=Paper=
{{Paper
|id=Vol-3254/paper405
|storemode=property
|title=Neuro-Symbolic AI at Bosch: Data Foundation, Insights, and Deployment
|pdfUrl=https://ceur-ws.org/Vol-3254/paper405.pdf
|volume=Vol-3254
|authors=Baifan Zhou,Zhipeng Tan,Zhuoxun Zheng,Dongzhuoran Zhou,Yunjie He,Yuqicheng Zhu,Muhammad Yahya,Trung-Kien Tran,Daria Stepanova,Mohamed H. Gad-Elrab,Evgeny Kharlamov
|dblpUrl=https://dblp.org/rec/conf/semweb/ZhouTZZHZYT0GK22
}}
==Neuro-Symbolic AI at Bosch: Data Foundation, Insights, and Deployment==
https://ceur-ws.org/Vol-3254/paper405.pdf
Neuro-Symbolic AI at Bosch:
Data Foundation, Insights, and Deployment
Baifan Zhou1,∗ , Zhipeng Tan2,3 , Zhuoxun Zheng2,4 , Dongzhuoran Zhou2,1 ,
Yunjie He2,5 , Yuqicheng Zhu2,5 , Muhammad Yahya6 , Trung-Kien Tran2 ,
Daria Stepanova2 , Mohamed H. Gad-Elrab2 and Evgeny Kharlamov2,1
1
SIRIUS Centre, University of Oslo, Norway
2
Bosch Center for Artificial Intelligence, Germany
3
RWTH Aachen University, Germany
4
Department of Computer Science, Oslo Metropolitan University, Norway
5
University of Stuttgart, Germany
6
University of Galway, Ireland
Motivation. Neuro-symbolic AI [1] refers to the integration of connectionist AI (neural net-
works) and symbolic AI approaches (e.g. ontology and logics). Neuro-symbolic AI in the industry
becomes possible thanks to the technological advances of Industry 4.0 [2], which bring a fast
growth in volume and complexity of heterogeneous manufacturing (big) data [3]. Despite the
popularity of this topic, how neuro-symbolic AI can be realised in the industry remains to be stud-
ied. In this paper, we exemplify neuro-symbolic AI with the activities of at Bosch (Fig. 1), where
semantic technologies play an essential role, including 1) the data foundation, which relies on
semantic data integration to unify heterogeneous data to uniform formats, 2) the insights, which
exploit data-driven methods especially machine learning (ML) to extract knowledge from the
data, and 3) the deployment, which gives industrial examples of value generation from the data.
Data Foundation: Semantic Data Integration. Bosch models industrial assets with their se-
mantic digital counterparts as ontologies, such as resistance spot welding (welding that connects
car bodies parts via welding nuggets). Bosch is also developing domain core ontology, based on
manufacturing standards of ISO and harmonised with the top level ontology such as BFO to
improve the Bosch applications interoperability. Industrial KGs. Bosch experts annotate hetero-
geneous manufacturing data with unified vocabularies from the ontologies, which are enhanced
by the ontology reshaping method [4] that removes classes unmapped to data. Following the
reshaped ontologies as KG schemata, knowledge graphs (KG) are semi-automatically generated
as homogeneous data formats/databases, which allow uniform access and interoperability [4].
Insights: AI-Powered Analytics. We give examples of such analytics built on the unified KG
data to extract insights, including numeric data such as sensor measurements as well as text data
like machine status text. Executable KG Analytics. Executable KGs [5] represent executable data
pipelines in a standardised and transparent way (namely executable KGs) for visual, statistical
and ML analytics (such as quality prediction), and these KGs can be transformed into executable
Hangzhou’22: The 21st International Semantic Web Conference, October 23–27, 2022, Hangzhou, China
∗
Corresponding author.
Envelope-Open baifanz@ifi.uio.no (B. Zhou)
© 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
Workshop
Proceedings
http://ceur-ws.org
ISSN 1613-0073
CEUR Workshop Proceedings (CEUR-WS.org)
Industrial Automation Systems
Layered Architecture
dustrial Automation Systems
Layer 4 – Management Layer
ayered Architecture
ayer 4 – Management Layer
Operations Production Manufacturing
Plant Engineering
Management Execution Intelligence
Information Silos Data Foundation Insights Deployment
Operations Production Manufacturing
Plant Engineering
Management Manufacturing Operations Execution Intelligence Engineering
Knowledge
Asset Data
Management Layer Procurement
Ontologies
Sem DTs /
Simulation
AI methods and Analytics
Manufacturing Operations
IT-System Knowledge
Knowledge Management Layer Supervisory Layer
Scheduling
Control & Automation
IT-System Knowledge Supervisory Layer Control Layer Executable KG Transfer
Engineering Knowledge
ETL AI Diagnostics
Analytics
Control & Automation
Electr. & Mech. Engineering ASP solver
Industrial KGs
Field Devices
Industrial Assets
Control Layer Analytics
Engineering Knowledge Knowledge
Neural-Symbolic
Electr. & Mech. Engineering
Learning Digital Req
Field Devices
Knowledge
Page 7 October 2015 Corporate Technology Unrestricted © Siemens AG 2015. All rights reserved
Standardize
ge 7 October 2015 Corporate Technology ChallengeUnrestricted © Siemens AG 2015. All rights reserved Solution Industrial Apps
Data Data Integration Neuro-symbolic AI Analytics Value
Figure 1: Overview: Semantic ETL creates the data foundation of AI-powered analytics, which extracts
insights that can be transferred to value in industrial deployment.
scripts in a highly reusable and modularised fashion, improving transparency and adoption in
the industry. ASP Solver. Bosch relies on Answer Set Programming (ASP) for solving difficult
(primarily NP-hard) search problems, which is a form of declarative programming and based on
the stable model (answer set) semantics of logic programming. ASP is beneficial for solving
knowledge-intense combinatorial (optimisation) problems. Neuro-Symbolic Learning. Currently
we focus on the state of the art KG embedding methods (e.g, TransE, RotatE) and GNN relevant
methods. Examples: 1) We rely on neuro-symbolic methods with dynamic link prediction for
complex query answering, which is more explainable compared to black-box neural models
for classification/regression, since the neuro-symbolic approach accompanies answers with
symbolic knowledge and confidence level. 2) Bosch studies different KG uncertainties caused by
e.g., inconsistency and incompleteness to reduce the learning/inference uncertainty.
Deployment: Industrial Applications. We give three examples 1) Process Diagnostics: in
manufacturing, some anomalous welding operations (that produce quality failures), machines
(that produce more quality failures), etc. need to be identified and their root-causes need to be
analysed via visual and statistical analytics; 2) Quality Monitoring: the numerical or categorical
quality indicators (such as welding diameter)need to be estimated/predicted by ML analytics
with classification/regression; 3) Personnel Scheduling: the automatic arrangement of personnel
with different available or preferred time and tasks need to be solved by ASP solver.
References
[1] A. S. d. Garcez, K. Broda, D. M. Gabbay, et al., Neural-symbolic learning systems: foundations
and applications, Springer Science & Business Media, 2002.
[2] H. Kagermann, Change through digitization – value creation in the age of Industry 4.0, in:
Management of Permanent Change, 2015.
[3] S. Chand, J. Davis, What is smart manufacturing, Time Magazine Wrapper (2010).
[4] D. Zhou, et al., Ontology reshaping for knowledge graph construction: Applied on bosch
welding case, in: ISWC, Springer, 2022.
[5] Z. Zheng, B. Zhou, et al., Executable knowledge graphs for machine learning: A Bosch case
of welding monitoring, in: ISWC, Springer, 2022.