Search Results

In this paper a rule-based energy management for parallel hybrid electric vehicles (HEVs) is presented, which is based on the principles describing the optimal control behavior. Therefore we first show the general relations that can be used to describe the optimal limit of electric driving as well as the optimal torque split among the two propulsion systems. Subsequently these relations are employed to derive maps, which represent the optimal behavior depending on several input parameters. These maps are then used as inputs for the rules in the proposed energy management. This not only makes it possible to automatically calibrate the rule-based controller but also gives the optimal control in every driving situation. Given it is not fuel-efficient to turn the internal combustion engine (ICE) on or off for short intervals, it is further shown how this approach allows to adjust the established limit for electric driving by additional rules.

In order to achieve high customer satisfaction and to avoid high warranty costs caused by component failures of the power-train of hybrid electric vehicles (HEV), car manufacturers have to optimize the dimensioning of these elements. Hence, it is obligatory for them to gain knowledge about the different types of vehicle usage being predominant all over the world. Therefore, in this paper we present a Data Mining system that employs a Random Forest (RF) based dissimilarity measure in the dimensionality reduction technique t-Distributed Stochastic Neighbor Embedding (t-SNE) to automatically identify and visualize different types of vehicle usage by applying these methods to aggregated logged on-board data, i.e., load spectrum data. This kind of data is calculated and recorded directly on the control units of the vehicles and consists of aggregated numerical data, like the histogram of the velocity signal or the traveled distance of a vehicle.