The continuous increase in the number of nuclear sites entering their final phase of use and decommissioning has drawn the attention of governments, regulatory bodies and industries towards decommissioning projects. However, despite the high number of uncertainties and risks of these projects, caused by their long duration and the uniqueness of each site, there has been a lack of dedicated risk management tools beyond the guidelines established by PMBoK. Therefore, this study aims to design an integrated model for risk management of nuclear decommissioning projects. For the construction of the model, one of the current trends in project management was followed, namely the use of artificial intelligence algorithms, relying on individual models already in the literature and integrating them into a single model, capable of assessing risks, identifying an optimal set of risk mitigation actions, and generating a prediction of the additional project delay or cost based on a quantitative risk analysis, given the lack of such a tool in the literature. To demonstrate its validity, the model is applied to a project currently underway in Italy, generating a forecast of the project delay itself. In order to apply the model, 4 experts answered a questionnaire with the aim of obtaining input data. The results are promising, as the delay prediction for the nearest phase of the project differs from the current one only by an error of 4.7%. The proposed model has the ability to help the project manager in managing risks and predicting delays or additional project costs during the preliminary phase. In addition, the approach is equally useful in controlling risks in the progress stages of the project by dynamically updating forecasts.
Il continuo aumento del numero di siti nucleari che entrano nella loro fase finale di utilizzo e decommissionamento ha attirato l’attenzione di governi, corpi regolatori e industrie verso i progetti di smantellamento. Tuttavia, nonostante l’elevato numero di incertezze e rischi di questi progetti, causati dalla loro lunga durata e dall’unicità di ogni sito, è stata riscontrata una mancanza di strumenti dedicati alla gestione del rischio, oltre alle linee guida stabilite dal PMBoK. Perciò, questo studio ha come obiettivo l’ideazione di un modello integrato per la gestione dei rischi dei progetti di decommissionamento nucleare. Per la costruzione del modello, si è seguito uno degli attuali trend nel project management, ovvero l’utilizzo di algoritmi di intelligenza artificiale, basandosi su singoli modelli già presenti in letteratura ed integrandoli in un unico modello, capace di valutare i rischi, individuare un set ottimale di azioni di mitigazione del rischio, e generare una previsione del ritardo o dei costi aggiuntivi di progetto sulla base di un’analisi quantitativa dei rischi, data la mancanza di un simile strumento in letteratura. Per dimostrarne la validità, il modello viene applicato ad un progetto attualmente in corso in Italia, generando una previsione del ritardo del progetto stesso. Per poter applicare il modello, 4 esperti hanno risposto ad un questionario con l’obiettivo di ottenere i dati di input. I risultati sono promettenti, in quanto la previsione del ritardo per la fase più prossima del progetto differisce da quello attuale solamente per un errore del 4.7%. Il modello proposto ha la capacità di aiutare il project manager nella gestione dei rischi e nella previsione dei ritardi o dei costi aggiuntivi del progetto durante la fase preliminare. Inoltre, l’approccio è ugualmente utile per il controllo dei rischi nelle fasi di avanzamento del progetto, aggiornando dinamicamente le previsioni.
Project risk management and artificial intelligence : a comprehensive framework for nuclear decommissioning
MANFREDI, CARMINE MATTIA
2020/2021
Abstract
The continuous increase in the number of nuclear sites entering their final phase of use and decommissioning has drawn the attention of governments, regulatory bodies and industries towards decommissioning projects. However, despite the high number of uncertainties and risks of these projects, caused by their long duration and the uniqueness of each site, there has been a lack of dedicated risk management tools beyond the guidelines established by PMBoK. Therefore, this study aims to design an integrated model for risk management of nuclear decommissioning projects. For the construction of the model, one of the current trends in project management was followed, namely the use of artificial intelligence algorithms, relying on individual models already in the literature and integrating them into a single model, capable of assessing risks, identifying an optimal set of risk mitigation actions, and generating a prediction of the additional project delay or cost based on a quantitative risk analysis, given the lack of such a tool in the literature. To demonstrate its validity, the model is applied to a project currently underway in Italy, generating a forecast of the project delay itself. In order to apply the model, 4 experts answered a questionnaire with the aim of obtaining input data. The results are promising, as the delay prediction for the nearest phase of the project differs from the current one only by an error of 4.7%. The proposed model has the ability to help the project manager in managing risks and predicting delays or additional project costs during the preliminary phase. In addition, the approach is equally useful in controlling risks in the progress stages of the project by dynamically updating forecasts.| File | Dimensione | Formato | |
|---|---|---|---|
|
Elaborato_CarmineMattia_Manfredi_Rev2911.pdf
accessibile in internet solo dagli utenti autorizzati
Dimensione
4.93 MB
Formato
Adobe PDF
|
4.93 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/183385