Journal of Intelligent Manufacturing

, Volume 29, Issue 8, pp 1923–1940 | Cite as

Automatic microstructural characterization and classification using probabilistic neural network on ultrasound signals

  • Masoud VejdannikEmail author
  • Ali Sadr


During the gas tungsten arc welding of nickel based superalloys, the secondary phases such as Laves and carbides are formed in final stage of solidification. But, other phases such as \(\gamma ^{{\prime \prime }}\) and \(\delta \) phases can precipitate in the microstructure, during aging at high temperatures. However, it is possible to minimize the formation of the Nb-rich Laves phases and therefore reduce the possibility of solidification cracking by adopting the appropriate welding conditions. This paper aims at the automatic microstructurally characterizing the kinetics of phase transformations on an Nb-base alloy, thermally aged at 650 and 950  \(^{\circ }\)C for 10, 100 and 200 h, through backscattered ultrasound signals at frequency of 4 MHz. The ultrasound signals are inherently non-linear and thus the conventional linear time and frequency domain methods can not reveal the complexity of these signals clearly. Consequently, an automated processing system is designed using the higher-order statistics techniques, such as 3rd-order cumulant and bispectrum. These techniques are non-linear methods which are highly robust to noise. For this, the coefficients of 3rd-order cumulant and bispectrum of ultrasound signals are subjected to the independent component analysis (ICA) technique to reduce the statistical redundancy and reveal discriminating features. These dimensionality reduced features are fed to the probabilistic neural network (PNN) to automatic microstructural classification. The training process of PNN depends only on the selection of the smoothing parameters of pattern neurons. In this article, we propose the application of the bees algorithm to the automatic adaptation of smoothing parameters. The ICA components of cumulant coefficients coupled with the optimized PNN yielded the highest average accuracy of 97.0 and 83.5 %, respectively for thermal aging at 650 and 950 \(^{\circ }\)C. Thus, the proposed processing system provides high reliability to be used for microstructure characterization through ultrasound signals.


Bees algorithm Higher-order statistics Independent component analysis Nondestructive inspection Probabilistic neural network Ultrasound signals 



The first author thanks from Victor Hugo C. de Albuquerque and is also grateful for his help for providing the experimental dataset.


