Politecnico di Torino (logo)

End-effector tools State of Health estimation: a data driven approach

Davide Zanon

End-effector tools State of Health estimation: a data driven approach.

Rel. Alessandro Rizzo, Giovanni Guida. Politecnico di Torino, Corso di laurea magistrale in Mechatronic Engineering (Ingegneria Meccatronica), 2021

PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (5MB) | Preview

Nowadays, the focusing on more efficient and cost saving maintenance techniques is the goal of both research and work areas. It is clear that the advantages coming from a preservation of the continuity of the industrial line can make an economic difference with the main competitors. The main technologies available in literature and on the field that cope with this topic make relevant use of machine learning algorithms, requiring thus high computational resources. On the contrary, the MorePRO project aims to introduce itself in this slice of the market, proposing an innovative edge computing device, able to carry out an on-line prediction of the State of Health of CNC machines. The main idea concerns the realization of a new product, that combines a consistent use of the multi-model approach, an approach refi ned by brain Technologies in the BAT-MAN and ERMES projects (based on some techniques such as Kalman fi ltering and residual error analysis), along with a data driven tool used to increase the robustness of the prediction. In this way, on the one hand, an effective and short-term estimate of usury is obtained, on the other, the possibility of refi ning the estimate itself in the long term. The main steps followed in this Thesis work are the building of the model under assumption, the application and testing of the methods coming from the previous projects and finally the implementation of the learning algorithm for the previously mentioned purposes.

Relators: Alessandro Rizzo, Giovanni Guida
Academic year: 2020/21
Publication type: Electronic
Number of Pages: 103
Corso di laurea: Corso di laurea magistrale in Mechatronic Engineering (Ingegneria Meccatronica)
Classe di laurea: New organization > Master science > LM-25 - AUTOMATION ENGINEERING
Aziende collaboratrici: Brain technologies
URI: http://webthesis.biblio.polito.it/id/eprint/18050
Modify record (reserved for operators) Modify record (reserved for operators)