Abstract: A system includes a first group of optic lenses within a focusing unit positioned along the propagation direction of a collimated laser beam, the first group of optic lenses separated by a predetermined fixed distance. The first group of optic lenses in conjunction cause the collimated beam to form as an annular beam as it passes through the first group of optic lenses. An axicon lens located distal from the first group of optic lenses along the propagation direction, the axicon lens operable to bifurcate the annular beam into two deflected collimated beam sections, and the axicon lens having a focus that causes the two deflected collimated beam sections to merge at a distance distal from the axicon lens to create an interference pattern region.

Abstract: Systems and methods for power system switching element (PSSE) anomaly detection are disclosed. An example PSSE anomaly detection unit may include a power system switching element position estimator (PSSEPE) and a comparison unit. The PSSEPE may be configured to receive a set of measurements and a set of control commands associated with a PSSE, calculate an anomaly confidence score based on the set of measurements and the set of control commands, and estimate a calculated PSSE position based on the set of measurements and the set of control commands. The comparison unit may be configured to receive the calculated PSSE position from the PSSEPE, receive the set of measurements and the set of control commands from the PSSEPE, receive a reported PSSE position associated with the PSSE, and determine a PSSE anomaly decision based on a difference between the reported PSSE position and the calculated PSSE position.

Abstract: An industrial asset may have monitoring nodes that generate current monitoring node values. A dynamic, resilient estimator may split a temporal monitoring node space into normal and one or more abnormal subspaces associated with different kinds of attack vectors. According to some embodiments, a neutralization model is constructed and trained for each attack vector using supervised learning and the associated abnormal subspace. In other embodiments, a single model is created using out-of-range values for abnormal monitoring nodes. Responsive to an indication of a particular abnormal monitoring node or nodes, the system may automatically invoke the appropriate neutralization model to determine estimated values of the particular abnormal monitoring node or nodes (e.g., by selecting the correct model or using out-of-range values). The series of current monitoring node values from the abnormal monitoring node or nodes may then be replaced with the estimated values.

Abstract: A system includes a first group of optic lenses within a focusing unit positioned along the propagation direction of a collimated laser beam, the first group of optic lenses separated by a predetermined fixed distance. The first group of optic lenses in conjunction cause the collimated beam to form as an annular beam as it passes through the first group of optic lenses. An axicon lens located distal from the first group of optic lenses along the propagation direction, the axicon lens operable to bifurcate the annular beam into two deflected collimated beam sections, and the axicon lens having a focus that causes the two deflected collimated beam sections to merge at a distance distal from the axicon lens to create an interference pattern region.

Abstract: According to some embodiments, system and methods are provided comprising receiving, via a communication interface of a part parameter dictionary module comprising a processor, geometry data for a plurality of geometric structures forming a plurality of parts, wherein the parts are manufactured with an additive manufacturing machine; determining, using the processor of the part parameter dictionary module, a feature set for each geometric structure; generating, using the processor of the part parameter dictionary module, one of a coupon and a coupon set for the feature set; generating an optimized parameter set for each coupon, using the processor of the part parameter dictionary module, via execution of an iterative learning control process for each coupon; mapping, using the processor of the part parameter dictionary module, one or more parameters of the optimized parameter set to one or more features of the feature set; and generating a dictionary of optimized scan parameter sets to fabricate geometric str

Abstract: The present disclosure provides techniques for implementing self-adapting neutralization against cyber-faults within industrial assets. The disclosed neutralization techniques may include obtaining an input dataset from a plurality of nodes of industrial assets and reconstructing compromised nodes in the plurality of nodes to neutralize cyber-faults detected based on the input dataset. A confidence metric may be computed for the reconstruction of the compromised nodes, e.g., using inductive conformal prediction. Based on the confidence metric and the reconstruction of the compromised nodes, input signals from the reconstruction of the compromised nodes may be transformed, or configuration parameters for a controller of the industrial assets may be tuned.

Abstract: The present disclosure relates to techniques for detecting cyber-faults in industrial assets. Such techniques may include obtaining an input dataset from a plurality of nodes of industrial assets and predicting fault nodes in the plurality of nodes by inputting the input dataset to a one-class classifier. The one-class classifier may be trained on normal operation data obtained during normal operations of the industrial assets. Further, the cyber-fault detection techniques may include computing a confidence level of cyber fault detection for the input dataset using the one-class classifier and adjusting decision thresholds based on the confidence level for categorizing the input dataset as normal or including cyber-faults. The predicted fault nodes and the adjusted decision thresholds may be used for detecting cyber-faults in the plurality of nodes of the industrial assets.

Abstract: An additive manufacturing apparatus, a computing system, and a method for operating an additive manufacturing apparatus are provided. The method includes obtaining two or more images corresponding to respective build layers at a build plate, wherein each image comprises a plurality of data points comprising a feature and corresponding location at the build plate; removing variation between the features of the plurality of data points; and normalizing each feature to remove location dependence in the plurality of data points.

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: According to some embodiments, system and methods are provided comprising receiving, via a communication interface of a parameter development module comprising a processor, a defined geometry for one or more parts, wherein the parts are manufactured with an additive manufacturing machine, and wherein a stack is formed from one or more parts; fabricating the one or more parts with the additive manufacturing machine based on a first parameter set; collecting in-situ monitoring data from one or more in-situ monitoring systems of the additive manufacturing machine for one or more parts; determining whether each stack should receive an additional part based on an analysis of the collected in-situ monitoring data; and fabricating each additional part based on the determination the stack should receive the additional part. Numerous other aspects are provided.

