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/

Zendy Plus

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

Zendy Tools

Zendy Open

In this paper, we demonstrate the combination of machine learning and threedimensional numerical simulations for multi-objective optimization of lowpressure die casting. The cooling of molten metal inside the mold is achievedtypically by passing water through the cooling lines in the die. Depending onthe cooling line location, coolant flow rate and die geometry, nonuniformtemperatures are imposed on the molten metal at the mold wall. This boundarycondition along with the initial molten metal temperature affect the productquality quantified in terms of micro-structure parameters and yield strength. Afinite volume based numerical solver is used to determine the temperature-timehistory and correlate the inputs to outputs. The objective of this research isto develop and demonstrate a procedure to obtain the initial and walltemperatures so as to optimize the product quality. The non-dominated sortinggenetic algorithm (NSGA-II) is used for multi-objective optimization in thiswork. The number of function evaluations required for NSGA-II can be of theorder of millions and hence, the finite volume solver cannot be used directlyfor optimization. Therefore, a multilayer perceptron feed-forward neuralnetwork is first trained using the results from the numerical solution of thefluid flow and energy equations and is subsequently used as a surrogate model.As an assessment, simplified versions of the actual problem are designed tofirst verify results of the genetic algorithm. An innovative local sensitivitybased approach is then used to rank the final Pareto optimal solutions andselect a single best design.

Optimization of Solidification in Die Casting using Numerical Simulations and Machine Learning