3D CAD Model Retrieval Based on Feature Fusion

Existing 3D model retrieval techniques focus on the global feature more than local detailed feature are not applicable to 3D CAD models. This paper combines the local feature and global feature to satisfy the needs of mechanical design. We first analyze the limitations of Shape Description (SD) algorithm. Then propose an automatic feature extraction technology based on the local characteristics of the curvature distribution. Next we fuse the extracted feature using a novel method. Lastly, we design an improved K-nearest neighbor algorithm to retrieve models. Experimental results indicate the efficiency and feasibility of the proposed method.

Download Full-text

Toward Effective Mechanical Design Reuse: CAD Model Retrieval Based on General and Partial Shapes

Journal of Mechanical Design ◽

10.1115/1.4000253 ◽

2009 ◽

Vol 131 (12) ◽

Cited By ~ 24

Author(s):

Min Li ◽

Y. F. Zhang ◽

J. Y. H. Fuh ◽

Z. M. Qiu

Keyword(s):

Computer Aided Design ◽

Mechanical Design ◽

Three Dimensional ◽

Cad Model ◽

Model Retrieval ◽

Cad Models ◽

Feature Based ◽

Novel Method ◽

Aided Design ◽

Model Similarity

In product design, a large proportion of three-dimensional (3D) computer-aided design (CAD) models can be reused to facilitate future product development due to their similarities in function and shape. This paper presents a novel method that incorporates modeling knowledge into CAD model similarity assessment to improve the effectiveness of reuse-oriented retrieval. First, knowledge extraction is performed on archived feature-based CAD models to construct feature dependency directed acyclic graph (FDAG). Second, based on the FDAG subgraph decomposition, two useful component partitioning approaches are developed to extract simplified essential shapes and meaningful subparts from CAD models. Third, the extracted shapes and their FDAG subgraphs are indexed. Finally, the indexed shapes that are similar to user-sketched queries are retrieved to reuse, and FDAG information of the retrieved shapes is provided as redesign suggestions. Experimental results suggest that the incorporation of modeling knowledge greatly facilitates CAD model retrieval and reuse. Algorithm evaluations also show the presented method outperforms other 3D retrieval methods.

Download Full-text

Evaluating the Impact of Virtual Reality on Mechanical Design Education

ASME-AFM 2009 World Conference on Innovative Virtual Reality ◽

10.1115/winvr2009-722 ◽

2009 ◽

Cited By ~ 2

Author(s):

Margherita Peruzzini ◽

Maura Mengoni ◽

Michele Germani

Keyword(s):

Virtual Reality ◽

Design Education ◽

Mechanical Design ◽

Design Activity ◽

Innovative Teaching ◽

3D Cad ◽

Technological Advances ◽

Cad Models ◽

Definition Of ◽

The Impact

The promise of Virtual Reality in design environments is to facilitate the interaction with digital models and to enhance the results of design activity. Design education is one of the most recent and interesting applications. Thanks to technological advances in human-computer interfaces, Virtual Reality represents a new way to stimulate design students and to develop innovative teaching methods. The paper explores the impact of Virtual Reality technologies on design learning, with particular attention to mechanical product design. It is focused on the analysis of cognitive and technical aspects of learning processes and the definition of a proper evaluation protocol. The protocol is based on the classification of the most meaningful activities in mechanical engineering teaching and the identification of a set of metrics that enable to objectively evaluate the learning process. Assessing how VR supports design education, an experimental study is proposed. It is based on the comparison of three different approaches performed by two-dimensional drawings, by 3D CAD models and, finally, by virtual reality technologies.

Download Full-text

Profiling the Desirable CAD Trainee: Technical Background, Personality Attributes, and Learning Preferences

Journal of Mechanical Design ◽

10.1115/1.4000455 ◽

2009 ◽

Vol 131 (12) ◽

Cited By ~ 6

Author(s):

Ramsey F. Hamade

Keyword(s):

Learning Styles ◽

Learning Style ◽

Computer Aided Design ◽

Mechanical Design ◽

Three Dimensional ◽

Learning Preferences ◽

Actual Behavior ◽

3D Cad ◽

Active Sensor ◽

Cad Models

This research aims to explore some of the underlying reasoning for why some individuals acquire mechanical computer-aided design (CAD) skills with relative ease while some others seem to falter. A methodical study was performed by monitoring 74 mechanical engineering seniors (over a 3 year period) in a semester-long formal training on a commercial three-dimensional (3D) CAD package (PRO/ENGINEER, version WILDFIRE). The study methodically explored the trainees’ (1) technical background, (2) personality attributes, and (3) learning preferences. Investigating the technical background included quantifying the trainees’ following technical foundations: basic math, advanced math, CAD-related math, computer science and engineering, methodologies related to CAD, graphics, and mechanical design. Determining the trainees’ personality attributes included exploring their willingness-to-learn CAD, perception, gauging their actual behavior (practice), and CAD syntax learned throughout the training. Trainees’ learning preferences were determined according to the index of learning styles (ILS). Furthermore, and in order to assess the trainees’ progress in CAD knowledge acquisition, competency tests were conducted at four intervals throughout the semester-long study. The assessment involved hands-on modeling of CAD test parts of comparable complexity. At the conclusion of the study, statistical methods were used to correlate the trainees’ attributes with their monitored performance. Only a fraction (17 out of a class of 74 trainees or 1 in 4) of the trainees were found to fit the “star CAD trainee” mold, which is defined here as someone who is fast on the tube and perceptive enough to see through the procedure of building progressively more sophisticated CAD models. A profile of the star CAD trainee character emerges as an individual who is technically competent, perceptive, and motivated. The study also reveals these most desirable trainees to possess an active, sensor, visual, and sequential learning style.

