Abstract
Damage detection, using vibrational properties, such as eigenfrequencies, is an efficient and straightforward method for detecting damage in structures, components, and machines. The method, however, is very inefficient when the values of the natural frequencies of damaged and undamaged specimens exhibit slight differences. This is particularly the case with lightweight structures, such as fiber-reinforced composites. The nonlinear support vector machine (SVM) provides enhanced results under such conditions by transforming the original features into a new space or applying a kernel trick. In this work, the natural frequencies of damaged and undamaged components are used for classification, employing the nonlinear SVM. The proposed methodology assumes that the frequencies are identified sequentially from an experimental modal analysis; for the study propose, however, the training data are generated from the FEM simulations for damaged and undamaged samples. It is shown that nonlinear SVM using kernel function yields in a clear classification boundary between damaged and undamaged specimens, even for minor variations in natural frequencies.
Highlights
Reliable detecting of internal damages in composites is still a challenging issue for many applications, such as aerospace, automotive, and other fields
The methods developed based on the structural dynamics provide more reliable results because the dynamic characteristics of composite structures and components change, due to damage that occurs during the manufacturing process or operating conditions [2]
This is more critical for fiber-reinforced composite structures as they exhibit complicated structural components that are subject to invisible delamination [3]
Summary
Reliable detecting of internal damages in composites is still a challenging issue for many applications, such as aerospace, automotive, and other fields. Damage detection is performed by extracting vibration characteristics from the response spectrum and applying a pattern recognition method that compares current characteristics with the (undamaged) reference condition Comparing vibrational parameters such as eigenfrequencies is very efficient and straightforward, owing the fact that delamination is detected at a specific vibration mode or in many modes [5,6]. One has to identify higher mode frequencies in order to detect delamination associated to the local variation in the structure This makes detecting damaged and undamaged samples very costly and difficult. The classical linear SVM leads in a not clear margin for detecting damaged and undamaged samples, owing the fact that the training data may not be linearly separable. The nonlinear SVM using kernel function yields in a clear classification boundary between damaged and undamaged specimens, even for minor variations in natural frequencies, as demonstrated in this paper. The conclusion is given in the last section of the paper
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.
