Abstract

This paper focuses on efficient computational optimization algorithms for the generation of micro electro discharge machining (µEDM) tool shapes. In a previous paper, the authors presented a reliable reverse modeling approach to perform such tasks based on a crater-by-crater simulation model and an outer optimization loop. Two-dimensional 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 modeling optimization framework is proposed, whereby the computational 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 evaluated, one trained without modification of process parameters (gap size and crater shape) and 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.

References

References
1.
Islam
,
N.
, and
Miyazaki
,
K.
,
2009
, “
Nanotechnology Innovation System: Understanding Hidden Dynamics of Nanoscience Fusion Trajectories
,”
Technol. Forecast. Soc. Change
,
76
(
1
), pp.
128
140
. 10.1016/j.techfore.2008.03.021
2.
Maropoulos
,
P. G.
,
2003
, “
Digital Enterprise Technology-Defining Perspectives and Research Priorities
,”
Int. J. Comput. Integr. Manuf.
,
16
(
7–8
), pp.
467
478
. 10.1080/0951192031000115787
3.
Shao
,
B.
, and
Rajurkar
,
K. P.
,
2015
, “
Modelling of the Crater Formation in Micro-EDM
,”
Procedia CIRP
,
33
, pp.
376
381
. 10.1016/j.procir.2015.06.085
4.
Kalajahi
,
M. H.
,
Ahmadi
,
S. R.
, and
Oliaei
,
S. N. B.
,
2013
, “
Experimental and Finite Element Analysis of EDM Process and Investigation of Material Removal Rate by Response Surface Methodology
,”
Int. J. Adv. Manuf. Technol.
,
69
(
1–4
), pp.
687
704
. 10.1007/s00170-013-5059-x
5.
Tan
,
P. C.
, and
Yeo
,
S. H.
,
2008
, “
Modelling of Overlapping Craters in Micro-Electrical Discharge Machining
,”
J. Phys. D: Appl. Phys.
,
41
(
20
), pp.
1
12
. https://iopscience.iop.org/article/10.1088/0022-3727/41/20/205302/meta
6.
Santos
,
P.
,
Teixidor
,
D.
,
Maudes
,
J.
, and
Ciurana
,
J.
,
2014
, “
Modelling Laser Milling of Microcavities for the Manufacturing of DES With Ensembles
,”
J. Appl. Math.
,
2014
, pp.
1
15
. https://doi.org/10.1155/2014/439091
7.
Kunieda
,
M.
,
Kanekob
,
Y.
, and
Natsub
,
W.
,
2012
, “
Reverse Simulation of Sinking EDM Applicable to Large Curvatures
,”
Precis. Eng.
,
36
(
2
), pp.
238
243
. 10.1016/j.precisioneng.2011.10.003
8.
Gilbert
,
D.
,
Stoesslein
,
M.
,
Axinte
,
D.
,
Butler-Smith
,
P.
, and
Kell
,
J.
,
2014
, “
A Time Based Method for Predicting the Workpiece Surface Micro-Topography Under Pulsed Laser Ablation
,”
J. Mater. Process. Technol.
,
214
(
12
), pp.
3077
3088
. 10.1016/j.jmatprotec.2014.07.008
9.
Claus
,
S.
,
Bigot
,
S.
, and
Kerfriden
,
P.
,
2018
, “
CutFEM Method for Stefan–Signorini Problems With Application in Pulsed Laser Ablation
,”
SIAM J. Sci. Comput.
,
40
(
5
), pp.
B1444
B1469
. 10.1137/18M1185697
10.
Otto
,
A.
, and
Schmidt
,
M.
,
2010
, “
Towards a Universal Numerical Simulation Model for Laser Material Processing
,”
Phys. Procedia
,
5
(
Part A
), pp.
35
46
. 10.1016/j.phpro.2010.08.120
11.
Kerfriden
,
P.
,
Passieux
,
J. C.
, and
Bordas
,
S. P. A.
,
2011
, “
Local/Global Model Order Reduction Strategy for the Simulation of Quasi-Brittle Fracture
,”
Int. J. Numer. Methods Eng.
,
89
(
2
), pp.
154
179
. 10.1002/nme.3234
12.
Ghanem
,
R.
, and
Spanos
,
P.
,
1991
,
Stochastic Finite Elements: A Spectral Approach
,
Springer Verlag
