Research of EMI Structural Health Monitoring Based on BP Neural Networks

2012 ◽  
Vol 188 ◽  
pp. 231-235
Author(s):  
Fu Hou Xu ◽  
Dong Dong Wen ◽  
Yu Xiang Zhang ◽  
Hua Cheng Li

Based on the coupling characteristic of piezoelectric ceramics (PZT) and electro-mechanical, impedance changes were measured by the impedance analyzer. Aluminum plate’s impedance response under different load conditions was analyzed with electromechanical impedance technique. BP neural networks were established to identify the structural damage status and the RMSDR was calculated as neural network input data, then the networks was trained and validated. Experiment results show that the trained network can successfully identify the structural load state.

2009 ◽  
Vol 79-82 ◽  
pp. 35-38 ◽  
Author(s):  
Dong Yu Xu ◽  
Xin Cheng ◽  
Shi Feng Huang ◽  
Min Hua Jiang

The structural damage of mortar caused by simulated crack was evaluated using embedded PZT sensor combining with dynamic electromechanical impedance technique. The influence of embedded PZT sensors layout on detecting structural damage induced by the simulated cracks was also investigated. The results indicate that with increasing the simulated crack depth, the impedance real part of PZT sensors shift leftwards accompanying with the appearance of new peaks in the spectra. When more simulated cracks occur, the shift of the impedance curve becomes more obvious, and the amounts of new peaks in the impedance spectra also increase. RMSD indices of the structures with PZT sensors embedded in them with different layout can show the structural incipient damage clearly. With increasing more simulated cracks in the mortar structures, RMSD values of the structures with different PZT sensors layout become larger, under the same depth, RMSD indices of the structures with PZT sensor embedded transversely and horizontally in them show the increasing trend.


2011 ◽  
Vol 243-249 ◽  
pp. 5475-5480
Author(s):  
Zhang Jun

Modals of BP neural networks with different inputs and outputs are presented for different damage detecting schemes. To identify locations of structural damages, the regular vectors of changes in modal flexibility are looked on as inputs of the networks, and the state of localized damage are as outputs. To identify extents of structural damage, parameters combined with changes in flexibility and the square changes in frequency are as inputs of the networks, and the state of damage extents are as outputs. Examples of a simply supported beam and a plate show that the BP neural network modal can detect damage of structures in quantitative terms.


2011 ◽  
Vol 230-232 ◽  
pp. 587-591
Author(s):  
Yu Xiang Zhang ◽  
Dong Dong Wen ◽  
Hua Cheng Li ◽  
Fu Hou Xu

Electromechanical impedance technique which based on smart material is a new method for structural damage detection, and it could be widely applied in structural health monitoring field. However, a very expensive and bulky analyzer is being used to measure the impedance, which is not practical for on-line system. Therefore, this paper developed a device that can measure the electric impedance using small modular electric components and reasonable circuit. Experiments are carried out to test the aluminum beam crack. Results indicate that the device can measure the electric impedance and detect the damage effectively. The proposed method provides a solution to miniaturize the impedance-measuring equipment and reduce the cost of measurement.


Author(s):  
David Hunter ◽  
Andrei Zagrai

Electro-mechanical impedance diagnostic is one of key structural health monitoring approaches in aerospace structures. Considerable number of studies have demonstrated its efficiency in monitoring bolted joints. This investigation focuses on effect of a bolted boundary on the electro-mechanical impedance response of the space structure. Many space vehicles incorporate cylindrical payloads featuring multiple plates connected with threaded rods. Position of nuts on the threaded rods determine layered structure of the payload. Because of the cylindrical configuration of the payload, internal layers are formed by circular plates bolted to the connection rods. The number of connection rods determines the number of bolted boundary conditions around plate’s circumference. In this case, the boundary of the plate is essentially a mix of bolted and free segments and is not associated with a classical boundary condition. It is suggested that this case may be represented by an elastic boundary conditions with boundary stiffnesses depending on torque applied to each bolted joint. Vibrations of a circular plate with indicated complex boundary conditions were studied in this contribution theoretically and experimentally. As a result of numerical studies, a range of stiffnesses was suggested to model the bolted boundary. An analytical expression for the electro-mechanical impedance of a circular plate was presented and was utilized in the calculation of the response of a circular plate with the complex boundary. Structural damage was modeled as deviation of the stiffness associated with the bolted joint. Experimental studies were carried out to validate results of theoretical investigations. Electro-mechanical impedance signatures of the circular plate with an attached piezoelectric active sensor were collected for different sets of boundary conditions representing theoretical scenarios. Effect of the compromised bolted joint on the electro-mechanical impedance response of the whole circular plate was explored and the analysis of changes due to different conditions of the bolted boundary was provided.


