This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Optimization of Gaussian Process Regression Model for Characterization of In-Vehicle Wet Clutch Behavior
Technical Paper
2022-01-0222
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
The advancement of Machine-learning (ML) methods enables data-driven creation of Reduced Order Models (ROMs) for automotive components and systems. For example, Gaussian Process Regression (GPR) has emerged as a powerful tool in recent years for building a static ROM as an alternative to a conventional parametric model or a multi-dimensional look-up table. GPR provides a mathematical framework for probabilistically representing complex non-linear behavior. Today, GPR is available in various programing tools and commercial CAE packages. However, the application of GPR is system dependent and often requires careful design considerations such as selection of input features and specification of kernel functions. Hence there is a need for GPR design optimization driven by application requirements. For example, a moving window size for training must be tuned to balance performance and computational efficiency for tracking changing system behavior. In this paper, a detailed design evaluation of GPR is conducted for the characterization of an engine disconnect clutch in P2 hybrid electric vehicle. Specifically, a clutch transfer function is constructed using GPR that maps actuator pressure to clutch torque. The disconnect clutch exhibits highly non-linear behaviors with a distinct hysteresis loop. A casual application of GPR results in a misrepresentation of clutch behaviors with a risk of overfitting. This paper first describes a process to select input features based on statistical measures. Several pre-defined kernel functions and their combinations are evaluated for generalization capability and computational efficiency. A size of data from a moving window is also evaluated for its effect on training errors as well as efficiency. The optimized GPR is applied to a set of disconnect clutch engagement data obtained from a long drive sequence for enabling accurate tracking of clutch behaviors in vehicles. This paper concludes with a set of recommendations for successfully deploying powerful GPR tool for addressing real-world automotive problems.
Authors
Citation
Shui, H., Zhang, Y., Yi, E., Bichkar, A. et al., "Optimization of Gaussian Process Regression Model for Characterization of In-Vehicle Wet Clutch Behavior," SAE Technical Paper 2022-01-0222, 2022, https://doi.org/10.4271/2022-01-0222.Also In
References
- Gillespie , T. Fundamentals of Vehicle Dynamics SAE International 1992 978-1-56091-199-9
- Bai , S. , Maguire , J. , and Peng , H. Dynamic Analysis and Control System Design of Automatic Transmissions SAE International 2013 978-0-7680-7604-2
- Eriksson , L. and Nielsen , L. Modeling and Control of Engines and Drivelines John Wiley & Sons 2014 10: 9781118479995
- Shui , H. , Zhang , Y. , Yang , H. , Upadhyay , D. et al. Machine Learning Approach for Constructing Wet Clutch Torque Transfer Function SAE Technical Paper 2021-01-0712 2021 https://doi.org/10.4271/2021-01-0712
- Gardner , G. 10R80 MHT Transmission SAE Innovations in Mobility Symposium Novi, MI 2019
- Xu , X. , Liang , Y. , Jordan , M. , Tenberge , P. et al. Optimized Control of Engine Start Assisted by the Disconnect Clutch in a P2 Hybrid Automatic Transmission Journal of Mechanical Systems and Signal Processing 124 2019 313 329
- Fujii , Y. , Kapas , N. , and Tseng , J. Clutch Wet Encyclopedia of Automotive Engineering New York Wiley & Sons 2014
- Haria , H. , Fujii , Y. , Pietron , G. , Sun , A. et al. Advanced Bench Test Methodology for Generating Wet Clutch Torque Transfer Functions for Enhanced Drivability Simulations SAE Technical Paper 2019-01-2340 (JSAE 20199181) 2019 https://doi.org/10.4271/2019-01-2340
- Zhang , Y. , Chen , F. , Chen , W. , Bichkar , A. et al. Machine-Learning Approach to Behavioral Identification of Hybrid Powertrain System and Component SAE Technical Paper 2022-01-0229 2022 https://doi.org/10.4271/2022-01-0229
- Zhang , Y. , Chen , F. , Riedle , B. , Chen , W. , and Fujii , Y. 2021
- Chen , F. , Zhang , Y. , Riedle , B. , Chen , W. , and Fujii , Y. 2022
- Rasmussen , C.E. and Williams , C.K.I. Gaussian Processes for Machine Learning MIT Press 2006 026218253X
- Python https://www.python.org 2021
- Bishop , C.M. Pattern Recognition and Machine Learning Springer 2006 10: 0-387-31073-8
- Chandrashekar , G. and Sahin , F. A Survey on Feature Selection Method Computers & Electrical Engineering 40 2014 16 28