Multi-class recognition of objects technical condition by classifier based on probabilistic neural network

Authors

DOI:

https://doi.org/10.15587/1729-4061.2017.109968

Keywords:

multi-class recognition, neural network classifier, diagnostic feature vector, probability of correct classification

Abstract

The paper deals with the efficiency study of the classifier developed based on the probabilistic neural network for multi-class diagnostics of a complex spatial object in the presence of multi-site damage. For recognition, the multidimensional diagnostic feature vector is used, the values of the features may have a deviation of ±5 % for the defect-free condition of an object, and exceed the permissible deviation in case of occurrence and development of damage. For the vector containing 5 diagnostic features, 6 classes of technical condition of an object are substantiated. Formation of sets of training and test input vectors, used for the classifier training and testing is performed. In order to evaluate the multi-class recognition efficiency, the coefficient, which is a percentage of the probability of correct classification of test vectors, is used. The analysis of the dependence of the efficiency coefficient on the characteristics of the classifier and the set of training vectors is carried out. It is found that error-free multi-class recognition of the object condition over the entire set of input vectors with different values of deviation of feature elements is provided in the range of values of the classifier parameter spread of [0,02; 0.07]. It is revealed that the greater the diagnostic feature deviation in test vectors, the greater the influence of the dimension of the set of training vectors on the multi-class recognition efficiency. The minimum size of the set of training vectors (68 vectors) and the limit value of diagnostic feature deviation in test vectors (17 %), which provide error-free multi-class recognition by the developed classifier are determined.

Author Biographies

Nadiia Bouraou, National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute» Peremohy ave., 37, Kyiv, Ukraine, 03056

Doctor of Technical Sciences, Professor, Head of Department

Department of Instrumentation and Orientation and Navigation Systems

Diana Pivtorak, National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute» Peremohy ave., 37, Kyiv, Ukraine, 03056

PhD

Department of Instrumentation and Orientation and Navigation Systems

Sergey Rupich, National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute» Peremohy ave., 37, Kyiv, Ukraine, 03056

Postgraduate Student

Department of Instrumentation and Orientation and Navigation Systems

References

  1. Shanyavskiy, A. A. (2003). Bezopasnoe ustalostnoe razrushenie elementov aviakonstrukciy. Ufa, 802.
  2. Goranson, U. G. (2007). Damage tolerance. Facts and fiction. Keynote Presentation in Int. Conf. on Damage Tolerance of Aircraft Structure. Delft Technical University, 58. Available at: http://dtas2007.fyper.com/userfiles/file/Paper%2011_Goranson.pdf
  3. Ignatovich, S. R., Humaryan, L. A. (2013). Ocenka dostovernosti kontrolya treshchin v aviacionnyh konstrukciyah. Visnyk Ternopilskoho natsionalnoho tekhnichnoho universytetu, 72 (4), 117–124.
  4. Nagarajaiah, S., Erazo, K. (2016). Structural monitoring and identification of civil infrastructure in the United States. Structural Monitoring and Maintenance, 3 (1), 51–69. doi: 10.12989/smm.2016.3.1.051
  5. Bouraou, N. I., Cybul'nik, S. A., Shevchuk, D. V. (2015). Investigation of the model of the vibration measuring channel of the complex monitoring system of steel tanks. Eastern-European Journal of Enterprise Technologies, 5 (9 (77)), 45–52. doi: 10.15587/1729-4061.2015.50980
  6. Ali, Y. H., Abd Rahman, R., Raja Hamzah, R. I. (2014). Acoustic Emission Signal Analysis and Artificial Intelligence Techniques in Machine Condition Monitoring and Fault Diagnosis: A Review. Jurnal Teknologi, 69 (2). doi: 10.11113/jt.v69.3121
  7. Bielza, C., Li, G., Larrañaga, P. (2011). Multi-dimensional classification with Bayesian networks. International Journal of Approximate Reasoning, 52 (6), 705–727. doi: 10.1016/j.ijar.2011.01.007
  8. Bouraou, N. I., Zazhytskyi, O. V. (2014). Rozpiznavannia tekhnichnoho stanu ob‘yektiv na osnovi shtuchnykh neironnykh merezh. Kyiv: NAU, 120.
  9. Hoła, J., Bień, J., Sadowski, Ł., Schabowicz, K. (2015). Non-destructive and semi-destructive diagnostics of concrete structures in assessment of their durability. Bulletin of the Polish Academy of Sciences Technical Sciences, 63 (1). doi: 10.1515/bpasts-2015-0010
  10. Balageas, D., Fritzen, C.-P., Gemes, A. (2006). Structural Health Monitoring. John Wiley & Sons, 495. doi: 10.1002/9780470612071
  11. Dworakowski, Z., Ambrozinski, L., Packo, P., Dragan, K., Stepinski, T., Uhl, T. (2013). Application of Artificial Neural Networks for Damage Indices Classification with the Use of Lamb Waves for the Aerospace Structures. Key Engineering Materials, 588, 12–21. doi: 10.4028/www.scientific.net/kem.588.12
  12. Shen, T., Wan, F., Song, B., Wu, Y. (2011). Damage location and identification of the wing structure with Probabilistic Neural Networks. 2011 Prognostics and System Health Managment Confernece. doi: 10.1109/phm.2011.5939524
  13. Palomino, L. V., Steffen, V., Finzi Neto, R. M. (2014). Probabilistic Neural Network and Fuzzy Cluster Analysis Methods Applied to Impedance-Based SHM for Damage Classification. Shock and Vibration, 2014, 1–12. doi: 10.1155/2014/401942
  14. Bouraou, N. I., Protasov, A. H., Myronenko, P. S., Rupich, S. S. (2015). Syntez neironnoi merezhi dlia bahatoklasovoi diahnostyky elementiv konstruktsiy v ekspluatatsiy. Metody ta prylady kontroliu yakosti, 2 (35), 83–93.

Downloads

Published

2017-10-30

How to Cite

Bouraou, N., Pivtorak, D., & Rupich, S. (2017). Multi-class recognition of objects technical condition by classifier based on probabilistic neural network. Eastern-European Journal of Enterprise Technologies, 5(4 (89), 24–31. https://doi.org/10.15587/1729-4061.2017.109968

Issue

Section

Mathematics and Cybernetics - applied aspects