# US 11,079,739 B2 · Transfer learning/dictionary generation and usage for tailored part parameter generation from coupon builds

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,079,739 B2
- Document ID: US11079739B2
- Status: Granted
- Kind: B2
- Application number: 16/284,409
- Filed: 2019-02-25
- Published: 2020-08-27
- Granted: 2021-08-03
- Earliest claimed: 2019-02-25
- Assignees: General Electric Company
- Applicants: General Electric Company
- Inventors: Subhrajit Roychowdhury; Alexander Chen; Xiaohu Ping; John Erik Hershey
- Web page: https://patentgrep.com/patent/US11079739B2

## CPC

- G05B 19/4099: Surface or curve machining, making three-dimensional [3D] objects, e.g. desktop manufacturing
- B22F 10/36: of energy beam parameters
- B29C 64/386: Data acquisition or data processing for additive manufacturing
- B29C 64/393: for controlling or regulating additive manufacturing processes
- B33Y 50/00: Data acquisition or data processing for additive manufacturing
- B33Y 50/02: for controlling or regulating additive manufacturing processes
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- B22F 10/20: Direct sintering or melting
- B22F 10/28: Powder bed fusion, e.g. selective laser melting [SLM] or electron beam melting [EBM]
- B22F 10/30: Process control
- B22F 12/90: Means for process control, e.g. cameras or sensors
- B29C 64/153: using layers of powder being selectively joined, e.g. by selective laser sintering or melting
- B33Y 10/00: Processes of additive manufacturing
- G05B 2219/33034: Online learning, training
- G05B 2219/35134: 3-D cad-cam
- G05B 2219/49007: Making, forming 3-D object, model, surface
- G05B 2219/49018: Laser sintering of powder in layers, selective laser sintering SLS
- Y02P 10/25: Process efficiency
- Y02P 90/02: Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- B22F: WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER (making alloys by powder metallurgy C22C); APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
- B29C: SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING (making preforms B29B11/00; making laminated products by combining previously unconnected layers which become one product whose layers will remain together B32B37/00 - B32B41/00)
- B33Y: ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

According to some embodiments, system and methods are provided comprising receiving, via a communication interface of a part parameter dictionary module comprising a processor, geometry data for a plurality of geometric structures forming a plurality of parts, wherein the parts are manufactured with an additive manufacturing machine; determining, using the processor of the part parameter dictionary module, a feature set for each geometric structure; generating, using the processor of the part parameter dictionary module, one of a coupon and a coupon set for the feature set; generating an optimized parameter set for each coupon, using the processor of the part parameter dictionary module, via execution of an iterative learning control process for each coupon; mapping, using the processor of the part parameter dictionary module, one or more parameters of the optimized parameter set to one or more features of the feature set; and generating a dictionary of optimized scan parameter sets to fabricate geometric structures with a material used in additive manufacturing. Numerous other aspects are provided.

## Claims

### Claim 1

A method comprising:
receiving, via a communication interface of a part parameter dictionary module comprising a processor, geometry data for a plurality of geometric structures represented when forming a plurality of parts, wherein the received geometry data represents geometric structures in unspecified parts and the parts are manufactured with an additive manufacturing machine;
determining, using the processor of the part parameter dictionary module, a feature set for each geometric structure;
fabricating, using the processor of the part parameter dictionary module, one of a coupon and a coupon set for the feature set, wherein each coupon is a representative test sample of the feature set for each geometric structure;
generating an optimized parameter set for each coupon, using the processor of the part parameter dictionary module, via execution of an iterative learning control process for each coupon;
mapping, using the processor of the part parameter dictionary module, one or more parameters of the optimized parameter set to one or more features of the feature set; and
generating a dictionary of optimized scan parameter sets to fabricate geometric structures with a material used in additive manufacturing.

### Claim 2 (depends on 1)

The method of claim 1, wherein a feature set is one or more features, and wherein a feature is one or more structural aspects of the part.

### Claim 3 (depends on 2)

The method of claim 2, wherein the feature set includes at least one of thermal leakage, voxel size, scan direction, hatch spacing, and thermal lag.

### Claim 4 (depends on 1)

The method of claim 1, wherein the parameter set includes at least one of laser power, scan speed, laser spot size, layer thickness and hatch spacing.

### Claim 5 (depends on 1)

The method of claim 1, wherein each entry in the dictionary comprises part-specific geometries associated with a specific build model.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
receiving, at the part parameter dictionary module, a request for a scan parameter set for the part having a 3D geometry;
decomposing the part into one or more geometric structures;
assigning each of the geometric structures to one or more voxels;
receiving, at the dictionary, a request including the one or more assigned voxels;
generating, using the processor of the part parameter dictionary module, an optimized parameter set for the one or more assigned voxels; and
outputting the optimized parameters in a scan file to the additive manufacturing machine to produce the part.

