Hardware Supported Data-Driven Modeling for ECU Function Development 2020-01-1366
The powertrain module is being introduced to embedded System on Chips (SoCs) designed to increase available computational power. These high performance SoCs have the potential to enhance the computational power along with providing on-board resources to support unexpected feature growth and on-demand customer requirements.
This project will investigate the Radial Basis Function (RBF) using the Gaussian Processing Regression algorithm, the ASCMO tool and the hardware accelerator Advanced Modeling Unit (AMU) being introduced by Infineon AURIX 2nd Generation.
ETAS ASCMO tool is one of the solutions for data-based modeling and model-based calibration. It enables users to accurately model, analyze, and optimize the behavior of complex systems with few measurements and advanced algorithms. Both steady state and transient system behaviors can be captured.
The Advanced Modeling Unit (AMU) computation engine is a floating-point unit designed to speed-up performance critical applications by off-loading the computation from CPU.
The paper will share insight of addressable applications in automotive with focus on powertrain by utilizing the ASCMO tool to provide the RBF model for the microcontroller integrated AMU HW feature. Moreover, we will show the tool and HW performance. Additionally we will lay down the path to utilize AMU within the SW environment.
Chinh Nguyen, Tobias Gutjahr, Adam Banker, Dona Burkard, Klaus Scheibert, Atilla Bulmus
Ford Motor Company, ETAS Inc., Infineon Technologies AG, Infineon Technologies North America Corp.