Literal-Aware Knowledge Graph Embedding for Welding Quality Monitoring: A Bosch Case

TL;DR

This paper explores the application of knowledge graph embedding techniques to monitor welding quality in manufacturing, specifically in the automotive industry, addressing complex classification challenges with real industrial data.

Contribution

It introduces a novel approach applying literal-aware KGE methods to industrial welding quality monitoring, highlighting their potential and limitations in a real-world setting.

Findings

KGE methods show promise for industrial quality monitoring

Limitations identified in current KGE approaches for this task

Experimental results on real data demonstrate feasibility

Abstract

Recently there has been a series of studies in knowledge graph embedding (KGE), which attempts to learn the embeddings of the entities and relations as numerical vectors and mathematical mappings via machine learning (ML). However, there has been limited research that applies KGE for industrial problems in manufacturing. This paper investigates whether and to what extent KGE can be used for an important problem: quality monitoring for welding in manufacturing industry, which is an impactful process accounting for production of millions of cars annually. The work is in line with Bosch research of data-driven solutions that intends to replace the traditional way of destroying cars, which is extremely costly and produces waste. The paper tackles two very challenging questions simultaneously: how large the welding spot diameter is; and to which car body the welded spot belongs to. The problem setting is difficult for traditional ML because there exist a high number of car bodies that should be assigned as class labels. We formulate the problem as link prediction, and experimented popular KGE methods on real industry data, with consideration of literals. Our results reveal both limitations and promising aspects of adapted KGE methods.