SavedAdd your journal

Journals / Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi / 2026 / Cilt: 7 Sayı: 1

-

AYDINLATMA ELEMANLARINDAKİ IŞIK AKISI AZALMALARININ YAPAY SİNİR AĞLARI İLE TAHMİNİ

Mustafa Şahin
Fuat Büyüktümtürk
Yüksel Oğuz
Paşa Yalçın
Pages
19–36
Publication Date
2014-06-06
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

As a result, in this study, with estimations of brightness levels, the extent to which the artificial neutral Networks become successful was observed and more correct results have been obtained in terms of both economy and usage.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The aim of this study is analyzing different views of the concept of the decreasing of the quantity of illumination elements luminous flux with the title of artificial neural networks along with modeling the measurements which is impossible for manual measuring because it takes long time with measuring device with artificial neural Networks and to predict illumination of unlimited points to artificial neural network with minimum error in a short time and to create a new luminance model results of estimation.
📊
Key Findings & Data:In this way, maintenances of luminance systems which is complex and take lots of time, was aimed to establish in less time more reliable.
💡
Conclusion & Impact:As a result, in this study, with estimations of brightness levels, the extent to which the artificial neutral Networks become successful was observed and more correct results have been obtained in terms of both economy and usage.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Aydınlatma Sistemleri · Yapay Sinir Ağları · Lamba Ömrü

Abstract

The aim of this study is analyzing different views of the concept of the decreasing of the quantity of illumination elements luminous flux with the title of artificial neural networks along with modeling the measurements which is impossible for manual measuring because it takes long time with measuring device with artificial neural Networks and to predict illumination of unlimited points to artificial neural network with minimum error in a short time and to create a new luminance model results of estimation. In this way, maintenances of luminance systems which is complex and take lots of time, was aimed to establish in less time more reliable. Thus, complex and time consuming maintenance of lighting systems has been targeted in less time. Firstly, artificial neural networks (Artificial Neural Networks) and illumination systems were researched from various positions. As a result, in this study, with estimations of brightness levels, the extent to which the artificial neutral Networks become successful was observed and more correct results have been obtained in terms of both economy and usage.

Özet

Bu çalışmada, aydınlatma elemanlarındaki performans düşüşlerini, yıpranmalardan ve kullanımdan kaynaklanan ışık akısı azalmalarının mekân içerisindeki aydınlık düzeyi dağılımına etkisini, yapay sinir ağları (Artificial Neural Networks) kullanılarak farklı açılardan incelenmiştir. Klasik yöntemlerle hesabı mümkün olmayan, ölçme cihazlarıyla uzun zaman alan ölçümleri, kısa sürede yapay sinir ağlarına minimum hata oranı ile tahmin ettirebilmek ve tahminler sonucunda bir değerlendirme modeli oluşturmaktır. Böylelikle aydınlatma sistemlerinin karmaşık ve uzun zaman alan bakımlarının daha az sürede ve daha güvenilir bir şekilde yapılması hedeflenmiştir. Bunun için öncelikle yapay sinir ağları (YSA) ve aydınlatma kavramları çeşitli açılardan incelenmiştir. Sonuç olarak bu bilgiler doğrultusunda seçilen modelin tahmin ettiği değerler ile ölçülen değerler arasındaki hata oranını çıkartılıp iyi bir aydınlatmanın yanında istenilen yerlerin aydınlatılması sağlanmıştır. Bunun neticesinde, ergonomik, ekonomik ve kullanım açısından daha doğru sonuçlara ulaşıldığı gözlemlenmiştir.

