Damage localization in structures. A pattern recognition perspective
نویسنده
چکیده
The problem for damage detection and localization in structures is studied using an artificial intelligence approach. The structure is divided into sub-structures. The use of pattern recognition techniques is suggested to find the damaged substructure. The frequency response functions for a certain number of degrees of freedom for a number of frequencies are used to form the features. A mapping between the space, defined by the dynamic response of the structure in the frequency domain, and the space spanned by the features is used to develop a pattern recognition procedure. The pattern vectors and the standard samples defining the different classes are obtained using this mapping. Eventually a computer code (classifier) is built that can answer the question for the damage localization. * On leave from Institute of Mechanics, Bulgarian Academy of Sciences, bl.4 Acad. G. Bontchev str.,1113 Sofia, Bulgaria
منابع مشابه
A New Two-Stage Method for Damage Identification in Linear-Shaped Structures Via Grey System Theory and Optimization Algorithm
The main objective of this paper is concentrated on presenting a new two-stage method for damage localization and quantification in the linear-shaped structures. A linear-shaped structure is defined as a structure in which all elements are arranged only on a straight line. At the first stage, by employing Grey System Theory (GST) and diagonal members of the Generalized Flexibility Matrix (GFM),...
متن کاملArtificial immune pattern recognition for structure damage classification
Damage detection in structures is one of the research topics that have received growing interest in research communities. While a number of damage detection and localization methods have been proposed, very few attempts have been made to explore the structure damage classification problem. This paper presents an Artificial Immune Pattern Recognition (AIPR) approach for the damage classification...
متن کاملInvestigation of Time Series Representations and Similarity Measures for Structural Damage Pattern Recognition
This paper investigates the time series representation methods and similarity measures for sensor data feature extraction and structural damage pattern recognition. Both model-based time series representation and dimensionality reduction methods are studied to compare the effectiveness of feature extraction for damage pattern recognition. The evaluation of feature extraction methods is performe...
متن کاملThe application of statistical pattern recognition methods for damage detection to field data
Recent studies in structural health monitoring have shown that damage detection algorithms based on statistical pattern recognition techniques for ambient vibrations can be used to successfully detect damage in simulated models. However, these algorithms have not been tested on full-scale civil structures, because such data are not readily available. A unique opportunity for examining the effec...
متن کاملLIQUEFACTION POTENTIAL ASSESSMENT USING MULTILAYER ARTIFICIAL NEURAL NETWORK
In this study, a low-cost, rapid and qualitative evaluation procedure is presented using dynamic pattern recognition analysis to assess liquefaction potential which is useful in the planning, zoning, general hazard assessment, and delineation of areas, Dynamic pattern recognition using neural networks is generally considered to be an effective tool for assessing of hazard potential on the b...
متن کامل