Authors:
Edwin Lughofer
1
;
Gabriel Kronberger
2
;
Michael Kommenda
2
;
Susanne Saminger-Platz
1
;
Andreas Promberger
3
;
Falk Nickel
3
;
Stephan Winkler
2
and
Michael Affenzeller
2
Affiliations:
1
Johannes Kepler University Linz, Austria
;
2
School of Informatics and Communications and Media, Austria
;
3
Miba Frictec, Austria
Keyword(s):
Tribological Systems, Robust Fuzzy Modeling, Generalized Takagi-Sugeno Fuzzy Systems, Symbolic Regression, Multi-objective Accuracy/Complexity Tradeoff, Enhanced Regularized Learning.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Computer-Supported Education
;
Domain Applications and Case Studies
;
Fuzzy Systems
;
Fuzzy Systems Design, Modeling and Control
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Industrial, Financial and Medical Applications
;
Learning and Adaptive Fuzzy Systems
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
System Identification and Fault Detection
;
Theory and Methods
Abstract:
In this contribution, we discuss data-based methods for building regression
models for predicting important characteristics of tribological
systems (such as the friction coefficient), with the overall goal of
improving and partially automatizing the design and dimensioning of
tribological systems. In particular, we focus on two methods for synthesis of
interpretable and potentially non-linear regression models: (i)
robust fuzzy modeling and (ii) enhanced symbolic regression using
genetic programming, both embedding new methodological extensions.
The robust fuzzy modeling technique employs generalized
Takagi-Sugeno fuzzy systems. Its learning
engine is based on the Gen-Smart-EFS approach, which in this paper is
(i) adopted to the batch learning case and (ii) equipped with a new
enhanced regularized learning scheme for the rule consequent
parameters. Our enhanced symbolic regression method addresses (i) direct
gradient-based optimization of numeric const
ants (in a kind of memetic approach) and (ii) multi-objectivity
by adding complexity as a second optimization criterion to
avoid over-fitting and to increase transparency of the resulting
models.
The comparison of the new extensions with state-of-the-art non-linear modeling techniques based on nine different learning problems
(including targets wear, friction coefficients, temperatures and NVH) shows indeed similar errors on separate validation data, but while (i) achieving much less complex models and
(ii) allowing some insights into model structures and
components, such that they could be confirmed as very reliable by the experts working with the concrete
tribological system.
(More)