PSI - Issue 5

Piotr Nazarko et al. / Procedia Structural Integrity 5 (2017) 460–467 Nazarko and Ziemianski / Structural Integrity Procedia 00 (2017) 000 – 000

467

8

5. Conclusions and final remark

The obtained results of preliminary tests have showed that ANNs are able to find the relation between the changes in signals and force variations. They provided very accurate results (the error less than 2%) when testing and validation patterns were selected with constant distribution. It seems, however, that the principal components do not contain information suitable enough for precise prediction of axial forces in the bolts that were not included into the training patterns database (even in case of the single connection where environmental conditions were the same). The signals measured showed significant differences and therefore, at this stage of the research, the ANNs trained were not able to generalize data and to predict the unknown forces with acceptable accuracy. In the future work the other signal parameters will be studied (ToF, signal amplitudes, wavelet coefficients, etc.) in order to improve the accuracy of the force prediction. The set of training patterns should be also extended with data related to experimental data performed on the wider group of bolts.

Acknowledgments

The studies were performed with the use of equipment purchased in project No. POPW.01.03.00-18-012/09 from the Structural Funds, The Development of Eastern Poland Operational Programme, co-financed by the European Union and the European Regional Development Fund.

References

Chaki, S., Bourse, G., 2009. Guided ultrasonic waves for non-destructive monitoring of the stress levels in prestressed steel strands. Ultrasonics, 49, 162 – 171. Chen, R., Chen, S., Lixia, Y., Wang, J., Xu, X., Luo, T., 2017. Looseness diagnosis method for connecting bolt of fan foundation based on sensitive mixed-domain features of excitation-response and manifold learning. Neurocomputing, 219, 376-388. Ding, X., Wu, X., Wang, Y., 2014. Bolt axial stress measurement based on a mode-converted ultrasound method using an electromagnetic acoustic transducer. Ultrasonics, 54, 914 – 920. Fric, N., Budjevac, D., Miskovic, Z., Veljkovic, M., Markovic, Z., Dobric, J., 2015. Calibration of the high strenght bolts for measuring of the pretension force, Eighth International Conference on Advances in Steel Structures. Lisbon, Portugal, 1 – 10. Kim, N., Hong, M., 2009. Measurement of axial stress using mode-converted ultrasound. NDT&E International, 42, 164 – 169. Nazarko, P., 2013. Soft computing methods in the analysis of elastic wave signals and damage identification. Inverse Problems in Science and Engineering, 21 (6), 945 – 956. Nazarko, P., Ziemiański, L., 2016. Damage detection in aluminum and composite elements using neural networks for Lamb waves signal processing. Engineering Failure Analysis, 69, 97 – 107.