Information Modeling and Visualization of Assembly Fat Model for Large-Scale Product

Yang

et al. 2014

KEM

Self Cite

With the rapid development of 3D CAD technology, 3D assembly process is playing an important role in the on-site assembly. A closed-loop control method and three-dimensional site visualization technology site is presented. The methodology takes into account CAD design stage, assembly process design, site assembly and site inspection. The method includes three key technologies: the verification process technology of three-dimensional assembly process, optimization and process simulation techniques of site assembly, closed-loop control technology of assembly process quality inspection. Finally, the method and technology has applied in the actual assembly, and achieved good results.

Section: Assembly Process Information Modeling and Storagementioning

confidence: 99%

The Site Visualization and Closed-Loop Control for 3D Assembly Process

Zhang

Yang

et al. 2014

KEM

Self Cite

“…In brief, in order to generate expert knowledge to guide assembly operations, it is necessary to build an assembly information model that can integrate information from the CAD model and the assembly process. Currently, there are several approaches to model assembly process information, including objectoriented model (Wang et al 2010), XML-based model (Bao et al 2013), Petri network-based model (Yang, Han, and Pan 2014), and ontology-based model (Sayed and Lohse 2014). Specifically, the object-oriented model is difficult to handle the information interaction between heterogeneous systems.…”

Section: Introductionmentioning

confidence: 99%

KGAssembly: Knowledge graph-driven assembly process generation and evaluation for complex components

Zhou

International Journal of Computer Integrated Manufacturing

Chen

et al. 2021

The semantic information of process documents for the assembly of complex components plays an important role in the guidance of assembly operations and the feasibility evaluation of process plans. There are many types of semantic elements contained in assembly process documents. The semantic relationship between assembly elements is complex. Additionally, there is a lack of effective modeling method to deal with the implicit associative semantic knowledge that exists among existing assembly process cases. In this case, it is a great challenge to use the professional knowledge in assembly process documents to guide the intelligent decision-making of assembly process planning and the intelligent analysis of assembly process enforceability evaluation. In this paper, a knowledge graph-driven assembly process generation and evaluation method for complex components is proposed. An APKG (assembly process knowledge graph) model is built. A distributed graph embedding-based model SKGCN (sequence knowledge graph convolutional network) is designed to generate assembly process planning. Furthermore, model and knowledge dual-driven evaluation method for assembly sequences is presented. It provides assembly expert knowledge support for the evaluation method of interference detection of assembly sequence based on point cloud assembly feature recognition. Finally, the approach is evaluated by assembling an aeroengine compressor rotor.

Assembly Information Model Based on Knowledge Graph

Chen

J. Shanghai Jiaotong Univ. (Sci.)

Zheng

et al. 2020

Unsupervised graph alignment finds the one-to-one node correspondence between a pair of attributed graphs by only exploiting graph structure and node features. One category of existing works first computes the node representation and then matches nodes with close embeddings, which is intuitive but lacks a clear objective tailored for graph alignment in the unsupervised setting. The other category reduces the problem to optimal transport (OT) via Gromov-Wasserstein (GW) learning with a well-defined objective but leaves a large room for exploring the design of transport cost. We propose a principled approach to combine their advantages motivated by theoretical analysis of model expressiveness. By noticing the limitation of discriminative power in separating matched and unmatched node pairs, we improve the cost design of GW learning with feature transformation, which enables feature interaction across dimensions. Besides, we propose a simple yet effective embedding-based heuristic inspired by the Weisfeiler-Lehman test and add its prior knowledge to OT for more expressiveness when handling non-Euclidean data. Moreover, we are the first to guarantee the oneto-one matching constraint by reducing the problem to maximum weight matching. The algorithm design effectively combines our OT and embedding-based predictions via stacking, an ensemble learning strategy. We propose a model framework named CombAlign integrating all the above modules to refine node alignment progressively. Through extensive experiments, we demonstrate significant improvements in alignment accuracy compared to state-of-the-art approaches and validate the effectiveness of the proposed modules.