Matching Strain Signals to Structural Operational Conditions by Means of an Improved Genetic Density Based Algorithm
Structural health monitoring SHM is highly relevant nowadays, not only for aerospace maintenance, but also there is a large number of newly applications in which this methodology is involved, like in the civil and mechanical fields for structure operational conservation. Pattern recognition has become an important part of SHM for signal processing and anomalies or damage detection, assuring structural integrity. New methods are created day by day and more researches and engineers feel the interest to generate techniques which can make SHM become a more compacted, sophisticated and automatized system, eliminating human factors and intrinsic errors. This work evaluates a novelty methodology as a part of the SHM in which it is used an unsupervised clustering algorithm based on density DBSCAN, to facilitate the detection and interpretation of structural behaviors, with low computational cost and processing time and fairly accuracy.
Index Terms - Clustering, Pattern Recognition, Shm, Unsupervised Learning And Structural Evaluation.