Identifying and distributing optimal machine parameters within a fleet of additive manufacturing machines

Patent metadata

Field	Value
Publication number	US-10725459-B2
Application number	US-201715671823-A
Country	US
Kind code	B2
Filing date	Aug 8, 2017
Priority date	Aug 8, 2017
Publication date	Jul 28, 2020
Grant date	Jul 28, 2020

Abstract

Method, and corresponding system, for iteratively distributing improved process parameters to a fleet of additive manufacturing machines. The method includes receiving sensor data from a sensor for a first machine of the fleet of machines. The method further includes comparing the sensor data values at the working tool positions of the plurality of layers to reference data values at the working tool positions for the plurality of layers to determine a set of comparison measures for the first machine. The method further includes selecting a machine from among the first machine and at least a second machine of the fleet of machines based at least in part on the comparison measures of each of the machines. The method further includes receiving, from the selected machine, process parameters of the selected machine; and transmitting at least part of the process parameters of the selected machine to other machines of the fleet.

First claim

The invention claimed is:

1. A method comprising:
receiving, at a host server, sensor data captured of a plurality of machines within a fleet performing a manufacturing process;
receiving, at the host server, tool position data of the plurality of machines performing the manufacturing process;
correlating sensor data values and tool positions of a part being manufactured to render correlated sensor data, the sensor data values and the tool positions being correlated based on respective timing information included in the received sensor data and the received tool position data;
generating, for each of the plurality of machines performing the manufacturing process, a set of comparison measures by comparing the correlated sensor data to reference data values for a plurality of layers of the part;
determining an optimum-performing machine from among the plurality of machines based on the set of comparison measures generated for each of the plurality of machines, wherein the optimum-performing machine is determined as a machine from among the plurality of machines having a generated set of comparison measures that is closest to a defined goal for the sets of comparison measures;
distributing manufacturing process parameters of the optimum-performing machine to at least one other machine from among the plurality of machines of the fleet; and
manufacturing, by the at least one other machine of the fleet, a second part using the manufacturing process parameters of the optimum-performing machine.

2. The method of claim 1 , wherein the correlating comprises determining tool positions relative to time based on process data which controls operation of the plurality of machines, the process data comprising vectors defining the tool positions at each of the plurality of layers of the part being manufactured.

3. The method of claim 1 , wherein the correlating, the determining, and the distributing of the process parameters are iteratively repeated to reach a defined manufacturing performance goal for the plurality of machines.

4. The method of claim 1 , wherein the determining further comprises applying a probabilistic function to the reference data values at the tool positions of the plurality of layers of the part being manufactured.

5. The method of claim 1 , further comprising:
receiving image data produced at the plurality of machines during the manufacturing process and correlating the image data to the tool positions of the plurality of layers of the part being manufactured;
wherein the determining of the optimum-performing machine is further performed based on the correlated image data.

6. The method of claim 5 , wherein the determining is performed based on deviation values between an actual laser path indicated by the image data and a target laser path defined by reference image data.

7. The method of claim 6 , wherein the reference image data is determined by analysis of a reference part.

8. The method of claim 6 , wherein the reference image data is determined based on vectors of process data defining the tool positions of each of the plurality of layers of the part to be manufactured.

9. The method of claim 1 , wherein the process parameters include at least one of: process data defining the tool positions during manufacturing of the part, measurements of the operating environment of the optimum-performing machine, and operational settings of the optimum-performing machine.

10. A system comprising:
a storage configured to store reference data values for a part to be manufactured; and
a processor configured to perform:
receiving sensor data captured of a plurality of machines within a fleet performing a manufacturing process;
receiving tool position data of the plurality of machines performing the manufacturing process;
correlating sensor data values and tool positions of a part being manufactured to render correlated sensor data, the sensor data values and the tool positions being correlated based on respective timing information included in the received sensor data and the received tool position data;
generating, for each of the plurality of machines performing the manufacturing process, a set of comparison measures by comparing the correlated sensor data to reference data values for a plurality of layers of the part;
determining an optimum-performing machine from among the plurality of machines based on the set of comparison measures generated for each of the plurality of machines, wherein the optimum-performing machine is determined as a machine from among the plurality of machines having a generated set of comparison measures that is closest to a defined goal for the sets of comparison measures;
distributing manufacturing process parameters of the optimum-performing machine to at least one other machine from among the plurality of machines of the fleet; and
cause, by the at least one other machine of the fleet, a second part to be manufactured using the process parameters of the optimum-performing machine.

11. The system of claim 10 , wherein the processor is further configured to perform determining tool positions relative to time based on process data which controls operation of the plurality of machines, the process data comprising vectors defining the tool positions at each of the plurality of layers of the part being manufactured.

12. The system of claim 10 , wherein the correlating, the determining, and the distributing of the process parameters are iteratively repeated to reach a defined manufacturing performance goal for the plurality of machines.

13. The system of claim 10 , wherein the determining further comprises applying a probabilistic function to the reference data values at the tool positions of the plurality of layers of the part being manufactured.

14. The system of claim 10 , wherein the processor is further configured to perform:
receiving image data produced at the plurality of machines during the manufacturing process and correlating the image data to the tool positions of the plurality of layers of the part being manufactured; and
wherein the determining of the optimum-performing machine is further performed based on the correlated image data.

15. The system of claim 14 , wherein the determining is performed based on deviation values between an actual laser path indicated by the image data and a target laser path defined by reference image data.

16. The system of claim 15 , wherein the reference image data is determined by analysis of a reference part.

17. The system of claim 15 , wherein the reference image data is determined based on vectors of process data defining the tool positions of each of the plurality of layers of the part to be manufactured.

18. The system of claim 10 , wherein the process parameters include at least one of: process data defining the tool positions during manufacturing of the part, measurements of the operating environment of the optimum-performing machine, and operational settings of the optimum-performing machine.

19. A method comprising:
receiving manufacturing data of a plurality of machines performing a manufacturing process, the manufacturing data for each machine comprising sensor information measuring an attribute of the manufacturing process performed by a respective machine, and tool position information of the respective machine during the manufacturing process;
correlating the sensor information and the tool position information of a part being manufactured to render correlated sensor data,
generating, for each of the plurality of machines performing th

Assignees

• Gen Electric

Inventors

• Good Brandon
• Berlier Jacob
• Zhang Li
• Mccann Adam

Classifications

• B23K26/032 Primary

  using optical means · CPC title

• B22F12/90

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

• B22F10/85

  for controlling or regulating additive manufacturing processes · CPC title

• B22F10/30

  Process control · CPC title

• B22F10/366

  Scanning parameters, e.g. hatch distance or scanning strategy · CPC title