YAPAY ZEKÂ MODELLERİ İLE BETONARME YAPILARA AİT ENERJİ PERFORMANS SINIFLARININ TAHMİNİ

Yıl 2017, Cilt: 22 Sayı: 3, 325 - 346, 01.12.2017

Ersin Namlı , Melda Yücel

https://doi.org/10.17482/uumfd.332320

Cited By: 6

Öz

Günümüzde giderek önemi artan enerji verimliliği ve etkin enerji
kullanımı, hayatın her alanında ihtiyaç duyulan enerji ve kaynaklarının daha
bilinçli ve verimli kullanılmasını gerektirmiştir. Özellikle inşaat sektörü
enerji verimliliği konusunun en dikkat çeken uygulamalarına sahip alanıdır ve
birçok inşai faaliyette enerji konusunda çeşitli çalışmalar gerçekleştirilmektedir.
Bu açıdan bir sistemin enerjiyi kullanımı ve ne ölçüde etkin/verimli
davrandığının göstergesi sayılabilecek performans, özellikle inşaat sektöründe
önemli bir konuma gelmiştir. Ancak bina enerji performansının hesaplanma
zorluğu, hesaplama işleminin uzmanlık istemesi ve uzun sürmesi enerji
verimliliği ve etkin kullanımı konusunda yaşanacak gelişmeleri
yavaşlatmaktadır. Bu çalışmada binaların enerji performansını belirleyen enerji
sistemlerinin ve mimari özelliklerinin verimlilik seviyesini gösteren enerji sınıflarının
yapay zekâ algoritmaları kullanılarak doğru ve kolayca tahmin edilebilmesi için
bir sistem geliştirilmiştir. Bu amaçla, betonarme yapıda çeşitli niteliklerdeki
127 binanın mimari proje ve enerji kimlik belgeleriyle girdi ve çıktı
nitelikleri belirlenerek özgün bir veri seti oluşturulmuştur. Isıtma sınıfı
modelinde çok katmanlı yapay sinir ağı (YSA), Bayes sınıflandırıcı, k-en yakın
komşu sınıflandırıcısı ve C4.5 algoritması; soğutma sınıfında ise yalnızca YSA
modeli kullanılmıştır. Uygulamalar sonucunda ısıtma sınıfı modelinde 127
veriden 117’sinin doğru sınıflandırılmasıyla en yüksek sınıflandırma doğruluk
değeri %92.126 ile YSA’nda gerçekleşmiştir. Soğutma sınıfındaysa YSA modelinin
uygulanıp gerekli optimizasyonların gerçekleştirilmesiyle %62’ye varan bir oran
elde edilmiştir.

Anahtar Kelimeler

Enerji verimliliği, Bina enerji performansı, Yapay Zekâ, Makine Öğrenme

Energy Performance Classes Prediction of Concrete Buildings with Artificial Intelligence Models

Öz

Today,
increasingly important energy efficiency and effective use of energy
necessitate more conscious and efficient use of the energy and resources are
necessary in every area of ​​life. Especially the construction sector has the
most remarkable applications of energy efficiency and various studies on energy
area are carried out in many construction activities. When considered from this
point of view, in recent years, energy performance which is an indicator of energy
usage of a system and how effective and efficiently it is consumed takes an
important place especially in the construction sector. In addition to
difficulty in calculating of building energy performance, the calculation
process requires expertness and calculation takes long time. In this study, an
artificial intelligence based model developed for predicting energy classes
which represents energy systems' efficiency level. With this aim, Input and
output attributes are determined from architecture projects and energy
performance certificates of 127 buildings' which are reinforced concrete
structures with various qualities, so an original data set generated. In
heating class model, multilayer artificial neural networks (ANN), Bayesian
classifier, k-nearest neighbor classifier and C4.5 algorithm; for cooling
class, only ANN based model was used.In
heating classification prediction model the best classification accuracy value
92.126% were achieved by ANN algorithm, 117 of 127 instances correctly
classified. In cooling classification prediction model, with ANN algorithm and
application of parameter optimizations 62% accuracy rate is obtained.

Anahtar Kelimeler

Energy efficiency, Building energy performance, Artificial intelligence, Machine learning.

