Intelligent 3D printing through optimization of 3D print parameters

1. A system comprising:

three dimensional (3D) printer hardware; and

at least one computer communicatively coupled with the 3D printer hardware, the at least one computer programed to receive 3D print type inputs for an object to be 3D printed and create a 3D print profile comprising parameters for 3D printing the object using the 3D printer hardware by matching the 3D print type inputs against a database;

wherein the at least one computer is programed to perform model analytics to optimize the parameters in the 3D print profile using simulation of the 3D printing and analysis of previous simulation data retrieved from the database for prior 3D prints having corresponding 3D print type inputs, the at least one computer is programed to select a type of the simulation from a plurality of simulations based on the 3D print type inputs, the 3D print type inputs comprise 3D geometry, a 3D printing technique, a material of the 3D printing, and a specific industry application, and the parameters in the 3D print profile comprise ambient conditions, build speed, material conditions, layer thickness and power profiles; and

wherein the at least one computer is programed to operate the 3D printer using the optimized parameters in the 3D print profile to increase 3D print success rate, 3D print quality, 3D print speed, or a combination thereof.

2. The system of claim 1 , wherein the 3D printer hardware comprises one or more embedded sensors and an onboard computer arranged in a closed-loop feedback configuration with a 3D print engine to dynamically alter 3D print parameters to optimize a 3D print during 3D printing of the 3D print.

3. The system of claim 1 , wherein the at least one computer is programed to perform database analysis by cross referencing the 3D print type inputs in the database, which contains previous 3D geometries, simulations, 3D print profiles and user feedback on the success or failure of previous 3D prints, such that the parameters for 3D printing are optimized based on historic data.

4. The system of claim 1 , wherein the type of the simulation is at least one selected from finite element analysis, computational fluid dynamics, and support generation.

5. The system of claim 1 , wherein the at least one computer is programed to perform model analytics and fault analysis, wherein the fault analysis employs one or more machine learning algorithms to analyze a database for trends that link outcomes of 3D prints with specific 3D geometries, 3D print profiles, materials or specific industry applications, and wherein user feedback regarding success or failure of 3D printing and quality thereof are solicited and used as feedback to the fault analysis and the model analytics.

6. The system of claim 5 , wherein the at least one computer comprises an onboard computer of the 3D printer hardware.

7. A method comprising:

receiving three dimensional (3D) print type inputs for an object to be 3D printed;

creating a 3D print profile comprising parameters for 3D printing the object using 3D printer hardware by matching the 3D print type inputs against a database; and

outputting the 3D print profile and causing 3D printing of the object using the 3D print profile with the 3D printer hardware;

wherein the creating comprises performing model analytics to optimize the parameters in the 3D print profile using simulation of the 3D printing and analysis of previous simulation data retrieved from the database for prior 3D prints having corresponding 3D print type inputs, the method comprises selecting a type of the simulation from a plurality of simulations based on the 3D print type inputs, wherein the 3D print type inputs comprise 3D geometry, a 3D printing technique, a material of the 3D printing, and a specific industry application, and the parameters in the 3D print profile comprise ambient conditions, build speed, material conditions, layer thickness and power profiles.

8. The method of claim 7 , wherein the receiving comprises receiving the 3D print type inputs including user selected critical features of a 3D model of the object and material properties of the object to be 3D printed.

9. The method of claim 7 , comprising dynamically altering the parameters of the 3D print profile while 3D printing the object using the 3D printer hardware responsive to data received from one or more sensors in the 3D printer hardware arranged in a closed-loop feedback configuration with a 3D print engine.

10. The method of claim 9 , wherein the creating comprises adding to the 3D print profile multiple different sets of two or more 3D print parameters, and the altering comprises switching between respective ones of the different sets of two or more 3D print parameters during 3D printing of a single object using the 3D printer hardware.

11. The method of claim 9 , comprising monitoring 3D print progress during the 3D printing by collecting and processing key indicators using the one or more sensors in the 3D printer hardware.

12. The method of claim 11 , wherein the key indicators comprise:

ambient machine, part and raw material temperatures;

compressive, tensile, shear, bending and torsional stresses;

visual indicators captured via one or more cameras; and

audible indicators captured via one or more microphones.

13. The method of claim 7 , wherein the database includes both a local component and a remote component, and the method comprises sharing data between the local database component and the remote database component across a network such that actions taken by an experienced user at one location are used to improve the 3D print profile generated for a different user at a different location.

14. The method of claim 7 , wherein the creating comprises performing database analysis by cross referencing the 3D print type inputs in the database, which contains previous 3D geometries, simulations, 3D print profiles and user feedback on the success or failure of previous 3D prints, such that the parameters for 3D printing are optimized based on historic data.

15. The method of claim 7 , wherein the type of the simulation is at least one selected from finite element analysis, computational fluid dynamics, or support generation.

16. The method of claim 7 , comprising:

performing model analytics and fault analysis, wherein the fault analysis employs one or more machine learning algorithms to analyze a database for trends that link outcomes of 3D prints with specific 3D geometries, 3D print profiles, materials or specific industry applications;

obtaining user input regarding success or failure of 3D printing and quality; and

using the user input regarding success or failure as feedback to the fault analysis and the model analytics.