Scientific and Technical Journal

ELECTROTECHNIC AND COMPUTER SYSTEMS

ISSN Print 2221-3937
ISSN Online 2221-3805
THE NEURAL NETWORK PREDICTING METHOD FOR OBJECT’S CONDITION DIAGNOSING ON THE METALLURGICAL ENTERPRISE
Abstract:

The predicting problem urgency of the lining condition has been substantiated. The choice of neural networks for basic parameters predicting of the diagnostic objects on iron and steel works has been substantiated. An approach for time series analyzing of the diagnostic object parameters on iron and steel works which based on neural network predicting has been proposed. The neural network structure to predict the basic parameters of the moving mixers condition on iron and steel works has been described. The results of the moving mixers condition predicting by the classical methods and neural network have been compared.The neural network method has the best prediction efficiency.The usage of the developed neural network method for detecting points in the time series amounts of iron castings in moving mixers, during which there is a qualitative change in the lining state has been described.

Authors:
Keywords
DOI
10.15276/etks.13.89.2014.10
References

1. Sukov S.G., Belobrov Iu.N., Popov N.N. and Dzerginskii V.A. Modernizatciia i compleksnoe osnashchenie sovremennym oborudovaniem predpriiatii metalurgii [Modernization and Integrated with Modern Equipment in Metallurgy], (2008), Metallurgy: Tendencies of development Publ., Vol. 03, pp. 4 – 7(In Russian).

2. Bigus G. and Daniev Iu. Tehnicheskaia diagnostika opasnyh proizvodstvennyh obektov [Technical Diagnostics of the Dangerous Industrial Objects], (2010), Science Publ., Moscow, Russian Federation, 418 p. (in Russian).

3. Czichos H. Handbook of Technical Diagnostics, (2013), Springer Publ., 566 p.(In English).

4. Gerasimos R. Intelligent Industrial Systems: Modeling, Automation and Adaptive Behavior, (2010),  Industrial  Systems Institute & National Technical University of Athens Publ., Athens, Greece, 601 p. (In English).

5. Korbicz J., and Koscielny J.M. Modeling, Diagnostics and Process Control, (2011), Springer Publ., 400 p.(In English).

6. Afanasiev V.N., and Iuzbashev P.N. Analiz vremennyh riadov s prognozirovanie [Time Series Analysis and Prediction], (2001), Finance and Statistics Publ., Moscow, Russian Federation, 288 p. (In Russian).

7. Nazarov A.V., and Loskutov A.I. Neirosetevye algoritmy prognozirovaniia I optimizacii system [Neural Network Algorithms of the Prediction and Optimization], (2003), Science and Thechnics Publ., St. Petersburg, Russian Federation, 384 p.(In Russian).

8. Chen X., Tang Z., and Varjappan C. (2005), A Modified, Error Back-propagation Algorithm for Complex-value Neural Networks,  International Journal of Neural Systems Publ., Vol. l5(6), pp. 435 – 443 (In English).

9. Costarelli D., and  Spigler R., (2013), Multivariate Neural Network Operators with Sigmoidal Activation Functions, Neural Networks Journal Publ., Vol. 48, pp. 72 – 77 (In English).

10. Haykin S. Neural Networks and Learning Machines, (2008), Prentice Hall Publ., 936 p. (In English).

11. Suzuki K. Artificial Neural Networks: Architectures and Applications, (2013), InTech Publ., Winchester, Hampshire, 256 p. (In English).

Published:
Last download:
2017-11-16 10:40:59

[ © KarelWintersky ] [ All articles ] [ All authors ]
[ © Odessa National Polytechnic University, 2014. Any use of information from the site is possible only under the condition that the source link! ]
Яндекс.Метрика