Research Papers: D3 Methods

A Convolutional Neural Network Model for Predicting a Product's Function, Given Its Form

[+] Author and Article Information
Matthew L. Dering

Computer Science and Engineering,
Penn State University,
University Park, PA 16802
e-mail: mld284@psu.edu

Conrad S. Tucker

Engineering Design and Industrial Engineering,
Penn State University,
University Park, PA 16802
e-mail: ctucker4@psu.edu

1Corresponding author.

Contributed by the Design Automation Committee of ASME for publication in the JOURNAL OF MECHANICAL DESIGN. Manuscript received February 24, 2017; final manuscript received June 28, 2017; published online October 2, 2017. Assoc. Editor: Charlie C. L. Wang.

J. Mech. Des 139(11), 111408 (Oct 02, 2017) (14 pages) Paper No: MD-17-1178; doi: 10.1115/1.4037309 History: Received February 24, 2017; Revised June 28, 2017

Quantifying the ability of a digital design concept to perform a function currently requires the use of costly and intensive solutions such as computational fluid dynamics. To mitigate these challenges, the authors of this work propose a deep learning approach based on three-dimensional (3D) convolutions that predict functional quantities of digital design concepts. This work defines the term functional quantity to mean a quantitative measure of an artifact's ability to perform a function. Several research questions are derived from this work: (i) Are learned 3D convolutions able to accurately calculate these quantities, as measured by rank, magnitude, and accuracy? (ii) What do the latent features (that is, internal values in the model) discovered by this network mean? (iii) Does this work perform better than other deep learning approaches at calculating functional quantities? In the case study, a proposed network design is tested for its ability to predict several functions (sitting, storing liquid, emitting sound, displaying images, and providing conveyance) based on test form classes distinct from training class. This study evaluates several approaches to this problem based on a common architecture, with the best approach achieving F scores of >0.9 in three of the five functions identified. Testing trained models on novel input also yields accuracy as high as 98% for estimating rank of these functional quantities. This method is also employed to differentiate between decorative and functional headwear, which yields an 84.4% accuracy and 0.786 precision.

Copyright © 2017 by ASME
Your Session has timed out. Please sign back in to continue.


