Abstract: A system and method is provided for predicting deterioration in a mechanical device. The deterioration prediction system and method includes a dynamic model of the mechanical device and a state estimator to predict deterioration in a mechanical device. The dynamic model includes a plurality of evolving health states that describe the performance of the mechanical device. The dynamic model can be implemented such that several distinct factors contribute the evolution of the health states. These factors can include damage accumulation, interaction between components in the device, deviation from design conditions, and the influence of discrete events. In one embodiment, the dynamic model uses a Poisson distribution to model the rate of damage accumulation in the mechanical device.

Abstract: A system and method for combining conclusions from multiple fault detection techniques to isolate likely faults in a turbine engine is provided. The system and method provide the ability to effectively deal with multiple concurrent faults in the engine. Additionally, the embodiments of the invention provide the ability to correctly characterize multiple conclusions generated from evidence having different levels of interdependence. In one embodiment, the conclusions based on device data with high dependency are aggregated using a high dependency aggregation rule, and the resulting high-dependency sets are then further aggregated using a weak dependency rule. Finally, any conclusions based on independent evidence can be aggregated using an independent combination rule. The resulting aggregation determines which fault(s) are most likely indicated by the plurality of conclusions, taken into account the dependency of the device data used to generate the conclusions.

Abstract: Various methods, devices, systems, and computer programs are disclosed relating to the use of models to represent systems and processes (such as manufacturing and production plants). For example, a method may include generating a first model and a second model using operating data associated with a system or process. The method may also include using the first and second models to predict one or more events associated with the system or process. The one or more events are predicted by generating one or more initial event predictions using the first model and adjusting the one or more initial event predictions using the second model. The first model may represent a Principal Component Analysis (PCA) model, and the second model may represent a Fuzzy Logic model.

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.

Abstract: A system and method for detecting erosion in turbine engine blades is provided. The blade erosion detection system includes a sensor data processor and a cluster analysis mechanism. The sensor data processor receives engine sensor data, including exhaust gas temperature (EGT) data, and augments the sensor data to determine sensor data residual values and the rate of change of the sensor data residual values. The augmented sensor data is passed to the cluster analysis mechanism. The cluster analysis mechanism analyzes the augmented sensor data to determine the likelihood that compressor blade erosion has occurred. Specifically, the cluster analysis mechanism performs a 2-tuple cluster feature analysis using Gaussian density functions that provide approximations of normal and eroded blades in a turbine engine. The 2-tuple cluster feature analysis thus provides the probability that the sensor data indicates erosion has occurred in the turbine engine.

Abstract: A system and method is provided for detecting anomalies in turbine engines emanating from the main shaft and/or main shaft bearings. The anomaly detection system includes a sensor data processor and a matrix analysis mechanism. The sensor data processor receives engine sensor data, including main engine speed data during spin down, and formats the engine sensor data into an appropriate matrix. The matrix analysis mechanism receives the sensor data matrix and performs a singular value analysis on the sensor data matrix to detect potential anomalies in the turbine engine main shaft and/or bearings. The output of the matrix analysis mechanism is passed to a diagnostic system where further evaluation of the anomaly detection determination can occur.

Abstract: A method and control system is disclosed that monitors the high frequency or commonly referred to as the “noise” component of a measurement signal to detect plugging conditions in fluid flow systems monitored by DP-cell based sensors. This high frequency component has contributions from the process factors like disturbances, user actions and random effects like turbulence. A test statistic ?(t) has been developed that monitors the proportion of variance introduced by process factors and random effects. By monitoring this proportion, it is possible to detect a frozen sensor that is characterized by a dramatic reduction in the variance due to process factors over a sufficiently long detection window. The method works with measurements sampled at frequencies commonly achievable in a process environment.

Abstract: A graphical user interface (GUI) is used to quickly and easily find data patterns within a data sequence that match a target data pattern representing an event of interest. The user first specifies the target data pattern either by dragging a cursor over the target or by selecting the target from a palette of predefined trend patterns. Search criteria, such as a match threshold and amplitude and duration constraints, are then specified. A pattern recognition technique is then used to find data patterns within the data sequence that satisfy the search criteria. These matching data patterns are then presented to the user ranked by similarity, avoiding the need for the user to sift through large amounts of irrelevant data. Particular pattern recognition algorithms are also disclosed.

Abstract: A method and control system that monitors the high frequency or commonly referred to as the “noise” component of a measurement signal to detect plugging conditions in fluid flow systems monitored by DP-cell based sensors. This high frequency component has contributions from the process factors like disturbances, user actions and random effects like turbulence. A test statistic &thgr;(t) has been developed that monitors the proportion of variance introduced by the first two factors and the third factor. By monitoring this proportion, it is possible to detect a frozen sensor that is characterized by a dramatic reduction in the variance due to process factors over a sufficiently long detection window. The method has successfully detected a frozen level sensor using historical data from a large petrochemical plant. Unlike spectral analysis, this method works with measurements sampled at frequencies commonly achievable in a process environment. This increases the practical utility of the method.