DEEP LEARNING FRAMEWORK FOR CYBER-ENABLED MANUFACTURING ADI DITY - - PowerPoint PPT Presentation

▶
deep learning
SMART_READER_LITE
LIVE PREVIEW

DEEP LEARNING FRAMEWORK FOR CYBER-ENABLED MANUFACTURING ADI DITY - - PowerPoint PPT Presentation

Jan 28, 2024 5 likes •330 views

GPU-ACCELERATED DEEP LEARNING FRAMEWORK FOR CYBER-ENABLED MANUFACTURING ADI DITY TYA A BALU SA SAMBIT IT GHADAI AI SO SOUMIK K SA SARKA KAR ADARS RSH H KR KRISH SHNAMUR AMURTHY THY Outline Volumetric Deep Learning based

slide-1
SLIDE 1

GPU-ACCELERATED DEEP LEARNING FRAMEWORK FOR CYBER-ENABLED MANUFACTURING

ADI DITY TYA A BALU SA SAMBIT IT GHADAI AI SO SOUMIK K SA SARKA KAR ADARS RSH H KR KRISH SHNAMUR AMURTHY THY

slide-2
SLIDE 2

Design for Manufacturing

Outline

Volumetric Representations for CAD Models Deep Learning based Design for Manufacturing Explainable Deep Learning

May 15, 2017 2

slide-3
SLIDE 3

Design Manufacturing

INFLUENCE OVER PRODUCT COST

10 20 30 40 50 60 70 80 90 100 Percentage Time Design Production

Reducing Product Cost

  • Design has a large influence on

final product cost

  • DFM helps identify production

issues early

May 15, 2017 3

Source: David Stienstra (Rose-Hulman)

Design freedom to make change Cost of change Design knowledge DFM

slide-4
SLIDE 4

Challenges

  • Traditional DFM method involves

rule based analysis

  • Depends on the experience of the

engineers

  • Several rules for different

processes

  • Example ISO/ASTM 52910:2017(E)

Standard Guidelines for Design for Additive Manufacturing

May 15, 2017 4

Design Manufacturing Redesign

slide-5
SLIDE 5

Artificial Intelligence for Design for Manufacturing

  • Use deep learning to learn non-

manufacturable features in a CAD model

  • Learn from examples of manufacturable

and non-manufacturable models

  • Advantages
  • No explicit hand-crafting of rules
  • Learn complicated rules that are

difficult to codify

May 15, 2017 5

slide-6
SLIDE 6

Feasibility Demonstration – Drilling Holes

  • Common manufacturing operations
  • Fewer set of design rules
  • Can manually create ground-truth data
  • Complex design rules
  • Depth to diameter ratio
  • Blind vs. through holes
  • Proximity of holes to object boundaries

May 15, 2017 6

slide-7
SLIDE 7

Boundary Representation (B-Rep) CAD Models

  • De-facto representation for

CAD models

  • Can be easily tessellated into

triangles for rendering

  • Difficult to interpret

volumetric information

  • Size of a feature
  • Internal location of a feature

May 15, 2017 7

slide-8
SLIDE 8

Voxel Representation

  • Binary occupancy information
  • Augmented with extra geometry

information

  • Can be used as direct input to a

convolutional neural network

  • Require a fast method to voxelize a

large number of CAD models

May 15, 2017 8

slide-9
SLIDE 9

Design for Manufacturing

Outline

Volumetric Representations for CAD Models Deep Learning based Design for Manufacturing Explainable Deep Learning

May 15, 2017 9

slide-10
SLIDE 10

Volumetric Voxelization

  • Overlay a regular voxel grid on

the object

  • Test point membership of the

voxel bounding-box center points, classify as in or out

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

May 15, 2017 10

slide-11
SLIDE 11

Point Membership Classification (PMC) Using GPU Slicing

  • Use standard PMC using odd ray

intersection test

  • Slice the object perpendicular to

an arbitrary axis

  • Render the sliced object and

count the number of pixels

  • Extend to 3D; Each pixel

corresponds to a grid point in a 2D slice

May 15, 2017 11 View Direction Pixels

slide-12
SLIDE 12

Design for Manufacturing

Outline

Volumetric Representations for CAD Models Deep Learning based Design for Manufacturing Explainable Deep Learning

May 15, 2017 12

slide-13
SLIDE 13

Learning Local Features

  • Local Feature learning is different from object

recognition

  • Variation in features affect the object

classification

  • Learning the features by semi-supervised

learning

May 15, 2017 13

[1]. http://dfmpro.geometricglobal.com/files/2017/04/Whitepaper-A-new-approach- to-design-and-manufacturing-collaboration.pdf

slide-14
SLIDE 14

Need for 3D Convolutional Nets

  • Hierarchical feature extraction from volumetric representation
  • Capability to learn features with object classification
  • Amenable to model interpretability due to learning of spatial location

May 15, 2017 14

slide-15
SLIDE 15
  • Binary definition of manufacturability (binary cross-entropy loss)
  • Choice of input resolution depending on the GPUs
  • Architecture
  • 3D convolutional layer and 3D max. pooling layer
  • ReLU activation with output layer having Sigmoid activation

