Abstract: For viability determination with self-attention for process optimization, various process and state information in the manufacture (e.g., forming, assembling, and/or handling) of a part are embedded. A machine-learned model generates the embedding, which is used with self-attention similarity to identify similar cases based on the embedding. The model was trained using both regression for continuous information (e.g., variable names) in the embedding and classification for non-continuous information (e.g., value of a variable) in the embedding. By including both regression and classification, the same machine-learned model may be used for reliable and nuanced viability determination.

Abstract: In an embodiment, an X-ray imaging apparatus includes an X-ray radiation source to emit X-ray radiation, an object to be sampled being within a receiving region; a converter for spatially resolved conversion of X-ray radiation, after passing through the receiving region, into visible light; a detector, to emit a detector signal based upon visible light from the converter registered by the detector; a pattern generator, to realize a large number of light and shadow patterns (LSPs) in a time-staggered manner by acting on visible light generated by the converter, respective detector signals being generated based upon respective LSPs; and at least one processor, to generate the image of the object based upon the detector signals generated and an item of information about the LSPs. The pattern generator device is configured to generate the large number of LSPs by at least one of overriding and partial shadowing of the visible light.

Abstract: In an embodiment, an X-ray imaging apparatus includes an X-ray radiation source to emit X-ray radiation, an object to be sampled being within a receiving region; a converter for spatially resolved conversion of X-ray radiation, after passing through the receiving region, into visible light; a detector, to emit a detector signal based upon visible light from the converter registered by the detector; a pattern generator, to realize a large number of light and shadow patterns (LSPs) in a time-staggered manner by acting on visible light generated by the converter, respective detector signals being generated based upon respective LSPs; and at least one processor, to generate the image of the object based upon the detector signals generated and an item of information about the LSPs. The pattern generator device is configured to generate the large number of LSPs by at least one of overriding and partial shadowing of the visible light.