Abstract: An additive manufacturing system comprises an apparatus arranged to distribute layer of metallic powder across a build plane and a power source arranged to emit a beam of energy at the build plane and fuse the metallic powder into a portion of a part. The system includes a processor configured to steer the beam of energy across the build plane and receive data generated by one or more sensors that detect electromagnetic energy emitted from the build plane when the beam of energy fuses the metallic powder. The received data is converted into one or more parameters that indicate one or more conditions at the build plane while the beam of energy fuses the metallic powder. The one or more parameters are used as input into a machine learning algorithm to detect one or more defects in the fused metallic powder.

Abstract: This invention teaches a multi-sensor quality inference system for additive manufacturing. This invention still further teaches a quality system that is capable of discerning and addressing three quality issues: i) process anomalies, or extreme unpredictable events uncorrelated to process inputs; ii) process variations, or difference between desired process parameters and actual operating conditions; and iii) material structure and properties, or the quality of the resultant material created by the Additive Manufacturing process. This invention further teaches experimental observations of the Additive Manufacturing process made only in a Lagrangian frame of reference. This invention even further teaches the use of the gathered sensor data to evaluate and control additive manufacturing operations in real time.

Abstract: An additive manufacturing system comprises an apparatus arranged to distribute layer of metallic powder across a build plane and a power source arranged to emit a beam of energy at the build plane and fuse the metallic powder into a portion of a part. The system includes a processor configured to steer the beam of energy across the build plane and receive data generated by one or more sensors that detect electromagnetic energy emitted from the build plane when the beam of energy fuses the metallic powder. The received data is converted into one or more parameters that indicate one or more conditions at the build plane while the beam of energy fuses the metallic powder. The one or more parameters are used as input into a machine learning algorithm to detect one or more defects in the fused metallic powder.

Abstract: This disclosure describes various methods and apparatus for characterizing an additive manufacturing process. A method for characterizing the additive manufacturing process can include generating scans of an energy source across a build plane; measuring an amount of energy radiated from the build plane during each of the scans using an optical sensor; determining an area of the build plane traversed during the scans; determining a thermal energy density for the area of the build plane traversed by the scans based upon the amount of energy radiated and the area of the build plane traversed by the scans; mapping the thermal energy density to one or more location of the build plane; determining that the thermal energy density is characterized by a density outside a range of density values; and thereafter, adjusting subsequent scans of the energy source across or proximate the one or more locations of the build plane.

Abstract: This disclosure describes an additive manufacturing method that includes monitoring a temperature of a portion of a build plane during an additive manufacturing operation using a temperature sensor as a heat source passes through the portion of the build plane; detecting a peak temperature associated with one or more passes of the heat source through the portion of the build plane; determining a threshold temperature by reducing the peak temperature by a predetermined amount; identifying a time interval during which the monitored temperature exceeds the threshold temperature; identifying, using the time interval, a change in manufacturing conditions likely to result in a manufacturing defect; and changing a process parameter of the heat source in response to the change in manufacturing conditions.

Abstract: In some aspects, the additive manufacturing system may access, by a processor of an additive manufacturing system, a machine learning model that is trained to identify defects within a build plane. Also, the additive manufacturing system may capture, by an imaging system of the additive manufacturing system, an image of a build plane of the additive manufacturing system. The build plane can contain an object being manufactured through an additive manufacturing process. In addition, the additive manufacturing system may provide, by the processor, the captured image as an input to the machine learning model. Moreover, the additive manufacturing system may receive, by the processor, an output from the machine learning model identifying a defect in the build plane.

Abstract: This invention teaches a multi-sensor quality inference system for additive manufacturing. This invention still further teaches a quality system that is capable of discerning and addressing three quality issues: i) process anomalies, or extreme unpredictable events uncorrelated to process inputs; ii) process variations, or difference between desired process parameters and actual operating conditions; and iii) material structure and properties, or the quality of the resultant material created by the Additive Manufacturing process. This invention further teaches experimental observations of the Additive Manufacturing process made only in a Lagrangian frame of reference. This invention even further teaches the use of the gathered sensor data to evaluate and control additive manufacturing operations in real time.

Abstract: This disclosure describes various methods and apparatus for characterizing an additive manufacturing process. A method for characterizing the additive manufacturing process can include generating scans of an energy source across a build plane; measuring an amount of energy radiated from the build plane during each of the scans using an optical sensing system that monitors two discrete wavelengths associated with a blackbody radiation curve of the layer of powder; determining temperature variations for an area of the build plane traversed by the scans based upon a ratio of sensor readings taken at the two discrete wavelengths; determining that the temperature variations are outside a threshold range of values; and thereafter, adjusting subsequent scans of the energy source across or proximate the area of the build plane.

Abstract: This disclosure describes various methods and apparatus for calibration of temperature sensors in additive manufacturing systems. A method for calibration of temperature sensors can include selecting a first wavelength and a second wavelength spaced apart from the first wavelength; measuring an amount of energy radiated from a black body source at the first wavelength; measuring an amount of energy radiated from the black body source at the second wavelength; generating a relationship between a ratio of the amount of energy radiated at the first wavelength to the amount of energy radiated at the second wavelength; and determining, using the relationship, variations in a temperature of a build plane of an additive manufacturing system based upon a ratio of energy radiated at the first wavelength to energy radiated at the second wavelength.

