Simeone, Alessandro
(2013)
Multi-Sensor Process Monitoring in
Turning of Inconel 718.
[Tesi di dottorato]
| Tipologia del documento: |
Tesi di dottorato
|
| Lingua: |
English |
| Titolo: |
Multi-Sensor Process Monitoring in
Turning of Inconel 718 |
| Autori: |
| Autore | Email |
|---|
| Simeone, Alessandro | alessandro.simeone@unina.it |
|
| Data: |
31 Marzo 2013 |
| Numero di pagine: |
207 |
| Istituzione: |
Università degli Studi di Napoli Federico II |
| Dipartimento: |
Ingegneria Chimica, dei Materiali e della Produzione Industriale |
| Scuola di dottorato: |
Ingegneria industriale |
| Dottorato: |
Tecnologie e sistemi di produzione |
| Ciclo di dottorato: |
25 |
| Coordinatore del Corso di dottorato: |
| nome | email |
|---|
| Carrino, Luigi | luigi.carrino@unina.it |
|
| Tutor: |
| nome | email |
|---|
| Teti, Roberto | roberto.teti@unina.it |
|
| Data: |
31 Marzo 2013 |
| Numero di pagine: |
207 |
| Parole chiave: |
Sensor Monitoring, Inconel 718, Turning, Neural Networks, Surface Integrity, Sensor Fusion, Multiple Sensor Monitoring, Tool State Identification |
| Settori scientifico-disciplinari del MIUR: |
Area 09 - Ingegneria industriale e dell'informazione > ING-IND/16 - Tecnologie e sistemi di lavorazione |
[error in script]
[error in script]
| Depositato il: |
03 Apr 2013 15:36 |
| Ultima modifica: |
24 Lug 2014 07:06 |
| URI: |
http://www.fedoa.unina.it/id/eprint/9288 |
| DOI: |
10.6092/UNINA/FEDOA/9288 |
Abstract
This thesis work was developed in conjunction with the activities of the EC FP7 Adaptive Control of Manufacturing Processes for a New Generation of Jet Engine Components (ACCENT) Project (See section 1.4).
Most of the experimental activities were carried out at AVIO SpA facilities, Pomigliano d’Arco, Naples; Avio SpA is an industrial partner in the EC FP7 ACCENT Project.
The goals of this thesis work are explained below.
First of all, the design and realization of an experimental campaign of turning tests on a nickel base alloy of aeronautical interest (Inconel 718) was carried out in an industrial environment.
A multi sensor monitoring system, endowed with diverse sensing units was designed, assembled, calibrated and employed during machining tests in order to acquire different sensor signals on an online basis.
Raw signals acquired were subjected to conventional and advanced signal analysis methods in order to extract significant features useful for decision making on process conditions.
This thesis work includes material characterization tests carried out to investigate the surface integrity of the workpiece as well as the state of the tool wear with the scope of correlating these conditions to sensor signals features.
By the implementation of a decision making support system, sensor signal features extracted by signal processing techniques were utilized for the identification of defects in the workpiece due to the machining process, as revealed by the material characterization tests.
Decision making was carried out by diverse Neural Network pattern recognition paradigms, designed and implemented for the purpose.
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
