Search

In computer-aided design (CAD) and process planning (CAPP), feature recognition is an essential task which identifies the feature type of a 3D model for computer-aided manufacturing (CAM). In general, traditional rule-based feature recognition methods are computationally expensive, and dependent on surface or feature types. In addition, it is quite challenging to design proper rules to recognise intersecting features. Recently, a learning-based method, named FeatureNet, has been proposed for both single and multi-feature recognition. This is a general purpose algorithm which is capable of dealing with any type of features and surfaces. However, thousands of annotated training samples for each feature are required for training to achieve a high single feature recognition accuracy, which makes this technique difficult to use in practice. In addition, experimental results suggest that multi-feature recognition part in this approach works very well on intersecting features with small overlapping areas, but may fail when recognising highly intersecting features. To address the above issues, a deep learning framework based on multiple sectional view (MSV) representation named MsvNet is proposed for feature recognition. In the MsvNet, MSVs of a 3D model are collected as the input of the deep network, and the information achieved from different views are combined via the neural network for recognition. In addition to MSV representation, some advanced learning strategies (e.g. transfer learning, data augmentation) are also employed to minimise the number of training samples and training time. For multi-feature recognition, a novel view-based feature segmentation and recognition algorithm is presented. Experimental results demonstrate that the proposed approach can achieve the state-of-the-art single feature performance on the FeatureNet dataset with only a very small number of training samples (e.g. 8–32 samples for each feature), and outperforms the state-of-the-art learning-based multi-feature recognition method in terms of recognition performances. [ABSTRACT FROM AUTHOR]

In this paper, a tolerance representation model for generating tolerance specification schemes and corresponding tolerance zones is proposed to meet the requirement of the representation of tolerance information semantics. This model is hierarchically organized and consists of five layers. They are component, geometric feature, variational geometric constraint, tolerance specification scheme, and tolerance zone layers. The mating relations between components in the component layer, the mating relations between geometric features in the geometric feature layer, the variational geometric constraints between geometric features in the variational geometric constraint layer, the tolerance specification schemes of component in the tolerance specification scheme layer, and the tolerance zones of tolerance specification schemes in the tolerance zone layer are formally defined by one or more adjacency matrices, respectively. Based on the model, a method for generating tolerance specification schemes for component and their resultant tolerance zones is designed. This method shows how to adopt a top-down strategy to carry out tolerance specification for an arbitrary assembly designed in a CAD system. The paper also provides a practical example to illustrate how the method works. [ABSTRACT FROM AUTHOR]

The optimized design and reliable measurement of surface texture are essential to guarantee the functional performance of a geometric product. Current support tools are however often limited in functionality, integrity and efficiency. In this paper, an integrated surface texture information system for design, manufacture and measurement, called “CatSurf”, has been designed and developed, which aims to facilitate rapid and flexible manufacturing requirements. A category theory based knowledge acquisition and knowledge representation mechanism has been devised to retrieve and organize knowledge from various Geometrical Product Specifications (GPS) documents in surface texture. Two modules (for profile and areal surface texture) each with five components are developed in the CatSurf. It also focuses on integrating the surface texture information into a Computer-aided Technology (CAx) framework. Two test cases demonstrate design process of specifications for the profile and areal surface texture in AutoCAD and SolidWorks environments respectively. [ABSTRACT FROM AUTHOR]

In this paper, an ontology-supported case-based reasoning approach for computer-aided tolerance specification is proposed. This approach firstly considers the past tolerance specification problems and their schemes as previous cases and the new tolerance specification problems as target cases and uses an ontology to represent previous and target cases. Then certain ontology-based similarity measure is used to assess the similarity between the toleranced features of target and previous cases, the similarity between the part features of target and previous cases, and the similarity between the topological relations of target and previous cases. Based on these similarities, an ontology-based similarity measure for computing the similarity between target and previous cases is designed, and an algorithm for establishing such similarity measure with high accuracy and retrieving similar previous cases for a target case with this similarity measure is presented. This algorithm shows how to linearly combine the similarity of toleranced features, the similarity of part features, and the similarity of topological relations to assess the similarity between target and previous cases to implement retrieval of previous cases under the prerequisite of ensuring the highest accuracy of the similarity measure. The paper also reports a prototype implementation of the proposed approach, provides an example to illustrate how the approach works, and evaluates the approach via theoretical and experimental comparisons. [ABSTRACT FROM AUTHOR]

Semantic similarity measure technology based approach is one of the most popular approaches aiming at implementing semantic mapping between two different CAD model data ontologies. The most important problem in this approach is how to measure the semantic similarities of concepts between two different ontologies. A number of measure methods focusing on this problem have been presented in recent years. Each method can work well between its specific ontologies. But it is unclear how accurate the measured semantic similarities in these methods are. Moreover, there is yet no evidence that any of the methods presented how to select a measure with high similarity calculation accuracy. To compensate for such deficiencies, this paper proposes a method for selecting a semantic similarity measure with high similarity calculation accuracy for concepts in two different CAD model data ontologies. In this method, the similarity calculation accuracy of each candidate measure is quantified using Pearson correlation coefficient or residual sum of squares. The measure with high similarity calculation accuracy is selected through a comparison of the Pearson correlation coefficients or the residual sums of squares of all candidate measures. The paper also reports an implementation of the proposed method, provides an example to show how the method works, and evaluates the method by theoretical and experimental comparisons. The evaluation result suggests that the measure selected by the proposed method has good human correlation and high similarity calculation accuracy. [ABSTRACT FROM AUTHOR]