Physics-based modelling and simulation of reverberating reflections in ultrasonic guided wave inspections applied to welded rail tracks

Ramatlo, Dineo A.; Long, Craig S.; Loveday, Philip W.; Wilke, Daniel N.

doi:10.1016/j.jsv.2022.116914

Cited by 20 publications

(14 citation statements)

References 37 publications

(86 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, in addition to the crack reflection at 108.5 m in Figure 9(b), we further notice another reflection reconstructed by the VAE at approximately 273 m. This double reflection is the result of reverberation between the crack and weld B, which the VAE can predict. This result highlights the importance of accounting for multiple reflections by using the physics-based modelling procedure in the study by Ramatlo et al 15 to simulate the training and testing data.…”

Section: Vae Reconstructionmentioning

confidence: 71%

“…The amplitude of the damage decreases with an increasing distance, implying that attenuation in the rail was well captured. The attenuation model employed was validated in the study by Ramatlo et al 15 In the next section, we demonstrate how a VAE can be used to reconstruct virtual experimental signals containing damage by fusing the baseline signal in Figure 4(c) with damage reflections at user-specified distances.…”

Section: Transverse Damage In the Head Of The Railmentioning

confidence: 99%

“…A schematic representation of the field layout of the section of rail considered is illustrated in Figure 2 and the measurement details are provided in the study by Loveday et al 3 The virtual experimental responses for training the VAE were simulated using a digital model replicating the experimental field scenario in Figure 2. This digital model is a physics-based framework presented and validated in the study by Ramatlo et al 15 The digital model for the set-up considered in this paper is illustrated in Figure 3(a). For completeness, the model will be briefly explained, but the reader is referred to the studies by Ramatlo et al 11,15 for additional details.…”

Section: Simulated Virtual Experimental Baseline Signal For a Damage-...mentioning

confidence: 99%

“…They are finally converted to the distance domain by applying an inverse Fourier Transform followed by a dispersion compensation procedure. 28 Details of the coupling procedure and computation of response signals can be found in the studies by Ramatlo et al 15 and Baronian et al 27 Figure 4 shows a spectrogram of the simulated virtual experimental response and the equivalent distance domain signals. The response was validated using the measured experimental response in the study by Ramatlo et al 11 The spectrogram shows that the simulated experiment contains many propagation modes that are reflected from each weld.…”

Section: Simulated Virtual Experimental Baseline Signal For a Damage-...mentioning

confidence: 99%

“…The modelling framework is continuously enhanced as the aim is to attain a digital model that can capture the complexities in an operational system. In reference, 15 the digital model was improved to account for multiple reflections, which are most common when working in the web section of the rail. The digital model was validated using a field experiment from an operational railway line.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A data-driven hybrid approach to generate synthetic data for unavailable damage scenarios in welded rails for ultrasonic guided wave monitoring

Ramatlo,

Wilke,

Loveday

2023

Structural Health Monitoring

View full text Add to dashboard Cite

Developing reliable ultrasonic-guided wave monitoring systems requires a significant amount of inspection data for each application scenario. Experimental investigations are fundamental but require a long period and are costly, especially for real-life testing. This is exacerbated by a lack of experimental data that includes damage. In some guided wave applications, such as pipelines, it is possible to introduce artificial damage and perform lab experiments on the test structure. However, in rail track applications, laboratory experiments are either not possible or meaningful. The generation of synthetic data using modelling capabilities thus becomes increasingly important. This paper presents a variational autoencoder (VAE)-based deep learning approach for generating synthetic ultrasonic inspection data for welded railway tracks. The primary aim is to use a VAE model to generate synthetic data containing damage signatures at specified positions along the length of a rail track. The VAE is trained to encode an input damage-free baseline signal and decode to reconstruct an inspection signal with damage by adding a damage signature on either side of the transducer by specifying the distance to the damage signature as an additional variable in the latent space. The training data was produced from a physics-based model that computes virtual experimental response signals using the semi-analytical finite element and the traditional finite element procedures. The VAE reconstructed response signals containing damage signatures were almost identical to the original target signals simulated using the physics-based model. The VAE was able to capture the complex features in the signals resulting from the interaction of multiple propagating modes in a multi-discontinuous waveguide. The VAE model successfully generated synthetic inspection data by fusing reflections from welds with the reflection from a crack model at specified distances from the transducer on either the right or left side. In some cases, the VAE did not exactly reconstruct the peak amplitude of the reflections. This study demonstrated the potential and highlighted the benefit of using a VAE to generate synthetic data with damage signatures as opposed to using superposition to fuse the damage-free responses containing reflections from welds with a damage signature. The results show that it is possible to generate realistic inspection data for unavailable damage scenarios.

show abstract

Section: Vae Reconstructionmentioning

confidence: 71%

Section: Transverse Damage In the Head Of The Railmentioning

confidence: 99%