Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Formal Model for Artificial Intelligence Applications in Automation Systems

Marvin Schieseck, Philip Topalis, Lasse Reinpold, Felix Gehlhoff, Alexander Fay

TL;DR

The paper addresses the challenge of documenting AI applications within automation systems, where complexity and interdependencies hinder adoption. It proposes AIAS, a formal information model built from modular Ontology Design Patterns (ODPs) aligned to standards (ISO 22989, VDI 3682, ISO 7489) to capture automation components, AI data, and their interdependencies. The contributions include an alignment ontology that links technical-system and AI-Data ODPS, a practical industrial use case modeled as a knowledge graph, and demonstrated capabilities for SPARQL querying, SWRL-based reasoning, and SHACL constraints. The approach aims to standardize documentation and support sustainable AI integration in industrial settings by enabling reasoning, querying, and extensible documentation across evolving regulations and standards.

Abstract

The integration of Artificial Intelligence (AI) into automation systems has the potential to enhance efficiency and to address currently unsolved existing technical challenges. However, the industry-wide adoption of AI is hindered by the lack of standardized documentation for the complex compositions of automation systems, AI software, production hardware, and their interdependencies. This paper proposes a formal model using standards and ontologies to provide clear and structured documentation of AI applications in automation systems. The proposed information model for artificial intelligence in automation systems (AIAS) utilizes ontology design patterns to map and link various aspects of automation systems and AI software. Validated through a practical example, the model demonstrates its effectiveness in improving documentation practices and aiding the sustainable implementation of AI in industrial settings.

A Formal Model for Artificial Intelligence Applications in Automation Systems

TL;DR

The paper addresses the challenge of documenting AI applications within automation systems, where complexity and interdependencies hinder adoption. It proposes AIAS, a formal information model built from modular Ontology Design Patterns (ODPs) aligned to standards (ISO 22989, VDI 3682, ISO 7489) to capture automation components, AI data, and their interdependencies. The contributions include an alignment ontology that links technical-system and AI-Data ODPS, a practical industrial use case modeled as a knowledge graph, and demonstrated capabilities for SPARQL querying, SWRL-based reasoning, and SHACL constraints. The approach aims to standardize documentation and support sustainable AI integration in industrial settings by enabling reasoning, querying, and extensible documentation across evolving regulations and standards.

Abstract

The integration of Artificial Intelligence (AI) into automation systems has the potential to enhance efficiency and to address currently unsolved existing technical challenges. However, the industry-wide adoption of AI is hindered by the lack of standardized documentation for the complex compositions of automation systems, AI software, production hardware, and their interdependencies. This paper proposes a formal model using standards and ontologies to provide clear and structured documentation of AI applications in automation systems. The proposed information model for artificial intelligence in automation systems (AIAS) utilizes ontology design patterns to map and link various aspects of automation systems and AI software. Validated through a practical example, the model demonstrates its effectiveness in improving documentation practices and aiding the sustainable implementation of AI in industrial settings.
Paper Structure (16 sections, 5 figures, 1 table)

This paper contains 16 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Analysis of Requirements
  3. Requirements for the Information Model
  4. Related Works
  5. Datasheets and Cards
  6. Ontologies
  7. Graphical Modeling
  8. Discussion of Related Works
  9. Formal Artificial Intelligence Application Description
  10. Description of the Technical System and Process
  11. Description of the Artificial Intelligence and Data
  12. Description of the Alignment Ontology
  13. Application in an Industrial Scenario
  14. Discussion
  15. Conclusion
  16. ...and 1 more sections

Figures (5)

  • Figure 1: Core concepts and relations of the ISO 7489 ODP.
  • Figure 2: ISO 22989 ODP from a component and functions viewpoint. Classes and relations that are not mandatory for this viewpoint are not shown.
  • Figure 3: ISO 22989 ODP from an algorithmic viewpoint. Classes and relations that are not mandatory for this viewpoint are not shown.
  • Figure 4: ISO 22989 ODP from a data viewpoint. Classes and relations that are not mandatory for this viewpoint are not shown.
  • Figure 5: Core Concept of the alignment ontology AIAS, showing the connection of different standards through ODPs. Most of the concepts of the ODPs have been hidden to maintain readability.