In recent decades, the manufacturing sector undergone significant transformations driven by increasing global competition and the rapid development of digital technologies. In this context, companies have progressively adopted production models focused on efficiency, flexibility, and waste reduction, among which lean manufacturing is recognized as one of the most relevant organizational paradigms in industrial environments. Within this framework, the continuous improvement's philosphy, known as Kaizen, plays a central role. Kaizen events represent one of the most widely used operational tools for implementing this philosophy, enabling the analysis and improvement of specific production processes through structured, short-term interventions characterized by strong employee involvement. This thesis aims to analyze the main characteristics of Kaizen events, describing their operational phases, the tools employed, and the benefits achievable in terms of process efficiency and quality. In addition, the main limitations of this approach are highlighted, particularly with respect to the management of complex production systems and the analysis of large volumes of data. The study further explores the role of digital technologies introduced by the Industry 4.0 paradigm, with particular focus on artificial intelligence and big data analytics. The integration between Lean methodologies and advanced digital technologies is examined as an evolution toward increasingly data-driven production systems, capable of more effectively supporting decision-making processes and continuous improvement activities. Finally, the thesis highlights how the combined adoption of Lean tools and artificial intelligence-based technologies represents a strategic lever for optimizing production processes, contributing to the development of more efficient, flexible, and competitive industrial systems.
Negli ultimi decenni il settore manifatturiero è stato caratterizzato da profondi cambiamenti dovuti alla crescente competitività dei mercati globali e allo sviluppo delle tecnologie digitali. In tale contesto, le imprese hanno progressivamente adottato modelli produttivi orientati all’efficienza, alla flessibilità e alla riduzione degli sprechi, tra cui la lean manufacturing, oggi riconosciuta come uno dei principali paradigmi organizzativi in ambito industriale. All’interno di questo approccio, la filosofia del miglioramento continuo, nota come Kaizen, assume un ruolo centrale. I cantieri Kaizen rappresentano uno degli strumenti operativi più diffusi per l’implementazione di tale filosofia, consentendo di analizzare e migliorare specifici processi produttivi attraverso interventi strutturati, di breve durata e caratterizzati da un elevato coinvolgimento del personale. La presente tesi si propone di analizzare le caratteristiche dei cantieri Kaizen, descrivendone le principali fasi operative, gli strumenti utilizzati e i benefici ottenibili in termini di efficienza e qualità dei processi. Vengono inoltre evidenziati i principali limiti di tale approccio, in particolare in relazione alla gestione di sistemi produttivi complessi e all’analisi di grandi quantità di dati. Successivamente, il lavoro approfondisce il ruolo delle tecnologie digitali introdotte dal paradigma dell’Industry 4.0, con particolare riferimento all’intelligenza artificiale e all’analisi dei big data. L’integrazione tra metodologie Lean e tecnologie avanzate viene analizzata come evoluzione verso sistemi produttivi sempre più data-driven, in grado di supportare in modo più efficace i processi decisionali e le attività di miglioramento continuo. Infine, la tesi evidenzia come l’adozione congiunta di strumenti Lean e tecnologie basate sull’intelligenza artificiale rappresenti una leva strategica per l’ottimizzazione dei processi produttivi, contribuendo allo sviluppo di sistemi industriali più efficienti, flessibili e competitivi.
Tecniche di gestione di un progetto: influenza dell'intelligenza artificiale nei cantieri Kaizen
SCHIEVANO, GIOVANNI
2025/2026
Abstract
In recent decades, the manufacturing sector undergone significant transformations driven by increasing global competition and the rapid development of digital technologies. In this context, companies have progressively adopted production models focused on efficiency, flexibility, and waste reduction, among which lean manufacturing is recognized as one of the most relevant organizational paradigms in industrial environments. Within this framework, the continuous improvement's philosphy, known as Kaizen, plays a central role. Kaizen events represent one of the most widely used operational tools for implementing this philosophy, enabling the analysis and improvement of specific production processes through structured, short-term interventions characterized by strong employee involvement. This thesis aims to analyze the main characteristics of Kaizen events, describing their operational phases, the tools employed, and the benefits achievable in terms of process efficiency and quality. In addition, the main limitations of this approach are highlighted, particularly with respect to the management of complex production systems and the analysis of large volumes of data. The study further explores the role of digital technologies introduced by the Industry 4.0 paradigm, with particular focus on artificial intelligence and big data analytics. The integration between Lean methodologies and advanced digital technologies is examined as an evolution toward increasingly data-driven production systems, capable of more effectively supporting decision-making processes and continuous improvement activities. Finally, the thesis highlights how the combined adoption of Lean tools and artificial intelligence-based technologies represents a strategic lever for optimizing production processes, contributing to the development of more efficient, flexible, and competitive industrial systems.| File | Dimensione | Formato | |
|---|---|---|---|
|
Schievano_Giovanni.pdf
accesso aperto
Dimensione
6.07 MB
Formato
Adobe PDF
|
6.07 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/111732