scholarly journals Machine Learning for Additive Manufacturing

Encyclopedia ◽  
2021 ◽  
Vol 1 (3) ◽  
pp. 576-588
Author(s):  
Dean Grierson ◽  
Allan E. W. Rennie ◽  
Stephen D. Quayle
Keyword(s):  
Machine Learning ◽  
Additive Manufacturing ◽  
Design Process ◽  
Manufacturing Processes ◽  
Wide Range ◽  
Production Techniques ◽  
End Use ◽  
Industrial Adoption ◽  
Further Development ◽  
Modelling Data

Additive manufacturing (AM) is the name given to a family of manufacturing processes where materials are joined to make parts from 3D modelling data, generally in a layer-upon-layer manner. AM is rapidly increasing in industrial adoption for the manufacture of end-use parts, which is therefore pushing for the maturation of design, process, and production techniques. Machine learning (ML) is a branch of artificial intelligence concerned with training programs to self-improve and has applications in a wide range of areas, such as computer vision, prediction, and information retrieval. Many of the problems facing AM can be categorised into one or more of these application areas. Studies have shown ML techniques to be effective in improving AM design, process, and production but there are limited industrial case studies to support further development of these techniques.

Design Innovation With Additive Manufacturing: A Methodology

2019 ◽  
Author(s):  
K. Blake Perez ◽  
Carlye A. Lauff ◽  
Bradley A. Camburn ◽  
Kristin L. Wood
Keyword(s):  
Additive Manufacturing ◽  
Design Process ◽  
Business Models ◽  
Engineering Product ◽  
Process Framework ◽  
New Business ◽  
Design Innovation ◽  
End Use ◽  
New Business Models

Abstract Additive manufacturing (AM) has matured rapidly in the past decade and has made significant progress towards a reliable and repeatable manufacturing process. The technology opens the doors for new types of innovation in engineering product development. However, there exists a need for a design process framework to efficiently and effectively explore these newly enabled design spaces. Significant work has been done to understand how to make existing products and components additively manufacturable, yet there still exists an opportunity to understand how AM can be leveraged from the very outset of the design process. Beyond end use products, AM-enabled opportunities include an enhanced design process using AM, new business models enabled by AM, and the production of new AM technologies. In this work, we propose the use, adaptation and evolution of the SUTD-MIT International Design Centre’s Design Innovation (DI) framework to assist organizations effectively explore all of these AM opportunities in an efficient and guided manner. We build on prior work that extracted and formalized design principles for AM. This paper discusses the creation and adaptation of the Design Innovation with Additive Manufacturing (DIwAM) methodology, through the combination of these principles and methods under the DI framework to better identify and realize new innovations enabled by AM. The paper concludes with a representative case study with industry that employs the DIwAM framework and the outcomes of that project. Future studies will analyze the effects that DIwAM has on designers, projects, and solutions.

Study and Application of Machine Learning Methods in Modern Additive Manufacturing Processes

2022 ◽  
pp. 75-95
Author(s):  
Ranjit Barua ◽  
Sudipto Datta ◽  
Pallab Datta ◽  
Amit Roychowdhury
Keyword(s):  
Machine Learning ◽  
Additive Manufacturing ◽  
Quality Evaluation ◽  
Mechanical Characteristics ◽  
Manufacturing Processes ◽  
Superior Part ◽  
Machine Learning Methods ◽  
Excellent Control ◽  
Part Feature ◽  
Counting Model

Additive manufacturing (AM) make simpler the manufacturing of difficult geometric structures. Its possibility has quickly prolonged from the manufacture of pre-fabrication conception replicas to the making of finish practice portions driving the essential for superior part feature guarantee in the additively fabricated products. Machine learning (ML) is one of the encouraging methods that can be practiced to succeed in this aim. A modern study in this arena contains the procedure of managed and unconfirmed ML algorithms for excellent control and forecast of mechanical characteristics of AM products. This chapter describes the development of applying machine learning (ML) to numerous aspects of the additive manufacturing whole chain, counting model design, and quality evaluation. Present challenges in applying machine learning (ML) to additive manufacturing and possible solutions for these problems are then defined. Upcoming trends are planned in order to deliver a general discussion of this additive manufacturing area.

Redesigning a Reaction Control Thruster for Metal-Based Additive Manufacturing: A Case Study in Design for Additive Manufacturing

2017 ◽  
Vol 139 (10) ◽  
Author(s):  
Nicholas A. Meisel ◽  
Matthew R. Woods ◽  
Timothy W. Simpson ◽  
Corey J. Dickman
Keyword(s):  
Additive Manufacturing ◽  
Attitude Control ◽  
Manufacturing Processes ◽  
Development Effort ◽  
Design For Additive Manufacturing ◽  
Powder Bed ◽  
Subtractive Manufacturing ◽  
End Use ◽  
Manufacturing Time

