Industry 4.0 and the technologies that support it are now topics on the agenda. Machine learning, big data, blockchain…

Occasionally we get a chance to observe some of the varied uses of these technologies, from the more “mundane” recommendation method used by Netflix or Amazon that relies on Big Data analysis, to the use of online automated translators that leverage Machine Learning algorithms, to Bitcoin, the cryptocurrency first example of Blockchain that has been so much talked about just lately.

Sometimes not, sometimes these technologies are the pillars on which projects or other technologies whose uses cannot yet be observed or it is rare that this has already happened.

Maybe you’ve heard of them, maybe you’re waiting for them to come out of the woodwork, such as fog computing, the evolution of the cloud that could be a key support for self-driving cars, or even the application of Analytics in the medical field whose potential is mind-blowing at times.

The choice to deal with these “innovative” topics (although, as fast as technology runs they could be called contemporary) was dictated both by the importance of these technologies, both for the present and the future, and by a personal passion sparked during studies and later cultivated individually.

For this reason, it was decided to start with an in-depth and at times technical analysis of the technologies and the macro field that brings them together (precisely, Industry 4.0), dwelling briefly on the present situation in Italy.

In order then to show with concrete examples the actual pervasiveness and enormous impact they have once they are made available to companies and public and private entities, we will go on to analyze the new SAP Leonardo innovation system, a “product” of the German multinational SAP that is particularly fitting precisely because it touches on the totality of the issues exposed in the course of the work.

Thanks then to the possibility of following a predictive quality project carried out for the company Arvedi Tubi Acciaio located in Cremona (CR), it was finally chosen to focus on the field of Predictive Analytics, within which this topic fits, first defining by means of the present literature, the phases, management and criticalities (from a theoretical point of view) of a project of this type and then focusing on the practical case, defining what the objectives were and what were the results that were achieved.

The goal of this section, in particular, is to document the development and implementation of a predictive quality project in the hope of providing sometimes support, sometimes inspiration for possible future projects, while also considering the inherent link between the issues of predictive, prescriptive, and automated quality.

DEPARTMENT OF MECHANICAL AND INDUSTRIAL ENGINEERING
Master’s Degree Program in Engineering Management

Sergio Soragni’s dissertation

Correlators:

Eng. Nicola Segnali (Regesta)
Eng. Giorgio Grazioli (Regesta)