Assembly Information Model Based on Knowledge Graph

Abstract

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.

Overview of virtual assembly for array antennas and future work under industry 4.0

“…As for the research on assembly information model, Zhiyu Chen et al 4 based on the basic characteristics of assemblies and assembly relationships, for the assemblability of parts reflected by the errors of assembly boundaries, and analyzed the degree of assembly between parts by calculating the values of overfitting boundaries. bronsvoort H et al 5 oriented integrated product model, built wood for the assemblies and parts in them separately, and analyzed the assembly relationship from the connection information perspective focused on the assembly relationships and applied the model to a variety of planning and assembly simulation studies.…”

Model-based approach for the automatic inclusion of production considerations in the conceptual design of aircraft structures

“…(iii) The methodology depends on the use of software tools (such as Product Lifecycle Management (PLM) or manufacturability analysis) not suited for automation/conceptual design [9][10][11]. (iv) Aspects of manufacturing ( [3,4,8]) and assembly ( [12][13][14][15][16]) are not considered together. This paper presents a new model, called the Manufacturing Information Model (MIM), which focuses on formalizing and documenting manufacturing and assembly knowledge while overcoming the challenges stated above.…”

Knowledge Graph Construction of End-of-Life Electric Vehicle Batteries for Robotic Disassembly

“…An assembly information model based on a knowledge graph can facilitate the sharing of assembly process documentation information and increase the rate of information interaction during the development phase of the assembly process [11]. The advantage of EV battery knowledge graphs lies in the ability to display the first level, or even the second and third levels, of surrounding nodes intuitively on a graph.…”