Real Time Predictive and Adaptive Hybrid Powertrain Control Development via Neuroevolution

The real-time application of powertrain-based predictive energy management (PrEM) brings the prospect additional savings for hybrid powertrains. Torque split optimal control methodologies have been a focus in automotive industry and academia many years. Their modern vehicles is, however, still lagging behind. While conventional exact non-exact techniques such as Dynamic Programming Model Predictive Control demonstrated, they suffer from curse dimensionality quickly display limitations with high system complexity highly stochastic environment operation. This paper demonstrates that Neuroevolution associated drive cycle classification algorithms can infer strategies any environment, hence streamlining speeding up development process. also circumvents integration low fidelity online plant models, further avoiding prohibitive embedded computing requirements loss. to complex multi-physics applications. methodology presented here covers cycles used train validate neurocontrollers classifiers, well