Научная электронная библиотека ULRICH'S Periodicals Directory

Сибирский государственный университет
науки и технологий имени академика М.Ф. Решетнева

Сибирский аэрокосмический журнал
ISSN 2712-8970 (Print) ISSN 2782-5760 (on-line)

Сведения об образовательной организации

UDK 519.6 Vestnik SibGAU 2014, No. 3(55), P. 139–145
DYNAMICS FORECASTING FOR ELECTRICAL CHARACTERISTICS OF SPACECRAFT SOLAR ARRAYS BY MEANS OF COMPUTATIONAL INTELLIGENCE
M. E. Semenkina, E. S. Semenkin, I. S. Ryzhikov
Siberian State Aerospace University named after academician M. F. Reshetnev 31, Krasnoyarsky Rabochy Av., Krasnoyarsk, 660014, Russian Federation E-mail: semenkina88@mail.ru, eugenesemenkin@yandex.ru, ryzhikov-88@yandex.ru
We consider the problem of forecasting the degradation process of spacecraft’s solar arrays according to their available parameter changes measured together with the corresponding parameters of solar activity during the fulfilment of the real spacecraft’s mission. The application of ANN-based predictors is proposed because of their generalization ability. In this paper, predictors automated design with self-adaptive evolutionary algorithms is suggested because of the ANN efficiency dependence on the choice of an effective structure and the successful tuning of weight coefficients. The adaptation of evolutionary algorithms is implemented on the base of the algorithms’ self-configuration. In self-configuration technique, setting variants were used instead of the adjusting real parameters, namely types of selection, crossover, population control and level of mutation. Each of these has its own initial probability distribution which is changed as the algorithm executes. ANN-based predictors are automatically designed with the self-configured genetic algorithm and the self-configured genetic programming algorithm. In both cases the most informative features are selected for each neural network. Besides, the self-configuring genetic programming is used for the automated design of ensembles of ANN-based predictors. The performance of developed algorithms for automated design of ANN-based predictors is estimated on real-world data and the most perspective approach is determined. Self-configuring genetic programming algorithm for automated ANN design has the best performance among non-ensemble techniques. Self-configuring genetic programming for the automated design of ensembles presents the best result among all considered approaches.
spacecraft solar array, degradation forecasting, ANN-based predictors, automated design, self-configuring evolutionary algorithms.
References

  1. Zhang G., Patuwo B. E., Hu M. Y. Forecasting with artificial neural networks: The state of the art. International Journal of Forecasting 14. 1998, vol. 14,
    p. 35–62.

