[Paper Review] Data in Context: How Digital Transformation Can Support Human Reasoning in Cyber-Physical Production Systems

Romy Müller|arXiv (Cornell University)|Jun 17, 2021

Big Data and Business Intelligence200 references8 citations

TL;DR

This paper proposes that digital transformation technologies—particularly information modelling and data integration tools—can support human reasoning in cyber-physical production systems by enabling contextualization of operational data. By drawing on cognitive psychology, it identifies four core human reasoning challenges (information sampling, integration, categorization, causal reasoning) and shows how technologies like OPC UA, ontologies, and linked data can address them, ultimately enabling more effective human-technology cooperation in complex industrial environments.

ABSTRACT

In traditional production plants, current technologies do not provide sufficient context to support information integration and interpretation. Digital transformation technologies have the potential to support contextualization, but it is unclear how this can be achieved. The present article presents a selection of the psychological literature in four areas relevant to contextualization: information sampling, information integration, categorization, and causal reasoning. Characteristic biases and limitations of human information processing are discussed. Based on this literature, we derive functional requirements for digital transformation technologies, focusing on the cognitive activities they should support. We then present a selection of technologies that have the potential to foster contextualization. These technologies enable the modelling of system relations, the integration of data from different sources, and the connection of the present situation with historical data. We illustrate how these technologies can support contextual reasoning, and highlight challenges that should be addressed when designing human–machine cooperation in cyber-physical production systems.

Motivation & Objective

• . The paper aims to address the lack of contextual support in current industrial monitoring systems, where operators struggle to interpret data due to missing interdependencies and historical context.
• It investigates how digital transformation technologies can support four core cognitive activities: information sampling, data integration, situation categorization, and causal reasoning in complex production environments.
• The study seeks to shift focus from technology as a source of cognitive burden to a tool that enhances human reasoning by providing structured, context-aware information.
• It aims to bridge psychological research on human cognition with technical solutions in cyber-physical production systems (CPPS), emphasizing information modelling and integration as foundational enablers.

Proposed method

• . The authors conducted a literature review across four psychological domains: information sampling, integration, categorization, and causal reasoning, focusing on human cognitive biases and limitations.
• They derived functional requirements for digital technologies based on psychological findings, emphasizing the need for context-aware data access and interpretation.
• The paper evaluates existing digital transformation technologies such as OPC UA, ontologies, and linked data for their ability to model system relations and integrate heterogeneous data sources.
• It examines how these technologies can connect real-time data with historical data to support contextual reasoning and decision-making.
• The approach integrates cognitive psychology with engineering systems design, proposing that formal models of production systems are essential for enabling context-aware operator support.
• The study uses a conceptual framework to map psychological challenges to technical solutions, focusing on information modelling as the core enabler of contextualization.

Experimental results

Research questions

• RQ1 . How can digital transformation technologies support the contextualization of operational data in cyber-physical production systems?
• RQ2 What cognitive challenges do operators face when monitoring complex industrial systems, and how do these relate to information sampling, integration, categorization, and causal reasoning?
• RQ3 Which digital transformation technologies are best suited to support these cognitive activities, and how do they address human cognitive limitations?
• RQ4 How can information modelling and data integration technologies be designed to enhance human reasoning rather than increase cognitive load?
• RQ5 What are the key design principles for integrating psychological insights with technical systems in human-technology cooperation within CPPS?

Key findings

• . Digital transformation technologies such as OPC UA, ontologies, and linked data can model system relations and integrate data from multiple sources, enabling more effective contextual reasoning.
• Current industrial systems fail to support contextualization, leading to operator challenges in selecting relevant data, integrating disparate information, and reasoning about causes.
• The integration of historical data with real-time data through formal models improves situation categorization and supports causal inference in complex production environments.
• Technologies that support formal information modelling are essential for enabling context-aware operator assistance systems in cyber-physical production systems.
• The paper identifies a critical gap in current systems: while interface design has been widely studied, information modelling—crucial for context—has been largely overlooked in human factors research.
• Future systems should integrate psychological support strategies (e.g., training in causal reasoning, reducing overconfidence) with technological solutions to enhance human-technology cooperation.