Abstract: A health monitoring system for a vehicle system includes a plurality of managers and a decision support module. Each manager corresponds to a different sub-system of the vehicle system, and generates manager output pertaining to the sub-system based at least in part on an intermediate output. Each manager comprises a plurality of reasoners. Each reasoner corresponds to a different component of the sub-system, and comprises a plurality of modules and a reasoner fusion block. Each module obtains data regarding a different aspect of the component and generates a preliminary output based on the data. The reasoner fusion block is coupled to the plurality of modules, receives the preliminary output, and generates the intermediate output based on the preliminary output. The decision support module is coupled to the plurality of managers, receives the manager output therefrom, and provides a decision support output based on the manager output.

Abstract: A health monitoring system for a vehicle system includes an operational support system including a plurality of managers and a decision support module. Each manager corresponds to a different sub-system of the vehicle system, and comprises a plurality of reasoners and a fusion block. Each reasoner is configured to obtain data and provide preliminary output regarding a different component of the sub-system based on the data. The fusion block is coupled to the plurality of reasoners, and is configured to receive the preliminary output and generating manager output based on the preliminary output. The decision support module is coupled to the plurality of managers, and is configured to receive the manager output and provide a decision support output based on the manager output.

Abstract: A system and method includes receiving an event, for example, from a frame relay network or from a system log. Whether the event designates a virtual circuit fault in at least one of the local network, the service provider network, or the communications link is determined. When the event designates a virtual circuit fault it is distinguished which of the local network, the service provider network, or the communications link is the source of the fault.

Abstract: Described are computer-based methods and apparatuses, including computer program products, for service integration on a network. Telecommunication services (e.g., calendar, television, phone, location) on a network are integrated using service codelets designed to interface with the services. A default codelet associated with the user (e.g., via a service plan) dynamically calls the service codelets to request information from the associated services (e.g., calendar data) and/or perform tasks with the associated services (e.g., update calendar). The service codelets can dynamically call other service codelets based on the results of their requests for information. The information from the services is integrated and returned to the user.

Abstract: Described are computer-based methods and apparatuses, including computer program products, for personal service integration on a network. A personal service monitors and stores user requests for services. The stored user requests are processed to determine usage patterns. The personal service processes the usage patterns to determine future requests and/or to determine how to fulfill a request. The personal service processes the request.

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: Methods and apparatus are provided for predicting ice formation on and shedding from blades of an air cycle machine (“ACM”) turbine. The method comprises generating operational condition data representative of ACM turbine operating conditions using a software model of the ACM, determining an amount of ice formation on the blades of the ACM turbine, and determining an amount of ice shed from the blades of the ACM turbine. The apparatus comprises means for generating operational condition data representative of ACM turbine operating conditions using a software model of the ACM, means for determining an amount of ice formation on the blades of the ACM turbine, and means for determining an amount of ice shed from the blades of the ACM turbine. In some embodiments, the means and apparatus may also involve predicting ACM wear, based at least in part on the predicted ice formation and shedding.

Abstract: Methods and apparatus are provided pertaining to a design of experiments. The method comprises generating a data set from historical data; identifying and removing any fault data points in the data set so as to create a revised data set; supplying the data points from the revised data set into a nonlinear neural network model; and deriving a simulator model characterizing a relationship between the input variables and the output variables. The apparatus comprises means for generating a data set from historical data; means for identifying and removing any fault data points in the data set so as to create a revised data set; means for supplying the data points from the revised data set into a nonlinear neural network model; and means for deriving a simulator model characterizing a relationship between the input variables and the output variables.

Abstract: A system and method is provided for lightoff detection in a turbine engine that provides improved accuracy and consistency. The system and method use engine temperature and engine rotation speed sensor data to determine a first time interval during which the lightoff is estimated to have occurred. A peak gradient in the temperature sensor data within the first time interval and a peak gradient in the engine rotation sensor data within the first time interval are then determined. The temperature peak gradient time and the engine rotation peak gradient time are then used as boundaries to determine a narrowed time interval within the first time interval. The minimum gradient in the engine rotation sensor data in the narrowed time interval is determined, with the minimum gradient time in the engine rotation sensor data comprising an accurate estimate of lightoff time for the turbine engine.

