scholarly journals A New Structural Health Monitoring Strategy Based on PZT Sensors and Convolutional Neural Network

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 2955 ◽  
Author(s):  
Mario de Oliveira ◽  
Andre Monteiro ◽  
Jozue Vieira Filho
Keyword(s):  
Neural Network ◽  
Structural Health Monitoring ◽  
Convolutional Neural Network ◽  
Lead Zirconate Titanate ◽  
Health Monitoring ◽  
Lead Zirconate ◽  
Industrial Applications ◽  
Electromechanical Impedance ◽  
Structural Health

Preliminaries convolutional neural network (CNN) applications have recently emerged in structural health monitoring (SHM) systems focusing mostly on vibration analysis. However, the SHM literature shows clearly that there is a lack of application regarding the combination of PZT-(lead zirconate titanate) based method and CNN. Likewise, applications using CNN along with the electromechanical impedance (EMI) technique applied to SHM systems are rare. To encourage this combination, an innovative SHM solution through the combination of the EMI-PZT and CNN is presented here. To accomplish this, the EMI signature is split into several parts followed by computing the Euclidean distances among them to form a RGB (red, green and blue) frame. As a result, we introduce a dataset formed from the EMI-PZT signals of 720 frames, encompassing a total of four types of structural conditions for each PZT. In a case study, the CNN-based method was experimentally evaluated using three PZTs glued onto an aluminum plate. The results reveal an effective pattern classification; yielding a 100% hit rate which outperforms other SHM approaches. Furthermore, the method needs only a small dataset for training the CNN, providing several advantages for industrial applications.

scholarly journals A New Structural Health Monitoring Strategy Based on PZT Sensors and Convolutional Neural Network

2018 ◽  
Author(s):  
Mario A. de Oliveira ◽  
Andre V. Monteiro ◽  
Jozue Vieira Filho
Keyword(s):  
Neural Network ◽  
Structural Health Monitoring ◽  
Convolutional Neural Network ◽  
Lead Zirconate Titanate ◽  
Health Monitoring ◽  
Lead Zirconate ◽  
Industrial Applications ◽  
Electromechanical Impedance ◽  
Structural Health

Preliminaries Convolutional Neural Network (CNN) applications have recently emerged in Structural Health Monitoring (SHM) systems focusing mostly on vibration analysis. However, the SHM literature shows clearly that there is a lack of application regarding the combination of PZT (Lead Zirconate Titanate) based method and CNN. Likewise, applications using CNN along with the Electromechanical Impedance (EMI) technique applied to SHM systems are rare. To encourage this combination, an innovative SHM solution through the combination of the EMI-PZT and CNN is presented here. To accomplish this, the EMI signature is split into several parts followed by computing the Euclidean distances among them to form a RGB (red, green and blue) frame. As a result, we introduce a dataset formed from the EMI-PZT signals of 720 frames, encompassing a total of 4 types of structural conditions for each PZT. In a case study, the CNN-based method was experimentally evaluated using three PZTs glued onto an aluminum plate. The results reveal an effective pattern classification; yielding a 100% hit rate which outperforms other SHM approaches. Furthermore, the method needs only a small dataset for training the CNN, providing several advantages for industrial applications.

Reusable piezoelectric transducer for structural health monitoring using both Lamb wave and electromechanical impedance modes

2020 ◽  
Vol 31 (16) ◽  
pp. 1898-1909
Author(s):  
Qijian Liu ◽  
Yuan Chai ◽  
Xinlin Qing
Keyword(s):  
Structural Health Monitoring ◽  
Lead Zirconate Titanate ◽  
Health Monitoring ◽  
Lamb Wave ◽  
Lead Zirconate ◽  
Aluminum Plate ◽  
Electromechanical Impedance ◽  
Structural Health ◽  
Zirconate Titanate ◽  
Piezoelectric Lead Zirconate Titanate

