Material estimate for fabrication of three-dimensional object

• US 10,414,149 B2
• Filed: 10/21/2016
• Issued: 09/17/2019
• Est. Priority Date: 10/21/2016
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Mummidi, Lakshmi Narayana, Singh, Parmjeet
• Primary Examiner(s): Pham, Ly D
• Application Number:
  US15/299,849
• Publication Number:
  US 20180111335A1
• Time in Patent Office: 1,061 Days
• Field of Search: 706 12
• CPC Class Codes: B29C 64/20 Apparatus for additive manufacturing; Details thereof or accessories therefor
• CPC Class Codes: B29C 64/386 Data acquisition or data processing for additive manufacturing
• CPC Class Codes: B33Y 10/00 Processes of additive manufacturing
• CPC Class Codes: B33Y 30/00 Apparatus for additive manufacturing; Details thereof or accessories therefor
• CPC Class Codes: B33Y 50/00 Data acquisition or data processing for additive manufacturing
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

The system includes a predictive model trained to estimate an amount of material to be used to fabricate three-dimensional objects. The system further includes an estimation component that receives information regarding the three-dimensional object. The estimation component, using the predictive model, estimates the amount of material to be used to fabricate the three-dimensional object based upon the information regarding the three-dimensional object. The estimation component compares the estimated amount of material with an available amount to determine whether the material available is less than the estimated amount of material to fabricate the three-dimensional object. When it is determined the material available is less than the estimated amount of material, the estimation component can perform an action such as preventing commencement of a fabrication process and/or providing information to a user. The predictive model can be adaptively updated based upon an actual amount of material used during the fabrication process.

Claims

1. A system for estimating material for fabrication of a particular three-dimensional object, comprising:

a computer comprising a processor and a memory, the memory comprising;

a predictive model trained to estimate an amount of material to be used to fabricate three-dimensional objects;

an estimation component configured to receive information regarding the particular three-dimensional object, the estimation component further configured to, using the predictive model, estimate the amount of material to be used to fabricate the particular three-dimensional object based upon the information regarding the particular three-dimensional object, wherein the predictive model is trained based on a plurality of fabrication requests and associated actual amounts of materials used to fabricate three-dimensional objects specified by the plurality of fabrication requests, the estimation component further configured to compare the estimated amount of material with an available amount of material to determine whether the material available is less than the estimated amount of material to fabricate the particular three-dimensional object, the estimation component further configured to, when it is determined the material available is less than the estimated amount of material, perform an action, and, when it is determined the material available is greater or equal to the estimated amount of material, fabricate the particular three-dimensional object;

a machine learning component configured to receive an actual amount of material used during a fabrication process, the machine learning component further configured to adaptively update the predictive model based on the actual amount of material used to fabricate the particular three-dimensional object.

2. The system of claim 1, wherein the information about the particular three-dimensional object comprises a 3D Manufacturing Format (3MF) file, an object (OBJ) file, a stereo lithography (STL) file, a virtual reality modeling language (VRML) file, an X3G file, a polygon (PLY) file or a filmbox (FBX) file.

3. The system of claim 1, wherein the information about the particular three-dimensional object comprises a file.

4. The system of claim 1, wherein the predictive model is trained using a machine learning algorithm.

5. The system of claim 1, wherein the available amount of material is based on user input.

6. The system of claim 1, wherein the available amount of material is based on information received from a fabrication apparatus.

7. The system of claim 1, wherein the estimation component utilizes at least one of a job name of the particular three-dimensional object, a mesh count of the particular three-dimensional object, a triangle count of the particular three-dimensional object, a printer name of a fabrication apparatus, a printer driver name of the fabrication apparatus, a printer driver version of the fabrication apparatus, a width of the particular three-dimensional object, a depth of the particular three-dimensional object, a height of the particular three-dimensional object, a quality of the particular three-dimensional object, a density of the particular three-dimensional object, a raft used during a fabrication process, a support used during the fabrication process, a slicer speed of the fabrication apparatus, a material type of material utilized by the fabrication apparatus or a material manufacturer of material utilized by the fabrication apparatus to estimate the amount of material to be used to fabricate the particular three-dimensional object.

8. The system of claim 1, wherein the action performed comprises preventing commencement of a fabrication process.

9. The system of claim 1, wherein the action performed comprises providing information to a user indicating that insufficient material is available to successfully fabricate the particular three-dimensional object.

10. The system of claim 1, wherein the plurality of fabrication requests and associated actual amounts of materials used to fabricate three-dimensional objects specified by the plurality of fabrication requests are performed over a plurality of fabrication sites.

11. A method of estimating material for fabrication of a three-dimensional object, comprising:

training a predictive model using a machine learning algorithm, wherein the predictive model is trained based on a plurality of fabrication requests and associated actual amounts of materials used to fabricate three-dimensional objects specified by the plurality of fabrication requests;

receiving information regarding a three-dimensional object to be fabricated;

using the predictive model, estimating an amount of material to be used in fabrication of the three-dimensional object;

receiving information regarding an available amount of material from a fabrication apparatus;

determine whether the available amount of material is greater than or equal to the estimated amount of material;

when the available amount of material is not greater than or equal to the estimated amount of material, perform an action; and

when the available amount of material is greater the estimated amount of material, fabricate the particular three-dimensional object using the fabrication apparatus, and, adaptively update the predictive model based on an actual amount of material used to fabricate the particular three-dimensional object.

12. The method of claim 11, wherein the available amount of material is further based on user input.

13. The method of claim 11, wherein the estimation component utilizes at least one of a job name of the three-dimensional object, a mesh count of the three-dimensional object, a triangle count of the three-dimensional object, a printer name of a fabrication apparatus, a printer driver name of the fabrication apparatus, a printer driver version of the fabrication apparatus, a width of the three-dimensional object, a depth of the three-dimensional object, a height of the three-dimensional object, a quality of the three-dimensional object, a density of the three-dimensional object, a raft used during a fabrication process, a support used during the fabrication process, a slicer speed of the fabrication apparatus, a material type of material utilized by the fabrication apparatus or a material manufacturer of material utilized by the fabrication apparatus to estimate the amount of material to be used to fabricate the three-dimensional object.

14. A computer storage media storing computer-readable instructions that when executed cause a computing device to:

train a predictive model using a machine learning algorithm, wherein the predictive model is trained based on a plurality of fabrication requests and associated actual amounts of materials used to fabricate three-dimensional objects specified by the plurality of fabrication requests;

receive information regarding a particular three-dimensional object to be fabricated;

using the predictive model, estimate an amount of material to be used in fabrication of the particular three-dimensional object;

receive information regarding an available amount of material from a fabrication apparatus;

determine whether the available amount of material is greater than or equal to the estimated amount of material;

when the available amount of material is not greater than or equal to the estimated amount of material, perform an action;

when the available amount of material is greater the estimated amount of material, fabricate the particular three-dimensional object using the fabrication apparatus; and

adaptively update the predictive model based on an actual amount of material used to fabricate the particular three-dimensional object.

15. The computer storage media of claim 14, wherein the received information regarding the three-dimensional object to be fabricated comprises a 3D Manufacturing Format (3MF) file, an object (OBJ) file, a stereo lithography (STL) file, a virtual reality modeling language (VRML) file, an X3G file, a polygon (PLY) file or a filmbox (FBX) file.