Deep Learning Based Design for Manufacturing

May 15, 2017 15

slide-16
SLIDE 16

Deep Learning Based Design for Manufacturing

(a) (b) (c) (d) (e) (f) DLDFM

May 15, 2017 16

slide-17
SLIDE 17

Results

May 15, 2017 17 0% 20% 40% 60% 80% 100% DLDFM (binary + normals) DLDFM (Orthogonal Distance Fields) DLDFM (binary)

Representative Test Data Manufacturable

True Positive (Predicted Manufacturable, Actually Manufacturable) False Negative (Predicted Non-Manufacturable, Actually Manufacturable) 0% 20% 40% 60% 80% 100% DLDFM (binary + normals) DLDFM (Orthogonal Distance Fields) DLDFM (binary)

Representative Test Data Non-Manufacturable

True Negative (Predicted Non-Manufacturable, Actually Non-Manufacturable) False Positive (Predicted Manufacturable, Actually Non-Manufacturable)

slide-18
SLIDE 18

0% 20% 40% 60% 80% 100% DLDFM (binary + normals) DLDFM (Orthogonal Distance Fields) DLDFM (binary)

Non-Representative Test Data Manufacturable

True Positive (Predicted Manufacturable, Actually Manufacturable) False Negative (Predicted Non-Manufacturable, Actually Manufacturable)

Results

May 15, 2017 18 0% 20% 40% 60% 80% 100% DLDFM (binary + normals) DLDFM (Orthogonal Distance Fields) DLDFM (binary)

Non-Representative Test Data Non-Manufacturable

True Negative (Predicted Non-Manufacturable, Actually Non-Manufacturable) False Positive (Predicted Manufacturable, Actually Non-Manufacturable)

slide-19
SLIDE 19

Results

May 15, 2017 19 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% DLDFM (orthogonal distance fields) DLDFM (binary + normals) DLDFM (binary) True Positive (Predicted Manufacturable, Actually Manufacturable) True Negative (Predicted Non-Manufacturable, Actually Non-Manufacturable) False Negative (Predicted Non-Manufacturable, Actually Manufacturable) False Positive (Predicted Manufacturable, Actually Non-Manufacturable)

slide-20
SLIDE 20

Design for Manufacturing

Outline

Volumetric Representations for CAD Models Deep Learning based Design for Manufacturing Explainable Deep Learning

May 15, 2017 20

slide-21
SLIDE 21

Model Interpretability

  • Possible methods
  • Back-propagation
  • Guided back-propagation, saliency map, etc.

Disadvantage: Not class discriminative

  • Grad-CAM
  • Class discriminative

References: [1]. Zeiler, Matthew D., and Rob Fergus. "Visualizing and understanding convolutional networks." European conference on computer vision. Springer International Publishing, 2014. [2]. Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014). [3]. Zhou, Bolei, et al. "Learning deep features for discriminative localization." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. [4]. Selvaraju, Ramprasaath R., et al. "Grad-CAM: Why did you say that?." arXiv preprint arXiv:1611.07450 (2016). May 15, 2017 21

slide-22
SLIDE 22

3D Grad-CAM

  • Perform global average pooling and back-propagate the activations

Input: Volumetric Representation

Convolutional Layer Convolution Filters 1 Convolution Filters 2 Convolutional Layer Pooling Layer Fully Connected Layer (Yes/No) Interpretation Class Activation Map

Output: Manufacturability

May 15, 2017 22

slide-23
SLIDE 23

Insights from GradCAM

May 15, 2017 23

slide-24
SLIDE 24

One Hole Manufacturable Insight: 3D Grad-CAM is class discriminative

May 15, 2017 24

slide-25
SLIDE 25

Two Holes Manufacturable (both)

May 15, 2017 25

Insight: DLDFM can predict manufacturability of multiple features simultaneously

slide-26
SLIDE 26

Insight: DLDFM can predict manufacturability of individual features

May 15, 2017 26

Two Holes Non-Manufacturable (due to one of them)

slide-27
SLIDE 27

May 15, 2017 27

Insight: DLDFM can predict manufacturability of interacting features by generalizing the rules Two Holes Non-Manufacturable (due to interaction between them)

slide-28
SLIDE 28

L-Shaped Block with Hole Non-Manufacturable (close to external face) Insight: DLDFM can predict manufacturability based on a local feature instead of external geometry

May 15, 2017 28

slide-29
SLIDE 29

Cylindrical-Shaped Block with Hole Non- Manufacturable (close to external cylindrical face) Insight: DLDFM can predict manufacturability based on a local feature even with complicated external geometry

May 15, 2017 29

slide-30
SLIDE 30

Demo

May 15, 2017 30

slide-31
SLIDE 31

Acknowledgements

  • AI-based Design and Manufacturability Lab (ADAM Lab)
  • Gavin Young
  • Kin Gwn Lore
  • Funding Sources
  • National Science Foundation
  • CMMI:1644441 – CM: Machine-Learning Driven Decision Support in Design for Manufacturability
  • nVIDIA
  • Titan X GPU for Academic Research

May 15, 2017 31

slide-32
SLIDE 32

Thank You!

Questions?

May 15, 2017 32