Abstract: A method includes receiving an input signal containing information associated with a rolling element bearing and/or a piece of equipment containing the rolling element bearing. The method also includes decomposing the input signal into a frequency-domain signal and determining at least one family of frequencies corresponding to at least one failure mode of the rolling element bearing. The method further includes generating a reconstructed input signal using the at least one family of frequencies and the frequency-domain signal. In addition, the method includes determining, using the reconstructed input signal, an indicator identifying an overall health of the rolling element bearing. The indicator could be determined using a baseline signal associated with either (i) normal operation of the rolling element bearing and/or the piece of equipment or (ii) defective operation of the rolling element bearing and/or the piece of equipment (where a severity of the defective operation will increase over time).

Abstract: An improved fault detection system and method is provided. The fault detection system and method combines the use of discrimination and representation based feature extraction to reliably detect symptoms of faults in turbine engines. Specifically, the fault detection system and method uses a kernel-based Maximum Representation Discrimination Features (MRDF) technique to detect symptoms of fault in turbine engines. The kernel-based MRDF system and method combines the use of discriminatory features and representation features in historical sensor data to facilitate feature extraction and classification of new sensor data as indicative fault in the turbine engine. Furthermore, the kernel-based MRDF technique facilitates the uncovering of nonlinear features in the sensor data, thus improving the reliability of the fault detection.

Abstract: A system and method for fault detection is provided. The fault detection system provides the ability to detect symptoms of fault in turbine engines and other mechanical systems that have nonlinear relationships. The fault detection system uses a neural network to perform a data representation and feature extraction where the extracted features are analogous to principal components derived in a principal component analysis. This neural network data representation analysis can then be used to determine the likelihood of a fault in the system.

Abstract: A method includes receiving an input signal containing information associated with a rolling element bearing and/or a piece of equipment containing the rolling element bearing. The method also includes decomposing the input signal into a frequency-domain signal and determining at least one family of frequencies corresponding to at least one failure mode of the rolling element bearing. The method further includes generating a reconstructed input signal using the at least one family of frequencies and the frequency-domain signal. In addition, the method includes determining, using the reconstructed input signal, an indicator identifying an overall health of the rolling element bearing. The indicator could be determined using a baseline signal associated with either (i) normal operation of the rolling element bearing and/or the piece of equipment or (ii) defective operation of the rolling element bearing and/or the piece of equipment (where a severity of the defective operation will increase over time).

Abstract: A system and method for fault detection is provided. The fault detection system provides the ability to detect symptoms of fault in turbine engines and other mechanical systems that have nonlinear relationships between two or more variables. The fault detection system uses a neural network to perform feature extraction from data for representation of faulty or normal conditions. The values of extracted features, referred to herein as scores, are then used to determine the likelihood of fault in the system. Specifically, the lower order scores, referred to herein as “approximate null space” scores can be classified into one or more clusters, where some clusters represent types of faults in the turbine engine. Classification based on the approximate null space scores provides the ability to classify faulty or nominal conditions that could not be reliably classified using higher order scores.