Using Unsupervised Learning for Regulating Deposition Speed During Robotic Wire Arc Additive Manufacturing

2021 ◽  
Author(s):  
Ashish Kulkarni ◽  
Prahar M. Bhatt ◽  
Alec Kanyuck ◽  
Satyandra K. Gupta
Keyword(s):  
Additive Manufacturing ◽  
Unsupervised Learning ◽  
Molten Metal ◽  
Length Variation ◽  
Bead Geometry ◽  
Layer By Layer ◽  
Arc Length ◽  
Regulation Scheme ◽  
Speed Regulation ◽  
Wire Arc Additive Manufacturing

Abstract Robotic Wire Arc Additive Manufacturing (WAAM) is the layer-by-layer deposition of molten metal to build a three-dimensional part. In this process, the fed metal wire is melted using an electric arc as a heat source. The process is sensitive to the arc conditions, such as arc length. While building WAAM parts, the metal beads overlap at corners causing material accumulation. Material accumulation is undesirable as it leads to uneven build height and process failures caused by arc length variation. This paper introduces a deposition speed regulation scheme to avoid the corner accumulation problem and build parts with uniform build height. The regulated speed has a complex relationship with the corner angle, bead geometry, and molten metal dynamics. So we need to train a model that can predict suitable speed regulations for corner angles encountered while building the part. We develop an unsupervised learning technique to characterize the uniformity of the bead profile of a WAAM built layer and check for anomalous bead profiles. We train a model using these results that can predict suitable speed regulation parameters for different corner angles. We test this model by building a WAAM part using our speed regulation scheme and validate if the built part has uniform build height and reduced corner defects.

Control of humping phenomenon and analyzing mechanical properties of Al–Si wire-arc additive manufacturing fabricated samples using cold metal transfer process

2021 ◽  
pp. 095440622199840
Author(s):  
Yashwant Koli ◽  
N Yuvaraj ◽  
Aravindan Sivanandam ◽  
Vipin
Keyword(s):  
Mechanical Properties ◽  
Additive Manufacturing ◽  
Heat Input ◽  
Large Scale ◽  
High Deposition Rate ◽  
Bead Geometry ◽  
Layer By Layer ◽  
Cold Metal Transfer ◽  
Geometrical Shapes ◽  
Wire Arc Additive Manufacturing

Nowadays, rapid prototyping is an emerging trend that is followed by industries and auto sector on a large scale which produces intricate geometrical shapes for industrial applications. The wire arc additive manufacturing (WAAM) technique produces large scale industrial products which having intricate geometrical shapes, which is fabricated by layer by layer metal deposition. In this paper, the CMT technique is used to fabricate single-walled WAAM samples. CMT has a high deposition rate, lower thermal heat input and high cladding efficiency characteristics. Humping is a common defect encountered in the WAAM method which not only deteriorates the bead geometry/weld aesthetics but also limits the positional capability in the process. Humping defect also plays a vital role in the reduction of hardness and tensile strength of the fabricated WAAM sample. The humping defect can be controlled by using low heat input parameters which ultimately improves the mechanical properties of WAAM samples. Two types of path planning directions namely uni-directional and bi-directional are adopted in this paper. Results show that the optimum WAAM sample can be achieved by adopting a bi-directional strategy and operating with lower heat input process parameters. This avoids both material wastage and humping defect of the fabricated samples.

Wire arc additive manufacturing of Invar parts: bead geometry and melt pool monitoring

Measurement ◽  
2021 ◽  
pp. 110452
Author(s):  
Fernando Veiga ◽  
Alfredo Suarez ◽  
Eider Aldalur ◽  
Teresa Artaza
Keyword(s):  
Additive Manufacturing ◽  
Bead Geometry ◽  
Melt Pool ◽  
Wire Arc Additive Manufacturing

scholarly journals Review of Aluminum Alloy Development for Wire Arc Additive Manufacturing