Kaynakça

• Aditya, L., Mahliaa, TMI., Rismanchi, B., Ng, HM., Hasan, MH., Metselaar, HSC., Murazaf, O. ve Aditiya, HB. (2017) A review on insulation materials for energy conservation in buildings, Renewable and Sustainable Energy Reviews, 73, 1352-1365. doi: 10.1016/j.rser.2017.02.034.
• Aydoğmuş, H. Y., Erdal, H. İ., Karakurt, O., Namli, E., Türkan, Y. S., & Erdal, H. (2015). A comparative assessment of bagging ensemble models for modeling concrete slump flow. Computers and Concrete, 16(5), 741-757. doi: 10.12989/cac.2015.16.5.741
• Bakar, NNA., Hassan, M.Y., Abdullah, H., Rahman, H.A., Abdullah, M.P. ve Hussin, F., Bandi, M. (2015) Energy efficiency index as an indicator for measuring building energy performance: A review, Renewable and Sustainable Energy Reviews, 44, 1-11. doi: 10.1016/j.rser.2014.12.018
• Chandel, S.S., Sharma, A. ve Marwaha, B.M. (2016) Review of energy efficiency initiatives and regulations for residential buildings in India, Renewable and Sustainable Energy Reviews, 54, 1443-1458. doi: 10.1016/j.rser.2015.10.060
• Chou, J. S., Lin, C. W., Pham, A. D., & Shao, J. Y. (2015). Optimized artificial intelligence models for predicting project award price. Automation in Construction, 54, 106-115. doi: 10.1016/j.autcon.2015.02.006
• Chou, J.S., Tsai, C.F., Pham, A.D. ve Lu, Y.H. (2014) Machine learning in concrete strength simulations: multi-nation data analytics, Construction and Building Materials, 73, 771-780. doi: 10.1016/j.conbuildmat.2014.09.054
• Clarke, J.A., Johnstone, C.M., Kelly, N.J., Strachan, P.A. ve Tuohy, P. (2008) The role of built environment energy efficiency in a sustainable UK energy economy, Energy Policy, 36(12), 4605-4609. doi: 10.1016/j.enpol.2008.09.004
• Durmuş, G. ve Önal, S. (2015) Assessment of energy performance of buildings constructed in different regions of Turkey, 2nd International Sustainable Buildings Symposium, Gazi Üniversitesi, Ankara, Türkiye, 920-924.
• Düzgün, B. ve Kömürgöz, G. (2014) Turkey’s energy efficiency assessment: white certificates systems and their applicability in Turkey, Energy Policy, 65(47), 465-474. doi: 10.1016/j.enpol.2013.10.036
• Elsland, R., Divrak, C., Fleiter, T. ve Wietschel, M. (2014) Turkey’s strategic energy efficiency plan–an ex anten impact assessment of the residential Sector, Energy Policy, 70 (2), 14-29. doi: 10.1016/j.enpol.2014.03.010
• Ercan, T. (2006). Performance Analysis of Desicion Tree Alghorithms on Water-Consumptıon Domain, Yüksek Lisans Tezi, Çankaya Üniversitesi, Türkiye.
• Erdal, H. (2015). Makine Öğrenmesi Yöntemlerinin İnşaat Sektörüne Katkısı: Basınç Dayanımı Tahminlemesi. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 21(3), 109-114. doi: 10.5505/pajes.2014.26121
• Erdal, H.I., Karakurt, O. ve Namli, E. (2013) High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform, Engineering Applications of Artificial Intelligence, 26(4), 1246-1254. doi: 10.1016/j.engappai.2012.10.014
• Fossati, M., Scalco, V.A., Linczuk, V.C.C. ve Lamberts, R. (2016) Building energy efficiency: An overview of the Brazilian residential labeling scheme, Renewable and Sustainable Energy Reviews, 65, 1216-1231. doi: 10.1016/j.rser.2016.06.048
• Frank E., Hall, M.A., Witten, I.H. ve Pal CJ. (2016) Data Mining: Practical Machine Learning Tools and Techniques, 4th ed, Morgan Kaufmann, Cambridge, Massachusetts, USA.
• Gellert, R. (2010) “Inorganic Mineral Materials for Insulation in Buildings”, Materials for Energy Efficiency and Thermal Comfort in Buildings, Editör: Hall, MR., Woodhead Publishing Limited and CRC Press LLC, Cambridge, UK, 193-228.
• Han, J., Kamber, M. (2006) Data Mining: Concepts and Techniques, 2nd ed., Morgan Kaufmann, California, USA.
• Heravi, G. ve Qaemi, M. (2014) Energy performance of buildings: The evaluation of design and construction measures concerning building energy efficiency in Iran, Energy and Buildings, 75, 456-464. doi: 10.1016/j.enbuild.2014.02.035
• Hwang, W.J. ve Wen, K.W. (1998) Fast kNN classification algorithm based on partial distance search, Electronics Letters, 34(21), 2062-2063. doi: 10.1049/el:19981427
• Jha, S.K., Bilalovic, J., Jha, A., Patel, N. ve Zhang, H. (2017) Renewable energy: Present research and future scope of Artificial Intelligence, Renewable and Sustainable Energy Reviews, 77, 297-317. doi: 10.1016/j.rser.2017.04.018