  1. Albuquerque, V., Tavares, J., & Cortez, P. (2010). Quantification of the microstructures of hypoeutectic white cast iron using mathematical morphology and an artificial neural network. IJMMP, 5(1), 52.CrossRefGoogle Scholar
  2. Boser, O. (1979). The behavior of inconel 625 in a silver environment. Materials Science and Engineering, 41(1), 59–64.CrossRefGoogle Scholar
  3. Chen, J., Shi, Y., & Shi, S. (1999). Noise analysis of digital ultrasonic nondestructive evaluation system. International Journal of Pressure Vessels and Piping, 76(9), 619–630.CrossRefGoogle Scholar
  4. Chtioui, Y. (1998). Conjugate gradient and approximate Newton methods for an optimal probabilistic neural network for food color classification. Optical Engineering, 37(11), 3015.CrossRefGoogle Scholar
  5. Cieslak, M. (1991). The welding and solidification metallurgy of alloy 625. Welding Journal, 70(2), 49–56.Google Scholar
  6. Cieslak, M., Headley, T., & Romig, A. (1986). The welding metallurgy of HASTELLOY alloys C-4, C-22, and C-276. Metallurgical Transactions A, 17(11), 2035–2047.CrossRefGoogle Scholar
  7. Cox, D. (2006). Principles of statistical inference. Cambridge: Cambridge University Press.CrossRefGoogle Scholar
  8. de Albuquerque, V., de Alexandria, A., Cortez, P., & Tavares, J. (2009). Evaluation of multilayer perceptron and self-organizing map neural network topologies applied on microstructure segmentation from metallographic images. NDT and E International, 42(7), 644–651.CrossRefGoogle Scholar
  9. de Albuquerque, V., Barbosa, C., Silva, C., Moura, E., Filho, P., Papa, J., et al. (2015). Ultrasonic sensor signals and optimum path forest classifier for the microstructural characterization of thermally-aged Inconel 625 alloy. Sensors, 15(6), 12474–12497.CrossRefGoogle Scholar
  10. de Albuquerque, V., Cortez, P., de Alexandria, A., & Tavares, J. (2008). A new solution for automatic microstructures analysis from images based on a backpropagation artificial neural network. Nondestructive Testing and Evaluation, 23(4), 273–283.CrossRefGoogle Scholar
  11. de Albuquerque, V., Filho, P., Cavalcante, T., & Tavares, J. (2010). New computational solution to quantify synthetic material porosity from optical microscopic images. Journal of Microscopy, 240(1), 50–59.CrossRefGoogle Scholar
  12. de Albuquerque, V., de Macedo Silva, E., Leite, J. P., de Moura, E., de Araújo Freitas, V., & Tavares, J. (2010). Spinodal decomposition mechanism study on the duplex stainless steel UNS S31803 using ultrasonic speed measurements. Materials and Design, 31(4), 2147–2150.CrossRefGoogle Scholar
  13. de Albuquerque, V., Melo, T., de Oliveira, D., Gomes, R., & Tavares, J. (2010). Evaluation of grain refiners influence on the mechanical properties in a CuAlBe shape memory alloy by ultrasonic and mechanical tensile testing. Materials and Design, 31(7), 3275–3281.CrossRefGoogle Scholar
  14. de Albuquerque, V., Silva, C., Normando, P., Moura, E., & Tavares, J. (2012). Thermal aging effects on the microstructure of Nb-bearing nickel based superalloy weld overlays using ultrasound techniques. Materials and Design, 36, 337–347.CrossRefGoogle Scholar
  15. de Araújo Freitas, V., Normando, P., de Albuquerque, V., de Macedo Silva, E., Silva, A., & Tavares, J. (2011). Nondestructive characterization and evaluation of embrittlement kinetics and elastic constants of duplex stainless steel SAF 2205 for different aging times at \(425^{\circ }\text{ C }\) and \(475^{\circ }\text{ C }\). Journal of Nondestructive Evaluation, 30(3), 130–136.CrossRefGoogle Scholar
  16. de Macedo Silva, E., de Albuquerque, V., Leite, J., & Varela, A. (2009). Phase transformations evaluation on a UNS S31803 duplex stainless steel based on nondestructive testing. Materials Science and Engineering: A, 516(1–2), 126–130.CrossRefGoogle Scholar
  17. de Moura, E., Normando, P., Gonçalves, L., & Kruger, S. (2011). Characterization of cast iron microstructure through fluctuation and fractal analyses of ultrasonic backscattered signals combined with classification techniques. Journal of Nondestructive Evaluation, 31(1), 90–98.CrossRefGoogle Scholar
  18. Duda, R., Hart, P., & Stork, D. (2001). Pattern classification. New York: Wiley.Google Scholar
  19. Dupont, J., Banovic, S., & Marder, A. (2003). Microstructural evolution and weldability of dissimilar welds between a super austenitic stainless steel and nickel-based alloys. Welding Journal, 82(6), 125–156.Google Scholar
  20. Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874.CrossRefGoogle Scholar
  21. Freedman, D. (2005). Statistical models. Cambridge: Cambridge University Press.Google Scholar
  22. Freitas, V., Albuquerque, V., Silva, E., Silva, A., & Tavares, J. (2010). Nondestructive characterization of microstructures and determination of elastic properties in plain carbon steel using ultrasonic measurements. Materials Science and Engineering: A, 527(16–17), 4431–4437.CrossRefGoogle Scholar
  23. Gorunescu, F., Gorunescu, M., El-Darzi, E., & Gorunescu, S. (2005) An evolutionary computational approach to probabilistic neural network with application to hepatic cancer diagnosis. In IEEE Symposium on Computer-Based Medical Systems (pp. 461–466).Google Scholar
