Abstract: A system and method including receiving a set of deep neural networks (DNN) including DNNs trained with an embedded trojan and DNNs trained without any embedded trojan, each of the trained DNNs being represented by a mathematical formulation learned by the DNNs and expressing a relationship between an input of the DNNs and an output of the DNNs; extracting at least one characteristic feature from the mathematical formulation of each of the trained DNNs; statistically analyzing the at least one characteristic feature to determine whether there is a difference between the DNNs trained with the embedded trojan and the DNNs trained without any embedded trojan; generating, in response to the determination indicating there is a difference, a detector model to execute the statistical analyzing on deep neural networks; and storing a file including the generated detector model in a memory device.

Abstract: Determining a quality score for a part manufactured by an additive manufacturing machine based on build parameters and sensor data without the need for extensive physical testing of the part. Sensor data is received from the additive manufacturing machine during manufacture of the part using a first set of build parameters. The first set of build parameters is received. A first algorithm is applied to the first set of build parameters and the received sensor data to generate a quality score. The first algorithm is trained by receiving a reference derived from physical measurements performed on at least one reference part built using a reference set of build parameters. The quality score is output via the communication interface of the device.

Abstract: A method of transferring operational parameter sets between different domains of additive manufacturing machines includes creating a first machine domain parameter set in a first machine domain, accessing a model of a second additive manufacturing in a second machine domain, creating a second machine domain parameter set by applying transfer learning techniques including learning differences between the first machine domain and the second machine domain, adjusting the first machine domain parameter set using the differences before incorporation into the second machine domain to obtain the second machine domain parameter set, the second machine domain parameter set representing operational settings for the second additive manufacturing machine, the second additive manufacturing machine producing a product sample, determining if the product sample is within quality assurance metrics, and if the product sample is not within the quality assurance metrics, adjusting the second machine domain parameter set.

Abstract: A method of calibrating an additive manufacturing machine includes obtaining a model for the additive manufacturing machine, obtaining a baseline sensor data set for a particular additive manufacturing machine, creating a machine-specific nominal fingerprint for the particular additive manufacturing machine with controllable variation for one or more process inputs, producing on the particular additive manufacturing machine a test-page based object, obtaining a current sensor data set of the test-page based object on the particular additive manufacturing machine, estimating a scaling factor or a bias for each of the one or more process inputs from the current data set, and updating a calibration file for the particular additive machine if the estimated scaling error or bias are greater than a respective predetermined tolerance. A system for implementing the method and a non-transitory computer-readable medium are also disclosed.

Abstract: A system and method including receiving a set of deep neural networks (DNN) including DNNs trained with an embedded trojan and DNNs trained without any embedded trojan, each of the trained DNNs being represented by a mathematical formulation learned by the DNNs and expressing a relationship between an input of the DNNs and an output of the DNNs; extracting at least one characteristic feature from the mathematical formulation of each of the trained DNNs; statistically analyzing the at least one characteristic feature to determine whether there is a difference between the DNNs trained with the embedded trojan and the DNNs trained without any embedded trojan; generating, in response to the determination indicating there is a difference, a detector model to execute the statistical analyzing on deep neural networks; and storing a file including the generated detector model in a memory device.

Abstract: Determining a quality score for a part manufactured by an additive manufacturing machine based on build parameters and sensor data without the need for extensive physical testing of the part. Sensor data is received from the additive manufacturing machine during manufacture of the part using a first set of build parameters. The first set of build parameters is received. A first algorithm is applied to the first set of build parameters and the received sensor data to generate a quality score. The first algorithm is trained by receiving a reference derived from physical measurements performed on at least one reference part built using a reference set of build parameters. The quality score is output via the communication interface of the device.

Abstract: A method of calibrating an additive manufacturing machine includes obtaining a model for the additive manufacturing machine, obtaining a baseline sensor data set for a particular additive manufacturing machine, creating a machine-specific nominal fingerprint for the particular additive manufacturing machine with controllable variation for one or more process inputs, producing on the particular additive manufacturing machine a test-page based object, obtaining a current sensor data set of the test-page based object on the particular additive manufacturing machine, estimating a scaling factor or a bias for each of the one or more process inputs from the current data set, and updating a calibration file for the particular additive machine if the estimated scaling error or bias are greater than a respective predetermined tolerance. A system for implementing the method and a non-transitory computer-readable medium are also disclosed.

Abstract: A method of transferring operational parameter sets between different domains of additive manufacturing machines includes creating a parameter set for a first additive manufacturing machine domain, accessing a model of a second additive manufacturing machine domain, creating a second parameter set of operational settings used to operate the second additive manufacturing machine, obtaining a second sensor data suite during the operation of the second additive manufacturing machine, comparing the second sensor data suite to one or more predetermined performance thresholds to determine if a product sample is within quality assurance metrics, and if the product sample is not within the quality assurance metrics, adjusting the second parameter set. A system for implementing the method and a non-transitory computer-readable medium are also disclosed.

