Search results

The purpose of this paper is to propose a three-dimensional (3D) assembly model retrieval method based on assembling semantic information to address semantic mismatches, poor accuracy and low efficiency in existing 3D assembly model retrieval methods.

The paper proposes an assembly model retrieval method. First, assembly information retrieval is performed, and 3D models that conform to the design intention of the assembly are found by retrieving the code. On this basis, because there are conjugate subgraphs between attributed adjacency graphs (AAG) that have an assembly relationship, the assembly model geometric retrieval is translated into a problem of finding AAGs with a conjugate subgraph. Finally, the frequent subgraph mining method is used to retrieve AAGs with conjugate subgraphs.

The method improved the efficiency and accuracy of assembly model retrieval.

The examples illustrate the specific retrieval process and verify the feasibility and reasonability of the assembly model retrieval method in practical applications.

The assembly model retrieval method in the paper is an original method. Compared with other methods, good results were obtained.

Handling feature interaction is an unsolved issue in feature recognition approach. This paper presents a method for recognizing the presence of feature interactions. First, based on the convex hull concept, a so‐called reference face is defined. Second, by adding the reference face into the attributes adjacency graph (AAG), a modified AAG is obtained. Two general feature types, namely depression and protrusion features, are identified by the reference face. The basic features such as slots, pockets and bosses are represented by the modified AAG. Any features that remain unrecognized by the modified AAG are regarded as interacting features. The types of reference faces and feature face are also classified. Based on the kind of face classification, the interacting features are finally recognized via a process of virtual face extension and volume addition.

Virtual assembly process plays an important role in assembly design of complex product and is typically time- and resource-intensive. This paper aims to investigate a dynamic assembly simplification approach in order to demonstrate and interact with virtual assembly process of complex product in real time.

The proposed approach regards the virtual assembly process of complex product as an incremental growth process of dynamic assembly. During the growth process, the current-assembled-state assembly model is simplified with appearance preserved by detecting and removing its invisible features, and the to-be-assembled components are simplified with assembly features preserved using conjugated subgraphs matching method based on an improved subgraph isomorphism algorithm.

The dynamic assembly simplification approach is applied successfully to reduce the complexity of computer aided design models during the virtual assembly process and it is proved by several cases.

A new assembly features definition is proposed based on the notion of “conjugation” to assist the assembly features recognition, which is a main step of the dynamic assembly simplification and has been translated into conjugated subgraphs matching problem. And an improved subgraph isomorphism algorithm is presented to address this problem.

Three-dimensional computer-aided design (CAD) assembly model has become important resource for design reuse in enterprises, which implicates plenty of design intent, assembly intent, design experience knowledge and functional structures. To acquire quickly CAD assembly models associated with specific functions by using product function requirement information in the product conceptual design phase for model reuse, this paper aims to find an approach for structure-function correlations analysis and functional semantic annotation of mechanical CAD assembly model before functional semantic-based assembly retrieval.

An approach for structure-function correlations analysis and functional semantic annotation of CAD assembly model is proposed. First, the product knowledge model is constructed based on ontology including design knowledge and function knowledge. Then, CAD assembly model is represented by part attributed adjacency graph and partitioned into multiple functional regions. Assembly region and flow-activity region are defined for structure-function correlations analysis of CAD assembly model. Meanwhile, the extraction process of assembly region and flow-activity region is given in detail. Furthermore, structure-function correlations analysis and functional semantic annotation are achieved by considering comprehensively assembly structure and assembled part shape structure in CAD assembly model. After that, a structure-function relation model is established based on polychromatic sets for expressing explicitly and formally relationships between functional structures, assembled parts and functional semantics.

The correlation between structure and function is analyzed effectively, and functional semantics corresponding to structures in CAD assembly model are labeled. Additionally, the relationships between functional structures, assembled parts and functional semantics can be described explicitly and formally.

The approach can be used to help designers accomplish functional semantic annotation of CAD assembly models in model repository, which provides support for functional semantic-based CAD assembly retrieval in the product conceptual design phase. These assembly models can be reused for product structure design and assembly process design.