### Claim 7 (depends on 6)

The method of claim 6, wherein the optimized parameter set is generated via application of a transfer learning algorithm.

### Claim 8

A system comprising:
a part parameter dictionary module including a processor; and
a memory storing program instructions, the part parameter dictionary module operative with the program instructions to perform the functions as follows:
receive geometry data for a plurality of geometric structures represented when forming a plurality of parts, wherein the received geometry data represents geometric structures in unspecified parts and the parts are manufactured with an additive manufacturing machine;
determine a feature set for each geometric structure;
fabricate one of a coupon and a coupon set for the feature set, wherein each coupon is a representative test sample of the feature set for each geometric structure;
generate an optimized parameter set for each coupon via execution of an iterative learning control process for each coupon;
map one or more parameters of the optimized parameter set to one or more features of the feature set;
generate a dictionary of optimized scan parameter sets to fabricate geometric structures with a material used in additive manufacturing.

### Claim 9 (depends on 8)

The system of claim 8, wherein a feature set is one or more features, and wherein a feature is one or more structural aspects of the part.

### Claim 10 (depends on 9)

The system of claim 9, wherein the feature set includes at least one of thermal leakage, voxel size, scan direction, hatch spacing, and thermal lag.

### Claim 11 (depends on 8)

The system of claim 8, wherein the parameter set includes at least one of laser power, scan speed, laser spot size, layer thickness and hatch spacing.

### Claim 12 (depends on 8)

The system of claim 8, wherein each entry in the dictionary comprises part-specific geometries associated with a specific build model.

### Claim 13 (depends on 12)

The system of claim 12, further comprising program instructions to:
receive, at the part parameter dictionary module, a request for a scan parameter set for the part having a 3D geometry;
decompose the part into one or more geometric structures;
assign each of the geometric structures to one or more voxels;
receive, at the dictionary, a request including the one or more assigned voxels;
generate an optimized parameter set for the one or more assigned voxels; and
output the optimized parameters in a scan file to the additive manufacturing machine to produce the part.

### Claim 14 (depends on 13)

The system of claim 13, wherein the optimized parameter set is generated via application of a transfer learning algorithm.

### Claim 15

A non-transitory computer-readable medium storing instructions that, when executed by a computer processor, cause the computer processor to perform a method comprising:
receiving, via a communication interface of a part parameter dictionary module comprising a processor, geometry data for a plurality of geometric structures represented when forming a plurality of parts, wherein the received geometry data represents geometric structures in unspecified parts and the parts are manufactured with an additive manufacturing machine;
determining, using the processor of the part parameter dictionary module, a feature set for each geometric structure;
fabricating, using the processor of the part parameter dictionary module, one of a coupon and a coupon set for the feature set, wherein each coupon is a representative test sample of the feature set for each geometric structure;
generating an optimized parameter set for each coupon, using the processor of the part parameter dictionary module, via execution of an iterative learning control process for each coupon;
mapping, using the processor of the part parameter dictionary module, one or more parameters of the optimized parameter set to one or more features of the feature set; and
generating a dictionary of optimized scan parameter sets to fabricate geometric structures with a material used in additive manufacturing.

### Claim 16 (depends on 15)

The medium of claim 15, wherein each entry in the dictionary comprises part-specific geometries associated with a specific build model.

### Claim 17 (depends on 16)

The medium of claim 16, further comprising:
receiving, at the part parameter dictionary module, a request for a scan parameter set for the part having a 3D geometry;
decomposing the part into one or more geometric structures;
assigning each of the geometric structures to one or more voxels;
receiving, at the dictionary, a request including the one or more assigned voxels;
generating, using the processor of the part parameter dictionary module, an optimized parameter set for the one or more assigned voxels; and
outputting the optimized parameters in a scan file to the additive manufacturing machine to produce the part.

### Claim 18 (depends on 15)

The system of claim 15, wherein the parameter set includes at least one of laser power, scan speed, laser spot size, layer thickness and hatch spacing.

### Claim 19 (depends on 15)

The medium of claim 15, wherein the feature set includes at least one of thermal leakage, voxel size, scan direction, hatch spacing, and thermal lag.

### Claim 20 (depends on 15)

The medium of claim 15, wherein the optimized parameter set is generated via application of a transfer learning algorithm.