Optimal wireless sensor network configuration for structural monitoring using automatic-learning firefly algorithm

Wireless sensor networks are becoming attractive data communication patterns in structural health monitoring systems. Designing and applying effective wireless sensor network-based structural health monitoring systems for large-scale civil infrastructure require a great number of wireless sensors and the optimal wireless sensor networks configuration becomes critical for such spatially separated large structures. In this article, optimal wireless sensor network configuration for structural health monitoring is treated as a discrete optimization problem, where parameter identification and network performance are simultaneously addressed. To solve this rather complicated optimization problem, a novel swarm intelligence algorithm called the automatic-learning firefly algorithm is proposed by integrating the original firefly algorithm with the Levy flight and the automatic-learning mechanism. In the proposed algorithm, the Levy flight is adopted to maximize the searching capability in unknown solution space and avoid premature convergence and the automatic-learning mechanism is designed to drive fireflies to move toward better locations at high speed. Numerical experiments are performed on a long-span bridge to demonstrate the effectiveness of the proposed automatic-learning firefly algorithm. Results indicate that automatic-learning firefly algorithm can find satisfactory wireless sensor network configurations, which facilitate easy discrimination of identified mode vectors and long wireless sensor network lifetime, and the innovations in automatic-learning firefly algorithm make it superior to the simple discrete firefly algorithm as to solution quality and convergence speed.