TY - GEN
T1 - Robust fuzzy modeling and symbolic regression for establishing accurate and interpretable prediction models in supervising tribological systems
AU - Lughofer, Edwin
AU - Kronberger, Gabriel
AU - Kommenda, Michael
AU - Saminger-Platz, Susanne
AU - Promberger, Andreas
AU - Nickel, Falk
AU - Winkler, Stephan
AU - Affenzeller, Michael
N1 - Publisher Copyright:
© Copyright 2016 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.
PY - 2016
Y1 - 2016
N2 - 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 constants (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.
AB - 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 constants (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.
KW - Enhanced Regularized Learning
KW - Generalized Takagi-Sugeno Fuzzy Systems
KW - Multi-objective Accuracy/Complexity Tradeoff
KW - Robust Fuzzy Modeling
KW - Symbolic Regression
KW - Tribological Systems
UR - http://www.scopus.com/inward/record.url?scp=85006356612&partnerID=8YFLogxK
U2 - 10.5220/0006068400510063
DO - 10.5220/0006068400510063
M3 - Conference contribution
SN - 978-989-758-201-1
T3 - IJCCI 2016 - Proceedings of the 8th International Joint Conference on Computational Intelligence
SP - 51
EP - 63
BT - FCTA 2016 - 8th International Conference on Fuzzy Computation Theory and Applications
A2 - Merelo, Juan Julian
A2 - Melicio, Fernando
A2 - Cadenas, Jose M.
A2 - Dourado, Antonio
A2 - Madani, Kurosh
A2 - Ruano, Antonio
A2 - Filipe, Joaquim
PB - SciTePress
T2 - 8th International Joint Conference on Computational Intelligence, IJCCI 2016
Y2 - 9 November 2016 through 11 November 2016
ER -