Skip to main content
SpringerLink
Log in

Use of Artificial Neural Networks in Identification of Modulated Pulses Due to Flaws

  • Published:
Russian Journal of Nondestructive Testing Aims and scope Submit manuscript

Abstract

The analysis of a number of publications proved that artificial neural networks show much promise in identification of signals and images in nondestructive testing. A three-layered neural network with backward propagation has been used in separating noisy signals due to flaws from spurious signals (due to a slant or separation of an eddy-current transducer) in the process of eddy-current testing. Network characteristics at different numbers of neurons in its layers have been investigated. Probabilities of signal identification at different rms noise intensities have been determined.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

REFERENCES

  1. Kawada Akira and Hayash Sigeyu, Methods for Diagnostic of Works Using Computer-Simulated Neural Networks, Gien, 1994, no. 80, pp. 16-20.

  2. Roy Amitava, Barat, P., and De Swapan Kumar, Material Classification through Neural Network, Ultrasonics, 1995, no. 33, pp. 175-180.

  3. Wang Suju, Use of Neural Networks in Nondestructive Tests with the Help of Eddy Currents, Narjing HongKong Daxue Huebao (J. Narjing Univ. Aerocom. and Astronaut.), 1995, vol. 27, no. 5, pp. 696-700.

    Google Scholar 

  4. Lei Yinishao and Ma Xinshen, Use of Intelligent Neural Networks in Eddy-Current Tests, Wasan Jinance (Nondestructive Testing), 1994, vol. 16, no. 2, pp. 31-33.

    Google Scholar 

  5. Kreis Thomas, Juptner Werner, and Biedermann Ralf, Neural Network Approach to Holographic Nondestructive Testing, Appl. Optics, 1995, vol. 34, no. 8, pp. 1407-1415.

    Google Scholar 

  6. Koh Chan Scop, Mohammed Osana A., and Hahn Song-yop, Detection of Magnetic Materials Using Artificial Neural Network with Modified Simulated Annealing, IEEE Trans. Magn., 1994, vol. 30, no. 5, pt. 2, pp. 3644-3647.

    Google Scholar 

  7. Wetzlar Dietmar, Neural Networks in Measuring Techniques, Techn. Mess., 1995, vol. 62, no. 3, pp. 87-90.

    Google Scholar 

  8. Cai Yu-dong and Vao Lin-Chang, Utilization of Artificial Neural Network in Calibration of Transducers, Chin. I.: Sci. Instrum., 1994, vol. 15, no. 3, pp. 299-302.

    Google Scholar 

  9. Pham, D.T. and Bayro-Corrochano, E.I., Neural Classifiers for Automated Inspection, Inst. Mech. Eng., 1994, vol. 208, no. 2, pp. 83-89.

    Google Scholar 

  10. Enokizino, M., Todaka, T., Akita, M., and Nagata, S., Rotational Magnetic Flux Sensor with Neural Network for Nondestructuve Testing, IEEE Trans. Magn., 1993, vol. 29, no. 6, pt. 1, pp. 3195-3197.

    Google Scholar 

  11. Notaka Masayoshi, Yabe Yasuhiro, Takadoya Masaki, and Egoshira Niwa, Application of Mathematical Methods and Neural Networks to Nondestructive Testing, Mitsubishi Sogo Kenkyujo shoho (J. Mitsubishi Research Institute), 1995, no. 23, pp. 182-197.

  12. Nogami Takeki, Yokoi Yoshihide, Kasai Masao, Kawai Katsurori, and Takaura Katsuhisa, Failure Diagnostic System for Air-Operated Control Valuese Using Neural Network, ISME Int. I.C., 1995, vol. 38, no. 4, pp. 693-632.

    Google Scholar 

  13. Takumo Masanori, Shinke Noboru, and Motono Hitochi, Evaluation of Function of Spot-Welded Joint Using Ultrasonic Inspection. Nondestructive Evaluation of Tension Shearing Strength with Neural Network, ISME Int. I.A., 1996, vol. 39, no. 4, pp. 626-632.

    Google Scholar 

  14. Donka, C., Ultrasonic Testing of Materials with Neural Network, Strojn. Vestn., 1996, vol. 42, no. 1, pp. 17-26.

    Google Scholar 

  15. Huang Minchao and Chen Qizhi, Control of Transducers Using Fuzzy Sets, Trainable Artificial Neural Networks for Detection and Localization of Flaws in Rocket Engines, Guofang Keji Daxue Xuebao (J. National Univ. Defense Technol.), 1996, vol. 18, no. 4, pp. 7-10.

