Mattera, Giulio (2024) Monitoring and Control of Wire Arc Additive Manufacturing Process using Artificial Intelligence. [Tesi di dottorato]
Questa è la versione più aggiornata di questo documento.
![[thumbnail of PhDThesis_XXXVII_Mattera_final.pdf]](https://www.fedoa.unina.it/style/images/fileicons/other.png "PhDThesis_XXXVII_Mattera_final.pdf") |
Documento PDF
PhDThesis_XXXVII_Mattera_final.pdf Visibile a [TBR] Amministratori dell'archivio Download (6MB) |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | Monitoring and Control of Wire Arc Additive Manufacturing Process using Artificial Intelligence |
| Autori: | Autore Email Mattera, Giulio giulio.mattera@unina.it |
| Data: | 3 Dicembre 2024 |
| Numero di pagine: | 165 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dipartimento: | Ingegneria Chimica, dei Materiali e della Produzione Industriale |
| Dottorato: | Ingegneria dei prodotti e dei processi industriali |
| Ciclo di dottorato: | 37 |
| Coordinatore del Corso di dottorato: | nome email D'Anna, Andrea anddanna@unina.it |
| Tutor: | nome email Nele, Luigi [non definito] Caggiano, Alessandra [non definito] |
| Data: | 3 Dicembre 2024 |
| Numero di pagine: | 165 |
| Parole chiave: | additive manufacturing; artificial intelligence; feedback control; process monitoring; welding; |
| Settori scientifico-disciplinari del MIUR: | Area 09 - Ingegneria industriale e dell'informazione > ING-IND/16 - Tecnologie e sistemi di lavorazione |
| Informazioni aggiuntive: | giuliomattera@outlook.it |
| Depositato il: | 24 Nov 2025 05:52 |
| Ultima modifica: | 09 Ago 2026 05:55 |
| URI: | https://www.fedoa.unina.it/id/eprint/16302 |
Available Versions of this Item
-
Analisi del ruolo delle varianti geniche del recettore della trombina nella patogenesi della cardiopatia ischemica in pazienti ipertesi. (deposited 11 Giu 2008)
- Monitoring and Control of Wire Arc Additive Manufacturing Process using Artificial Intelligence. (deposited 24 Nov 2025 05:52) [Attualmente visualizzato]
Abstract
Wire Arc Additive Manufacturing (WAAM) is an additive manufacturing process that is attracting attention from both the research and industrial fields due to its high print rates and the ability to build mid to large-sized metal components in a cost-effective manner. While the mechanical properties of printed components and general print parameters have been extensively studied in the literature, a shifting focus towards the application of Artificial Intelligence (AI) to enhance the quality and sustainability of the printed components is emerging. AI can be employed to monitor the process in real-time, providing feedback on component quality. Moreover, advanced feedback control mechanisms can then adjust process parameters online to improve surface quality and prevent defects. Furthermore, optimisation techniques can be utilised to solve complex goal-oriented problems, determining optimal process parameters before printing the part. A comprehensive literature survey was conducted in this thesis, identified gaps in the current literature such as the employment of multi-sensor frameworks for process monitoring and the use of frequency domain analysis and unsupervised learning for developing monitoring applications. Additionally, advanced model-free control policies have been designed using a disruptive technology like Reinforcement Learning, substituting the need for complex and time-consuming Multiple Input, Multiple Output (MIMO) nonlinear controllers like Model Predictive Control (MPC), which represent the actual state of the art in this field. Finally, metaheuristic optimisation techniques are employed to fine-tune process parameters to achieve goals such as sustainable fabrication of components.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
