consider the use of a Delaunay triangulation or alternatively, the eikonal equation. We compare and modify these approaches with the aim of combining their respective advantages. Then in the second task, to find an optimal tool path guaranteeing minimal production time and high quality of the workpiece, a mixed-integer linear programming problem is derived. The model takes thermal conduction and radiation during the process into account and aims to minimize temperature gradients inside the material. Its solvability for standard mixed-integer solvers is demonstrated on several test-instances. The results are compared with manufactured workpieces.

Machine Learning Models for Detecting Weld Bead Defects in Wire-Arc Additive Manufacturing

2021 ◽  
Vol 26 (2) ◽  
pp. 131-143
Author(s):  
Jun-Seong Kim ◽  
Gi-Jeong Seo ◽  
Duck Bong Kim ◽  
Jong-Ho Shin ◽  
Hyungjun Park
Keyword(s):  
Machine Learning ◽  
Additive Manufacturing ◽  
Weld Bead ◽  
Learning Models ◽  
Wire Arc Additive Manufacturing ◽  
Machine Learning Models

scholarly journals A Multiaxis Tool Path Generation Approach for Thin Wall Structures Made with WAAM

2021 ◽  
Vol 5 (4) ◽  
pp. 128
Author(s):  
Matthieu Rauch ◽  
Jean-Yves Hascoet ◽  
Vincent Querard
Keyword(s):  
Additive Manufacturing ◽  
High Performance ◽  
Tool Path ◽  
Tool Path Generation ◽  
Path Generation ◽  
Thin Wall ◽  
Process Data ◽  
Technical Data ◽  
Wall Structures ◽  
Wire Arc Additive Manufacturing

Wire Arc Additive Manufacturing (WAAM) has emerged over the last decade and is dedicated to the realization of high-dimensional parts in various metallic materials. The usual process implementation consists in associating a high-performance welding generator as heat source, a NC controlled 6 or 8 degrees (for example) of freedom robotic arm as motion system and welding wire as feedstock. WAAM toolpath generation methods, although process specific, can be based on similar approaches developed for other processes, such as machining, to integrate the process data into a consistent technical data environment. This paper proposes a generic multiaxis tool path generation approach for thin wall structures made with WAAM. At first, the current technological and scientific challenges associated to CAD/CAM/CNC data chains for WAAM applications are introduced. The focus is on process planning aspects such as non-planar non-parallel slicing approaches and part orientation into the working space, and these are integrated in the proposed method. The interest of variable torch orientation control for complex shapes is proposed, and then, a new intersection crossing tool path method based on Design For Additive Manufacturing considerations is detailed. Eventually, two industrial use cases are introduced to highlight the interest of this approach for realizing large components.

scholarly journals Quality Prediction and Control in Wire Arc Additive Manufacturing via Novel Machine Learning Framework

Micromachines ◽  
2022 ◽  
Vol 13 (1) ◽  
pp. 137
Author(s):  
Xinyi Xiao ◽  
Clarke Waddell ◽  
Carter Hamilton ◽  
Hanbin Xiao
Keyword(s):  
Machine Learning ◽  
Additive Manufacturing ◽  
Prediction Model ◽  
Analytical Models ◽  
Process Variables ◽  
Depth Of Penetration ◽  
Bead Width ◽  
Learning Framework ◽  
And Control ◽  
Wire Arc Additive Manufacturing

Wire arc additive manufacturing (WAAM) is capable of rapidly depositing metal materials thus facilitating the fabrication of large-shape metal components. However, due to the multi-process-variability in the WAAM process, the deposited shape (bead width, height, depth of penetration) is difficult to predict and control within the desired level. Ultimately, the overall build will not achieve a near-net shape and will further hinder the part from performing its functionality without post-processing. Previous research primarily utilizes data analytical models (e.g., regression model, artificial neural network (ANN)) to forwardly predict the deposition width and height variation based on single or cross-linked process variables. However, these methods cannot effectively determine the optimal printable zone based on the desired deposition shape due to the inability to inversely deduce from these data analytical models. Additionally, the process variables are intercorrelated, and the bead width, height, and depth of penetration are highly codependent. Therefore, existing analysis cannot grant a reliable prediction model that allows the deposition (bead width, height, and penetration height) to remain within the desired level. This paper presents a novel machine learning framework for quantitatively analyzing the correlated relationship between the process parameters and deposition shape, thus providing an optimal process parameter selection to control the final deposition geometry. The proposed machine learning framework can systematically and quantitatively predict the deposition shape rather than just qualitatively as with other existing machine learning methods. The prediction model can also present the complex process-quality relations, and the determination of the deposition quality can guide the WAAM to be more prognostic and reliable. The correctness and effectiveness of the proposed quantitative process-quality analysis will be validated through experiments.

Sign in / Sign up

Export Citation Format

Share Document