A variety of structural health monitoring techniques have been developed to support the efficient online monitoring of structural integrity. Moreover, Lamb wave and electromechanical impedance methods are increasingly used for structural health monitoring applications due to their high sensitivity and effectiveness in detecting damage. However, these techniques require transducers to be permanently attached to structures because of the usage of baselines recorded under the condition without damage. In this study, a reusable piezoelectric lead zirconate titanate transducer for monitoring corrosion damage on the aluminum plate is introduced, which can be removed from the test specimen and reused with the repeatability of signals. The reusable piezoelectric lead zirconate titanate transducer is bonded on the aluminum plate using the ethylene-acrylic acid copolymer with an aluminum enclosure. A series of experiments are conducted on an aluminum plate, including the investigation for repeatability of signals and the capability of corrosion detection of the designed piezoelectric lead zirconate titanate transducer through the Lamb wave and electromechanical impedance methods. The simulated corrosion defect with the area of 15 × 15 mm2 is detected during experiments. The experimental results confirm that the reusable piezoelectric lead zirconate titanate transducer can effectively evaluate the corrosion damage to plate structure and can be reused many times.

scholarly journals Guided Wave-Convolutional Neural Network Based Fatigue Crack Diagnosis of Aircraft Structures

Sensors ◽  
2019 ◽  
Vol 19 (16) ◽  
pp. 3567 ◽  
Author(s):  
Xu ◽  
Yuan ◽  
Chen ◽  
Ren
Keyword(s):  
Neural Network ◽  
Fatigue Crack ◽  
Structural Health Monitoring ◽  
Convolutional Neural Network ◽  
Health Monitoring ◽  
Guided Wave ◽  
Engineering Applications ◽  
Monitoring Method ◽  
Structural Health ◽  
High Level

Fatigue crack diagnosis (FCD) is of great significance for ensuring safe operation, prolonging service time and reducing maintenance cost in aircrafts and many other safety-critical systems. As a promising method, the guided wave (GW)-based structural health monitoring method has been widely investigated for FCD. However, reliable FCD still meets challenges, because uncertainties in real engineering applications usually cause serious change both to the crack propagation itself and GW monitoring signals. As one of deep learning methods, convolutional neural network (CNN) owns the ability of fusing a large amount of data, extracting high-level feature expressions related to classification, which provides a potential new technology to be applied in the GW-structural health monitoring method for crack evaluation. To address the influence of dispersion on reliable FCD, in this paper, a GW-CNN based FCD method is proposed. In this method, multiple damage indexes (DIs) from multiple GW exciting-acquisition channels are extracted. A CNN is designed and trained to further extract high-level features from the multiple DIs and implement feature fusion for crack evaluation. Fatigue tests on a typical kind of aircraft structure are performed to validate the proposed method. The results show that the proposed method can effectively reduce the influence of uncertainties on FCD, which is promising for real engineering applications.

Monitoring Vibrating Structures Using PZT Impedance Transducers

2008 ◽  
Vol 47-50 ◽  
pp. 85-88
Author(s):  
Ai Wei Miao ◽  
Yao Wen Yang
Keyword(s):  
Experimental Study ◽  
Lead Zirconate Titanate ◽  
Health Monitoring ◽  
Lead Zirconate ◽  
Frequency Range ◽  
External Excitation ◽  
Real Situation ◽  
Electromechanical Impedance ◽  
Structural Health ◽  
Vibrating Structures

Electromechanical impedance (EMI) technique using lead zirconate titanate (PZT) transducers has been increasingly applied to structural health monitoring (SHM) of aerospace, civil and mechanical structures. The PZT transducers are usually surface bonded to or embedded in a structure and subjected to actuation so as to interrogate the structure at the desired frequency range. The interrogation results in the electromechanical admittance (inverse of EMI) signatures which can be used to estimate the structural health or integrity according to the changes of the signatures. In the existing EMI method, the monitored structure is only excited by the PZT transducers for the interrogating of EMI signature, while the vibration of the structure caused by the external excitations other than the PZT actuation is not considered. However, in real situation many structures work under vibrations. To monitor such structures, issues related to the effects of vibration on the EMI signature need to be addressed because these effects may lead to misinterpretation of the structural health. This paper develops an EMI model for beam structures, which takes into account the effect of beam vibration caused by the external excitations. An experimental study is carried out to verify the theoretical model. A Lab sized specimen with external excitation is tested and the effect of excitation on EMI signature is discussed.

scholarly journals Evaluation of the Influence of Sensor Geometry and Physical Parameters on Impedance-Based Structural Health Monitoring

