Continuous casting parameter value and set-up condition determination using artificial intelligence
AssigneeWagstaff, Inc.
InventorCraig Lee Shaber
Life of this patent
Estimating the term…
Loading patent…
AssigneeWagstaff, Inc.
InventorCraig Lee Shaber
Estimating the term…
Provided herein is a system and method for parameter value determination of direct chill casting using artificial intelligence. The system may employ one or more image sensors configured to capture images of a surface of a direct chill cast billet or ingot, where the images depict one or more casting anomalies. A first machine learning model configured to process images is configured to identify, within the images, casting anomalies along with metrics of the casting anomalies or anomalies can be directly input to the first machine learning model. The casting anomalies are identified by the first machine learning model, classified through conditional statements according to anomaly type and scale. A second machine learning model is configured to process the casting anomaly type and scale as an input along with most parameters and set-up conditions that can cause the anomaly to generate changes to parameter values of the direct chill casting process to reduce or eliminate the casting anomalies.
A method of parameter value determination for direct chill casting comprising:
A method of parameter value determination for direct chill casting comprising:
An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and computer program code configured to, with the processor, cause the apparatus to at least:
Dependencies are inferred from the claim text.