Optimization of Gaussian Process Regression Model for Characterization of In-Vehicle Wet Clutch Behaviors
2022-01-0253
03/29/2022
- Event
- Content
- The advancement of Machine-learning (ML) methodology enables a data-driven creation of Reduced Order Model (ROM) for automotive components and systems. In recent years Gaussian Process Regression (GPR) has emerged as a powerful tool for building a static ROM as an alternative to a conventional parametric method. It provides a mathematical framework for probabilistically representing complex non-linear behaviors. Today GPR is available in various programing tools and commercial CAE packages. However, its application requires a careful design consideration such as a selection of input features and a specification of kernel functions, depending on the characteristics of a target system. The GPR design optimization is also driven by application requirements. For example, a moving window size must be tuned to balance performance and computational efficiency for tracking changing system behaviors. In this paper, a detailed design evaluation of GPR is conducted for the characterization of an engine disconnect clutch in P2 hybrid vehicle. Specifically, a clutch transfer function is constructed using GPR that maps actuator pressure to clutch torque. The clutch behaviors are highly sensitive to control profiles and operating conditions. A casual application of GPR can result in a misrepresentation of clutch behaviors with a risk of overfitting. This paper first describes a process to select input features based on correlation analysis. Several kernel functions and their combinations are evaluated for generalization capability and computational efficiency. A size of data from a moving window is evaluated for its effect on training errors as well as efficiency. The optimized GPR is successfully applied to a sequence of disconnect clutch engagement data obtained from multiple drive sequences for enabling accurate tracking of clutch behaviors. This paper concludes with a set of recommendations for successfully deploying powerful GPR tool for addressing real-world automotive problems.
- Citation
- Shui, H., Zhang, Y., Yi, E., Bichkar, A. et al., "Optimization of Gaussian Process Regression Model for Characterization of In-Vehicle Wet Clutch Behaviors ," SAE Technical Paper 2022-01-0253, 2022, .