Abstract
Structural health monitoring (SHM) is a very important area in a wide spectrum of fields and engineering applications. With an SHM system, it is possible to reduce the number of non-necessary inspection tasks, the associated risk and the maintenance cost in a wide range of structures during their lifetime. One of the problems in the detection and classification of damage are the constant changes in the operational and environmental conditions. Small changes of these conditions can be considered by the SHM system as damage even though the structure is healthy. Several applications for monitoring of structures have been developed and reported in the literature, and some of them include temperature compensation techniques. In real applications, however, digital processing technologies have proven their value by: (i) offering a very interesting way to acquire information from the structures under test; (ii) applying methodologies to provide a robust analysis; and (iii) performing a damage identification with a practical useful accuracy. This work shows the implementation of an SHM system based on the use of piezoelectric (PZT) sensors for inspecting a structure subjected to temperature changes. The methodology includes the use of multivariate analysis, sensor data fusion and machine learning approaches. The methodology is tested and evaluated with aluminum and composite structures that are subjected to temperature variations. Results show that damage can be detected and classified in all of the cases in spite of the temperature changes.
Highlights
The variability in the dynamic properties of a structure in service can be the result of time-varying environmental and operational conditions [1]
We present a structural health monitoring system based on [23] that is oriented to detect and classify the damage of a structure subjected to temperature variations
One of the most used algorithms in machine learning applications is the k-NN, known as k-nearest neighbors. k-NN stands out due to its simplicity and the excellent results obtained when this technique is applied to diverse problems [35]
Summary
The variability in the dynamic properties of a structure in service can be the result of time-varying environmental and operational conditions [1]. Structural health monitoring strategies that do not consider principal component analysis include, for instance, the work by Deraemaeker et al [12], where the damage detection strategy is uniquely based on vibration measurements under changing environmental conditions. The system works with data collected from a piezoelectric sensor network attached permanently to the structure, and it introduces the use of a new way to organize the data, multivariate data analysis techniques and machine learning analysis Some contributions of this system are the use of sensor data fusion, which introduces a different organization of the data, and the feature extraction vector for including temperature during the training process. This means that in the analysis, there are measurements from all of the sensors distributed all along the structure, which offers a generalized analysis from different points of view by fusing data in the only result This procedure allows reducing the effect of the temperature in the damage detection and classification process when machine learning approaches are applied.
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