Materials ◽  
2021 ◽  
Vol 14 (18) ◽  
pp. 5370
Author(s):  
Geir Langelandsvik ◽  
Odd M. Akselsen ◽  
Trond Furu ◽  
Hans J. Roven
Keyword(s):  
Aluminum Alloy ◽  
Additive Manufacturing ◽  
Alloy Composition ◽  
Layer By Layer ◽  
Alloy Development ◽  
And Performance ◽  
Crack Susceptibility ◽  
Wire Arc Additive Manufacturing ◽  
Further Development ◽  
Complex Parts

Processing of aluminum alloys by wire arc additive manufacturing (WAAM) gained significant attention from industry and academia in the last decade. With the possibility to create large and relatively complex parts at low investment and operational expenses, WAAM is well-suited for implementation in a range of industries. The process nature involves fusion melting of a feedstock wire by an electric arc where metal droplets are strategically deposited in a layer-by-layer fashion to create the final shape. The inherent fusion and solidification characteristics in WAAM are governing several aspects of the final material, herein process-related defects such as porosity and cracking, microstructure, properties, and performance. Coupled to all mentioned aspects is the alloy composition, which at present is highly restricted for WAAM of aluminum but received considerable attention in later years. This review article describes common quality issues related to WAAM of aluminum, i.e., porosity, residual stresses, and cracking. Measures to combat these challenges are further outlined, with special attention to the alloy composition. The state-of-the-art of aluminum alloy selection and measures to further enhance the performance of aluminum WAAM materials are presented. Strategies for further development of new alloys are discussed, with attention on the importance of reducing crack susceptibility and grain refinement.

scholarly journals Experimental Investigation on Mechanical Properties of Part Fabricated by Wire Arc Additive Manufacturing Process

2021 ◽  
Author(s):  
Vivek Kumar P ◽  
◽  
Soundrapandian E ◽  
Jenin Joseph A ◽  
Kanagarajan E ◽  
...  
Keyword(s):  
Mechanical Properties ◽  
Additive Manufacturing ◽  
Manufacturing Process ◽  
Three Dimensional ◽  
Casting Process ◽  
Significant Rise ◽  
Layer By Layer ◽  
Cnc Machine ◽  
Hardness Tester ◽  
Wire Arc Additive Manufacturing

Additive manufacturing process is a method of layer by layer joining of materials to create components from three-dimensional (3D) model data. After their introduction in the automotive sector a decade ago, it has seen a significant rise in research and growth. The Additive manufacturing is classified into different types based upon the energy source use in the fabrication process. In our project, we used self-build CNC machine that runs MACH3 software, as well as the MACH3 controller is used to control the welding torch motion for material addition through three axis movement (X, Y and Z). In the project we used ER70 S-6 weld wire for the fabrication and examined its microstructure and mechanical properties. Different layers of the specimen had different microstructures, according to microstructural studies of the product. Rockwell hardness tester used for testing hardness of the product. According to the observation of the part fabricated components using the Wire Arc Additive Manufacturing process outperformed the mechanical properties of mild steel casting process. The product fabricated by Wire Arc Additive Manufacturing process properties is superior to conventional casting process.

Mapping of Bead Geometry in Wire Arc Additive Manufacturing Systems Using Passive Vision

2022 ◽  
Author(s):  
Marcus O. Couto ◽  
Arthur G. Rodrigues ◽  
Fernando Coutinho ◽  
Ramon R. Costa ◽  
Antonio C. Leite ◽  
...  
Keyword(s):  
Additive Manufacturing ◽  
Manufacturing Systems ◽  
Bead Geometry ◽  
Wire Arc Additive Manufacturing

scholarly journals In Situ Production of Titanium Aluminides during Wire Arc Additive Manufacturing with Hot-Wire Assisted GMAW Process

Metals ◽  
2019 ◽  
Vol 9 (5) ◽  
pp. 578 ◽  
Author(s):  
Philipp Henckell ◽  
Yarop Ali ◽  
Andreas Metz ◽  
Jean Pierre Bergmann ◽  
Jan Reimann
Keyword(s):  
Additive Manufacturing ◽  
Titanium Aluminides ◽  
Gas Metal Arc Welding ◽  
Welding Process ◽  
Alloy Formation ◽  
Layer By Layer ◽  
Feeding Rates ◽  
Hot Wire ◽  
Wire Arc Additive Manufacturing

