Automatic microstructural characterization and classification using dual tree complex wavelet-based features and Bees Algorithm

Abstract 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 γ″ and δ 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 °C for 10, 100 and 200 h, through backscattered ultrasound signals at frequency of 4 MHz and dual tree complex wavelet transform (DTCWT)-based feature extraction technique. The feature set comprises of statistical attributes (such as variance, skewness and kurtosis) extracted from the complex wavelet coefficients which are obtained using the DTCWT decomposition of a backscattered ultrasound signal. Also, the performance of the proposed feature extraction technique is compared with the conventional discrete wavelet transform. Finally, these features are fed to the probabilistic neural network (PNN) and radial basis function classifiers to automatic microstructural classification. The training process of these networks depends on the selection of the smoothing parameter of the networks’ activation function in a hidden layer. In this article, we introduce the application of the Bees Algorithm to the automatic adaptation of smoothing parameters. The proposed feature extraction technique coupled with the optimized PNN yielded the highest average accuracy of 96 and 83 %, respectively, for thermal aging at 650 and 950 °C. Thus, the proposed processing system provides high reliability to be used for microstructure characterization through ultrasound signals.

[1]  O. Boser,et al.  The behavior of inconel 625 in a silver environment , 1979 .

[2]  Howard B. Demuth,et al.  Neutral network toolbox for use with Matlab , 1995 .

[3]  Manu Thomas,et al.  Automatic ECG arrhythmia classification using dual tree complex wavelet based features , 2015 .

[4]  Rodrigo Nakamura,et al.  Computer techniques towards the automatic characterization of graphite particles in metallographic images of industrial materials , 2013, Expert Syst. Appl..

[5]  Osama S. Faragallah,et al.  Efficient video watermarking based on singular value decomposition in the discrete wavelet transform domain , 2013 .

[6]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[7]  E. Jaynes,et al.  Probability Theory: Other approaches to probability theory , 2003 .

[8]  A. D. Romig,et al.  The welding metallurgy of HASTELLOY alloys C-4, C-22, and C-276 , 1986 .

[9]  João Paulo Papa,et al.  Ultrasonic Sensor Signals and Optimum Path Forest Classifier for the Microstructural Characterization of Thermally-Aged Inconel 625 Alloy , 2015, Sensors.

[10]  João Paulo Papa,et al.  Automatic microstructural characterization and classification using artificial intelligence techniques on ultrasound signals , 2013, Expert Syst. Appl..

[11]  John N. DuPont,et al.  Microstructural evolution and weldability of dissimilar welds between a super austenitic stainless steel and nickel-based alloys , 2003 .

[12]  Mark Rivera,et al.  Gap-Based Estimation: Choosing the Smoothing Parameters for Probabilistic and General Regression Neural Networks , 2006, Neural Computation.

[13]  L. Padovese,et al.  Ultrasound, eddy current and magnetic Barkhausen noise as tools for sigma phase detection on a UNS S31803 duplex stainless steel , 2010 .

[14]  Wee Ser,et al.  Probabilistic neural-network structure determination for pattern classification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[15]  H. K. Kohl,et al.  Thermal stability of the superalloys Inconel 625 and Nimonic 86 , 1981 .

[16]  João Manuel R. S. Tavares,et al.  Spinodal decomposition mechanism study on the duplex stainless steel UNS S31803 using ultrasonic speed measurements , 2010 .

[17]  E. P. Moura,et al.  Characterization of welding defects by fractal analysis of ultrasonic signals , 2006, cond-mat/0612416.

[18]  N. Kingsbury Complex Wavelets for Shift Invariant Analysis and Filtering of Signals , 2001 .

[19]  D. Pham,et al.  THE BEES ALGORITHM, A NOVEL TOOL FOR COMPLEX OPTIMISATION PROBLEMS , 2006 .

[20]  S. Kruger,et al.  Characterization of Cast Iron Microstructure Through Fluctuation and Fractal Analyses of Ultrasonic Backscattered Signals Combined with Classification Techniques , 2012 .

[21]  David G. Stork,et al.  Pattern Classification , 1973 .

[22]  João Manuel R. S. Tavares,et al.  Phase transformations evaluation on a UNS S31803 duplex stainless steel based on nondestructive testing , 2009 .

[23]  T. A. Siewert,et al.  WELDING TECHNOLOGY IN EASTERN EUROPE , 1991 .

[24]  João Manuel R. S. Tavares,et al.  Evaluation of multilayer perceptron and self-organizing map neural network topologies applied on microstructure segmentation from metallographic images , 2009 .

[25]  J. Tavares,et al.  Thermal aging effects on the microstructure of Nb-bearing nickel based superalloy weld overlays using ultrasound techniques , 2012 .

[26]  L. L. Gonçalves,et al.  Fluctuation Analyses for Pattern Classification in Nondestructive Materials Inspection , 2010, EURASIP J. Adv. Signal Process..

[27]  Florin Gorunescu,et al.  An evolutionary computational approach to probabilistic neural network with application to hepatic cancer diagnosis , 2005, 18th IEEE Symposium on Computer-Based Medical Systems (CBMS'05).

[28]  Charles Thomas,et al.  The performance of Alloy 625 in long-term intermediate temperature applications , 1994 .

[29]  João Paulo Papa,et al.  A path- and label-cost propagation approach to speedup the training of the optimum-path forest classifier , 2014, Pattern Recognit. Lett..

[30]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[31]  João Manuel R. S. Tavares,et al.  Nondestructive characterization of microstructures and determination of elastic properties in plain carbon steel using ultrasonic measurements , 2010 .

[32]  S. L. Mannan,et al.  Microstructure and mechanical properties of Inconel 625 superalloy , 2001 .

[33]  Ali Sadr,et al.  Application of Linear Discriminant Analysis to Ultrasound Signals for Automatic Microstructural Characterization and Classification , 2016, J. Signal Process. Syst..

[34]  João Paulo Papa,et al.  Efficient supervised optimum-path forest classification for large datasets , 2012, Pattern Recognit..

[35]  V. H. C. de Albuquerque,et al.  New computational solution to quantify synthetic material porosity from optical microscopic images , 2010, Journal of microscopy.

[36]  M. J. Cieslak,et al.  THE WELDING AND SOLIDIFICATION METALLURGY OF ALLOY 625 , 1991 .

[37]  Victor Hugo C. de Albuquerque,et al.  A new solution for automatic microstructures analysis from images based on a backpropagation artificial neural network , 2008 .

[38]  J. Tavares,et al.  Evaluation of grain refiners influence on the mechanical properties in a CuAlBe shape memory alloy by ultrasonic and mechanical tensile testing , 2010 .

[39]  J. Tavares,et al.  Nondestructive Characterization and Evaluation of Embrittlement Kinetics and Elastic Constants of Duplex Stainless Steel SAF 2205 for Different Aging Times at 425°C and 475°C , 2011 .

[40]  Shu Shi,et al.  Noise analysis of digital ultrasonic nondestructive evaluation system , 1999 .

[41]  Ronald Marsh,et al.  Conjugate gradient and approximate Newton methods for an optimal probabilistic neural network for food color classification , 1998 .

[42]  João Manuel R. S. Tavares,et al.  Quantification of the microstructures of hypoeutectic white cast iron using mathematical morphology and an artificial neural network , 2010 .

[43]  Zushu Hu,et al.  Formation of μ phase during thermal exposure and its effect on the properties of K465 superalloy , 2006 .