Publication

  • L. Davoli, L. Belli and G. Ferrari. IoT-enabled Smart Monitoring and Optimization for Industry 4.0. In Internet of Things: Techonologies, Challenges and Impact, \TeX MAT, pp. 207–226, 2020. bib | preprint ]
  • @inbook{dabefe:2020:cnit,
        title = {{IoT-enabled Smart Monitoring and Optimization for Industry 4.0}},
        author = {{Davoli}, Luca and {Belli}, Laura and {Ferrari}, Gianluigi},
        editor = {{Atzori}, Luigi and {Ferrari}, Gianluigi},
        url = {https://www.texmat.it/internet-of-things-technologies-challenges-and-impact.html},
        isbn = {978-88-949-8239-8},
        year = {2020},
        date = {2020-09-04},
        booktitle = {Internet of Things: Techonologies, Challenges and Impact},
        volume = {5},
        pages = {207--226},
        publisher = {\TeX MAT},
        address = {Roma, Italy},
        chapter = {11},
        abstract = {In the last decades, forward-looking companies have introduced Internet of Things (IoT) concepts in several industrial application scenarios, leading to the so-called Industrial IoT (IIoT) and, restricting to the manufacturing scenario, to Industry 4.0. Their ambition is to enhance, through proper field data collection and analysis, the productivity of their facilities and the creation of real-time digital twins of different industrial scenarios, aiming to significantly improve industrial management and business processes. Moreover, since modern companies should be as ``smart'' as possible and should adapt themselves to the varying nature of the digital supply chains, they need different mechanisms in order to (i) enhance the control of the production plant and (ii) comply with high-layer data analysis and fusion tools that can foster the most appropriate evolution of the company itself (thus lowering the risk of machine failures) by adopting a predictive approach. Focusing on the overall company management, in this chapter we present an example of a ``renovation'' process, based on: (i) digitization of the control quality process on multiple production lines, aiming at digitally collecting and processing information already available in the company environment; (ii) monitoring and optimization of the production planning activity through innovative approaches, aiming at extending the quantity of collected data and providing a new perspective of the overall current status of a factory; and (iii) a predictive maintenance approach, based on a set of heterogeneous analytical mechanisms to be applied to on-field data collected in different production lines, together with the integration of sensor-based data, toward a paradigm that can be denoted as Maintenance-as-a-Service (MaaS). In particular, these data are related to the operational status of production machines and the currently available warehouse supplies. Our overall goal is to show that IoT-based Industry 4.0 strategies allow to continuously collect heterogeneous Human-to-Things (H2T) and Machine-to-Machine (M2M) data, which can be used to optimize and improve a factory as a whole entity.}
    }