A neural network-based build time estimator for layer manufactured objects

Angelo, Luca Di; Stefano, Paolo Di

doi:10.1007/s00170-011-3284-8

Cited by 74 publications

(31 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Build time dictates how machine costs are allocated to a given part and is therefore essential for accurate AM cost estimations [87]. Existing build time models can be grouped into 3 categories: models dedicated to one process using a limit set of parameters; generic build time models that use many parameters to estimate build times; and parametric models that use neural networks to predict production times based on historic data.…”

Section: Build Time Models For Am Productionmentioning

confidence: 99%

“…More recently, process-specific built time models have been proposed for SLM [269], SLS [367], and FDM [373]. Finally, di Angelo and di Stefano developed a neural network-based build time estimator [87]. After 72 training cases, they were able to estimate the build time of six different FDM samples with errors ranging from 6.07 to 20.3%.…”

Section: Build Time Models For Am Productionmentioning

confidence: 99%

See 1 more Smart Citation

Design for Additive Manufacturing: Trends, opportunities, considerations, and constraints

et al. 2016

View full text Add to dashboard Cite

The past few decades have seen substantial growth in Additive Manufacturing (AM) technologies. However, this growth has mainly been process-driven. The evolution of engineering design to take advantage of the possibilities afforded by AM and to manage the constraints associated with the technology has lagged behind. This paper presents the major opportunities, constraints, and economic considerations for Design for Additive Manufacturing. It explores issues related to design and redesign for direct and indirect AM production. It also highlights key industrial applications, outlines future challenges, and identifies promising directions for research and the exploitation of AM's full potential in industry.Design, Manufacturing, Additive Manufacturing

show abstract

Section: Build Time Models For Am Productionmentioning

confidence: 99%

Section: Build Time Models For Am Productionmentioning

confidence: 99%

Design for Additive Manufacturing: Trends, opportunities, considerations, and constraints

et al. 2016

View full text Add to dashboard Cite

show abstract

“…A considerable number of time and cost estimation techniques have been developed since the conception of additive manufacturing and over time have increased in accuracy and practicality. [17][18][19][20][21] Central to many of the techniques presented in the literature is the idea of driving factors for cost and build time: geometric characteristics and additive manufacturing process specifics that ultimately drive the time and material quantity required to construct a design. Topology optimization only has influence over the geometric characteristics of the part design, and therefore, only those factors will be discussed here.…”

Section: Factors Influencing Additive Manufacturing Cost and Build Timementioning

confidence: 99%

“…As previously stated, the K ∼ −1 term in (30) does not need to be solved for explicitly, but rather (30) can be reformulated in a similar manner to (21) and (22).…”

Section: Sensitivity Analysismentioning

confidence: 99%

A multiobjective topology optimization approach for cost and time minimization in additive manufacturing

Ryan

Kim

2019

Numerical Meth Engineering

View full text Add to dashboard Cite

The ever-present drive for increasingly high-performance designs realized on shorter timelines has fostered the need for computational design generation tools such as topology optimization. However, topology optimization has always posed the challenge of generating difficult, if not impossible to manufacture designs. The recent proliferation of additive manufacturing technologies provides a solution to this challenge. The integration of these technologies undoubtedly has the potential for significant impact in the world of mechanical design and engineering. This work presents a new methodology which mathematically considers additive manufacturing cost and build time alongside the structural performance of a component during the topology optimization procedure. Two geometric factors, namely, the surface area and support volume required for the design, are found to correlate to cost and build time and are controlled through the topology optimization procedure. A novel methodology to consider each of these factors dynamically during the topology optimization procedure is presented. The methodology, based largely on the use of the spatial gradient of the density field, is developed in such a way that it does not leverage the finite element discretization scheme. This work investigates a problem that has not yet been explored in the literature: direct minimization of support material volume in density-based topology optimization. The entire methodology is formulated in a smooth and differentiable manner, and the sensitivity expressions required by gradient based optimization solvers are presented. A series of example problems are provided to demonstrate the efficacy of the proposed methodology.

show abstract

“…Rudimentary neural networks have been used to support DfAM in several ways, including estimation of build time [29], prediction of bead geometry for weld-based rapid prototyping [30], and compensation for thermal deformation [31]. In most cases, these and other AM-related neural networks primarily serve to approximate time-consuming calculations that directly connect the "as-designed" structure to the "as-manufactured" structure.…”

Section: Machine Learning To Predict Am Qualitymentioning

confidence: 99%

Predicting Part Mass, Required Support Material, and Build Time via Autoencoded Voxel Patterns

McComb¹,

Meisel²,

Simpson³

et al. 2018

Preprint

View full text Add to dashboard Cite

Additive Manufacturing (AM) allows designers to create intricate geometries that were once too complex or expensive to achieve through traditional manufacturing processes. Currently, Design for Additive Manufacturing (DfAM) is restricted to experts in the field, and novices may overlook potentially transformational design potential enabled by AM. This project aims to make DfAM accessible to a broader audience through deep learning, enabling designers of all skill levels to leverage unique AM geometries when creating new designs. To demonstrate such an approach, a database of files was acquired from industry-sponsored AM challenges focused on lightweight design. These files were converted to a voxelized format, which provides more robust information for machine learning applications. Next, an autoencoder was constructed to a low-dimensional representation of the part designs. Finally, that autoencoder was used to construct a deep neural network capable of predicting various DfAM attributes. This work demonstrates a novel foray towards a more extensive DfAM support system that supports designers at all experience levels.

show abstract

A neural network-based build time estimator for layer manufactured objects

Cited by 74 publications

References 23 publications

Design for Additive Manufacturing: Trends, opportunities, considerations, and constraints

Design for Additive Manufacturing: Trends, opportunities, considerations, and constraints

A multiobjective topology optimization approach for cost and time minimization in additive manufacturing

Predicting Part Mass, Required Support Material, and Build Time via Autoencoded Voxel Patterns

Contact Info

Product

Resources

About