Abstract: The present application describes an apparatus having a processor configured to receive a plurality of sensor measurements for each sensor of a plurality of sensors of the system. The processor may be configured to compare the plurality of sensor measurements from each sensor to a respective threshold value, determine, based on the comparisons, a condition of the system having a degraded state and one or more conditions of the system having a normal state, and select at least one of the one or more conditions of the system having a normal state. The processor may be configured to input the condition having degraded state and the at least one condition having a normal state into a diagnostic model. Further, the processor may be configured to isolate, using the diagnosis model, a failed or degraded component of the system.

Abstract: An interface system for flight deck communications includes a chatbot configured to perform a conversation with a pilot. The conversation includes speech communications, visual communications using a display, or both. The interface system also includes a dynamic conversational graph generator. The dynamic conversational graph generator is configured to perform a set of functions including determining a flight operational procedure from the conversation with the pilot. The set of functions also include providing information associated with the flight operational procedure to the chatbot for communicating to the pilot. The set of functions also include responding to any requests received from the pilot by the chatbot during the conversation with the pilot.

Abstract: Subject matter described herein includes generating a visual environment for interactive development of a machine learning (ML) model. The method includes accessing observations of data each of which includes values of independent variables and a dependent variable. The method includes performing an interactive feature construction and selection in which select independent variables are selected as or transformed into a set of features for use in building a ML model to predict the dependent variable. The method includes building the ML model using a ML algorithm, the set of features, and a training set produced from the set of features and observations of the data. And the method includes outputting the ML model for deployment to predict the dependent variable for additional observations of the data.

Abstract: A method for predictive product quality assessment comprises receiving initialization product assessment data for a plurality of products. The initialization product assessment data comprises, for each product, one or more events, and for each of the one or more events, an amount of remediation time, a reassessment status, and a recurring event status. The initialization product assessment data is used to initialize a product readiness model to determine a product readiness score based upon run-time product assessment data. The run-time product assessment data comprises, for a selected product, one or more run-time events. For each of the one or more run-time events, a run-time reassessment status and a run-time recurring event status are obtained. A total run-time remediation time, the run-time reassessment status and the run-time recurring event status are input into the product readiness model. The product readiness model is utilized to determine and output the product readiness score.

Abstract: Predicting a future needed repair and/or maintenance activity for an aircraft system such as a cabin air compressor detects a fault signal from the aircraft system, the fault signal being indicative of a fault in the aircraft system. The fault signal is logged into a machine learning computer system. A root cause of a fault signal is determined and the root cause of the fault signal is logged into the computer system. A repair of the root cause of the fault signal is determined and the repair of the root cause of the fault signal is logged into the computer system. The root cause of the fault signal and the repair of the root cause of the fault signal are merged, creating a classification of a future fault signal, a future root cause of the future fault signal and future repair of the future root cause.

Abstract: A method is provided for maintaining an onboard reasoner for diagnosing failures on an aircraft that includes aircraft systems configured to report faults to the onboard reasoner. The method includes accessing diagnostic data received from an onboard computer of the aircraft that includes the onboard reasoner. An off-board reasoner builds an off-board diagnostic causal model that describes causal relationships between the failed tests and the diagnosed failure modes. The off-board diagnostic causal model is compared to the diagnostic data. Based thereon, a discrepancy is identified between the graph of the off-board diagnostic causal model, and the other graph of the onboard diagnostic causal model, to determine a new causal relationship relative to the known causal relationships. The onboard diagnostic causal model is updated to further describe the new causal relationship, including producing an updated model, and uploading the updated model to the onboard computer.

Abstract: A method is provided that includes generating a visual environment for interactive development of a machine learning (ML) model. The method includes accessing observations of data each of which includes values of independent variables and a dependent variable, and performing an interactive exploratory data analysis (EDA) of the values of a set of the independent variables. The method includes performing an interactive feature construction and selection based on the interactive EDA, and in which select independent variables are selected as or transformed into a set of features for use in building a ML model to predict the dependent variable. The method includes building the ML model using a ML algorithm, the set of features, and a training set produced from the set of features and observations of the data. And the method includes outputting the ML model for deployment to predict the dependent variable for additional observations of the data.

Abstract: A method is provided for diagnosing a failure on an aircraft that includes aircraft systems configured to report faults to an onboard reasoner. The method includes receiving a fault report at an onboard computer of the aircraft from an aircraft system of the aircraft systems, the fault report indicating failed tests reported by the aircraft system. The onboard reasoner accesses an onboard diagnostic causal model represented by a graph describing known causal relationships between possible failed tests reported by the respective ones of the aircraft systems, and possible failure modes of the respective ones of the aircraft systems. The onboard reasoner diagnoses a failure mode of the aircraft system or another of the aircraft systems, from the failed tests, and using a graph-theoretic algorithm and the onboard diagnostic causal model. A maintenance action is determined for the failure mode, and a maintenance message is generated including the maintenance action.

Abstract: A method of categorizing natural language text using a processor configured to execute instructions stored on a memory to perform the steps. The method includes selecting candidate keywords from a list of potential keywords based on the natural language text, the candidate keywords having a probability of success being greater than a threshold value. The method also includes generating, using a classification machine learning model (MLM), a list of candidate categories based on the potential keywords. The method also includes generating, using a similarity comparison MLM, a similarity score based on the candidate categories and a set of pre-determined categories. The method also includes assigning a selected category based on the similarity score to the natural language text.

