A hybrid PSO-EnKF framework for optimal sensor placement in structural health monitoring: modeling and comparative evaluation against GA-EnKF and SA-EnKF

Purpose Structural health monitoring (SHM) helps assess how structures perform over time, especially in earthquake-prone regions. However, a persistent practical challenge is deciding where to install the sensors – instrumenting all possible locations is neither feasible nor cost-effective. This study addresses that challenge by developing and evaluating a hybrid Particle Swarm Optimization-Ensemble Kalman Filter (PSO-EnKF) framework for optimal sensor placement in SHM applications. Design/methodology/approach The PSO-EnKF framework was applied to a 10-story shear building subjected to El Centro Earthquake record. The objective was to identify the most informative sensor positions by minimizing the discrepancy between synthetic measured and EnKF-predicted displacement and velocity responses, for both a two-sensor and a three-sensor case. Results were benchmarked against GA-EnKF, SA-EnKF and Brute-Force search. Findings PSO-EnKF converged to near-optimal sensor configurations, floors 3 and 10 for the two-sensor case and floors 3, 5 and 7 for the three-sensor case, both yielding small discrepancies between measured and predicted responses. GA-EnKF matched the Brute-Force optimal locations in both scenarios: floors 1 and 10 and floors 1, 7 and 10. Repeated runs showed that PSO-EnKF consistently reached near-optimal configurations but remained less accurate than GA-EnKF and less computationally efficient than SA-EnKF for this discrete, floor-based problem. Originality/value The contribution lies in integrating and comparatively evaluating PSO within an EnKF-based OSP framework for SHM, using consistent benchmark conditions for a direct and fair comparison. The findings highlight the strengths and limitations of standard PSO for this discrete benchmark and suggest continuous or coordinate-based sensor placement applications should be investigated in future work.

Authors

Institutions

Publication Details

Journal
Smart and Sustainable Built Environment
Published
2026-11-19
DOI
https://doi.org/10.1108/sasbe-03-2026-0191
Primary Topic
Structural Health Monitoring Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A hybrid PSO-EnKF framework for optimal sensor placement in structural health monitoring: modeling and comparative evaluation against GA-EnKF and SA-EnKF

Abdulkader El‐Mir, Maria Ghannoum, Joseph Jean Assaad, Dana Nasr et al.
2 links
Smart and Sustainable Built Environment
Structural Health Monitoring Techniques
article

A hybrid PSO-EnKF framework for optimal sensor placement in structural health monitoring: modeling and comparative evaluation against GA-EnKF and SA-EnKF

Abdulkader El‐Mir, Maria Ghannoum, Joseph Jean Assaad, Dana Nasr, Mohamad Ezzedine El Dandachy, Georges Najem
article en

Abstract

Purpose Structural health monitoring (SHM) helps assess how structures perform over time, especially in earthquake-prone regions. However, a persistent practical challenge is deciding where to install the sensors – instrumenting all possible locations is neither feasible nor cost-effective. This study addresses that challenge by developing and evaluating a hybrid Particle Swarm Optimization-Ensemble Kalman Filter (PSO-EnKF) framework for optimal sensor placement in SHM applications. Design/methodology/approach The PSO-EnKF framework was applied to a 10-story shear building subjected to El Centro Earthquake record. The objective was to identify the most informative sensor positions by minimizing the discrepancy between synthetic measured and EnKF-predicted displacement and velocity responses, for both a two-sensor and a three-sensor case. Results were benchmarked against GA-EnKF, SA-EnKF and Brute-Force search. Findings PSO-EnKF converged to near-optimal sensor configurations, floors 3 and 10 for the two-sensor case and floors 3, 5 and 7 for the three-sensor case, both yielding small discrepancies between measured and predicted responses. GA-EnKF matched the Brute-Force optimal locations in both scenarios: floors 1 and 10 and floors 1, 7 and 10. Repeated runs showed that PSO-EnKF consistently reached near-optimal configurations but remained less accurate than GA-EnKF and less computationally efficient than SA-EnKF for this discrete, floor-based problem. Originality/value The contribution lies in integrating and comparatively evaluating PSO within an EnKF-based OSP framework for SHM, using consistent benchmark conditions for a direct and fair comparison. The findings highlight the strengths and limitations of standard PSO for this discrete benchmark and suggest continuous or coordinate-based sensor placement applications should be investigated in future work.

Smart and Sustainable Built Environment
University of Balamand (LB), Beirut Arab University (LB)
Industry, innovation and infrastructure
Structural Health Monitoring Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon