identifying damage location under statistical pattern recognition by new feature extraction and feature analysis methods

The main objective of this article is to identify the location of damage by a newfeature extraction technique and to propose some efficient feature analysis tools as statisticaldistance measures. the proposed algorithm of feature extraction relies on a combinationof the well-known principal component analysis (pca) and convolution strategy. afterextracting the features from raw vibration signals of undamaged and damaged conditions,those are applied to the proposed feature analysis approaches called coecient of variation,fisher criterion, fano factor, and relative reliability index, all of which are formulated byusing statistical moments of the features extracted from the pca-convolution algorithm.to localize damage, the sensor location with the distance value exceeding a certain thresholdlimit is identied as the damaged area. the main innovations of this research are to presenta new hybrid technique of feature extraction suitable for structural health monitoring(shm) applications and four effective statistical measures for feature analysis and damageidentication. the performance and reliability of the proposed methods are veried bya four-story shear-building model and a benchmark concrete beam. results demonstratethat the approaches presented here can substantially identify the location of damage usingthe features extracted from the proposed pca-convolution algorithm.