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

During the past decade, metal additive manufacturing (MAM) has experiencedsignificant developments and gained much attention due to its ability tofabricate complex parts, manufacture products with functionally gradedmaterials, minimize waste, and enable low-cost customization. Despite theseadvantages, predicting the impact of processing parameters on thecharacteristics of an MAM printed clad is challenging due to the complex natureof MAM processes. Machine learning (ML) techniques can help connect the physicsunderlying the process and processing parameters to the clad characteristics.In this study, we introduce a hybrid approach which involves utilizing the dataprovided by a calibrated multi-physics computational fluid dynamic (CFD) modeland experimental research for preparing the essential big dataset, and thenuses a comprehensive framework consisting of various ML models to predict andunderstand clad characteristics. We first compile an extensive dataset byfusing experimental data into the data generated using the developed CFD modelfor this study. This dataset comprises critical clad characteristics, includinggeometrical features such as width, height, and depth, labels identifying cladquality, and processing parameters. Second, we use two sets of processingparameters for training the ML models: machine setting parameters andphysics-aware parameters, along with versatile ML models and reliableevaluation metrics to create a comprehensive and scalable learning frameworkfor predicting clad geometry and quality. This framework can serve as a basisfor clad characteristics control and process optimization. The frameworkresolves many challenges of conventional modeling methods in MAM by solving tthe issue of data scarcity using a hybrid approach and introducing anefficient, accurate, and scalable platform for clad characteristics predictionand optimization.

A hybrid machine learning framework for clad characteristics prediction in metal additive manufacturing