Vasudevan, N. , and Tucker, C. S. , 2013, “ Digital Representation of Physical Artifacts: The Effect of Low Cost, High Accuracy 3D Scanning Technologies on Engineering Education, Student Learning and Design Evaluation,” ASME Paper No. DETC2013-12651.
Tucker, C. S. , Saint John, D. B. , Behoora, I. , and Marcireau, A. , 2014, “ Open Source 3D Scanning and Printing for Design Capture and Realization,” ASME Paper No. DETC2014-34801.
Shyy, W. , Udaykumar, H. S. , Rao, M. M. , and Smith, R. W. , 2012, Computational Fluid Dynamics With Moving Boundaries, Courier, North Chelmsford, MA.
Buede, D. M. , and Miller, W. D. , 2016, The Engineering Design of Systems: Models and Methods, Wiley, Hoboken, NJ.
Gero, J. S. , and Kannengiesser, U. , 2004, “ The Situated Function–Behaviour–Structure Framework,” Des. Stud., 25(4), pp. 373–391. [CrossRef]
Chandrasegaran, S. K. , Ramani, K. , Sriram, R. D. , Horváth, I. , Bernard, A. , Harik, R. F. , and Gao, W. , 2013, “ The Evolution, Challenges, and Future of Knowledge Representation in Product Design Systems,” Comput. Aided Des., 45(2), pp. 204–228. [CrossRef]
Chen, Y. , Liu, Z.-L. , and Xie, Y.-B. , 2012, “ A Knowledge-Based Framework for Creative Conceptual Design of Multi-Disciplinary Systems,” Comput. Aided Des., 44(2), pp. 146–153. [CrossRef]
Qi, J. , Hu, J. , Zhu, G. , and Peng, Y. , 2015, “ Automatically Synthesizing Principle Solutions in Multi-Disciplinary Conceptual Design With Functional and Structural Knowledge,” ASME Paper No. DETC2015-46373.
Bhatt, M. , Hois, J. , and Kutz, O. , 2012, “ Ontological Modelling of Form and Function for Architectural Design,” Appl. Ontology, 7(3), pp. 233–267.
Townsend, J. D. , Kang, W. , Montoya, M. M. , and Calantone, R. J. , 2013, “ Brand-Specific Design Effects: Form and Function,” J. Prod. Innovation Manage., 30(5), pp. 994–1008. [CrossRef]
Kang, S. W. , and Tucker, C. S. , 2015, “ Automated Concept Generation Based on Function-Form Synthesis,” ASME Paper No. DETC2015-47687.
Tseng, I. , Cagan, J. , Kotovsky, K. , and Wood, M. , 2013, “ Form Function Fidelity,” ASME J. Mech. Des., 135(1), p. 011006. [CrossRef]
Roy, U. , Pramanik, N. , Sudarsan, R. , Sriram, R. D. , and Lyons, K. W. , 2001, “ Function-to-Form Mapping: Model, Representation and Applications in Design Synthesis,” Comput. Aided Des., 33(10), pp. 699–719. [CrossRef]
Tsai, H.-C. , Hsiao, S.-W. , and Hung, F.-K. , 2006, “ An Image Evaluation Approach for Parameter-Based Product Form and Color Design,” Comput. Aided Des., 38(2), pp. 157–171. [CrossRef]
Sylcott, B. , Cagan, J. , and Tabibnia, G. , 2013, “ Understanding Consumer Tradeoffs Between Form and Function Through Metaconjoint and Cognitive Neuroscience Analyses,” ASME J. Mech. Des., 135(10), p. 101002. [CrossRef]
Sylcott, B. , and Cagan, J. , 2014, “ Modeling Aggregate Choice for Form and Function Through Metaconjoint Analysis,” ASME J. Mech. Des., 136(12), p. 124501. [CrossRef]
Orsborn, S. , Cagan, J. , and Boatwright, P. , 2009, “ Quantifying Aesthetic Form Preference in a Utility Function,” ASME J. Mech. Des., 131(6), p. 061001. [CrossRef]
Tseng, I. , Cagan, J. , and Kotovsky, K. , 2012, “ Concurrent Optimization of Computationally Learned Stylistic Form and Functional Goals,” ASME J. Mech. Des., 134(11), p. 111006. [CrossRef]
Cheong, H. , Chiu, I. , Shu, L. , Stone, R. , and McAdams, D. , 2011, “ Biologically Meaningful Keywords for Functional Terms of the Functional Basis,” ASME J. Mech. Des., 133(2), p. 021007. [CrossRef]
Lowe, D. G. , 1999, “ Object Recognition From Local Scale-Invariant Features,” Seventh IEEE International Conference on Computer Vision (ICCV), Kerkyra, Greece, Sept. 20–27, pp. 1150–1157.
Bay, H. , Tuytelaars, T. , and Van Gool, L. , 2006, “ Surf: Speeded Up Robust Features,” European Conference on Computer Vision (ECCV), Graz, Austria, May 7–13, pp. 404–417.
Rublee, E. , Rabaud, V. , Konolige, K. , and Bradski, G. , 2011, “ Orb: An Efficient Alternative to Sift or Surf,” IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, Nov. 6–13, pp. 2564–2571.
Dalal, N. , and Triggs, B. , 2005, “ Histograms of Oriented Gradients for Human Detection,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, June 20–25, pp. 886–893.
Tombari, F. , Salti, S. , and Di Stefano, L. , 2011, “ A Combined Texture-Shape Descriptor for Enhanced 3D Feature Matching,” 18th IEEE International Conference on Image Processing (ICIP), Brussels, Belgium, Sept. 11–14, pp. 809–812.
Song, M. , Sun, Z. , Liu, K. , and Lang, X. , 2015, “ Iterative 3D Shape Classification by Online Metric Learning,” Comput. Aided Geom. Des., 35–36, pp. 192–205. [CrossRef]
Cortes, C. , and Vapnik, V. , 1995, “ Support-Vector Networks,” Mach. Learn., 20(3), pp. 273–297.
Breiman, L. , 2001, “ Random Forests,” Mach. Learn., 45(1), pp. 5–32. [CrossRef]
Russakovsky, O. , Deng, J. , Su, H. , Krause, J. , Satheesh, S. , Ma, S. , Huang, Z. , Karpathy, A. , Khosla, A. , Bernstein, M. , Berg, A. , and Fei-Fei, L. , 2015, “ Imagenet Large Scale Visual Recognition Challenge,” Int. J. Comput. Vision, 115(3), pp. 211–252. [CrossRef]
Krizhevsky, A. , Sutskever, I. , and Hinton, G. E. , 2012, “ ImageNet Classification With Deep Convolutional Neural Networks,” 25th International Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, NV, Dec. 3–6, pp. 1097–1105.
Simonyan, K. , and Zisserman, A. , 2014, “ Very Deep Convolutional Networks for Large-Scale Image Recognition,” preprint arXiv:1409.1556.
He, K. , Zhang, X. , Ren, S. , and Sun, J. , 2016, “ Deep Residual Learning for Image Recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, June 27–30, pp. 770–778.
Wu, Z. , Song, S. , Khosla, A. , Yu, F. , Zhang, L. , Tang, X. , and Xiao, J. , 2015, “ 3D Shapenets: A Deep Representation for Volumetric Shapes,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, June 7–12, pp. 1912–1920.
Chang, A. X. , Funkhouser, T. , Guibas, L. , Hanrahan, P. , Huang, Q. , Li, Z. , Savarese, S. , Savva, M. , Song, S. , Su, H. , Xiao, J. , Yi, L. , and Yu, F. , 2015, “ ShapeNet: An Information-Rich 3D Model Repository,” preprint arXiv:1512.03012.
Maturana, D. , and Scherer, S. , 2015, “ Voxnet: A 3D Convolutional Neural Network for Real-Time Object Recognition,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, Sept. 28–Oct. 2, pp. 922–928.
Su, H. , Maji, S. , Kalogerakis, E. , and Learned-Miller, E. , 2015, “ Multi-View Convolutional Neural Networks for 3D Shape Recognition,” International Conference on Computer Vision (ICCV), Santiago, Chile, Dec. 7–13, pp. 945–953.
Shi, B. , Bai, S. , Zhou, Z. , and Bai, X. , 2015, “ Deeppano: Deep Panoramic Representation for 3-D Shape Recognition,” IEEE Signal Process. Lett., 22(12), pp. 2339–2343. [CrossRef]
Su, H. , Qi, C. R. , Li, Y. , and Guibas, L. J. , 2015, “ Render for CNN: Viewpoint Estimation in Images Using Cnns Trained With Rendered 3D Model Views,” IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, Dec. 7–13, pp. 2686–2694.
Boscaini, D. , Masci, J. , Rodolà, E. , and Bronstein, M. , 2016, “ Learning Shape Correspondence With Anisotropic Convolutional Neural Networks,” International Conference on Neural Information Processing Systems (NIPS), Barcelona, Spain, Dec. 5–10, pp. 3189–3197.
Shu, Z. , Qi, C. , Xin, S. , Hu, C. , Wang, L. , Zhang, Y. , and Liu, L. , 2016, “ Unsupervised 3D Shape Segmentation and Co-Segmentation Via Deep Learning,” Comput. Aided Geom. Des., 43, pp. 39–52. [CrossRef]
Zhang, Y. , Bai, M. , Kohli, P. , Izadi, S. , and Xiao, J. , 2016, “ Deepcontext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding,” preprint arXiv:1603.04922.
Maas, A. L. , Hannun, A. Y. , and Ng, A. Y. , 2013, “ Rectifier Nonlinearities Improve Neural Network Acoustic Models,” 30th International Conference on Machine Learning (ICML), Atlanta, GA, June 16–21.
Glorot, X. , and Bengio, Y. , 2010, “ Understanding the Difficulty of Training Deep Feedforward Neural Networks,” 13th International Conference on Artificial Intelligence and Statistics (AISTATS), Sardinia, Italy, May 13–15, pp. 249–256.
Rothe, R. , Timofte, R. , and Van Gool, L. , 2015, “ Dex: Deep Expectation of Apparent Age From a Single Image,” IEEE International Conference on Computer Vision Workshops (ICCVW), Santiago, Chile, Dec. 7–13, pp. 10–15.
Nooruddin, F. S. , and Turk, G. , 2003, “ Simplification and Repair of Polygonal Models Using Volumetric Techniques,” IEEE Trans. Visualization Comput. Graphics, 9(2), pp. 191–205. [CrossRef]
Riegler, G. , Ulusoy, A. O. , and Geiger, A. , 2017, “ Octnet: Learning Deep 3D Representations at High Resolutions,” Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, July 21–26.
Theano Development Team, 2016, “ Theano: A Python Framework for Fast Computation of Mathematical Expressions,” preprint arXiv:abs/1605.02688.
Kingma, D. , and Ba, J. , 2014, “ Adam: A Method for Stochastic Optimization,” preprint arXiv:1412.6980.
Zeiler, M. D. , and Fergus, R. , 2014, “ Visualizing and Understanding Convolutional Networks,” European Conference on Computer Vision (ECCV), Zürich, Switzerland, Sept. 6–12, pp. 818–833.