2016 ◽  
Vol 28 (7) ◽  
pp. 837-850 ◽  
Author(s):  
Demi Ai ◽  
Hui Luo ◽  
Hongping Zhu

Piezoelectric sensor diagnosis and validity assessment as a prior component of structural health monitoring system are necessary in the practical application of electromechanical impedance technique. This article proposed an innovative sensor self-diagnosis process based on extracting the characterization of the real admittance (inverse of impedance) signature within a high-frequency range, which covered both diagnosis on damaged sensor after its installation and discrimination of sensor and structural damages during structural health monitoring process. Theoretical analysis was derived from the impedance model of piezoelectric-bonding layer-structure dynamic interaction system. Experimental investigations on piezoelectric sensor-bonded steel beam involved with structural damages of mass addition and notch damage were conducted to verify the process. It was found that the real admittance was reliable and critical in sensor diagnosis, and sensor faults of debonding, scratch, and breakage can be identified and differentiated from structural damage. Validity assessment of the diagnosed damaged sensor was addressed through resonant frequency shift method. The results showed that the validity of damaged sensor for structural health monitoring was inordinately depreciated by sensor damage. This article is expected to be useful for structural health monitoring application especially when damaged piezoelectric sensors existed.


Sensor Review ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Quan Zhai ◽  
Jicheng Zhang ◽  
Guofeng Du ◽  
Yulong Rao ◽  
Xiaoyu Liu

Purpose At present, piezoelectric impedance technology has been used in the study of wood damage monitoring. However, little effort has been made in the research on the application of piezoelectric impedance system to monitor the change of wood moisture content (MC). The monitoring method of wood MC is used by piezoelectric impedance technique in this study. Design/methodology/approach One piezoceramic transducer is bonded to the surface of wood specimens. The MC of the wood specimens increases gradually from 0% to 60% with 10% increments; the mechanical impedance of the wood specimen will change, and the change in the mechanical impedance of the structure is reflected by monitoring the change in the electrical impedance of lead zirconate titanate. Therefore, this paper investigates the relationship between wood MC change and piezoelectric impedance change to verify the feasibility of the piezoelectric impedance method for monitoring wood MC change. Findings The experiment verified that the real part of impedance of the wood increased with the increase of wood MC. Besides, the damage index root mean square deviation is introduced to quantify the damage degree of wood under different MC. At the same time, the feasibility and validity of this experiment were verified from the side by finite element simulation. Finally, MC monitoring by piezoelectric impedance technique is feasible. Originality/value To the best of the authors’ knowledge, this work is the first to apply piezoelectric ceramics to the monitoring of wood MC, which provides a theoretical basis for the follow-up study of a wide range of wood components and even wood structure MC changes.


Materials ◽  
2021 ◽  
Vol 14 (23) ◽  
pp. 7168
Author(s):  
Liaqat Ali ◽  
Sikandar Khan ◽  
Naveed Iqbal ◽  
Salem Bashmal ◽  
Hamad Hameed ◽  
...  

Many methods have been used in the past two decades to detect crack damage in steel joints of the offshore structures, but the electromechanical impedance (EMI) method is a comparatively recent non-destructive method that can be used for quality monitoring of the weld in structural steel joints. The EMI method ensures the direct assessment, analysis and particularly the recognition of structural dynamics by acquiring its EM admittance signatures. This research paper first briefly introduces the theoretical background of the EMI method, followed by carrying out the experimental work in which damage in the form of a crack is simulated by using an impedance analyser at different distances. The EMI technique is used to identify the existence of damage in the welded steel joints of offshore steel jacket structures, and Q345B steel was chosen as the material for test in the present study. Sub-millimetre cracks were found in four typical welded steel joints on the jacket platform under circulating loads, and root average variance was used to assess the extent of the crack damage.


Sign in / Sign up

Export Citation Format

Share Document