,
New York
.
13.
Rasmussen
,
C. E.
, and
Williams
,
C. K. I.
,
2006
,
Gaussian Processes for Machine Learning
,
The MIT Press
,
Boston, MA
.
14.
Chinesta
,
F.
,
Leygue
,
A.
,
Bordeu
,
F.
,
Aguado
,
J. V.
,
Cueto
,
E.
,
Gonzalez
,
D.
,
Alfaro
,
I.
,
Ammar
,
A.
, and
Huerta
,
A.
,
2013
, “
PGD-Based Computational Vademecum for Efficient Design
,”
Arch. Comput. Meth. Eng.
,
20
(
1
), pp.
31
59
. 10.1007/s11831-013-9080-x
15.
Pham
,
D.
,
Ivanov
,
A.
,
Bigot
,
S.
,
Popov
K.
, and
Dimov
,
S.
,
2007
, “
A Study of Micro-Electro Discharge Machining Electrode Wear
,”
Proc. Inst. Mech. Eng. Part C: J. Mech. Eng. Sci.
,
221
(
5
), pp.
605
612
. 10.1243/0954406JMES413
16.
Liang
,
W.
,
Tong
,
H.
,
Li
,
Y.
, and
Li
,
B.
,
2019
, “
Tool Electrode Wear Compensation in Block Divided EDM Process for Improving Accuracy of Diffuser Shaped Film Cooling Holes
,”
Int. J. Adv. Manuf. Technol.
,
103
(
5–8
), pp.
1759
1767
. 10.1007/s00170-019-03591-8
17.
Pham
,
D. T.
,
Dimov
,
S. S.
,
Bigot
,
S.
,
Ivanov
,
A.
, and
Popov
,
K.
,
2004
, “
MicroEDM—Recent Developments and Research Issues
,”
J. Mater. Process. Technol.
,
149
(
1–3
), pp.
50
57
. 10.1016/j.jmatprotec.2004.02.008
18.
Bleys
,
P.
,
Kruth
,
J. P.
,
Lauwers
,
B.
,
Zryd
,
A.
,
Delpretti
,
R.
, and
Tricarico
,
C.
,
2002
, “
Real Time Tool Wear Compensation in Milling EDM
,”
CIRP Ann.
,
51
(
1
), pp.
157
160
. 10.1016/S0007-8506(07)61489-9
19.
Bissacco
,
G.
,
Hansen
,
H. N.
,
Tristo
,
G.
, and
Valentinčič
,
J.
,
2011
, “
Feasibility of Wear Compensation in Micro EDM Milling Based on Discharge Counting and Discharge Population Characterization
,”
CIRP Ann.
,
60
(
1
), pp.
231
234
. 10.1016/j.cirp.2011.03.064
20.
Yu
,
Z.
,
Masuzawa
,
T.
, and
Fujino
,
M.
,
1998
, “
3D Micro-EDM With Simple Shape Electrode
,”
Int. J. Electr. Mach.
,
3
, pp.
7
12
.
21.
Surleraux
,
A.
,
Pernot
,
J.
, and
Bigot
,
S.
,
2016
, “
A Comparative Study Between NURBS Surfaces and Voxels to Simulate the Wear Phenomenon in Micro-EDM
,”
Comput. Aided Des. Appl.
,
13
(
6
), pp.
792
798
. 10.1080/16864360.2016.1168222
22.
Surleraux
,
A.
,
Lepert
,
R.
,
Pernot
,
J.-P.
, and
Bigot
,
S.
,
2015
, “
Computer-Aided Micro-EDM Die-Sinking Tool Design Optimization
,”
J. Innov. Impact
,
8
(
2
), pp.
552
571
.
23.
Bigot
,
S.
,
Pernot
,
J.
,
Surleraux
,
A.
, and
Elkaseer
,
A.
,
2013
, “
Micro-EDM Numerical Simulation and Experimental Validation
,”
Proceedings of the 10th International Conference on Multi-Material Micro Manufacture
,
San Sebastian, Spain
,
Oct. 8–10
, pp.
55
58
.
24.
Kudryavtsev
,
L. D.
, and
Samarin
,
M. K.
,
2011
, “
Lagrange Interpolation Formula
,” http://www.encyclopediaofmath.org/index.php?title=Lagrange_interpolation_formula&oldid=17497, Accessed 6 April, 2019.
25.
Heaton
,
J.
,
2013
,
Artificial Intelligence for Humans, Volume 1: Fundamental Algorithms
,
CreateSpace Independent Publishing Platform
.
26.
Cassandra
,
A.
,
Littman
,
M. L.
, and
Zhang
,
N. L.
,
1997
, “
Incremental Pruning: A Simple, Fast, Exact Method for Partially Observable Markov Decision Processes
,”
Proceedings of the Thirteenth Annual Conference on Uncertainty in Artificial Intelligence (UAI-97)
,
Providence, RI
,
Aug. 1–3
, pp.
54
61
.
27.
Heaton
,
J.
,
2011
,
Introduction to the Math of Neural Networks
,
Heaton Research Inc
.
You do not currently have access to this content.