Methods and apparatus for sensor-assisted part development in additive manufacturing
Methods and apparatus for sensor-based part development are disclosed. An example apparatus includes at least one memory, instructions in the apparatus, and processor circuitry to execute the instructions to identify a reference process observable of a computer-generated part, receive input from at least one sensor during three-dimensional printing to identify an estimated process observable using feature extraction, and adjust at least one three-dimensional printing process parameter to reduce an error identified from a mismatch between the estimated process observable and the reference process observable.
1 . An apparatus, comprising:
at least one memory;
instructions in the apparatus; and
processor circuitry to execute the instructions to:
identify a reference process observable of a computer-generated part based on a voxelized reference map, the voxelized reference map corresponding to a mapping of voxels representative of three-dimensional (3D) units of an input image, the voxelized reference map determined based on a drill down model identifying a vertical distance from a voxel to a printing powder of a three-dimensional printer;
receive an image input from at least one sensor during three-dimensional printing;
perform feature extraction from the image input using a machine learning model to identify an estimated process observable, the machine learning model trained based on data from one or more three-dimensional printer sensors; and
adjust at least one three-dimensional printing process parameter of the three-dimensional printer to reduce an error identified from a mismatch between the estimated process observable and the reference process observable.
2 . The apparatus of claim 1 , wherein the processor circuitry is to identify the reference process observable based on a material property or a geometric feature of the computer-generated part.
3 . The apparatus of claim 1 , wherein the reference process observable or the estimated process observable is at least one of a meltpool width, a meltpool depth, a meltpool height, a temperature profile, or a cooling rate.
4 . The apparatus of claim 1 , wherein, when the reference process observable is a meltpool characteristic, the processor circuitry is to extract meltpool features, in real-time or offline, using the at least one sensor.
5 . The apparatus of claim 1 , wherein the processor circuitry is to adjust the at least one three-dimensional printing process parameter based on at least one of a real-time feedback implementation, a layer-to-layer feedback implementation, or a build-to-build feedback implementation.
6 . The apparatus of claim 5 , wherein the processor circuitry is to obtain (1) first estimated process observable information from a previous build using the build-to-build feedback implementation and (2) second estimated process observable information from a previous layer of a same build using the layer-to-layer feedback implementation.
7 . The apparatus of claim 1 , wherein the at least one three- dimensional printing process parameter includes at least one of a power, a speed, a focus, a beam shape, or an energy density.
8 . The apparatus of claim 1 , wherein the at least one sensor includes an on-axis sensor or an off-axis sensor.
9 . A method, comprising:
identifying a reference process observable of a computer-generated part based on a voxelized reference map, the voxelized reference map corresponding to a mapping of voxels representative of three-dimensional (3D) units of an input image, the voxelized reference map determined based on a drill down model identifying a vertical distance from a voxel to a printing powder of a three-dimensional printer;
receiving an image input from at least one sensor during three-dimensional printing;
performing feature extraction from the image input using a machine learning model to identify an estimated process observable, the machine learning model trained based on data from one or more three-dimensional printer sensors; and
adjusting at least one three-dimensional printing process parameter of the three-dimensional printer to reduce an error identified from a mismatch between the estimated process observable and the reference process observable.
10 . The method of claim 9 , further including identifying the reference process observable based on a material property or a geometric feature of the computer-generated part.
11 . The method of claim 9 , wherein the reference process observable or the estimated process observable is at least one of a meltpool width, a meltpool depth, a meltpool height, a temperature profile, or a cooling rate.
12 . The method of claim 9 , further including, when the reference process observable is a meltpool characteristic, extracting meltpool features, in real-time or offline, using the at least one sensor.
13 . The method of claim 9 , further including adjusting the at least one three-dimensional printing process parameter based on at least one of a real-time feedback implementation, a layer-to-layer feedback implementation, or a build-to-build feedback implementation.
14 . The method of claim 13 , further including (1) obtaining first estimated process observable information from a previous build using the build-to-build feedback implementation and (2) obtaining second estimated process observable information from a previous layer of a same build using the layer-to-layer feedback implementation.
15 . The method of claim 9 , wherein the at least one three-dimensional printing process parameter includes at least one of a power, a speed, a focus, a beam shape, or an energy density.
16 . The method of claim 9 , wherein the at least one sensor includes an on-axis sensor or an off-axis sensor.
17 . A non-transitory computer readable storage medium comprising instructions that, when executed, cause a processor to at least:
identify a reference process observable based on a computer-generated part based on a voxelized reference map, the voxelized reference map corresponding to a mapping of voxels representative of three-dimensional (3D) units of an input image, the voxelized reference map determined based on a drill down model identifying a vertical distance from a voxel to a printing powder of a three-dimensional printer;
receive an image input from at least one sensor during three-dimensional printing;
perform feature extraction from the image input using a machine learning model to identify an estimated process observable, the machine learning model trained based on data from one or more three-dimensional printer sensors; and
adjust at least one three-dimensional printing process parameter of the three-dimensional printer to reduce an error identified from a mismatch between the estimated process observable and the reference process observable.
18 . The non-transitory computer readable storage medium of claim 17 , wherein the processor is to identify the reference process observable based on a material property or a geometric feature of the computer-generated part.
19 . The non-transitory computer readable storage medium of claim 17 , wherein the processor is to adjust the at least one three-dimensional printing process parameter based on at least one of a real-time feedback implementation, a layer-to-layer feedback implementation, or a build-to-build feedback implementation.
20 . The non-transitory computer readable storage medium of claim 19 , wherein the processor is to obtain (1) first estimated process observable information from a previous build using the build-to-build feedback implementation and (2) second estimated process observable information from a previous layer of a same build using the layer-to-layer feedback implementation.