    Google Scholar 

  16. Oxara, D., High-Accuracy Automatic Inspection System Based on Neural Network, Techno Jap., 1995, vol. 28, no. 2, pp. 100-105.

    Google Scholar 

  17. Shi Keren and He Zhaohui, Use of Artificial Neural Networks for Processing Signals in Eddy-Current Tests, Nondestructive Testing, 1996, vol. 18, no. 7, pp. 100-201.

    Google Scholar 

  18. Takuma Masanori, Shinke Noboru, and Motono Hitoshi, Nondestructive Testing of Welded Joints Using Neural Networks, Nihon Kikai Gakkai Ronbunshu (Trans. Jap. Soc. Mech. Eng.), 1996, vol. 62, no. 595, pp. 776-780.

    Google Scholar 

  19. Liu Weijun, Wang Xiaoming, Wu Hongji, and Liu Jian, Nondestructive Testing of Welded Joints by Ultrasonic Methods Using Neural Networks, Dalian Ligong Daxue Xuebao (J. Dalian Univ. Technol.), 1998, vol. 38, no. 5, pp. 548-552.

    Google Scholar 

  20. Rajeic Vlatka, Neural Network for Wood Member Classification Based on the Results from Nondestructive Testing of Wood Samples, Proc. 4th Int. Conf. Sloven. Soc. Nondestructive Test., Appl. Contemp. Nondestructive Test. Eng., Ljubljana, April 24–25, 1997, pp. 59-66.

  21. Tain Hoisheng, Li Yanning, Cao Xiuyuo, and Li Ye, Testing of Concrete Quality Based on Novel Neural Network with Fuzzy Logic, Xian Jiaotong Daxue Xuebao (J. Xian Jiaotong Univ.), 1997, vol. 31, no. 1, pp. 25-31.

    Google Scholar 

  22. Guo, G. and Yi, W., Identification of Structural Boundary Conditions and Analysis of Flaws Based on the Use of Neural Networks, Nunan Daxue Xuebao. Zuran Kehue Ban (J. Hunan Univ. Natur. Sci.), 1998, vol. 25, no. 1, pp. 71-76.

    Google Scholar 

  23. Tao Chen, Shaomu Han, Shubong Huong, and Dechaug Li, Use of Hybrid Neural Networks in Diagnostic of Turbine Generators, Huashong Ligong Daxue Xuebao (J. Huashing Univ. Sci. and Technol.), 1998, vol. 26, no. 6, pp. 37-39.

    Google Scholar 

  24. Wassermann, F., Neurocomputer Techniques. Theory and Practice. Translated under the title Neirokomp'yuternaya tekhnika. Teoriya i praktika), Moscow: Mir, 1992.

    Google Scholar 

  25. Werbos, P.I., Beyong Regression: New Tools for Prediction and Analysis in the Behavioral Sciences, Masters Thesis, Harward University, 1974.

  26. Parkar, D.B., Learning Logic. Invention Report, S. 81-64, File 1, Office of Technology Licensing, Standford University, Standford, CA, 1982.

    Google Scholar 

  27. Rumelhart, D.E., Hinton, G.E., and Williams, R.I., Learning Internal Representations by Error Propagation, Parallel Distributed Processing, 1986, vol. 1, pp. 318-362, Cambridge MA: MIT Press.

    Google Scholar 

  28. Pribory dlya nerazrushayushchego kontrolya materialov i izdelii (Instruments for Nondestructive Testing of Materials and Works), Klyuev, V.V., Ed., Moscow: Mashinostroenie, 1976.

    Google Scholar 

  29. Beda, P.I., Investigation of Signals from Applied Transducer versus Dimensions and Locations of Crack-Like Flaws, Defektoskopiya, 1970, no. 1, pp. 62-67.

Download references

Author information

Authors and Affiliations

  1. Dnepropetrovsk National University, Dnepropetrovsk, Ukraine

    V. S. Khandetskii & I. N. Antonyuk

Authors
  1. V. S. Khandetskii
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. I. N. Antonyuk
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Khandetskii, V.S., Antonyuk, I.N. Use of Artificial Neural Networks in Identification of Modulated Pulses Due to Flaws. Russian Journal of Nondestructive Testing 37, 278–285 (2001). https://doi.org/10.1023/A:1012359106804

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1012359106804

Keywords

Search

Navigation