Electric Machine Co-Optimization: System Design Process Using Bayesian Optimization and Nonlinear Model Predictive Control

Abstract

Electric powertrains are becoming increasingly prevalent in various mobile propulsion applications, not only due to legislation’s for lower CO2 emissions and local pollution, but also due to growing sustainable consciousness. However, conceptualizing those systems, consisting of component and controller design processes, is a complex task. The complexity itself arises from the amount of requirements for design objectives and use-cases, which can be met inside a multidimensional parameter space. Additionally, system design and evaluation are inherently tied to simultaneous component and system control strategy optimization. In this context, the paper presents a fully automated active machine learning methodology applied for a combined optimization of electric machine and system controller design, evaluating system performance, durability, and energy consumption. During this iterative approach an offline optimization of a permanent magnet synchronous machine takes place, constrained from a nonlinear model predictive control in a model-in-the-loop system environment. The active learning is covered by a Bayesian optimization algorithm with a Gaussian process regression to determine the next observable design parameters. To demonstrate the feasibility of this novel methodology, a thermal subsystem from an electrified state-of-theart powertrain has been used and further optimized regarding PMSM scaling and final gear ratio. Different real-world drive scenarios from highway to city were taken into account to cover typical sport utility vehicle use-cases. It could be shown that the electric machine losses of the optimized system are reduced by up to 32.8%, which equals a consumption of −0.42 kWh/100km compared to the reference vehicle. Due to slightly worse operating conditions of the inverter the whole system consumption has been minimized by −0.33 kWh/100km . Three parameter studies with fixed iteration count have been executed to find the optimal machine diameter to be increased by 25% and the length slightly reduced by 16%.

Keywords: Model Predictive Thermal Control, Thermal Field Weakening, Powertrain Right Sizing, Electric Machine Design, Bayesian Optimization