Journal Article10.23919/cnsm59352.2023.10327814
Tailoring MLOps Techniques for Industry 5.0 Needs
Csaba Hegedüs,Pál Varga +1 more
- 30 Oct 2023
pp 1-7
5
TL;DR: This paper explores the key requirements for deploying ML applications in industrial scenarios, emphasizing the critical role of Digital Twins, edge AI, and responsible-explainable AI techniques in ensuring efficient and responsible operations.
read more
Abstract: It is a very popular era for machine learning (ML) applications, and Industry5.0 aims to have AI as one of its key technologies. Still, only a few ML initiatives make it to a production-grade implementation, mostly due to lacking proper Continuous Integration and Delivery framework and MLOps practices. This is especially true for industrial use cases, where the trust and reliability of ML applications are mission-critical. Most of these applications fail during the final stage of the development lifecycle, i.e. acceptance testing and validation of the ML application, while being integrated into Cyber-Physical System of Systems (CPSoS). This paper explores the key requirements for deploying ML applications in industrial scenarios, emphasizing the critical role of Digital Twins, edge AI, and responsible-explainable AI techniques in ensuring efficient and responsible operations. Building upon previous models, this paper suggests two process models: (i) the Olympics model for MLOps-coupled CPS engineering and (ii) the MLOps engineering toolchain for industrial applications.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Using FactoryML for Deployment of Machine Learning Models in Industrial Production
Christian Remi Wewer,Harshit Mahapatra,Lukas Esterle,Peter Gorm Larsen +3 more
- 10 Sep 2024
TL;DR: FactoryML framework simplifies ML model deployment in manufacturing environments by packaging models into a portable format and facilitating communication via Programmable Logic Controllers, reducing the barrier to operational deployment.
MLOps in CPS – a use-case for image recognition in changing industrial settings
Pál Varga,Attila Kővári,Márton Herkules,Csaba Hegedűs +3 more
- 06 May 2024
TL;DR: This paper presents an Industry5.0-motivated use-case involving image recognition, demonstrating the development, testing, and deployment of ML models using MLOps tools, and argues against the challenges of manual processes and show the benefits of automation in enhancing efficiency and reducing error.
Machine Learning Operations: A Mapping Study
Abhijit Chakraborty,Suddhasvatta Das,Kevin Gary +2 more
- 28 Sep 2024
TL;DR: This study maps challenges in Machine Learning Operations (MLOps) pipelines, including data manipulation, model building, and deployment, and provides recommendations for tools and solutions to address these challenges in both research and industrial settings.
Dynamic Execution of Engineering Processes in Cyber-Physical Systems of Systems Toolchains
Federico Montori,Marek Tatara,Pal Varga +2 more
TL;DR: This paper proposes an automated toolchain building and execution process for Cyber-Physical System of Systems (CPSoS) using the Eclipse Arrowhead framework, addressing tool interoperability, interaction, automation, and dynamic choreography, and validates its feasibility through a demonstration.
A Machine Learning Operations Platform for Streamlined Model Serving in Industry 5.0
Lorenzo Colombi,Alessandro Gilli,Simon Dahdal,Ion Boleac,Mauro Tortonesi,Cesare Stefanelli,Massimiliano Vignoli +6 more
- 06 May 2024
TL;DR: An MLOps platform that is capable of managing ML models through their entire lifecycle and enabling their deployment in different ML serving runtimes and provides a comparative evaluation at both the quantitative and qualitative levels is realized.
References
Digital Twin in Industry: State-of-the-Art
TL;DR: This paper thoroughly reviews the state-of-the-art of the DT research concerning the key components of DTs, the current development ofDTs, and the major DT applications in industry and outlines the current challenges and some possible directions for future work.
2.8K
Industry 4.0: A Survey on Technologies, Applications and Open Research Issues
TL;DR: A comprehensive review on Industry 4.0 is conducted and presents an overview of the content, scope, and findings by examining the existing literatures in all of the databases within the Web of Science.
2.7K
Industry 5.0: A survey on enabling technologies and potential applications
Praveen Kumar Reddy Maddikunta,Quoc-Viet Pham,B. Prabadevi,N. Deepa,Kapal Dev,Thippa Reddy Gadekallu,Rukhsana Ruby,Madhusanka Liyanage +7 more
TL;DR: This paper aims to provide a survey-based tutorial on potential applications and supporting technologies of Industry 5.0 from the perspective of different industry practitioners and researchers.
Smart manufacturing: Characteristics, technologies and enabling factors:
Sameer Mittal,Muztoba Ahmad Khan,David Romero,Thorsten Wuest +3 more
- 01 Apr 2019
TL;DR: In this paper, a comprehensive list of such characteristics, technologies and enabling factors that are regularly associated with smart manufacturing is presented, which can be used as a basis for a future smart manufacturing ontology.
484
Tackling Faults in the Industry 4.0 Era-A Survey of Machine-Learning Solutions and Key Aspects.
A. Angelopoulos,Emmanouel T. Michailidis,Nikolaos Nomikos,Panagiotis Trakadas,Antonis Hatziefremidis,Stamatis Voliotis,Theodore Zahariadis +6 more
TL;DR: A detailed overview of ML-based human–machine interaction techniques is provided, allowing humans to be in-the-loop of the manufacturing processes in a symbiotic manner with minimal errors.
300