Neural Network Based Inverse Analysis for Defect Identification with Laser Ultrasonics

Yoshimura, Shinobu; Yagawa, Genki; Oishi, Atsuya; Yamada, Kazumasa

doi:10.4028/www.scientific.net/kem.145-149.443

Cited by 14 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Laser. Non-contact excitation of Lamb waves via laserbased ultrasonics (LBU) and acquisition using a laser interferometer has recently appeared as a promising method for contactless NDI [21,[24][25][26][27]. Flexibly controllable, the LBU can be designed to be broadband or narrow-band, depending on the application, providing excellent spatial resolution.…”

Section: Generation Of Lamb Wavesmentioning

confidence: 99%

See 1 more Smart Citation

Selective generation of Lamb wave modes and their propagation characteristics in defective composite laminates

2004

Proceedings of the Institution of Mechanical Engineers, Part L:

View full text Add to dashboard Cite

Techniques for the generation of Lamb waves with purpose of non-destructive inspection (NDI) were brie y reviewed. An active excitation control circuit was designed and instrumented with an online damage diagnosis system, by which the desired fundamental symmetric Lamb mode, shear mode and antisymmetric mode can be selectively stimulated. A signal processing and identi cation algorithm in the timescale domain, using spectrographic analyses based on the wavelet transform technique, was developed to assist the wave signal interpretation. The proposed excitation methodology was applied to the study of the dispersion and propagation characteristics of Lamb waves in quasi-isotropic CF/EP composite laminates with delamination. For validation, numerical simulations were conducted in parallel with experimental investigations.

show abstract

Section: Generation Of Lamb Wavesmentioning

confidence: 99%

“…Compared with the laminate, the PZT sensor is geometrically small (e r 0 º e y 0 º e cen , where e cen is the strain at the centre of the PZT disc), and equation ( 23) can accordingly be simpli ed as [41] V otpˆG Ge cen (24) wherẽ…”

Section: Sensor Modelmentioning

confidence: 99%

Selective generation of Lamb wave modes and their propagation characteristics in defective composite laminates

2004

Proceedings of the Institution of Mechanical Engineers, Part L:

View full text Add to dashboard Cite

show abstract

“…(e r 0 ‡ e y 0 )r 0 dr 0 dy 0 (23) Compared with the laminate, the PZT sensor is geometrically small (e r 0 º e y 0 º e cen , where e cen is the strain at the centre of the PZT disc), and equation (23) can accordingly be simpli ed as [41] V otpˆG Ge cen (24) wherẽ…”

Section: Sensor Modelmentioning

confidence: 99%

Selective generation of Lamb wave modes and their propagation characteristics in defective composite laminates

2004

Proc. Instn Mech. Engrs, Part L: J. Mat

View full text Add to dashboard Cite

show abstract

“…Worden et al, Nakamura et al, Chen et al and Yoshimura et al employed an ANN-based nonparametric approach for the detection of changes in the characteristics of unknown structure systems. [13][14][15][16] A study by Masri et al 17 demonstrated that ANNs are powerful tools for the identification of nonlinear systems typically encountered in the structural dynamics field. Kosmatopoulos et al 18 employed ANNs to realize online tracking of nonlinear restoring forces in nonlinear structures.…”

Section: Introductionmentioning

confidence: 99%

Damage detection for a frame structure model using vibration displacement measurement

Song

Masri

2012

Structural Health Monitoring

View full text Add to dashboard Cite

A structural parameter identification and damage detection approach using displacement measurement time series is proposed, and the performance of the approach is validated experimentally with a frame structure model in a healthy condition and with joint connection damages. The dynamic displacement response of the frame structure under base excitation is measured by noncontact laser displacement sensors. The proposed approach is carried out using two neural networks: one is called displacement-based neural network emulator (DNNE) and the other is called parametric evaluation neural network (PENN). First, the theoretical basis and the selection of the input and output of the DNNE and the PENN are explained, and second, an identification index called root mean square (RMS) of prediction displacement difference vector (RMSPDDV) is defined. The performance of the proposed methodology for damage detection of the frame structure model with different joint damage scenarios introduced by loosening the bolts connecting the beams and columns is investigated with the direct use of displacement measurement under base excitations. The results from the proposed time domain displacement-based identification approach are compared with them based on the extracted frequencies and show that the proposed time domain methodology can identify the variation of interstory stiffness due to the joint damage with acceptable accuracy without any modal shapes and frequencies extracted from a dynamic test. The proposed approach provides an alternative way for damage detection of engineering structures by the direct use of structural dynamic displacement measurements.

show abstract

Neural Network Based Inverse Analysis for Defect Identification with Laser Ultrasonics

Cited by 14 publications

References 0 publications

Selective generation of Lamb wave modes and their propagation characteristics in defective composite laminates

Selective generation of Lamb wave modes and their propagation characteristics in defective composite laminates

Selective generation of Lamb wave modes and their propagation characteristics in defective composite laminates

Damage detection for a frame structure model using vibration displacement measurement

Contact Info

Product

Resources

About