PSI - Issue 5

Piotr Nazarko et al. / Procedia Structural Integrity 5 (2017) 131–138 P.Nazarko et al./ Structural Integrity Procedia 00 (2017) 000 – 000

138

8

distribution into two classes (damaged/undamaged) could be performed based on the data projection of the first two principal components. However, in the classification task the NI was used and its values allowed the separation of classes through the application of appropriate threshold levels. Unfortunately, on this basis it was not possible to separate all the individual cases of severe damages. Usually this task may be solved using other types of NNs (SVM for classification, NN for regression). The experiments carried out on composite specimens with defects of various origin have proved that damage detection and evaluation are possible by using the proposed diagnostic system. Examples of preliminary fault detection results showed that any signal anomalies are detected perfectly, whereas the prediction of damage level enabled distinguishing the defects. This work provides insight into the potential use of soft computing methods for damage detection and evaluation in SHM system. Moreover, the system proposed is able to perform automatic analysis of the elastic waves and to accelerate the process of structures diagnosis. Although the creation of an appropriate patterns database associated with damage located at different positions is very labor-intensive, a further work may take into account the prediction of fault location on the basis of calculated values of NI. They may be helpful here imaging methods, such as probability density index (PDI). Acknowledgements Financial support of Structural Funds in the Operational Programme - Innovative Economy (IE OP) financed from the European Regional Development Fund - Project ''Modern material technologies in aerospace industry'', no. POIG.01.01.02-00-015/08-00 is gratefully acknowledged. References Hernandez-Garcia, M.R., Sanchez-Silva, M., 2007., Learning Machines for Structural Damage Detection, in: Lagaros, N., Tsompanakis, Y. (Eds.), Intelligent Computational Paradigms in Earthquake Engineering . Idea Group Publishing. Kirikera, G., Lee, J., Schulz, M., Ghoshal, A., Sundaresan, M., Allemang, R., Shanov, V., Westheider, H., 2006. Initial evaluation of an active/passive structural neural system for health monitoring of composite materials, Smart Mater. Struct., 15. Liu, S., Du, C., Mou, J., Martua, L., Zhang, J., Lewis, F., 2013. Diagnosis of structural cracks using wavelet transform and neural networks, NDT&E International, 54, 9-18. Martin, W., Ghoshal, A., Sundaresan, M., Lebby, G., Pratap, P., Schulz, M., 2005. An Artificial Neural Receptor System for Structural Health Monitoring, Structural Health Monitoring, 4, 229-245. Michaels, J., Dawson, A., Michaels, T., Ruzzene, M., 2014. Approaches to Hybrid SHM and NDE of Composite Aerospace Structures, in: Kundu, T. (Ed.), Health Monitoring of Structural and Biological Systems , Proc. of SPIE, 9064, 906427. 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., 2015. Soft Computing Applied to Defect Detection in Composite Materials, in: T sompanakis, Y., Kruis, J., Topping, B.H.V., (Eds.), Proceedings of the Fourth International Conference on Soft Computing Technology in Civil, Structural and Environmental Engineering , Civil-Comp Press, Stirlingshire, UK, Paper 46, 2015. doi:10.4203/ccp.109.46. Su, Z., Ye, L., 2005. Quantitative Damage Prediction for Composite Laminates Based on Wave Propagation and Artificial Neural Networks, Structural Health Monitoring, 4, 57-66. Taha, M., Noureldin, A., Lucero, J., Baca, T., 2006. Wavelet Transform for Structural Health Monitoring: A Compendium of Uses and Features, Structural Health Monitoring, 5, 267-295. Yu, L., Giurgiutiu, V., 2005. Advanced signal processing for enhanced damage detection with piezoelectric wafer active sensors, Smart Structures and Systems, 1, 185-215. Waszczyszyn, Z., Ziemiański, L., 2001. Neural networks in mechanics of structures and materials - new results and prospects of applications, Computers & Structures, 79, 22-25, 2261-2276.