Abstract: A method is provided that includes generating a visual environment for interactive development of a machine learning (ML) model. The method includes accessing observations of data each of which includes values of independent variables and a dependent variable, and performing an interactive exploratory data analysis (EDA) of the values of a set of the independent variables. The method includes performing a feature construction and selection based on the interactive EDA, and in which select independent variables are selected as or transformed into a set of features for use in building a ML model to predict the dependent variable. The method includes building the ML model using a ML algorithm, the set of features, and a training set produced from the set of features and observations of the data. And the method includes outputting the ML model for deployment to predict the dependent variable for additional observations of the data.

Abstract: An aircraft performance analysis system and method include a performance analysis control unit that receives original performance model data, receives flight data from an aircraft, and determines a current performance model for the aircraft based on the original performance model data and the flight data.

Abstract: A method is provided that includes generating a visual environment for interactive development of a machine learning (ML) model. The method includes accessing observations of data each of which includes values of independent variables and a dependent variable, and performing an interactive exploratory data analysis (EDA) of the values of a set of the independent variables. The method includes performing an interactive feature construction and selection based on the interactive EDA, and in which select independent variables are selected as or transformed into a set of features for use in building a ML model to predict the dependent variable. The method includes building the ML model using a ML algorithm, the set of features, and a training set produced from the set of features and observations of the data. And the method includes outputting the ML model for deployment to predict the dependent variable for additional observations of the data.

Abstract: An interface system for flight deck communications includes a chatbot configured to perform a conversation with a pilot. The conversation includes speech communications, visual communications using a display, or both. The interface system also includes a dynamic conversational graph generator. The dynamic conversational graph generator is configured to perform a set of functions including determining a flight operational procedure from the conversation with the pilot. The set of functions also include providing information associated with the flight operational procedure to the chatbot for communicating to the pilot. The set of functions also include responding to any requests received from the pilot by the chatbot during the conversation with the pilot.

Abstract: A method is provided that includes generating a visual environment for interactive development of a machine learning (ML) model. The method includes accessing observations of data each of which includes values of independent variables and a dependent variable. The method includes performing a feature construction and selection based on the interactive EDA, and in which select independent variables are selected as or transformed into a set of features for use in building a ML model to predict the dependent variable. The method includes an interactive model building to build the ML model using a ML algorithm, the set of features, and a training set produced from the set of features and observations of the data. And the method includes outputting the ML model for deployment to predict the dependent variable for additional observations of the data.

Abstract: A method is provided that includes generating a visual environment for interactive development of a machine learning (ML) model. The method includes accessing observations of data each of which includes values of independent variables and a dependent variable, and performing an interactive exploratory data analysis (EDA) of the values of a set of the independent variables. The method includes performing an interactive feature construction and selection based on the interactive EDA, and in which select independent variables are selected as or transformed into a set of features for use in building a ML model to predict the dependent variable. The method includes building the ML model using a ML algorithm, the set of features, and a training set produced from the set of features and observations of the data. And the method includes outputting the ML model for deployment to predict the dependent variable for additional observations of the data.

Abstract: A method of architecting machine learning pipelines is provided. Example implementations of the method include causing an apparatus to generate a graphical user interface (GUI) from which a computing platform is accessible to architect machine learning pipelines. In example implementations, the method includes for a machine learning pipeline for a phase in the machine learning lifecycle: building software components that are separate, distinct and encapsulate respective processes executable to implement the phase in the machine learning lifecycle, the software components including ports that are communication endpoints of the software components. The method further includes interconnecting the software components with connections attached to the ports and thereby forming a network of interconnected software components that embodies the machine learning pipeline.

Abstract: A method is provided that includes generating a visual environment for interactive development of a machine learning (ML) model. The method includes accessing observations of data each of which includes values of independent variables and a dependent variable, and performing an interactive exploratory data analysis (EDA) of the values of a set of the independent variables. The method includes performing an interactive feature construction and selection based on the interactive EDA, and in which select independent variables are selected as or transformed into a set of features for use in building a ML model to predict the dependent variable. The method includes building the ML model using a ML algorithm, the set of features, and a training set produced from the set of features and observations of the data. And the method includes outputting the ML model for deployment to predict the dependent variable for additional observations of the data.

Abstract: A method is provided for repair of a mechanical or electromechanical system of a machine. An inference engine receives indication of a failure mode of the system, and measurements of operating conditions of the machine, and the inference engine defines a current problem including (a) the failure mode of the system, and (b) a pattern in the measurements. The inference engine searches a knowledge base with historical problems including (a) failure modes of systems of the machine, and (b) patterns in measurements of the operating conditions, and respective solutions with (c) repair actions performed to address the respective ones of the failure modes, for a respective solution to a historical problem most similar to the current problem. This is inferred as a solution to the current problem, and the inference engine generates an output display indicating the repair action of the solution to address the failure mode of the system.

Abstract: An aircraft performance analysis system and method include a performance analysis control unit that receives original performance model data, receives flight data from an aircraft, and determines a current performance model for the aircraft based on the original performance model data and the flight data.

Abstract: A method is provided for maintaining an onboard reasoner for diagnosing failures on an aircraft that includes aircraft systems configured to report faults to the onboard reasoner. The method includes accessing diagnostic data received from an onboard computer of the aircraft that includes the onboard reasoner. An off-board reasoner builds an off-board diagnostic causal model that describes causal relationships between the failed tests and the diagnosed failure modes. The off-board diagnostic causal model is compared to the diagnostic data. Based thereon, a discrepancy is identified between the graph of the off-board diagnostic causal model, and the other graph of the onboard diagnostic causal model, to determine a new causal relationship relative to the known causal relationships. The onboard diagnostic causal model is updated to further describe the new causal relationship, including producing an updated model, and uploading the updated model to the onboard computer.