The paper proposes a novel approach for structure-function correlations analysis and functional semantic annotation of mechanical CAD assembly model. Functional structures in assembly model are extracted and analyzed from the point of view of assembly structure and function part structure. Furthermore, the correlation relation between structures, assembled parts and functional semantics is expressed explicitly and formally based on polychromatic sets.

Computer aided process planning (CAPP) is an effective way to integrate computer aided design and manufacturing (CAD/CAM). There are two key issues with the integration: design input in a feature‐based model and acquisition and representation of process knowledge especially empirical knowledge. This paper presents a state of the art review of research in computer integrated manufacturing using neural network techniques. Neural network‐based methods can eliminate some drawbacks of the conventional approaches, and therefore have attracted research attention particularly in recent years. The four main issues related to the neural network‐based techniques, namely the topology of the neural network, input representation, the training method and the output format are discussed with the current systems. The outcomes of research using neural network techniques are studied, and the limitations and future work are outlined.

This study aims to compute 3D model similarity by extracting and comparing shape features from the neutral files.

In this work, the clear text encoding document STEP (Standard for The Exchange of Product model data) of 3D models was analysed, and the models were characterized by two-depth trees consisting of both surface and shell nodes. All surfaces in the STEP files can be subdivided into three kinds, namely, free, analytical and loop surfaces. Surface similarity is defined by the variation coefficients of distances between data points on two surfaces, and subsequently, the shell similarity and 3D model similarity are determined using an optimal algorithm for bipartite graph matching.

This approach is used to experimentally verify the effectiveness of the 3D model similarity algorithm.

The novelty of this study research lies in the computation of 3D model similarity by comparison of all surfaces. In addition, the study makes several key observations: surfaces reflect the most information concerning the functions and attributes of a 3D model and so the similarity between surfaces generates more comprehensive content (both external and internal); semantic-based 3D retrieval can be obtained under the premise of comparison of surface semantics; and more accurate similarity of 3D models can be obtained using the optimal algorithm of bipartite graph matching for all surfaces.

Complex mechanical 3D computer-aided design (CAD) model embodies rich implicit design knowledge. Through discovering the key function parts and key function module in 3D CAD assembly model in advance, it can promote the designers’ understanding and reuse efficiency of 3D assembly model in design reuse.

An approach for discovering key function module in complex mechanical 3D CAD assembly model is proposed. First, assembly network for 3D CAD assembly model is constructed, where the topology structure characteristics of 3D assembly model are analyzed based on complex network centrality. The degree centrality, closeness centrality, betweenness centrality and mutual information of node are used to evaluate the importance of the parts in 3D assembly model. Then, a multi-attribute decision model for part-node importance is established, and the comprehensive evaluation for key function parts in 3D assembly model is accomplished by combining Analytic Hierarchy Process and Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS). Subsequently, a community discovery of function module in assembly model-based Clauset–Newman–Moore (CNM)-Centrality is given in details. Finally, 3D CAD assembly model of worm gear reducer is taken as an example to verify the effectiveness and feasibility of proposed method.

The key function part in CAD assembly model is evaluated comprehensively considering assembly topology more objectively. In addition, the key function module containing key function part is discovered from CAD assembly model by using CNM-Centrality-based community discovery.

The approach can be used for discovering important design knowledge from complex CAD assembly model when reusing the assembly model. It can help designers capture and understand the design thinking and intent, improve the reuse efficiency and quality.

The paper first proposes an approach for discovering key function module in complex mechanical 3D CAD assembly model taking advantage of complex network theory, where the key function part is evaluated using node centrality and TOPSIS, and the key function module is identified based on community discovery.

Recognition of machining features is an essential step in the development of efficient‐automated process plans from solid modeling data. This process represents the effective interpretation of the geometric data in a computer‐aided design (CAD) model to create semantically rich manufacture‐oriented features such as holes, slots, pockets, and others that may be exploited in downstream computer‐aided manufacturing/computer‐aided process planning applications. Most successful approaches towards feature recognition have been based on hint‐based procedures operating on a 3D B‐Rep model. The purpose of this paper is to propose an approach by which features are identified in a solid model that is built mainly using sweep solid modeling operations.

