Neuro-fuzzy logic for controlling material addition processes

Patent metadata

Field	Value
Publication number	US-10406760-B2
Application number	US-201614988368-A
Country	US
Kind code	B2
Filing date	Jan 5, 2016
Priority date	Jan 6, 2015
Publication date	Sep 10, 2019
Grant date	Sep 10, 2019

Abstract

A method may include controlling, by a computing device, a directed energy deposition material addition (DED MA) technique based at least in part on a thermal model. The thermal model may define a plurality of default operating parameters for the DED MA technique. The method also may include detecting, by at least one sensor, at least one parameter related to the DED MA technique. Further, the method may include, responsive to determining, by the computing device, that a value of the at least one detected parameter is different from an expected value of a corresponding parameter predicted by the thermal model, determining, by the computing device and using a neuro-fuzzy algorithm, an updated value for at least one operating parameter for the DED MA technique, and controlling, by the computing device, the DED MA technique based at least in part on the updated value.

First claim

What is claimed is:

1. A method comprising:
controlling, by a computing device, a directed energy deposition material addition (DED MA) technique based at least in part on a thermal model of the DED MA technique for a component, wherein the thermal model defines a plurality of default operating parameters for the DED MA technique;
detecting, by at least one sensor comprising a thermal camera, at least one parameter comprising at least one of a melt pool geometry, a melt pool temperature, or a temperature of the component;
responsive to determining, by the computing device, that a value of the at least one detected parameter is different from an expected value of a corresponding parameter predicted by the thermal model, determining, by the computing device and using a neuro-fuzzy algorithm, an updated value for at least one operating parameter for the DED MA technique, wherein the neuro-fuzzy algorithm includes at least two fuzzy nodes in an adaptive network; and
controlling, by the computing device, the DED MA technique based at least in part on the updated value for the at least one operating parameter.

2. The method of claim 1 , wherein the plurality of default operating parameters comprise at least one of:
a power level of the energy source;
a focal spot size of an energy beam delivered adjacent to a surface of the component;
a material delivery rate;
relative movement of a focal spot of the energy beam relative to the component;
a pause time between bursts of energy;
a flow rate of gas adjacent to the component;
a position of a gas delivery device relative to the component;
an angle of an energy delivery head relative to the component;
a standoff between the focal spot and the surface of the component; or
a tool path followed by the energy delivery head.

3. The method of claim 1 , wherein the at least one detected parameter further comprises at least one of a geometry of the component, a surface feature geometry, or a presence of a defect.

4. The method of claim 1 , wherein the component comprises at least one of a gas turbine engine blade, a gas turbine engine blisk, or a gas turbine engine blisk drum.

5. The method of claim 1 , further comprising:
inputting a set of inputs from a training set to the neuro-fuzzy algorithm, wherein the at least two fuzzy nodes include node parameters;
evaluating outputs of the neuro-fuzzy algorithm against outputs of the training set; and
modifying at least one of the node parameters based on the evaluation of the outputs of the neuro-fuzzy algorithm.

6. A directed energy deposition material addition (DED MA) system comprising:
a material delivery device;
an energy source;
an energy delivery head;
at least one sensor comprising a thermal camera; and
a computing device, wherein the computing device is configured to:
control at least one of the material delivery device, the energy source, and the energy delivery head based at least in part on a thermal model of the DED MA technique for a component, wherein the thermal model defines a plurality of default operating parameters for the DED MA technique;
receive, from the at least one sensor comprising the thermal camera, a signal indicative of at least one parameter comprising at least one of a melt pool geometry, a melt pool temperature, or a temperature of a component;
responsive to determining that a value of the at least one detected parameter is different from an expected value of a corresponding parameter predicted by the thermal model, determine, using a neuro-fuzzy algorithm, an updated value for at least one operating parameter for the DED MA technique, wherein the neuro-fuzzy algorithm includes at least two fuzzy nodes in an adaptive network; and
control at least one of the material delivery device, the energy source, and the energy delivery head based at least in part on the updated value for the at least one operating parameter.

7. The DED MA system of claim 6 , wherein the plurality of default operating parameters comprise at least one of:
a power level of the energy source;
a focal spot size of an energy beam delivered by the energy delivery head adjacent to a surface of the component;
a rate at which the material delivery device delivers material;
relative movement of the energy delivery head relative to the component;
a pause time between bursts of energy generated by the energy source;
an angle of the energy delivery head relative to the component;
a standoff between the energy delivery head and the surface of the component; or
a tool path followed by an energy delivery head.

8. The DED MA system of claim 6 , further comprising a gas delivery device, and wherein the plurality of default operating parameters comprise at least one of
a flow rate of gas adjacent to the component; or
a position of a gas delivery device relative to the component.

9. The DED MA system of claim 6 , wherein the at least one detected parameter further comprises at least one of a geometry of the component a surface feature geometry, or a presence of a defect.

10. The DED MA system of claim 6 , wherein the component comprises at least one of a gas turbine engine blade, a gas turbine engine blisk, or a gas turbine engine blisk drum.

11. The DED MA system of claim 6 , wherein the computing device is further configured to:
receive a set of inputs from a training set to the neuro-fuzzy algorithm, wherein the at least two fuzzy nodes include node parameters;
evaluate outputs of the neuro-fuzzy algorithm against outputs of the training set; and
modify at least one of the node parameters based on the evaluation of the outputs of the neuro-fuzzy algorithm.

12. A non-transitory computer-readable storage medium comprising instructions that, when executed, cause at least one processor to:
control a directed energy deposition material addition (DED MA) technique based at least in part on a thermal model of the DED MA technique for a component, wherein the thermal model defines a plurality of default operating parameters for the DED MA technique;
receive, from at least one sensor comprising a thermal camera, a signal indicative of at least one parameter comprising at least one of a melt pool geometry, a melt pool temperature, or a temperature of a component;
responsive to determining that a value of the at least one detected parameter is different from an expected value of a corresponding parameter predicted by the thermal model, determine, using a neuro-fuzzy algorithm including at least two fuzzy nodes in an adaptive network, an updated value for at least one operating parameter for the DED MA technique; and
control the DED MA technique based at least in part on the updated value for the at least one operating parameter.

13. The non-transitory computer-readable storage medium of claim 12 , wherein the plurality of default operating parameters comprise at least one of:
a power level of the energy source;
a focal spot size of an energy beam delivered adjacent to a surface of the component;
a material delivery rate;
relative movement of a focal spot of the energy beam relative to the component;
a pause time between bursts of energy;
a flow rate of gas adjacent to the component;
a position of a gas delivery device relative to the component;
an angle of an energy delivery head relative to the component;
a standoff between the focal spot and the surface of the component; or
a tool path followed by an energy delivery head.

14. The non-transitory computer-readable storage medium of claim 12 , wherein the at least one detected parameter further comprises at least one of a geometry of the component, a me

Assignees

• Rolls Royce Corp

Inventors

• Shuck Quinlan Yee
• Ma Kong

Classifications

• B22F5/009 Primary

  of turbine components other than turbine blades (of turbine blades B22F5/04) · CPC title

• B22F10/322

  of the gas flow, e.g. rate or direction · CPC title

• B22F12/90

  Means for process control, e.g. cameras or sensors · CPC title

• B22F12/70

  Gas flow means · CPC title

• B22F12/20

  Cooling means · CPC title