Abstract: This disclosure describes an additive manufacturing method that includes monitoring a temperature of a portion of a build plane during an additive manufacturing operation using a temperature sensor as a heat source passes through the portion of the build plane; detecting a peak temperature associated with one or more passes of the heat source through the portion of the build plane; determining a threshold temperature by reducing the peak temperature by a predetermined amount; identifying a time interval during which the monitored temperature exceeds the threshold temperature; identifying, using the time interval, a change in manufacturing conditions likely to result in a manufacturing defect; and changing a process parameter of the heat source in response to the change in manufacturing conditions.

Abstract: This disclosure describes various methods and apparatus for characterizing an additive manufacturing process. A method for characterizing the additive manufacturing process can include generating scans of an energy source across a build plane; measuring an amount of energy radiated from the build plane during each of the scans using an optical sensor; determining an area of the build plane traversed during the scans; determining a thermal energy density for the area of the build plane traversed by the scans based upon the amount of energy radiated and the area of the build plane traversed by the scans; mapping the thermal energy density to one or more location of the build plane; determining that the thermal energy density is characterized by a density outside a range of density values; and thereafter, adjusting subsequent scans of the energy source across or proximate the one or more locations of the build plane.

Abstract: This disclosure describes an additive manufacturing system that includes a build plane having a first region and a second region. Multiple energy source can be positioned above the build plane and configured to direct energy into the first and second regions of the build plane. The system includes optical sensors configured to monitor an intensity of light emitted from the energy sources. A processor associated with the additive manufacturing system is configured to adjust the sensor outputs in response to the energy sources coming into close proximity.

Abstract: Various ways in which material property variations of raw materials used in additive manufacturing can be identified and accounted for are described. In some embodiments, the raw material can take the form of powdered metal. The powdered metal can have any number of variations including the following: particle size variation, contamination, particle composition and particle shape. Prior to utilizing the powders in an additive manufacturing operation, the powders can be inspected for variations. Variations and inconsistencies in the powder can also be identified by monitoring an additive manufacturing with one or more sensors. In some embodiments, the additive manufacturing process can be adjusted in real-time to adjust for inconsistencies in the powdered metal.

Abstract: This disclosure describes an additive manufacturing system that includes a build plane having a first region and a second region. Multiple energy source can be positioned above the build plane and configured to direct energy into the first and second regions of the build plane. The system includes optical sensors configured to monitor an intensity of light emitted from the energy sources. A processor associated with the additive manufacturing system is configured to adjust the sensor outputs in response to the energy sources coming into close proximity.

Abstract: A system and a corresponding method of correcting temperature data from a non-imaging optical sensor involve collecting temperature data generated using the optical sensor. The temperature data describes temperature changes across a surface of a material during an additive manufacturing operation in which the material is heated by a heat source. The method includes estimating a size of a hot spot corresponding to a hottest region formed on the surface by the heat source; and estimating a size of a heated region corresponding to a locus of points within the field of view that contribute to the temperature data. The method further includes correcting the temperature data based on the estimated sizes of the hot spot and the heated region.

Abstract: An additive manufacturing system comprises an apparatus arranged to distribute layer of metallic powder across a build plane and a power source arranged to emit a beam of energy at the build plane and fuse the metallic powder into a portion of a part. The system includes a processor configured to steer the beam of energy across the build plane and receive data generated by one or more sensors that detect electromagnetic energy emitted from the build plane when the beam of energy fuses the metallic powder. The received data is converted into one or more parameters that indicate one or more conditions at the build plane while the beam of energy fuses the metallic powder. The one or more parameters are used as input into a machine learning algorithm to detect one or more defects in the fused metallic powder.

Abstract: The disclosed embodiments relate to the monitoring and control of additive manufacturing. In particular, a method is shown for removing errors inherent in thermal measurement equipment so that the presence of errors in a product build operation can be identified and acted upon with greater precision. Instead of monitoring a grid of discrete locations on the build plane with a temperature sensor, the intensity, duration and in some cases position of each scan is recorded in order to characterize one or more build operations.

Abstract: An optical manufacturing process sensing and status indication system is taught that is able to utilize optical emissions from a manufacturing process to infer the state of the process. In one case, it is able to use these optical emissions to distinguish thermal phenomena on two timescales and to perform feature extraction and classification so that nominal process conditions may be uniquely distinguished from off-nominal process conditions at a given instant in time or over a sequential series of instants in time occurring over the duration of the manufacturing process. In other case, it is able to utilize these optical emissions to derive corresponding spectra and identify features within those spectra so that nominal process conditions may be uniquely distinguished from off-nominal process conditions at a given instant in time or over a sequential series of instants in time occurring over the duration of the manufacturing process.

Abstract: An additive manufacturing system includes a work region having a layer of metallic powder distributed across at least a portion of the work region. The system further includes a power source, a scanning and focusing system and a processor. The processor is configured to control the power source to emit a beam of energy at a power level and to manipulate the beam of energy across the work region in a plurality of build tracks to form a part from the fused metallic powder. The processor further determines a cooling rate at a termination of each of the plurality of build tracks and controls the power level of the power source in response to the determined cooling rate.

Abstract: This invention teaches a quality assurance system for additive manufacturing. This invention teaches a multi-sensor, real-time quality system including sensors, affiliated hardware, and data processing algorithms that are Lagrangian-Eulerian with respect to the reference frames of its associated input measurements. The quality system for Additive Manufacturing is capable of measuring true in-process state variables associated with an additive manufacturing process, i.e. those in-process variables that define a feasible process space within which the process is deemed nominal. The in-process state variables can also be correlated to the part structure or microstructure and can then be useful in identifying particular locations within the part likely to include defects.