Damage localization using pattern recognition techniques and statistical dissimilarity analysis
Document typeConference report
Rights accessOpen Access
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain
The increasing expansion of standards and regulations aimed to guarantee the safe operation of different types of structures and materials ---which are extensively used in buildings, airplanes, transformers, machinery, etc.--- has driven the development and implementation of systems intended to supervise the state of the structure so critical failures may be predicted and avoided. Nevertheless many of those systems are expensive and require the structure to be inactive in order to evaluate its state, so it is frequently necessary to use external equipment and specialized technician teams, producing therefore a high interest in many sectors of industry, military and academic fields on supporting structural health monitoring (SHM) projects to develop new alternative systems. Among the proposals, the ones that includes integrated sensor networks systems are becoming increasingly popular due to their potential to perform the structure health evaluation even during these equipment are still in use, which results in a significant reduction in the economical and productive impact that other systems cause and the possibility to introduce new evaluation techniques that exploit the sensor and programming flexibility. This paper introduces a SHM system aimed to locate damages on metallic and composite material structures. For this purpose, a methodology is applied in this work that combines statistical analysis of dissimilarity with pattern recognition on the data recollected from the piezoelectric sensors network distributed on the structure surface. This methodology is tested in an aluminum plate instrumented with eight piezoelectric sensors and some masses added to the structure in order to emulate changes in the structure due to a damage. Results shows that it is possible to locate all damages.
CitationRodríguez, H. [et al.]. Damage localization using pattern recognition techniques and statistical dissimilarity analysis. A: International Workshop on Structural Health Monitoring. "Structural Health Monitoring 2019. Enabling intelligent life-cycle health management for industry internet of things (IIOT)". Destech, 2019, p. 1-9.