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: According to some embodiments, system and methods are provided comprising receiving, via a communication interface of a parameter development module comprising a processor, a defined geometry for one or more parts, wherein the parts are manufactured with an additive manufacturing machine, and wherein a stack is formed from one or more parts; fabricating the one or more parts with the additive manufacturing machine based on a first parameter set; collecting in-situ monitoring data from one or more in-situ monitoring systems of the additive manufacturing machine for one or more parts; determining whether each stack should receive an additional part based on an analysis of the collected in-situ monitoring data; and fabricating each additional part based on the determination the stack should receive the additional part. Numerous other aspects are provided.

Abstract: An industrial asset may have monitoring nodes (e.g., sensor or actuator nodes) that generate current monitoring node values. An abnormality detection and localization computer may receive the series of current monitoring node values and output an indication of at least one abnormal monitoring node that is currently being attacked or experiencing a fault. An actor-critic platform may tune a dynamic, resilient state estimator for a sensor node and output tuning parameters for a controller that improve operation of the industrial asset during the current attack or fault. The actor-critic platform may include, for example, a dynamic, resilient state estimator, an actor model, and a critic model. According to some embodiments, a value function of the critic model is updated for each action of the actor model and each action of the actor model is evaluated by the critic model to update a policy of the actor-critic platform.

Abstract: An industrial asset may have monitoring nodes that generate current monitoring node values. An abnormality detection computer may determine that an abnormal monitoring node is currently being attacked or experiencing fault. A dynamic, resilient estimator constructs, using normal monitoring node values, a latent feature space (of lower dimensionality as compared to a temporal space) associated with latent features. The system also constructs, using normal monitoring node values, functions to project values into the latent feature space. Responsive to an indication that a node is currently being attacked or experiencing fault, the system may compute optimal values of the latent features to minimize a reconstruction error of the nodes not currently being attacked or experiencing a fault. The optimal values may then be projected back into the temporal space to provide estimated values and the current monitoring node values from the abnormal monitoring node are replaced with the estimated values.

Abstract: Generating fault indications for an additive manufacturing machine based on a comparison of the outputs of multiple process models to measured sensor data. The method receiving sensor data from the additive manufacturing machine during manufacture of at least one part. Models are selected from a model database, each model generating expected sensor values for a defined condition. Difference values are computed between the received sensor data and an output of each of the models. A probability density function is computed, which defines, for each of the models, a likelihood that a given difference value corresponds to each respective model. A probabilistic rule is applied to determine, for each of the models, a probability that the corresponding model output matches the received sensor data. An indicator is output of a defined condition corresponding to a model having the highest match probability.

Abstract: Generating fault indications for an additive manufacturing machine based on a comparison of the outputs of multiple process models to measured sensor data. The method receiving sensor data from the additive manufacturing machine during manufacture of at least one part. Models are selected from a model database, each model generating expected sensor values for a defined condition. Difference values are computed between the received sensor data and an output of each of the models. A probability density function is computed, which defines, for each of the models, a likelihood that a given difference value corresponds to each respective model. A probabilistic rule is applied to determine, for each of the models, a probability that the corresponding model output matches the received sensor data. An indicator is output of a defined condition corresponding to a model having the highest match probability.

Abstract: According to some embodiments, system and methods are provided comprising receiving, via a communication interface of a part parameter dictionary module comprising a processor, geometry data for a plurality of geometric structures forming a plurality of parts, wherein the parts are manufactured with an additive manufacturing machine; determining, using the processor of the part parameter dictionary module, a feature set for each geometric structure; generating, using the processor of the part parameter dictionary module, one of a coupon and a coupon set for the feature set; generating an optimized parameter set for each coupon, using the processor of the part parameter dictionary module, via execution of an iterative learning control process for each coupon; mapping, using the processor of the part parameter dictionary module, one or more parameters of the optimized parameter set to one or more features of the feature set; and generating a dictionary of optimized scan parameter sets to fabricate geometric str

Abstract: A method of additive manufacturing machine (AMM) build process control includes obtaining AMM machine and process parameter settings, accessing sensor data for monitored physical conditions in the AMM, calculating a difference between expected AMM physical conditions and elements of the monitored conditions, providing the machine and process parameter settings, monitored conditions, and differences to one or more material property prediction models, computing a predicted value or range for the monitored conditions, comparing the predicted value or range to a predetermined target range, based on a determination that predicted value(s) are within the predetermined range, maintaining the machine and process parameter settings, or based on a determination that one or more of the predicted value(s) is outside the predetermined range, generating commands to compensate the machine and process parameter settings, and repeating the closed feedback loop at intervals of time during the build process.

Abstract: A direct metal laser melting (DMLM) system includes a rotatable base, and a build plate mounted on and supported by the rotatable base, where the build plate includes a build surface. The DMLM system also includes a first actuator assembly, a first powder dispenser disposed proximate the build plate and configured to deposit a weldable powder on the build surface of the build plate. In addition, the DMLM system includes a first powder spreader disposed proximate the build plate and configured to spread the weldable powder deposited on the build surface of the build plate, and a first laser scanner supported by the first actuator assembly in a position relative to the build plate, such that at least a portion of the build surface is within a field of view of the first laser scanner. The first laser scanner is configured to selectively weld the weldable powder. The first laser scanner is further configured to translate axially relative to the build surface on the first actuator assembly.

Abstract: An example additive manufacturing apparatus includes an energy source to melt material to form a component in an additive manufacturing process, a camera aligned with the energy source to obtain image data of the melted material during the additive manufacturing process, and a controller to control the energy source during the additive manufacturing process in response to processing of the image data. The controller adjusts control of the energy source based on a correction determined by: applying an artificial intelligence model to image data captured by a camera during an additive manufacturing process, the image data including an image of a melt pool of the additive manufacturing process; predicting an error in the additive manufacturing process using an output of the artificial intelligence model; and compensating for the error by generating a correction to adjust a configuration of the energy source during the additive manufacturing process.