Abstract: A method for estimating a trend in exhaust gas temperature in a turbine engine includes sampling exhaust gas temperature and a plurality of variables associated with the exhaust gas temperature over a set of observation times for a turbine engine to acquire exhaust gas temperature data. A trend in the exhaust gas temperature for the specific turbine engine is identified by removing the effect of the plurality of variables on the exhaust gas temperature data.

Abstract: In an experimental design strategy for evaluating systems with complex physical, chemical and structural requirements, a first population of entities is synthesized, a property of each of the entities can be detected by a high throughput screening (HTS) method and a genetic algorithm based on the property of the entities is executed to identify a second population of entities. A system for screening constructs to determine a problem solution includes a generator to provide a binary string representing a random first population of the constructs, a combinatorial reactor to synthesize the first population of constructs and to determine a fitness function for each construct of the population by a high throughput screening process and an executor to execute a genetic algorithm on the first population to produce a generation that defines a second population of the materials.

Abstract: An interactive graphics-based analysis tool for performing reliability analysis of a system formed from a variety of subsystems and components within each subsystem. The tool uses a hierarchical representation component to organize the system, subsystems and components into a hierarchical representation. An interactive selection component provides different options for analyzing the hierarchical representation. A reliability analysis component, responsive to the hierarchical representation component and the interactive selection component, allows a user to perform a reliability analysis at any level of the hierarchical representation.

Abstract: A system and method for automatically interpreting a multi-threaded event log. A medical imaging device such as a magnetic resonance (MR) or computed tomography (CT) device records imaging data correlating to medical examinations. The imaging data is stored in an event log along with other data such as system errors and table movement. Certain useful information must be extracted from the event logs to provide useful reports for clinician review or further processing. The present system incorporates a state machine to extract useful information based on predefined conditions. The useful information is automatically extracted from the event log and stored in a reduced data set event log.

Abstract: A hybrid learning system is provided for searching an experimental space. A data mart is configured to acquire, store, and manipulate a set or meta-set of data including at least historical experimental data, descriptor data, and concurrent experimental data. A search engine is designed to use unsupervised learning techniques to select a set of evaluation points representing a corresponding set of experiments to be run, based on data from the data mart. A point evaluation mechanism provided with supervised learning modules which perform predictive processing based on the evaluation points selected by the search engine, and a scoring module performs a rating operation on outputs of the learning modules to rate the outputs of the learning modules from best to worst. The data mart search engine and point evaluation mechanism allow for a repetitive processing to refine an output of potential solutions without the requirement of continually running actual physical experiments.