Abstract: In an example, a tangible machine-readable medium stores instructions which, when executed by a processor, cause the processor to evaluate a plurality of possible object generation arrangements based on a default separation distance and an enhanced separation distance, wherein the enhanced separation distance is used to assess predefined object sub-portions.

Abstract: In an example, a method includes determining a training dataset for an inference model to evaluate spatial arrangements of objects to be generated in additive manufacturing. Determining the training dataset may include obtaining, by at least one processor, a temperature distribution for each of a plurality of spatial arrangements of objects to be generated in additive manufacturing. The method may further include obtaining, using at least one processor, an indication of thermal interaction for each spatial arrangement based on the obtained temperature distribution.

Abstract: Examples of the present disclosure relate to a method for packing three dimensional (3D) models. The method comprises identifying a plurality of sections of each 3D model according to curvature profiles of the sections; associating a build material layer thickness to each section of the plurality of sections, whereby each associated build material layer thickness is one of a set of pre-established build material layer thicknesses; packing the plurality of 3D models according to each associated build material layer thickness, whereby packing comprises spatially arranging at least some 3D models in the 3D virtual build volume according to one or more criteria, such that at least some of the sections of different 3D models associated to a same build material layer thickness are arranged in a same region of the 3D virtual build volume.

Abstract: An example method includes acquiring, by at least one processor, (i) an indication of measured dimensions of objects generated in a common additive manufacturing build operation, wherein the objects include at least one instance of a first object generated based on first object model data and at least one instance of a second object based on second object model data; and (ii) an indication of the orientation of the measured dimensions. Vector components for each of the measured dimensions may be determined based on the indication of the orientation. A first geometrical compensation for use in modifying the first object model data may be determined based on the measured dimensions and the vector components relating to the first object and a second geometrical compensation for use in modifying the second object model data may be determined based on the measured dimensions and the vector components relating to the second object.

Abstract: In an example, a method may include obtaining a first measurement of a first object generated using additive manufacturing apparatus based on object model data and obtaining a second measurement of a second object generated using the additive manufacturing apparatus based on object model data to which a first geometrical compensation parameter has been applied. An effect of the first geometrical compensation parameter may be determined based on the first and second measurements and, based on the determined effect, the first geometrical compensation parameter may be evaluated.

Abstract: Examples of the present disclosure relate to a method for packing three dimensional (3D) models. The method comprises identifying a plurality of sections of each 3D model according to curvature profiles of the sections; associating a build material layer thickness to each section of the plurality of sections, whereby each associated build material layer thickness is one of a set of pre-established build material layer thicknesses; packing the plurality of 3D models according to each associated build material layer thickness, whereby packing comprises spatially arranging at least some 3D models in the 3D virtual build volume according to one or more criteria, such that at least some of the sections of different 3D models associated to a same build material layer thickness are arranged in a same region of the 3D virtual build volume.

Abstract: In an example a tangible machine-readable medium stores instructions which, when executed by a processor, cause the processor to determine an object generation arrangement for additive manufacturing based on a separation distance between objects, wherein the separation distance varies based on an intended location of object generation.

Abstract: In an example, a tangible machine-readable medium stores instructions which, when executed by a processor, cause the processor to evaluate a plurality of possible object generation arrangements based on a default separation distance and an enhanced separation distance, wherein the enhanced separation distance is used to assess predefined object sub-portions.