Abstract

Inverse uncertainty quantification commonly uses the well established Bayesian framework. Recently, alternative interval methodologies have been introduced. However, in their current state of the art implementation, both techniques suffer from a large and usually unpredictable computational effort. Thus, both techniques are not applicable in a real-time context. To achieve a low-cost, real-time solution to this inverse problem, we introduce a deep-learning framework consisting of unsupervised auto-encoders and a shallow neural network. This framework is trained by means of a numerically generated dataset that captures typical relations between the model parameters and selected measured system responses. The performance and efficacy of the technique is illustrated using two distinct case studies. The first case involves the DLR AIRMOD, a benchmark case that has served as reference case for the inverse uncertainty quantification problem. The results demonstrate that the achieved accuracy is on par with the existing interval method found in literature, while requiring only a fraction of its computational resources. The second case study examines a resistance pressure welding process, which is known to require extremely fast monitoring and control due to the high process throughput. Based on the proposed method, and with only a limited selection of simulated responses of the process, it is possible to identify the interval uncertainty of the crucial parameters of the process. The computational cost in this case makes it possible for an inverse uncertainty quantification in a real-time setting.

References

1.
Stefanou
,
G.
,
2009
, “
The Stochastic Finite Element Method: Past, Present and Future
,”
Comput. Methods Appl. Mech. Eng.
,
198
(
9–12
), pp.
1031
1051
.10.1016/j.cma.2008.11.007
2.
Faes
,
M.
, and
Moens
,
D.
,
2020
, “
Recent Trends in the Modeling and Quantification of Non-Probabilistic Uncertainty
,”
Arch. Comput. Methods Eng.
,
27
(
3
), pp.
633
671
.10.1007/s11831-019-09327-x
3.
Faes
,
M. G.
,
Daub
,
M.
,
Marelli
,
S.
,
Patelli
,
E.
, and
Beer
,
M.
,
2021
, “
Engineering Analysis With Probability Boxes: A Review on Computational Methods
,”
Struct. Saf.
,
93
, p.
102092
.10.1016/j.strusafe.2021.102092
4.
Faes
,
M.
,
Broggi
,
M.
,
Patelli
,
E.
,
Govers
,
Y.
,
Mottershead
,
J.
,
Beer
,
M.
, and
Moens
,
D.
,
2019
, “
A Multivariate Interval Approach for Inverse Uncertainty Quantification With Limited Experimental Data
,”
Mech. Syst. Signal Process.
,
118
, pp.
534
548
.10.1016/j.ymssp.2018.08.050
5.
Broggi
,
M.
,
Faes
,
M.
,
Patelli
,
E.
,
Govers
,
Y.
,
Moens
,
D.
, and
Beer
,
M.
,
2018
, “
Comparison of Bayesian and Interval Uncertainty Quantification: Application to the AIRMOD Test Structure
,”
2017 IEEE Symposium Series on Computational Intelligence,
(
SSCI
), Honolulu, HI, Nov. 27–Dec. 1, pp.
1
8
.10.1109/SSCI.2017.8280882
6.
Beer
,
M.
,
Ferson
,
S.
, and
Kreinovich
,
V.
,
2013
, “
Imprecise Probabilities in Engineering Analyses
,”
Mech. Syst. Signal Process.
,
37
(
1–2
), pp.
4
29
.10.1016/j.ymssp.2013.01.024
7.
Bi
,
S.
,
He
,
K.
,
Zhao
,
Y.
,
Moens
,
D.
,
Beer
,
M.
, and
Zhang
,
J.
,
2022
, “
Towards the Nasa uq Challenge 2019: Systematically Forward and Inverse Approaches for Uncertainty Propagation and Quantification
,”
Mech. Syst. Signal Process.
,
165
, p.
108387
.10.1016/j.ymssp.2021.108387
8.
Zhao
,
Y.
,
Yang
,
J.
,
Faes
,
M. G.
,
Bi
,
S.
, and
Wang
,
Y.
,
2022
, “
The Sub-Interval Similarity: A General Uncertainty Quantification Metric for Both Stochastic and Interval Model Updating
,”
Mech. Syst. Signal Process.
,
178
, p.
109319
.10.1016/j.ymssp.2022.109319
9.
Sudret
,
B.
,
2008
, “
Global Sensitivity Analysis Using Polynomial Chaos Expansions
,”
Reliab. Eng. Syst. Safety
,
93
(
7
), pp.
964
979
.10.1016/j.ress.2007.04.002
10.
Bach
,
F.
,
2017
, “
Breaking the Curse of Dimensionality With Convex Neural Networks
,”
J. Mach. Learn. Res.
,
18
(
April
), pp.
1
53
.10.48550/arXiv.1412.8690
11.
Mak
,
K. K.
,
Kounseok
,
L.
, and
Cheolyong
,
P.
,
2019
, “
Applications of Machine Learning in Addiction Studies: A Systematic Review
,”
Psychiatry Res.
,
275
, pp.
53
60
.10.1016/j.psychres.2019.03.001
12.
Stetco
,
A.
