A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Damage classification in structural health monitoring using principal component analysis and self‐organizing maps
Damage classification is an important issue within SHM going beyond the purely damage detection. This paper proposes a data‐driven statistical approach for damage classification, which is constructed over a distributed piezoelectric active sensor network for excitation and measurement of vibrational structural responses. At different phases, a single piezoelectric transducer is used as actuator, and the others are used as sensors. An initial baseline model for each phase for the healthy structure is built by applying PCA to the data collected in several experiments. In addition, same experiments are performed with the structure in different states (damaged or not), and the dynamic responses are projected into the different baseline PCA models for each actuator. Some of these projections and damage indices are used as input features for a self‐organizing map, which is properly trained and validated to build a pattern baseline model. This baseline is further used as a reference for blind diagnosis tests of structures. Both training/validation and diagnosis modes are experimentally assessed using an aluminum plate instrumented with four piezoelectric transducers. Damages are simulated by adding mass at different positions. Results show that all these damages are successfully classified both in the baseline pattern model and in further diagnosis tests. Copyright © 2012 John Wiley & Sons, Ltd.
Damage classification in structural health monitoring using principal component analysis and self‐organizing maps
Damage classification is an important issue within SHM going beyond the purely damage detection. This paper proposes a data‐driven statistical approach for damage classification, which is constructed over a distributed piezoelectric active sensor network for excitation and measurement of vibrational structural responses. At different phases, a single piezoelectric transducer is used as actuator, and the others are used as sensors. An initial baseline model for each phase for the healthy structure is built by applying PCA to the data collected in several experiments. In addition, same experiments are performed with the structure in different states (damaged or not), and the dynamic responses are projected into the different baseline PCA models for each actuator. Some of these projections and damage indices are used as input features for a self‐organizing map, which is properly trained and validated to build a pattern baseline model. This baseline is further used as a reference for blind diagnosis tests of structures. Both training/validation and diagnosis modes are experimentally assessed using an aluminum plate instrumented with four piezoelectric transducers. Damages are simulated by adding mass at different positions. Results show that all these damages are successfully classified both in the baseline pattern model and in further diagnosis tests. Copyright © 2012 John Wiley & Sons, Ltd.
Damage classification in structural health monitoring using principal component analysis and self‐organizing maps
Tibaduiza, D. A. (author) / Mujica, L. E. (author) / Rodellar, J. (author)
Structural Control and Health Monitoring ; 20 ; 1303-1316
2013-10-01
14 pages
Article (Journal)
Electronic Resource
English
Applications of Self-Organizing Maps in Structural Health Monitoring
| British Library Online Contents | 2012
An Enhanced Principal Component Analysis for Structural Health Monitoring
| British Library Conference Proceedings | 2006
Structural damage assessment using principal component analysis [5394-54]
| British Library Conference Proceedings | 2004
Structural damage assessment using principal component analysis [5394-54]
| British Library Conference Proceedings | 2004
Deep learning enhanced principal component analysis for structural health monitoring
| BASE | 2022