Topological surrogates for computationally efficient seismic robustness optimization of water pipe networks

Abstract

The criticality of seismic robustness of the water pipe networks cannot be overstated. Current methodologies for optimizing seismic robustness of city‐scale water pipe networks are scarce. A very few studies that can be found are also prone to long optimization runtimes due to the requirement of repeated hydraulic analysis. Hence, there is a critical need for the identification of computationally efficient surrogate optimization methods for maximizing seismic robustness of water pipe networks. To address this need, this research was conducted to identify, for the first time, computationally efficient topological surrogates for hydraulic simulation‐based optimization. The computational efficiency of surrogate optimization was measured in terms of solution quality (i.e., post‐earthquake serviceability) and computational runtime. Ten different topological connectivity metrics were evaluated out of which five were considered computationally infeasible due to their prohibitive optimization runtime. Five remaining metrics were then used to formulate five surrogate objective functions for seismic robustness of water pipe networks. Each of these functions was optimized using a simulated annealing‐based algorithm. Application of the proposed approach to city‐level benchmark networks helped to identify two metrics out of ten that offered a substantial reduction in optimization runtime with a minimal loss in solution quality. These findings will be highly valuable to water distribution network managers for identifying economical rehabilitation policies for enhancing the seismic robustness at a city‐scale within a reasonable amount of time.

Simulation of spatially varying ground motion of urban buildings based on wavelet packet neural network

“…In recent years, machine learning and data-driven methods have been widely applied in the field of earthquake engineering and rapid seismic damage assessment due to their great potential in accurate mapping and surrogate calculation. [30][31][32][33] By training the precomputed data samples, the seismic responses or damage indexes at high fidelity can be rapidly obtained in urban seismic damage assessment. This helps regulatory bodies make more timely and optimal decisions to mitigate earthquake disasters.…”

“…But a series of assumptions aggravated the randomness of the calculation results and multiple influential factors of SSCI were difficult to consider adequately by such means. In recent years, machine learning and data‐driven methods have been widely applied in the field of earthquake engineering and rapid seismic damage assessment due to their great potential in accurate mapping and surrogate calculation 30–33 . By training the precomputed data samples, the seismic responses or damage indexes at high fidelity can be rapidly obtained in urban seismic damage assessment.…”

A graph convolution network‐deep reinforcement learning model for resilient water distribution network repair decisions

“…Correspondingly, the methods for resilience quantification can be broadly divided into two major categories, that is, surrogate‐based resilience quantification method and performance‐based resilience quantification method. The surrogate‐based quantification method treats the WDNs as static systems (typically before disruption) without considering their time‐dependent performance during or after the disruption (Jayaram & Srinivasan, 2008; Prasad et al., 2004; Pudasaini & Shahandashti, 2020; Todini, 2000; Zarghami et al., 2018). However, when it comes to the WDN post‐hazard management, the performance‐based method can provide a more straightforward evaluation method and therefore has been widely used.…”

Selection of the modeling resolution of infrastructure

“…Past research focused on developing the engineering tools needed to model the performance of individual infrastructure components like bridges, electric substations, and water and gas pipelines (e.g., Gardoni et al., 2002; Lanzano et al., 2013; Paolucci et al., 2010) and individual infrastructure like transportation, power, water, and gas distribution infrastructure (e.g., Bocchini & Frangopol, 2011; Cavalieri et al., 2014; Esposito et al., 2015; Nocera, Tabandeh, et al., 2019; Pudasaini & Shahandashti, 2020; Sharma & Gardoni, 2022). Past research also focused on additional important factors like the effects of aging and deterioration (e.g., Adeli, 2001; Kumar et al., 2015; Sanchez‐Silva et al., 2011), and the interdependencies among critical infrastructure (e.g., Argyroudis et al., 2015; Galbusera et al., 2018; Ouyang, 2014; Thacker et al., 2017) and among infrastructure and social systems (e.g., Franchin & Cavalieri, 2015; Guidotti et al., 2019).…”