System and methods for determining a quality score for a part manufactured by an additive manufacturing machine

Patent metadata

Field	Value
Publication number	US-11580430-B2
Application number	US-201916257367-A
Country	US
Kind code	B2
Filing date	Jan 25, 2019
Priority date	Jan 25, 2019
Publication date	Feb 14, 2023
Grant date	Feb 14, 2023

Abstract

Determining a quality score for a part manufactured by an additive manufacturing machine based on build parameters and sensor data without the need for extensive physical testing of the part. Sensor data is received from the additive manufacturing machine during manufacture of the part using a first set of build parameters. The first set of build parameters is received. A first algorithm is applied to the first set of build parameters and the received sensor data to generate a quality score. The first algorithm is trained by receiving a reference derived from physical measurements performed on at least one reference part built using a reference set of build parameters. The quality score is output via the communication interface of the device.

First claim

What is claimed is:

1. A method, comprising:
manufacturing a first part with an additive manufacturing machine using a first set of build parameters;
measuring, by at least one sensor configured to measure parameters of a process of manufacturing a part with the additive manufacturing machine, sensor data during manufacture of the first part using a first set of build parameters;
determining a quality score using a first algorithm applied to at least the received sensor data, wherein the first algorithm is trained by receiving a reference derived from physical measurements performed on at least one reference part built using a reference set of build parameters;
determining a second set of build parameters using a second algorithm applied to the received sensor data and the determined quality score, the second algorithm being trained to determine a set of build parameters that improve the quality score; and
manufacturing a second part with the additive manufacturing machine using the second set of build parameters.

2. The method of claim 1 , further comprising:
receiving the first set of build parameters,
wherein the first algorithm is applied to the received sensor data and the first set of build parameters to generate the quality score.

3. The method of claim 2 , wherein the reference relates a quantity of at least one anomaly type to the reference set of build parameters.

4. The method of claim 2 , wherein the reference relates a quantity of the at least one anomaly type to a reference set of sensor data measured during manufacture of the reference part using the reference set of build parameters.

5. The method of claim 4 , wherein the reference comprises coordinates for plotting the density of the at least one anomaly type relative to the reference set of sensor data.

6. The method of claim 4 , wherein the reference comprises coefficients of a function relating the density of the at least one anomaly type to the reference set of sensor data.

7. The method of claim 2 , further comprising:
generating thermal data based on a thermal model of the first part derived from the first set of build parameters.

8. The method of claim 7 , further comprising:
determining a the second set of build parameters using the second algorithm applied to the received sensor data, the determined quality score, and the thermal data, the second algorithm being trained to improve the quality score.

9. The method of claim 1 , wherein the at least one sensor includes of an actuator sensor, a melt pool sensor, and an environmental sensor.

10. A system, comprising:
an additive manufacturing machine configured to manufacture a part using a set of build parameters;
at least one sensor configured to generate sensor data measuring parameters of a process of manufacturing a part by the additive manufacturing machine;
a device comprising a communication interface and a processor configured to perform operations including:
receiving, via the communication interface of the device, sensor data from the at least one sensor during manufacture of a first part by the additive manufacturing machine using a first set of build parameters;
determining a quality score using a first algorithm applied to at least the received sensor data, wherein the first algorithm is trained by receiving a reference derived from physical measurements performed on at least one reference part built using a reference set of build parameters;
determining a second set of build parameters using a second algorithm applied to the received sensor data and the determined quality score, the second algorithm being trained to determine a set of build parameters that improve the quality score; and
outputting the second set of build parameters to the additive manufacturing machine.

11. The system of claim 10 , wherein the processor is further configured to perform:
receiving the first set of build parameters,
wherein the first algorithm is applied to the received sensor data and the first set of build parameters to generate the quality score.

12. The system of claim 11 , wherein the reference relates a quantity of at least one anomaly type to the reference set of build parameters.

13. The system of claim 11 , wherein the reference relates a quantity of at least one anomaly type to a reference set of sensor data measured during manufacture of the reference part using the reference set of build parameters.

14. The system of claim 11 , wherein the processor is further configured to perform:
generating thermal data based on a thermal model of the part derived from the first set of build parameters.

15. The system of claim 14 , further comprising:
Determining the second set of build parameters using the second algorithm applied to the received sensor data, the determined quality score, and the thermal data, the second algorithm being trained to improve the quality score.

16. A non-transitory computer-readable medium storing program instructions that when executed, in a device comprising a communication interface and a processor, cause the processor to perform a method comprising:
receiving sensor data from an additive manufacturing machine during manufacture of a first part using a first set of build parameters;
determining a quality score using a first algorithm applied to at least the received sensor data, wherein the first algorithm is trained by receiving a reference derived from physical measurements performed on at least one reference part built using a reference set of build parameters;
determining a second set of build parameters using a second algorithm applied to the received sensor data and the determined quality score, the second algorithm being trained to determine a set of build parameters that improve the quality score; and
outputting the second set of build parameters to the additive manufacturing machine.

17. The computer readable medium of claim 16 , wherein the performed method further comprises:
receiving the first set of build parameters,
wherein the first algorithm is applied to the received sensor data and the first set of build parameters to generate the quality score.

18. The computer readable medium of claim 17 , wherein the reference relates a quantity of at least one anomaly type to the reference set of build parameters.

19. The computer readable medium of claim 17 , wherein the reference relates a quantity of the at least one anomaly type to a reference set of sensor data measured during manufacture of the reference part using the reference set of build parameters.

20. The computer readable medium of claim 17 , wherein the performed method further comprises:
generating thermal data based on a thermal model of the first part derived from the first set of build parameters.

Assignees

• Gen Electric

Inventors

• Salasoo Lembit
• Gupta Vipul K
• Ping Xiaohu
• Roychowdhury Subhrajit
• Gambone Jr Justin
• Iyer Naresh
• Shi Xiaolei
• Wang Mengli

Classifications

• B22F10/368

  Temperature or temperature gradient, e.g. temperature of the melt pool · CPC title

• B22F10/85

  for controlling or regulating additive manufacturing processes · CPC title

• B22F10/366

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

• G06N7/00 Primary

  Computing arrangements based on specific mathematical models · CPC title

• B22F10/64

  by thermal means (control of energy beam parameters for post heating B22F10/364) · CPC title