Part geometric model is queried for both 2D and 3D geometric elements. Feature hints are generated by an analysis of sweep operations and their 2D sketches, which are defined prior to building the solid model. These hints are then analyzed and validated by applying a two‐phase approach: 2D validation in the sketch geometry; and 3D validation in the final constructive solid geometry tree of the solid model. Valid hints are the basis for the creation of a machining feature model that can be input to a process planning module. In addition, interaction information for machining features is extracted from both 2D hints and their 3D validation. Feature interaction information is obtained by analysis of face/edge neighborhood and their geometric relations in both 2D and 3D spaces.

This approach provides a benefit of performing the majority of geometric analysis in 2D space which is much simpler and computationally more efficient than corresponding analyses in 3D space. Only minimal portion of the analysis is computed on 3D solid models. The approach is implemented in the Java‐based prototype system and is demonstrated and tested on several real‐world examples.

The initial prototype implementation is limited to prismatic parts and linear sweep. Only hole and slot feature can be recognized due to the fact that pocket recognition appears to be trivial.

Motivation for this approach is in the fact that sweep operations from 2D sketches are very commonly used in the mechanical design process, so the approach may be applicable in practical applications of CAD.

This novel approach provides value to product designers and manufacturing planners since linear (extrusion) and circular (rotation) sweeps are very popular design engineer tools.

The purpose of this paper is to assist facility designers decide when to use the graph‐theoretic (GTH) approach to develop a block layout and when to seek another alternative that requires a lesser effort. Difficulties encountered when a GTH block layout is developed from an adjacency graph could force designers to sacrifice or change some of the adjacencies of the adjacency graph in the GTH block layout. Consequently, the value of the objective function of a GTH block layout could become less than what would be expected from the GTH approach.

A computational study is performed to assess the value of the objective function of block layouts produced by the GTH approach when adjacencies of the adjacency graph are deleted or changed in the GTH block layout and two of the procedures in the literature.

The computational study reveals that the magnitude of the decline in the value of the objective function of the GTH block layout renders it comparable to values obtained by the two procedures selected from the literature.

The results of the study could motivate layout designers to resort to various approaches to develop a block layout rather than sacrifice some adjacencies of the adjacency graph in the GTH block layout, which would adversely affect its objective function value.

A community demonstrates the unique qualities and relationships between its members that distinguish it from other communities within a network. Network analysis relies heavily on community detection. Despite the traditional spectral clustering and statistical inference methods, deep learning techniques for community detection have grown in popularity due to their ease of processing high-dimensional network data. Graph convolutional neural networks (GCNNs) have received much attention recently and have developed into a potential and ubiquitous method for directly detecting communities on graphs. Inspired by the promising results of graph convolutional networks (GCNs) in analyzing graph structure data, a novel community graph convolutional network (CommunityGCN) as a semi-supervised node classification model has been proposed and compared with recent baseline methods graph attention network (GAT), GCN-based technique for unsupervised community detection and Markov random fields combined with graph convolutional network (MRFasGCN).

This work presents the method for identifying communities that combines the notion of node classification via message passing with the architecture of a semi-supervised graph neural network. Six benchmark datasets, namely, Cora, CiteSeer, ACM, Karate, IMDB and Facebook, have been used in the experimentation.

In the first set of experiments, the scaled normalized average matrix of all neighbor's features including the node itself was obtained, followed by obtaining the weighted average matrix of low-dimensional nodes. In the second set of experiments, the average weighted matrix was forwarded to the GCN with two layers and the activation function for predicting the node class was applied. The results demonstrate that node classification with GCN can improve the performance of identifying communities on graph datasets.

The experiment reveals that the CommunityGCN approach has given better results with accuracy, normalized mutual information, F1 and modularity scores of 91.26, 79.9, 92.58 and 70.5 per cent, respectively, for detecting communities in the graph network, which is much greater than the range of 55.7–87.07 per cent reported in previous literature. Thus, it has been concluded that the GCN with node classification models has improved the accuracy.