This study was developed at the Department of Architecture of Pescara and Department of Energy, Systems, Territory and Construction Engineering of the University of Pisa as part of an experimental thesis that led to the implementation of a Decision Support System. The objective of the work was to implement a tool capable of evaluating - in relation to the choices concerning the morphology of the building, the construction technologies, the materials and the design of the architectural elements - the levels of maintenance quality implemented in the various phases of the project, from the first phases, in which few relevant decisions are made, to the executive phase characterized by a multiplicity of choices. The aim was to construct a tool in which the reliability of the evaluations was related to the quantity and quality of the data that feeds the decision-making process, but which is also able to evaluate preliminary decisions based on the elements of choice that characterize the first phases of the project. The conceptual model has been defined through the construction and implementation of a Bayesian Network or a graphical system of probabilistic inference able to represent the set of stochastic variables and their conditional dependencies through the use of a direct acyclic graph. Through the interrogation of the network it is therefore possible to evaluate through the expression of a synthetic index, a real overall rating of the different aspects that contribute to define the maintenance quality. The use of Bayesian Networks, in the light of the analyses carried out on an experimental basis - exemplified here on the case study of ING Groupe headquarters - for the ability to control a multitude of factors linked to the durability of materials, the morphology of systems and ease of intervention, seems capable of generating useful, effective and expandable tools to support the design decision-making process.

Maintenance-Oriented Design in Architecture. A Decision Support System for the Evaluation of Maintenance Scenarios Through Bayesian Networks Use. A Case Study: the Headquarters of ING Groupe in Amsterdam

Di Sivo, M.
;
Ladiana, D.
;
2020-01-01

Abstract

This study was developed at the Department of Architecture of Pescara and Department of Energy, Systems, Territory and Construction Engineering of the University of Pisa as part of an experimental thesis that led to the implementation of a Decision Support System. The objective of the work was to implement a tool capable of evaluating - in relation to the choices concerning the morphology of the building, the construction technologies, the materials and the design of the architectural elements - the levels of maintenance quality implemented in the various phases of the project, from the first phases, in which few relevant decisions are made, to the executive phase characterized by a multiplicity of choices. The aim was to construct a tool in which the reliability of the evaluations was related to the quantity and quality of the data that feeds the decision-making process, but which is also able to evaluate preliminary decisions based on the elements of choice that characterize the first phases of the project. The conceptual model has been defined through the construction and implementation of a Bayesian Network or a graphical system of probabilistic inference able to represent the set of stochastic variables and their conditional dependencies through the use of a direct acyclic graph. Through the interrogation of the network it is therefore possible to evaluate through the expression of a synthetic index, a real overall rating of the different aspects that contribute to define the maintenance quality. The use of Bayesian Networks, in the light of the analyses carried out on an experimental basis - exemplified here on the case study of ING Groupe headquarters - for the ability to control a multitude of factors linked to the durability of materials, the morphology of systems and ease of intervention, seems capable of generating useful, effective and expandable tools to support the design decision-making process.
2020
978-84-121101-8-0
File in questo prodotto:
File Dimensione Formato  
paper.pdf

accesso aperto

Tipologia: PDF editoriale
Dimensione 2.77 MB
Formato Adobe PDF
2.77 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11564/747962
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact