Identifizierung von Range Extender Fahrten anhand realer Bewegungsprofile durch künstliche neuronale Netze

Alternative drives become more important in our society continuously. Due to the target change of mobility from conventional to emission-free cars based on renewable energies, existing synthetic driving cycles are extended to determine the fuel consumption of hybrid vehicles. In reality the fuel consumption and the green gas emission of for example a battery electric vehicle with range extender depend on the operational state of the range extender. In this paper a method based on artificial neural networks is provided for the detection of the operational state of a range extender. The database for the training of the neural network contain measurements of the velocity of the car and the current of the traction battery.