An additive manufacturing system includes an additive manufacturing (AM) device, a first sensor device, and a compute device. The AM device is configured to form a bulk component in a layer-by-layer manner, by at least iteratively depositing a first layer of raw material onto a working surface in a deposition chamber, consolidating the initial layer into an initial additive portion of the bulk component, then forming subsequent additive portions of the bulk component by depositing and consolidating a subsequent plurality of layers of the raw material onto the first additive portion. The first sensor device is configured to measure an actual composition of at least one first byproduct portion formed upon consolidation of one of the first or subsequent layers of raw material in the deposition chamber. The compute device includes a processor and a memory, and is communicatively coupled to the additive manufacturing device and first sensor device. The additive manufacturing device and compute device provide an in situ sensor analysis of the component while in a formation state during a build process by comparing an actual composition of the at least one first byproduct portion to an expected composition range stored in the memory.

Plant (1) for additively manufacturing at least one three-dimensional object (2), comprising at least one process station (3a-3c) being configured to perform an additive manufacturing process and/or at least one preprocessing process for an additive manufacturing process and/or at least one postprocessing process for an additive manufacturing process; at least one conveying device (19) configured to convey an item (20) between at least two positions (P1, P2) of the plant (1), the conveying device (19) comprising at least one conveying element (22), the at least one conveying element (22) being at least partially bound to ground (23), and at least one conveying carriage (24) being connectable or connected with the conveying element (22) so as to be moveable between at least two positions (P1, P2) of the plant (1), the at least one conveying carriage (24) comprising at least one supporting interface (25) for supporting at least one item (20).

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.

Method for operating an apparatus (1) for additively manufacturing three-dimensional objects (2) by means of successive layerwise selective irradiation and consolidation of layers of a build material (3) which can be consolidated by means of an energy beam (5), wherein at least one region in a build plane (6) is irradiated in the additive manufacturing process, wherein an interrupted state of the additive manufacturing process is determined and a defined amount of energy is deposited in at least one previously irradiated region (7, 8) of the build plane (6) in an interrupted state of the additive manufacturing process.

A powder-based additive manufacturing installation (10) comprises a powder layering device (14) that can be displaced along a path linking a start zone (A) and an end zone (B). The layering device (14) comprises powder smoothing means (35) for depositing powder in a powder deposition zone (P) situated between the start zone (A) and the end zone (B). The installation furthermore comprises a cleaning device (60) situated on the path of the layering device (14), the cleaning device (60) comprising a brushing device (62) for brushing at least one surface of the powder smoothing means (35).

A method for providing control data for manufacturing at least one three-dimensional object by means of a layer-wise solidification of a building material in an additive manufacturing apparatus is provided. The method includes at least the following steps: a) determining the locations corresponding to the cross section of the at least one object, b) determining at least two different regions to be solidified in said at least one layer, wherein said at least two regions are chosen from the group of: sandwiched region, down-facing region and up-facing region, c) defining a scanning sequence for the beam so as to solidify the building material at least at the locations corresponding to said portion of the cross section of the object, wherein at an interface between a first and a second region differing from each other a scan line of the beam is continuous and at least one beam parameter value is changed.

A method of providing a dataset for additive manufacturing includes collecting a first type of data for the dataset during the additive buildup of a at least one layer of a component to be manufactured, evaluating of the structural quality of the layer by the first type of data, modifying the first type of data in that fractions of the data representing an insufficient structural quality of the layer are deleted from the first type of data, and superimposing second type of data, to the first type of data, wherein the second type of data is suitable to support a validation of the structural quality of the as-manufactured component.

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.

A method, computing system, and one or more computer-readable storage media for fabricating full color three-dimensional objects are provided herein. The method includes transforming a three-dimensional model into instructions for a fabrication device by slicing the three-dimensional model into layers with color information preserved, generating two-dimensional polygons for each layer based on colors on faces, colors on textures, and/or gradient colors, and determining a tool path for fabricating an object from colored materials based on the two-dimensional polygons for each layer. Determining the tool path includes generating instructions that direct the fabrication device to apply colored material for all two-dimensional polygons of a same color before switching colors, smooth an exterior of the object by switching colors at an internal vertex of each two-dimensional polygon within each layer, and deposit transitional material within an infill area, a support structure, and/or an area outside the object when switching colors.

Methods and apparatus to identify additively manufactured parts are disclosed. An example apparatus includes a body, formed of layers layered substantially parallel to a base layer, composed of a first material having a first density, a first indicium embedded internally in the body as a void, and a second indicium on an external surface of the body, the second indicium aligning with the first indicium.