A three-dimensional fabricating apparatus includes a fabrication chamber, a supply chamber, a flattening unit, and a controller. In the fabrication chamber, powder is layered to form a powder layer and bonded together in a desired shape to form a layered fabrication object. The supply chamber stores the powder. The flattening unit is reciprocally movable above the supply chamber and the fabrication chamber, to transfer the powder and flatten the powder in the fabrication chamber to form the powder layer. The controller is configured to control the flattening unit to move in a first direction to transfer and supply the powder from the supply chamber to the fabrication chamber. The controller is configured to control the flattening unit to move in a second direction opposite the first direction to form the powder layer and transfer an unused portion of the powder from the fabrication chamber to the supply chamber.

Method, and corresponding system, for producing an alert during manufacture of a part formed by a plurality of layers. The method includes determining the sensor data values at the working tool positions of each of the plurality of layers based on a correlation of the values of the sensor data relative to time and the working tool positions of each of the plurality of layers relative to time. During the manufacturing process, the sensor data values at the working tool positions of at least one of the plurality of layers are compared to reference data values at the working tool positions for the at least one layer to determine a comparison measure for the at least one layer. An alert is transmitted if the determined comparison measure of a layer is not within a defined range. A defined action is applied to the manufacturing process based on the transmitted alert.

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.

An NC device includes an additive manufacturing execution unit that controls an additive manufacturing process for producing a shaped object by stacking layers of a material melted, a subtractive manufacturing execution unit that controls a subtractive manufacturing process for cutting the shaped object using a tool, a status analysis unit that analyzes a machining status of the shaped object based on sensor data obtained by monitoring of the machining status of the shaped object produced by a combination of the additive and subtractive manufacturing processes, a production process change unit that outputs, to the additive and subtractive manufacturing execution units, a switching command that commands switching a production process, based on the analysis of the machining status, and a process condition generation unit that determines a process condition to be used in a production process after switching, based on a process condition used before the switching.

A method of calibrating a scanner of an additive manufacturing apparatus, in which an energy beam is directed with the scanner to consolidate material in a working plane to build up a workpiece in a layer-by-layer manner. The method includes directing the energy beam with the scanner across a test surface in the working plane to form a test pattern, the test pattern having at least one periodic feature, capturing an image of the test pattern, determining from the image a periodic property of the test pattern and determining correction data for control of the scanner based upon the periodic property.

Method, and corresponding system, for producing an alert during manufacture of a part formed by a plurality of layers. The method includes determining the sensor data values at the working tool positions of each of the plurality of layers based on a correlation of the values of the sensor data relative to time and the working tool positions of each of the plurality of layers relative to time. During the manufacturing process, the sensor data values at the working tool positions of at least one of the plurality of layers are compared to reference data values at the working tool positions for the at least one layer to determine a comparison measure for the at least one layer. An alert is transmitted if the determined comparison measure of a layer is not within a defined range. A defined action is applied to the manufacturing process based on the transmitted alert.

Methods and apparatus for two-dimensional and three-dimensional scanning path visualization are disclosed. An example apparatus includes at least one memory, instructions in the apparatus, and processor circuitry to execute the instructions to identify at least one melt pool dimension using a beam parameter setting, the at least one melt pool dimension identified from a plurality of melt pool dimensions obtained by varying the beam parameter setting, identify a response surface model based on the plurality of melt pool dimensions to determine an effect of variation in the beam parameter setting on the at least one melt pool dimension, output a three-dimensional model of a scanning path for an additive manufacturing process using the response surface model, and adjust the beam parameter setting based on the three-dimensional model to identify a second beam parameter setting.

The present disclosure provides methods of defining internal secondary structures of an object to be formed at least in part by additive manufacturing. The object may include a primary structure having a volume. The methods may include applying a balancing parameter within an axis-aligned bounding box that encompasses the primary structure. The methods may further include refining the balancing parameter until the volume is delimited into a plurality of the internal structures. The plurality of internal structures may be oriented at an angle to a global z-axis that is substantially parallel to a build direction, such as angled in a range of 40 degrees to 70 degrees to the z-axis.

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.

A method and an apparatus for additive manufacturing pertaining to high efficiency, energy beam patterning and beam steering to effectively and efficiently utilize the source energy. In one embodiment recycling and reuse of unwanted light includes a source of multiple light patterns produced by one or more light valves, with at least one of the multiple light patterns being formed from rejected patterned light. An image relay is used to direct the multiple light patterns, and a beam routing system receives the multiple light patterns and respectively directs them toward defined areas on a powder bed.