Abstract: Described are methods, systems, and apparatus, including computer program products for generating an integrated call control and dialog application. A graphical user interface is provided. A user is enabled, using the graphical user interface, to select an element from a plurality of elements. The plurality of elements include at least one call control element and at least one dialog element. The at least one call control element define control of at least one call event associated with the at least one dialog element. A module for telephony applications is generated using the graphical user interface.

Abstract: Described are methods, systems, and apparatus, including computer program products for interworking messages based on a session initiation protocol. A set of one or more instructions is associated with a rule. A session initiation protocol message based on a first format is received. The session initiation protocol message is transformed, using the set of one or more instructions, into a target session initiation protocol message based on a second format different from the first format.

Abstract: Described are methods, systems, and apparatus, including computer program products for transforming call control and dialog elements for telephony service applications from an intermediate language into a target language. A module that includes a plurality of elements is generated. At least a first element of the plurality of elements is a call control element and at least a second element of the plurality of elements is a dialog element. The call control element defines control of at least one call event associated with the dialog element. The module is stored in an intermediate design file, which is based on one or more intermediate languages. At least a part of the intermediate design file is transformed, using a transformation rule, into one or more target design files, which are based on one or more target languages. The one or more target languages are different from the one or more intermediate languages.

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: 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: In an exemplary embodiment, a method for managing a network includes monitoring a network using an interior gateway protocol to detect change in the network, and determining effects of the detected network change on Multi Protocol Label Switching paths in the network. For example, the MPLS paths can be the same as IGP best paths. An exemplary embodiment includes managing a Multi Protocol Label Switching network by discovering edge routers in the Multi Protocol Label Switching network, determining possible combinations of Multi Protocol Label Switching path end points based on services provided within the network, selecting discovered edge routers for observation, based on the determined possible combinations, monitoring the selected edge routers, and determining status of Multi Protocol Label Switching paths in the network based on the monitoring.

Abstract: A method is disclosed for managing network nodes, such as the nodes of a network, which communicate via connectivity services of a service provider. An exemplary method includes discovering status and configuration information for each set of nodes grouped by the service provider; and assigning a name to each set of nodes.

Abstract: Described are methods and apparatus, including computer program products, for controlling time-sensitive data in a packet-based network. Data associated with a call is received, and the data includes an identifier associated with the data, a data source, or one or more data destinations. The data is associated with a logical trunk group selected from a plurality of logical trunk groups each in communication with the one or more data destinations over a packet-based network. The logical trunk group is selected based in part on the identifier. Calls through the packet-based network are managed based in part on the associated logical trunk group.

Abstract: Described are methods and apparatus, including computer program products, for hierarchically organizing logical trunk groups in a packet-based network. A first hierarchical group includes a first logical trunk group that is associated with a first trunk resource parameter. The first hierarchical group is associated with a group resource parameter, a portion of which is based on the trunk resource parameter. Data associated with a telephone call is associated with a logical trunk group. Transmission of the data through a packet-based network is based in part on the group resource parameter.

Abstract: Described are methods and apparatus, including computer program products, for defining logical trunk groups in a packet-based network. A plurality of logical trunk groups are defined for a first media gateway in communication with a packet-based network. Each of the plurality of logical trunk groups is associated with one or more media gateways in communication over the packet-based network with the first media gateway. Data associated with a call that is received or transmitted by the media gateway is associated with a first logical trunk group of the plurality of logical trunk groups.

Abstract: A method embodiment for determining status of a private virtual network is disclosed. The method comprising classifying reachability faults of a virtual routing address into a plurality of first levels; classifying infrastructure faults of the virtual routing address into a plurality of second levels; and determining the status of the private virtual network based on one or a combination of the plurality of first and second levels of the plurality of virtual routing addresses. The private virtual network is part of a computing network including a provider network providing service to a plurality of virtual private networks. A virtual private network links a plurality of site networks.