Search Results

Modeling thermal systems in Battery Electric Vehicles (BEVs) is crucial for enhancing energy efficiency through predictive control strategies, thereby extending vehicle range. A major obstacle in this modeling is the often limited availability of detailed system information. This research introduces a methodology using neural networks for system identification, a powerful technique capable of approximating the physical behavior of thermal systems with minimal data requirements. By employing black-box models, this approach supports the creation of optimization-based operational strategies, such as Model Predictive Control (MPC) and Reinforcement Learning-based Control (RL). The system identification process is executed using MATLAB Simulink, with virtual training data produced by validated Simulink models to establish the method's feasibility. The neural networks utilized for system identification are implemented in MATLAB code.

Prospective combustion engine applications require the highest possible energy conversion efficiencies for environmental and economic sustainability. For conventional Spark-Ignition (SI) engines, the quasi-hemispherical flame propagation combustion method can only be significantly optimized in combination with high excess air dilution or increased combustion speed. However, with increasing excess air dilution, this is difficult due to decreasing flame speeds and flammability limits. Pre-Chamber (PC) initiated jet ignition combustion systems significantly shift the flammability and flame stability limits towards higher dilution areas due to high levels of introduced turbulence and a significantly increased flame area in early combustion stages, leading to considerably increased combustion speeds and high efficiencies. By now, vehicle implementations of PC-initiated combustion systems remain niche applications, especially in combination with lean mixtures.