Smart Steel Pipe Production Plant via Cognitive Digital Twins: A Case Study on Digitalization of Spiral Welded Pipe Machinery

Albayrak, Özlem; Unal, Perin

doi:10.1007/978-3-030-69367-1_11

Cited by 9 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data is transferred through FTP on WiFi to the Windows computer which is placed just by the logger near the Mogensen separator inside the facility. A telegraf 5 service is running on the Windows machine constantly sending newly…”

Section: Data Acquisition Pipelinementioning

confidence: 99%

“…W ITHIN mining and metal processing industries, digital transformation is becoming a driving force changing the nature of companies and interaction with employees, communities, government, and environment at every step of the value chain [1]- [3]. The metal processing industry is already gathering a huge amount of data from sensors to collect real-time information about the performance of their infrastructure [4], [5]. Since many processes and machines can possibly generate data, smart sensors -instruments with on-board signal conditioning or feature extraction capabilities -become a primary data source for producing insights via big data analytics [6], [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Vibration Sensors for Detecting Critical Events: A Case Study in Ferrosilicon Production

Waszak,

Moen,

Hansen

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The mining and metal processing industries are undergoing a transformation through digitization, with sensors and data analysis playing a crucial role in modernization and increased efficiency. Vibration sensors are particularly important in monitoring production infrastructure in metal processing plants. This paper presents the installation of vibration sensors in an actual industrial environment and the results of spectral vibration data analysis. The study demonstrates that vibration sensors can be installed in challenging environments such as metal processing plants and that analyzing vibration patterns can provide valuable insights into predicting machine failures and different machine states. By utilizing dimensionality reduction and dominant frequency observation we analyzed vibration data and identified patterns that are indicative for potential machine states and critical events that reduce the production throughput. This information can be used to improve maintenance, minimize downtime, and ultimately improve the production process' overall efficiency. This study highlights the importance of digitization and data analysis in the mining and metal processing industries, particularly through the capability not only to predict critical events before they have an impact on the production throughput and take action accordingly but also to identify machine states for legacy equipment and be part of the retrofitting strategy.

show abstract

Section: Data Acquisition Pipelinementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Vibration Sensors for Detecting Critical Events: A Case Study in Ferrosilicon Production

Waszak,

Moen,

Hansen

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A cognitive twin toolbox conceptual architecture was developed and applied to several use cases such as operational optimization for aluminum production, silicon production, steel and related products production etc. [27,29]. An application case was presented in a recent study [30], in which a CDT enabled by KG was developed to support demand forecasting and production planning in a manufacturing plant.…”

Section: Introductionmentioning

confidence: 99%

Exploring the concept of Cognitive Digital Twin from model-based systems engineering perspective

Zhaorui

Zheng

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Digital Twin technology has been widely applied in various industry domains. Modern industrial systems are highly complex consisting of multiple interrelated systems, subsystems and components. During the lifecycle of an industrial system, multiple digital twin models might be created related to different domains and lifecycle phases. The integration of these relevant models is crucial for creating higher-level intelligent systems. The Cognitive Digital Twin (CDT) concept has been proposed to address this challenge by empowering digital twins with augmented semantic capabilities. It aims at identifying the dynamics and interrelationships of virtual models, thus to enhance complexity management capability and to support decision-making during the entire system lifecycle. This paper aims to explore the CDT concept and its core elements following a systems engineering approach. A conceptual architecture is designed according to the ISO 42010 standard to support CDT development; and an application framework enabled by knowledge graph is provided to guide the CDT applications. In addition, an enabling tool-chain is proposed corresponding to the framework to facilitate the implementation of CDT. Finally, a case study is conducted, based on simulation experiments as a proof-of-concept.

show abstract

Data-Driven Artificial Intelligence and Predictive Analytics for the Maintenance of Industrial Machinery with Hybrid and Cognitive Digital Twins

Unal¹,

Albayrak²,

Jomâa

et al. 2022

Technologies and Applications for Big Data Value

View full text Add to dashboard Cite

This chapter presents a Digital Twin Pipeline Framework of the COGNITWIN project that supports Hybrid and Cognitive Digital Twins, through four Big Data and AI pipeline steps adapted for Digital Twins. The pipeline steps are Data Acquisition, Data Representation, AI/Machine learning, and Visualisation and Control. Big Data and AI Technology selections of the Digital Twin system are related to the different technology areas in the BDV Reference Model. A Hybrid Digital Twin is defined as a combination of a data-driven Digital Twin with First-order Physical models. The chapter illustrates the use of a Hybrid Digital Twin approach by describing an application example of Spiral Welded Steel Industrial Machinery maintenance, with a focus on the Digital Twin support for Predictive Maintenance. A further extension is in progress to support Cognitive Digital Twins includes support for learning, understanding, and planning, including the use of domain and human knowledge. By using digital, hybrid, and cognitive twins, the project’s presented pilot aims to reduce energy consumption and average duration of machine downtimes. Data-driven artificial intelligence methods and predictive analytics models that are deployed in the Digital Twin pipeline have been detailed with a focus on decreasing the machinery’s unplanned downtime. We conclude that the presented pipeline can be used for similar cases in the process industry.

show abstract

Smart Steel Pipe Production Plant via Cognitive Digital Twins: A Case Study on Digitalization of Spiral Welded Pipe Machinery

Cited by 9 publications

References 13 publications

Vibration Sensors for Detecting Critical Events: A Case Study in Ferrosilicon Production

Vibration Sensors for Detecting Critical Events: A Case Study in Ferrosilicon Production

Exploring the concept of Cognitive Digital Twin from model-based systems engineering perspective

Data-Driven Artificial Intelligence and Predictive Analytics for the Maintenance of Industrial Machinery with Hybrid and Cognitive Digital Twins

Contact Info

Product

Resources

About