Semantic web and machine learning techniques addressing semantic interoperability in Industry 4.0

Abstract

Purpose

This paper aims to offer a comprehensive examination of the various solutions currently accessible for addressing the challenge of semantic interoperability in cyber physical systems (CPS). CPS is a new generation of systems composed of physical assets with computation capabilities, connected with software systems in a network, exchanging data collected from the physical asset, models (physics-based, data-driven, . . .) and services (reconfiguration, monitoring, . . .). The physical asset and its software system are connected, and they exchange data to be interpreted in a certain context. The heterogeneous nature of the collected data together with different types of models rise interoperability problems. Modeling the digital space of the CPS and integrating information models that support cyber physical interoperability together are required.

Design/methodology/approach

This paper aims to identify the most relevant points in the development of semantic models and machine learning solutions to the interoperability problem, and how these solutions are implemented in CPS. The research analyzes recent papers related to the topic of semantic interoperability in Industry 4.0 (I4.0) systems.

Findings

Semantic models are key enabler technologies that provide a common understanding of data, and they can be used to solve interoperability problems in Industry by using a common vocabulary when defining these models.

Originality/value

This paper provides an overview of the different available solutions to the semantic interoperability problem in CPS.

Citation

Hafidi, M.M., Djezzar, M., Hemam, M., Amara, F.Z. and Maimour, M. (2023), "Semantic web and machine learning techniques addressing semantic interoperability in Industry 4.0", International Journal of Web Information Systems, Vol. 19 No. 3/4, pp. 157-172. https://doi.org/10.1108/IJWIS-03-2023-0046