,
Nenadic
,
G.
,
Flynn
,
D.
,
Barnes
,
M.
,
Zhao
,
X.
,
Dinmohammadi
,
F.
,
Keane
,
J.
, and
Robu
,
V.
,
2019
, “
Machine Learning Methods for Wind Turbine Condition Monitoring: A Review
,”
Renewable Energy
,
133
, pp.
620
635
.10.1016/j.renene.2018.10.047
13.
Olshausen
,
B. A.
, and
Field
,
D. J.
,
1997
, “
Sparse Coding With an Overcomplete Basis Set: A Strategy Employed by v1?
,”
Vision Res.
,
37
(
23
), pp.
3311
3325
.10.1016/S0042-6989(97)00169-7
14.
Namazi
,
M.
,
Karimi-Jafari
,
M. H.
,
Qassemi
,
F.
, and
Ghasemi
,
J. B.
,
2023
, “
Autoencoders in Generative Modeling, Feature Extraction, Regression, and Classification
,”
Machine Learning and Pattern Recognition Methods in Chemistry From Multivariate and Data Driven Modeling
,
Elsevier
, Amsterdam, The Netherlands, pp.
119
136
.
15.
Faes
,
M.
,
Cerneels
,
J.
,
Vandepitte
,
D.
, and
Moens
,
D.
,
2017
, “
Identification and Quantification of Multivariate Interval Uncertainty in Finite Element Models
,”
Comput. Methods Appl. Mech. Eng.
,
315
, pp.
896
920
.10.1016/j.cma.2016.11.023
16.
Bogaerts
,
L.
,
Faes
,
M.
, and
Moens
,
D.
,
2019
, “
A Fast Inverse Approach for the Quantification of Settheoretical Uncertainty
,” IEEE Symposium Series on Computational Intelligence (
SSCI
), Xiamen, China, Dec. 6–9, pp.
768
775
.10.1109/SSCI44817.2019.9002995
17.
Govers
,
Y.
,
Haddad Khodaparast
,
H.
,
Link
,
M.
, and
Mottershead
,
J. E.
,
2014
, “
Stochastic Model Updating of the DLR AIRMOD Structure
,”
Second International Conference on Vulnerability and Risk Analysis and Management (ICVRAM) and the Sixth International Symposium on Uncertainty Modelling and Analysis (ISUMA)
, Liverpool, UK, July 13–16, pp.
475
484
.10.1061/9780784413609.049
18.
Callens
,
R. R.
,
Faes
,
M. G.
, and
Moens
,
D.
,
2021
, “
Local Explicit Interval Fields for Non-Stationary Uncertainty Modelling in Finite Element Models
,”
Comput. Methods Appl. Mech. Eng.
,
379
, p.
113735
.10.1016/j.cma.2021.113735
19.
Dang
,
C.
,
Wei
,
P.
,
Faes
,
M. G.
,
Valdebenito
,
M. A.
, and
Beer
,
M.
,
2022
, “
Interval Uncertainty Propagation by a Parallel Bayesian Global Optimization Method
,”
Appl. Math. Modell.
,
108
, pp.
220
235
.10.1016/j.apm.2022.03.031
20.
Hanss
,
M.
,
2002
, “
The Transformation Method for the Simulation and Analysis of Systems With Uncertain Parameters
,”
Fuzzy Sets Systems
,
130
(
3
), pp.
277
289
.10.1016/S0165-0114(02)00045-3
21.
Faes
,
M.
, and
Moens
,
D.
,
2019
,
Recent Trends in the Modeling and Quantification of Non-Probabilistic Uncertainty No. 0123456789
,
Springer
,
Netherlands
.
22.
Fernández-Martínez
,
J. L.
, and
Fernández-Muñiz
,
Z.
,
2020
, “
The Curse of Dimensionality in Inverse Problems
,”
J. Comput. Appl. Math.
,
369
, p.
112571
.10.1016/j.cam.2019.112571
23.
Hinton
,
G. E.
, and
Salakhutdinov
,
R.
,
2006
, “
Reducing the Dimensionality of Data With Neural Networks
,”
Science
,
313
(
5786
), pp.
504
507
.10.1126/science.1127647
24.
Moller
,
M. F.
,
1993
, “
Efficient Training of Feed-Forward Neural Networks
,” Ph.D. thesis,
Aarhus University
, Aarhus, Denmark.
25.
van der Maaten
,
L.
,
Postma
,
E.
, and
van den Herik
,
J.
,
2009
, “
Dimensionality Reduction: A Comparative Review
,”
J. Mach. Learn. Res.
,
10
, pp.
1
35
.https://lvdmaaten.github.io/publications/papers/TR_Dimensionality_Reduction_Review_2009.pdf
26.
Strange
,
H.
, and
Zwiggelaar
,
R.
,
2014
,
Open Problems in Spectral Dimensionality Reduction
,
Springer, Heidelberg, Germany
.
27.
Oparaji
,
U.
,
Sheu
,
R. J.
,
Bankhead
,
M.
,
Austin
,
J.
