Volume 4, Issue 1, June 2018, Page: 15-23
An Effective Combination of Pre-Processing Technique and Deep Learning Algorithm for Hammering Sound Inspection
Balage Don Hiroshan Lakmal, Department of Science and Engineering, Graduate School of Science and Technology, Gunma University, Gunma, Japan
Daisuke Oka, Department of Science and Engineering, Graduate School of Science and Technology, Gunma University, Gunma, Japan
Yoichi Shiraishi, Department of Science and Engineering, Graduate School of Science and Technology, Gunma University, Gunma, Japan
Kazuhiro Motegi, Department of Science and Engineering, Graduate School of Science and Technology, Gunma University, Gunma, Japan
Received: Jul. 3, 2018;       Accepted: Aug. 6, 2018;       Published: Sep. 1, 2018
DOI: 10.11648/j.ajnna.20180401.13      View  377      Downloads  31
Abstract
This paper deals with the identification problem of defective products of door strikers installed in automobiles based on their hammering sounds. The difference of the hammering sounds between defective and acceptable products is very small and each sound signal has a unique pattern. The capabilities of conventional human sensory tests are not enough to identify such differences between these two classes. Hence it is suggested to apply deep learning algorithms (DLA) as per the versatility and feature extraction power. Usually, some kinds of pre-processing are adopted before the application of DLA in order to increase the accuracy of inspection as well as to reduce the training and the application time of DLA. In this paper, the combinations of five kinds of pre-processing techniques and three types of DLAs are applied to the actual hammering sounds inspection of door strikers. Especially in two types of DLAs, the sound data have been evaluated as images. The evaluation results show that the combination of the wavelet analysis and the Convolutional Neural Network (CNN) only attained the 100% accuracy of inspection with great response time. The wavelet analysis and the CNN are independently attain the high performances comparing with others and it is likely that they are useful in this kind of hammering sound inspections.
Keywords
Pre-Processing, Deep Learning Algorithms, Non-Destructive Testing, Door Striker, Convolutional Neural Network, Wavelet Analysis
To cite this article
Balage Don Hiroshan Lakmal, Daisuke Oka, Yoichi Shiraishi, Kazuhiro Motegi, An Effective Combination of Pre-Processing Technique and Deep Learning Algorithm for Hammering Sound Inspection, American Journal of Neural Networks and Applications. Vol. 4, No. 1, 2018, pp. 15-23. doi: 10.11648/j.ajnna.20180401.13
Copyright
Copyright © 2018 Authors retain the copyright of this article.
This article is an open access article distributed under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Reference
[1]
Daisuke Oka, Don Hiroshan Lakmal Balage, Kazuhiro Motegi, Yasuhiro Kobayashi, and Yoichi Shiraishi, “A Combination of Support Vector Machine and Heuristics in On-line Non-Destructive Inspection System,” International Conference on Machine Learning and Machine Intellignece (MLMI), Hanoi, Vietnam, September, 2018 (In press).
[2]
Tetsuharu Akiyama, Satoshi Kiyomiya, Yuta Yamashita and Naoyuki Iki, “An Analytical Consideration of Hammering Sound Method as Nondestructive Inspection Method," Proceedings of the Japan Concrete Institute, Vol. 26, No. 1, pp. 1815-1820, 2004.
[3]
Mitsuo Iso, Kazunori Kubota, Kengo Yoshiie, Shin-ichi Hatankenaka, Shigeru Echigo and Yoshihiro Tachibana, “Study on Non-Destructive Testing Method of Steel Plate Concrete Composite Deck by Impact Accoustics,” Kawada Technical Report, Vol. 27, pp. 30-35, 2008.
[4]
Keiichi Itohira, Hiromi Yamamoto, Keiichiro Yamamoto, Yasuhiko Wakibe, Mikio Iwamoto, Kenichi Yoshinaga and Takaki Egashira, " Hammering Inspection of the Soldering Part,” Research Report of Fukuoka Industrial Technology Center, No. 24, pp. 20-21, 2014.
[5]
Atsushi Yamashita, Takahiro Hara and Toru Kaneko, “Hammering Test with Image and Sound Signal Processing,” Transactions of the JSME C, Vol. 72, No. 715, pp. 772-779, 2006.
[6]
Shuji Takahashi, Masaya Miyajima, Atsushi Horiguchi, Kyoji Nakajo, Kazuhiro Motegi and Takashi Suda, “A Non-Destructive Defect Estimation of Metal Pole by using Hammering Sounds based on Machine Learning,” NAIS Journal, Vol. 10, pp. 9-15, September 2016.
[7]
Grader: CANOPUS, NABEL Co., Ltd., Retrieved from https://www.nabel.co.jp/english/product/canopus.html.
[8]
B. Richhariya, M. Tanveer, “EEG signal classification using universum support vector machine,” Expert Systems with Applications, Elsevier Journal, Volume 106, pp. 169-182, 2018.
[9]
Sandeep Kumar Satapathya, Satchidananda Dehurib, Alok Kumar Jagadevc, “EEG signal classification using PSO trained RBF neural network for epilepsy identification,” Elsevier Journal, Informatics in Medicine Unlocked, pp. 1-11, 2017.
[10]
Manjeevan Seera, Chee Peng Lim, Kay Sin Tan, Wei Shiung Liew, “Classification of transcranial Doppler signals using individual and ensemble recurrent neural networks,” Elsevier Journal, Neurocomputing pp. 337–344, 2017.
[11]
Babatunde S. Emmanuel, “Discrete wavelet mathematical transformation method for non-stationary heart sounds signal analysis,” ARPN Journal of Engineering and applied science, vol. 7, pp. 1022-1026, August 2012.
[12]
Paul Bourke, “Cross correlation,” (August 1996), Retrieved from http://paulbourke.net/miscellaneous/correlate/.
[13]
“The discrete fourier transform,” pp82-pp85, Retrieved from http://www.robots.ox.ac.uk/~sjrob/Teaching/SP/l7.pdf.
[14]
Jennifer Seberry, Mieko Yamada, “Hadamard matrices, sequences and block designs, Contemporary design theory – A Collection of Surveys,”D. J. Stinson and J. Dinitz, Eds., John Wiley and Sons, pp. 431-433, 1992.
[15]
R. Rojas, “Neural networks,” Springer-Verlag, Berlin, Chapter 4/Chapter 7, pp. 77-83/, pp. 151-171, 1996.
[16]
Danie Graupe, “Deep learning neural networks- Design and case studies,” World scientific publishing Co. Ltd., Chapter 5, pp. 41-53, 2016.
[17]
Stuart Russell, Peter Norvig, “Artificial intelligence – A modern approach,”3rd ed., Prentice hall series in artificial intelligence, Chapter 19, pp. 563-597, 1995.
[18]
Pierre Baldi, “Autoencoders, Unsupervised Learning, and Deep Architectures,” JMLR: Workshop and conference proceedings, pp. 27-37, 2012.
[19]
Alex K., Ilya S., Geoffrey E., “ImageNet Classification with Deep Convolutional Neural Networks”, Communications of the ACM, Vol. 60, No. 6, pp 84-90, 2017.
[20]
“Backpropagation In Convolutional Neural Networks,” Retrieved from http://www.jefkine.com/general/2016/09/05/backpropagation-in-convolutional-neural-networks/.
Browse journals by subject