Abstract: According to some embodiments, system and methods are provided, comprising calculating a region of competence for a data-driven model; executing a physics-driven model when the calculated region of competence for the data-driven model falls outside of a threshold region of competence; and calibrating the physics-driven model as a function of a discrepancy between physics-driven model and actual field data when a stopping criterion has not been met. Numerous other aspects are provided.

Abstract: Systems and methods for planning and optimizing air traffic flow within an airspace are provided.

Abstract: Systems and methods for optimizing a plurality of competing portfolios of logistical alternatives are disclosed. In one embodiment, where the competing portfolios of logistical alternatives are competing portfolios of flight paths, a method (1100) for optimizing a plurality of competing portfolios of logistical alternatives includes receiving (1102) competing flight path portfolios from one or more flight operation centers. Dominance criteria are applied (1104) to select a subset of the portfolios from the plurality of competing portfolios for further consideration. Multi-objective genetic optimization is applied (1106) to the subset of portfolios to identify an optimal portfolio among the plurality of competing portfolios of logistical alternatives.

Abstract: Monitoring dynamic units that operate in complex, dynamic environments, is provided in order to classify and track unit behavior over time. When domain knowledge is available, feature-based models may be used to capture the essential state information of the units. When domain knowledge is not available, raw data is relied upon to perform this task. By analyzing logs of event messages (without having access to their data dictionary), embodiments allow the identification of anomalies (novelties). Specifically, a Normalized Compression Distance (such as one based on Kolmogorov Complexity) may be applied to logs of event messages. By analyzing the similarity and differences of the event message logs, units are identified that did not experience any abnormality (and locate regions of normal operations) and units that departed from such regions. Of particular interest is the detection and identification of units' epidemics, which is defined as sustained/increasing numbers of anomalies over time.

Abstract: A system and method for monitoring the vibrations of a machine that includes a reflective patch affixed to the machine and a vibration detection unit including an optics module. The optics module may be positioned remotely from the machine such that the optics module transmits an electromagnetic beam to the reflective patch and reflected from the reflective patch to the optics module. The optics module demodulates the electromagnetic beam to determine the vibration of the machine.

Abstract: Systems and methods for determining the inspection schedule of a plurality of machines based on at least one operating condition including a monitoring system for determining at least one operating condition for a plurality of machines and a microprocessor programmed to analyze the at least one operating condition to identify whether a machine is unhealthy based on the analysis of at least one operating condition monitored and programmed to determine an optimal schedule for inspecting the plurality of machines using a PDC device.

Abstract: The performance of optimization algorithms operating with compute-intensive fitness functions is enhanced by constraining time-intensive fitness evaluations for candidate solutions that show low likelihood of being fit at early stages of the fitness evaluation. By prematurely discarding alternatives that could be potentially optimal upon complete fitness evaluation but with low likelihood, the running time of the overall optimization process is advantageously reduced substantially, thereby trading off time complexity for search fidelity.

Abstract: A method of managing lifecycle costs for an asset inventory is provided. The method includes obtaining data related to assets for the asset inventory and analyzing the obtained data to generate a plurality of domain-dependent rules having parameters corresponding to assets of the asset inventory. The method also includes determining an optimal setting of the parameters to achieve an estimated least-cost value of owning the assets over a period of time and applying the optimal setting of the parameters to each asset to generate customized asset parameters.

Abstract: A method for analyzing vibration including: acquiring a vibration signal; isolating a vibration signal event in the acquired signal; determining a frequency of a damped sinusoid of the vibration signal event, wherein the damped sinusoid characterizes the vibration signal event, and using the characteristic damped sinusoid to identify an occurrence of the vibration signal event in another vibration signal.

Abstract: A method and system for performing model-based multi-objective asset optimization and decision-making is provided. The method includes building at least two predictive models for an asset. The building includes categorizing operational historical data via at least one of: controllable variables, uncontrollable variables, output objectives, and constraints. The building also includes selecting at least two output objectives or constraints, and identifying at least one controllable or uncontrollable variable suitable for achieving the at least two output objectives or constraints. The method also includes validating each predictive model and performing multi-objective optimization using the predictive models. The multi-objective optimization includes specifying search constraints and applying a multi-objective optimization algorithm. The method further includes generating a Pareto Frontier, and selecting a Pareto optimal input-output vector.

Abstract: A method and system for performing multi-objective predictive modeling, monitoring, and update for an asset is provided. The method includes determining a status of each of at least two predictive models for an asset as a result of monitoring predicted performance values. The status of each predictive model includes at least one of: acceptable performance values, validating model, and unacceptable performance values. Based upon the status of each predictive model, the method includes performing at least one of: terminating use of the at least two predictive models for the asset, generating an alert for the asset of the status of the at least two predictive models, and updating the at least two predictive models based upon the status of the at least two predictive models.

Abstract: A method of managing an asset inventory is provided. The method includes obtaining data related to assets of the asset inventory and analyzing the obtained data to estimate a total number of assets required by the asset inventory over a time period. The method also includes determining a first cost of owning an asset and a second cost of leasing an asset and allocating the asset inventory between a first number of owned assets and a second number of leased assets to achieve an estimated least-cost value of maintaining the total number of assets over the time period.