Prior research has shown that powder-bed fusion (PBF) additive manufacturing (AM) can be used to make functional, end-use components from powdered metallic alloys, such as Inconel® 718 superalloy. However, these end-use components and products are often based on designs developed for more traditional subtractive manufacturing processes and do not take advantage of the unique design freedoms afforded by AM. In this paper, we present a case study involving the redesign of NASA’s existing “pencil” thruster used for spacecraft attitude control. The initial pencil thruster was designed for and manufactured using traditional subtractive methods. The main focus in this paper is to (a) identify the need for and use of both opportunistic and restrictive design for additive manufacturing (DfAM) concepts and considerations in redesigning the thruster for fabrication with PBF AM and (b) compare the resulting DfAM thruster with a parallel development effort redesigning the original thruster to be manufactured more effectively using subtractive manufacturing processes. The results from this case study show how developing end-use AM components using specific DfAM guidelines can significantly reduce manufacturing time and costs while enabling new and novel design geometries.

scholarly journals Additive methods in micro and nano manufacturing technologies

Mechanik ◽  
2019 ◽  
Vol 92 (5-6) ◽  
pp. 386-390
Author(s):  
Adam Ruszaj
Keyword(s):  
Additive Manufacturing ◽  
Scanning Tunneling ◽  
Manufacturing Processes ◽  
Technological Problem ◽  
Tunneling Microscopy ◽  
Force Microscopy ◽  
Atomic Force ◽  
Manufacturing Technologies ◽  
Further Development ◽  
Working Out

In 1959 R.P. Feynman has presented the concept and strategy of micro- and nanotechnology development. Their introduction to the practice took place after working out the scanning tunneling microscopy (1981) and atomic force microscopy (1985). In the further development of micro- and nanotechnology the micro and nano electromechanical systems (MEMS, NEMS) have been worked. MEMS and NEMS are widely applied in majority of modern equipment and the production of the equipment increases about 17÷20% per year since 1990s. MEMS and NEMS manufacture usually is a difficult technological problem because of small dimensions and complex outside and inside structures. In such cases the application of additive manufacturing processes can be very promising. In the paper the possibilities of additive manufacturing processes applications, mainly in microtechnologies, is presented.

Design Process Deconstructed: The Industry Case of an Elevator Button Assembly Redesigned for Additive Manufacturing

2019 ◽  
Author(s):  
Tuomas Puttonen
Keyword(s):  
Functional Analysis ◽  
Additive Manufacturing ◽  
Design Process ◽  
Efficient Design ◽  
3D Design ◽  
Design Methodologies ◽  
Current Design ◽  
Volume Product ◽  
End Use ◽  
Manufacturing Technologies

Abstract Additive manufacturing (AM) has during the 21st century gradually shifted from prototyping towards the manufacture of end-use quality parts. The drivers to utilize AM instead of conventional manufacturing methods are often linked to geometrical design freedom, increased performance, customization, part consolidation, and weight reduction. However, designers have struggled to take full advantage of these new capabilities. In part, this is due to a pervasive engineering mindset locked into the constraints of conventional manufacturing technologies. Another reason is the lack of efficient design methodologies that would take into account the new capabilities of AM. In this paper, to address the latter deficiency, an assembly redesign process for AM is deconstructed and analyzed. The studied assembly is an elevator accessibility button, which is a high-mix low-volume product. From the industry perspective, AM could reduce costs and increase the agility of production. Through systematic requirements mapping, part- and product-level functional analysis, a holistic functional analysis of the product is composed. The results of the product functional analysis are illustrated in a visual 3D design space. The 3D illustration is suggested as a conceptualization tool for the designers and as a way to reinforce creativity in the design process. The usability and expandability of the tool are discussed and contrasted with the current design methodologies for AM.

scholarly journals A Machine Learning Approach of Lattice Infill Pattern for Increasing Material Efficiency in Additive Manufacturing Processes

2020 ◽  
pp. 1253-1263
Author(s):  
Jonnel D. Alejandrino ◽  
Ronnie S. II Concepcion ◽  
Sandy C. Lauguico ◽  
Rogelio Ruzcko Tobias ◽  
Lenardo Venancio ◽  
...  
Keyword(s):  
Machine Learning ◽  
Additive Manufacturing ◽  
Manufacturing Processes ◽  
Learning Approach ◽  
Material Efficiency ◽  
Machine Learning Approach

Application of TEM to Deformation, Wear, and Fracture of Ceramics

1974 ◽  
Vol 32 ◽  
pp. 472-473
Author(s):  
B. J. Hockey
Keyword(s):  
Wear Resistance ◽  
High Temperature ◽  
Mechanical Behavior ◽  
Brittle Materials ◽  
High Temperature Strength ◽  
Wide Range ◽  
Corrosive Environments ◽  
Further Development

Ceramics, such as Al2O3 and SiC have numerous current and potential uses in applications where high temperature strength, hardness, and wear resistance are required often in corrosive environments. These materials are, however, highly anisotropic and brittle, so that their mechanical behavior is often unpredictable. The further development of these materials will require a better understanding of the basic mechanisms controlling deformation, wear, and fracture.The purpose of this talk is to describe applications of TEM to the study of the deformation, wear, and fracture of Al2O3. Similar studies are currently being conducted on SiC and the techniques involved should be applicable to a wide range of hard, brittle materials.

Sign in / Sign up

Export Citation Format

Share Document