Abstract: Process control parameters are predicted to fabricate an object using deposition. An input design geometry is provided for the object. A training data set includes past post-build physical inspection data for a plurality of objects that comprise at least one object that is different from the object to be physically fabricated; and training data generated through a repetitive process of randomly choosing values for each of multiple process control parameters and scoring adjustments to the multiple process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments. A machine learning algorithm is trained using the provided training data set and a predicted optimal set of the multiple process control parameters is generated for initiating and performing the deposition process to fabricate the object.

Abstract: Process control parameters are predicted to fabricate an object using deposition. An input design geometry is provided for the object. A training data set includes past post-build physical inspection data for a plurality of objects that comprise at least one object that is different from the object to be physically fabricated; and training data generated through a repetitive process of randomly choosing values for each of multiple process control parameters and scoring adjustments to the multiple process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments. A machine learning algorithm is trained using the provided training data set and a predicted optimal set of the multiple process control parameters is generated for initiating and performing the deposition process to fabricate the object.

Abstract: Methods for control of post-design free form deposition processes or joining processes are described that utilize machine learning algorithms to improve fabrication outcomes. The machine learning algorithms use real-time object property data from one or more sensors as input, and are trained using training data sets that comprise: i) past process simulation data, past process characterization data, past in-process physical inspection data, or past post-build physical inspection data, for a plurality of objects that comprise at least one object that is different from the object to be fabricated; and ii) training data generated through a repetitive process of randomly choosing values for each of one or more input process control parameters and scoring adjustments to process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments.

Abstract: Embodiments provide a camera design (e.g., an eyeball camera) that mimics a human eye in geometry, optical performance and/or motion. The eyeball camera adopts the same cornea and pupil geometry from the human eye, and has the iris and pupil configured with multiple texture, color or diameter options. The resolution of the eyeball camera is designed to match the acuity of typical 20/20 human vision, and focus is adjusted from 0 to 4 diopters. A pair of eyeball cameras are mounted independently on two hexapods to simulate the human eye gaze and vergence. The perceived virtual and real world are calibrated and evaluated based on eye conditions like pupil location and gaze using the eyeball cameras. The eyeball camera serves as a bridge to combine the data from spatial computing like eye tracking, 3D geometry of the digital world, display color accuracy/uniformity, and display optical quality (sharpness, contrast, etc.).

Abstract: Machine learning-based methods and systems for automated object defect classification and adaptive, real-time control of manufacturing processes are described.

Abstract: Methods for control of post-design free form deposition processes or joining processes are described that utilize machine learning algorithms to improve fabrication outcomes. The machine learning algorithms use real-time object property data from one or more sensors as input, and are trained using training data sets that comprise: i) past process simulation data, past process characterization data, past in-process physical inspection data, or past post-build physical inspection data, for a plurality of objects that comprise at least one object that is different from the object to be fabricated; and ii) training data generated through a repetitive process of randomly choosing values for each of one or more input process control parameters and scoring adjustments to process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments.

Abstract: Methods for control of post-design free form deposition processes or joining processes are described that utilize machine learning algorithms to improve fabrication outcomes. The machine learning algorithms use real-time object property data from one or more sensors as input, and are trained using training data sets that comprise: i) past process simulation data, past process characterization data, past in-process physical inspection data, or past post-build physical inspection data, for a plurality of objects that comprise at least one object that is different from the object to be fabricated; and ii) training data generated through a repetitive process of randomly choosing values for each of one or more input process control parameters and scoring adjustments to process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments.

Abstract: Disclosed herein are machine learning-based methods and systems for automated object defect classification and adaptive, real-time control of additive manufacturing and/or welding processes.

Abstract: Methods for control of post-design free form deposition processes or joining processes are described that utilize machine learning algorithms to improve fabrication outcomes. The machine learning algorithms use real-time object property data from one or more sensors as input, and are trained using training data sets that comprise: i) past process simulation data, past process characterization data, past in-process physical inspection data, or past post-build physical inspection data, for a plurality of objects that comprise at least one object that is different from the object to be fabricated; and ii) training data generated through a repetitive process of randomly choosing values for each of one or more input process control parameters and scoring adjustments to process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments.

Abstract: Disclosed herein are machine learning-based methods and systems for automated object defect classification and adaptive, real-time control of additive manufacturing and/or welding processes.

Abstract: Disclosed is a method of and system for managing service requests. The method may include determining, with a processor, a Service Level Agreement (SLA) target associated with each service request of a plurality of service requests. Additionally, the method may include determining, with a processor, a target delivery time corresponding to each service request of the plurality of service requests. A target delivery time of a service request may be determined based on each of an origin time and a SLA target associated with the service request. Furthermore, the method may include determining, with a processor, a priority value corresponding to each service request of the plurality of service requests. The priority value corresponding to a service request may be determined based on at least one of the origin time of the service request and the target delivery time of the service request.

Abstract: A beacon light member including a housing configured to be attached to a base member of a beacon light, the base member of the beacon light configured to utilize an incandescent light source. A power supply contained in the housing is configured to electrically connect to a power point in the base member. At least one light emitting diode (LED) light source is contained in the housing. A beacon light including a first base member, a second member, and at least one incandescent light source can also be retrofit. Under the retrofitting method, the at least one incandescent light source is removed, the second member is removed, and the second member is replaced with a beacon light module including at least one light emitting diode (LED) light source.

Abstract: A beacon light member including a housing configured to be attached to a base member of a beacon light, the base member of the beacon light configured to utilize an incandescent light source. A power supply contained in the housing is configured to electrically connect to a power point in the base member. At least one light emitting diode (LED) light source is contained in the housing. A beacon light including a first base member, a second member, and at least one incandescent light source can also be retrofit. Under the retrofitting method, the at least one incandescent light source is removed, the second member is removed, and the second member is replaced with a beacon light module including at least one light emitting diode (LED) light source.