  24. Hyvarinen, A., Karhunen, J., & Oja, E. (2001). Independent component analysis. New York: Wiley.CrossRefGoogle Scholar
  25. Jaynes, E., & Bretthorst, G. (2003). Probability theory. Cambridge: Cambridge University Press.CrossRefGoogle Scholar
  26. Kohl, H., & Peng, K. (1981). Thermal stability of the superalloys Inconel 625 and Nimonic 86. Journal of Nuclear Materials, 101(3), 243–250.CrossRefGoogle Scholar
  27. Liu, X., Ghorpade, A., Tu, Y., & Zhang, W. (2012). A novel approach to probability distribution aggregation. Information Sciences, 188, 269–275.CrossRefGoogle Scholar
  28. Mao, K., Tan, K., & Ser, W. (2000). Probabilistic neural-network structure determination for pattern classification. IEEE Transactions on Neural Networks, 11(4), 1009–1016.CrossRefGoogle Scholar
  29. Mendel, J. (1991). Tutorial on higher-order statistics (spectra) in signal processing and system theory: Theoretical results and some applications. Proceedings of the IEEE, 79(3), 278–305.CrossRefGoogle Scholar
  30. Modi, S., Lin, Y., Cheng, L., Yang, G., Liu, L., & Zhang, W. (2011). A socially inspired framework for human state inference using expert opinion integration. IEEE/ASME Transactions on Mechatronics, 16(5), 874–878.CrossRefGoogle Scholar
  31. Nikias, C., & Mendel, J. (1993). Signal processing with higher-order spectra. IEEE Signal Processing Magazine, 10(3), 10–37.CrossRefGoogle Scholar
  32. Normando, P., Moura, E., Souza, J., Tavares, S., & Padovese, L. (2010). Ultrasound, eddy current and magnetic Barkhausen noise as tools for sigma phase detection on a UNS S31803 duplex stainless steel. Materials Science and Engineering: A, 527(12), 2886–2891.CrossRefGoogle Scholar
  33. Nunes, T., de Albuquerque, V., Papa, J., Silva, C., Normando, P., Moura, E., et al. (2013). Automatic microstructural characterization and classification using artificial intelligence techniques on ultrasound signals. Expert Systems with Applications, 40(8), 3096–3105.CrossRefGoogle Scholar
  34. Papa, J., Nakamura, R., de Albuquerque, V., Falcão, A., & Tavares, J. (2013). Computer techniques towards the automatic characterization of graphite particles in metallographic images of industrial materials. Expert Systems with Applications, 40(2), 590–597.CrossRefGoogle Scholar
  35. Pham, D.T., Ghanbarzadeh, A., Koc, E., Otri, S., Rahim, S., & Zaidi M. (2006). The bees algorithm, a novel tool for complex optimisation problems. In Proceedings IPROMS Conference (pp. 454–456).CrossRefGoogle Scholar
  36. Pham, D. T., Ghanbarzadeh, A., Koc, E., Otri, S., Rahim, S., & Zaidi, M. (2005). The bees algorithm. Technical Note. Manufacturing Engineering Centre, Cardiff University, UK.Google Scholar
  37. Schölkopf, B., & Smola, A. (2002). Learning with kernels. Cambridge, MA: MIT Press.Google Scholar
  38. Shankar, V., Rao, K. Bhanu Sankara, & Mannan, S. (2001). Microstructure and mechanical properties of Inconel 625 superalloy. Journal of Nuclear Materials, 288(2–3), 222–232.CrossRefGoogle Scholar
  39. Specht, D. (1991). A general regression neural network. IEEE Transactions on Neural Networks, 2(6), 568–576.CrossRefGoogle Scholar
  40. Thomas, C., & Tait, P. (1994). The performance of alloy 625 in long-term intermediate temperature applications. International Journal of Pressure Vessels and Piping, 59(1–3), 41–49.CrossRefGoogle Scholar
  41. Vejdannik, M., & Sadr, A. (2016a). Application of linear discriminant analysis to ultrasound signals for automatic microstructural characterization and classification. Journal of Signal Processing Systems, 83(3), 411–421.CrossRefGoogle Scholar
  42. Vejdannik, M., & Sadr, A. (2016b). Automatic microstructural characterization and classification using higher-order spectra on ultrasound signals. Journal of Nondestructive Evaluation, 35(1), 1.Google Scholar
  43. Vejdannik, M., & Sadr, A. (2016c). Automatic microstructural characterization and classification using dual tree complex wavelet-based features and bees algorithm. Neural Computing and Applications. doi: 10.1007/s00521-016-2188-9.CrossRefGoogle Scholar
  44. Vieira, A., de Moura, E., & Gonçalves, L. (2010). Fluctuation analyses for pattern classification in nondestructive materials inspection. EURASIP Journal on Advances in Signal Processing, 2010(1), 262869.CrossRefGoogle Scholar
  45. Vieira, A., de Moura, E., Gonçalves, L., & Rebello, J. (2008). Characterization of welding defects by fractal analysis of ultrasonic signals. Chaos, Solitons and Fractals, 38(3), 748–754.CrossRefGoogle Scholar
  46. Yang, J., Zheng, Q., Sun, X., Guan, H., & Hu, Z. (2006). Formation of \(\mu \) phase during thermal exposure and its effect on the properties of K465 superalloy. Scripta Materialia, 55(4), 331–334.CrossRefGoogle Scholar
  47. Zhong, M., Coggeshall, D., Ghaneie, E., Pope, T., Rivera, M., Georgiopoulos, M., et al. (2007). Gap-based estimation: Choosing the smoothing parameters for probabilistic and general regression neural networks. Neural Computation, 19(10), 2840–2864.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.School of Electrical EngineeringIran University of Science and Technology (IUST)Narmak, TehranIran

Personalised recommendations