Grahic Jump Location
Fig. 1

Cross sections of selected layers of a 3D CNN. These show the activations of certain kernels of the layers in the trained network on the voxelized input shownleft.

Grahic Jump Location
Fig. 2

An artificial neuron. The inputs are represented by xi that are multiplied by the weights wi, summed with a bias term b, and activated by a function f to produce an output y. Each layer type principally defines how the inputs are mapped to theprevious layer, along with which activation function is employed. The rest of the terms are learned.

Grahic Jump Location
Fig. 3

Selected 3 × 3 × 3 learned kernels

Grahic Jump Location
Fig. 4

The convolution and pooling operation

Grahic Jump Location
Fig. 5

The scaling scheme of the functional quantity targets

Grahic Jump Location
Fig. 6

Confusion matrix for the binary (qualitative) variation of this network

Grahic Jump Location
Fig. 7

Confusion matrix for the softmax regression variation of this network

Grahic Jump Location
Fig. 8

Confusion matrix for the absolute regression variation of this network

Grahic Jump Location
Fig. 9

Confusion matrix for the aggregated left out classes

Grahic Jump Location
Fig. 10

Performance on this task by VoxNet Network [34]

Grahic Jump Location
Fig. 11

Activations of the left out networks on novel inputs for well performing inputs

Grahic Jump Location
Fig. 12

Headwear from the dataset [33], the left helmet is functional, while center is purely decorative. Right depicts the confusion matrix of this experiment.




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In