A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Damage localization using pattern recognition techniques and statistical dissimilarity analysis
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. ; Postprint (published version)
Damage localization using pattern recognition techniques and statistical dissimilarity analysis
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. ; Postprint (published version)
Damage localization using pattern recognition techniques and statistical dissimilarity analysis
Rodríguez Lozada, Harold S. (author) / Tibaduiza Burgos, Diego Alexander (author) / Pozo Montero, Francesc (author) / Leon Medina, Jersson Xavier (author) / Universitat Politècnica de Catalunya. Departament de Matemàtiques / Universitat Politècnica de Catalunya. CoDAlab - Control, Modelització, Identificació i Aplicacions
2019-01-01
Conference paper
Electronic Resource
English
Àrees temàtiques de la UPC::Enginyeria civil::Materials i estructures::Càlcul d'estructures , Àrees temàtiques de la UPC::Enginyeria dels materials::Desgast de materials , Structural failures , Strength of materials , Structural control (Engineering) , Reconeixement de formes (Informàtica) , Resistència estructural , Resistència de materials , Control d'estructures (Enginyeria)
Application of Pattern Recognition to Damage Localization
| Online Contents | 1996
Classification of Damage using Time Series Analysis and Statistical Pattern Recognition
| British Library Conference Proceedings | 2008
Health Monitoring of Structures Using Statistical Pattern Recognition Techniques
| Online Contents | 2013
Health Monitoring of Structures Using Statistical Pattern Recognition Techniques
| British Library Online Contents | 2013