Abstract: The present invention provides a system and method for automatically tagging documents with a given set of user-defined tags. The present invention takes as input the document to be tagged, and also a list of tags along with keywords belonging to these tags. The present invention then selects a tag, and scans the document for sentences that have keywords corresponding to the selected tag. Sentences that match the keywords are tagged with the selected tag. Once the whole document has been scanned, the present invention selects the next tag and repeats the whole process. This process is repeated until all tags have been seen.

Abstract: A system, method and computer program product is provided for tagging various portions of documents and measuring their usefulness for a particular purpose. The method takes a document that is to be tagged as input, and facilitates a user to tag various portions of the document, which the user considers as important. These tags are user-defined. Subsequently, the usefulness of the document for a particular purpose is determined by calculating quality of the document. The quality of a document is a combination of completeness and various other factors such as priority and severity as reported by a customer. Quality is used to sort results of a search query, which is made by the user, on the documents.

Abstract: The present invention provides a method for maintaining a knowledge base. The method taking as input, text examples that are tagged with a structural markup language; and maps knowledge nodes in the knowledge base with the tagged examples to determine: (1) the knowledge nodes that best match the tagged examples, and (2) the knowledge nodes that are best connected to the tagged examples. The results are displayed to the user, who verifies that the tagged examples match the selected knowledge nodes. Based on the user response, indices of the knowledge nodes are updated. The method may further include determining discrepancies between the existing knowledge base and the tagged examples, and further displaying the discrepancies to the user. The user can update the missing information in the knowledge base to remove the discrepancies in the existing knowledge base.

Abstract: A method of integrating case based reasoning data and FMECA data for product life cycle support. The method comprises creating an access path to case based data using a FMECA classification. The creating includes receiving a case based record including heading data. The heading data includes data elements and the data elements are correlated with data fields in a FMECA database. The FMECA database is searched for an entry that includes one or more of the data elements. The creating further includes determining if the entry should include a reference to the case based record. A new pointer to the case based record is inserted if the determining results in finding that the entry should include a reference to the case based record. The method for integrating case based reasoning data and FMECA data further comprises receiving a request from a user to access the case based data. The case based data is accessed via the FMECA database using the access path in response to the request.

Abstract: An exemplary embodiment of the invention relates to a method, system, and storage medium for building and maintaining a remote monitoring and diagnostics knowledge base via an alert fusion system. The method comprises receiving at least one alert relating to a condition detected on field equipment being remotely monitored. The method further comprises processing the alert which includes evaluating a severity level, and if a severity threshold is reached, generating a summary alert. The summary alert is transmitted to an end user at a remote client. The invention also includes a system and a storage medium for implementing the invention.

Abstract: A system for monitoring the condition of a vehicle has at least one wireless transmitter in on the vehicle, and in communication with the vehicle computer system. Data representative of operating parameters generated during the operation of the vehicle is downloaded to the transmitter, which transmits the data to a wireless receiver positioned proximal to a path of travel of the vehicle. The receiver is linked to a processor for transmission of the data to the processor for storage and processing if necessary. The system may also include at least one sensor, positioned proximal the path of travel, for detecting a physical phenomenon emanating from at least one vehicle component. The sensor generates a signal, which is transmitted to the processor. The processor is capable of analyzing the signal generating data indicative of operating condition of the vehicle component. The sensor, and/or receiver, mounted to a structure positioned proximal the path of travel of the vehicle.

Abstract: An on-board monitor for a railroad locomotive is disclosed. The on-board monitor interfaces with the controller subsystems of the locomotive to collect parametric performance data. The specific data to be collected and the collection intervals are defined at a remote service center and transmitted to the on-board monitor. The on-board monitor also includes the capability to collect additional data or collect data more frequently in response to the results of certain triggering events.

Abstract: An intelligent analysis apparatus and method for fluid filled electrical equipment includes sensors for measuring various parameters of the electrical equipment. Analytical models calculate parameters based on measurements of other parameters. The measured and calculated parameters are compared and the result of the comparison is used as an indicator in a causal network. The probabilities of the causal network are recalculated by a belief network. The analytical models are adjusted over time to account for acceptable changes in behavior of the equipment over time. The output of the causal network can be used for diagnostic and prognostic indication.

Abstract: A locomotive diagnostic system. A first sensor outputs a measurement of a first state variable (such as vibration) of a first locomotive component, such as a blower fan bearing set, and a second sensor outputs a measurement of a second state variable (such as rotational speed) of a second locomotive component, such as a blower fan shaft. The first state variable is indicative of the operation of the first component and is dependent on the second state variable. Data represents, for each of a number of different values of the second state variable, first, second, and third ranges of values of the first state variable which indicate, respectively, normal, worn, and failed operation of the first component. A mechanism, such as a digital computer, determines if the measurement of the first state variable is within the first, second, or third range of values of the first state variable for the measurement of the second state variable.

Abstract: A locomotive for model-based incipient failure detection includes at least one replaceable unit and at least one sensor to generate signals representative of current engine conditions related to the at least one replaceable unit. A controller includes an embedded replaceable unit model algorithm. Current operating conditions and ambient conditions are utilized within the algorithm to generate a model-based predicted value for the at least one sensor. The controller compares the at least one sensor signals to the model-based predicted values for calculating deviations therebetween and detecting incipient failure of the at least one replaceable unit.

Abstract: This invention is directed in general to a locomotive diesel engine, and more specifically, to a method and apparatus for performance based assessment of a locomotive diesel engine.

Abstract: The present invention discloses a system and method for isolating failures in a locomotive. In the present invention, the cause of failures occurring in the locomotive sub-systems are determined quickly and efficiently, while minimizing the need for human interaction. However, the present invention can incorporate information provided by an operator to produce a more refined diagnosis. In the present invention, incidents are recorded in an incident log and mapped to indicators, which are sent to a fault isolator for diagnosis. The fault isolator uses a diagnostic knowledge base having diagnostic information between failures occurring in locomotive and observable symptoms happening therein. A diagnostic engine then processes the mapped indicators with the diagnostic information in the diagnostic knowledge base and produces a list of the most likely causes for any failures. The present invention then provides a course of action to correct the failures.

Abstract: A locomotive control system for performance assessment of a locomotive engine includes a controller and at least one sensor coupled to the controller. The at least one sensor is located proximal to the locomotive engine so as to gather actual performance data from the locomotive engine. The controller monitors locomotive current operating conditions and utilizes the current operating conditions to calculate predicted performance. The controller compares the predicted performance output based upon the current operating conditions with the actual performance data to monitor any substantial deviations therefrom.