English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Additive Manufacturing (AM) is a manufacturing paradigm that buildsthree-dimensional objects from a computer-aided design model by successivelyadding material layer by layer. AM has become very popular in the past decadedue to its utility for fast prototyping such as 3D printing as well asmanufacturing functional parts with complex geometries using processes such aslaser metal deposition that would be difficult to create using traditionalmachining. As the process for creating an intricate part for an expensive metalsuch as Titanium is prohibitive with respect to cost, computational models areused to simulate the behavior of AM processes before the experimental run.However, as the simulations are computationally costly and time-consuming forpredicting multiscale multi-physics phenomena in AM, physics-informeddata-driven machine-learning systems for predicting the behavior of AMprocesses are immensely beneficial. Such models accelerate not only multiscalesimulation tools but also empower real-time control systems using in-situ data.In this paper, we design and develop essential components of a scientificframework for developing a data-driven model-based real-time control system.Finite element methods are employed for solving time-dependent heat equationsand developing the database. The proposed framework uses extremely randomizedtrees - an ensemble of bagged decision trees as the regression algorithmiteratively using temperatures of prior voxels and laser information as inputsto predict temperatures of subsequent voxels. The models achieve mean absolutepercentage errors below 1% for predicting temperature profiles for AMprocesses. The code is made available for the research community athttps://github.com/paularindam/ml-iter-additive.

A real-time iterative machine learning approach for temperature profile prediction in additive manufacturing processes