Industry 4.0

PREMA – PREdictiveMAIntenance

Project started in 2020, with targets:

  • Application of industry 4.0 to Bottero glass handling machinery.
  • Usage of IoT and Big Data Analysis technologies to extract information and gain knowledge about the real-time behavior of objects subjected to vibrational stresses
    • Minimize damage and allow intelligent predictive analysis

ICT platform for integrated dynamic and autonomous management of high-level automation production operations aimed at optimizing resources (people, materials, production systems).

DISLO-MAN
D
ynamic Integrated ShopfLoor Operation MANagement for Industry 4.0

ICT platform for integrated dynamic and autonomous management of high-level automation production operations aimed at optimizing resources (people, materials, production systems).

Project financed under POR 2014/2020 of the Piedmont Region, FESR (European Regional Development Fund) and MIUR program – Piedmont Region – Action 3 – “Intelligent Factory”

For more information visit the website disloman.it

Roller-bearing

Innovative research related to the use of vibration signals for the prognostic / early identification of the type and severity of damage occurring to roller-bearings through the implementation of machine learning and/or neural networks algorithms.

Project financed under POR 2014/2020 of the Piedmont Region, FESR (European Regional Development Fund) and MIUR program – Piedmont Region – Action 3 – “Intelligent Factory”

For more information visit the website disloman.it

Two data base as input:

1) data collected over a rig set up at Department of Mechanical and Aerospace Engineering lab of  Politecnico di Torino

cylindrical roller bearings (roller and inner ring)

intended to test high speed aeronautical bearings

512k samples, 6 channels.

2) data collected in the test rig the NSF I/UCRC on Intelligent Maintenance Systems (IMS)

  • spherical roller bearings
  • the bearing test rig hosts four test bearings on one shaft, driven by an AC motor and coupled by rub belts.
  • 3 Run of failure tests, 20k samples, 4 channels.
Several machine learning algorythms and neural networks have been applied, compared and enhanced.
As a result, 97.71% of average prediction accuracy has been achieved

    Fill the form to submit your application

    Experiences *
    Attach your CV *
    Field marked with * are mandatory.
    By clicking "Send" you accept our terms and conditions. Find out how we collect, use and share your data in our Privacy and Cookie Policy.
    Please prove you are human by selecting the Plane.