Siemens Aktiengesellschaft

Symeo Gmbh

Leif Wiebking

Holger Hackstein

Amit Chakraborty

Chao Yuan

Martin Vossiek

Patric Heide

Martin Nalezinski

A method for monitoring a condition of a system or process includes acquiring sensor data from a plurality of sensors disposed within the system (Sand S). The acquired sensor data is streamed in real-time to a computer system (Sand S). A discriminative framework is applied to the streaming sensor data using the computer system (Sand S). The discriminative framework provides a probability value representing a probability that the sensor data is indicative of an anomaly within the system. The discriminative framework is an integration of a Kalman filter with a logistical function (S).

Discriminative hidden kalman filters for classification of streaming sensor data in condition monitoring

A thermal power plant, in particular to a steam-electric power plant or a combined cycle power plant (CCPP), and a method for operating a thermal power plant is adapted to accelerate, or to technically and/or economically optimize the start-up of the thermal power plant, in particular to accelerate/optimize a cold-start phase of the thermal power station. The thermal power plant has an auxiliary energy store integrated into the power plant. The store, during the start-up of the thermal power plant, delivers energy for heating/pre-heating components and/or media of the thermal power plant, or supplies an electrical power distribution network.

Optimization of cold starts in thermal power stations, in particular in steam-electric power plants or in combined cycle power plants (CCPPS)

A generalized pattern recognition is used to identify faults in machine condition monitoring. Pattern clusters are identified in operating data. A classifier is trained using the pattern clusters in addition to annotated training data. The operating data is also used to cluster the signals in the operating data into signal clusters. Monitored data samples are then classified by evaluating confidence vectors that include substitutions of signals contained in the training data by signals in the same signal clusters as the signals contained in the training data.

Generalized pattern recognition for fault diagnosis in machine condition monitoring

Separation determination systems for determining the separation between a base station and a transponder, whereby the base station includes an oscillating signal source, for generating a signal and a transmission device for broadcasting the signal. The transponder includes a receiving device, for receiving the signal from the base station, an oscillator, for generating a signal which is phase-coherent therewith and a transmission device for broadcasting the phase-coherent signal. The base station furthermore includes a receiver device, for receiving the phase-coherent signal from the transponder and a separation determination device for determining the distance between base station and transponder. The system and components may be improved whereby the oscillator in the transponder is energized with the received signal in order to generate a quasi-phase-coherent signal.

Growing community of inventors

Karlsruhe, Germany

Leif Wiebking