1-20 of 433 Search Results for

data-driven optimization

Follow your search
Access your saved searches in your account

Would you like to receive an alert when new items match your search?
Close Modal
Sort by
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.a0006994
EISBN: 978-1-62708-439-0
... Abstract Process optimization is the discipline of adjusting a process to optimize a specified set of parameters without violating engineering constraints. This article reviews data-driven optimization methods based on genetic algorithms and stochastic models and demonstrates their use...
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.a0006975
EISBN: 978-1-62708-439-0
..., demonstrating the potential of AM data-driven deep learning to accelerate DFAM processes ( Ref 21 , 22 ). Qui et al. proposed a deep-learning-based model for topology optimization ( Fig. 3 ) ( Ref 21 ). The deep learning model used convolutional neural network, U-net architecture, and recurrent neural network...
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.a0007020
EISBN: 978-1-62708-439-0
... Abstract Data formats play an integral role in leveraging the flexibility of additive manufacturing and achieving consistent part quality. This article compares and contrasts data formats optimized for design, materials, processes, and inspection methods. It also discusses the types of data...
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.a0006950
EISBN: 978-1-62708-439-0
...-for-additive-manufacturing (DFAM) principles are design optimization (DO) and simulation-driven design (SDD). In line with the adoption of AM processes by industry and extensive research efforts in the research community, this article focuses on powder-bed fusion for metal AM and material extrusion for polymer...
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.a0006988
EISBN: 978-1-62708-439-0
... as the former. However, in the pursuit of optimizing structure-property relationships for AM, there is an obvious need for data-driven modeling. This need is motivated simultaneously by the expansive AM design spaces and high computational costs of physics-driven models. At the highest level and in the context...
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.a0006958
EISBN: 978-1-62708-439-0
..., most products and services will be created with the new paradigm of function-driven optimal design, unconstrained by manufacturing methods of the past. In turn, this new paradigm will enable the transformation of supply chains—“Make anything, anywhere, anytime”—whether in the manufacturing plant...
Series: ASM Handbook
Volume: 2B
Publisher: ASM International
Published: 15 June 2019
DOI: 10.31399/asm.hb.v02b.a0006608
EISBN: 978-1-62708-210-5
... (0.25 to 2.0 in.) in T84, T8, and T82 tempers. Tempers are obtained through a conventional one step aging treatment, preceded by a moderate level of cold work. Artificial aging is optimized to provide a good balance of static properties, fracture toughness, and excellent stress corrosion resistance...
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.a0006978
EISBN: 978-1-62708-439-0
... Interpretation There is optimism for implementing machine learning to interpret in situ monitoring data, because these techniques allow for the analysis of large volumes of data, which in turn aids in the discovery of new data relationships. These relationships can then be transformed into actionable...
Series: ASM Handbook
Volume: 8
Publisher: ASM International
Published: 01 January 2000
DOI: 10.31399/asm.hb.v08.a0003259
EISBN: 978-1-62708-176-4
... Abstract The article provides an overview of the various types of testing machines: gear-driven or screw-driven machines and servohydraulic machines. It examines force application systems, force measurement, and strain measurement. The article discusses important instrument considerations...
Series: ASM Handbook
Volume: 22B
Publisher: ASM International
Published: 01 November 2010
DOI: 10.31399/asm.hb.v22b.a0005513
EISBN: 978-1-62708-197-9
... of the deposition due to its computational needs. The “measurements” are data in the thermomechanics solution, which represents how the process wants to evolve under its present parameter setup ( Ref 11 , Ref 12 , Ref 13 , Ref 14 , Ref 15 ). The “feedback” is the correction computed by the optimization solution...
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.a0006951
EISBN: 978-1-62708-439-0
... in the article “ Simulation-Driven Design and the Role of Optimization in Design for Additive Manufacturing ” in this Volume; the emphasis in this article is on the first two approaches. In the field superimposition approach, as shown in Fig. 12 , a physical field can be derived from simulation...
Series: ASM Handbook
Volume: 22A
Publisher: ASM International
Published: 01 December 2009
DOI: 10.31399/asm.hb.v22a.a0005430
EISBN: 978-1-62708-196-2
... of diffusion mobility parameter optimization procedure General Principles The same principles guiding the assessment of thermodynamic data ( Ref 28 ) also apply to diffusion data, with a few additional constraints. First, a thermodynamic database (or description) must be selected to calculate...
Series: ASM Handbook
Volume: 22A
Publisher: ASM International
Published: 01 December 2009
DOI: 10.31399/asm.hb.v22a.a0005407
EISBN: 978-1-62708-196-2
... and not generalize well to new data. In other words, the network is too flexible, and the error of the training set is driven to very small values, but when new data are presented to the network, the error is large. The optimal NNHL depends on the database, nature of the problem to be modeled, and the training...
Series: ASM Handbook
Volume: 14A
Publisher: ASM International
Published: 01 January 2005
DOI: 10.31399/asm.hb.v14a.a0004022
EISBN: 978-1-62708-185-6
... that is driven by factors such as emerging technology, changing customer requirements, and generations of new parts. A design that is optimized under today's conditions may not remain the same tomorrow, due to changes in the available technologies and the marketplace. Arora ( Ref 1 ) observes that correctly...
Series: ASM Handbook
Volume: 22B
Publisher: ASM International
Published: 01 November 2010
DOI: 10.31399/asm.hb.v22b.a0005544
EISBN: 978-1-62708-197-9
... such as design of experiments, optimization, approximations, and design for Six Sigma. Dassault Systèmes http://www.simulia.com/products/isight2.html MATLAB MATLAB is a high-level technical computing language and interactive environment for algorithm development, data visualization, data analysis...
Series: ASM Handbook
Volume: 23A
Publisher: ASM International
Published: 12 September 2022
DOI: 10.31399/asm.hb.v23A.a0006893
EISBN: 978-1-62708-392-8
... photopolymerization, (b) becomes milky white after photopolymerization. Source: Ref 10 . Creative Commons License (CC BY 4.0), https://creativecommons.org/licenses/by/4.0/ The 3D bioprinting process can be classified into four steps: Data acquisition for 3D models . 3D models can be obtained using x...
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.a0006992
EISBN: 978-1-62708-439-0
... ( Ref 1 , 2 ). More recently, applications of machine learning (ML) in the analysis of sensor data have become prevalent. The complex physical phenomena of the AM process lend themselves to analysis by highly nonlinear, data-driven algorithms, making ML an ideal candidate for such analysis. Many...
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.a0006979
EISBN: 978-1-62708-439-0
... in fostering FAIR data management practices/principles and outlines the consequence of such efforts on technology maturation and industrialization for AM technologies. additive manufacturing data management HUMANITY is at the dawn of Materials 4.0, a critical component of the digitally driven, data...
Series: ASM Handbook
Volume: 24A
Publisher: ASM International
Published: 30 June 2023
DOI: 10.31399/asm.hb.v24A.9781627084390
EISBN: 978-1-62708-439-0
Series: ASM Handbook
Volume: 6A
Publisher: ASM International
Published: 31 October 2011
DOI: 10.31399/asm.hb.v06a.a0005608
EISBN: 978-1-62708-174-0
... wire seam welding. Two rotating circular electrode wheels are often used to apply current, force, and cooling to the work metal. When two electrode wheels are used, one or both wheels are driven, either by a direct drive of the wheel axles or by a knurl drive that contacts the peripheral surface...