2012 ◽  
Vol 19 (5) ◽  
pp. 811-823 ◽  
Author(s):  
L.V. Palomino ◽  
K.M. Tsuruta ◽  
J.R.V. Mour Jr ◽  
D.A. Radea ◽  
V. Steffen Jr. ◽  
...  
Keyword(s):  
Structural Health Monitoring ◽  
Lead Zirconate Titanate ◽  
Health Monitoring ◽  
Residual Life ◽  
Environmental Influences ◽  
Mechanical Impedance ◽  
Physical Parameters ◽  
Present Contribution ◽  
Electromechanical Impedance ◽  
Structural Health

Structural Health Monitoring (SHM) is the process of damage identification in mechanical structures that encompasses four main phases: damage detection, damage localization, damage extent evaluation and prognosis of residual life. Among various existing SHM techniques, the one based on electromechanical impedance measurements has been considered as one of the most effective, especially in the identification of incipient damage. This method measures the variation of the electromechanical impedance of the structure as caused by the presence of damage by using piezoelectric transducers bonded on the surface of the structure (or embedded into it). The most commonly used smart material in the context of the present contribution is the lead zirconate titanate (PZT). Through these piezoceramic sensor-actuators, the electromechanical impedance, which is directly related to the mechanical impedance of the structure, is obtained as a frequency domain dynamic response. Based on the variation of the impedance signals, the presence of damage can be detected. A particular damage metric can be used to quantify the damage. For the success of the monitoring procedure, the measurement system should be robust enough with respect to environmental influences from different sources, in such a way that correct and reliable decisions can be made based on the measurements. The environmental influences become more critical under certain circumstances, especially in aerospace applications, in which extreme conditions are frequently encountered. In this paper, the influence of electromagnetic radiation, temperature and pressure variations, and ionic environment have been examined in laboratory. In this context, the major concern is to determine if the impedance responses are affected by these influences. In addition, the sensitivity of the method with respect to the shape of the PZT patches is evaluated. Conclusions are drawn regarding the monitoring efficiency, stability and precision.

scholarly journals Deep residual network framework for structural health monitoring

2020 ◽  
pp. 147592172091837 ◽  
Author(s):  
Ruhua Wang ◽  
Chencho ◽  
Senjian An ◽  
Jun Li ◽  
Ling Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Structural Health Monitoring ◽  
Convolutional Neural Network ◽  
Health Monitoring ◽  
Damage Identification ◽  
State Of The Art ◽  
Experimental Studies ◽  
The State ◽  
Residual Network ◽  
Structural Health

Convolutional neural networks have been widely employed for structural health monitoring and damage identification. The convolutional neural network is currently considered as the state-of-the-art method for structural damage identification due to its capabilities of efficient and robust feature learning in a hierarchical manner. It is a tendency to develop a convolutional neural network with a deeper architecture to gain a better performance. However, when the depth of the network increases to a certain level, the performance will degrade due to the gradient vanishing issue. Residual neural networks can avoid the problem of vanishing gradients by utilizing skip connections, which allows the information flowing to the next layer through identity mappings. In this article, a deep residual network framework is proposed for structural health monitoring of civil engineering structures. This framework is composed of purely residual blocks which operate as feature extractors and a fully connected layer as a regressor. It learns the damage-related features from the vibration characteristics such as mode shapes and maps them into the damage index labels, for example, stiffness reductions of structures. To evaluate the efficacy and robustness of the proposed framework, an intensive evaluation is conducted with both numerical and experimental studies. The comparison between the proposed approach and the state-of-the-art models, including a sparse autoencoder neural network, a shallow convolutional neural network and a convolutional neural network with the same structure but without skip connections, is conducted. In the numerical studies, a 7-storey steel frame is investigated. Four scenarios with considering measurement noise and finite element modelling errors in the data sets are studied. The proposed framework consistently outperforms the state-of-the-art models in all the scenarios, especially for the most challenging scenario, which includes both measurement noise and uncertainties. Experimental studies on a prestressed concrete bridge in the laboratory are conducted. The proposed framework demonstrates consistent damage prediction results on this beam with the state-of-the-art models.

Sign in / Sign up

Export Citation Format

Share Document