Abstract: A method for determining relative likelihood of a failure mode is provided. The method comprises receiving evidence observations of a monitored system from monitors connected in a many-to-many relationship to the failure modes, generating a fault condition including states of all failure modes that are connected to the monitors, and computing a relative probability of failure for each failure mode. The fault condition is generated for a reference model of the monitored system and is based on the received evidence observations. The relative probability of failure for each failure mode is based on a false alarm probability, a detection probability, and a ratio of prior probabilities of a candidate hypothesis to a null hypothesis of no active failure mode.

Abstract: A method, system, and computer program product for predicting the functional availability of a complex system is provided. Parameters of the complex system are converted from a plurality of binary values to at least one prognostic vector. At least a portion of a binary input expression is converted into an equivalent fuzzy output expression, the fuzzy output expression operable on the at least one prognostic vector.

Abstract: The present application relates to a method of splitting a fault condition including receiving evidence observations of a monitored system from monitors connected in a many-to-many relationship to the failure modes, generating a fault condition, computing a relative probability of failure for each failure mode in the fault condition. When there is more than one failure mode in the fault condition, the method includes computing a relative probability of each pair of failure modes in the fault condition, ranking the computed relative probabilities of the individual failure modes and the computed relative probabilities of the pairs of failure modes. If the highest ranked failure mode is a pair of failure modes, the fault condition is split based on the failure modes in the highest ranked pair of failure modes are split. If the highest ranked failure mode is an individual failure mode, a failure is isolated based on the ranking.

Abstract: A recursive mapping structure for diagnostic models is provided. A parent diagnostic model includes a first input module, a first output module, a first monitor module coupled to the first input and first output modules, and a first propagation module coupled between the first input and first output modules. A child diagnostic model includes a second input module, a second output module, a second monitor module coupled to the second input and second output modules, and a second propagation module coupled between the second input and second output modules, wherein the second monitor module is coupled to the first monitor module.

Abstract: A method for determining a probabilistic loss of function of a system includes the steps of determining a plurality of failure mode probabilities, ranking a plurality of functions pertaining to the failure mode probabilities, and identifying a likely function at least substantially lost by the system based at least in part on the plurality of failure mode probabilities and the ranking.

Abstract: The present application relates to a method of splitting a fault condition including receiving evidence observations of a monitored system from monitors connected in a many-to-many relationship to the failure modes, generating a fault condition, computing a relative probability of failure for each failure mode in the fault condition. When there is more than one failure mode in the fault condition, the method includes computing a relative probability of each pair of failure modes in the fault condition, ranking the computed relative probabilities of the individual failure modes and the computed relative probabilities of the pairs of failure modes. If the highest ranked failure mode is a pair of failure modes, the fault condition is split based on the failure modes in the highest ranked pair of failure modes are split. If the highest ranked failure mode is an individual failure mode, a failure is isolated based on the ranking.

Abstract: A method for determining relative likelihood of a failure mode is provided. The method comprises receiving evidence observations of a monitored system from monitors connected in a many-to-many relationship to the failure modes, generating a fault condition including states of all failure modes that are connected to the monitors, and computing a relative probability of failure for each failure mode. The fault condition is generated for a reference model of the monitored system and is based on the received evidence observations. The relative probability of failure for each failure mode is based on a false alarm probability, a detection probability, and a ratio of prior probabilities of a candidate hypothesis to a null hypothesis of no active failure mode.

Abstract: A method for determining a probabilistic loss of function of a system includes the steps of determining a plurality of failure mode probabilities, ranking a plurality of functions pertaining to the failure mode probabilities, and identifying a likely function at least substantially lost by the system based at least in part on the plurality of failure mode probabilities and the ranking.

Abstract: A health monitoring system includes a first monitoring unit configured to monitor health status indicators of a subject system; and a second monitoring unit configured to monitor the health status indicators of the subject system upon receiving a transfer signal.

Abstract: A method for diagnostic reasoning of faults appearing in a vehicle health monitoring system (VHM) is provided. One of alternatively a signal mode or a failure mode state is identified based on an input. If a signal is identified, the signal is queried to determine if the signal indicts a failure mode. If the signal indicts the failure mode, an intermittent watch flag is set for the failure mode. A count representing a number of occurrences of the signal as an intermittent fault is incremented. It is determined if the count exceeds a predetermined threshold. If the count exceeds the predetermined threshold, the intermittent fault is determined to be a permanent fault.

Abstract: A distributed decision making architecture for embedded prognostics in a platform is provided. An estimation system determines at least one performance characteristic of at least one device in the platform. A supervisory system is in communication with, and superior to, the estimation system. The supervisory system calculates a prediction of remaining useful life (RUL) of the at least one device in the platform. The supervisory system is adapted for collecting the at least one performance characteristic from the estimation system to generate a performance estimate, and implementing at least one data-driven equation to match the at least one performance estimate against of at least one known degradation condition to generate the prediction of remaining useful life of the at least one device.

Abstract: A recursive mapping structure for diagnostic models is provided. A parent diagnostic model includes a first input module, a first output module, a first monitor module coupled to the first input and first output modules, and a first propagation module coupled between the first input and first output modules. A child diagnostic model includes a second input module, a second output module, a second monitor module coupled to the second input and second output modules, and a second propagation module coupled between the second input and second output modules, wherein the second monitor module is coupled to the first monitor module.

Abstract: A method, system, and computer program product for predicting the functional availability of a complex system is provided. Parameters of the complex system are converted from a plurality of binary values to at least one prognostic vector. At least a portion of a binary input expression is converted into an equivalent fuzzy output expression, the fuzzy output expression operable on the at least one prognostic vector.