Rolls-Royce North American Technologies Inc.

Rolls-Royce Corporation

Commonwealth Center for Advanced Manufacturing

Marshall Louis Sweet

Benjamin Joseph Zimmerman

Matthew R Gold

Keith Bourne

Frol Periverzov

Taylor K Blair

Michael Cybulsky

Andrea Marcon

An example method that includes receiving, by a computing device, a geometry of the component that includes a plurality of locations on a surface of the component; determining, by the computing device, a respective target thickness of the coating for each respective location of the plurality of locations based on a target coated component geometry and the geometry of the component; and determining, by the computing device, a number of passes or velocity of a coating device for each respective position of a plurality of positions to achieve the respective target thickness for each respective location.

Adaptive control of coating thickness

An example method that includes receiving a first geometry of a component in an uncoated state and a second geometry of the component in a coated state; determining a first difference between the second geometry and a first simulated geometry based on the first geometry and a first spray law comprising a plurality of first spray law parameters; iteratively adjusting at least one first spray law parameter to determine a respective subsequent spray law; iteratively determining a respective subsequent difference between the second geometry and a subsequent simulated geometry based on the first geometry and the subsequent respective spray law; selecting a subsequent spray law from the respective subsequent spray laws based on the respective subsequent differences; and controlling a coating process based on the selected subsequent spray law.

An example system includes at least one acoustic sensor and one optical sensor to monitor a thermal spray system controlled by a plurality of control parameters and performing a process associated with a plurality of process outputs. The system includes a computing device including a machine learning module and a control module. The machine learning module is configured to determine, based on at least the plurality of control parameters, an at least one time-dependent acoustic data signal, an at least one image data signal, and the plurality of process outputs, a relationship between the plurality of control parameters and the plurality of process outputs by machine learning. The control module is configured to control the thermal spray system to adjust the plurality of process outputs toward a plurality of respective operating ranges.

System control based on acoustic and image signals

Growing community of inventors

Midlothian, VA, United States of America

Marshall Louis Sweet