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

Abstract

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.

Uncertainty in Building Inspection and Diagnosis: A Probabilistic Model Quantification

“…The proposed model supplies a graphical representation of quantitative and qualitative data that is easy to interpret, focusing on the cause-defect relationship. BN models have also been used by other authors with similar purposes, for instance, evaluation of maintenance scenarios [16], making predictive maintenance decisions [9,10], inspection planning in ships [53], damage assessment [54] and design-for-maintainability assessment of building systems [17]. Yet, to the best of the authors' knowledge, no other research has centred on the use of BN models to analyse the diagnosis process of building defects on rendered façades.…”

“…Bayesian belief networks were also used, for instance, to assess the probability of collapse of structures associated with the corrosion of reinforcement in concrete structures of buildings, for repair optimisation [14] and to monitor the condition state of a bridge [15]. Additionally, maintenance scenarios were also explored using Bayesian networks to support decision making at the design stage of a building, accommodating a design-for-maintainability approach [16,17]. Most of the mentioned research in the literature input conditional probabilities in the BN based on the judgement of experts, while the model proposed in this research is based on an existing dataset from on-site inspections, providing conditional probabilities from real scenarios.…”