Rohde and Schwarz Gmbh & Co. Kg

Bayerische Motoren Werke Aktiengesellschaft

Andreas Werner

Robert Griessbach

Sven Barthel

Steffen Lutz

Robert Wagner

Rolf Kruse

A method for providing a training data set used for training a signal classification neural network is provided. The method includes generating at least one first virtual waveform primitive comprising a predetermined signal level and at least one second virtual waveform primitive comprising a signal edge. The training data set is formed and comprises a predetermined number of generated virtual waveform primitives including first virtual waveform primitives and second virtual waveform primitives. Each virtual waveform primitive comprises a sequence of time and amplitude discrete values. The training data set is used for training the signal classification neural network.

Method and apparatus providing a trained signal classification neural network

The present disclosure relates to a method of analyzing a pulse modulated signal, wherein the method comprises: receiving a pulse modulated signal; determining a dynamic threshold level based on a period of the pulse modulated signal and the pulse modulated signal; and demodulating the pulse modulated signal by the dynamic threshold level. Moreover, a signal analysis instrument for analyzing a pulse modulated signal is described.

Method and signal analysis instrument for analyzing a pulse modulated signal

In a multi-cylinder internal combustion engine for vehicles, having a plurality of air ducts leading to the cylinders and an associated engine control device situated in a housing, the air ducts are combined into a single unit, on the exterior of which the engine control device housing is situated on its lower part which forms the underside, and the lower part of the engine control device housing simultaneously forms a part of the air ducts.

Growing community of inventors

Munich, Germany

Andreas Werner