Methods and apparatus for sensor-assisted part development in additive manufacturing

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.

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.