Scaling Usability of ML Analytics with Knowledge Graphs: Exemplified with A Bosch Welding Case

Automated welding is heavily used in the automotive industry to produce car bodies by connecting metal parts with welding spots. Modern welding solutions and manufacturing environments produce a high volume of heterogeneous data. Analytics of these data with machine learning (ML) can help to ensure high quality of welding operations. However, due to heterogeneity of data and application scenarios, it is challenging to scale usability of such ML analytics is challenging, namely saving time in developing new solutions and reusing already developed solutions. We address this challenge by relying on knowledge graphs (KG) that not only conveniently allow to integrate welding data, but also to serve as a basis for layering ML-based analytical applications, thus enabling quality monitoring of welding operations. In this work we focus on the construction of a KG for welding that is tailored towards further use for ML applications. Furthermore, we demonstrate how selected ML analytical tasks are supported by this KG.

[1]  Steffen Lamparter,et al.  Use Cases of the Industrial Knowledge Graph at Siemens , 2018, SEMWEB.

[2]  Michael Cochez,et al.  Leveraging Knowledge Graph Embedding Techniques for Industry 4.0 Use Cases , 2018, ArXiv.

[3]  Evgeny Kharlamov,et al.  Faceted Search over Ontology-Enhanced RDF Data , 2014, CIKM.

[4]  Evgeny Kharlamov,et al.  Querying industrial stream-temporal data: An ontology-based visual approach , 2017, J. Ambient Intell. Smart Environ..

[5]  Ralf Mikut,et al.  Predicting Quality of Automated Welding with Machine Learning and Semantics: A Bosch Case Study , 2020, CIKM.

[6]  Evgeny Kharlamov,et al.  Semantic ML for Manufacturing Monitoring at Bosch , 2020, SEMWEB.

[7]  Stefano Borgo,et al.  The Role of Foundational Ontologies in Manufacturing Domain Applications , 2004, CoopIS/DOA/ODBASE.

[8]  Nitisha Jain,et al.  Domain-Specific Knowledge Graph Construction for Semantic Analysis , 2020, ESWC.

[9]  Arthur L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[10]  Patrick Koopmann,et al.  Deductive Module Extraction for Expressive Description Logics , 2020, IJCAI.

[11]  A. Siadat,et al.  MASON: A Proposal For An Ontology Of Manufacturing Domain , 2006, IEEE Workshop on Distributed Intelligent Systems: Collective Intelligence and Its Applications (DIS'06).

[12]  Evgeny Kharlamov,et al.  Ontology-Enhanced Machine Learning: A Bosch Use Case of Welding Quality Monitoring , 2020, SEMWEB.

[13]  Antoine Zimmermann,et al.  A SPARQL Extension for Generating RDF from Heterogeneous Formats , 2017, ESWC.

[14]  Stefan Decker,et al.  Mapping between RDF and XML with XSPARQL , 2012, Journal on Data Semantics.

[15]  Evgeny Kharlamov,et al.  How Semantic Technologies Can Enhance Data Access at Siemens Energy , 2014, SEMWEB.

[16]  Tim Pychynski,et al.  SemFE: Facilitating ML Pipeline Development with Semantics , 2020, CIKM.

[17]  Oscar Corcho,et al.  Knowledge Graph Construction with R2RML and RML: An ETL System-based Overview , 2021, KGCW@ESWC.

[18]  Anees Mehdi,et al.  Ontologies and Reasoning to Capture Product Complexity in Automation Industry , 2017, International Semantic Web Conference.

[19]  Thorsten Liebig,et al.  Building a Knowledge Graph for Products and Solutions in the Automation Industry , 2019, KGB@ESWC.

[20]  Ian Horrocks,et al.  Ontology-based end-user visual query formulation: Why, what, who, how, and which? , 2016, Universal Access in the Information Society.

[21]  Ian Horrocks,et al.  Publishing the Norwegian Petroleum Directorate's FactPages as Semantic Web Data , 2013, SEMWEB.

[22]  Evgeny Kharlamov,et al.  PCSG: Pattern-Coverage Snippet Generation for RDF Datasets , 2021, SEMWEB.

[23]  Peter F. Patel-Schneider,et al.  OWL 2 Web Ontology Language Primer (Second Edition) , 2012 .

[24]  Gong Cheng,et al.  Entity Summarization with User Feedback , 2020, ESWC.

[25]  H. Kagermann.  Change Through Digitization—Value Creation in the Age of Industry 4.0 , 2015 .

[26]  Sanda M. Harabagiu,et al.  Automatic Generation of a Qualified Medical Knowledge Graph and Its Usage for Retrieving Patient Cohorts from Electronic Medical Records , 2013, 2013 IEEE Seventh International Conference on Semantic Computing.

[27]  Evgeny Kharlamov,et al.  A Framework for Evaluating Snippet Generation for Dataset Search , 2019, SEMWEB.

[28]  Nina F. Thornhill,et al.  Improving Root Cause Analysis by Detecting and Removing Transient Changes in Oscillatory Time Series with Application to a 1,3-Butadiene Process , 2019 .

[29]  Ian Horrocks,et al.  SemFacet: Making Hard Faceted Search Easier , 2017, CIKM.

