Optimization of solidification in die casting using numerical simulations and machine learning

Shahane, Shantanu; Aluru, N. R.; Ferreira, Placid M.; Kapoor, Shiv Gopal; Vanka, Surya Pratap

doi:10.1016/j.jmapro.2020.01.016

Cited by 30 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Miller demonstrated in a 1-D model to challenge common notions of how many cycles it takes to attain a quasi-steady state [50]. Other studies, especially modeling-based investigations, have shown that die temperature is a high impact parameter on castings and the dies themselves [51][52][53][54]. For these reasons, a robust and reliable method of collecting the die temperature is the next source of data to drive predictive modeling forward.…”

Section: Results Of Neural Network Regression Methodsmentioning

confidence: 99%

Model Selection and Evaluation for Machine Learning: Deep Learning in Materials Processing

Kopper¹,

Karkare

Paffenroth³

et al. 2020

Integr Mater Manuf Innov

View full text Add to dashboard Cite

Materials processing is a critical subset of manufacturing which is benefitting by implementing machine learning to create knowledge from the data mined/collected and gain a deeper understanding of manufacturing processes. In this study, we focus on aluminum high-pressure die-casting (HPDC) process, which constitutes over 60% of all cast Al components. Routinely collected process data over a year's time of serial production are used to make predictions on mechanical properties of castings, specifically, the ultimate tensile strength (UTS). Random Forest, Support Vector Machine (SVM), and XGBoost regression algorithms were selected from the machine learning spectrum along with a Neural Network, a deep learning method. These methods were evaluated and assessed and were compared to predictions based on historical data. Machine learning, including Neural Network, regression models do improve the predictability of UTS above that of predicting the mean from prior tests. Choosing the correct models to use for the data requires an understanding of the bias-variance trade-off such that a balance is struck between the complexity of the algorithms chosen and the size of the dataset in question. These concepts are reviewed and discussed in context of HPDC.

show abstract

Section: Results Of Neural Network Regression Methodsmentioning

confidence: 99%

Model Selection and Evaluation for Machine Learning: Deep Learning in Materials Processing

Kopper¹,

Karkare

Paffenroth³

et al. 2020

Integr Mater Manuf Innov

View full text Add to dashboard Cite

show abstract

“…Finally, in a number of previous papers on metal manufacturing, several optimization techniques, such as the genetic algorithm, [131][132][133][134] particle swarm optimization, 46,135 Bayesian optimization, [136][137][138] and even statistical approaches like response surface methodology, 17,139,140 Taguchi's design of experiment, and analysis of variance (ANOVA), [141][142][143] have been used. The main difference between these methods and the RL is that the former do not ''learn from experience.''…”

Section: Process Optimizations For Manufacturing Mmcs Using Reinforcement Learningmentioning

confidence: 99%

A Review of Application of Machine Learning in Design, Synthesis, and Characterization of Metal Matrix Composites: Current Status and Emerging Applications

Kordijazi

Zhao

Zhang

et al. 2021

JOM

View full text Add to dashboard Cite

In this article we provide an overview on the current and emerging applications of machine learning (ML) in the design, synthesis, and characterization of metal matrix composites (MMC). We have demonstrated that ML methods can be applied in three distinct categories, namely property prediction, microstructure analysis, and process optimization, which are associated with three major classes of ML techniques, i.e., regression, classification, and optimal control, respectively. ML algorithms have been successfully applied for prediction of mechanical, tribological, corrosion, and wetting properties of different MMCs. However, ML methods (e.g., computer vision, which is suitable for microstructural characterization and defect detections) and optimization algorithms (e.g., reinforcement learning) have not been fully utilized for design, processing, and characterization of metal matrix composites despite their enormous capacities. We conclude that ML methods are promising not only to predict various properties but also to automate microstructural analysis and optimization of manufacturing MMCs.

show abstract

“…Based on these results, the molten metal flow systems are modified, which leads to improvements of the process and deepened knowledge about the phenomena of flow in casting processes. An approach for multi-objective optimization of the solidification of casting processes is shown in [29] by using machine learning combined with process simulations.…”

Section: Combining Structural Optimization and Process Assurancementioning

confidence: 99%

Combining Structural Optimization and Process Assurance in Implicit Modelling for Casting Parts

et al. 2021

View full text Add to dashboard Cite

The structural optimization of manufacturable casting parts is still a challenging and time-consuming task. Today, topology optimization is followed by a manual reconstruction of the design proposal and a process assurance simulation to endorse the design proposal. Consequently, this process is iteratively repeated until it reaches a satisfying compromise. This article shows a method to combine structural optimization and process assurance results to generate automatically structure- and process-optimized die casting parts using implicit geometry modeling. Therefore, evaluation criteria are developed to evaluate the current design proposal and qualitatively measure the improvement of manufacturability between two iterations. For testing the proposed method, we use a cantilever beam as an example of proof. The combined iterative method is compared to manual designed parts and a direct optimization approach and evaluated for mechanical performance and manufacturability. The combination of topology optimization (TO) and process assurance (PA) results is automated and shows a significant enhancement to the manual reconstruction of the design proposals. Further, the improvement of manufacturability is better or equivalent to previous work in the field while using less computational effort, which emphasizes the need for suitable metamodels to significantly reduce the effort for process assurance and enable much shorter iteration times.

show abstract

Optimization of solidification in die casting using numerical simulations and machine learning

Cited by 30 publications

References 34 publications

Model Selection and Evaluation for Machine Learning: Deep Learning in Materials Processing

Model Selection and Evaluation for Machine Learning: Deep Learning in Materials Processing

A Review of Application of Machine Learning in Design, Synthesis, and Characterization of Metal Matrix Composites: Current Status and Emerging Applications

Combining Structural Optimization and Process Assurance in Implicit Modelling for Casting Parts

Contact Info

Product

Resources

About