Performance Analysis of Ground Source Heat Pump With Artificial Neural Networks Approach

Netice Duman; Ahmet Gürkan Yüksek; Mustafa Caner; Ertan Buyruk

Makale detayları

Performance Analysis of Ground Source Heat Pump With Artificial Neural Networks Approach

Yazarlar:

Netice Duman | Ahmet Gürkan Yüksek | Mustafa Caner | Ertan Buyruk

Yayıncı:

Cukurova University

Ana Başlıklar:

Yapay Zeka (Diğer) | Makine Mühendisliği (Diğer)

Dergi:

Çukurova Üniversitesi Mühendislik Fakültesi Dergisi Vol.39 Issue 1, pp.57-72

Belge Tipi:

Makale

Yayın Tarihi:

3/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001314534

pISSN:

2757-9255

Anahtar kelimeler:

Özet:

 Heat pumps are efficient and accessible alternatives to conventional systems used for cooling and heating in buildings. Ground Source Heat Pumps GSHP, using ground heat as the heat source, are promising technologies to meet heating and cooling loads in a clean and sustainable way. GSHP is a system with high installation and operating costs. For this reason, it is very important that performance analyzes can be made without installing the GSHP system, which is suitable for use in different sectors in terms of efficiency. An artificial neural network ANN model is proposed to predict the performance of the heat pump and system and the heat removed from the condenser, starting from the approach of evaluating the performance values with models from which the systems can be estimated before they are installed. Regression analysis with artificial neural networks is a machine learning method that has the ability to learn complex relationships between input and output data and can effectively model non-linear relationships in problems. The data measured by the established in Sivas province experimental system are separated as training data and test data to train the ANN and in the first stage of the model, the training data; In the second stage, test data was used. In the presented study, the applicability of artificial neural networks, which have been used in various applications to estimate the coefficient of performance of horizontal GSHP, and which have been shown to be especially useful in system modeling and system description, has been demonstrated. As a result of this study, it was determined that the COP R2 value of the heat pump was 0,9733, the COP R2 value of the TKIP system was 0,9896, and the R2 value of the ANN model of the heat removed from the condenser was 0,9878. Based on the statistical determinants produced, it was concluded that ANNs can be used for COP estimation as an accurate method in the GSHP system.

 Heat pumps are efficient and accessible alternatives to conventional systems used for cooling and heating in buildings. Ground Source Heat Pumps GSHP, using ground heat as the heat source, are promising technologies to meet heating and cooling loads in a clean and sustainable way. GSHP is a system with high installation and operating costs. For this reason, it is very important that performance analyzes can be made without installing the GSHP system, which is suitable for use in different sectors in terms of efficiency. An artificial neural network ANN model is proposed to predict the performance of the heat pump and system and the heat removed from the condenser, starting from the approach of evaluating the performance values with models from which the systems can be estimated before they are installed. Regression analysis with artificial neural networks is a machine learning method that has the ability to learn complex relationships between input and output data and can effectively model non-linear relationships in problems. The data measured by the established in Sivas province experimental system are separated as training data and test data to train the ANN and in the first stage of the model, the training data; In the second stage, test data was used. In the presented study, the applicability of artificial neural networks, which have been used in various applications to estimate the coefficient of performance of horizontal GSHP, and which have been shown to be especially useful in system modeling and system description, has been demonstrated. As a result of this study, it was determined that the COP R2 value of the heat pump was 0,9733, the COP R2 value of the TKIP system was 0,9896, and the R2 value of the ANN model of the heat removed from the condenser was 0,9878. Based on the statistical determinants produced, it was concluded that ANNs can be used for COP estimation as an accurate method in the GSHP system.

 Heat pumps are efficient and accessible alternatives to conventional systems used for cooling and heating in buildings. Ground Source Heat Pumps GSHP, using ground heat as the heat source, are promising technologies to meet heating and cooling loads in a clean and sustainable way. GSHP is a system with high installation and operating costs. For this reason, it is very important that performance analyzes can be made without installing the GSHP system, which is suitable for use in different sectors in terms of efficiency. An artificial neural network ANN model is proposed to predict the performance of the heat pump and system and the heat removed from the condenser, starting from the approach of evaluating the performance values with models from which the systems can be estimated before they are installed. Regression analysis with artificial neural networks is a machine learning method that has the ability to learn complex relationships between input and output data and can effectively model non-linear relationships in problems. The data measured by the established in Sivas province experimental system are separated as training data and test data to train the ANN and in the first stage of the model, the training data; In the second stage, test data was used. In the presented study, the applicability of artificial neural networks, which have been used in various applications to estimate the coefficient of performance of horizontal GSHP, and which have been shown to be especially useful in system modeling and system description, has been demonstrated. As a result of this study, it was determined that the COP R2 value of the heat pump was 0,9733, the COP R2 value of the TKIP system was 0,9896, and the R2 value of the ANN model of the heat removed from the condenser was 0,9878. Based on the statistical determinants produced, it was concluded that ANNs can be used for COP estimation as an accurate method in the GSHP system.