Download Full-text

3D CAD Model Retrieval Algorithm Based on Accessibility Cone Distributions

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.834-836.1444 ◽

2013 ◽

Vol 834-836 ◽

pp. 1444-1447

Author(s):

Wei Qiang

Keyword(s):

Engineering Application ◽

Similarity Coefficient ◽

Retrieval Algorithm ◽

Cad Model ◽

3D Cad ◽

Planar Grid ◽

Model Retrieval ◽

Cad Models ◽

The Given ◽

3D Cad Model Retrieval

To reuse 3D CAD models more efficiently, a new 3D CAD model retrieval algorithm based on accessibility cone distributions is proposed. Firstly, a sufficiently large number of random sample points on surface of 3D CAD model are taken and the normal direction of each sample point is recorded. Then, the accessibility cone of the given sampled point is computed. Secondly, a planar grid is constructed to express the accessibility cone distribution by obtaining a statistic data of the sampled points. Lastly, the L1 distance metric method is taken to compute the similarity between the two accessibility cone matrices, which can give the similarity coefficient for two compared 3D CAD models. Experiments results show that the algorithm can effectively support 3D CAD model retrieval, and the efficiency meets the requirement of engineering application.

Download Full-text

Bag-of-Features Sampling Techniques for 3D CAD Model Retrieval

Volume 2: 31st Computers and Information in Engineering Conference, Parts A and B ◽

10.1115/detc2011-48064 ◽

2011 ◽

Author(s):

Y. Wang ◽

W. F. Lu ◽

J. Y. H. Fuh ◽

Y. S. Wong

Keyword(s):

Feature Detection ◽

Sampling Techniques ◽

Cad Model ◽

Sampling Strategies ◽

3D Cad ◽

Bag Of Features ◽

Model Retrieval ◽

Cad Models ◽

Dense Sampling ◽

3D Cad Model Retrieval

This paper investigates two sampling strategies, dense sampling and PHOW sampling, for bag-of-features 3D CAD model retrieval. Previous methods [1] use original salient SIFT feature detection for general 3D model retrieval which does not suit the need for CAD models representation. CAD models contain mostly piecewise-smooth surfaces and thus only sharp edges can be described. To overcome these limitations, two new sampling strategies are investigated to improve the feature extraction process. Dense sampling extracts SIFT features on regular spatial grids with even spacing. Pyramid Histogram Of visual Words (PHOW) [2] extracts features on repeatedly finer scales. Both the two sampling methods extract features that are covered the whole shape. In addition, the influences of codebook size and distance metric are also studied to optimize the retrieval performance. Experiments on Purdue Engineering Benchmark [3] show that the proposed sampling techniques achieve better retrieval accuracy than the original salient SIFT sampling method.

Download Full-text

3D CAD Model Retrieval Based on Oriented Bounding Box and Normals Distribution

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.496-500.2324 ◽

2014 ◽

Vol 496-500 ◽

pp. 2324-2327

Author(s):

Qiang Chen ◽

Yong Mei Yu

Keyword(s):

Experimental Results ◽

Cad Model ◽

Global Feature ◽

Shape Distribution ◽

3D Cad ◽

Bounding Box ◽

Model Retrieval ◽

3D Cad Model Retrieval ◽

Initial Retrieval

Shape Distribution (SD) describes the global feature of 3D CAD model which can be used to distinguish one model from others. But sometimes, different models may have the similar SD features. In this case SD is not suitable for 3D CAD model retrieval. Although two models have the same SD features, their oriented bounding box (OBB) and normals distribution may differ from each other. In this paper, a new algorithm based on OBB and normals distribution is proposed to tackle this problem. SD feature is used for initial retrieval, then OBB and normals distribution are used for fine retrieval. Experimental results indicate the efficiency and feasibility of the proposed method.

Download Full-text

Automatized Evaluation of Students’ CAD Models

Education Sciences ◽

10.3390/educsci11040145 ◽

2021 ◽

Vol 11 (4) ◽

pp. 145

Author(s):

Nenad Bojcetic ◽

Filip Valjak ◽

Dragan Zezelj ◽

Tomislav Martinec

Keyword(s):

Computer Aided Design ◽

Three Dimensional ◽

Computer Application ◽

Test Cases ◽

Cad Model ◽

Computer Solution ◽

3D Cad ◽

Computer Aided ◽

Cad Models ◽

Aided Design

The article describes an attempt to address the automatized evaluation of student three-dimensional (3D) computer-aided design (CAD) models. The driving idea was conceptualized under the restraints of the COVID pandemic, driven by the problem of evaluating a large number of student 3D CAD models. The described computer solution can be implemented using any CAD computer application that supports customization. Test cases showed that the proposed solution was valid and could be used to evaluate many students’ 3D CAD models. The computer solution can also be used to help students to better understand how to create a 3D CAD model, thereby complying with the requirements of particular teachers.

Download Full-text