As part of a feasibility study, an alternative production process for titanium aluminides was investigated. This process is based on in situ alloying by means of a multi-wire technique in the layer-wise additive manufacturing process. Thereby, gas metal arc welding (GMAW) was combined with additional hot-wire feeding. By using two separate wires made of titanium and aluminum, it is possible to implement the alloy formation of titanium aluminides directly in the weld bead of the welding process. In this study, wall structures were built layer-by-layer with alloy compositions between 10 at% and 55 at% aluminum by changing the feeding rates. During this investigation, the macroscopic characteristics, microstructural formation, and the change of the microhardness values were analyzed. A close examination of the influence of welding speed and post-process heat treatment on the Ti–47Al alloy was performed; this being particularly relevant due to its economically wide spread applications.

scholarly journals WAAM Application for EPC Company

2019 ◽  
Vol 269 ◽  
pp. 05002
Author(s):  
Priyantomo Agustinus Ananda
Keyword(s):  
Additive Manufacturing ◽  
Manufacturing Process ◽  
Complex Geometry ◽  
Welding Process ◽  
Feed Speed ◽  
Layer By Layer ◽  
Delivery Time ◽  
Project Schedule ◽  
Wide Range ◽  
Wire Arc Additive Manufacturing

WAAM ( Wire + Arc Additive Manufacturing) is a process of adding material layer by layer in order to build a near net shape components. It shows a further promising future for fabricating large expensive metal components with complex geometry. Engineering Procurement and Construction (EPC) company as one of the industrial section which related with engineering design and products, wide range of material type, and shop based or site based manufacturing process have been dealing with conventional manufacturing and procurement process in order to fulfill its requirement for custom parts and items for the project completion purpose. During the conventional process, there is a risk during the transportation of the products from the manufacturing shop to then site project, this risk is even greater when the delivery time take part as one of the essential part which affect the project schedule. Wire Arc Additive Manufacturing process offering an alternative process to shorten the delivery time and process for a selected material and engineered items, with the consideration of essential variables which can affect the final products of WAAM process, such as : heat input, wire feed speed, travel speed, shielding gas, welding process and robotic system applied. In this paper, the possibilities of WAAM application in EPC company will be assessed, an in depth literature review of the various process which possible to applied, include the loss and benefit compared with conventional method will be presented. The main objective is to identify the current challenge and the prospect of WAAM application in EPC company.

scholarly journals Bead Geometry Prediction in Laser-Wire Additive Manufacturing Process Using Machine Learning: Case of Study

2021 ◽  
Vol 11 (24) ◽  
pp. 11949
Author(s):  
Natago Guilé Mbodj ◽  
Mohammad Abuabiah ◽  
Peter Plapper ◽  
Maxime El Kandaoui ◽  
Slah Yaacoubi
Keyword(s):  
Machine Learning ◽  
Additive Manufacturing ◽  
Prediction Model ◽  
Travel Speed ◽  
Bead Geometry ◽  
Layer By Layer ◽  
Evolutionary Trend ◽  
Deposition Parameters ◽  
Layer Deposition ◽  
Height Prediction

In Laser Wire Additive Manufacturing (LWAM), the final geometry is produced using the layer-by-layer deposition (beads principle). To achieve good geometrical accuracy in the final product, proper implementation of the bead geometry is essential. For this reason, the paper focuses on this process and proposes a layer geometry (width and height) prediction model to improve deposition accuracy. More specifically, a machine learning regression algorithm is applied on several experimental data to predict the bead geometry across layers. Furthermore, a neural network-based approach was used to study the influence of different deposition parameters, namely laser power, wire-feed rate and travel speed on bead geometry. To validate the effectiveness of the proposed approach, a test split validation strategy was applied to train and validate the machine learning models. The results show a particular evolutionary trend and confirm that the process parameters have a direct influence on the bead geometry, and so, too, on the final part. Several deposition parameters have been found to obtain an accurate prediction model with low errors and good layer deposition. Finally, this study indicates that the machine learning approach can efficiently be used to predict the bead geometry and could help later in designing a proper controller in the LWAM process.

Sign in / Sign up

Export Citation Format

Share Document