Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Machine learning based reverse modelling approach for rapid tool shape optimization in die-sinking μEDM

Surleraux, Anthony, Lepert, Romain, Pernot, Jean-Philippe, Kerfriden, Pierre ORCID: https://orcid.org/0000-0002-7749-3996 and Bigot, Samuel ORCID: https://orcid.org/0000-0002-0789-4727 2020. Machine learning based reverse modelling approach for rapid tool shape optimization in die-sinking μEDM. Journal of Computing and Information Science in Engineering 23 (3) , 031002. 10.1115/1.4045956
Item availability restricted.

[thumbnail of Bigot S -MachineLearningBasedToolShapeOptimization.pdf] PDF - Accepted Post-Print Version
Restricted to Repository staff only

Download (846kB)

Abstract

This paper focuses on efficient computational optimization algorithms for the generation of µEDM tool shapes. In a previous paper, the authors presented a reliable reverse modelling approach to perform such tasks, based on a crater-by-crater simulation model and an outer optimization loop. 2D results were obtained, but 3D tool shapes proved difficult to generate due to the high numerical cost of the simulation strategy. In this paper, a new reduced modelling optimization framework is proposed, whereby the computa-tional optimizer is replaced by an inexpensive surrogate that is trained by examples. More precisely, an Artificial Neural Network (ANN) is trained using a small number of full reverse simulations and subsequently used to directly generate optimal tool shapes, given the geometry of the desired workpiece cavity. In order to train the ANN efficiently, a method of data augmentation is developed, whereby multiple features from fully simulated EDM cavities are used as separate instances. The performances of two ANN are evalu-ated, one trained without modification of process parameters (gap size and crater shape), the second trained with a range of process parameter instances. It is shown that in both cases, the ANN can produce unseen tool shape geometries with less than 6% deviation compared to the full computational optimization process, and at virtually no cost. Our results demonstrate that optimized tool shapes can be generated almost instantaneously, opening the door to the rapid virtual design and manufacturability assessment of µEDM die sinking operations.

Item Type: Article
Date Type: Published Online
Status: Published
Schools: Engineering
Publisher: American Society of Mechanical Engineers (ASME)
ISSN: 1530-9827
Date of First Compliant Deposit: 19 November 2019
Date of Acceptance: 17 November 2019
Last Modified: 19 Nov 2023 15:31
URI: https://orca.cardiff.ac.uk/id/eprint/126963

Citation Data

Cited 8 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics