AI Asset Management for Manufacturing (AIM4M): Development of a Process Model for Operationalization

2025-09-15

AI Summary

In manufacturing, AI assets struggle to transition from prototypes to scalable deployment within cyber-physical production systems (CPPS), primarily due to high technical complexity, absence of domain-specific implementation standards, and fragmented organizational processes. Method: This paper proposes a full-lifecycle management process model for AI assets tailored to CPPS. Grounded in MLOps, the model integrates manufacturing systems engineering principles and industrial compliance requirements, customizing development collaboration, deployment integration, and operational governance dimensions for the manufacturing domain. Contribution/Results: It establishes the first industrial-grade AI asset management framework that jointly ensures technical feasibility, engineering operability, and regulatory compliance. The model significantly improves deployment efficiency, runtime robustness, and continuous iteration capability of AI models in dynamic production-line environments. By enabling systematic AI asset governance across the lifecycle, it provides a reusable methodological foundation for closing the AI value loop in smart manufacturing.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The benefits of adopting artificial intelligence (AI) in manufacturing are undeniable. However, operationalizing AI beyond the prototype, especially when involved with cyber-physical production systems (CPPS), remains a significant challenge due to the technical system complexity, a lack of implementation standards and fragmented organizational processes. To this end, this paper proposes a new process model for the lifecycle management of AI assets designed to address challenges in manufacturing and facilitate effective operationalization throughout the entire AI lifecycle. The process model, as a theoretical contribution, builds on machine learning operations (MLOps) principles and refines three aspects to address the domain-specific requirements from the CPPS context. As a result, the proposed process model aims to support organizations in practice to systematically develop, deploy and manage AI assets across their full lifecycle while aligning with CPPS-specific constraints and regulatory demands.

Problem

• Addressing AI operationalization challenges in manufacturing
• Developing lifecycle management for AI assets in CPPS
• Aligning MLOps with domain-specific manufacturing requirements

Innovation

• Process model for AI asset lifecycle management
• Refines MLOps principles for manufacturing
• Addresses CPPS-specific constraints and requirements