ANN-Based modeling and performance analysis of pyrolytic oil production system

Emirhan Yelekin; İbrahim Mutlu; Murat Alçın; Murat Tuna; İsmail Koyuncu

Makale detayları

ANN-Based modeling and performance analysis of pyrolytic oil production system

Yazarlar:

Emirhan Yelekin | İbrahim Mutlu | Murat Alçın | Murat Tuna | İsmail Koyuncu

Yayıncı:

Pamukkale University

Ana Başlıklar:

Makine Mühendisliği (Diğer)

Dergi:

Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi Vol.31 Issue 5, pp.750-757

Belge Tipi:

Makale

Yayın Tarihi:

10/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001360208

pISSN:

2147-5881

Anahtar kelimeler:

Özet:

 In this study, the modeling of the Pyrolytic oil production system using Artificial Neural Networks ANNs has been conducted with oak acorn, which can be considered as non-wood forest product. The parameters used in the pyrolytic oil production system have been determined as reactor temperature, nitrogen gas flow rate, biomass particle size, and heating rate. In experimental studies, the highest pyrolytic oil production has been achieved at 500 C temperature, 1.5 Lmin nitrogen gas flow rate, 5 Cmin heating rate, and 0-2 mm biomass particle size, with a product yield of 17.83. 164 different Multi-Layer Feed Forward MLFF ANN-based network architectures have been trained for 20,000 iterations using the data obtained from the pyrolytic oil production system. In the training process, various network architectures including activation functions such as TanSig, LogSig, and RadBas with one or two hidden layers have been utilized. According to the results obtained from the studies, the Multi-Layer Feed Forward ANN-based Pyrolytic Oil Production System structure, which has a single hidden layer and contains 16 LogSig activation function neurons, has been the network structure with the best performance with the value of 1.08E-15.

 In this study, the modeling of the Pyrolytic oil production system using Artificial Neural Networks ANNs has been conducted with oak acorn, which can be considered as non-wood forest product. The parameters used in the pyrolytic oil production system have been determined as reactor temperature, nitrogen gas flow rate, biomass particle size, and heating rate. In experimental studies, the highest pyrolytic oil production has been achieved at 500 C temperature, 1.5 Lmin nitrogen gas flow rate, 5 Cmin heating rate, and 0-2 mm biomass particle size, with a product yield of 17.83. 164 different Multi-Layer Feed Forward MLFF ANN-based network architectures have been trained for 20,000 iterations using the data obtained from the pyrolytic oil production system. In the training process, various network architectures including activation functions such as TanSig, LogSig, and RadBas with one or two hidden layers have been utilized. According to the results obtained from the studies, the Multi-Layer Feed Forward ANN-based Pyrolytic Oil Production System structure, which has a single hidden layer and contains 16 LogSig activation function neurons, has been the network structure with the best performance with the value of 1.08E-15.

 In this study, the modeling of the Pyrolytic oil production system using Artificial Neural Networks ANNs has been conducted with oak acorn, which can be considered as non-wood forest product. The parameters used in the pyrolytic oil production system have been determined as reactor temperature, nitrogen gas flow rate, biomass particle size, and heating rate. In experimental studies, the highest pyrolytic oil production has been achieved at 500 C temperature, 1.5 Lmin nitrogen gas flow rate, 5 Cmin heating rate, and 0-2 mm biomass particle size, with a product yield of 17.83. 164 different Multi-Layer Feed Forward MLFF ANN-based network architectures have been trained for 20,000 iterations using the data obtained from the pyrolytic oil production system. In the training process, various network architectures including activation functions such as TanSig, LogSig, and RadBas with one or two hidden layers have been utilized. According to the results obtained from the studies, the Multi-Layer Feed Forward ANN-based Pyrolytic Oil Production System structure, which has a single hidden layer and contains 16 LogSig activation function neurons, has been the network structure with the best performance with the value of 1.08E-15.

 Bu çalışmada, odun dışı orman ürünü olarak değerlendirilebilecek meşe palamudu ile Yapay Sinir Ağları YSA-Artificial Neural Network kullanılarak Pirolitik yağ üretim sisteminin modellenmesi gerçekleştirilmiştir. Pirolitik yağ üretim sisteminde kullanılan parametreler; reaktör sıcaklığı, azot gazı akış hızı, biyokütle parçacık boyutu ve ısıtma hızı olarak belirlenmiştir. Deneysel çalışmalarda, 500 C sıcaklıkta, 1.5 Ldk. azot gazı akış oranı, 5 Cdk. ısıtma oranı ve 0-2 mm biyokütle tanecik boyutunda en yüksek pirolitik yağ üretimi gerçekleştirilmiş olup ürün verimi 17.83 elde edilmiştir. Pirolitik yağ üretim sisteminden elde edilen veriler kullanılarak 164 farklı Çok Katmanlı İleri Beslemeli MLFF ANN-tabanlı ağ mimarisi 20.000 iterasyon için eğitilmiştir. Eğitim sürecinde, bir veya iki gizli katmana sahip TanSig, LogSig ve RadBas transfer fonksiyonları içeren farklı ağ yapıları kullanılmıştır. Çalışmalardan elde edilen sonuçlara göre, tek gizli katmanlı olan ve 16 LogSig aktivasyon fonksiyonlu nöron içeren Çok Katmanlı İleri Beslemeli YSA-tabanlı Pirolitik Yağ Üretim Sistemi yapısı 1.08E-15 değeri ile en iyi performans elde edilen ağ yapısı olmuştur.

Makale detayları

ANN-Based modeling and performance analysis of pyrolytic oil production system

Yazarlar:

Emirhan Yelekin | İbrahim Mutlu | Murat Alçın | Murat Tuna | İsmail Koyuncu

Yayıncı:

Pamukkale University

Ana Başlıklar:

Makine Mühendisliği (Diğer)

Dergi:

Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi Vol.31 Issue 5, pp.750-757

Belge Tipi:

Makale

Yayın Tarihi:

10/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001360208

pISSN:

2147-5881

Acorn

Activation functions

Artificial neural networks

Pyrolytic oil productionMeşe palamudu

Aktivasyon fonksiyonları

Yapay sinir ağları

Pirolitik yağ üretimi

Sayı

Makale detayları

Yazarlar: Emirhan Yelekin | İbrahim Mutlu | Murat Alçın | Murat Tuna | İsmail Koyuncu

Yayıncı: Pamukkale University

Ana Başlıklar: Makine Mühendisliği (Diğer)

Dergi: Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi Vol.31 Issue 5, pp.750-757

Belge Tipi: Makale

Yayın Tarihi: 10/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001360208

pISSN: 2147-5881

Sayı

Yazarlar:

Emirhan Yelekin | İbrahim Mutlu | Murat Alçın | Murat Tuna | İsmail Koyuncu

Yayıncı:

Pamukkale University

Ana Başlıklar:

Makine Mühendisliği (Diğer)

Dergi:

Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi Vol.31 Issue 5, pp.750-757

Belge Tipi:

Makale

Yayın Tarihi:

10/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001360208

pISSN:

2147-5881