Abstract
The damage identification process provides relevant information about the current state of a structure under inspection, and it can be approached from two different points of view. The first approach uses data-driven algorithms, which are usually associated with the collection of data using sensors. Data are subsequently processed and analyzed. The second approach uses models to analyze information about the structure. In the latter case, the overall performance of the approach is associated with the accuracy of the model and the information that is used to define it. Although both approaches are widely used, data-driven algorithms are preferred in most cases because they afford the ability to analyze data acquired from sensors and to provide a real-time solution for decision making; however, these approaches involve high-performance processors due to the high computational cost. As a contribution to the researchers working with data-driven algorithms and applications, this work presents a brief review of data-driven algorithms for damage identification in structural health-monitoring applications. This review covers damage detection, localization, classification, extension, and prognosis, as well as the development of smart structures. The literature is systematically reviewed according to the natural steps of a structural health-monitoring system. This review also includes information on the types of sensors used as well as on the development of data-driven algorithms for damage identification.
Highlights
Ensuring the proper performance of all elements in a structure is a priority for designers and users
The definition of the operating and environmental conditions to which the system will be exposed is required: this has been a recurring topic for several authors [155]. This evaluation can reduce these factors when they are implemented by applying certain hardware elements or software strategies. These strategies include the use of interpolation and regression tools [156] to determine and eliminate the influence of these variables [157]; the use of measurements that are independent of the influence of conditions that have been addressed using mathematical methods, such as singular value decomposition (SVD), principal component analysis (PCA), auto-associative neural networks (AANN), factor analysis (FA), or cointegration; and, the use of variables that are not affected in the short term by changes in environmental conditions [158], as is quite common in the instrumentation of civil structures
Since data in Structural health monitoring (SHM) can come from different kinds of sensors as was previously explained, there is not a general form to apply in all the cases; from this point of view, it is desireable to explore different methods to determine wich one produces the best results in the final damage-identification process
Summary
Ensuring the proper performance of all elements in a structure is a priority for designers and users. Da ma ge ide nti fic at i on p ro ce ss SHM is still a developing area—as evidenced by the rapid increase in the number of research works and publications—research has been ongoing for the past 23 years [1] Both the benefits in the above list and the advances in computation and data science applications motivate the continually rising interest in structural health-monitoring applications. Different algorithms and methodologies have been developed for each level of the damage identification process, including the management of historical information on the functioning of the structure, and they often use different sensors and actuators, materials, and configurations.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
