Quality assessment feedback control loop for additive manufacturing

A non-transitory computer-readable medium having stored thereon executable instructions when executed by a processor unit cause the processor unit to perform a method of additive manufacturing machine (AMM) control, the AMM configured to manufacture a part, the method comprising:

• obtaining AMM machine and process parameter settings as a physical conditions goal for the AMM for an ongoing build process;
• accessing sensor data for a set of monitored physical conditions in the AMM;
• calculating a respective difference between the physical conditions goal for the AMM and respective elements of the set of monitored physical conditions;
• providing the AMM machine and process parameter settings, the set of monitored physical conditions, and the respective differences to one or more material property prediction models;
• computing a respective predicted value for one or more material properties for the part;
• wherein the respective predicted value is a function of the AMM machine and process parameter settings plus their respective difference from the respective elements of the set of monitored physical conditions;
• comparing the respective predicted value to the respective predetermined target range for the one or more material properties for the part;
• based on a determination that each respective predicted value is within the respective predetermined target range, maintaining the AMM machine and process parameter settings;
• based on a determination that one or more of the respective predicted value is outside the respective predetermined target range, generating commands to compensate the AMM machine and process parameter settings;
• and repeating a closed feedback loop at intervals of time during the build process.

A system comprising:

• an additive manufacturing machine (AMM) having a control unit including a processor and a memory unit, the AMM configured to manufacture a part;
• the memory unit including executable instructions that cause the processor to perform a method, the method including:
• obtaining AMM machine and process parameter settings as a physical conditions goal for the AMM for an ongoing build process;
• accessing sensor data for a set of monitored physical conditions in the AMM;
• calculating a respective difference between the physical conditions goal for the AMM and respective elements of the set of monitored physical conditions;
• providing the AMM machine and process parameter settings, the set of monitored physical conditions, and the respective differences to one or more material property prediction models;
• computing a respective predicted value for one or more material properties for the part;
• wherein the respective predicted value is a function of the AMM machine and process parameter settings plus their respective difference from the respective elements of the set of monitored physical conditions;
• comparing the respective predicted value to a respective predetermined target range for the one or more material properties for the part;
• based on a determination that each respective predicted value is within the respective predetermined target range, maintaining the AMM machine and process parameter settings;
• based on a determination that one or more of the respective predicted value is outside the predetermined respective predetermined target range, generating commands to compensate the AMM machine and process parameter settings;
• and
• repeating a closed feedback loop at intervals of time during the build process.