• Kumar, V. ve Wu, X. (2009) The Top Ten Algorithms in Data Mining, Chapman & Hall/CRC Press, Boca Raton, Florida, USA.
• Laustsen, J. (2010) Energy Performance Certification of Building, The IEA Policy Pathway, Paris, Fransa.
• Li, B. ve Yao, R. (2009) Urbanisation and its impact on building energy consumption and efficiency in China, Renewable Energy, 34(9), 1994-1998. doi: 10.1016/j.renene.2009.02.015
• Li, J., Colombier, M. ve Giraud, P.N. (2009) Decision on optimal building energy efficiency standard in China—the case for Tianjin, Energy Policy, 37(7), 2546-2559. doi: 10.1016/j.enpol.2009.01.014
• Luger, G.F. (2009) Artificial Intelligence: Structures and Strategies for Complex Problem Solving, 6th ed., Pearson Education, Boston, USA.
• Mangan, S.D. ve Oral, G.K. (2016) Assessment of residential building performances for the different climate zones of Turkey in terms of life cycle energy and cost efficiency, Energy and Buildings, 110, 362-376. doi: 10.1016/j.enbuild.2015.11.002
• Martínez-Molina, A., Tort-Ausina, I., Cho, S. ve Vivancos, J.L. (2016) Energy efficiency and thermal comfort in historic buildings: A review, Renewable and Sustainable Energy Reviews, 61, 70-85. doi: 10.1016/j.rser.2016.03.018
• Mccarthy, J., (2007). What is Artificial Intelligence?. Erişim adresi: http://www-formal.stanford.edu/jmc/whatisai.html (Erişim Tarihi: 28.01.2017)
• Mitchell, T.M. (1997) “Bayesian Learning”, Machine Learning, Editör: Eric, M., McGraw Hill Education, Boston, Massachusetts, USA, 154-200.
• Namlı, E., Erdal, H.İ. ve Erdal, H. (2016) Dalgacık dönüşümü ile beton basınç dayanım tahmininin iyileştirilmesi, Politeknik Dergisi, 19(4), 471-480. doi: 10.2339/2016.19.4
• Nilsson, NJ. (1998) Introduction To Machine Learning An Early Draft of A Proposed Textbook. Erişim adresi: http://ai.stanford.edu/~nilsson/MLBOOK.pdf (Erişim Tarihi: 30.01.2017)
• Seyhan, A.T., Tayfur, G., Karakurt, M. ve Tanoğlu, M. (2005) Artificial neural network (ANN) prediction of compressive strength of VARTM processed polymer composites, Computational Materials Science, 34(1), 99-105. doi: 10.1016/j.commatsci.2004.11.001
• Rokach, L. ve Maimon, O. Data Mining and Knowledge Discovery Handbook, 2nd ed, Springer, New York, USA.
• Ruggieri, S. (2002) Efficient C4.5 [classification algorithm], IEEE Transactions on Knowledge and Data Engineering, 14(2), 438-444. doi: 10.1109/69.991727
• Russell, S.J. ve Norvig, P. (1995) Artificial Intelligence: A Modern Approach, Prentice-Hall, Egnlewood Cliffs, New Jersey, USA.
• Shaikh, P.H., Nor, N.B.M., Sahito, A.A., Nallagownden, P., Elamvazuthi, I. ve Shaikh, M.S (2017) Building energy for sustainable development in Malaysia: A review, Renewable and Sustainable Energy Reviews, 75, 1392-1403. doi: 10.1016/j.rser.2016.11.128
• T.C. Çevre ve Şehircilik Bakanlığı ve Enerji Verimliliği Daire Başkanlığı Mesleki Hizmetler Genel Müdürlüğü, Binalarda Enerji Performans Yönetmeliği ve Enerji Etkin Bina Tasarım Prensipleri. Erişim adresi: http://www.bep.gov.tr/MERKEZIISITMA/Sunumlar.aspx (Erişim Tarihi: 20.04.2017)
• T.C. Çevre ve Şehircilik Bakanlığı, (2010). Binalarda Enerji Performansı Yönetmeliğinde Değişiklik Dair Yönetmelik. Erişim adresi: http://www.enerjikimlikbelgesi.com/wp-content/uploads/2017/05/Binalarda_ Enerji Performansi Yonetmeligi-28-04-2017.pdf, (Erişim Tarihi: 11.05.2017)
• Wang, Z. ve Srinivasan, R.S. (2017) A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models, Renewable and Sustainable Energy Reviews, 75, 796-808. doi: 10.1016/j.rser.2016.10.079
• Xu, P., Chan, E.H.W. ve Qian, Q.K. (2011) Success factors of energy performance contracting (EPC) for sustainable building energy efficiency retrofit (BEER) of hotel buildings in China, Energy Policy, 39(11), 7389-7398. doi: 10.1016/j.enpol.2011.09.001
• Yıldız, Y. ve Arsan, Z.D. (2011) Identification of the building parameters that influence heating and cooling energy loads for apartment buildings in hot-humid climates, Energy, 36(7), 4287-4296. doi: 10.1016/j.energy.2011.04.013
• Yiğit, K. ve Acarkan, B. (2016) Assessment of energy performance certificate systems: a case study for residential buildings in Turkey, Turkish Journal of Electrical Engineering & Computer Sciences, 24(6), 4839-4848. doi: 10.3906/elk-1407-87