A feature-based method of rapidly detecting global exact symmetries in CAD models

Jiang, Junfeng; Chen, Zhengming; He, Kunjin

doi:10.1016/j.cad.2013.04.005

Cited by 22 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This property greatly reduces the search field for symmetry extraction. Among the research works more targeted to engineering applications, the algorithms aimed at partial symmetry detection [1,4,5,6,7] share many similarities in their structure and the main stages of these approaches can be summarized as follows:…”

Section: Related Workmentioning

confidence: 99%

“…During the product development process, symmetry properties of mechanical components can be used to compute tool path trajectories of a machining process and to structure these trajectories in order to optimize the tool displacements. In practice, this helps locating the machining and assembly arms when the product needs to be machined and assembled [5]. Similarly, in the shape adaptation process for finiteelement analysis symmetries can be used to facilitate the simplification of the model for the validation stage [4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Regularities in CAD Part and Assembly Models

Chiang

Giannini

Monti

2016

Product Lifecycle Management in the Era of Internet of Things

View full text Add to dashboard Cite

The identification of regular patterns of congruent features in CAD models can enrich the object representation by a set of higher level information, which can be exploited for the reuse of the part model. In this paper, a method for the detection of regular patterns and symmetries of repeated subparts in B-Rep part and assembly models is proposed. The method is implemented as a plug-in of a commercial CAD system and detects linear, circular translational, rotational and reflectional patterns of congruent sub-parts of the model.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Identification of Regularities in CAD Part and Assembly Models

Chiang

Giannini

Monti

2016

Product Lifecycle Management in the Era of Internet of Things

View full text Add to dashboard Cite

show abstract

“…Liu et al [2] proposed a back propagation neural network method based on fusion edge detection to identify precision parts. Jiang et al [3] proposed a method to identify precision parts by feature classification and merging symmetry; however, the method of using face as a symmetric identification unit is inefficient. Inic et al [4] proposed a vehicle part shape detection method based on milling simulation.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Recognition Method for 0.8 cm Darning Needles and KR22 Bearings Based on Convolution Neural Networks and Data Increase

Yang

Zong

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

The complexity of the background and the similarities between different types of precision parts, especially in the high-speed movement of conveyor belts in complex industrial scenes, pose immense challenges to the object recognition of precision parts due to diversity in illumination. This study presents a real-time object recognition method for 0.8 cm darning needles and KR22 bearing machine parts under a complex industrial background. First, we propose an image data increase algorithm based on directional flip, and we establish two types of dataset, namely, real data and increased data. We focus on increasing recognition accuracy and reducing computation time, and we design a multilayer feature fusion network to obtain feature information. Subsequently, we propose an accurate method for classifying precision parts on the basis of non-maximal suppression, and then form an improved You Only Look Once (YOLO) V3 network. We implement this method and compare it with models in our real-time industrial object detection experimental platform. Finally, experiments on real and increased datasets show that the proposed method outperforms the YOLO V3 algorithm in terms of recognition accuracy and robustness.

show abstract

“…A feature-based CAD model contains not only the B-Rep representation but also the abundant feature information such as feature types, parameters, sketches, references and building histories. We put forward a method [7] to rapidly detect symmetries in CAD models by making full use of feature information. It shows that our last feature-based method has an extremely high performance in comparison with face-based methods.…”

Section: Introductionmentioning

confidence: 99%

A feature-based approach for detecting global symmetries in CAD models with free-form surfaces

Jiang

Chen

2013

2013 International Conference on Computer-Aided Design and Computer Graphics

Self Cite

View full text Add to dashboard Cite

Detecting global symmetries in CAD models with free-form surfaces (FFS CAD models) is of great importance in the research of CAD/CAE/CAM integration. A feature-based approach is proposed to rapidly detect global symmetries in FFS CAD models. The key problem is how to detect global symmetries of surface (or curve) models by using feature information. First, our previous basic theories on detecting solid models' symmetries are expanded to handle surface (or curve) models. Then, the feature tuples are used to uniquely describe the surface (or curve) models' non-unique design histories. Based on these studies, the feature reference tree and the parent-child relationships of topological elements are built to construct feature tuples. Finally, the symmetries of the surface (or curve) models are robustly and rapidly detected by using feature information in feature tuples and using the symmetries that have already been detected in solid, surface and curve layers. Experiments show that the FFS CAD models' symmetries can be robustly and rapidly detected by using our approach. I. INTRODUCTIONDetecting the CAD models' symmetries can improve the efficiency in the following process: performing finite element analyses [1], recognizing machining features [2], retrieving CAD models [3], analyzing design aesthetics [4] and detecting design intent of CAD models from the reverse engineering [5]. Our paper's purpose is to rapidly detect the global rotational and reflectional symmetries in CAD models.The previous methods are face-based methods [5][6], which take face as the basic unit for symmetry detection. The detection efficiency of face-based methods decreases sharply with even a tiny increase in the number of faces. Currently, the parametric feature-based modeling technique is becoming mature and has been widely adopted by most CAD modelers. A feature-based CAD model is created through the combinations of finite features. A feature-based CAD model contains not only the B-Rep representation but also the abundant feature information such as feature types, parameters, sketches, references and building histories. We put forward a method [7] to rapidly detect symmetries in CAD models by making full use of feature information. It

show abstract

A feature-based method of rapidly detecting global exact symmetries in CAD models

Cited by 22 publications

References 14 publications

Identification of Regularities in CAD Part and Assembly Models

Identification of Regularities in CAD Part and Assembly Models

Real-Time Recognition Method for 0.8 cm Darning Needles and KR22 Bearings Based on Convolution Neural Networks and Data Increase

A feature-based approach for detecting global symmetries in CAD models with free-form surfaces

Contact Info

Product

Resources

About