The development of structural health monitoring (SHM) systems and their integration in actual structures has become a necessity as it can provide a robust and low-cost solution for monitoring the structural integrity of and the ability to predict the remaining life of structures. In this review, we aim at focusing on one of the important issues of SHM, the design, and implementation of sensor networks. Location and number of sensors, in any SHM system, are of high importance as they impact the system integration, system performance, and accuracy of assessment, as well as the total cost. Hence we are interested in shedding the light on the sensor networks as an essential component of SHM systems. The review discusses several important parameters including design and optimization of sensor networks, development of academic and commercial solutions, powering of sensors, data communication, data transmission, and analytics. Finally, we presented some successful case studies including the challenges and limitations associated with the sensor networks.

The propagation properties of ultrasonic waves in rebar-reinforced concrete beams were investigated and their ability for damage identification was demonstrated. Rectangular piezoelectric ceramics were attached at the exposed ends of the rebar to monitor the wave transmission along the rebar with and without simulated corrosion, which was introduced in the form of partial removal of material from the rebar. Experimental testing demonstrated that the presence of concrete had a significant influence on the propagation characteristics of guided waves along the rebar. In consideration of the inevitable discrepancies in different concrete beams due to individual specimen preparation and sensor installation, the time-reversal process was applied to identify the damage. A damage index was defined based on the correlation coefficient between the actuated and the reconstructed wave signals. Wavelet transform was applied to overcome the wave conversion difficulty and to reduce the noise in the captured wave signals. Damage of different sizes was introduced and then was correlated with the damage index. Enlarging the damage size resulted in an increase in the level of distortion in the reconstructed wave signals, and consequently, a higher damage index was obtained. The results demonstrate the efficiency of the time-reversal process in identifying damage in rebar-reinforced concrete structures.

Structural health monitoring has been increasingly used due to the advances in sensing technology and data analysis, facilitating the shift from time-based to condition-based maintenance. This work is part of the efforts which have applied structural health monitoring to the Sydney Harbour Bridge – one of Australia’s iconic structures. It combines dimensionality reduction and pattern recognition techniques to accurately and efficiently distinguish faulty components from well-functioning ones. Specifically, random projection is used for dimensionality reduction on the vibration feature data. Then, healthy and damaged patterns of bridge components are learned in the lower dimensional projected space using supervised and unsupervised machine learning methods, namely, support vector machine and one-class support vector machine. The experimental results using data from a laboratory-based building structure and the Sydney Harbour Bridge showed high feasibility of applying machine learning techniques to dimensionality reduction and damage detection in structural health monitoring. Random projection combined with support vector machine significantly reduces the computational time while maintaining the detection accuracy. The proposed method also outperformed popular dimensionality reduction techniques. The computational time of the method using random projection can be more than 200 times faster than that without using dimensionality reduction while still achieving similar detection accuracy.