 Isı pompaları, binalarda soğutma ve ısıtma için kullanılan konvansiyonel sistemlere verimli ve ulaşılabilir alternatiflerdir. Isı kaynağı olarak toprak ısısını kullanan toprak kaynaklı ısı pompaları TKIP, ısıtma ve soğutma yüklerini temiz ve sürdürülebilir bir şekilde karşılamak için umut verici teknolojilerdir. TKIP, kurulum ve işletme maliyetleri yüksek olan bir sistemdir. Bu nedenle verimlilik açısından farklı sektörlerde kullanımı uygun olan TKIP sistemini kurmadan performans analizleri yapılabilir olması çok önemlidir. Sistemler kurulmadan önce performans değerlerinin tahmin edilebilecek olduğu modeller ile değerlendirilmesi yaklaşımdan yola çıkılarak, ısı pompası ve sistemin performansı ve yoğuşturucudan atılan ısıyı tahmin etmek için bir yapay sinir ağı YSA modeli önerilmektedir. Yapay sinir ağları ile regresyon analizi, girdi ve çıkış verileri arasındaki karmaşık ilişkileri öğrenme yeteneğine sahip bir makine öğrenimi yöntemidir ve problemlerindeki non-lineer ilişkileri etkili bir şekilde modelleyebilir. Sivas ilinde Kurulan deneysel sistem ile ölçülen veriler, YSAyı eğitmek için eğitim verisi ve test verisi olarak ayrılmıştır ve modelin ilk aşamasında eğitim verisi; ikinci aşamasında ise test verisi kullanılmıştır. Sunulan çalışmada, yatay TKIPın performans katsayısını tahmin etmek için çeşitli uygulamalarda kullanılmış ve özellikle sistem modelleme ve sistem tanımlamada yararlı oldukları gösterilmiş yapay sinir ağlarının uygulanabilirliği ortaya konulmuştur. Bu çalışmanın sonucunda, ısı pompası COP R2 değeri 0,9733, TKIP sistemi COP R2 değeri 0,9896 ve yoğuşturucudan atılan ısının YSA modelinin R2 değeri 0,9878 olduğu tespit edilmiştir. Üretilen istatistiksel belirleyiciler üzerinden yola çıkılarak YSAların TKIP sisteminde doğru bir yöntem olarak COP tahmini için kullanılabileceği sonucuna varılmıştır.

Makale detayları

Performance Analysis of Ground Source Heat Pump With Artificial Neural Networks Approach

Yazarlar:

Netice Duman | Ahmet Gürkan Yüksek | Mustafa Caner | Ertan Buyruk

Yayıncı:

Cukurova University

Ana Başlıklar:

Yapay Zeka (Diğer) | Makine Mühendisliği (Diğer)

Dergi:

Çukurova Üniversitesi Mühendislik Fakültesi Dergisi Vol.39 Issue 1, pp.57-72

Belge Tipi:

Makale

Yayın Tarihi:

3/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001314534

pISSN:

2757-9255

Ground source heat pump

Performance analysis

Heating

Artificial neural network

Regression analysisToprak kaynaklı ısı pompası

Performans analizi

Isıtma

Yapay sinir ağları

Regresyon analizi

Sayı

Makale detayları

Yazarlar: Netice Duman | Ahmet Gürkan Yüksek | Mustafa Caner | Ertan Buyruk

Yayıncı: Cukurova University

Ana Başlıklar: Yapay Zeka (Diğer) | Makine Mühendisliği (Diğer)

Dergi: Çukurova Üniversitesi Mühendislik Fakültesi Dergisi Vol.39 Issue 1, pp.57-72

Belge Tipi: Makale

Yayın Tarihi: 3/2024

Belge Dili: Türkçe

Document ID (Org No.): 2001314534

pISSN: 2757-9255

Sayı

Yazarlar:

Netice Duman | Ahmet Gürkan Yüksek | Mustafa Caner | Ertan Buyruk

Yayıncı:

Cukurova University

Ana Başlıklar:

Yapay Zeka (Diğer) | Makine Mühendisliği (Diğer)

Dergi:

Çukurova Üniversitesi Mühendislik Fakültesi Dergisi Vol.39 Issue 1, pp.57-72

Belge Tipi:

Makale

Yayın Tarihi:

3/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001314534

pISSN:

2757-9255