, and
Patelli
,
E.
,
2017
, “
Robust Artificial Neural Network for Reliability and Sensitivity Analyses of Complex Non-Linear Systems
,”
Neural Networks
,
96
, pp.
80
90
.10.1016/j.neunet.2017.09.003
28.
Sadeghi
,
J.
,
de Angelis
,
M.
, and
Patelli
,
E.
,
2019
, “
Efficient Training of Deep Neural Networks for Dealing With Incertitude and Big Training Data
,”
Neural Networks
,
118
, pp.
338
351
.10.1016/j.neunet.2019.07.005
29.
Goodfellow
,
I.
,
Bengio
,
Y.
, and
Courville
,
A.
,
2016
,
Deep Learning
,
MIT Press
,
Cambridge, MA
.
30.
Nasir
,
V.
, and
Sassani
,
F.
,
2021
, “
A Review on Deep Learning in Machining and Tool Monitoring: Methods, Opportunities, and Challenges
,”
Int. J. Adv. Manuf. Technol.
,
115
(
9–10
), pp.
2683
2709
.10.1007/s00170-021-07325-7
31.
Alzubaidi
,
L.
,
Zhang
,
J.
,
Humaidi
,
A. J.
,
Al-Dujaili
,
A.
,
Duan
,
Y.
,
Al-Shamma
,
O.
,
Santamaría
,
J.
,
Fadhel
,
M. A.
, and
Al-Amidie
,
M.
, et al.,
2021
, “
Review of Deep Learning: Concepts, Cnn Architectures, Challenges, Applications, Future Directions
,”
J. Big Data
,
8
(
1
), p. 53.10.1186/s40537-021-00444-8
32.
Sarker
,
I. H.
,
2021
, “
Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions
,”
SN Comput. Sci.
,
2
(
6
), p.
420
.10.1007/s42979-021-00815-1
33.
Mehrish
,
A.
,
Majumder
,
N.
,
Bharadwaj
,
R.
,
Mihalcea
,
R.
, and
Poria
,
S.
,
2023
, “
A Review of Deep Learning Techniques for Speech Processing
,”
Inf. Fusion
,
99
, p.
101869
.10.1016/j.inffus.2023.101869
34.
Bogaerts
,
L.
,
Faes
,
M.
, and
Moens
,
D.
,
2019
, “
A Machine Learning Approach For the Inverse Quantification of Set-Theoretical Uncertainty
,”
3rd International Conference on Uncertainty Quantification in Computational Sciences and Engineering
, Crete, Greece, June 24–26, pp.
1
13
.https://files.eccomasproceedia.org/papers/uncecomp-2019/18848.pdf?mtime=20191120124822
35.
Dickinson
,
D. W.
,
Franklin
,
J. E.
, and
Stanya
,
A.
,
1980
, “
Characterization of Spot Welding Behavior by Dynamic Electrical Parameter Monitoring
,”
Weld. J. (Miami, Fla)
,
59
(
6
), pp.
170
176
.https://www.semanticscholar.org/paper/Characterization-of-Spot-Welding-Behaviorby-Dickinson-Franklin/efd7b0036c987f1384222725785a396cafd931cb
36.
Hao
,
M.
,
Osman
,
K. A.
,
Boomer
,
D. R.
, and
Newton
,
C. J.
,
1996
, “
Developments in Characterization of Resistance Spot Welding of Aluminum
,”
Weld. J. (Miami, Fla)
,
75
(
1
), p.
1
.https://www.osti.gov/biblio/197651
37.
Hamedi
,
M.
, and
Atashparva
,
M.
,
2017
, “
A Review of Electrical Contact Resistance Modeling in Resistance Spot Welding
,”
Weld. World
,
61
(
2
), pp.
269
290
.10.1007/s40194-016-0419-4
38.
Brunton
,
S. L.
, and
Kutz
,
J. N.
,
2019
,
Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control
,
Cambridge University Press
, Cambridge, UK.
39.
Wan
,
X.
,
Wang
,
Y.
,
Zhao
,
D.
,
Huang
,
Y. A.
, and
Yin
,
Z.
,
2017
, “
Weld Quality Monitoring Research in Small Scale Resistance Spot Welding by Dynamic Resistance and Neural Network
,”
Meas.: J. Int. Meas. Confederation
,
99
, pp.
120
127
.10.1016/j.measurement.2016.12.010
40.
Bogaerts
,
L.
,
Dejans
,
A.
,
Faes
,
M. G.
, and
Moens
,
D.
,
2023
, “
A Machine Learning Approach for Efficient and Robust Resistance Spot Welding Monitoring
,”
Weld. World
,
67
(
8
), pp.
1923
1935
.10.1007/s40194-023-01519-1
41.
Marelli
,
S.
, and
Sudret
,
B.
,
2014
, “
UQLab: A Framework for Uncertainty Quantification in MATLAB
,”
Vulnerability, Uncertainty, and Risk: Quantification, Mitigation, and Management
, American Society of Civil Engineers, Liverpool, UK, pp.
2554
2563
.
You do not currently have access to this content.