Defect identification using machine learning in an additive manufacturing system

An additive manufacturing system comprising:

• a recoater arm arranged to distribute layer of metallic powder across a build plane;
• a power source arranged to emit a beam of energy at the build plane and fuse the metallic powder into a portion of a part;
• and
• a processor configured to:
• access a part geometry for the part;
• steer the beam of energy across the build plane based on the part geometry;
• receive data generated by one or more sensors that detect electromagnetic energy emitted from the build plane when the beam of energy fuses the metallic powder;
• convert the received data into one or more parameters that indicate one or more conditions at the build plane while the beam of energy fuses the metallic powder;
• select a machine learning algorithm based on at least in part on the part geometry;
• use the one or more parameters as input into the machine learning algorithm to generate an output from the machine learning algorithm;
• and
• use the output of the machine learning algorithm to detect one or more defects in the fused metallic powder.