KAPPS: A knowledge-based CPPS Architecture for the...

KAPPS: A knowledge-based CPPS Architecture for the... | AI Research

Key Takeaways

KAPPS: A knowledge-based CPPS Architecture for the Circular Factory The Circular Factory represents a shift in manufacturing where used products—often in unc...
While linear manufacturing relies on homogeneous materials and predefined process sequences, circular manufacturing reintroduces used products with heterogeneous and uncertain conditions.
This shift demands manufacturing systems capable of handling variable product states, dynamically reconfigurable processes, and the integration of human and machine knowledge.
Following a design science methodology for developing a Cyber Physical Production System for circular manufacturing, we derive 14 requirements from five complementary perspectives.
KAPPS incorporates modules for constraint enforcement and event-driven planning, enabling incremental adaptation of execution plans under uncertainty and human-machine knowledge exchange.

Paper AbstractExpand

While linear manufacturing relies on homogeneous materials and predefined process sequences, circular manufacturing reintroduces used products with heterogeneous and uncertain conditions. This shift demands manufacturing systems capable of handling variable product states, dynamically reconfigurable processes, and the integration of human and machine knowledge. Conventional manufacturing IT architectures, designed for stable structures and deterministic execution, are unable to meet these requirements, as they cannot adequately represent and manage the uniqueness of individual components at runtime. Following a design science methodology for developing a Cyber Physical Production System for circular manufacturing, we derive 14 requirements from five complementary perspectives. Based on these requirements, we design KAPPS, a knowledge-based architecture that uses an ontology-grounded knowledge graph as a unifying data backbone, combined with a semantic interface layer to enable consistent data and information integration, reasoning, and communication across heterogeneous systems and services, turning the knowledge graph from an integration layer into the factories authoritative write-time state. KAPPS incorporates modules for constraint enforcement and event-driven planning, enabling incremental adaptation of execution plans under uncertainty and human-machine knowledge exchange. The applicability of KAPPS is demonstrated through two implemented use cases: (i) Anomaly detection and learning through knowledge graph mediated services and (ii) runtime constraint enforcement in a modular conveyor system. Subsequently, the architecture is evaluated against the 14 requirements (ed. abstract shortened)

KAPPS: A knowledge-based CPPS Architecture for the Circular Factory
The Circular Factory represents a shift in manufacturing where used products—often in uncertain or variable conditions—are reintroduced into the production cycle. Unlike traditional linear manufacturing, which relies on fixed, predictable sequences, circular production requires systems that can adapt to unique product states and reconfigure processes on the fly. This paper introduces KAPPS, a new architecture for Cyber-Physical Production Systems (CPPS) designed to bridge the gap between these complex circular requirements and the rigid, deterministic nature of conventional manufacturing IT.

Defining the Requirements for Circular Production

To understand what a modern factory needs, the authors analyzed the Circular Factory through five distinct perspectives: perception, product management, production planning, resource management, and learning. From these, they derived 14 specific requirements (R1–R14). These requirements emphasize the need for a system that can handle heterogeneous data, maintain a persistent digital identity for every component, ensure that planned operations are physically feasible at runtime, and allow the system to learn from both machine data and human interventions.

The KAPPS Architecture

KAPPS is built as a four-layer architecture designed to act as the "authoritative write-time state" of the factory. At its core is an ontology-grounded knowledge graph that serves as a unified data backbone. By combining this knowledge graph with a semantic interface layer, KAPPS enables different systems and services to communicate and reason consistently, even when they use different protocols or data formats. The architecture includes specific modules for event-driven planning and constraint enforcement, ensuring that as a product moves through the factory, the system continuously validates that every action is safe and logical based on the most current information available.

Demonstrating and Evaluating the System

The researchers demonstrated the effectiveness of KAPPS through two practical use cases: using knowledge-graph-mediated services for anomaly detection in a robotic disassembly cell, and enforcing physical constraints in a modular conveyor system. By evaluating the architecture against the 14 derived requirements, the authors showed that KAPPS successfully provides instance-level traceability and allows for the integration of heterogeneous services. The system ensures that planning and execution remain synchronized, even when dealing with the high levels of uncertainty inherent in remanufacturing.

Future Development

The KAPPS architecture is released as an open-source project to support further research and industrial application. The authors view this work as an iterative process; the current implementation serves as a foundation that satisfies the initial design requirements. Future work will focus on the continued development of the system, incorporating feedback from the evaluation phase to further refine how the architecture handles the evolving complexities of the Circular Factory.