Research Papers: Design Theory and Methodology

A Sketch-Based Tool for Analyzing Vibratory Mechanical Systems

[+] Author and Article Information
Levent Burak Kara

Mechanical Engineering Department, Carnegie Mellon University, Pittsburgh, PA 15213lkara@andrew.cmu.edu

Leslie Gennari

 ExxonMobil Chemical Company, 4500 Bayway Drive, Baytown, TX 77520leslie.m.gennari@exxonmobil.com

Thomas F. Stahovich

Mechanical Engineering Department, University of California, Riverside, CA 92521stahov@engr.ucr.edu

This threshold was selected empirically. A larger threshold would make the system more tolerant of drawing errors but could lead to false positives. A smaller threshold would tend to reduce false positives but could increase false negatives.

In an informal study involving a few engineering students, we observed that users typically draw masses with two or three strokes. An upper limit of five strokes was selected as a means of reducing computational cost without substantial risk of false negatives. This limit has worked well in practice but could be increased if false negatives become a problem.

To ensure consistency across participants, they were asked to sketch vibratory systems that were presented in a schematic drawing. While this study design does provide a meaningful evaluation of our software, it would also be useful to conduct additional studies in which subjects were asked to sketch devices of their choosing.

J. Mech. Des 130(10), 101101 (Sep 10, 2008) (11 pages) doi:10.1115/1.2965595 History: Received September 24, 2007; Revised May 14, 2008; Published September 10, 2008

Sketches are a ubiquitous form of communication in engineering design due to their simplicity and efficiency. However, because of a lack of suitable machine-interpretation techniques, they are virtually unusable with current computer-aided design and engineering tools. The informal nature of sketches and their inherent ambiguity present a number of challenges to the development of such techniques. Here we address one particular challenge, the task of reliably locating and recognizing the intended visual objects from a continuous stream of pen strokes. We present an integrated sketch parsing and recognition approach, based on a novel mark-group-recognize paradigm, which is tailored to the domain of mechanical systems. In the first step of processing, the sketch is examined to identify certain delimiting symbols called “markers.” The remaining pen strokes are then partitioned into distinct clusters, each representing a single symbol. Finally, a trainable symbol recognizer is used to find the best interpretation of each cluster. We have used these techniques to build a sketch-based tool for designing and analyzing vibratory mechanical systems. This tool enables designers to analyze and animate vibratory systems by simply sketching them on a tablet computer. User studies indicate that even first-time users find our tool to be effective.

Copyright © 2008 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

A typical vibratory system created with our software. The program interprets the sketch, performs a simulation of it, and displays the results in the form of live animations and graphs of performance variables. The user can interact with recognized objects to interactively change their parameters.

Grahic Jump Location
Figure 2

Process for interpreting a sketch of a vibratory system

Grahic Jump Location
Figure 3

Masses are identified as “stroke chains.” The mass on the left is described by the stroke chain on the right. The mass recognizer is insensitive to drawing order and direction. (The numbers next to the strokes indicate the drawing order, and the arrowheads indicate the drawing direction.)

Grahic Jump Location
Figure 4

(a) Examples of ground symbols our system can recognize. (b) The definition of a ground symbol is based on the length of the skeleton and the orientation of and separation between hatches.

Grahic Jump Location
Figure 5

(a) The objects remaining to be identified once the masses and the grounds in Fig. 1 have been recognized. (b) The clustering algorithm is run until a single cluster is obtained. The intended clusters, which are encircled with ellipses, are then identified by examining the distance between the two clusters merged at each iteration.

Grahic Jump Location
Figure 6

The dissimilarity score δ increases monotonically with the number of iterations. Sharp leaps, such as the one at iteration 17, usually correspond to forced merges and thus can be used to determine the number of natural clusters.

Grahic Jump Location
Figure 7

The clustering algorithm fails when symbols overlap or when intrasymbol distances are comparable to intersymbol distances

Grahic Jump Location
Figure 8

Processing times of the various program modules for three different sketches. All times are in milliseconds. “Number of markers” includes both ground and mass symbols. Experiments conducted on a 1.7 GHz Pentium 4 machine with 256 Mbytes of RAM.

Grahic Jump Location
Figure 9

Examples of sketches from the user study and their interpretations

Grahic Jump Location
Figure 10

An example sketch attempted by our system. The sketch is accurately recognized except for one spring symbol (enclosed in box at the bottom).




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