header

SemML: Facilitating Development of ML Models for Condition Monitoring with Semantics

24 Pages Posted: 19 Oct 2021 Publication Status: Accepted

See all articles by Baifan Zhou

Baifan Zhou

Bosch Corporate Research Center

Yulia Svetashova

Bosch Corporate Research Center

Andre Gusmao

OsloMet - Oslo Metropolitan University - Department of Computer Science

Ahmet Soylu

OsloMet - Oslo Metropolitan University - Department of Computer Science

Gong Cheng

Nanjing University - National Key Laboratory for Novel Software Technology

Ralf Mikut

Karlsruhe Institute of Technology - Institute for Automation and Applied Informatics

Arild Waaler

University of Oslo - Department of Informatics (UiO)

Evgeny Kharlamov

Bosch Center for Artificial Intelligence

Abstract

Monitoring of the state, performance, quality of operations and other parameters of equipment and productiosn processes, which is typically referred to as condition monitoring, is an important common practice in many industries including manufacturing, oil and gas, chemical and process industry. In the age of Industry 4.0, where the aim is a deep degree of production automation, unprecedented amounts of data are generated by equipment and processes, and this enables adoption of Machine Learning (ML) approaches for condition monitoring. Development of such ML models is challenging. On the one hand, it requires collaborative work of experts from different areas, including data scientists, engineers, process experts, and managers with asymmetric backgrounds. On the other hand, there is high variety and diversity of data relevant for condition monitoring. Both factors hampers ML modeling for condition monitoring. In this work, we address these challenges by empowering ML-based condition monitoring with semantic technologies. To this end we propose a software system SemML that allows to reuse and generalise ML pipelines for conditions monitoring by relying on semantics. In particular, SemML has several novel components and relies on ontologies and ontology templates for ML task negotiation and for data and ML feature annotation. SemML also allows to instantiate parametrised ML pipelines by semantic annotation of industrial data. With SemML, users do not need to dive into data and ML scripts when new datasets of a studied application scenario arrive. They only need to annotate data and then ML models will be constructed through the combination of semantic reasoning and ML modules. We demonstrate the benefits of SemML on a Bosch use-case of electric resistance welding with very promising results.

Suggested Citation

Zhou, Baifan and Svetashova, Yulia and Gusmao, Andre and Soylu, Ahmet and Cheng, Gong and Mikut, Ralf and Waaler, Arild and Kharlamov, Evgeny, SemML: Facilitating Development of ML Models for Condition Monitoring with Semantics. Journal of Web Semantics First Look , Available at SSRN: https://ssrn.com/abstract=3945440 or http://dx.doi.org/10.2139/ssrn.3945440

Baifan Zhou (Contact Author)

Bosch Corporate Research Center ( email )

Renningen
Germany

Yulia Svetashova

Bosch Corporate Research Center ( email )

Renningen
Germany

Andre Gusmao

OsloMet - Oslo Metropolitan University - Department of Computer Science ( email )

United States

Ahmet Soylu

OsloMet - Oslo Metropolitan University - Department of Computer Science ( email )

United States

Gong Cheng

Nanjing University - National Key Laboratory for Novel Software Technology ( email )

Nanjing, Jiangsu 210093
China

Ralf Mikut

Karlsruhe Institute of Technology - Institute for Automation and Applied Informatics ( email )

United States

Arild Waaler

University of Oslo - Department of Informatics (UiO) ( email )

P.O box 1080
Oslo
Norway

Evgeny Kharlamov

Bosch Center for Artificial Intelligence ( email )

Renningen
Germany

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
55
Downloads
7
PlumX Metrics