Digital Twins & ZeroConf AI: Structuring Automated Intelligent Pipelines for Industrial Applications

TL;DR

This paper presents a modular, interoperable framework using Digital Twins and ZeroConf AI pipelines to streamline and accelerate the deployment of AI in complex industrial Cyber-Physical Systems.

Contribution

It introduces a novel ZeroConf AI pipeline concept that decouples AI components from Digital Twins, enhancing scalability and reusability in industrial applications.

Findings

Supports concurrent machine learning models

Enables dynamic data processing in industrial settings

Accelerates deployment of intelligent services

Abstract

The increasing complexity of Cyber-Physical Systems (CPS), particularly in the industrial domain, has amplified the challenges associated with the effective integration of Artificial Intelligence (AI) and Machine Learning (ML) techniques. Fragmentation across IoT and IIoT technologies, manifested through diverse communication protocols, data formats and device capabilities, creates a substantial gap between low-level physical layers and high-level intelligent functionalities. Recently, Digital Twin (DT) technology has emerged as a promising solution, offering structured, interoperable and semantically rich digital representations of physical assets. Current approaches are often siloed and tightly coupled, limiting scalability and reuse of AI functionalities. This work proposes a modular and interoperable solution that enables seamless AI pipeline integration into CPS by minimizing configuration and decoupling the roles of DTs and AI components. We introduce the concept of Zero Configuration (ZeroConf) AI pipelines, where DTs orchestrate data management and intelligent augmentation. The approach is demonstrated in a MicroFactory scenario, showing support for concurrent ML models and dynamic data processing, effectively accelerating the deployment of intelligent services in complex industrial settings.