Search Results

Hybrid electric vehicles (HEV) contribute to reduce emissions from transportation. The energy management controls the powertrain components in HEVs. In addition to minimizing fuel consumption, improving air quality is a major opportunity for hybrid vehicles. Pollutant emissions can only be mapped with sufficient accuracy using dynamic models. The introduced nitrogen oxide model is created using a supervised learning approach based on recorded measurement data. This dynamic model requires input data from previous time steps to ensure sufficient model quality. Classical algorithms such as Dynamic Programming are not able to find solutions for such high-dimensional problems in reasonable computing times. A promising approach to solve the resulting problem is Deep Reinforcement Learning (Deep RL), which has recently been introduced in the field of HEV energy management.

A vital contribution for the development of an environmental friendly society is improved energy efficiency in public transport systems. Increased electrification of these systems is essential to achieve the high objectives stated. Since the operating range of an electrical vehicle is heavily influenced of the available energy, which primarily is used for propulsion and thermal passenger comfort, all heat losses in the vehicle systems must be minimized. Especially for urban buses, the unwanted heat losses through open doors while passengers are boarding, have to be controlled. These energy fluxes are due to the large temperature gradients generated between in- and outdoor conditions and to install air-walls in the door opening areas have turned out to be a promising technical solution. Based on air-wall technologies used for climate control in buildings, this paper presents an experimental investigation on the reduction of heat losses in the door opening of urban buses.

The reduction of fuel consumption as well as the rising demands of customers regarding a vehicle’s driving dynamic and the legislator’s continually rising demands are a current issue in vehicle development. Hybrid vehicles offer a possibility to rise to this challenge. Realistic driving cycles are of utmost importance for the calibration of a hybrid vehicle’s operational strategy. Deriving replacement speed cycles from extensive customer data sets seems to be an approach for solving these problems. The contribution at hand describes the derivation of replacement cycles by using stochastic models, probabilistic (weighted) drawings and a combinatorial optimisation. The novelty value is that the characteristic influences of all drivers are being considered in the generation due to the stochastic modelling.