Optimization of prototype and machine design within a 3d fluid modeling environment

Patent metadata

Field	Value
Publication number	US-2018260503-A1
Application number	US-201715630941-A
Country	US
Kind code	A1
Filing date	Jun 22, 2017
Priority date	Mar 10, 2017
Publication date	Sep 13, 2018
Grant date	—

Abstract

Techniques that facilitate optimization of prototype and machine design within a three-dimensional fluid modeling environment are presented. For example, a system includes a modeling component, a machine learning component, and a graphical user interface component. The modeling component generates three-dimensional model of a mechanical device based on a library of stored data elements. The machine learning component predicts one or more characteristics of the mechanical device based on a first machine learning process associated with the three-dimensional model. The machine learning component also generates physics modeling data of the mechanical device based on the one or more characteristics of the mechanical device. The graphical user interface component provides, via a graphical user interface, a three-dimensional design environment associated with the three-dimensional model and a probabilistic simulation environment associated with optimization of the three-dimensional model.

First claim

What is claimed is:

1 . A system, comprising:
a memory storing computer executable components; and a processor configured to execute the following computer executable components stored in the memory:
a modeling component that generates a three-dimensional model of a mechanical device based on a library of stored data elements;
a machine learning component that predicts one or more characteristics of the mechanical device based on a first machine learning process associated with the three-dimensional model, and generates physics modeling data of the mechanical device based on the one or more characteristics of the mechanical device; and
a graphical user interface component that provides, via a graphical user interface, a three-dimensional design environment associated with the three-dimensional model and a probabilistic simulation environment associated with optimization of the three-dimensional model, wherein the three-dimensional design environment renders the physics modeling data on the three-dimensional model, and wherein the probabilistic simulation environment renders a modified version of the physics modeling data on the three-dimensional model based on a second machine learning process associated with the optimization of the three-dimensional model.

2 . The system of claim 1 , wherein the graphical user interface component presents, via a display device associated with the graphical user interface, a set of components associated with the library of stored data elements based on a set of physical characteristics associated with the set of components.

3 . The system of claim 2 , wherein the modeling component modifies the three-dimensional model to generate a modified version of the three-dimensional model based on a selection of one or more components associated with the set of physical characteristics.

4 . The system of claim 3 , wherein the machine learning component performs the second machine learning process based on the modified version of the three-dimensional model.

5 . The system of claim 1 , wherein the graphical user interface component presents, via a display device associated with the graphical user interface, a set of components associated with the library of stored data elements based on a set of thermal characteristics associated with the set of components.

6 . The system of claim 5 , wherein the modeling component modifies the three-dimensional model to generate a modified version of the three-dimensional model based on a selection of one or more components associated with the set of thermal characteristics.

7 . The system of claim 6 , wherein the machine learning component performs the second machine learning process based on the modified version of the three-dimensional model.

8 . The system of claim 1 , wherein the machine learning component performs the second machine learning process associated with the optimization of the three-dimensional model, and generates the modified version of the physics modeling data of based on the second machine learning process.

9 . The system of claim 1 , wherein the machine learning component performs the second machine learning process to generate the modified version of the physics modeling data based on a Latin hypercube sampling process that modifies one or more values of the physics modeling data.

10 . The system of claim 1 , wherein the machine learning component performs the second machine learning process to generate the modified version of the physics modeling data based a Monte Carlo sampling process that modifies one or more values of the physics modeling data.

11 . A method, comprising:
generating, by a system comprising a processor, a three-dimensional model of a mechanical device based on a library of stored data elements; performing, by the system, a first machine learning process associated with the three-dimensional model to predict one or more characteristics of the mechanical device; generating, by the system, physics modeling data of the mechanical device based on the one or more characteristics of the mechanical device; and generating, by the system, a graphical user interface that presents a three-dimensional design environment associated with the three-dimensional model and a probabilistic simulation environment associated with optimization of the three-dimensional model, comprising rendering the physics modeling data on the three-dimensional model via the three-dimensional design environment, and rendering a modified version of the physics modeling data on the three-dimensional model via the probabilistic simulation environment based on a second machine learning process associated with the optimization of the three-dimensional model.

12 . The method of claim 11 , further comprising:
displaying, by the system, information associated with a set of components included in the library of stored data elements based on a set of physical characteristics associated with the set of components.

13 . The method of claim 12 , further comprising:
generating, by the system, a modified version of the three-dimensional model based on a selection of one or more components associated with the set of physical characteristics.

14 . The method of claim 11 , further comprising:
displaying, by the system, information associated with a set of components included in the library of stored data elements based on a set of thermal characteristics associated with the set of components.

15 . The method of claim 14 , further comprising:
generating, by the system, a modified version of the three-dimensional model based on a selection of one or more components associated with the set of thermal characteristics.

16 . The method of claim 12 , further comprising:
performing, by the system, the second machine learning process based on a Latin hypercube sampling technique or a Monte Carlo sampling technique.

17 . A computer readable storage device comprising instructions that, in response to execution, cause a system comprising a processor to perform operations, comprising:
generating a three-dimensional model of a mechanical device based on a library of stored data elements; performing a machine learning process associated with the three-dimensional model to predict one or more characteristics of the mechanical device; determining physics modeling data of the mechanical device based on the one or more characteristics of the mechanical device; and providing a graphical user interface that presents a three-dimensional design environment associated with the three-dimensional model and a probabilistic simulation environment associated with optimization of the three-dimensional model.

18 . The computer readable storage device of claim 17 , wherein the operations further comprise:
selecting a portion of the mechanical device from the library of stored data elements based on a set of characteristics for a set of components presented via the graphical user interface.

19 . The computer readable storage device of claim 17 , wherein the machine learning process is a first machine learning process, and wherein the operations further comprise:
performing a second machine learning process that determines a modified version of the physics modeling data based on a Latin hypercube sampling technique.

20 . The computer readable storage device of claim 17 , wherein the machine learning process is a first machine learning process, and wherein the operations further comprise:
performing a second machine learning process that deter

Assignees

• Gen Electric

Inventors

• Dweik Zain S
• Sethuraman Vijay
• Elbir Berkay

Classifications

• G06N3/042

  Knowledge-based neural networks; Logical representations of neural networks · CPC title

• G06N3/043

  based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS] · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title