[30]  Lifting Tabular Data to RDF: A Survey , 2021, MTSR.

[31]  Klaus-Dieter Thoben,et al.  Machine learning in manufacturing: advantages, challenges, and applications , 2016 .

[32]  Evgeny Kharlamov,et al.  BANDAR: Benchmarking Snippet Generation Algorithms for (RDF) Dataset Search , 2021, IEEE Transactions on Knowledge and Data Engineering.

[33]  Robert X. Gao,et al.  Deep learning and its applications to machine health monitoring , 2019, Mechanical Systems and Signal Processing.

[35]  Dirk Walther,et al.  Computing Minimal Subsumption Modules of Ontologies , 2018, GCAI.

[36]  Evgeny Kharlamov,et al.  Faceted search over RDF-based knowledge graphs , 2016, J. Web Semant..

[37]  Evgeny Kharlamov,et al.  Entity Summarization in Knowledge Graphs: Algorithms, Evaluation, and Applications , 2020, WWW.

[38]  Evgeny Kharlamov,et al.  Towards Ontology Reshaping for KG Generation with User-in-the-Loop: Applied to Bosch Welding , 2021, IJCKG.

[39]  Markus Reischl,et al.  Data mining in medical time series , 2006, Biomedizinische Technik. Biomedical engineering.

[40]  Ruben Verborgh,et al.  Using OpenRefine , 2013 .

[41]  Jenny A. Harding,et al.  A Manufacturing Core Concepts Ontology for Product Lifecycle Interoperability , 2011, IWEI.

[42]  E. Kharlamov,et al.  SemML: Reusable ML for Condition Monitoring in Discrete Manufacturing , 2020, SEMWEB.

[43]  Xenia Fiorentini,et al.  OntoSTEP: OWL-DL Ontology for STEP | NIST , 2009 .

[44]  Ian Horrocks,et al.  Towards Analytics Aware Ontology Based Access to Static and Streaming Data , 2016, SEMWEB.

[45]  Dirk Walther,et al.  On Computing Minimal EL-Subsumption Modules , 2016, JOWO@FOIS.

[46]  Ian Horrocks,et al.  BootOX: Practical Mapping of RDBs to OWL 2 , 2015, SEMWEB.

[47]  Arkopaul Sarkar,et al.  SIMPM – Upper-level ontology for manufacturing process plan network generation , 2019, Robotics and Computer-Integrated Manufacturing.

[48]  Evgeny Kharlamov,et al.  Towards More Usable Dataset Search: From Query Characterization to Snippet Generation , 2019, CIKM.

[49]  Yavor Nenov,et al.  Capturing Industrial Information Models with Ontologies and Constraints , 2016, SEMWEB.

[50]  Heiko Paulheim,et al.  Semantic Web in data mining and knowledge discovery: A comprehensive survey , 2016, J. Web Semant..

[51]  Dirk Walther,et al.  Zooming in on Ontologies: Minimal Modules and Best Excerpts , 2017, International Semantic Web Conference.

[52]  Ian Horrocks,et al.  OptiqueVQS: A visual query system over ontologies for industry , 2018, Semantic Web.

[53]  Dirk Walther,et al.  Computing Minimal Projection Modules for ELH^r -Terminologies , 2019, JELIA.

[54]  Evgeny Kharlamov,et al.  An ontology-mediated analytics-aware approach to support monitoring and diagnostics of static and streaming data , 2019, J. Web Semant..

[55]  Sudarsan Rachuri,et al.  An ontology for assembly representation , 2007 .

[56]  T. Edgar,et al.  Smart Manufacturing. , 2015, Annual review of chemical and biomolecular engineering.

[57]  Peer Kröger,et al.  On event-driven knowledge graph completion in digital factories , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[58]  Felix Lösch,et al.  Semantic Integration of Bosch Manufacturing Data Using Virtual Knowledge Graphs , 2020, SEMWEB.

[59]  Baifan Zhou.  Machine Learning Methods for Product Quality Monitoring in Electric Resistance Welding , 2021 .

[60]  Pai Zheng,et al.  Towards Self-X cognitive manufacturing network: An industrial knowledge graph-based multi-agent reinforcement learning approach , 2021 .

[61]  Baifan Zhou,et al.  Practical methods for detecting and removing transient changes in univariate oscillatory time series , 2017 .

[62]  Evgeny Kharlamov,et al.  Semantic access to streaming and static data at Siemens , 2017, J. Web Semant..

[63]  Evgeny Kharlamov,et al.  Semantic Faceted Search with Aggregation and Recursion , 2017, SEMWEB.

[64]  Carsten Binnig,et al.  RODI: Benchmarking relational-to-ontology mapping generation quality , 2017, Semantic Web.

[65]  Heike Adel,et al.  Towards the Bosch Materials Science Knowledge Base , 2019, SEMWEB.

[66]  M. Kubát.  An Introduction to Machine Learning , 2017, Springer International Publishing.

[67]  Evgeny Kharlamov,et al.  Ontology Based Data Access in Statoil , 2017, J. Web Semant..

[68]  Ian Horrocks,et al.  Ontology Based Access to Exploration Data at Statoil , 2015, SEMWEB.