TY - JOUR
T1 - Self-powered piezo-floating-gate sensors for health monitoring of steel plates
AU - Hasni, Hassene
AU - Alavi, Amir H.
AU - Lajnef, Nizar
AU - Abdelbarr, Mohamed
AU - Masri, Sami F.
AU - Chakrabartty, Shantanu
N1 - Funding Information:
The presented work is supported by a research grant from the Federal Highway Administration (FHWA) (DTFH61-13-C-00015).
Publisher Copyright:
© 2017 Elsevier Ltd
PY - 2017/10/1
Y1 - 2017/10/1
N2 - This paper presents a new method for structural health monitoring using self-powered piezo-floating-gate (PFG) sensors with variable injection rates. An experimental study was performed on an A36 thin steel plate subjected to an in-plane tension mode to verify the proposed method. Different piezoelectric transducers were mounted on the plate for both empowering the sensor and monitoring the damage progression. The changes of charge on the floating-gates of the sensor due to electron injection were considered as damage indicator parameters. In order to improve the damage detection accuracy, several features were extracted from the cumulative voltage droppage for each memory gate, based on sensor group concept. The obtained features were then fed into a support vector machine (SVM) classifier to identify multiple damage states. An optimization process was developed to optimize the parameters of the classifier in order to increase the detection rate accuracy. Based on the results, the performance of the proposed method is satisfactory for detecting damage progression in steel plates.
AB - This paper presents a new method for structural health monitoring using self-powered piezo-floating-gate (PFG) sensors with variable injection rates. An experimental study was performed on an A36 thin steel plate subjected to an in-plane tension mode to verify the proposed method. Different piezoelectric transducers were mounted on the plate for both empowering the sensor and monitoring the damage progression. The changes of charge on the floating-gates of the sensor due to electron injection were considered as damage indicator parameters. In order to improve the damage detection accuracy, several features were extracted from the cumulative voltage droppage for each memory gate, based on sensor group concept. The obtained features were then fed into a support vector machine (SVM) classifier to identify multiple damage states. An optimization process was developed to optimize the parameters of the classifier in order to increase the detection rate accuracy. Based on the results, the performance of the proposed method is satisfactory for detecting damage progression in steel plates.
KW - Damage detection
KW - Piezo-floating-gate
KW - Self-powered wireless sensor
KW - Steel plates
KW - Structural health monitoring
KW - Support vector machine
UR - http://www.scopus.com/inward/record.url?scp=85023192514&partnerID=8YFLogxK
U2 - 10.1016/j.engstruct.2017.06.063
DO - 10.1016/j.engstruct.2017.06.063
M3 - Article
AN - SCOPUS:85023192514
SN - 0141-0296
VL - 148
SP - 584
EP - 601
JO - Engineering Structures
JF - Engineering Structures
ER -