The evolution of internet of things, cyber physical system, digital twin and artificial intelligence is stimulating the transformation of the product-centric processes toward smart control digital service-oriented ones. With the implementation of artificial intelligence and machine learning algorithms, IoT has accelerated the movement from connecting devices to the Internet to collecting and analyzing data by using sensors to extract data throughout the lifecycle of the product, in order to create value and knowledge from the huge amount of the collected data, such as the knowledge of the product performance and conditions. The importance of internet of things technology in manufacturing comes from its ability to collect real time data and extract valuable knowledge from these huge amount of data which can be supported through the implementation of smart IoT-based servitization framework which was presented in this research together with a 10-steps approach diagram. Moreover, literature review has been carried out to develop the research and deepen the knowledge in the field of IoT, CPS, DT and Artificial Intelligence, and then interviews with experts have been conducted to validate the contents, since DT is a quite new technology, so there are different points of view about certain concepts of this technology. The main scope and objective of this research is to allow organizational processes and companies to benefit form the value added information that can be achieved through the right implementation of advanced technologies such as IoT, DT, CPS, and artificial intelligence which can provide financial benefits to the manufacturing companies and competitive advantages to make them stand among the other competitors in the market. The effectiveness of such technologies can not only improve the financial benefits of the companies, but the workers’ safety and health through the real time monitoring of the work environment. Here in this research the main aim is to present the right frameworks that can be used in the literature through companies and researchers to allow them to implement these technologies correctly in the boundaries of their businesses. In addition to that, the Smart factory concept, as introduced in the context of Industry 4.0, promotes the development of a new interconnected manufacturing environment where human operators cooperate with machines. While the role of the operator in the smart factory is substantially being rediscussed, the industrial approach towards safety and ergonomics still appears frequently outdated and inadequate. This research approaches such topic referring to the vibration risk, a well-known cause of work-related pathologies, and proposes an original methodology for mapping the risk exposure related to the performed activities. A miniaturized wearable device is employed to collect vibration data, and the obtained signals are segmented and processed in order to extract the significant features. An original machine learning classifier is then employed to recognize the worker’s activity and evaluate the related exposure to vibration risks. Finally, the results obtained from the experimental analysis demonstrate feasibility and the effectiveness of the proposed methodology.

IoT and Industry 4.0 technologies in Digital Manufacturing Transformation

ABUSOHYON, ISLAM ASEM SALAH
2022

Abstract

The evolution of internet of things, cyber physical system, digital twin and artificial intelligence is stimulating the transformation of the product-centric processes toward smart control digital service-oriented ones. With the implementation of artificial intelligence and machine learning algorithms, IoT has accelerated the movement from connecting devices to the Internet to collecting and analyzing data by using sensors to extract data throughout the lifecycle of the product, in order to create value and knowledge from the huge amount of the collected data, such as the knowledge of the product performance and conditions. The importance of internet of things technology in manufacturing comes from its ability to collect real time data and extract valuable knowledge from these huge amount of data which can be supported through the implementation of smart IoT-based servitization framework which was presented in this research together with a 10-steps approach diagram. Moreover, literature review has been carried out to develop the research and deepen the knowledge in the field of IoT, CPS, DT and Artificial Intelligence, and then interviews with experts have been conducted to validate the contents, since DT is a quite new technology, so there are different points of view about certain concepts of this technology. The main scope and objective of this research is to allow organizational processes and companies to benefit form the value added information that can be achieved through the right implementation of advanced technologies such as IoT, DT, CPS, and artificial intelligence which can provide financial benefits to the manufacturing companies and competitive advantages to make them stand among the other competitors in the market. The effectiveness of such technologies can not only improve the financial benefits of the companies, but the workers’ safety and health through the real time monitoring of the work environment. Here in this research the main aim is to present the right frameworks that can be used in the literature through companies and researchers to allow them to implement these technologies correctly in the boundaries of their businesses. In addition to that, the Smart factory concept, as introduced in the context of Industry 4.0, promotes the development of a new interconnected manufacturing environment where human operators cooperate with machines. While the role of the operator in the smart factory is substantially being rediscussed, the industrial approach towards safety and ergonomics still appears frequently outdated and inadequate. This research approaches such topic referring to the vibration risk, a well-known cause of work-related pathologies, and proposes an original methodology for mapping the risk exposure related to the performed activities. A miniaturized wearable device is employed to collect vibration data, and the obtained signals are segmented and processed in order to extract the significant features. An original machine learning classifier is then employed to recognize the worker’s activity and evaluate the related exposure to vibration risks. Finally, the results obtained from the experimental analysis demonstrate feasibility and the effectiveness of the proposed methodology.
File in questo prodotto:
File Dimensione Formato  
phdunige_4627373.pdf

accesso aperto

Tipologia: Tesi di dottorato
Dimensione 2.2 MB
Formato Adobe PDF
2.2 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/1081117
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact