Abstract:
The invention provides a method for obtaining valid oscillating components from raw process data in a process plant. The method includes applying a decomposition technique on the raw process data to obtain oscillating components having period values. These period values may be subjected to statistical treatment or be used as such to obtain applicable period values. Then, a regularity check is performed on the applicable period values to obtain first level valid oscillating components. Noise level in a process is estimated from the time series data, which is used to remove noisy oscillating components from the first level valid oscillating components to obtain second level valid oscillating components. The invention further includes clustering the second level valid oscillating components into unique oscillating components based on a mean period distance between given oscillating components.
Abstract:
The data acquisition unit [10] obtains information and for the analysis of disturbances within the system. The analysis is carried out by a processor [20] that connects with a classifier [30] that provides spectral analysis and classifies the relevant disturbances. The generated classes are subject to further analysis [40].
Abstract:
The method involves determining forecast-data by physical or mathematical models (2.1-2.n) i.e. forecast model, under consideration of design data (1) e.g. material thickness, comprising planning data, stock data and account data. The forecast-data is updated by considering actual process data by repetition of the determination process following over a period of time of machine or system operation such that updated process information (6) is provided as operating data, maintenance data and measurement data. Results (3.1-3.n) of the models are concatenated to common information. An independent claim is also included for a device for determining forecast-data for a worn machine, components of a technical system and a technical sub-system.
Abstract:
The system has a detection module (10), which conveys process variables as measured values to a preprocessing module (20). The preprocessing module filters useless measured values from the detected measured values. A compensation unit (32) compensates the preprocessed measured values based on preset reference conditions. An evaluation unit (36) determines and evaluates a degradation index from deviations between actual parameters and target parameters. The evaluation unit automatically transfers a message to an output unit (40). An independent claim is also included for a method for monitoring condition and detecting operation deterioration and failures in a compressing and rotating machine.