INCREMENTAL SYNTHESIS OF GROWING MODULAR NEURAL NETWORK FOR CHP-PLANT SUPPLY WATER TEMPERATURE CONTROLLER
Keywords:
growing modular artificial neural network, genetic algorithm, neurocontroller, supply water temperature controller, CHP-plantAbstract
The paper considers the use of growing modular neural networks for incremental synthesis of the neurocontroller of supply water temperature at CHP-plant. There has been proposed the architecture of the growing modular neural networks on the basis of a three-layer perceptron, allowing the network modules training using genetic algorithm. For test problem it is shown that the training time of growing neural network reduced and its accuracy increased compared to a fixed architecture neural network. The problem of CHP–plant supply water temperature neurocontroller synthesis that provides a reference daily heat output and stable hourly temperature of the return water is successfully solved on the basis of the proposed type of growing network.
References
2. Вороновський Г. К. Підвищення енергоефективності алгоритмів централізованого якісного регулювання відпуску тепла від заміської ТЕЦ / Г. К. Вороновський, К. В. Махотіло, С. А. Сергеєв // Енергоефективність та відновлювані дже-рела енергії / під. заг. ред. А. К. Шидловського. — Київ : Українські енциклопедичні знання. 2007. — С. 163—200.
3. Вороновский Г. К. Проблемы и перспективы использования искусственных нейронных сетей в энергетике: Часть I. Моделирование / Г. К. Вороновский, К. В. Махотило, С. А. Сергеев // Проблеми загальної енергетики. — Київ : Інститут загальної енергетики НАНУ, 2006. — № 14. — С. 50—61.
4. Вороновский Г. К. Проблемы и перспективы использования искусственных нейронных сетей в энергетике : Часть 2. Управление / Г. К. Вороновский, К. В. Махотило, С. А. Сергеев // Проблеми загальної енергетики. — Київ : Інститут загальної енергетики НАНУ, 2007. — № 16. — С. 54—67.
5. Ronco E. Modular neural networks: a state of the art / E. Ronco, Peter J. Gawthrop // Technical Report CSC-95026. Centre for System and Control. Faculty of mechanincal Engineering, University of Glasgow, Uk. — 1995.
6. MacLeod C. Incremental growth in modular neural networks / C. MacLeod, G. M. Maxwell, S. Muthuraman // Engineering Applications of Artificial Intelligence, 2009, — 22 (4/5), — P. 660—666.
7. Carpenter G. A. ART-2: self organisation of stable category recognition codes for analog input patterns / G. A. Carpenter, S. Grossberg // Applied optics, 26, 1987. — P. 4919—4930.
8. Alpaydin E. GAL: Networks that grow when they learn and shrink when they forget / E. Alpaydin // International Journal of Pattern Recognition, 1994. — 8, 1, — P. 391—414.
9 Fahlman S. E. The Cascade-Correlation Learning Architecture / S. E. Fahlman, C. Lebiere // In: Touretzky D., (ed.), Advances in neural information processing systems 2. Morgan Kaufmann Publishers., Los Altos CA. 1990, — P. 524 — 32.
10. Ash T. Dynamic node creation in backpropagation networks / T. Ash // Connection science, 1989, — 1, — P. 365—375.
11. Chakraborty G. A growing network which optimises between undertraining and overtraining / G. Chakraborty // IEEE conference on Neural Networks, 2, 1995. — P. 1116—1120.
12. Miller G. F. Designing neural networks using genetic algorithms / G. F. Miller, P. M. Todd, S. U. Hegde // In Proc. 3rd Int. Conf. Genetic Algorithms and Their Applications. San Mateo. — CA: Morgan Kaufmann, 1989. — P. 379—384.
13. Whitley D. Genetic algorithms and neural networks: Optimizing connections and connectivity / D. Whitley,
T. Starkweather, C. Bogart // Parallel Computing. — 1990. — Vol. 14, No. 3. — P. 347—361.
14. Curran D. Applying evolutionary computation to designing neural networks: A study of the state of the art / D. Curran, C. O’Riordan // Technical report NUIG-IT-111002. Galway : National University of Ireland. — 2002.
15. MacLeod C. Incremental evolution in ANNs: neural nets which grow / C. MacLeod, G. Maxwell // Artificial Intelligence Rev. 16. — 2001. — P. 201—224.
16. Himmelblau D. Applied Nonlinear Programming / D. Himmelblau. — McGraw-Hill, 1972.
17. Махотило К. В. Диплоидный генетический алгоритм со смертностью / К. В. Махотило // Международный научно-технический журнал «Проблемы управления и информатики». — 2011. — № 3. — С. 138—150.
18. Yongyong He. A Hierarchical Evolutionary Algorithm for Constructing and Training Wavelet Networks / Yongyong He, Fulei Chu, Binglin Zhong. // Neural Computing & Application. — Springer-Verlag, 2002. — Vol. 10. — P. 357—366.
19. Махотило К. В. Повышение точности моделирования среднечасовой температуры обратного теплоносителя ТЭЦ / К. В. Махотило // Збірник наукових праць Інституту проблем моделювання в енергетиці ім. Г. Є. Пухова. — НАН України, 2009. — Вип. № 53. — С. 118—128.
Downloads
-
PDF (Українська)
Downloads: 62
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).