The increased frequency of natural disasters and man-made catastrophes has caused major disruptions to critical infrastructures (CI) such as water distribution networks (WDNs). Therefore, reducing the vulnerability of the systems through physical and organizational restoration plans are the main concern for system engineers and utility managers that are responsible for the design, operation, and protection of WDNs. In this paper, a resilience index (R) of a WDN has been proposed that is the product of three indices: (1) the number of users temporarily without water, (2) the water level in the tank, and (3) the water quality. The resilience index is expected to help planners and engineers evaluate the functionality of a WDN, which includes: (1) delivering a certain demand of water with an acceptable level of pressure and quality, and (2) the restoration process following an extreme event. A small town in the south of Italy has been selected as a case study to show the applicability of this index us...

A neural network–based methodology is proposed for the rapid evaluation of the seismic demand using data extracted from ground motion records. Limit‐state fragilities for a moment‐resisting steel frame are developed using Monte Carlo simulation. The proposed methodology allows taking into account uncertainties on both structural capacity and seismic demand with reduced computational cost. The use of neural networks is motivated by the approximate concepts inherent in the fragility assessment and the large number of time‐consuming nonlinear response history analyses required for the accurate calculation of the probability of a limit‐state being exceeded. The trained neural network is used to obtain the level of seismic demand, which is expressed in terms of maximum interstory drift. The methodology proposed is efficient and general in application.