🔖

Cite This Article

Şahin, M., Büyüktümtürk, F., Oğuz, Y., Yalçın, P. (2014). -. Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Cilt: 7 Sayı: 1, 19–36. https://doi.org/10.18185/eufbed.38129

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (18)

  1. Cristea, V.M., Hosu A., Sandru, M., Seserman, L., 2011. Antioxidant activity prediction and classification of some teas usin artificial neural networks. Neural networks, Food Chemistry, Vol.127, pp. 1323-1328. Janjai, S.,Plaon, P. 2011. Estimation of sky luminance in the tropics using artificial neural networks: Modeling and performance comparison with the CIE model. Applied Energy, Vol. 88, pp. 840-847, Thailand. Jin, L.V. 2007. Summary of Artificial Neuron Model Research’, Industrial Electronics Society, IECON 2007. 33rd Annual Conference of the IEEE, 5-8 Nov. pp. 677 – 682, Taipei.
  2. Kalogirou S. A. 2000. Long-Term Performance Prediction of Forced Circulation Solar Domestic Water Heating Systems Using Artificial Neural Networks”, Applied Energy, pp 61–75.
  3. Kalogirou S.A. 2000. Artificial Neural Networks in Renewable Energy Systems Applications: A Review. Renewable and Sustainable Energy Reviews, pp 373-401.
  4. Kalogirou, S.A. 1999. Applications of Artificial Neural Networks in Energy Systems a Review. Energy Conversion and Management, Vol. 40, pp. 1073-1087.
  5. Kazanasmaz, T., Günaydın, M., Binol, S. 2009. Artificial neural Networks to predict daylight illuminance in office buildings. Buildingand Environment, vol. 44, Issue 8, pp. 1751-1757.
  6. Kocabey S. 2008. İç Hacimlerde Aydınlık Düzeyi Dağılımının Bulunması Ve Sonlu Elemanlar Yöntemi İle İncelenmesi. Doktora Tezi, Marmara Üniversitesi Fen Bilimleri Enstitüsü, İstanbul.
  7. Li, Y., Ma, W. 2010. Applications of Artificial Neural Networks in Financial Economics: A Survey. Computational Intelligence and Design (ISCID), China.
  8. Lopez, G., Gueymard, C.A. 2007. Clear-sky solar luminous efficacy determination using artificial neural networks. Solar Energy, Vol. 81, pp. 929–939, USA.
  9. Matić, D., Kulić, F., Sanchez, M.P., Llinares, J.P. 2010. Artificial Neural Networks Eccentricity Fault Detection of Induction Motor, Fifth International Multi-conference on Computing in the Global Information Technology, pp.1, Serbia.
  10. Medsker, L.R. 1997. The future of artificial neural Networks could be bright”, Computers/Control engineering, Vol.10, pp. 28-9, Washington, DC, USA.
  11. Onaygil, S. 2007. Aydınlatmanın Temel Prensipleri’, Tedaş Semineri, 23-24 Ocak.
  12. Saoud, S., Khellaf, A., 2011. A neural network based on an inexpensiveeightbit microcontroller, Neural Computing and Applications, Vol.20, pp.329-334, Algeria.
  13. Şahin, M., 2010. Yapay sinir ağları ile dâhili ortamlardaki aydınlık düzeyinin analizi, Marmara Üniversitesi Fen bilimleri Enstitüsü, Yüksek Lisans Tezi, İstanbul.
  14. Şahin M, Büyüktümtürk F, Oğuz Y. 2012. Yapay Sinir Ağları ile Aydınlık Kalitesi Kontrolü, AKU J. Sci. Eng. Pp.1-10.
  15. Villaverde, I., Granna, M. 2011. Neuro-evolutionary mobile robot egomotion estimation with a 3D ToF camera, Neural Computing and Applications, Vol.20, pp. 345-354, Spain.
  16. U.R.L:http://www.psych.utoronto.ca/users/reingold/courses/ai/cache/n euralhtml Erişim: 13.11.2012 ****
  17. Lopez, G., Gueymard, C.A. 2007. Clear-sky solar luminous efficacy determination using artificial neural networks. Solar Energy, Vol. 81, pp. 929–939, USA.
  18. Villaverde, I., Granna, M. 2011. Neuro-evolutionary mobile robot egomotion estimation with a 3D ToF camera, Neural Computing and Applications, Vol.20, pp. 345-354, Spain.