Assessment of thermal conductivity of rocks using regression analyses and artificial neural networks

Hilal Özer Aral; Ebru Başpınar Tuncay

Makale detayları

Assessment of thermal conductivity of rocks using regression analyses and artificial neural networks

Yazarlar:

Hilal Özer Aral | Ebru Başpınar Tuncay

Yayıncı:

Pamukkale University

Ana Başlıklar:

Yer Bilimleri ve Jeoloji Mühendisliği (Diğer)

Dergi:

Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi Vol.30 Issue 4, pp.556-563

Belge Tipi:

Makale

Yayın Tarihi:

8/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001325679

pISSN:

2147-5881

Anahtar kelimeler:

Özet:

 This study investigated the thermal conductivity of natural stones  through regression analyses and artificial neural networks . In order to gather a sizable number of datasets for the aforementioned analytic methodologies, a thorough literature review was carried out. Based on different physicomechanical rock characteristics, like dry density , effective porosity , uniaxial compressive strength , and pulse wave velocity , seven estimated models M1-M7 were created for the evaluation of . The regression-based models M1-M5 demonstrated that the considered rock properties influence the  of natural stones at different degrees. Notably, the  and  were found to be highly correlative parameters for estimating the  of natural stones. A number of statistical indicators were used to assess the performance of the developed models. The statistical evaluations indicated that the ANN-based models M6, M7 provided more consistent results than the M1-M5 models. In addition, the mathematical expressions for ANN-based models were also given in the present study to let users carry out them more efficiently. In this case, this study is thought to ensure applicable and comprehensible information on the heat conduction of natural stones and can be described as a research study on how to model the  of natural stones as a factor of various rock characteristics.

 This study investigated the thermal conductivity of natural stones  through regression analyses and artificial neural networks . In order to gather a sizable number of datasets for the aforementioned analytic methodologies, a thorough literature review was carried out. Based on different physicomechanical rock characteristics, like dry density , effective porosity , uniaxial compressive strength , and pulse wave velocity , seven estimated models M1-M7 were created for the evaluation of . The regression-based models M1-M5 demonstrated that the considered rock properties influence the  of natural stones at different degrees. Notably, the  and  were found to be highly correlative parameters for estimating the  of natural stones. A number of statistical indicators were used to assess the performance of the developed models. The statistical evaluations indicated that the ANN-based models M6, M7 provided more consistent results than the M1-M5 models. In addition, the mathematical expressions for ANN-based models were also given in the present study to let users carry out them more efficiently. In this case, this study is thought to ensure applicable and comprehensible information on the heat conduction of natural stones and can be described as a research study on how to model the  of natural stones as a factor of various rock characteristics.

 This study investigated the thermal conductivity of natural stones  through regression analyses and artificial neural networks . In order to gather a sizable number of datasets for the aforementioned analytic methodologies, a thorough literature review was carried out. Based on different physicomechanical rock characteristics, like dry density , effective porosity , uniaxial compressive strength , and pulse wave velocity , seven estimated models M1-M7 were created for the evaluation of . The regression-based models M1-M5 demonstrated that the considered rock properties influence the  of natural stones at different degrees. Notably, the  and  were found to be highly correlative parameters for estimating the  of natural stones. A number of statistical indicators were used to assess the performance of the developed models. The statistical evaluations indicated that the ANN-based models M6, M7 provided more consistent results than the M1-M5 models. In addition, the mathematical expressions for ANN-based models were also given in the present study to let users carry out them more efficiently. In this case, this study is thought to ensure applicable and comprehensible information on the heat conduction of natural stones and can be described as a research study on how to model the  of natural stones as a factor of various rock characteristics.

 Bu çalışma, doğal taşların  termal iletkenliğini regresyon analizleri ve yapay sinir ağları YSA yoluyla araştırmıştır. Bu amaçla, yukarıda belirtilen analiz yöntemleri için çok sayıda veri seti derlemek için kapsamlı bir literatür araştırması yapılmıştır. Kuru yoğunluk ρd, etkin gözeneklilik ne, tek eksenli basınç dayanımı UCS ve darbe dalga hızı Vp, gibi farklı fizikomekanik kaya özelliklerine dayanarak, nin değerlendirilmesi için yedi tahmin modeli M1-M7 kurulmuştur. Regresyona dayalı modeller M1-M5, dikkate alınan kaya özelliklerinin doğal taşların  değerini farklı derecelerde etkilediğini göstermiştir. Özellikle, ne ve Vpnin doğal taşların sini tahmin etmek için yüksek oranda bağıntılı parametreler olduğu bulunmuştur. Kurulan modellerin performansı da çeşitli istatistiksel göstergeler kullanılarak değerlendirilmiştir. İstatistiksel değerlendirmeler, YSA tabanlı modellerin M6, M7, M1-M5 modellerinden daha tutarlı sonuçlar verdiğini göstermiştir. Ayrıca, kullanıcıların bunları daha verimli bir şekilde uygulayabilmeleri için YSA tabanlı modeller için matematiksel ifadeler de bu çalışmada verilmiştir. Böylelikle, bu çalışmanın, doğal taşların ısı iletimi hakkında pratik ve anlaşılır bilgiler sağlayacağı düşünülmektedir ve farklı kaya özelliklerinin bir fonksiyonu olarak doğal taşların sının nasıl modelleneceğine dair bir vaka çalışması olarak tanımlanabilir.

Makale detayları

Assessment of thermal conductivity of rocks using regression analyses and artificial neural networks

Yazarlar:

Hilal Özer Aral | Ebru Başpınar Tuncay

Yayıncı:

Pamukkale University

Ana Başlıklar:

Yer Bilimleri ve Jeoloji Mühendisliği (Diğer)

Dergi:

Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi Vol.30 Issue 4, pp.556-563

Belge Tipi:

Makale

Yayın Tarihi:

8/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001325679

pISSN:

2147-5881

Thermal conductivity

Natural stone

Regression analysis

Artificial neural networksIsı iletkenliği

Doğal taş

regresyon analizi

Yapay sinir ağları

Sayı

Makale detayları

Yazarlar: Hilal Özer Aral | Ebru Başpınar Tuncay

Yayıncı: Pamukkale University

Ana Başlıklar: Yer Bilimleri ve Jeoloji Mühendisliği (Diğer)

Dergi: Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi Vol.30 Issue 4, pp.556-563

Belge Tipi: Makale

Yayın Tarihi: 8/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001325679

pISSN: 2147-5881

Sayı

Yazarlar:

Hilal Özer Aral | Ebru Başpınar Tuncay

Yayıncı:

Pamukkale University

Ana Başlıklar:

Yer Bilimleri ve Jeoloji Mühendisliği (Diğer)

Dergi:

Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi Vol.30 Issue 4, pp.556-563

Belge Tipi:

Makale

Yayın Tarihi:

8/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001325679

pISSN:

2147-5881