Lightweight CNC digital process twin framework: IIoT integration with open62541 OPC UA protocol

Arivazhagan A; Waqir Yusuf Zanhar; Shone George; Marcos Kauffman; Tengfei Long

doi:10.1080/21693277.2025.2544981

Lightweight CNC digital process twin framework: IIoT integration with open62541 OPC UA protocol

Centre for Manufacturing and Materials

Coventry University

Research output: Contribution to journal › Article › peer-review

16 Downloads (Pure)

Abstract

This research introduces a novel, lightweight Digital Process Twin
(DPT)-integrated IIoT framework for CNC machining, built on a modular
five-layer architecture using the open-source open62541 OPC
UA protocol. The layers include: (i) Physical – microcontroller with
sensors; (ii) Virtual – modeling and GM code generation; (iii) Data –
OPC UA-based transfer; (iv) Interaction – visualization via custom
nodes; and (v) Decision – rule-based logic and analytics. Distinctive
elements include custom Node-RED nodes and AI-generated synthetic
data using LSTM networks simulating 500 machining trials. This
data trained five ML models to predict sensor positions with high
accuracies (Random-Forest: R²(0.9994), KNN: R²(0.9998). Predictions
validated key digital twin functions, including error estimation,
synthetic data fidelity, and system integrity. A novel “match-rule”
algorithm is also introduced linking GM codes with sensor data,
enhancing traceability. Validated through a case study, the framework
supports predictive maintenance and offers SMEs a cost-effective
path to adopt DPT-based IIoT automation across CNC tools.

Original language	English
Number of pages	45
Journal	Production and Manufacturing Research
Volume	13
Issue number	1
Early online date	16 Aug 2025
DOIs	https://doi.org/10.1080/21693277.2025.2544981
Publication status	E-pub ahead of print - 16 Aug 2025

Bibliographical note

This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properlycited. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) orwith their consent.

Funding

This work was supported by the Innovate UK - Advanced Propulsion Centre (APC19) Project, Clean Logistics for Emerging African Nations (CLEAN) (Ref No: 10021053).

Funders	Funder number
Innovate UK - Advanced Propulsion Centre	APC19, 10021053

Keywords

Internet of Things (IoT)
open62541
Digital Twins
CNC machining
machine learning and AI

Access to Document

10.1080/21693277.2025.2544981Licence: CC BY

Anbalagan2025VORFinal published version, 28.2 MBLicence: CC BY

Cite this

@article{75a45e9fafd047be80d18f8861a6c02e,

title = "Lightweight CNC digital process twin framework: IIoT integration with open62541 OPC UA protocol",

abstract = "This research introduces a novel, lightweight Digital Process Twin (DPT)-integrated IIoT framework for CNC machining, built on a modular five-layer architecture using the open-source open62541 OPC UA protocol. The layers include: (i) Physical – microcontroller with sensors; (ii) Virtual – modeling and GM code generation; (iii) Data – OPC UA-based transfer; (iv) Interaction – visualization via custom nodes; and (v) Decision – rule-based logic and analytics. Distinctive elements include custom Node-RED nodes and AI-generated synthetic data using LSTM networks simulating 500 machining trials. This data trained five ML models to predict sensor positions with high accuracies (Random-Forest: R²(0.9994), KNN: R²(0.9998). Predictions validated key digital twin functions, including error estimation, synthetic data fidelity, and system integrity. A novel “match-rule” algorithm is also introduced linking GM codes with sensor data, enhancing traceability. Validated through a case study, the framework supports predictive maintenance and offers SMEs a cost-effective path to adopt DPT-based IIoT automation across CNC tools.",

keywords = "Internet of Things (IoT), open62541, Digital Twins, CNC machining, machine learning and AI",

author = "Arivazhagan A and \{Yusuf Zanhar\}, Waqir and Shone George and Marcos Kauffman and Tengfei Long",

note = "This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properlycited. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) orwith their consent.",

year = "2025",

month = aug,

day = "16",

doi = "10.1080/21693277.2025.2544981",

language = "English",

volume = "13",

journal = "Production and Manufacturing Research",

issn = "2169-3277",

publisher = "Taylor and Francis",

number = "1",

}

TY - JOUR

T1 - Lightweight CNC digital process twin framework

T2 - IIoT integration with open62541 OPC UA protocol

AU - A, Arivazhagan

AU - Yusuf Zanhar, Waqir

AU - George, Shone

AU - Kauffman, Marcos

AU - Long, Tengfei

N1 - This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properlycited. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) orwith their consent.

PY - 2025/8/16

Y1 - 2025/8/16

N2 - This research introduces a novel, lightweight Digital Process Twin (DPT)-integrated IIoT framework for CNC machining, built on a modular five-layer architecture using the open-source open62541 OPC UA protocol. The layers include: (i) Physical – microcontroller with sensors; (ii) Virtual – modeling and GM code generation; (iii) Data – OPC UA-based transfer; (iv) Interaction – visualization via custom nodes; and (v) Decision – rule-based logic and analytics. Distinctive elements include custom Node-RED nodes and AI-generated synthetic data using LSTM networks simulating 500 machining trials. This data trained five ML models to predict sensor positions with high accuracies (Random-Forest: R²(0.9994), KNN: R²(0.9998). Predictions validated key digital twin functions, including error estimation, synthetic data fidelity, and system integrity. A novel “match-rule” algorithm is also introduced linking GM codes with sensor data, enhancing traceability. Validated through a case study, the framework supports predictive maintenance and offers SMEs a cost-effective path to adopt DPT-based IIoT automation across CNC tools.

AB - This research introduces a novel, lightweight Digital Process Twin (DPT)-integrated IIoT framework for CNC machining, built on a modular five-layer architecture using the open-source open62541 OPC UA protocol. The layers include: (i) Physical – microcontroller with sensors; (ii) Virtual – modeling and GM code generation; (iii) Data – OPC UA-based transfer; (iv) Interaction – visualization via custom nodes; and (v) Decision – rule-based logic and analytics. Distinctive elements include custom Node-RED nodes and AI-generated synthetic data using LSTM networks simulating 500 machining trials. This data trained five ML models to predict sensor positions with high accuracies (Random-Forest: R²(0.9994), KNN: R²(0.9998). Predictions validated key digital twin functions, including error estimation, synthetic data fidelity, and system integrity. A novel “match-rule” algorithm is also introduced linking GM codes with sensor data, enhancing traceability. Validated through a case study, the framework supports predictive maintenance and offers SMEs a cost-effective path to adopt DPT-based IIoT automation across CNC tools.

KW - Internet of Things (IoT)

KW - open62541

KW - Digital Twins

KW - CNC machining

KW - machine learning and AI

UR - https://www.scopus.com/pages/publications/105013341968

U2 - 10.1080/21693277.2025.2544981

DO - 10.1080/21693277.2025.2544981

M3 - Article

SN - 2169-3277

VL - 13

JO - Production and Manufacturing Research

JF - Production and Manufacturing Research

IS - 1

ER -

Lightweight CNC digital process twin framework: IIoT integration with open62541 OPC UA protocol

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this