  2. Efimov S. N., Semenkin E. S., Tynchenko V. V. [Multi-criteria multi-population genetic algorithm for the structure design and parameters tuning of neural networks based models]. Sistemy upravleniya i informatsionnyye tekhnologii. 2009, vol. 35, no. 1.3, p. 346–350. (In Russ.)
  3. Semenkin E. S., Semenkina M. E. Self-configuring Genetic Algorithm with Modified Uniform Crossover Operator. Advances in Swarm Intelligence, Lecture Notes in Computer Science 7331. 2012, vol. 7331, p. 414–421.
  4. Semenkin E., Semenkina M. Self-Configuring Genetic Programming Algorithm with Modified Uniform Crossover Operator. Proceedings of the IEEE Congress on Evolutionary Computation (IEEE CEC). 2012,
    p. 1918–1923.  
  5. Semenkina M. E. [Effectiveness investigation of self-adaptive evolutionary algorithms for data mining information technology design]. 1.Iskusstvennyy intellekt i prinyatiye resheniy. 2013, no. 1, p. 13–23. (In Russ.)
  6. Gumennikova A. V., Emelyanova M. N., Semenkin E. S., Sopov E. A. [On evolutionary algorithms of complex optimization problems solving]. 1.Vestnik SibGAU. 2003, no. 4, p. 14–23. (In Russ.)
  7. Semenkin E. S., Semenkina M. E. [Application of genetic algorithm with modified uniform recombination operator for automated implementation of intelligent information technologies].Vestnik SibGAU. 2007, no. 3(16), p. 27–33. (In Russ.)
  8. Semenkina M. E., Semenkin E. S. [Investigation of self-configuring genetic programming algorithm behavior]. Trudy pjatoj mezhdunarodnoj konferentsii “Sistemnyj analiz i informatsionnye tekhnologii”. 2013, vol. 2, p. 78–87. (In Russ.)
  9. Semenkin E. S., Semenkina M. E., Panfilov I. A. [Neural Network Ensembles Design with Self-Configuring Genetic Programming Algorithm for Solving Computer Security Problems]. 1.Computational Intelligence in Security for Information Systems, Advances in Intelligent Systems and Computing 1892012, p. 25–32. 
  10. Semenkin E. S., Shabalov A. A., Efimov S. N. [Automated design of intelligent information technology collectives by means of genetic programming techniques]. 1.Vestnik SibGAU. 2011, no. 3 (36), p. 77–81. (In Russ.)
  11. Semenkina M., Semenkin E. [Integration of Intelligent Information Technologies Ensembles with Self-Configuring Genetic Programming Algorithm]. Vestnik SibGAU. 2012, no. 4 (44), p. 89–96. (In Russ.)
  12. Semenkina M., Semenkin E. [Classifier Ensembles Integration with Self-Configuring Genetic Programming Algorithm]. Adaptive and Natural Computing Algorithms, Lecture Notes in Computer Science.2013, vol. 7824, p. 60–69. 

  13. Breiman L. [Bagging predictors]. 1.Machine Learning1996, vol. 24 (2), p. 123–140.

  14. Shabalov A., Semenkin E., Galushin P. [Integration of Intelligent Information Technologies Ensembles for Modeling and Classification]. Proc.1.. of Hybrid artificial intelligent systems 7th International Conference, HAIS 2012.Salamanca, Spain, 2012, p. 365–374.   

  15. Bukhtoyarov V., Semenkin E., Shabalov A. [Neural Networks Ensembles Approach for Simulation of Solar Arrays Degradation Process]. Proc. of Hybrid artificial intelligent systems 7th International Conference, HAIS 2012. Salamanca, Spain, 2012, p. 186–195.

  16. Semenkina M., Semenkin E. [Hybrid Self-configuring Evolutionary Algorithm for Automated Design of Fuzzy Classifier]. Advances in Swarm Intelligence, Lecture Notes in Computer Science. 2014, vol. 8794, part 1, p. 310–317.  

  17. Akhmedova Sh., Semenkin E. [Data Mining Tools Design with Co-operation of Biology Related Algorithms]. Advances in Swarm Intelligence, Lecture Notes in Computer Science. 2014, vol. 8794, part 1, p. 499–506. 

  18. Ryzhikov I., Semenkin E. [The Application of Evolutionary Algorithm for the Linear Dynamic System Modelling]. Proc. of the 2nd International Conference on Simulation and Modelling Methodologies, Technologies and Applications. 2012, p. 234–237.

  19. Ryzhikov I., Semenkin E. [Modified Evolutionary Strategies Algorithm in Linear Dynamic System Identification]. Proc. of the 9th International Conference on Informatics in Control, Automation and Robotics. 2012, p. 618–621. 


Semenkina Maria Evgenyevna – Candidate of Engineering Science, senior teacher of Higher Mathematics Department, Siberian State Aerospace University named after academician M. F. Reshetnev. E-mail: semenkina88@mail.ru 

Semenkin Evgeny Stanislavovich – Doctor of Engineering Science, professor, professor of the Department of System analysis and research of operations, Siberian State Aerospace University named after academician
M. F. Reshetnev. E-mail: eugenesemenkin@yandex.ru

Ryzhikov Ivan Sergeevich – research engineer of Research and Development Department, Siberian State Aerospace University named after academician M. F. Reshetnev. E-mail: ryzhikov-88@yandex.ru