Systems and methods for receiving sensor data for an operating manufacturing machine and producing an alert during manufacture of a part

Patent metadata

Field	Value
Publication number	US-9977425-B1
Application number	US-201715649871-A
Country	US
Kind code	B1
Filing date	Jul 14, 2017
Priority date	Jul 14, 2017
Publication date	May 22, 2018
Grant date	May 22, 2018

Abstract

Method, and corresponding system, for producing an alert during manufacture of a part formed by a plurality of layers. The method includes determining the sensor data values at the working tool positions of each of the plurality of layers based on a correlation of the values of the sensor data relative to time and the working tool positions of each of the plurality of layers relative to time. During the manufacturing process, the sensor data values at the working tool positions of at least one of the plurality of layers are compared to reference data values at the working tool positions for the at least one layer to determine a comparison measure for the at least one layer. An alert is transmitted if the determined comparison measure of a layer is not within a defined range. A defined action is applied to the manufacturing process based on the transmitted alert.

First claim

The invention claimed is:

1. A method for receiving sensor data for an operating manufacturing machine and producing an alert during manufacture of a part formed by a plurality of layers, the method comprising:
receiving, at a first server, the sensor data from a sensor for the operating machine;
determining, using a processor of the first server, values of the sensor data relative to time;
determining, using the processor of the first server, working tool positions relative to time based on process data which controls operation of the manufacturing machine, the process data comprising vectors defining the working tool positions of each of the plurality of layers during a manufacturing process;
determining the sensor data values at the working tool positions of each of the plurality of layers based on a correlation of the values of the sensor data relative to time and the working tool positions of each of the plurality of layers relative to time;
comparing, during the manufacturing process, the sensor data values at the working tool positions of at least one of the plurality of layers to reference data values at the working tool positions for the at least one layer to determine a comparison measure for the at least one layer;
transmitting an alert if the determined comparison measure of a layer is not within a defined range; and
applying a defined action to the manufacturing process based on the transmitted alert.

2. The method of claim 1 , further comprising, before the comparing, applying a probabilistic function to the reference data values at the working tool positions for the at least one layer.

3. The method of claim 1 , further comprising:
receiving, at a second server, the sensor data values at the working tool positions of a fabricated layer;
receiving image data produced at the manufacturing machine for the fabricated layer; and
correlating the image data to the working tool positions of the fabricated layer.

4. The method of claim 3 , wherein the correlating of the image data to the working tool positions comprises converting high intensity lines of the image data into vectors.

5. The method of claim 3 , further comprising comparing, during the manufacturing process, the image data of at least one of the plurality of layers to reference image data for the at least one layer to determine a second comparison measure for the at least one layer.

6. The method of claim 5 , wherein the reference image data of the at least one layer are determined by analysis of a reference part.

7. The method of claim 1 , further comprising:
outputting the comparison measure for the at least one layer to an analytic model of the manufacturing machine;
receiving, from the analytic model of the manufacturing machine, adjusted process data, the adjusted process data being determined based at least in part on the analytic model and the comparison measure for the at least one layer, the analytic model being based at least in part on a measured characteristic of the manufacturing machine; and
using the adjusted process data to control the operation of the manufacturing machine.

8. The method of claim 1 , wherein the reference data values at the working tool positions of the at least one layer are determined by analysis of a reference part.

9. The method of claim 8 , wherein the reference data values at the working tool positions of the at least one layer are determined based on a correlation of values of sensor data relative to time measured for the reference part and working tool positions of a corresponding layer of the reference part relative to time, and
the working tool positions of the corresponding layer of the reference part relative to time are determined based on process data comprising vectors defining the working tool positions of the corresponding layer of the reference part during a manufacturing process of the reference part.

10. The method of claim 1 , wherein the method further comprises transmitting the alert via a network to at least one user interface device.

11. The method of claim 1 , wherein the alert identifies the layer for which the alert was produced.

12. The method of claim 1 , wherein the defined action is halting the manufacturing process.

13. A method for receiving sensor data for an operating manufacturing machine and producing an alert during manufacture of a part formed by a plurality of layers, the method comprising:
receiving, at a first server, the sensor data from a sensor for the operating machine;
determining, using a processor of the first server, values of the sensor data relative to time;
determining, using the processor of the first server, working tool positions relative to time based on process data which controls operation of the manufacturing machine, the process data comprising vectors defining the working tool positions of each of the plurality of layers during a manufacturing process;
determining the sensor data values at the working tool positions of each of the plurality of layers based on a correlation of the values of the sensor data relative to time and the working tool positions of each of the plurality of layers relative to time;
determining a quality score of at least one of the plurality of layers using a machine learning algorithm, the machine learning algorithm being trained based at least in part on sensor data from another machine manufacturing a same part;
comparing, during the manufacturing process, the quality score of at least one of the plurality of layers to a quality threshold for the at least one layer to determine a comparison measure for the at least one layer;
transmitting an alert if the determined comparison measure of a layer is not within a defined range; and
applying a defined action to the manufacturing process based on the transmitted alert.

14. A system for receiving sensor data for an operating manufacturing machine and producing an alert during manufacture of a part formed by a plurality of layers, the system comprising:
a first server having a processor configured to perform:
receiving, at a first server, the sensor data from a sensor for the operating machine;
determining, using a processor of the first server, values of the sensor data relative to time;
determining, using the processor of the first server, working tool positions relative to time based on process data which controls operation of the manufacturing machine, the process data comprising vectors defining the working tool positions of each of the plurality of layers during a manufacturing process;
determining the sensor data values at the working tool positions of each of the plurality of layers based on a correlation of the values of the sensor data relative to time and the working tool positions of each of the plurality of layers relative to time;
comparing, during the manufacturing process, the sensor data values at the working tool positions of at least one of the plurality of layers to reference data values at the working tool positions for the at least one layer to determine a comparison measure for the at least one layer;
transmitting an alert if the determined comparison measure of a layer is not within a defined range; and
applying a defined action to the manufacturing process based on the transmitted alert.

15. The system of claim 14 , wherein the first server is further configured to perform, before the comparing, applying a probabilistic function to the reference data values at the working tool positions for the at least one layer.

16. The system of claim 15 , wherein the correlating of the image data to the working tool

Assignees

• Gen Electric

Inventors

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

Classifications

• B22F12/90

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

• B22F10/85

  for controlling or regulating additive manufacturing processes · CPC title

• B22F10/38

  to achieve specific product aspects, e.g. surface smoothness, density, porosity or hollow structures · CPC title

• B22F10/368

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

• B22F10/28

  Powder bed fusion, e.g. selective laser melting [SLM] or electron beam melting [EBM] · CPC title